diff options
910 files changed, 26255 insertions, 8463 deletions
diff --git a/.editorconfig b/.editorconfig new file mode 100644 index 000000000000..854773350cc5 --- /dev/null +++ b/.editorconfig @@ -0,0 +1,32 @@ +# SPDX-License-Identifier: GPL-2.0-only + +root = true + +[{*.{awk,c,dts,dtsi,dtso,h,mk,s,S},Kconfig,Makefile,Makefile.*}] +charset = utf-8 +end_of_line = lf +trim_trailing_whitespace = true +insert_final_newline = true +indent_style = tab +indent_size = 8 + +[*.{json,py,rs}] +charset = utf-8 +end_of_line = lf +trim_trailing_whitespace = true +insert_final_newline = true +indent_style = space +indent_size = 4 + +# this must be below the general *.py to overwrite it +[tools/{perf,power,rcu,testing/kunit}/**.py,] +indent_style = tab +indent_size = 8 + +[*.yaml] +charset = utf-8 +end_of_line = lf +trim_trailing_whitespace = unset +insert_final_newline = true +indent_style = space +indent_size = 2 diff --git a/.gitignore b/.gitignore index 98274e1160d7..689a4fa3f547 100644 --- a/.gitignore +++ b/.gitignore @@ -96,6 +96,7 @@ modules.order # !.clang-format !.cocciconfig +!.editorconfig !.get_maintainer.ignore !.gitattributes !.gitignore @@ -179,6 +179,7 @@ E: ralf@gnu.org P: 1024/AF7B30C1 CF 97 C2 CC 6D AE A7 FE C8 BA 9C FC 88 DE 32 C3 D: Linux/MIPS port D: Linux/68k hacker +D: AX25 maintainer S: Hauptstrasse 19 S: 79837 St. Blasien S: Germany @@ -677,6 +678,10 @@ D: Media subsystem (V4L/DVB) drivers and core D: EDAC drivers and EDAC 3.0 core rework S: Brazil +N: Landen Chao +E: Landen.Chao@mediatek.com +D: MT7531 Ethernet switch support + N: Raymond Chen E: raymondc@microsoft.com D: Author of Configure script @@ -814,6 +819,10 @@ D: Support for Xircom PGSDB9 (firmware and host driver) S: Bucharest S: Romania +N: John Crispin +E: john@phrozen.org +D: MediaTek MT7623 Gigabit ethernet support + N: Laurence Culhane E: loz@holmes.demon.co.uk D: Wrote the initial alpha SLIP code @@ -1538,6 +1547,10 @@ N: Andrew Haylett E: ajh@primag.co.uk D: Selection mechanism +N: Johan Hedberg +E: johan.hedberg@gmail.com +D: Bluetooth subsystem maintainer + N: Andre Hedrick E: andre@linux-ide.org E: andre@linuxdiskcert.org @@ -3052,6 +3065,10 @@ S: Demonstratsii 8-382 S: Tula 300000 S: Russia +N: Thomas Petazzoni +E: thomas.petazzoni@bootlin.com +D: Driver for the Marvell Armada 370/XP network unit. + N: Gordon Peters E: GordPeters@smarttech.com D: Isochronous receive for IEEE 1394 driver (OHCI module). diff --git a/Documentation/ABI/testing/debugfs-vfio b/Documentation/ABI/testing/debugfs-vfio new file mode 100644 index 000000000000..90f7c262f591 --- /dev/null +++ b/Documentation/ABI/testing/debugfs-vfio @@ -0,0 +1,25 @@ +What: /sys/kernel/debug/vfio +Date: December 2023 +KernelVersion: 6.8 +Contact: Longfang Liu <liulongfang@huawei.com> +Description: This debugfs file directory is used for debugging + of vfio devices, it's a common directory for all vfio devices. + Vfio core will create a device subdirectory under this + directory. + +What: /sys/kernel/debug/vfio/<device>/migration +Date: December 2023 +KernelVersion: 6.8 +Contact: Longfang Liu <liulongfang@huawei.com> +Description: This debugfs file directory is used for debugging + of vfio devices that support live migration. + The debugfs of each vfio device that supports live migration + could be created under this directory. + +What: /sys/kernel/debug/vfio/<device>/migration/state +Date: December 2023 +KernelVersion: 6.8 +Contact: Longfang Liu <liulongfang@huawei.com> +Description: Read the live migration status of the vfio device. + The contents of the state file reflects the migration state + relative to those defined in the vfio_device_mig_state enum diff --git a/Documentation/ABI/testing/sysfs-bus-cxl b/Documentation/ABI/testing/sysfs-bus-cxl index e76c3600607f..fff2581b8033 100644 --- a/Documentation/ABI/testing/sysfs-bus-cxl +++ b/Documentation/ABI/testing/sysfs-bus-cxl @@ -28,6 +28,23 @@ Description: Payload in the CXL-2.0 specification. +What: /sys/bus/cxl/devices/memX/ram/qos_class +Date: May, 2023 +KernelVersion: v6.8 +Contact: linux-cxl@vger.kernel.org +Description: + (RO) For CXL host platforms that support "QoS Telemmetry" + this attribute conveys a comma delimited list of platform + specific cookies that identifies a QoS performance class + for the volatile partition of the CXL mem device. These + class-ids can be compared against a similar "qos_class" + published for a root decoder. While it is not required + that the endpoints map their local memory-class to a + matching platform class, mismatches are not recommended + and there are platform specific performance related + side-effects that may result. First class-id is displayed. + + What: /sys/bus/cxl/devices/memX/pmem/size Date: December, 2020 KernelVersion: v5.12 @@ -38,6 +55,23 @@ Description: Payload in the CXL-2.0 specification. +What: /sys/bus/cxl/devices/memX/pmem/qos_class +Date: May, 2023 +KernelVersion: v6.8 +Contact: linux-cxl@vger.kernel.org +Description: + (RO) For CXL host platforms that support "QoS Telemmetry" + this attribute conveys a comma delimited list of platform + specific cookies that identifies a QoS performance class + for the persistent partition of the CXL mem device. These + class-ids can be compared against a similar "qos_class" + published for a root decoder. While it is not required + that the endpoints map their local memory-class to a + matching platform class, mismatches are not recommended + and there are platform specific performance related + side-effects that may result. First class-id is displayed. + + What: /sys/bus/cxl/devices/memX/serial Date: January, 2022 KernelVersion: v5.18 diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 2e76c3476e2a..31b3a25680d0 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -888,9 +888,9 @@ memory region [offset, offset + size] for that kernel image. If '@offset' is omitted, then a suitable offset is selected automatically. - [KNL, X86-64, ARM64, RISCV] Select a region under 4G first, and - fall back to reserve region above 4G when '@offset' - hasn't been specified. + [KNL, X86-64, ARM64, RISCV, LoongArch] Select a region + under 4G first, and fall back to reserve region above + 4G when '@offset' hasn't been specified. See Documentation/admin-guide/kdump/kdump.rst for further details. crashkernel=range1:size1[,range2:size2,...][@offset] @@ -901,25 +901,27 @@ Documentation/admin-guide/kdump/kdump.rst for an example. crashkernel=size[KMG],high - [KNL, X86-64, ARM64, RISCV] range could be above 4G. + [KNL, X86-64, ARM64, RISCV, LoongArch] range could be + above 4G. Allow kernel to allocate physical memory region from top, so could be above 4G if system have more than 4G ram installed. Otherwise memory region will be allocated below 4G, if available. It will be ignored if crashkernel=X is specified. crashkernel=size[KMG],low - [KNL, X86-64, ARM64, RISCV] range under 4G. When crashkernel=X,high - is passed, kernel could allocate physical memory region - above 4G, that cause second kernel crash on system - that require some amount of low memory, e.g. swiotlb - requires at least 64M+32K low memory, also enough extra - low memory is needed to make sure DMA buffers for 32-bit - devices won't run out. Kernel would try to allocate + [KNL, X86-64, ARM64, RISCV, LoongArch] range under 4G. + When crashkernel=X,high is passed, kernel could allocate + physical memory region above 4G, that cause second kernel + crash on system that require some amount of low memory, + e.g. swiotlb requires at least 64M+32K low memory, also + enough extra low memory is needed to make sure DMA buffers + for 32-bit devices won't run out. Kernel would try to allocate default size of memory below 4G automatically. The default size is platform dependent. --> x86: max(swiotlb_size_or_default() + 8MiB, 256MiB) --> arm64: 128MiB --> riscv: 128MiB + --> loongarch: 128MiB This one lets the user specify own low range under 4G for second kernel instead. 0: to disable low allocation. diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst index bfdf236e2af3..e8c2ce1f9df6 100644 --- a/Documentation/arch/arm64/silicon-errata.rst +++ b/Documentation/arch/arm64/silicon-errata.rst @@ -71,6 +71,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #2658417 | ARM64_ERRATUM_2658417 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A510 | #3117295 | ARM64_ERRATUM_3117295 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A520 | #2966298 | ARM64_ERRATUM_2966298 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A53 | #826319 | ARM64_ERRATUM_826319 | @@ -235,11 +237,9 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Rockchip | RK3588 | #3588001 | ROCKCHIP_ERRATUM_3588001 | +----------------+-----------------+-----------------+-----------------------------+ - +----------------+-----------------+-----------------+-----------------------------+ | Fujitsu | A64FX | E#010001 | FUJITSU_ERRATUM_010001 | +----------------+-----------------+-----------------+-----------------------------+ - +----------------+-----------------+-----------------+-----------------------------+ | ASR | ASR8601 | #8601001 | N/A | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/arch/x86/tdx.rst b/Documentation/arch/x86/tdx.rst index dc8d9fd2c3f7..719043cd8b46 100644 --- a/Documentation/arch/x86/tdx.rst +++ b/Documentation/arch/x86/tdx.rst @@ -10,6 +10,191 @@ encrypting the guest memory. In TDX, a special module running in a special mode sits between the host and the guest and manages the guest/host separation. +TDX Host Kernel Support +======================= + +TDX introduces a new CPU mode called Secure Arbitration Mode (SEAM) and +a new isolated range pointed by the SEAM Ranger Register (SEAMRR). A +CPU-attested software module called 'the TDX module' runs inside the new +isolated range to provide the functionalities to manage and run protected +VMs. + +TDX also leverages Intel Multi-Key Total Memory Encryption (MKTME) to +provide crypto-protection to the VMs. TDX reserves part of MKTME KeyIDs +as TDX private KeyIDs, which are only accessible within the SEAM mode. +BIOS is responsible for partitioning legacy MKTME KeyIDs and TDX KeyIDs. + +Before the TDX module can be used to create and run protected VMs, it +must be loaded into the isolated range and properly initialized. The TDX +architecture doesn't require the BIOS to load the TDX module, but the +kernel assumes it is loaded by the BIOS. + +TDX boot-time detection +----------------------- + +The kernel detects TDX by detecting TDX private KeyIDs during kernel +boot. Below dmesg shows when TDX is enabled by BIOS:: + + [..] virt/tdx: BIOS enabled: private KeyID range: [16, 64) + +TDX module initialization +--------------------------------------- + +The kernel talks to the TDX module via the new SEAMCALL instruction. The +TDX module implements SEAMCALL leaf functions to allow the kernel to +initialize it. + +If the TDX module isn't loaded, the SEAMCALL instruction fails with a +special error. In this case the kernel fails the module initialization +and reports the module isn't loaded:: + + [..] virt/tdx: module not loaded + +Initializing the TDX module consumes roughly ~1/256th system RAM size to +use it as 'metadata' for the TDX memory. It also takes additional CPU +time to initialize those metadata along with the TDX module itself. Both +are not trivial. The kernel initializes the TDX module at runtime on +demand. + +Besides initializing the TDX module, a per-cpu initialization SEAMCALL +must be done on one cpu before any other SEAMCALLs can be made on that +cpu. + +The kernel provides two functions, tdx_enable() and tdx_cpu_enable() to +allow the user of TDX to enable the TDX module and enable TDX on local +cpu respectively. + +Making SEAMCALL requires VMXON has been done on that CPU. Currently only +KVM implements VMXON. For now both tdx_enable() and tdx_cpu_enable() +don't do VMXON internally (not trivial), but depends on the caller to +guarantee that. + +To enable TDX, the caller of TDX should: 1) temporarily disable CPU +hotplug; 2) do VMXON and tdx_enable_cpu() on all online cpus; 3) call +tdx_enable(). For example:: + + cpus_read_lock(); + on_each_cpu(vmxon_and_tdx_cpu_enable()); + ret = tdx_enable(); + cpus_read_unlock(); + if (ret) + goto no_tdx; + // TDX is ready to use + +And the caller of TDX must guarantee the tdx_cpu_enable() has been +successfully done on any cpu before it wants to run any other SEAMCALL. +A typical usage is do both VMXON and tdx_cpu_enable() in CPU hotplug +online callback, and refuse to online if tdx_cpu_enable() fails. + +User can consult dmesg to see whether the TDX module has been initialized. + +If the TDX module is initialized successfully, dmesg shows something +like below:: + + [..] virt/tdx: 262668 KBs allocated for PAMT + [..] virt/tdx: module initialized + +If the TDX module failed to initialize, dmesg also shows it failed to +initialize:: + + [..] virt/tdx: module initialization failed ... + +TDX Interaction to Other Kernel Components +------------------------------------------ + +TDX Memory Policy +~~~~~~~~~~~~~~~~~ + +TDX reports a list of "Convertible Memory Region" (CMR) to tell the +kernel which memory is TDX compatible. The kernel needs to build a list +of memory regions (out of CMRs) as "TDX-usable" memory and pass those +regions to the TDX module. Once this is done, those "TDX-usable" memory +regions are fixed during module's lifetime. + +To keep things simple, currently the kernel simply guarantees all pages +in the page allocator are TDX memory. Specifically, the kernel uses all +system memory in the core-mm "at the time of TDX module initialization" +as TDX memory, and in the meantime, refuses to online any non-TDX-memory +in the memory hotplug. + +Physical Memory Hotplug +~~~~~~~~~~~~~~~~~~~~~~~ + +Note TDX assumes convertible memory is always physically present during +machine's runtime. A non-buggy BIOS should never support hot-removal of +any convertible memory. This implementation doesn't handle ACPI memory +removal but depends on the BIOS to behave correctly. + +CPU Hotplug +~~~~~~~~~~~ + +TDX module requires the per-cpu initialization SEAMCALL must be done on +one cpu before any other SEAMCALLs can be made on that cpu. The kernel +provides tdx_cpu_enable() to let the user of TDX to do it when the user +wants to use a new cpu for TDX task. + +TDX doesn't support physical (ACPI) CPU hotplug. During machine boot, +TDX verifies all boot-time present logical CPUs are TDX compatible before +enabling TDX. A non-buggy BIOS should never support hot-add/removal of +physical CPU. Currently the kernel doesn't handle physical CPU hotplug, +but depends on the BIOS to behave correctly. + +Note TDX works with CPU logical online/offline, thus the kernel still +allows to offline logical CPU and online it again. + +Kexec() +~~~~~~~ + +TDX host support currently lacks the ability to handle kexec. For +simplicity only one of them can be enabled in the Kconfig. This will be +fixed in the future. + +Erratum +~~~~~~~ + +The first few generations of TDX hardware have an erratum. A partial +write to a TDX private memory cacheline will silently "poison" the +line. Subsequent reads will consume the poison and generate a machine +check. + +A partial write is a memory write where a write transaction of less than +cacheline lands at the memory controller. The CPU does these via +non-temporal write instructions (like MOVNTI), or through UC/WC memory +mappings. Devices can also do partial writes via DMA. + +Theoretically, a kernel bug could do partial write to TDX private memory +and trigger unexpected machine check. What's more, the machine check +code will present these as "Hardware error" when they were, in fact, a +software-triggered issue. But in the end, this issue is hard to trigger. + +If the platform has such erratum, the kernel prints additional message in +machine check handler to tell user the machine check may be caused by +kernel bug on TDX private memory. + +Interaction vs S3 and deeper states +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +TDX cannot survive from S3 and deeper states. The hardware resets and +disables TDX completely when platform goes to S3 and deeper. Both TDX +guests and the TDX module get destroyed permanently. + +The kernel uses S3 for suspend-to-ram, and use S4 and deeper states for +hibernation. Currently, for simplicity, the kernel chooses to make TDX +mutually exclusive with S3 and hibernation. + +The kernel disables TDX during early boot when hibernation support is +available:: + + [..] virt/tdx: initialization failed: Hibernation support is enabled + +Add 'nohibernate' kernel command line to disable hibernation in order to +use TDX. + +ACPI S3 is disabled during kernel early boot if TDX is enabled. The user +needs to turn off TDX in the BIOS in order to use S3. + +TDX Guest Support +================= Since the host cannot directly access guest registers or memory, much normal functionality of a hypervisor must be moved into the guest. This is implemented using a Virtualization Exception (#VE) that is handled by the @@ -20,7 +205,7 @@ TDX includes new hypercall-like mechanisms for communicating from the guest to the hypervisor or the TDX module. New TDX Exceptions -================== +------------------ TDX guests behave differently from bare-metal and traditional VMX guests. In TDX guests, otherwise normal instructions or memory accesses can cause @@ -30,7 +215,7 @@ Instructions marked with an '*' conditionally cause exceptions. The details for these instructions are discussed below. Instruction-based #VE ---------------------- +~~~~~~~~~~~~~~~~~~~~~ - Port I/O (INS, OUTS, IN, OUT) - HLT @@ -41,7 +226,7 @@ Instruction-based #VE - CPUID* Instruction-based #GP ---------------------- +~~~~~~~~~~~~~~~~~~~~~ - All VMX instructions: INVEPT, INVVPID, VMCLEAR, VMFUNC, VMLAUNCH, VMPTRLD, VMPTRST, VMREAD, VMRESUME, VMWRITE, VMXOFF, VMXON @@ -52,7 +237,7 @@ Instruction-based #GP - RDMSR*,WRMSR* RDMSR/WRMSR Behavior --------------------- +~~~~~~~~~~~~~~~~~~~~ MSR access behavior falls into three categories: @@ -73,7 +258,7 @@ trapping and handling in the TDX module. Other than possibly being slow, these MSRs appear to function just as they would on bare metal. CPUID Behavior --------------- +~~~~~~~~~~~~~~ For some CPUID leaves and sub-leaves, the virtualized bit fields of CPUID return values (in guest EAX/EBX/ECX/EDX) are configurable by the @@ -93,7 +278,7 @@ not know how to handle. The guest kernel may ask the hypervisor for the value with a hypercall. #VE on Memory Accesses -====================== +---------------------- There are essentially two classes of TDX memory: private and shared. Private memory receives full TDX protections. Its content is protected @@ -107,7 +292,7 @@ entries. This helps ensure that a guest does not place sensitive information in shared memory, exposing it to the untrusted hypervisor. #VE on Shared Memory --------------------- +~~~~~~~~~~~~~~~~~~~~ Access to shared mappings can cause a #VE. The hypervisor ultimately controls whether a shared memory access causes a #VE, so the guest must be @@ -127,7 +312,7 @@ be careful not to access device MMIO regions unless it is also prepared to handle a #VE. #VE on Private Pages --------------------- +~~~~~~~~~~~~~~~~~~~~ An access to private mappings can also cause a #VE. Since all kernel memory is also private memory, the kernel might theoretically need to @@ -145,7 +330,7 @@ The hypervisor is permitted to unilaterally move accepted pages to a to handle the exception. Linux #VE handler -================= +----------------- Just like page faults or #GP's, #VE exceptions can be either handled or be fatal. Typically, an unhandled userspace #VE results in a SIGSEGV. @@ -167,7 +352,7 @@ While the block is in place, any #VE is elevated to a double fault (#DF) which is not recoverable. MMIO handling -============= +------------- In non-TDX VMs, MMIO is usually implemented by giving a guest access to a mapping which will cause a VMEXIT on access, and then the hypervisor @@ -189,7 +374,7 @@ MMIO access via other means (like structure overlays) may result in an oops. Shared Memory Conversions -========================= +------------------------- All TDX guest memory starts out as private at boot. This memory can not be accessed by the hypervisor. However, some kernel users like device diff --git a/Documentation/block/ioprio.rst b/Documentation/block/ioprio.rst index a25c6d5df87b..4662e1ff3d81 100644 --- a/Documentation/block/ioprio.rst +++ b/Documentation/block/ioprio.rst @@ -6,17 +6,16 @@ Block io priorities Intro ----- -With the introduction of cfq v3 (aka cfq-ts or time sliced cfq), basic io -priorities are supported for reads on files. This enables users to io nice -processes or process groups, similar to what has been possible with cpu -scheduling for ages. This document mainly details the current possibilities -with cfq; other io schedulers do not support io priorities thus far. +The io priority feature enables users to io nice processes or process groups, +similar to what has been possible with cpu scheduling for ages. Support for io +priorities is io scheduler dependent and currently supported by bfq and +mq-deadline. Scheduling classes ------------------ -CFQ implements three generic scheduling classes that determine how io is -served for a process. +Three generic scheduling classes are implemented for io priorities that +determine how io is served for a process. IOPRIO_CLASS_RT: This is the realtime io class. This scheduling class is given higher priority than any other in the system, processes from this class are diff --git a/Documentation/dev-tools/checkuapi.rst b/Documentation/dev-tools/checkuapi.rst new file mode 100644 index 000000000000..9072f21b50b0 --- /dev/null +++ b/Documentation/dev-tools/checkuapi.rst @@ -0,0 +1,477 @@ +.. SPDX-License-Identifier: GPL-2.0-only + +============ +UAPI Checker +============ + +The UAPI checker (``scripts/check-uapi.sh``) is a shell script which +checks UAPI header files for userspace backwards-compatibility across +the git tree. + +Options +======= + +This section will describe the options with which ``check-uapi.sh`` +can be run. + +Usage:: + + check-uapi.sh [-b BASE_REF] [-p PAST_REF] [-j N] [-l ERROR_LOG] [-i] [-q] [-v] + +Available options:: + + -b BASE_REF Base git reference to use for comparison. If unspecified or empty, + will use any dirty changes in tree to UAPI files. If there are no + dirty changes, HEAD will be used. + -p PAST_REF Compare BASE_REF to PAST_REF (e.g. -p v6.1). If unspecified or empty, + will use BASE_REF^1. Must be an ancestor of BASE_REF. Only headers + that exist on PAST_REF will be checked for compatibility. + -j JOBS Number of checks to run in parallel (default: number of CPU cores). + -l ERROR_LOG Write error log to file (default: no error log is generated). + -i Ignore ambiguous changes that may or may not break UAPI compatibility. + -q Quiet operation. + -v Verbose operation (print more information about each header being checked). + +Environmental args:: + + ABIDIFF Custom path to abidiff binary + CC C compiler (default is "gcc") + ARCH Target architecture of C compiler (default is host arch) + +Exit codes:: + + 0) Success + 1) ABI difference detected + 2) Prerequisite not met + +Examples +======== + +Basic Usage +----------- + +First, let's try making a change to a UAPI header file that obviously +won't break userspace:: + + cat << 'EOF' | patch -l -p1 + --- a/include/uapi/linux/acct.h + +++ b/include/uapi/linux/acct.h + @@ -21,7 +21,9 @@ + #include <asm/param.h> + #include <asm/byteorder.h> + + -/* + +#define FOO + + + +/* + * comp_t is a 16-bit "floating" point number with a 3-bit base 8 + * exponent and a 13-bit fraction. + * comp2_t is 24-bit with 5-bit base 2 exponent and 20 bit fraction + diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h + EOF + +Now, let's use the script to validate:: + + % ./scripts/check-uapi.sh + Installing user-facing UAPI headers from dirty tree... OK + Installing user-facing UAPI headers from HEAD... OK + Checking changes to UAPI headers between HEAD and dirty tree... + All 912 UAPI headers compatible with x86 appear to be backwards compatible + +Let's add another change that *might* break userspace:: + + cat << 'EOF' | patch -l -p1 + --- a/include/uapi/linux/bpf.h + +++ b/include/uapi/linux/bpf.h + @@ -74,7 +74,7 @@ struct bpf_insn { + __u8 dst_reg:4; /* dest register */ + __u8 src_reg:4; /* source register */ + __s16 off; /* signed offset */ + - __s32 imm; /* signed immediate constant */ + + __u32 imm; /* unsigned immediate constant */ + }; + + /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ + EOF + +The script will catch this:: + + % ./scripts/check-uapi.sh + Installing user-facing UAPI headers from dirty tree... OK + Installing user-facing UAPI headers from HEAD... OK + Checking changes to UAPI headers between HEAD and dirty tree... + ==== ABI differences detected in include/linux/bpf.h from HEAD -> dirty tree ==== + [C] 'struct bpf_insn' changed: + type size hasn't changed + 1 data member change: + type of '__s32 imm' changed: + typedef name changed from __s32 to __u32 at int-ll64.h:27:1 + underlying type 'int' changed: + type name changed from 'int' to 'unsigned int' + type size hasn't changed + ================================================================================== + + error - 1/912 UAPI headers compatible with x86 appear _not_ to be backwards compatible + +In this case, the script is reporting the type change because it could +break a userspace program that passes in a negative number. Now, let's +say you know that no userspace program could possibly be using a negative +value in ``imm``, so changing to an unsigned type there shouldn't hurt +anything. You can pass the ``-i`` flag to the script to ignore changes +in which the userspace backwards compatibility is ambiguous:: + + % ./scripts/check-uapi.sh -i + Installing user-facing UAPI headers from dirty tree... OK + Installing user-facing UAPI headers from HEAD... OK + Checking changes to UAPI headers between HEAD and dirty tree... + All 912 UAPI headers compatible with x86 appear to be backwards compatible + +Now, let's make a similar change that *will* break userspace:: + + cat << 'EOF' | patch -l -p1 + --- a/include/uapi/linux/bpf.h + +++ b/include/uapi/linux/bpf.h + @@ -71,8 +71,8 @@ enum { + + struct bpf_insn { + __u8 code; /* opcode */ + - __u8 dst_reg:4; /* dest register */ + __u8 src_reg:4; /* source register */ + + __u8 dst_reg:4; /* dest register */ + __s16 off; /* signed offset */ + __s32 imm; /* signed immediate constant */ + }; + EOF + +Since we're re-ordering an existing struct member, there's no ambiguity, +and the script will report the breakage even if you pass ``-i``:: + + % ./scripts/check-uapi.sh -i + Installing user-facing UAPI headers from dirty tree... OK + Installing user-facing UAPI headers from HEAD... OK + Checking changes to UAPI headers between HEAD and dirty tree... + ==== ABI differences detected in include/linux/bpf.h from HEAD -> dirty tree ==== + [C] 'struct bpf_insn' changed: + type size hasn't changed + 2 data member changes: + '__u8 dst_reg' offset changed from 8 to 12 (in bits) (by +4 bits) + '__u8 src_reg' offset changed from 12 to 8 (in bits) (by -4 bits) + ================================================================================== + + error - 1/912 UAPI headers compatible with x86 appear _not_ to be backwards compatible + +Let's commit the breaking change, then commit the innocuous change:: + + % git commit -m 'Breaking UAPI change' include/uapi/linux/bpf.h + [detached HEAD f758e574663a] Breaking UAPI change + 1 file changed, 1 insertion(+), 1 deletion(-) + % git commit -m 'Innocuous UAPI change' include/uapi/linux/acct.h + [detached HEAD 2e87df769081] Innocuous UAPI change + 1 file changed, 3 insertions(+), 1 deletion(-) + +Now, let's run the script again with no arguments:: + + % ./scripts/check-uapi.sh + Installing user-facing UAPI headers from HEAD... OK + Installing user-facing UAPI headers from HEAD^1... OK + Checking changes to UAPI headers between HEAD^1 and HEAD... + All 912 UAPI headers compatible with x86 appear to be backwards compatible + +It doesn't catch any breaking change because, by default, it only +compares ``HEAD`` to ``HEAD^1``. The breaking change was committed on +``HEAD~2``. If we wanted the search scope to go back further, we'd have to +use the ``-p`` option to pass a different past reference. In this case, +let's pass ``-p HEAD~2`` to the script so it checks UAPI changes between +``HEAD~2`` and ``HEAD``:: + + % ./scripts/check-uapi.sh -p HEAD~2 + Installing user-facing UAPI headers from HEAD... OK + Installing user-facing UAPI headers from HEAD~2... OK + Checking changes to UAPI headers between HEAD~2 and HEAD... + ==== ABI differences detected in include/linux/bpf.h from HEAD~2 -> HEAD ==== + [C] 'struct bpf_insn' changed: + type size hasn't changed + 2 data member changes: + '__u8 dst_reg' offset changed from 8 to 12 (in bits) (by +4 bits) + '__u8 src_reg' offset changed from 12 to 8 (in bits) (by -4 bits) + ============================================================================== + + error - 1/912 UAPI headers compatible with x86 appear _not_ to be backwards compatible + +Alternatively, we could have also run with ``-b HEAD~``. This would set the +base reference to ``HEAD~`` so then the script would compare it to ``HEAD~^1``. + +Architecture-specific Headers +----------------------------- + +Consider this change:: + + cat << 'EOF' | patch -l -p1 + --- a/arch/arm64/include/uapi/asm/sigcontext.h + +++ b/arch/arm64/include/uapi/asm/sigcontext.h + @@ -70,6 +70,7 @@ struct sigcontext { + struct _aarch64_ctx { + __u32 magic; + __u32 size; + + __u32 new_var; + }; + + #define FPSIMD_MAGIC 0x46508001 + EOF + +This is a change to an arm64-specific UAPI header file. In this example, I'm +running the script from an x86 machine with an x86 compiler, so, by default, +the script only checks x86-compatible UAPI header files:: + + % ./scripts/check-uapi.sh + Installing user-facing UAPI headers from dirty tree... OK + Installing user-facing UAPI headers from HEAD... OK + No changes to UAPI headers were applied between HEAD and dirty tree + +With an x86 compiler, we can't check header files in ``arch/arm64``, so the +script doesn't even try. + +If we want to check the header file, we'll have to use an arm64 compiler and +set ``ARCH`` accordingly:: + + % CC=aarch64-linux-gnu-gcc ARCH=arm64 ./scripts/check-uapi.sh + Installing user-facing UAPI headers from dirty tree... OK + Installing user-facing UAPI headers from HEAD... OK + Checking changes to UAPI headers between HEAD and dirty tree... + ==== ABI differences detected in include/asm/sigcontext.h from HEAD -> dirty tree ==== + [C] 'struct _aarch64_ctx' changed: + type size changed from 64 to 96 (in bits) + 1 data member insertion: + '__u32 new_var', at offset 64 (in bits) at sigcontext.h:73:1 + -- snip -- + [C] 'struct zt_context' changed: + type size changed from 128 to 160 (in bits) + 2 data member changes (1 filtered): + '__u16 nregs' offset changed from 64 to 96 (in bits) (by +32 bits) + '__u16 __reserved[3]' offset changed from 80 to 112 (in bits) (by +32 bits) + ======================================================================================= + + error - 1/884 UAPI headers compatible with arm64 appear _not_ to be backwards compatible + +We can see with ``ARCH`` and ``CC`` set properly for the file, the ABI +change is reported properly. Also notice that the total number of UAPI +header files checked by the script changes. This is because the number +of headers installed for arm64 platforms is different than x86. + +Cross-Dependency Breakages +-------------------------- + +Consider this change:: + + cat << 'EOF' | patch -l -p1 + --- a/include/uapi/linux/types.h + +++ b/include/uapi/linux/types.h + @@ -52,7 +52,7 @@ typedef __u32 __bitwise __wsum; + #define __aligned_be64 __be64 __attribute__((aligned(8))) + #define __aligned_le64 __le64 __attribute__((aligned(8))) + + -typedef unsigned __bitwise __poll_t; + +typedef unsigned short __bitwise __poll_t; + + #endif /* __ASSEMBLY__ */ + #endif /* _UAPI_LINUX_TYPES_H */ + EOF + +Here, we're changing a ``typedef`` in ``types.h``. This doesn't break +a UAPI in ``types.h``, but other UAPIs in the tree may break due to +this change:: + + % ./scripts/check-uapi.sh + Installing user-facing UAPI headers from dirty tree... OK + Installing user-facing UAPI headers from HEAD... OK + Checking changes to UAPI headers between HEAD and dirty tree... + ==== ABI differences detected in include/linux/eventpoll.h from HEAD -> dirty tree ==== + [C] 'struct epoll_event' changed: + type size changed from 96 to 80 (in bits) + 2 data member changes: + type of '__poll_t events' changed: + underlying type 'unsigned int' changed: + type name changed from 'unsigned int' to 'unsigned short int' + type size changed from 32 to 16 (in bits) + '__u64 data' offset changed from 32 to 16 (in bits) (by -16 bits) + ======================================================================================== + include/linux/eventpoll.h did not change between HEAD and dirty tree... + It's possible a change to one of the headers it includes caused this error: + #include <linux/fcntl.h> + #include <linux/types.h> + +Note that the script noticed the failing header file did not change, +so it assumes one of its includes must have caused the breakage. Indeed, +we can see ``linux/types.h`` is used from ``eventpoll.h``. + +UAPI Header Removals +-------------------- + +Consider this change:: + + cat << 'EOF' | patch -l -p1 + diff --git a/include/uapi/asm-generic/Kbuild b/include/uapi/asm-generic/Kbuild + index ebb180aac74e..a9c88b0a8b3b 100644 + --- a/include/uapi/asm-generic/Kbuild + +++ b/include/uapi/asm-generic/Kbuild + @@ -31,6 +31,6 @@ mandatory-y += stat.h + mandatory-y += statfs.h + mandatory-y += swab.h + mandatory-y += termbits.h + -mandatory-y += termios.h + +#mandatory-y += termios.h + mandatory-y += types.h + mandatory-y += unistd.h + EOF + +This script removes a UAPI header file from the install list. Let's run +the script:: + + % ./scripts/check-uapi.sh + Installing user-facing UAPI headers from dirty tree... OK + Installing user-facing UAPI headers from HEAD... OK + Checking changes to UAPI headers between HEAD and dirty tree... + ==== UAPI header include/asm/termios.h was removed between HEAD and dirty tree ==== + + error - 1/912 UAPI headers compatible with x86 appear _not_ to be backwards compatible + +Removing a UAPI header is considered a breaking change, and the script +will flag it as such. + +Checking Historic UAPI Compatibility +------------------------------------ + +You can use the ``-b`` and ``-p`` options to examine different chunks of your +git tree. For example, to check all changed UAPI header files between tags +v6.0 and v6.1, you'd run:: + + % ./scripts/check-uapi.sh -b v6.1 -p v6.0 + Installing user-facing UAPI headers from v6.1... OK + Installing user-facing UAPI headers from v6.0... OK + Checking changes to UAPI headers between v6.0 and v6.1... + + --- snip --- + error - 37/907 UAPI headers compatible with x86 appear _not_ to be backwards compatible + +Note: Before v5.3, a header file needed by the script is not present, +so the script is unable to check changes before then. + +You'll notice that the script detected many UAPI changes that are not +backwards compatible. Knowing that kernel UAPIs are supposed to be stable +forever, this is an alarming result. This brings us to the next section: +caveats. + +Caveats +======= + +The UAPI checker makes no assumptions about the author's intention, so some +types of changes may be flagged even though they intentionally break UAPI. + +Removals For Refactoring or Deprecation +--------------------------------------- + +Sometimes drivers for very old hardware are removed, such as in this example:: + + % ./scripts/check-uapi.sh -b ba47652ba655 + Installing user-facing UAPI headers from ba47652ba655... OK + Installing user-facing UAPI headers from ba47652ba655^1... OK + Checking changes to UAPI headers between ba47652ba655^1 and ba47652ba655... + ==== UAPI header include/linux/meye.h was removed between ba47652ba655^1 and ba47652ba655 ==== + + error - 1/910 UAPI headers compatible with x86 appear _not_ to be backwards compatible + +The script will always flag removals (even if they're intentional). + +Struct Expansions +----------------- + +Depending on how a structure is handled in kernelspace, a change which +expands a struct could be non-breaking. + +If a struct is used as the argument to an ioctl, then the kernel driver +must be able to handle ioctl commands of any size. Beyond that, you need +to be careful when copying data from the user. Say, for example, that +``struct foo`` is changed like this:: + + struct foo { + __u64 a; /* added in version 1 */ + + __u32 b; /* added in version 2 */ + + __u32 c; /* added in version 2 */ + } + +By default, the script will flag this kind of change for further review:: + + [C] 'struct foo' changed: + type size changed from 64 to 128 (in bits) + 2 data member insertions: + '__u32 b', at offset 64 (in bits) + '__u32 c', at offset 96 (in bits) + +However, it is possible that this change was made safely. + +If a userspace program was built with version 1, it will think +``sizeof(struct foo)`` is 8. That size will be encoded in the +ioctl value that gets sent to the kernel. If the kernel is built +with version 2, it will think the ``sizeof(struct foo)`` is 16. + +The kernel can use the ``_IOC_SIZE`` macro to get the size encoded +in the ioctl code that the user passed in and then use +``copy_struct_from_user()`` to safely copy the value:: + + int handle_ioctl(unsigned long cmd, unsigned long arg) + { + switch _IOC_NR(cmd) { + 0x01: { + struct foo my_cmd; /* size 16 in the kernel */ + + ret = copy_struct_from_user(&my_cmd, arg, sizeof(struct foo), _IOC_SIZE(cmd)); + ... + +``copy_struct_from_user`` will zero the struct in the kernel and then copy +only the bytes passed in from the user (leaving new members zeroized). +If the user passed in a larger struct, the extra members are ignored. + +If you know this situation is accounted for in the kernel code, you can +pass ``-i`` to the script, and struct expansions like this will be ignored. + +Flex Array Migration +-------------------- + +While the script handles expansion into an existing flex array, it does +still flag initial migration to flex arrays from 1-element fake flex +arrays. For example:: + + struct foo { + __u32 x; + - __u32 flex[1]; /* fake flex */ + + __u32 flex[]; /* real flex */ + }; + +This change would be flagged by the script:: + + [C] 'struct foo' changed: + type size changed from 64 to 32 (in bits) + 1 data member change: + type of '__u32 flex[1]' changed: + type name changed from '__u32[1]' to '__u32[]' + array type size changed from 32 to 'unknown' + array type subrange 1 changed length from 1 to 'unknown' + +At this time, there's no way to filter these types of changes, so be +aware of this possible false positive. + +Summary +------- + +While many types of false positives are filtered out by the script, +it's possible there are some cases where the script flags a change +which does not break UAPI. It's also possible a change which *does* +break userspace would not be flagged by this script. While the script +has been run on much of the kernel history, there could still be corner +cases that are not accounted for. + +The intention is for this script to be used as a quick check for +maintainers or automated tooling, not as the end-all authority on +patch compatibility. It's best to remember: use your best judgment +(and ideally a unit test in userspace) to make sure your UAPI changes +are backwards-compatible! diff --git a/Documentation/dev-tools/index.rst b/Documentation/dev-tools/index.rst index 3d2286c683bc..efa49cdc8e2e 100644 --- a/Documentation/dev-tools/index.rst +++ b/Documentation/dev-tools/index.rst @@ -31,6 +31,7 @@ Documentation/dev-tools/testing-overview.rst kselftest kunit/index ktap + checkuapi .. only:: subproject and html diff --git a/Documentation/devicetree/bindings/eeprom/at24.yaml b/Documentation/devicetree/bindings/eeprom/at24.yaml index b6864d0ee81e..1812ef31d5f1 100644 --- a/Documentation/devicetree/bindings/eeprom/at24.yaml +++ b/Documentation/devicetree/bindings/eeprom/at24.yaml @@ -123,6 +123,7 @@ properties: - enum: - onnn,cat24c04 - onnn,cat24c05 + - rohm,br24g04 - const: atmel,24c04 - items: - const: renesas,r1ex24016 diff --git a/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml b/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml index c1060e5fcef3..d3d8a2e143ed 100644 --- a/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml +++ b/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml @@ -126,7 +126,7 @@ examples: - | #include <dt-bindings/interrupt-controller/arm-gic.h> - gpio@e000a000 { + gpio@a0020000 { compatible = "xlnx,xps-gpio-1.00.a"; reg = <0xa0020000 0x10000>; #gpio-cells = <2>; diff --git a/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml b/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml index 94b75d9f66cd..1b31b87c1800 100644 --- a/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml @@ -19,6 +19,7 @@ allOf: - st,stm32f7-i2c - st,stm32mp13-i2c - st,stm32mp15-i2c + - st,stm32mp25-i2c then: properties: i2c-scl-rising-time-ns: @@ -41,6 +42,30 @@ allOf: clock-frequency: enum: [100000, 400000] + - if: + properties: + compatible: + contains: + enum: + - st,stm32f4-i2c + - st,stm32f7-i2c + - st,stm32mp13-i2c + - st,stm32mp15-i2c + then: + properties: + interrupts: + minItems: 2 + + interrupt-names: + minItems: 2 + else: + properties: + interrupts: + maxItems: 1 + + interrupt-names: + maxItems: 1 + properties: compatible: enum: @@ -48,6 +73,7 @@ properties: - st,stm32f7-i2c - st,stm32mp13-i2c - st,stm32mp15-i2c + - st,stm32mp25-i2c reg: maxItems: 1 @@ -56,11 +82,13 @@ properties: items: - description: interrupt ID for I2C event - description: interrupt ID for I2C error + minItems: 1 interrupt-names: items: - const: event - const: error + minItems: 1 resets: maxItems: 1 diff --git a/Documentation/devicetree/bindings/input/adafruit,seesaw-gamepad.yaml b/Documentation/devicetree/bindings/input/adafruit,seesaw-gamepad.yaml new file mode 100644 index 000000000000..5e86f6de6978 --- /dev/null +++ b/Documentation/devicetree/bindings/input/adafruit,seesaw-gamepad.yaml @@ -0,0 +1,63 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/input/adafruit,seesaw-gamepad.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Adafruit Mini I2C Gamepad with seesaw + +maintainers: + - Anshul Dalal <anshulusr@gmail.com> + +description: | + Adafruit Mini I2C Gamepad + + +-----------------------------+ + | ___ | + | / \ (X) | + | | S | __ __ (Y) (A) | + | \___/ |ST| |SE| (B) | + | | + +-----------------------------+ + + S -> 10-bit precision bidirectional analog joystick + ST -> Start + SE -> Select + X, A, B, Y -> Digital action buttons + + Datasheet: https://cdn-learn.adafruit.com/downloads/pdf/gamepad-qt.pdf + Product page: https://www.adafruit.com/product/5743 + Arduino Driver: https://github.com/adafruit/Adafruit_Seesaw + +properties: + compatible: + const: adafruit,seesaw-gamepad + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + description: + The gamepad's IRQ pin triggers a rising edge if interrupts are enabled. + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + joystick@50 { + compatible = "adafruit,seesaw-gamepad"; + interrupts = <18 IRQ_TYPE_EDGE_RISING>; + reg = <0x50>; + }; + }; diff --git a/Documentation/devicetree/bindings/input/gpio-keys.yaml b/Documentation/devicetree/bindings/input/gpio-keys.yaml index 159cd9d9fe57..cc78c2152921 100644 --- a/Documentation/devicetree/bindings/input/gpio-keys.yaml +++ b/Documentation/devicetree/bindings/input/gpio-keys.yaml @@ -31,7 +31,23 @@ patternProperties: maxItems: 1 interrupts: - maxItems: 1 + oneOf: + - items: + - description: Optional key interrupt or wakeup interrupt + - items: + - description: Key interrupt + - description: Wakeup interrupt + + interrupt-names: + description: + Optional interrupt names, can be used to specify a separate dedicated + wake-up interrupt in addition to the gpio irq + oneOf: + - items: + - enum: [ irq, wakeup ] + - items: + - const: irq + - const: wakeup label: description: Descriptive name of the key. @@ -97,6 +113,20 @@ patternProperties: - required: - gpios + allOf: + - if: + properties: + interrupts: + minItems: 2 + required: + - interrupts + then: + properties: + interrupt-names: + minItems: 2 + required: + - interrupt-names + dependencies: wakeup-event-action: [ wakeup-source ] linux,input-value: [ gpios ] @@ -137,6 +167,15 @@ examples: linux,code = <108>; interrupts = <1 IRQ_TYPE_EDGE_FALLING>; }; + + key-wakeup { + label = "GPIO Key WAKEUP"; + linux,code = <143>; + interrupts-extended = <&intc 2 IRQ_TYPE_EDGE_FALLING>, + <&intc_wakeup 0 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "irq", "wakeup"; + wakeup-source; + }; }; ... diff --git a/Documentation/devicetree/bindings/input/gpio-mouse.txt b/Documentation/devicetree/bindings/input/gpio-mouse.txt deleted file mode 100644 index 519510a11af9..000000000000 --- a/Documentation/devicetree/bindings/input/gpio-mouse.txt +++ /dev/null @@ -1,32 +0,0 @@ -Device-Tree bindings for GPIO attached mice - -This simply uses standard GPIO handles to define a simple mouse connected -to 5-7 GPIO lines. - -Required properties: - - compatible: must be "gpio-mouse" - - scan-interval-ms: The scanning interval in milliseconds - - up-gpios: GPIO line phandle to the line indicating "up" - - down-gpios: GPIO line phandle to the line indicating "down" - - left-gpios: GPIO line phandle to the line indicating "left" - - right-gpios: GPIO line phandle to the line indicating "right" - -Optional properties: - - button-left-gpios: GPIO line handle to the left mouse button - - button-middle-gpios: GPIO line handle to the middle mouse button - - button-right-gpios: GPIO line handle to the right mouse button -Example: - -#include <dt-bindings/gpio/gpio.h> - -gpio-mouse { - compatible = "gpio-mouse"; - scan-interval-ms = <50>; - up-gpios = <&gpio0 0 GPIO_ACTIVE_LOW>; - down-gpios = <&gpio0 1 GPIO_ACTIVE_LOW>; - left-gpios = <&gpio0 2 GPIO_ACTIVE_LOW>; - right-gpios = <&gpio0 3 GPIO_ACTIVE_LOW>; - button-left-gpios = <&gpio0 4 GPIO_ACTIVE_LOW>; - button-middle-gpios = <&gpio0 5 GPIO_ACTIVE_LOW>; - button-right-gpios = <&gpio0 6 GPIO_ACTIVE_LOW>; -}; diff --git a/Documentation/devicetree/bindings/input/gpio-mouse.yaml b/Documentation/devicetree/bindings/input/gpio-mouse.yaml new file mode 100644 index 000000000000..3928ec6aff1d --- /dev/null +++ b/Documentation/devicetree/bindings/input/gpio-mouse.yaml @@ -0,0 +1,68 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/input/gpio-mouse.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: GPIO attached mouse + +description: | + This simply uses standard GPIO handles to define a simple mouse connected + to 5-7 GPIO lines. + +maintainers: + - Anshul Dalal <anshulusr@gmail.com> + +properties: + compatible: + const: gpio-mouse + + scan-interval-ms: + maxItems: 1 + + up-gpios: + maxItems: 1 + + down-gpios: + maxItems: 1 + + left-gpios: + maxItems: 1 + + right-gpios: + maxItems: 1 + + button-left-gpios: + maxItems: 1 + + button-middle-gpios: + maxItems: 1 + + button-right-gpios: + maxItems: 1 + +required: + - compatible + - scan-interval-ms + - up-gpios + - down-gpios + - left-gpios + - right-gpios + +additionalProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + + gpio-mouse { + compatible = "gpio-mouse"; + scan-interval-ms = <50>; + up-gpios = <&gpio0 0 GPIO_ACTIVE_LOW>; + down-gpios = <&gpio0 1 GPIO_ACTIVE_LOW>; + left-gpios = <&gpio0 2 GPIO_ACTIVE_LOW>; + right-gpios = <&gpio0 3 GPIO_ACTIVE_LOW>; + button-left-gpios = <&gpio0 4 GPIO_ACTIVE_LOW>; + button-middle-gpios = <&gpio0 5 GPIO_ACTIVE_LOW>; + button-right-gpios = <&gpio0 6 GPIO_ACTIVE_LOW>; + }; diff --git a/Documentation/devicetree/bindings/input/iqs269a.yaml b/Documentation/devicetree/bindings/input/iqs269a.yaml index 3c430d38594f..2c3f693b8982 100644 --- a/Documentation/devicetree/bindings/input/iqs269a.yaml +++ b/Documentation/devicetree/bindings/input/iqs269a.yaml @@ -9,6 +9,9 @@ title: Azoteq IQS269A Capacitive Touch Controller maintainers: - Jeff LaBundy <jeff@labundy.com> +allOf: + - $ref: input.yaml# + description: | The Azoteq IQS269A is an 8-channel capacitive touch controller that features additional Hall-effect and inductive sensing capabilities. @@ -17,7 +20,10 @@ description: | properties: compatible: - const: azoteq,iqs269a + enum: + - azoteq,iqs269a + - azoteq,iqs269a-00 + - azoteq,iqs269a-d0 reg: maxItems: 1 @@ -204,6 +210,73 @@ properties: default: 1 description: Specifies the slider coordinate filter strength. + azoteq,touch-hold-ms: + multipleOf: 256 + minimum: 256 + maximum: 65280 + default: 5120 + description: + Specifies the length of time (in ms) for which the channel selected by + 'azoteq,gpio3-select' must be held in a state of touch in order for an + approximately 60-ms pulse to be asserted on the GPIO4 pin. + + linux,keycodes: + minItems: 1 + maxItems: 8 + description: | + Specifies the numeric keycodes associated with each available gesture in + the following order (enter 0 for unused gestures): + 0: Slider 0 tap + 1: Slider 0 hold + 2: Slider 0 positive flick or swipe + 3: Slider 0 negative flick or swipe + 4: Slider 1 tap + 5: Slider 1 hold + 6: Slider 1 positive flick or swipe + 7: Slider 1 negative flick or swipe + + azoteq,gesture-swipe: + type: boolean + description: + Directs the device to interpret axial gestures as a swipe (finger remains + on slider) instead of a flick (finger leaves slider). + + azoteq,timeout-tap-ms: + multipleOf: 16 + minimum: 0 + maximum: 4080 + default: 400 + description: + Specifies the length of time (in ms) within which a slider touch must be + released in order to be interpreted as a tap. Default and maximum values + as well as step size are reduced by a factor of 4 with device version 2. + + azoteq,timeout-swipe-ms: + multipleOf: 16 + minimum: 0 + maximum: 4080 + default: 2000 + description: + Specifies the length of time (in ms) within which an axial gesture must be + completed in order to be interpreted as a flick or swipe. Default and max- + imum values as well as step size are reduced by a factor of 4 with device + version 2. + + azoteq,thresh-swipe: + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 0 + maximum: 255 + default: 128 + description: + Specifies the number of points across which an axial gesture must travel + in order to be interpreted as a flick or swipe. + +dependencies: + azoteq,gesture-swipe: ["linux,keycodes"] + azoteq,timeout-tap-ms: ["linux,keycodes"] + azoteq,timeout-swipe-ms: ["linux,keycodes"] + azoteq,thresh-swipe: ["linux,keycodes"] + patternProperties: "^channel@[0-7]$": type: object @@ -454,6 +527,21 @@ patternProperties: additionalProperties: false +if: + properties: + compatible: + contains: + enum: + - azoteq,iqs269a-d0 +then: + patternProperties: + "^channel@[0-7]$": + properties: + azoteq,slider1-select: false +else: + properties: + azoteq,touch-hold-ms: false + required: - compatible - reg @@ -484,6 +572,14 @@ examples: azoteq,hall-enable; azoteq,suspend-mode = <2>; + linux,keycodes = <KEY_PLAYPAUSE>, + <KEY_STOPCD>, + <KEY_NEXTSONG>, + <KEY_PREVIOUSSONG>; + + azoteq,timeout-tap-ms = <400>; + azoteq,timeout-swipe-ms = <800>; + channel@0 { reg = <0x0>; diff --git a/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml b/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml index e34c9e78d38d..70567d92c746 100644 --- a/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml +++ b/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml @@ -90,26 +90,4 @@ required: unevaluatedProperties: false -examples: - - | - #include <dt-bindings/input/input.h> - #include <dt-bindings/interrupt-controller/arm-gic.h> - - pmic { - compatible = "mediatek,mt6397"; - - keys { - compatible = "mediatek,mt6397-keys"; - mediatek,long-press-mode = <1>; - power-off-time-sec = <0>; - - key-power { - linux,keycodes = <KEY_POWER>; - wakeup-source; - }; - - key-home { - linux,keycodes = <KEY_VOLUMEDOWN>; - }; - }; - }; +... diff --git a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml index 5b5d4f7d3482..7ade03f1b32b 100644 --- a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml +++ b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml @@ -45,13 +45,13 @@ properties: Enables the Linux input system's autorepeat feature on the input device. linux,keycodes: - minItems: 6 - maxItems: 6 + minItems: 3 + maxItems: 8 description: | Specifies an array of numeric keycode values to be used for the channels. If this property is omitted, KEY_A, KEY_B, etc are used as defaults. - The array must have exactly six entries. + The number of entries must correspond to the number of channels. microchip,sensor-gain: $ref: /schemas/types.yaml#/definitions/uint32 @@ -70,6 +70,59 @@ properties: open drain. This property allows using the active high push-pull output. + microchip,sensitivity-delta-sense: + $ref: /schemas/types.yaml#/definitions/uint32 + default: 32 + enum: [1, 2, 4, 8, 16, 32, 64, 128] + description: + Controls the sensitivity multiplier of a touch detection. + Higher value means more sensitive settings. + At the more sensitive settings, touches are detected for a smaller delta + capacitance corresponding to a "lighter" touch. + + microchip,signal-guard: + $ref: /schemas/types.yaml#/definitions/uint32-array + minItems: 3 + maxItems: 8 + items: + enum: [0, 1] + description: | + 0 - off + 1 - on + The signal guard isolates the signal from virtual grounds. + If enabled then the behavior of the channel is changed to signal guard. + The number of entries must correspond to the number of channels. + + microchip,input-threshold: + $ref: /schemas/types.yaml#/definitions/uint32-array + minItems: 3 + maxItems: 8 + items: + minimum: 0 + maximum: 127 + description: + Specifies the delta threshold that is used to determine if a touch has + been detected. A higher value means a larger difference in capacitance + is required for a touch to be registered, making the touch sensor less + sensitive. + The number of entries must correspond to the number of channels. + + microchip,calib-sensitivity: + $ref: /schemas/types.yaml#/definitions/uint32-array + minItems: 3 + maxItems: 8 + items: + enum: [1, 2, 4] + description: | + Specifies an array of numeric values that controls the gain + used by the calibration routine to enable sensor inputs + to be more sensitive for proximity detection. + Gain is based on touch pad capacitance range + 1 - 5-50pF + 2 - 0-25pF + 4 - 0-12.5pF + The number of entries must correspond to the number of channels. + patternProperties: "^led@[0-7]$": type: object @@ -99,10 +152,29 @@ allOf: contains: enum: - microchip,cap1106 + - microchip,cap1203 + - microchip,cap1206 + - microchip,cap1293 + - microchip,cap1298 then: patternProperties: "^led@[0-7]$": false + - if: + properties: + compatible: + contains: + enum: + - microchip,cap1106 + - microchip,cap1126 + - microchip,cap1188 + - microchip,cap1203 + - microchip,cap1206 + then: + properties: + microchip,signal-guard: false + microchip,calib-sensitivity: false + required: - compatible - interrupts @@ -122,6 +194,8 @@ examples: reg = <0x28>; autorepeat; microchip,sensor-gain = <2>; + microchip,sensitivity-delta-sense = <16>; + microchip,input-threshold = <21>, <18>, <46>, <46>, <46>, <21>; linux,keycodes = <103>, /* KEY_UP */ <106>, /* KEY_RIGHT */ diff --git a/Documentation/devicetree/bindings/input/sprd,sc27xx-vibrator.yaml b/Documentation/devicetree/bindings/input/sprd,sc27xx-vibrator.yaml index a401a0bfcbec..4c8d303ff93c 100644 --- a/Documentation/devicetree/bindings/input/sprd,sc27xx-vibrator.yaml +++ b/Documentation/devicetree/bindings/input/sprd,sc27xx-vibrator.yaml @@ -28,21 +28,4 @@ required: additionalProperties: false -examples: - - | - #include <dt-bindings/interrupt-controller/arm-gic.h> - sc2731_pmic: pmic@0 { - compatible = "sprd,sc2731"; - reg = <0 0>; - spi-max-frequency = <26000000>; - interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>; - interrupt-controller; - #interrupt-cells = <2>; - #address-cells = <1>; - #size-cells = <0>; - - vibrator@eb4 { - compatible = "sprd,sc2731-vibrator"; - reg = <0xeb4>; - }; - }; +... diff --git a/Documentation/devicetree/bindings/input/ti,drv2665.txt b/Documentation/devicetree/bindings/input/ti,drv2665.txt deleted file mode 100644 index 1ba97ac04305..000000000000 --- a/Documentation/devicetree/bindings/input/ti,drv2665.txt +++ /dev/null @@ -1,17 +0,0 @@ -* Texas Instruments - drv2665 Haptics driver - -Required properties: - - compatible - "ti,drv2665" - DRV2665 - - reg - I2C slave address - - vbat-supply - Required supply regulator - -Example: - -haptics: haptics@59 { - compatible = "ti,drv2665"; - reg = <0x59>; - vbat-supply = <&vbat>; -}; - -For more product information please see the link below: -http://www.ti.com/product/drv2665 diff --git a/Documentation/devicetree/bindings/input/ti,drv2667.txt b/Documentation/devicetree/bindings/input/ti,drv2667.txt deleted file mode 100644 index 996382cf994a..000000000000 --- a/Documentation/devicetree/bindings/input/ti,drv2667.txt +++ /dev/null @@ -1,17 +0,0 @@ -* Texas Instruments - drv2667 Haptics driver - -Required properties: - - compatible - "ti,drv2667" - DRV2667 - - reg - I2C slave address - - vbat-supply - Required supply regulator - -Example: - -haptics: haptics@59 { - compatible = "ti,drv2667"; - reg = <0x59>; - vbat-supply = <&vbat>; -}; - -For more product information please see the link below: -http://www.ti.com/product/drv2667 diff --git a/Documentation/devicetree/bindings/input/ti,drv266x.yaml b/Documentation/devicetree/bindings/input/ti,drv266x.yaml new file mode 100644 index 000000000000..da1818824373 --- /dev/null +++ b/Documentation/devicetree/bindings/input/ti,drv266x.yaml @@ -0,0 +1,50 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/input/ti,drv266x.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Texas Instruments - drv266x Haptics driver + +description: | + Product Page: + http://www.ti.com/product/drv2665 + http://www.ti.com/product/drv2667 + +maintainers: + - Anshul Dalal <anshulusr@gmail.com> + +properties: + compatible: + enum: + - ti,drv2665 + - ti,drv2667 + + reg: + maxItems: 1 + + vbat-supply: + description: Required supply regulator + +required: + - compatible + - reg + - vbat-supply + +additionalProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + haptics@59 { + compatible = "ti,drv2667"; + reg = <0x59>; + vbat-supply = <&vbat>; + }; + }; diff --git a/Documentation/devicetree/bindings/input/touchscreen/neonode,zforce.yaml b/Documentation/devicetree/bindings/input/touchscreen/neonode,zforce.yaml new file mode 100644 index 000000000000..c2ee89b76ea1 --- /dev/null +++ b/Documentation/devicetree/bindings/input/touchscreen/neonode,zforce.yaml @@ -0,0 +1,72 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/input/touchscreen/neonode,zforce.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Neonode infrared touchscreen controller + +maintainers: + - Heiko Stuebner <heiko@sntech.de> + +allOf: + - $ref: touchscreen.yaml# + +properties: + compatible: + const: neonode,zforce + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + reset-gpios: + maxItems: 1 + + irq-gpios: + maxItems: 1 + + x-size: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + + y-size: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + + vdd-supply: true + +required: + - compatible + - reg + - interrupts + - reset-gpios + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + touchscreen@50 { + compatible = "neonode,zforce"; + reg = <0x50>; + interrupts = <2 0>; + vdd-supply = <®_zforce_vdd>; + + reset-gpios = <&gpio5 9 0>; /* RST */ + irq-gpios = <&gpio5 6 0>; /* IRQ, optional */ + + touchscreen-min-x = <0>; + touchscreen-size-x = <800>; + touchscreen-min-y = <0>; + touchscreen-size-y = <600>; + }; + }; +... diff --git a/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt b/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt deleted file mode 100644 index 6805d10d226d..000000000000 --- a/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt +++ /dev/null @@ -1,32 +0,0 @@ -* Samsung S6SY761 touchscreen controller - -Required properties: -- compatible : must be "samsung,s6sy761" -- reg : I2C slave address, (e.g. 0x48) -- interrupts : interrupt specification -- avdd-supply : analogic power supply -- vdd-supply : power supply - -Optional properties: -- touchscreen-size-x : see touchscreen.txt. This property is embedded in the - device. If defined it forces a different x resolution. -- touchscreen-size-y : see touchscreen.txt. This property is embedded in the - device. If defined it forces a different y resolution. - -Example: - -i2c@00000000 { - - /* ... */ - - touchscreen@48 { - compatible = "samsung,s6sy761"; - reg = <0x48>; - interrupt-parent = <&gpa1>; - interrupts = <1 IRQ_TYPE_NONE>; - avdd-supply = <&ldo30_reg>; - vdd-supply = <&ldo31_reg>; - touchscreen-size-x = <4096>; - touchscreen-size-y = <4096>; - }; -}; diff --git a/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.yaml b/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.yaml new file mode 100644 index 000000000000..1ffd17af3c53 --- /dev/null +++ b/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.yaml @@ -0,0 +1,54 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/input/touchscreen/samsung,s6sy761.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Samsung S6SY761 touchscreen controller + +maintainers: + - Andi Shyti <andi.shyti@kernel.org> + +allOf: + - $ref: touchscreen.yaml# + +properties: + compatible: + const: samsung,s6sy761 + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + avdd-supply: true + vdd-supply: true + +unevaluatedProperties: false + +required: + - compatible + - reg + - interrupts + - avdd-supply + - vdd-supply + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + i2c { + #address-cells = <1>; + #size-cells = <0>; + + touchscreen@48 { + compatible = "samsung,s6sy761"; + reg = <0x48>; + interrupt-parent = <&gpa1>; + interrupts = <1 IRQ_TYPE_LEVEL_HIGH>; + avdd-supply = <&ldo30_reg>; + vdd-supply = <&ldo31_reg>; + touchscreen-size-x = <4096>; + touchscreen-size-y = <4096>; + }; + }; diff --git a/Documentation/devicetree/bindings/input/touchscreen/zforce_ts.txt b/Documentation/devicetree/bindings/input/touchscreen/zforce_ts.txt deleted file mode 100644 index e3c27c4fd9c8..000000000000 --- a/Documentation/devicetree/bindings/input/touchscreen/zforce_ts.txt +++ /dev/null @@ -1,34 +0,0 @@ -* Neonode infrared touchscreen controller - -Required properties: -- compatible: must be "neonode,zforce" -- reg: I2C address of the chip -- interrupts: interrupt to which the chip is connected -- reset-gpios: reset gpio the chip is connected to -- x-size: horizontal resolution of touchscreen -- y-size: vertical resolution of touchscreen - -Optional properties: -- irq-gpios : interrupt gpio the chip is connected to -- vdd-supply: Regulator controlling the controller supply - -Example: - - i2c@00000000 { - /* ... */ - - zforce_ts@50 { - compatible = "neonode,zforce"; - reg = <0x50>; - interrupts = <2 0>; - vdd-supply = <®_zforce_vdd>; - - reset-gpios = <&gpio5 9 0>; /* RST */ - irq-gpios = <&gpio5 6 0>; /* IRQ, optional */ - - x-size = <800>; - y-size = <600>; - }; - - /* ... */ - }; diff --git a/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml b/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml index 00b570c82903..60441f0c5d72 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml @@ -11,8 +11,13 @@ maintainers: description: | This interrupt controller is found in the Loongson-3 family of chips and - Loongson-2K1000 chip, as the primary package interrupt controller which + Loongson-2K series chips, as the primary package interrupt controller which can route local I/O interrupt to interrupt lines of cores. + Be aware of the following points. + 1.The Loongson-2K0500 is a single core CPU; + 2.The Loongson-2K0500/2K1000 has 64 device interrupt sources as inputs, so we + need to define two nodes in dts{i} to describe the "0-31" and "32-61" interrupt + sources respectively. allOf: - $ref: /schemas/interrupt-controller.yaml# @@ -33,6 +38,7 @@ properties: - const: main - const: isr0 - const: isr1 + minItems: 2 interrupt-controller: true @@ -45,11 +51,9 @@ properties: interrupt-names: description: List of names for the parent interrupts. items: - - const: int0 - - const: int1 - - const: int2 - - const: int3 + pattern: int[0-3] minItems: 1 + maxItems: 4 '#interrupt-cells': const: 2 @@ -69,6 +73,7 @@ required: - compatible - reg - interrupts + - interrupt-names - interrupt-controller - '#interrupt-cells' - loongson,parent_int_map @@ -86,7 +91,8 @@ if: then: properties: reg: - minItems: 3 + minItems: 2 + maxItems: 3 required: - reg-names diff --git a/Documentation/devicetree/bindings/iommu/apple,dart.yaml b/Documentation/devicetree/bindings/iommu/apple,dart.yaml index 903edf85d72e..7adb1de455a5 100644 --- a/Documentation/devicetree/bindings/iommu/apple,dart.yaml +++ b/Documentation/devicetree/bindings/iommu/apple,dart.yaml @@ -24,6 +24,7 @@ properties: compatible: enum: - apple,t8103-dart + - apple,t8103-usb4-dart - apple,t8110-dart - apple,t6000-dart diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml index aa9e1c0895a5..a4042ae24770 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml @@ -56,6 +56,8 @@ properties: - qcom,sm8350-smmu-500 - qcom,sm8450-smmu-500 - qcom,sm8550-smmu-500 + - qcom,sm8650-smmu-500 + - qcom,x1e80100-smmu-500 - const: qcom,smmu-500 - const: arm,mmu-500 @@ -89,6 +91,8 @@ properties: - qcom,sm8150-smmu-500 - qcom,sm8250-smmu-500 - qcom,sm8350-smmu-500 + - qcom,sm8450-smmu-500 + - qcom,sm8550-smmu-500 - const: qcom,adreno-smmu - const: qcom,smmu-500 - const: arm,mmu-500 @@ -434,6 +438,30 @@ allOf: compatible: items: - enum: + - qcom,sm8350-smmu-500 + - const: qcom,adreno-smmu + - const: qcom,smmu-500 + - const: arm,mmu-500 + then: + properties: + clock-names: + items: + - const: bus + - const: iface + - const: ahb + - const: hlos1_vote_gpu_smmu + - const: cx_gmu + - const: hub_cx_int + - const: hub_aon + clocks: + minItems: 7 + maxItems: 7 + + - if: + properties: + compatible: + items: + - enum: - qcom,sm6115-smmu-500 - qcom,sm6125-smmu-500 - const: qcom,adreno-smmu @@ -453,6 +481,50 @@ allOf: - description: Voter clock required for HLOS SMMU access - description: Interface clock required for register access + - if: + properties: + compatible: + const: qcom,sm8450-smmu-500 + then: + properties: + clock-names: + items: + - const: gmu + - const: hub + - const: hlos + - const: bus + - const: iface + - const: ahb + + clocks: + items: + - description: GMU clock + - description: GPU HUB clock + - description: HLOS vote clock + - description: GPU memory bus clock + - description: GPU SNoC bus clock + - description: GPU AHB clock + + - if: + properties: + compatible: + const: qcom,sm8550-smmu-500 + then: + properties: + clock-names: + items: + - const: hlos + - const: bus + - const: iface + - const: ahb + + clocks: + items: + - description: HLOS vote clock + - description: GPU memory bus clock + - description: GPU SNoC bus clock + - description: GPU AHB clock + # Disallow clocks for all other platforms with specific compatibles - if: properties: @@ -472,9 +544,8 @@ allOf: - qcom,sdx65-smmu-500 - qcom,sm6350-smmu-500 - qcom,sm6375-smmu-500 - - qcom,sm8350-smmu-500 - - qcom,sm8450-smmu-500 - - qcom,sm8550-smmu-500 + - qcom,sm8650-smmu-500 + - qcom,x1e80100-smmu-500 then: properties: clock-names: false diff --git a/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml b/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml index ba9124f721f1..621dde0e45d8 100644 --- a/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml +++ b/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml @@ -19,9 +19,14 @@ description: |+ properties: compatible: - enum: - - rockchip,iommu - - rockchip,rk3568-iommu + oneOf: + - enum: + - rockchip,iommu + - rockchip,rk3568-iommu + - items: + - enum: + - rockchip,rk3588-iommu + - const: rockchip,rk3568-iommu reg: items: diff --git a/Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml b/Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml index 4191e33626f5..527a37368ed7 100644 --- a/Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml +++ b/Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml @@ -14,8 +14,8 @@ description: | programmable switching frequency to optimize efficiency. It supports two different dimming modes: - - analog mode, via I2C commands (default) - - PWM controlled mode. + - analog mode, via I2C commands, as default mode (32 dimming levels) + - PWM controlled mode (optional) The datasheet is available at: https://www.monolithicpower.com/en/mp3309c.html @@ -50,8 +50,6 @@ properties: required: - compatible - reg - - max-brightness - - default-brightness unevaluatedProperties: false @@ -66,8 +64,8 @@ examples: compatible = "mps,mp3309c"; reg = <0x17>; pwms = <&pwm1 0 3333333 0>; /* 300 Hz --> (1/f) * 1*10^9 */ - max-brightness = <100>; - default-brightness = <80>; + brightness-levels = <0 4 8 16 32 64 128 255>; + default-brightness = <6>; mps,overvoltage-protection-microvolt = <24000000>; }; }; diff --git a/Documentation/devicetree/bindings/loongarch/cpus.yaml b/Documentation/devicetree/bindings/loongarch/cpus.yaml new file mode 100644 index 000000000000..f175872995e1 --- /dev/null +++ b/Documentation/devicetree/bindings/loongarch/cpus.yaml @@ -0,0 +1,61 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/loongarch/cpus.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: LoongArch CPUs + +maintainers: + - Binbin Zhou <zhoubinbin@loongson.cn> + +description: + This document describes the list of LoongArch CPU cores that support FDT, + it describe the layout of CPUs in a system through the "cpus" node. + +allOf: + - $ref: /schemas/cpu.yaml# + +properties: + compatible: + enum: + - loongson,la264 + - loongson,la364 + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + +required: + - compatible + - reg + - clocks + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/clock/loongson,ls2k-clk.h> + + cpus { + #size-cells = <0>; + #address-cells = <1>; + + cpu@0 { + compatible = "loongson,la264"; + device_type = "cpu"; + reg = <0>; + clocks = <&clk LOONGSON2_NODE_CLK>; + }; + + cpu@1 { + compatible = "loongson,la264"; + device_type = "cpu"; + reg = <1>; + clocks = <&clk LOONGSON2_NODE_CLK>; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/loongarch/loongson.yaml b/Documentation/devicetree/bindings/loongarch/loongson.yaml new file mode 100644 index 000000000000..e1a4a97b7576 --- /dev/null +++ b/Documentation/devicetree/bindings/loongarch/loongson.yaml @@ -0,0 +1,34 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/loongarch/loongson.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Loongson SoC-based boards + +maintainers: + - Binbin Zhou <zhoubinbin@loongson.cn> + +properties: + $nodename: + const: '/' + compatible: + oneOf: + - description: Loongson-2K0500 processor based boards + items: + - const: loongson,ls2k0500-ref + - const: loongson,ls2k0500 + + - description: Loongson-2K1000 processor based boards + items: + - const: loongson,ls2k1000-ref + - const: loongson,ls2k1000 + + - description: Loongson-2K2000 processor based boards + items: + - const: loongson,ls2k2000-ref + - const: loongson,ls2k2000 + +additionalProperties: true + +... diff --git a/Documentation/devicetree/bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml b/Documentation/devicetree/bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml index c8c83acfb871..81c2654b7e57 100644 --- a/Documentation/devicetree/bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml +++ b/Documentation/devicetree/bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml @@ -16,20 +16,8 @@ properties: "#phy-cells": const: 0 - reg: - maxItems: 1 - required: - compatible - - reg - "#phy-cells" additionalProperties: false - -examples: - - | - phy@0 { - compatible = "amlogic,g12a-mipi-dphy-analog"; - reg = <0x0 0xc>; - #phy-cells = <0>; - }; diff --git a/Documentation/devicetree/bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml b/Documentation/devicetree/bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml index 009a39808318..70def36e5688 100644 --- a/Documentation/devicetree/bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml +++ b/Documentation/devicetree/bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml @@ -9,16 +9,6 @@ title: Amlogic AXG shared MIPI/PCIE analog PHY maintainers: - Remi Pommarel <repk@triplefau.lt> -description: |+ - The Everything-Else Power Domains node should be the child of a syscon - node with the required property: - - - compatible: Should be the following: - "amlogic,meson-gx-hhi-sysctrl", "simple-mfd", "syscon" - - Refer to the bindings described in - Documentation/devicetree/bindings/mfd/syscon.yaml - properties: compatible: const: amlogic,axg-mipi-pcie-analog-phy @@ -31,10 +21,3 @@ required: - "#phy-cells" additionalProperties: false - -examples: - - | - mpphy: phy { - compatible = "amlogic,axg-mipi-pcie-analog-phy"; - #phy-cells = <0>; - }; diff --git a/Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml b/Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml index 6703689fcdbe..f6e494d0d89b 100644 --- a/Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml +++ b/Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml @@ -31,6 +31,7 @@ properties: - items: - enum: - mediatek,mt8188-mipi-tx + - mediatek,mt8195-mipi-tx - mediatek,mt8365-mipi-tx - const: mediatek,mt8183-mipi-tx - const: mediatek,mt2701-mipi-tx diff --git a/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml b/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml index 2bb91542e984..acba0720125d 100644 --- a/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml +++ b/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml @@ -235,6 +235,15 @@ patternProperties: Specify the flag to enable BC1.2 if support it type: boolean + mediatek,force-mode: + description: + The force mode is used to manually switch the shared phy mode between + USB3 and PCIe, when USB3 phy type is selected by the consumer, and + force-mode is set, will cause phy's power and pipe toggled and force + phy as USB3 mode which switched from default PCIe mode. But perfer to + use the property "mediatek,syscon-type" for newer SoCs that support it. + type: boolean + mediatek,syscon-type: $ref: /schemas/types.yaml#/definitions/phandle-array maxItems: 1 diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml index 2c3d6553a7ba..6c03f2d5fca3 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml @@ -36,6 +36,8 @@ properties: - qcom,sm8450-qmp-gen4x2-pcie-phy - qcom,sm8550-qmp-gen3x2-pcie-phy - qcom,sm8550-qmp-gen4x2-pcie-phy + - qcom,sm8650-qmp-gen3x2-pcie-phy + - qcom,sm8650-qmp-gen4x2-pcie-phy reg: minItems: 1 @@ -147,6 +149,8 @@ allOf: - qcom,sm8450-qmp-gen3x2-pcie-phy - qcom,sm8550-qmp-gen3x2-pcie-phy - qcom,sm8550-qmp-gen4x2-pcie-phy + - qcom,sm8650-qmp-gen3x2-pcie-phy + - qcom,sm8650-qmp-gen4x2-pcie-phy then: properties: clocks: @@ -189,6 +193,7 @@ allOf: contains: enum: - qcom,sm8550-qmp-gen4x2-pcie-phy + - qcom,sm8650-qmp-gen4x2-pcie-phy then: properties: resets: diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml index f3a3296c811c..8474eef8d0ff 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml @@ -32,6 +32,7 @@ properties: - qcom,sm8350-qmp-ufs-phy - qcom,sm8450-qmp-ufs-phy - qcom,sm8550-qmp-ufs-phy + - qcom,sm8650-qmp-ufs-phy reg: maxItems: 1 @@ -112,6 +113,7 @@ allOf: - qcom,sm8250-qmp-ufs-phy - qcom,sm8350-qmp-ufs-phy - qcom,sm8550-qmp-ufs-phy + - qcom,sm8650-qmp-ufs-phy then: properties: clocks: diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml index 57702f7f2a46..15d82c67f157 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml @@ -32,6 +32,7 @@ properties: - qcom,sm8150-qmp-usb3-uni-phy - qcom,sm8250-qmp-usb3-uni-phy - qcom,sm8350-qmp-usb3-uni-phy + - qcom,x1e80100-qmp-usb3-uni-phy reg: @@ -135,6 +136,7 @@ allOf: - qcom,sm8150-qmp-usb3-uni-phy - qcom,sm8250-qmp-usb3-uni-phy - qcom,sm8350-qmp-usb3-uni-phy + - qcom,x1e80100-qmp-usb3-uni-phy then: properties: clocks: @@ -171,6 +173,7 @@ allOf: enum: - qcom,sa8775p-qmp-usb3-uni-phy - qcom,sc8280xp-qmp-usb3-uni-phy + - qcom,x1e80100-qmp-usb3-uni-phy then: required: - power-domains diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml index 9af203dc8793..2d0d7e9e6431 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml @@ -27,6 +27,8 @@ properties: - qcom,sm8350-qmp-usb3-dp-phy - qcom,sm8450-qmp-usb3-dp-phy - qcom,sm8550-qmp-usb3-dp-phy + - qcom,sm8650-qmp-usb3-dp-phy + - qcom,x1e80100-qmp-usb3-dp-phy reg: maxItems: 1 @@ -62,12 +64,12 @@ properties: "#clock-cells": const: 1 description: - See include/dt-bindings/dt-bindings/phy/phy-qcom-qmp.h + See include/dt-bindings/phy/phy-qcom-qmp.h "#phy-cells": const: 1 description: - See include/dt-bindings/dt-bindings/phy/phy-qcom-qmp.h + See include/dt-bindings/phy/phy-qcom-qmp.h orientation-switch: description: @@ -128,6 +130,8 @@ allOf: - qcom,sc8280xp-qmp-usb43dp-phy - qcom,sm6350-qmp-usb3-dp-phy - qcom,sm8550-qmp-usb3-dp-phy + - qcom,sm8650-qmp-usb3-dp-phy + - qcom,x1e80100-qmp-usb3-dp-phy then: required: - power-domains diff --git a/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml index c95828607ab6..b82f7f5731ed 100644 --- a/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml @@ -18,6 +18,8 @@ properties: - items: - enum: - qcom,sdx75-snps-eusb2-phy + - qcom,sm8650-snps-eusb2-phy + - qcom,x1e80100-snps-eusb2-phy - const: qcom,sm8550-snps-eusb2-phy - const: qcom,sm8550-snps-eusb2-phy diff --git a/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml b/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml index 14a262bcbf7c..627f8a6078c2 100644 --- a/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml +++ b/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml @@ -28,17 +28,15 @@ properties: items: - const: reboot-mode -patternProperties: - "^mode-.+": - $ref: /schemas/types.yaml#/definitions/uint32 - description: Vendor-specific mode value written to the mode register +allOf: + - $ref: reboot-mode.yaml# required: - compatible - nvmem-cells - nvmem-cell-names -additionalProperties: false +unevaluatedProperties: false examples: - | diff --git a/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml b/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml index 5e460128b0d1..fc8105a7b9b2 100644 --- a/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml +++ b/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml @@ -111,21 +111,24 @@ examples: #include <dt-bindings/interrupt-controller/irq.h> #include <dt-bindings/input/linux-event-codes.h> #include <dt-bindings/spmi/spmi.h> - spmi_bus: spmi@c440000 { + + spmi@c440000 { reg = <0x0c440000 0x1100>; #address-cells = <2>; #size-cells = <0>; - pmk8350: pmic@0 { + + pmic@0 { reg = <0x0 SPMI_USID>; #address-cells = <1>; #size-cells = <0>; - pmk8350_pon: pon_hlos@1300 { - reg = <0x1300>; + + pon@800 { compatible = "qcom,pm8998-pon"; + reg = <0x800>; pwrkey { compatible = "qcom,pm8941-pwrkey"; - interrupts = < 0x0 0x8 0 IRQ_TYPE_EDGE_BOTH >; + interrupts = <0x0 0x8 0 IRQ_TYPE_EDGE_BOTH>; debounce = <15625>; bias-pull-up; linux,code = <KEY_POWER>; diff --git a/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml b/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml index 9b1ffceefe3d..b6acff199cde 100644 --- a/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml +++ b/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml @@ -29,12 +29,10 @@ properties: $ref: /schemas/types.yaml#/definitions/uint32 description: Offset in the register map for the mode register (in bytes) -patternProperties: - "^mode-.+": - $ref: /schemas/types.yaml#/definitions/uint32 - description: Vendor-specific mode value written to the mode register +allOf: + - $ref: reboot-mode.yaml# -additionalProperties: false +unevaluatedProperties: false required: - compatible diff --git a/Documentation/devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml b/Documentation/devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml index 45792e216981..799831636194 100644 --- a/Documentation/devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml +++ b/Documentation/devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml @@ -57,7 +57,7 @@ examples: firmware { zynqmp-firmware { - zynqmp-power { + power-management { compatible = "xlnx,zynqmp-power"; interrupts = <0 35 4>; }; @@ -70,7 +70,7 @@ examples: firmware { zynqmp-firmware { - zynqmp-power { + power-management { compatible = "xlnx,zynqmp-power"; interrupt-parent = <&gic>; interrupts = <0 35 4>; diff --git a/Documentation/devicetree/bindings/power/supply/bq24190.yaml b/Documentation/devicetree/bindings/power/supply/bq24190.yaml index d3ebc9de8c0b..131b7e57d22f 100644 --- a/Documentation/devicetree/bindings/power/supply/bq24190.yaml +++ b/Documentation/devicetree/bindings/power/supply/bq24190.yaml @@ -20,6 +20,7 @@ properties: - ti,bq24192 - ti,bq24192i - ti,bq24196 + - ti,bq24296 reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/rtc/adi,max31335.yaml b/Documentation/devicetree/bindings/rtc/adi,max31335.yaml new file mode 100644 index 000000000000..0125cf6727cc --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/adi,max31335.yaml @@ -0,0 +1,70 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/adi,max31335.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Analog Devices MAX31335 RTC + +maintainers: + - Antoniu Miclaus <antoniu.miclaus@analog.com> + +description: + Analog Devices MAX31335 I2C RTC ±2ppm Automotive Real-Time Clock with + Integrated MEMS Resonator. + +allOf: + - $ref: rtc.yaml# + +properties: + compatible: + const: adi,max31335 + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + "#clock-cells": + description: + RTC can be used as a clock source through its clock output pin. + const: 0 + + adi,tc-diode: + description: + Select the diode configuration for the trickle charger. + schottky - Schottky diode in series. + standard+schottky - standard diode + Schottky diode in series. + enum: [schottky, standard+schottky] + + trickle-resistor-ohms: + description: + Selected resistor for trickle charger. Should be specified if trickle + charger should be enabled. + enum: [3000, 6000, 11000] + +required: + - compatible + - reg + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + i2c { + #address-cells = <1>; + #size-cells = <0>; + + rtc@68 { + compatible = "adi,max31335"; + reg = <0x68>; + pinctrl-0 = <&rtc_nint_pins>; + interrupts-extended = <&gpio1 16 IRQ_TYPE_LEVEL_HIGH>; + aux-voltage-chargeable = <1>; + trickle-resistor-ohms = <6000>; + adi,tc-diode = "schottky"; + }; + }; +... diff --git a/Documentation/devicetree/bindings/rtc/epson,rx8900.yaml b/Documentation/devicetree/bindings/rtc/epson,rx8900.yaml index 1df7c45d95c1..b770149c5fd6 100644 --- a/Documentation/devicetree/bindings/rtc/epson,rx8900.yaml +++ b/Documentation/devicetree/bindings/rtc/epson,rx8900.yaml @@ -29,6 +29,8 @@ properties: trickle-diode-disable: true + wakeup-source: true + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/rtc/nuvoton,ma35d1-rtc.yaml b/Documentation/devicetree/bindings/rtc/nuvoton,ma35d1-rtc.yaml new file mode 100644 index 000000000000..5e4ade803eed --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/nuvoton,ma35d1-rtc.yaml @@ -0,0 +1,48 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/nuvoton,ma35d1-rtc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Nuvoton MA35D1 Real Time Clock + +maintainers: + - Min-Jen Chen <mjchen@nuvoton.com> + +allOf: + - $ref: rtc.yaml# + +properties: + compatible: + enum: + - nuvoton,ma35d1-rtc + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + +required: + - compatible + - reg + - interrupts + - clocks + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/clock/nuvoton,ma35d1-clk.h> + rtc@40410000 { + compatible = "nuvoton,ma35d1-rtc"; + reg = <0x40410000 0x200>; + interrupts = <GIC_SPI 5 IRQ_TYPE_EDGE_RISING>; + clocks = <&clk RTC_GATE>; + }; + +... diff --git a/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml b/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml index b95a69cc9ae0..d274bb7a534b 100644 --- a/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml @@ -61,27 +61,27 @@ additionalProperties: false examples: - | + #include <dt-bindings/interrupt-controller/irq.h> #include <dt-bindings/spmi/spmi.h> - spmi_bus: spmi@c440000 { - reg = <0x0c440000 0x1100>; - #address-cells = <2>; - #size-cells = <0>; - pmicintc: pmic@0 { - reg = <0x0 SPMI_USID>; - compatible = "qcom,pm8921"; - interrupts = <104 8>; - #interrupt-cells = <2>; - interrupt-controller; - #address-cells = <1>; + + spmi { + #address-cells = <2>; #size-cells = <0>; - pm8921_rtc: rtc@11d { - compatible = "qcom,pm8921-rtc"; - reg = <0x11d>; - interrupts = <0x27 0>; - nvmem-cells = <&rtc_offset>; - nvmem-cell-names = "offset"; + pmic@0 { + compatible = "qcom,pm8941", "qcom,spmi-pmic"; + reg = <0x0 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + rtc@6000 { + compatible = "qcom,pm8941-rtc"; + reg = <0x6000>, <0x6100>; + reg-names = "rtc", "alarm"; + interrupts = <0x0 0x61 0x1 IRQ_TYPE_EDGE_RISING>; + nvmem-cells = <&rtc_offset>; + nvmem-cell-names = "offset"; + }; }; - }; }; ... diff --git a/Documentation/devicetree/bindings/sound/tas2562.yaml b/Documentation/devicetree/bindings/sound/tas2562.yaml index f01c0dde0cf7..d28c102c0ce7 100644 --- a/Documentation/devicetree/bindings/sound/tas2562.yaml +++ b/Documentation/devicetree/bindings/sound/tas2562.yaml @@ -18,7 +18,6 @@ description: | Specifications about the audio amplifier can be found at: https://www.ti.com/lit/gpn/tas2562 - https://www.ti.com/lit/gpn/tas2563 https://www.ti.com/lit/gpn/tas2564 https://www.ti.com/lit/gpn/tas2110 @@ -29,7 +28,6 @@ properties: compatible: enum: - ti,tas2562 - - ti,tas2563 - ti,tas2564 - ti,tas2110 diff --git a/Documentation/devicetree/bindings/sound/ti,tas2781.yaml b/Documentation/devicetree/bindings/sound/ti,tas2781.yaml index a69e6c223308..976238689249 100644 --- a/Documentation/devicetree/bindings/sound/ti,tas2781.yaml +++ b/Documentation/devicetree/bindings/sound/ti,tas2781.yaml @@ -5,36 +5,46 @@ $id: http://devicetree.org/schemas/sound/ti,tas2781.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Texas Instruments TAS2781 SmartAMP +title: Texas Instruments TAS2563/TAS2781 SmartAMP maintainers: - Shenghao Ding <shenghao-ding@ti.com> -description: - The TAS2781 is a mono, digital input Class-D audio amplifier - optimized for efficiently driving high peak power into small - loudspeakers. An integrated on-chip DSP supports Texas Instruments - Smart Amp speaker protection algorithm. The integrated speaker - voltage and current sense provides for real time +description: | + The TAS2563/TAS2781 is a mono, digital input Class-D audio + amplifier optimized for efficiently driving high peak power into + small loudspeakers. An integrated on-chip DSP supports Texas + Instruments Smart Amp speaker protection algorithm. The + integrated speaker voltage and current sense provides for real time monitoring of loudspeaker behavior. -allOf: - - $ref: dai-common.yaml# + Specifications about the audio amplifier can be found at: + https://www.ti.com/lit/gpn/tas2563 + https://www.ti.com/lit/gpn/tas2781 properties: compatible: - enum: - - ti,tas2781 + description: | + ti,tas2563: 6.1-W Boosted Class-D Audio Amplifier With Integrated + DSP and IV Sense, 16/20/24/32bit stereo I2S or multichannel TDM. + + ti,tas2781: 24-V Class-D Amplifier with Real Time Integrated Speaker + Protection and Audio Processing, 16/20/24/32bit stereo I2S or + multichannel TDM. + oneOf: + - items: + - enum: + - ti,tas2563 + - const: ti,tas2781 + - enum: + - ti,tas2781 reg: description: - I2C address, in multiple tas2781s case, all the i2c address + I2C address, in multiple-AMP case, all the i2c address aggregate as one Audio Device to support multiple audio slots. maxItems: 8 minItems: 1 - items: - minimum: 0x38 - maximum: 0x3f reset-gpios: maxItems: 1 @@ -49,6 +59,44 @@ required: - compatible - reg +allOf: + - $ref: dai-common.yaml# + - if: + properties: + compatible: + contains: + enum: + - ti,tas2563 + then: + properties: + reg: + description: + I2C address, in multiple-AMP case, all the i2c address + aggregate as one Audio Device to support multiple audio slots. + maxItems: 4 + minItems: 1 + items: + minimum: 0x4c + maximum: 0x4f + + - if: + properties: + compatible: + contains: + enum: + - ti,tas2781 + then: + properties: + reg: + description: + I2C address, in multiple-AMP case, all the i2c address + aggregate as one Audio Device to support multiple audio slots. + maxItems: 8 + minItems: 1 + items: + minimum: 0x38 + maximum: 0x3f + additionalProperties: false examples: diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst index 48b95d04f72d..4cc657d743f7 100644 --- a/Documentation/filesystems/netfs_library.rst +++ b/Documentation/filesystems/netfs_library.rst @@ -295,7 +295,6 @@ through which it can issue requests and negotiate:: struct netfs_request_ops { void (*init_request)(struct netfs_io_request *rreq, struct file *file); void (*free_request)(struct netfs_io_request *rreq); - int (*begin_cache_operation)(struct netfs_io_request *rreq); void (*expand_readahead)(struct netfs_io_request *rreq); bool (*clamp_length)(struct netfs_io_subrequest *subreq); void (*issue_read)(struct netfs_io_subrequest *subreq); @@ -317,20 +316,6 @@ The operations are as follows: [Optional] This is called as the request is being deallocated so that the filesystem can clean up any state it has attached there. - * ``begin_cache_operation()`` - - [Optional] This is called to ask the network filesystem to call into the - cache (if present) to initialise the caching state for this read. The netfs - library module cannot access the cache directly, so the cache should call - something like fscache_begin_read_operation() to do this. - - The cache gets to store its state in ->cache_resources and must set a table - of operations of its own there (though of a different type). - - This should return 0 on success and an error code otherwise. If an error is - reported, the operation may proceed anyway, just without local caching (only - out of memory and interruption errors cause failure here). - * ``expand_readahead()`` [Optional] This is called to allow the filesystem to expand the size of a @@ -460,14 +445,14 @@ When implementing a local cache to be used by the read helpers, two things are required: some way for the network filesystem to initialise the caching for a read request and a table of operations for the helpers to call. -The network filesystem's ->begin_cache_operation() method is called to set up a -cache and this must call into the cache to do the work. If using fscache, for -example, the cache would call:: +To begin a cache operation on an fscache object, the following function is +called:: int fscache_begin_read_operation(struct netfs_io_request *rreq, struct fscache_cookie *cookie); -passing in the request pointer and the cookie corresponding to the file. +passing in the request pointer and the cookie corresponding to the file. This +fills in the cache resources mentioned below. The netfs_io_request object contains a place for the cache to hang its state:: diff --git a/Documentation/filesystems/smb/ksmbd.rst b/Documentation/filesystems/smb/ksmbd.rst index 7bed96d794fc..6b30e43a0d11 100644 --- a/Documentation/filesystems/smb/ksmbd.rst +++ b/Documentation/filesystems/smb/ksmbd.rst @@ -73,15 +73,14 @@ Auto Negotiation Supported. Compound Request Supported. Oplock Cache Mechanism Supported. SMB2 leases(v1 lease) Supported. -Directory leases(v2 lease) Planned for future. +Directory leases(v2 lease) Supported. Multi-credits Supported. NTLM/NTLMv2 Supported. HMAC-SHA256 Signing Supported. Secure negotiate Supported. Signing Update Supported. Pre-authentication integrity Supported. -SMB3 encryption(CCM, GCM) Supported. (CCM and GCM128 supported, GCM256 in - progress) +SMB3 encryption(CCM, GCM) Supported. (CCM/GCM128 and CCM/GCM256 supported) SMB direct(RDMA) Supported. SMB3 Multi-channel Partially Supported. Planned to implement replay/retry mechanisms for future. @@ -112,6 +111,10 @@ DCE/RPC support Partially Supported. a few calls(NetShareEnumAll, for Witness protocol e.g.) ksmbd/nfsd interoperability Planned for future. The features that ksmbd support are Leases, Notify, ACLs and Share modes. +SMB3.1.1 Compression Planned for future. +SMB3.1.1 over QUIC Planned for future. +Signing/Encryption over RDMA Planned for future. +SMB3.1.1 GMAC signing support Planned for future. ============================== ================================================= diff --git a/Documentation/process/4.Coding.rst b/Documentation/process/4.Coding.rst index 1f0d81f44e14..c2046dec0c2f 100644 --- a/Documentation/process/4.Coding.rst +++ b/Documentation/process/4.Coding.rst @@ -66,6 +66,10 @@ for aligning variables/macros, for reflowing text and other similar tasks. See the file :ref:`Documentation/process/clang-format.rst <clangformat>` for more details. +Some basic editor settings, such as indentation and line endings, will be +set automatically if you are using an editor that is compatible with +EditorConfig. See the official EditorConfig website for more information: +https://editorconfig.org/ Abstraction layers ****************** diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst index 6db37a46d305..c48382c6b477 100644 --- a/Documentation/process/coding-style.rst +++ b/Documentation/process/coding-style.rst @@ -735,6 +735,10 @@ for aligning variables/macros, for reflowing text and other similar tasks. See the file :ref:`Documentation/process/clang-format.rst <clangformat>` for more details. +Some basic editor settings, such as indentation and line endings, will be +set automatically if you are using an editor that is compatible with +EditorConfig. See the official EditorConfig website for more information: +https://editorconfig.org/ 10) Kconfig configuration files ------------------------------- diff --git a/Documentation/rust/arch-support.rst b/Documentation/rust/arch-support.rst index b91e9ef4d0c2..73203ba1e901 100644 --- a/Documentation/rust/arch-support.rst +++ b/Documentation/rust/arch-support.rst @@ -12,10 +12,11 @@ which uses ``libclang``. Below is a general summary of architectures that currently work. Level of support corresponds to ``S`` values in the ``MAINTAINERS`` file. -============ ================ ============================================== -Architecture Level of support Constraints -============ ================ ============================================== -``um`` Maintained ``x86_64`` only. -``x86`` Maintained ``x86_64`` only. -============ ================ ============================================== +============= ================ ============================================== +Architecture Level of support Constraints +============= ================ ============================================== +``loongarch`` Maintained - +``um`` Maintained ``x86_64`` only. +``x86`` Maintained ``x86_64`` only. +============= ================ ============================================== diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst index 16122a8895ba..7e7b8ec17934 100644 --- a/Documentation/trace/ftrace.rst +++ b/Documentation/trace/ftrace.rst @@ -218,6 +218,27 @@ of ftrace. Here is a list of some of the key files: This displays the total combined size of all the trace buffers. + buffer_subbuf_size_kb: + + This sets or displays the sub buffer size. The ring buffer is broken up + into several same size "sub buffers". An event can not be bigger than + the size of the sub buffer. Normally, the sub buffer is the size of the + architecture's page (4K on x86). The sub buffer also contains meta data + at the start which also limits the size of an event. That means when + the sub buffer is a page size, no event can be larger than the page + size minus the sub buffer meta data. + + Note, the buffer_subbuf_size_kb is a way for the user to specify the + minimum size of the subbuffer. The kernel may make it bigger due to the + implementation details, or simply fail the operation if the kernel can + not handle the request. + + Changing the sub buffer size allows for events to be larger than the + page size. + + Note: When changing the sub-buffer size, tracing is stopped and any + data in the ring buffer and the snapshot buffer will be discarded. + free_buffer: If a process is performing tracing, and the ring buffer should be diff --git a/MAINTAINERS b/MAINTAINERS index e350c4e6a198..2b90c5e28100 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -441,6 +441,13 @@ W: http://wiki.analog.com/AD7879 W: https://ez.analog.com/linux-software-drivers F: drivers/input/touchscreen/ad7879.c +ADAFRUIT MINI I2C GAMEPAD +M: Anshul Dalal <anshulusr@gmail.com> +L: linux-input@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/input/adafruit,seesaw-gamepad.yaml +F: drivers/input/joystick/adafruit-seesaw.c + ADDRESS SPACE LAYOUT RANDOMIZATION (ASLR) M: Jiri Kosina <jikos@kernel.org> S: Maintained @@ -3383,9 +3390,8 @@ F: Documentation/devicetree/bindings/iio/adc/avia-hx711.yaml F: drivers/iio/adc/hx711.c AX.25 NETWORK LAYER -M: Ralf Baechle <ralf@linux-mips.org> L: linux-hams@vger.kernel.org -S: Maintained +S: Orphan W: https://linux-ax25.in-berlin.de F: include/net/ax25.h F: include/uapi/linux/ax25.h @@ -3624,7 +3630,6 @@ F: drivers/mtd/devices/block2mtd.c BLUETOOTH DRIVERS M: Marcel Holtmann <marcel@holtmann.org> -M: Johan Hedberg <johan.hedberg@gmail.com> M: Luiz Augusto von Dentz <luiz.dentz@gmail.com> L: linux-bluetooth@vger.kernel.org S: Supported @@ -3687,6 +3692,13 @@ L: bpf@vger.kernel.org S: Supported F: arch/arm64/net/ +BPF JIT for LOONGARCH +M: Tiezhu Yang <yangtiezhu@loongson.cn> +R: Hengqi Chen <hengqi.chen@gmail.com> +L: bpf@vger.kernel.org +S: Maintained +F: arch/loongarch/net/ + BPF JIT for MIPS (32-BIT AND 64-BIT) M: Johan Almbladh <johan.almbladh@anyfinetworks.com> M: Paul Burton <paulburton@kernel.org> @@ -4719,11 +4731,8 @@ F: drivers/i2c/busses/i2c-octeon* F: drivers/i2c/busses/i2c-thunderx* CAVIUM LIQUIDIO NETWORK DRIVER -M: Derek Chickles <dchickles@marvell.com> -M: Satanand Burla <sburla@marvell.com> -M: Felix Manlunas <fmanlunas@marvell.com> L: netdev@vger.kernel.org -S: Supported +S: Orphan W: http://www.marvell.com F: drivers/net/ethernet/cavium/liquidio/ @@ -5280,6 +5289,7 @@ M: Dan Williams <dan.j.williams@intel.com> L: linux-cxl@vger.kernel.org S: Maintained F: drivers/cxl/ +F: include/linux/cxl-event.h F: include/uapi/linux/cxl_mem.h F: tools/testing/cxl/ @@ -8211,6 +8221,19 @@ S: Supported F: fs/iomap/ F: include/linux/iomap.h +FILESYSTEMS [NETFS LIBRARY] +M: David Howells <dhowells@redhat.com> +L: linux-cachefs@redhat.com (moderated for non-subscribers) +L: linux-fsdevel@vger.kernel.org +S: Supported +F: Documentation/filesystems/caching/ +F: Documentation/filesystems/netfs_library.rst +F: fs/netfs/ +F: include/linux/fscache*.h +F: include/linux/netfs.h +F: include/trace/events/fscache.h +F: include/trace/events/netfs.h + FILESYSTEMS [STACKABLE] M: Miklos Szeredi <miklos@szeredi.hu> M: Amir Goldstein <amir73il@gmail.com> @@ -8656,14 +8679,6 @@ F: Documentation/power/freezing-of-tasks.rst F: include/linux/freezer.h F: kernel/freezer.c -FS-CACHE: LOCAL CACHING FOR NETWORK FILESYSTEMS -M: David Howells <dhowells@redhat.com> -L: linux-cachefs@redhat.com (moderated for non-subscribers) -S: Supported -F: Documentation/filesystems/caching/ -F: fs/fscache/ -F: include/linux/fscache*.h - FSCRYPT: FILE SYSTEM LEVEL ENCRYPTION SUPPORT M: Eric Biggers <ebiggers@kernel.org> M: Theodore Y. Ts'o <tytso@mit.edu> @@ -10053,7 +10068,7 @@ F: Documentation/i2c/busses/i2c-parport.rst F: drivers/i2c/busses/i2c-parport.c I2C SUBSYSTEM -M: Wolfram Sang <wsa@kernel.org> +M: Wolfram Sang <wsa+renesas@sang-engineering.com> L: linux-i2c@vger.kernel.org S: Maintained W: https://i2c.wiki.kernel.org/ @@ -10231,7 +10246,6 @@ IBM Power SRIOV Virtual NIC Device Driver M: Haren Myneni <haren@linux.ibm.com> M: Rick Lindsley <ricklind@linux.ibm.com> R: Nick Child <nnac123@linux.ibm.com> -R: Dany Madden <danymadden@us.ibm.com> R: Thomas Falcon <tlfalcon@linux.ibm.com> L: netdev@vger.kernel.org S: Supported @@ -12995,10 +13009,10 @@ S: Maintained F: drivers/thermal/armada_thermal.c MARVELL MVNETA ETHERNET DRIVER -M: Thomas Petazzoni <thomas.petazzoni@bootlin.com> +M: Marcin Wojtas <marcin.s.wojtas@gmail.com> L: netdev@vger.kernel.org S: Maintained -F: drivers/net/ethernet/marvell/mvneta.* +F: drivers/net/ethernet/marvell/mvneta* MARVELL MVPP2 ETHERNET DRIVER M: Marcin Wojtas <marcin.s.wojtas@gmail.com> @@ -13118,6 +13132,14 @@ F: Documentation/devicetree/bindings/hwmon/adi,max31827.yaml F: Documentation/hwmon/max31827.rst F: drivers/hwmon/max31827.c +MAX31335 RTC DRIVER +M: Antoniu Miclaus <antoniu.miclaus@analog.com> +L: linux-rtc@vger.kernel.org +S: Supported +W: https://ez.analog.com/linux-software-drivers +F: Documentation/devicetree/bindings/rtc/adi,max31335.yaml +F: drivers/rtc/rtc-max31335.c + MAX6650 HARDWARE MONITOR AND FAN CONTROLLER DRIVER L: linux-hwmon@vger.kernel.org S: Orphan @@ -13640,7 +13662,6 @@ F: drivers/dma/mediatek/ MEDIATEK ETHERNET DRIVER M: Felix Fietkau <nbd@nbd.name> -M: John Crispin <john@phrozen.org> M: Sean Wang <sean.wang@mediatek.com> M: Mark Lee <Mark-MC.Lee@mediatek.com> M: Lorenzo Bianconi <lorenzo@kernel.org> @@ -13796,7 +13817,6 @@ F: include/soc/mediatek/smi.h MEDIATEK SWITCH DRIVER M: Arınç ÃœNAL <arinc.unal@arinc9.com> M: Daniel Golle <daniel@makrotopia.org> -M: Landen Chao <Landen.Chao@mediatek.com> M: DENG Qingfang <dqfext@gmail.com> M: Sean Wang <sean.wang@mediatek.com> L: netdev@vger.kernel.org @@ -14803,6 +14823,13 @@ S: Maintained F: Documentation/driver-api/tty/moxa-smartio.rst F: drivers/tty/mxser.* +MP3309C BACKLIGHT DRIVER +M: Flavio Suligoi <f.suligoi@asem.it> +L: dri-devel@lists.freedesktop.org +S: Maintained +F: Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml +F: drivers/video/backlight/mp3309c.c + MR800 AVERMEDIA USB FM RADIO DRIVER M: Alexey Klimov <klimov.linux@gmail.com> L: linux-media@vger.kernel.org @@ -18436,7 +18463,6 @@ X: include/linux/srcu*.h X: kernel/rcu/srcu*.c REAL TIME CLOCK (RTC) SUBSYSTEM -M: Alessandro Zummo <a.zummo@towertech.it> M: Alexandre Belloni <alexandre.belloni@bootlin.com> L: linux-rtc@vger.kernel.org S: Maintained @@ -19124,7 +19150,7 @@ F: drivers/iommu/s390-iommu.c S390 IUCV NETWORK LAYER M: Alexandra Winter <wintera@linux.ibm.com> -M: Wenjia Zhang <wenjia@linux.ibm.com> +M: Thorsten Winkler <twinkler@linux.ibm.com> L: linux-s390@vger.kernel.org L: netdev@vger.kernel.org S: Supported @@ -19143,7 +19169,7 @@ F: arch/s390/mm S390 NETWORK DRIVERS M: Alexandra Winter <wintera@linux.ibm.com> -M: Wenjia Zhang <wenjia@linux.ibm.com> +M: Thorsten Winkler <twinkler@linux.ibm.com> L: linux-s390@vger.kernel.org L: netdev@vger.kernel.org S: Supported @@ -23002,6 +23028,7 @@ M: Alex Williamson <alex.williamson@redhat.com> L: kvm@vger.kernel.org S: Maintained T: git https://github.com/awilliam/linux-vfio.git +F: Documentation/ABI/testing/debugfs-vfio F: Documentation/ABI/testing/sysfs-devices-vfio-dev F: Documentation/driver-api/vfio.rst F: drivers/vfio/ @@ -23037,6 +23064,13 @@ L: kvm@vger.kernel.org S: Maintained F: drivers/vfio/pci/mlx5/ +VFIO VIRTIO PCI DRIVER +M: Yishai Hadas <yishaih@nvidia.com> +L: kvm@vger.kernel.org +L: virtualization@lists.linux-foundation.org +S: Maintained +F: drivers/vfio/pci/virtio + VFIO PCI DEVICE SPECIFIC DRIVERS R: Jason Gunthorpe <jgg@nvidia.com> R: Yishai Hadas <yishaih@nvidia.com> @@ -155,6 +155,15 @@ endif export KBUILD_EXTMOD +# backward compatibility +KBUILD_EXTRA_WARN ?= $(KBUILD_ENABLE_EXTRA_GCC_CHECKS) + +ifeq ("$(origin W)", "command line") + KBUILD_EXTRA_WARN := $(W) +endif + +export KBUILD_EXTRA_WARN + # Kbuild will save output files in the current working directory. # This does not need to match to the root of the kernel source tree. # @@ -181,14 +190,11 @@ ifeq ("$(origin O)", "command line") endif ifneq ($(KBUILD_OUTPUT),) -# Make's built-in functions such as $(abspath ...), $(realpath ...) cannot -# expand a shell special character '~'. We use a somewhat tedious way here. -abs_objtree := $(shell mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd) -$(if $(abs_objtree),, \ - $(error failed to create output directory "$(KBUILD_OUTPUT)")) - +# $(realpath ...) gets empty if the path does not exist. Run 'mkdir -p' first. +$(shell mkdir -p "$(KBUILD_OUTPUT)") # $(realpath ...) resolves symlinks -abs_objtree := $(realpath $(abs_objtree)) +abs_objtree := $(realpath $(KBUILD_OUTPUT)) +$(if $(abs_objtree),,$(error failed to create output directory "$(KBUILD_OUTPUT)")) endif # ifneq ($(KBUILD_OUTPUT),) ifneq ($(words $(subst :, ,$(abs_srctree))), 1) @@ -609,8 +615,6 @@ export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL KBUILD_RUSTFLAGS_KERNEL export RCS_FIND_IGNORE := \( -name SCCS -o -name BitKeeper -o -name .svn -o \ -name CVS -o -name .pc -o -name .hg -o -name .git \) \ -prune -o -export RCS_TAR_IGNORE := --exclude SCCS --exclude BitKeeper --exclude .svn \ - --exclude CVS --exclude .pc --exclude .hg --exclude .git # =========================================================================== # Rules shared between *config targets and build targets @@ -1662,6 +1666,7 @@ help: @echo ' 1: warnings which may be relevant and do not occur too often' @echo ' 2: warnings which occur quite often but may still be relevant' @echo ' 3: more obscure warnings, can most likely be ignored' + @echo ' c: extra checks in the configuration stage (Kconfig)' @echo ' e: warnings are being treated as errors' @echo ' Multiple levels can be combined with W=12 or W=123' @$(if $(dtstree), \ diff --git a/arch/Kconfig b/arch/Kconfig index 5ca66aad0d08..c91917b50873 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -301,6 +301,11 @@ config ARCH_HAS_DMA_CLEAR_UNCACHED config ARCH_HAS_CPU_FINALIZE_INIT bool +# The architecture has a per-task state that includes the mm's PASID +config ARCH_HAS_CPU_PASID + bool + select IOMMU_MM_DATA + config HAVE_ARCH_THREAD_STRUCT_WHITELIST bool help diff --git a/arch/alpha/kernel/rtc.c b/arch/alpha/kernel/rtc.c index fb3025396ac9..cfdf90bc8b3f 100644 --- a/arch/alpha/kernel/rtc.c +++ b/arch/alpha/kernel/rtc.c @@ -80,7 +80,7 @@ init_rtc_epoch(void) static int alpha_rtc_read_time(struct device *dev, struct rtc_time *tm) { - int ret = mc146818_get_time(tm); + int ret = mc146818_get_time(tm, 10); if (ret < 0) { dev_err_ratelimited(dev, "unable to read current time\n"); diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h index 563af3e75f01..329c94cd45d8 100644 --- a/arch/arc/include/asm/cacheflush.h +++ b/arch/arc/include/asm/cacheflush.h @@ -40,6 +40,7 @@ void dma_cache_wback(phys_addr_t start, unsigned long sz); /* TBD: optimize this */ #define flush_cache_vmap(start, end) flush_cache_all() +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) flush_cache_all() #define flush_cache_dup_mm(mm) /* called on fork (VIVT only) */ diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index 2a7fbbb83b70..197707bc7658 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -91,7 +91,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, * Plug in direct dma map ops. */ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { /* * IOC hardware snoops all DMA traffic keeping the caches consistent diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig index feb38a94c1a7..43bc1255a5db 100644 --- a/arch/arm/configs/mxs_defconfig +++ b/arch/arm/configs/mxs_defconfig @@ -138,7 +138,8 @@ CONFIG_PWM_MXS=y CONFIG_NVMEM_MXS_OCOTP=y CONFIG_EXT4_FS=y # CONFIG_DNOTIFY is not set -CONFIG_FSCACHE=m +CONFIG_NETFS_SUPPORT=m +CONFIG_FSCACHE=y CONFIG_FSCACHE_STATS=y CONFIG_CACHEFILES=m CONFIG_VFAT_FS=y diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index f6181f69577f..1075534b0a2e 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -340,6 +340,8 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end) dsb(ishst); } +#define flush_cache_vmap_early(start, end) do { } while (0) + static inline void flush_cache_vunmap(unsigned long start, unsigned long end) { if (!cache_is_vipt_nonaliasing()) diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c index cfd9c933d2f0..b94850b57995 100644 --- a/arch/arm/mm/dma-mapping-nommu.c +++ b/arch/arm/mm/dma-mapping-nommu.c @@ -34,7 +34,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, } void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { if (IS_ENABLED(CONFIG_CPU_V7M)) { /* diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index d688eac6dbc1..f68db05eba29 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -1710,7 +1710,7 @@ void arm_iommu_detach_device(struct device *dev) EXPORT_SYMBOL_GPL(arm_iommu_detach_device); static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { struct dma_iommu_mapping *mapping; @@ -1745,7 +1745,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev) #else static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { } @@ -1754,7 +1754,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev) { } #endif /* CONFIG_ARM_DMA_USE_IOMMU */ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { /* * Due to legacy code that sets the ->dma_coherent flag from a bus @@ -1773,8 +1773,8 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, if (dev->dma_ops) return; - if (iommu) - arm_setup_iommu_dma_ops(dev, dma_base, size, iommu, coherent); + if (device_iommu_mapped(dev)) + arm_setup_iommu_dma_ops(dev, dma_base, size, coherent); xen_setup_dma_ops(dev); dev->archdata.dma_ops_setup = true; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index ea01a2c43efa..aa7c1d435139 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1039,8 +1039,12 @@ config ARM64_ERRATUM_2645198 If unsure, say Y. +config ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD + bool + config ARM64_ERRATUM_2966298 bool "Cortex-A520: 2966298: workaround for speculatively executed unprivileged load" + select ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD default y help This option adds the workaround for ARM Cortex-A520 erratum 2966298. @@ -1052,6 +1056,20 @@ config ARM64_ERRATUM_2966298 If unsure, say Y. +config ARM64_ERRATUM_3117295 + bool "Cortex-A510: 3117295: workaround for speculatively executed unprivileged load" + select ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD + default y + help + This option adds the workaround for ARM Cortex-A510 erratum 3117295. + + On an affected Cortex-A510 core, a speculatively executed unprivileged + load might leak data from a privileged level via a cache side channel. + + Work around this problem by executing a TLBI before returning to EL0. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 7b1975bf4b90..513787e43329 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -760,32 +760,25 @@ alternative_endif .endm /* - * Check whether preempt/bh-disabled asm code should yield as soon as - * it is able. This is the case if we are currently running in task - * context, and either a softirq is pending, or the TIF_NEED_RESCHED - * flag is set and re-enabling preemption a single time would result in - * a preempt count of zero. (Note that the TIF_NEED_RESCHED flag is - * stored negated in the top word of the thread_info::preempt_count + * Check whether asm code should yield as soon as it is able. This is + * the case if we are currently running in task context, and the + * TIF_NEED_RESCHED flag is set. (Note that the TIF_NEED_RESCHED flag + * is stored negated in the top word of the thread_info::preempt_count * field) */ - .macro cond_yield, lbl:req, tmp:req, tmp2:req + .macro cond_yield, lbl:req, tmp:req, tmp2 +#ifdef CONFIG_PREEMPT_VOLUNTARY get_current_task \tmp ldr \tmp, [\tmp, #TSK_TI_PREEMPT] /* * If we are serving a softirq, there is no point in yielding: the * softirq will not be preempted no matter what we do, so we should - * run to completion as quickly as we can. + * run to completion as quickly as we can. The preempt_count field will + * have BIT(SOFTIRQ_SHIFT) set in this case, so the zero check will + * catch this case too. */ - tbnz \tmp, #SOFTIRQ_SHIFT, .Lnoyield_\@ -#ifdef CONFIG_PREEMPTION - sub \tmp, \tmp, #PREEMPT_DISABLE_OFFSET cbz \tmp, \lbl #endif - adr_l \tmp, irq_stat + IRQ_CPUSTAT_SOFTIRQ_PENDING - get_this_cpu_offset \tmp2 - ldr w\tmp, [\tmp, \tmp2] - cbnz w\tmp, \lbl // yield on pending softirq in task context -.Lnoyield_\@: .endm /* diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h index 50ce8b697ff3..e93548914c36 100644 --- a/arch/arm64/include/asm/irq.h +++ b/arch/arm64/include/asm/irq.h @@ -4,6 +4,8 @@ #ifndef __ASSEMBLER__ +#include <linux/cpumask.h> + #include <asm-generic/irq.h> void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu); diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index d95b3d6b471a..e5d03a7039b4 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -73,7 +73,13 @@ obj-$(CONFIG_ARM64_MTE) += mte.o obj-y += vdso-wrap.o obj-$(CONFIG_COMPAT_VDSO) += vdso32-wrap.o obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS) += patch-scs.o -CFLAGS_patch-scs.o += -mbranch-protection=none + +# We need to prevent the SCS patching code from patching itself. Using +# -mbranch-protection=none here to avoid the patchable PAC opcodes from being +# generated triggers an issue with full LTO on Clang, which stops emitting PAC +# instructions altogether. So instead, omit the unwind tables used by the +# patching code, so it will not be able to locate its own PAC instructions. +CFLAGS_patch-scs.o += -fno-asynchronous-unwind-tables -fno-unwind-tables # Force dependency (vdso*-wrap.S includes vdso.so through incbin) $(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 5ff1942b04fc..5a7dbbe0ce63 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -117,8 +117,6 @@ int main(void) DEFINE(DMA_FROM_DEVICE, DMA_FROM_DEVICE); BLANK(); DEFINE(PREEMPT_DISABLE_OFFSET, PREEMPT_DISABLE_OFFSET); - DEFINE(SOFTIRQ_SHIFT, SOFTIRQ_SHIFT); - DEFINE(IRQ_CPUSTAT_SOFTIRQ_PENDING, offsetof(irq_cpustat_t, __softirq_pending)); BLANK(); DEFINE(CPU_BOOT_TASK, offsetof(struct secondary_data, task)); BLANK(); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index e29e0fea63fb..967c7c7a4e7d 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -416,6 +416,19 @@ static struct midr_range broken_aarch32_aes[] = { }; #endif /* CONFIG_ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE */ +#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD +static const struct midr_range erratum_spec_unpriv_load_list[] = { +#ifdef CONFIG_ARM64_ERRATUM_3117295 + MIDR_ALL_VERSIONS(MIDR_CORTEX_A510), +#endif +#ifdef CONFIG_ARM64_ERRATUM_2966298 + /* Cortex-A520 r0p0 to r0p1 */ + MIDR_REV_RANGE(MIDR_CORTEX_A520, 0, 0, 1), +#endif + {}, +}; +#endif + const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { @@ -713,12 +726,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = { MIDR_FIXED(MIDR_CPU_VAR_REV(1,1), BIT(25)), }, #endif -#ifdef CONFIG_ARM64_ERRATUM_2966298 +#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD { - .desc = "ARM erratum 2966298", - .capability = ARM64_WORKAROUND_2966298, + .desc = "ARM errata 2966298, 3117295", + .capability = ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD, /* Cortex-A520 r0p0 - r0p1 */ - ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A520, 0, 0, 1), + ERRATA_MIDR_RANGE_LIST(erratum_spec_unpriv_load_list), }, #endif #ifdef CONFIG_AMPERE_ERRATUM_AC03_CPU_38 diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index a6030913cd58..7ef0e127b149 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -428,16 +428,9 @@ alternative_else_nop_endif ldp x28, x29, [sp, #16 * 14] .if \el == 0 -alternative_if ARM64_WORKAROUND_2966298 - tlbi vale1, xzr - dsb nsh -alternative_else_nop_endif -alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0 - ldr lr, [sp, #S_LR] - add sp, sp, #PT_REGS_SIZE // restore sp - eret -alternative_else_nop_endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 + alternative_insn "b .L_skip_tramp_exit_\@", nop, ARM64_UNMAP_KERNEL_AT_EL0 + msr far_el1, x29 ldr_this_cpu x30, this_cpu_vector, x29 @@ -446,16 +439,26 @@ alternative_else_nop_endif ldr lr, [sp, #S_LR] // restore x30 add sp, sp, #PT_REGS_SIZE // restore sp br x29 + +.L_skip_tramp_exit_\@: #endif - .else + .endif + ldr lr, [sp, #S_LR] add sp, sp, #PT_REGS_SIZE // restore sp + .if \el == 0 + /* This must be after the last explicit memory access */ +alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD + tlbi vale1, xzr + dsb nsh +alternative_else_nop_endif + .else /* Ensure any device/NC reads complete */ alternative_insn nop, "dmb sy", ARM64_WORKAROUND_1508412 + .endif eret - .endif sb .endm diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 505f389be3e0..a5dc6f764195 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -898,10 +898,8 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, * allocate SVE now in case it is needed for use in streaming * mode. */ - if (system_supports_sve()) { - sve_free(task); - sve_alloc(task, true); - } + sve_free(task); + sve_alloc(task, true); if (free_sme) sme_free(task); @@ -1219,8 +1217,10 @@ void fpsimd_release_task(struct task_struct *dead_task) */ void sme_alloc(struct task_struct *task, bool flush) { - if (task->thread.sme_state && flush) { - memset(task->thread.sme_state, 0, sme_state_size(task)); + if (task->thread.sme_state) { + if (flush) + memset(task->thread.sme_state, 0, + sme_state_size(task)); return; } diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 09bb7fc7d3c2..dc6cf0e37194 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1108,12 +1108,13 @@ static int za_set(struct task_struct *target, } } - /* Allocate/reinit ZA storage */ - sme_alloc(target, true); - if (!target->thread.sme_state) { - ret = -ENOMEM; - goto out; - } + /* + * Only flush the storage if PSTATE.ZA was not already set, + * otherwise preserve any existing data. + */ + sme_alloc(target, !thread_za_enabled(&target->thread)); + if (!target->thread.sme_state) + return -ENOMEM; /* If there is no data then disable ZA */ if (!count) { diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 3cb101e8cb29..61886e43e3a1 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -47,7 +47,7 @@ void arch_teardown_dma_ops(struct device *dev) #endif void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { int cls = cache_line_size_of_cpu(); @@ -58,7 +58,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, ARCH_DMA_MINALIGN, cls); dev->dma_coherent = coherent; - if (iommu) + if (device_iommu_mapped(dev)) iommu_setup_dma_ops(dev, dma_base, dma_base + size - 1); xen_setup_dma_ops(dev); diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 1e07d74d7a6c..b912b1409fc0 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -84,7 +84,6 @@ WORKAROUND_2077057 WORKAROUND_2457168 WORKAROUND_2645198 WORKAROUND_2658417 -WORKAROUND_2966298 WORKAROUND_AMPERE_AC03_CPU_38 WORKAROUND_TRBE_OVERWRITE_FILL_MODE WORKAROUND_TSB_FLUSH_FAILURE @@ -100,3 +99,4 @@ WORKAROUND_NVIDIA_CARMEL_CNP WORKAROUND_QCOM_FALKOR_E1003 WORKAROUND_REPEAT_TLBI WORKAROUND_SPECULATIVE_AT +WORKAROUND_SPECULATIVE_UNPRIV_LOAD diff --git a/arch/csky/abiv1/inc/abi/cacheflush.h b/arch/csky/abiv1/inc/abi/cacheflush.h index 908d8b0bc4fd..d011a81575d2 100644 --- a/arch/csky/abiv1/inc/abi/cacheflush.h +++ b/arch/csky/abiv1/inc/abi/cacheflush.h @@ -43,6 +43,7 @@ static inline void flush_anon_page(struct vm_area_struct *vma, */ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); #define flush_cache_vmap(start, end) cache_wbinv_all() +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) cache_wbinv_all() #define flush_icache_range(start, end) cache_wbinv_range(start, end) diff --git a/arch/csky/abiv2/inc/abi/cacheflush.h b/arch/csky/abiv2/inc/abi/cacheflush.h index 40be16907267..6513ac5d2578 100644 --- a/arch/csky/abiv2/inc/abi/cacheflush.h +++ b/arch/csky/abiv2/inc/abi/cacheflush.h @@ -41,6 +41,7 @@ void flush_icache_mm_range(struct mm_struct *mm, void flush_icache_deferred(struct mm_struct *mm); #define flush_cache_vmap(start, end) do { } while (0) +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) do { } while (0) #define copy_to_user_page(vma, page, vaddr, dst, src, len) \ diff --git a/arch/csky/configs/defconfig b/arch/csky/configs/defconfig index af722e4dfb47..ff559e5162aa 100644 --- a/arch/csky/configs/defconfig +++ b/arch/csky/configs/defconfig @@ -34,7 +34,8 @@ CONFIG_GENERIC_PHY=y CONFIG_EXT4_FS=y CONFIG_FANOTIFY=y CONFIG_QUOTA=y -CONFIG_FSCACHE=m +CONFIG_NETFS_SUPPORT=m +CONFIG_FSCACHE=y CONFIG_FSCACHE_STATS=y CONFIG_CACHEFILES=m CONFIG_MSDOS_FS=y diff --git a/arch/loongarch/Kbuild b/arch/loongarch/Kbuild index beb8499dd8ed..bfa21465d83a 100644 --- a/arch/loongarch/Kbuild +++ b/arch/loongarch/Kbuild @@ -4,6 +4,7 @@ obj-y += net/ obj-y += vdso/ obj-$(CONFIG_KVM) += kvm/ +obj-$(CONFIG_BUILTIN_DTB) += boot/dts/ # for cleaning subdir- += boot diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 15d05dd2b7f3..10959e6c3583 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -142,6 +142,7 @@ config LOONGARCH select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RETHOOK select HAVE_RSEQ + select HAVE_RUST select HAVE_SAMPLE_FTRACE_DIRECT select HAVE_SAMPLE_FTRACE_DIRECT_MULTI select HAVE_SETUP_PER_CPU_AREA if NUMA @@ -376,6 +377,24 @@ config CMDLINE_FORCE endchoice +config BUILTIN_DTB + bool "Enable built-in dtb in kernel" + depends on OF + help + Some existing systems do not provide a canonical device tree to + the kernel at boot time. Let's provide a device tree table in the + kernel, keyed by the dts filename, containing the relevant DTBs. + + Built-in DTBs are generic enough and can be used as references. + +config BUILTIN_DTB_NAME + string "Source file for built-in dtb" + depends on BUILTIN_DTB + help + Base name (without suffix, relative to arch/loongarch/boot/dts/) + for the DTS file that will be used to produce the DTB linked into + the kernel. + config DMI bool "Enable DMI scanning" select DMI_SCAN_MACHINE_NON_EFI_FALLBACK @@ -577,6 +596,9 @@ config ARCH_SELECTS_CRASH_DUMP depends on CRASH_DUMP select RELOCATABLE +config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION + def_bool CRASH_CORE + config RELOCATABLE bool "Relocatable kernel" help diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index 4ba8d67ddb09..983aa2b1629a 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -6,6 +6,7 @@ boot := arch/loongarch/boot KBUILD_DEFCONFIG := loongson3_defconfig +KBUILD_DTBS := dtbs image-name-y := vmlinux image-name-$(CONFIG_EFI_ZBOOT) := vmlinuz @@ -81,8 +82,11 @@ KBUILD_AFLAGS_MODULE += -Wa,-mla-global-with-abs KBUILD_CFLAGS_MODULE += -fplt -Wa,-mla-global-with-abs,-mla-local-with-abs endif +KBUILD_RUSTFLAGS_MODULE += -Crelocation-model=pic + ifeq ($(CONFIG_RELOCATABLE),y) KBUILD_CFLAGS_KERNEL += -fPIE +KBUILD_RUSTFLAGS_KERNEL += -Crelocation-model=pie LDFLAGS_vmlinux += -static -pie --no-dynamic-linker -z notext $(call ld-option, --apply-dynamic-relocs) endif @@ -141,7 +145,7 @@ endif vdso-install-y += arch/loongarch/vdso/vdso.so.dbg -all: $(notdir $(KBUILD_IMAGE)) +all: $(notdir $(KBUILD_IMAGE)) $(KBUILD_DTBS) vmlinuz.efi: vmlinux.efi diff --git a/arch/loongarch/boot/dts/Makefile b/arch/loongarch/boot/dts/Makefile index 5f1f55e911ad..747d0c3f6389 100644 --- a/arch/loongarch/boot/dts/Makefile +++ b/arch/loongarch/boot/dts/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -dtstree := $(srctree)/$(src) -dtb-y := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts)) +dtb-y = loongson-2k0500-ref.dtb loongson-2k1000-ref.dtb loongson-2k2000-ref.dtb + +obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_NAME)) diff --git a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts new file mode 100644 index 000000000000..b38071a4d0b0 --- /dev/null +++ b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 Loongson Technology Corporation Limited + */ + +/dts-v1/; + +#include "loongson-2k0500.dtsi" + +/ { + compatible = "loongson,ls2k0500-ref", "loongson,ls2k0500"; + model = "Loongson-2K0500 Reference Board"; + + aliases { + ethernet0 = &gmac0; + ethernet1 = &gmac1; + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + memory@200000 { + device_type = "memory"; + reg = <0x0 0x00200000 0x0 0x0ee00000>, + <0x0 0x90000000 0x0 0x60000000>; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + linux,cma { + compatible = "shared-dma-pool"; + reusable; + size = <0x0 0x2000000>; + linux,cma-default; + }; + }; +}; + +&gmac0 { + status = "okay"; + + phy-mode = "rgmii"; + bus_id = <0x0>; +}; + +&gmac1 { + status = "okay"; + + phy-mode = "rgmii"; + bus_id = <0x1>; +}; + +&i2c0 { + status = "okay"; + + #address-cells = <1>; + #size-cells = <0>; + eeprom@57{ + compatible = "atmel,24c16"; + reg = <0x57>; + pagesize = <16>; + }; +}; + +&ehci0 { + status = "okay"; +}; + +&ohci0 { + status = "okay"; +}; + +&sata { + status = "okay"; +}; + +&uart0 { + status = "okay"; +}; + +&rtc0 { + status = "okay"; +}; diff --git a/arch/loongarch/boot/dts/loongson-2k0500.dtsi b/arch/loongarch/boot/dts/loongson-2k0500.dtsi new file mode 100644 index 000000000000..444779c21034 --- /dev/null +++ b/arch/loongarch/boot/dts/loongson-2k0500.dtsi @@ -0,0 +1,266 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 Loongson Technology Corporation Limited + */ + +/dts-v1/; + +#include <dt-bindings/interrupt-controller/irq.h> + +/ { + #address-cells = <2>; + #size-cells = <2>; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + compatible = "loongson,la264"; + device_type = "cpu"; + reg = <0x0>; + clocks = <&cpu_clk>; + }; + }; + + cpu_clk: cpu-clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <500000000>; + }; + + cpuintc: interrupt-controller { + compatible = "loongson,cpu-interrupt-controller"; + #interrupt-cells = <1>; + interrupt-controller; + }; + + bus@10000000 { + compatible = "simple-bus"; + ranges = <0x0 0x10000000 0x0 0x10000000 0x0 0x10000000>, + <0x0 0x02000000 0x0 0x02000000 0x0 0x02000000>, + <0x0 0x20000000 0x0 0x20000000 0x0 0x10000000>, + <0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>, + <0xfe 0x0 0xfe 0x0 0x0 0x40000000>; + #address-cells = <2>; + #size-cells = <2>; + + isa@16400000 { + compatible = "isa"; + #size-cells = <1>; + #address-cells = <2>; + ranges = <1 0x0 0x0 0x16400000 0x4000>; + }; + + liointc0: interrupt-controller@1fe11400 { + compatible = "loongson,liointc-2.0"; + reg = <0x0 0x1fe11400 0x0 0x40>, + <0x0 0x1fe11040 0x0 0x8>; + reg-names = "main", "isr0"; + + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&cpuintc>; + interrupts = <2>; + interrupt-names = "int0"; + + loongson,parent_int_map = <0xffffffff>, /* int0 */ + <0x00000000>, /* int1 */ + <0x00000000>, /* int2 */ + <0x00000000>; /* int3 */ + }; + + liointc1: interrupt-controller@1fe11440 { + compatible = "loongson,liointc-2.0"; + reg = <0x0 0x1fe11440 0x0 0x40>, + <0x0 0x1fe11048 0x0 0x8>; + reg-names = "main", "isr0"; + + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&cpuintc>; + interrupts = <4>; + interrupt-names = "int2"; + + loongson,parent_int_map = <0x00000000>, /* int0 */ + <0x00000000>, /* int1 */ + <0xffffffff>, /* int2 */ + <0x00000000>; /* int3 */ + }; + + eiointc: interrupt-controller@1fe11600 { + compatible = "loongson,ls2k0500-eiointc"; + reg = <0x0 0x1fe11600 0x0 0xea00>; + interrupt-controller; + #interrupt-cells = <1>; + interrupt-parent = <&cpuintc>; + interrupts = <3>; + }; + + gmac0: ethernet@1f020000 { + compatible = "snps,dwmac-3.70a"; + reg = <0x0 0x1f020000 0x0 0x10000>; + interrupt-parent = <&liointc0>; + interrupts = <12 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq"; + status = "disabled"; + }; + + gmac1: ethernet@1f030000 { + compatible = "snps,dwmac-3.70a"; + reg = <0x0 0x1f030000 0x0 0x10000>; + interrupt-parent = <&liointc0>; + interrupts = <14 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq"; + status = "disabled"; + }; + + sata: sata@1f040000 { + compatible = "snps,spear-ahci"; + reg = <0x0 0x1f040000 0x0 0x10000>; + interrupt-parent = <&eiointc>; + interrupts = <75>; + status = "disabled"; + }; + + ehci0: usb@1f050000 { + compatible = "generic-ehci"; + reg = <0x0 0x1f050000 0x0 0x8000>; + interrupt-parent = <&eiointc>; + interrupts = <71>; + status = "disabled"; + }; + + ohci0: usb@1f058000 { + compatible = "generic-ohci"; + reg = <0x0 0x1f058000 0x0 0x8000>; + interrupt-parent = <&eiointc>; + interrupts = <72>; + status = "disabled"; + }; + + uart0: serial@1ff40800 { + compatible = "ns16550a"; + reg = <0x0 0x1ff40800 0x0 0x10>; + clock-frequency = <100000000>; + interrupt-parent = <&eiointc>; + interrupts = <2>; + no-loopback-test; + status = "disabled"; + }; + + i2c0: i2c@1ff48000 { + compatible = "loongson,ls2k-i2c"; + reg = <0x0 0x1ff48000 0x0 0x0800>; + interrupt-parent = <&eiointc>; + interrupts = <14>; + status = "disabled"; + }; + + i2c@1ff48800 { + compatible = "loongson,ls2k-i2c"; + reg = <0x0 0x1ff48800 0x0 0x0800>; + interrupt-parent = <&eiointc>; + interrupts = <15>; + status = "disabled"; + }; + + i2c@1ff49000 { + compatible = "loongson,ls2k-i2c"; + reg = <0x0 0x1ff49000 0x0 0x0800>; + interrupt-parent = <&eiointc>; + interrupts = <16>; + status = "disabled"; + }; + + i2c@1ff49800 { + compatible = "loongson,ls2k-i2c"; + reg = <0x0 0x1ff49800 0x0 0x0800>; + interrupt-parent = <&eiointc>; + interrupts = <17>; + status = "disabled"; + }; + + i2c@1ff4a000 { + compatible = "loongson,ls2k-i2c"; + reg = <0x0 0x1ff4a000 0x0 0x0800>; + interrupt-parent = <&eiointc>; + interrupts = <18>; + status = "disabled"; + }; + + i2c@1ff4a800 { + compatible = "loongson,ls2k-i2c"; + reg = <0x0 0x1ff4a800 0x0 0x0800>; + interrupt-parent = <&eiointc>; + interrupts = <19>; + status = "disabled"; + }; + + pmc: power-management@1ff6c000 { + compatible = "loongson,ls2k0500-pmc", "syscon"; + reg = <0x0 0x1ff6c000 0x0 0x58>; + interrupt-parent = <&eiointc>; + interrupts = <56>; + loongson,suspend-address = <0x0 0x1c000500>; + + syscon-reboot { + compatible = "syscon-reboot"; + offset = <0x30>; + mask = <0x1>; + }; + + syscon-poweroff { + compatible = "syscon-poweroff"; + regmap = <&pmc>; + offset = <0x14>; + mask = <0x3c00>; + value = <0x3c00>; + }; + }; + + rtc0: rtc@1ff6c100 { + compatible = "loongson,ls2k0500-rtc", "loongson,ls7a-rtc"; + reg = <0x0 0x1ff6c100 0x0 0x100>; + interrupt-parent = <&eiointc>; + interrupts = <35>; + status = "disabled"; + }; + + pcie@1a000000 { + compatible = "loongson,ls2k-pci"; + reg = <0x0 0x1a000000 0x0 0x02000000>, + <0xfe 0x0 0x0 0x20000000>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + bus-range = <0x0 0x5>; + ranges = <0x01000000 0x0 0x00004000 0x0 0x16404000 0x0 0x00004000>, + <0x02000000 0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>; + + pcie@0,0 { + reg = <0x0000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + interrupt-parent = <&eiointc>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x0 0x0 0x0 0x0>; + interrupt-map = <0x0 0x0 0x0 0x0 &eiointc 81>; + ranges; + }; + + pcie@1,0 { + reg = <0x0800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + interrupt-parent = <&eiointc>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x0 0x0 0x0 0x0>; + interrupt-map = <0x0 0x0 0x0 0x0 &eiointc 82>; + ranges; + }; + }; + }; +}; diff --git a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts new file mode 100644 index 000000000000..132a2d1ea8bc --- /dev/null +++ b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts @@ -0,0 +1,183 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 Loongson Technology Corporation Limited + */ + +/dts-v1/; + +#include "loongson-2k1000.dtsi" + +/ { + compatible = "loongson,ls2k1000-ref", "loongson,ls2k1000"; + model = "Loongson-2K1000 Reference Board"; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + memory@200000 { + device_type = "memory"; + reg = <0x0 0x00200000 0x0 0x06e00000>, + <0x0 0x08000000 0x0 0x07000000>, + <0x0 0x90000000 0x1 0xe0000000>; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + linux,cma { + compatible = "shared-dma-pool"; + reusable; + size = <0x0 0x2000000>; + linux,cma-default; + }; + }; +}; + +&gmac0 { + status = "okay"; + + phy-mode = "rgmii"; + phy-handle = <&phy0>; + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + phy0: ethernet-phy@0 { + reg = <0>; + }; + }; +}; + +&gmac1 { + status = "okay"; + + phy-mode = "rgmii"; + phy-handle = <&phy1>; + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + phy1: ethernet-phy@1 { + reg = <16>; + }; + }; +}; + +&i2c2 { + status = "okay"; + + pinctrl-0 = <&i2c0_pins_default>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + eeprom@57{ + compatible = "atmel,24c16"; + reg = <0x57>; + pagesize = <16>; + }; +}; + +&spi0 { + status = "okay"; + + #address-cells = <1>; + #size-cells = <0>; + spidev@0 { + compatible = "rohm,dh2228fv"; + spi-max-frequency = <100000000>; + reg = <0>; + }; +}; + +&ehci0 { + status = "okay"; +}; + +&ohci0 { + status = "okay"; +}; + +&sata { + status = "okay"; +}; + +&uart0 { + status = "okay"; +}; + +&clk { + status = "okay"; +}; + +&rtc0 { + status = "okay"; +}; + +&pctrl { + status = "okay"; + + sdio_pins_default: sdio-pins { + sdio-pinmux { + groups = "sdio"; + function = "sdio"; + }; + sdio-det-pinmux { + groups = "pwm2"; + function = "gpio"; + }; + }; + + pwm1_pins_default: pwm1-pins { + pinmux { + groups = "pwm1"; + function = "pwm1"; + }; + }; + + pwm0_pins_default: pwm0-pins { + pinmux { + groups = "pwm0"; + function = "pwm0"; + }; + }; + + i2c1_pins_default: i2c1-pins { + pinmux { + groups = "i2c1"; + function = "i2c1"; + }; + }; + + i2c0_pins_default: i2c0-pins { + pinmux { + groups = "i2c0"; + function = "i2c0"; + }; + }; + + nand_pins_default: nand-pins { + pinmux { + groups = "nand"; + function = "nand"; + }; + }; + + hda_pins_default: hda-pins { + grp0-pinmux { + groups = "hda"; + function = "hda"; + }; + grp1-pinmux { + groups = "i2s"; + function = "gpio"; + }; + }; +}; diff --git a/arch/loongarch/boot/dts/loongson-2k1000.dtsi b/arch/loongarch/boot/dts/loongson-2k1000.dtsi new file mode 100644 index 000000000000..49a70f8c3cab --- /dev/null +++ b/arch/loongarch/boot/dts/loongson-2k1000.dtsi @@ -0,0 +1,492 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 Loongson Technology Corporation Limited + */ + +/dts-v1/; + +#include <dt-bindings/interrupt-controller/irq.h> +#include <dt-bindings/clock/loongson,ls2k-clk.h> +#include <dt-bindings/gpio/gpio.h> + +/ { + #address-cells = <2>; + #size-cells = <2>; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + compatible = "loongson,la264"; + device_type = "cpu"; + reg= <0x0>; + clocks = <&clk LOONGSON2_NODE_CLK>; + }; + + cpu1: cpu@1 { + compatible = "loongson,la264"; + device_type = "cpu"; + reg = <0x1>; + clocks = <&clk LOONGSON2_NODE_CLK>; + }; + }; + + ref_100m: clock-ref-100m { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <100000000>; + clock-output-names = "ref_100m"; + }; + + cpuintc: interrupt-controller { + compatible = "loongson,cpu-interrupt-controller"; + #interrupt-cells = <1>; + interrupt-controller; + }; + + /* i2c of the dvi eeprom edid */ + i2c-gpio-0 { + compatible = "i2c-gpio"; + scl-gpios = <&gpio0 0 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + sda-gpios = <&gpio0 1 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + i2c-gpio,delay-us = <5>; /* ~100 kHz */ + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + /* i2c of the eeprom edid */ + i2c-gpio-1 { + compatible = "i2c-gpio"; + scl-gpios = <&gpio0 33 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + sda-gpios = <&gpio0 32 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + i2c-gpio,delay-us = <5>; /* ~100 kHz */ + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + thermal-zones { + cpu-thermal { + polling-delay-passive = <1000>; + polling-delay = <5000>; + thermal-sensors = <&tsensor 0>; + + trips { + cpu_alert: cpu-alert { + temperature = <33000>; + hysteresis = <2000>; + type = "active"; + }; + + cpu_crit: cpu-crit { + temperature = <85000>; + hysteresis = <5000>; + type = "critical"; + }; + }; + }; + }; + + bus@10000000 { + compatible = "simple-bus"; + ranges = <0x0 0x10000000 0x0 0x10000000 0x0 0x10000000>, + <0x0 0x02000000 0x0 0x02000000 0x0 0x02000000>, + <0x0 0x20000000 0x0 0x20000000 0x0 0x10000000>, + <0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>, + <0xfe 0x0 0xfe 0x0 0x0 0x40000000>; + #address-cells = <2>; + #size-cells = <2>; + dma-coherent; + + liointc0: interrupt-controller@1fe01400 { + compatible = "loongson,liointc-2.0"; + reg = <0x0 0x1fe01400 0x0 0x40>, + <0x0 0x1fe01040 0x0 0x8>, + <0x0 0x1fe01140 0x0 0x8>; + reg-names = "main", "isr0", "isr1"; + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&cpuintc>; + interrupts = <2>; + interrupt-names = "int0"; + loongson,parent_int_map = <0xffffffff>, /* int0 */ + <0x00000000>, /* int1 */ + <0x00000000>, /* int2 */ + <0x00000000>; /* int3 */ + }; + + liointc1: interrupt-controller@1fe01440 { + compatible = "loongson,liointc-2.0"; + reg = <0x0 0x1fe01440 0x0 0x40>, + <0x0 0x1fe01048 0x0 0x8>, + <0x0 0x1fe01148 0x0 0x8>; + reg-names = "main", "isr0", "isr1"; + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&cpuintc>; + interrupts = <3>; + interrupt-names = "int1"; + loongson,parent_int_map = <0x00000000>, /* int0 */ + <0xffffffff>, /* int1 */ + <0x00000000>, /* int2 */ + <0x00000000>; /* int3 */ + }; + + chipid@1fe00000 { + compatible = "loongson,ls2k-chipid"; + reg = <0x0 0x1fe00000 0x0 0x30>; + little-endian; + }; + + pctrl: pinctrl@1fe00420 { + compatible = "loongson,ls2k-pinctrl"; + reg = <0x0 0x1fe00420 0x0 0x18>; + status = "disabled"; + }; + + clk: clock-controller@1fe00480 { + compatible = "loongson,ls2k-clk"; + reg = <0x0 0x1fe00480 0x0 0x58>; + #clock-cells = <1>; + clocks = <&ref_100m>; + clock-names = "ref_100m"; + status = "disabled"; + }; + + gpio0: gpio@1fe00500 { + compatible = "loongson,ls2k-gpio"; + reg = <0x0 0x1fe00500 0x0 0x38>; + ngpios = <64>; + #gpio-cells = <2>; + gpio-controller; + gpio-ranges = <&pctrl 0x0 0x0 15>, + <&pctrl 16 16 15>, + <&pctrl 32 32 10>, + <&pctrl 44 44 20>; + interrupt-parent = <&liointc1>; + interrupts = <28 IRQ_TYPE_LEVEL_HIGH>, + <29 IRQ_TYPE_LEVEL_HIGH>, + <30 IRQ_TYPE_LEVEL_HIGH>, + <30 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <>, + <>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>, + <27 IRQ_TYPE_LEVEL_HIGH>; + }; + + tsensor: thermal-sensor@1fe01500 { + compatible = "loongson,ls2k1000-thermal"; + reg = <0x0 0x1fe01500 0x0 0x30>; + interrupt-parent = <&liointc0>; + interrupts = <7 IRQ_TYPE_LEVEL_HIGH>; + #thermal-sensor-cells = <1>; + }; + + dma-controller@1fe00c00 { + compatible = "loongson,ls2k1000-apbdma"; + reg = <0x0 0x1fe00c00 0x0 0x8>; + interrupt-parent = <&liointc1>; + interrupts = <12 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk LOONGSON2_APB_CLK>; + #dma-cells = <1>; + status = "disabled"; + }; + + dma-controller@1fe00c10 { + compatible = "loongson,ls2k1000-apbdma"; + reg = <0x0 0x1fe00c10 0x0 0x8>; + interrupt-parent = <&liointc1>; + interrupts = <13 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk LOONGSON2_APB_CLK>; + #dma-cells = <1>; + status = "disabled"; + }; + + dma-controller@1fe00c20 { + compatible = "loongson,ls2k1000-apbdma"; + reg = <0x0 0x1fe00c20 0x0 0x8>; + interrupt-parent = <&liointc1>; + interrupts = <14 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk LOONGSON2_APB_CLK>; + #dma-cells = <1>; + status = "disabled"; + }; + + dma-controller@1fe00c30 { + compatible = "loongson,ls2k1000-apbdma"; + reg = <0x0 0x1fe00c30 0x0 0x8>; + interrupt-parent = <&liointc1>; + interrupts = <15 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk LOONGSON2_APB_CLK>; + #dma-cells = <1>; + status = "disabled"; + }; + + dma-controller@1fe00c40 { + compatible = "loongson,ls2k1000-apbdma"; + reg = <0x0 0x1fe00c40 0x0 0x8>; + interrupt-parent = <&liointc1>; + interrupts = <16 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk LOONGSON2_APB_CLK>; + #dma-cells = <1>; + status = "disabled"; + }; + + uart0: serial@1fe20000 { + compatible = "ns16550a"; + reg = <0x0 0x1fe20000 0x0 0x10>; + clock-frequency = <125000000>; + interrupt-parent = <&liointc0>; + interrupts = <0x0 IRQ_TYPE_LEVEL_HIGH>; + no-loopback-test; + status = "disabled"; + }; + + i2c2: i2c@1fe21000 { + compatible = "loongson,ls2k-i2c"; + reg = <0x0 0x1fe21000 0x0 0x8>; + interrupt-parent = <&liointc0>; + interrupts = <22 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + i2c3: i2c@1fe21800 { + compatible = "loongson,ls2k-i2c"; + reg = <0x0 0x1fe21800 0x0 0x8>; + interrupt-parent = <&liointc0>; + interrupts = <23 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + pmc: power-management@1fe27000 { + compatible = "loongson,ls2k1000-pmc", "loongson,ls2k0500-pmc", "syscon"; + reg = <0x0 0x1fe27000 0x0 0x58>; + interrupt-parent = <&liointc1>; + interrupts = <11 IRQ_TYPE_LEVEL_HIGH>; + loongson,suspend-address = <0x0 0x1c000500>; + + syscon-reboot { + compatible = "syscon-reboot"; + offset = <0x30>; + mask = <0x1>; + }; + + syscon-poweroff { + compatible = "syscon-poweroff"; + regmap = <&pmc>; + offset = <0x14>; + mask = <0x3c00>; + value = <0x3c00>; + }; + }; + + rtc0: rtc@1fe27800 { + compatible = "loongson,ls2k1000-rtc"; + reg = <0x0 0x1fe27800 0x0 0x100>; + interrupt-parent = <&liointc1>; + interrupts = <8 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + spi0: spi@1fff0220 { + compatible = "loongson,ls2k1000-spi"; + reg = <0x0 0x1fff0220 0x0 0x10>; + clocks = <&clk LOONGSON2_BOOT_CLK>; + status = "disabled"; + }; + + pcie@1a000000 { + compatible = "loongson,ls2k-pci"; + reg = <0x0 0x1a000000 0x0 0x02000000>, + <0xfe 0x0 0x0 0x20000000>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + bus-range = <0x0 0xff>; + ranges = <0x01000000 0x0 0x00008000 0x0 0x18008000 0x0 0x00008000>, + <0x02000000 0x0 0x60000000 0x0 0x60000000 0x0 0x20000000>; + + gmac0: ethernet@3,0 { + reg = <0x1800 0x0 0x0 0x0 0x0>; + interrupt-parent = <&liointc0>; + interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, + <13 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq", "eth_lpi"; + status = "disabled"; + }; + + gmac1: ethernet@3,1 { + reg = <0x1900 0x0 0x0 0x0 0x0>; + interrupt-parent = <&liointc0>; + interrupts = <14 IRQ_TYPE_LEVEL_HIGH>, + <15 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq", "eth_lpi"; + status = "disabled"; + }; + + ehci0: usb@4,1 { + reg = <0x2100 0x0 0x0 0x0 0x0>; + interrupt-parent = <&liointc1>; + interrupts = <18 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + ohci0: usb@4,2 { + reg = <0x2200 0x0 0x0 0x0 0x0>; + interrupt-parent = <&liointc1>; + interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + display@6,0 { + reg = <0x3000 0x0 0x0 0x0 0x0>; + interrupt-parent = <&liointc0>; + interrupts = <28 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + hda@7,0 { + reg = <0x3800 0x0 0x0 0x0 0x0>; + interrupt-parent = <&liointc0>; + interrupts = <4 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + sata: sata@8,0 { + reg = <0x4000 0x0 0x0 0x0 0x0>; + interrupt-parent = <&liointc0>; + interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + pcie@9,0 { + reg = <0x4800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + #interrupt-cells = <1>; + interrupt-map-mask = <0x0 0x0 0x0 0x0>; + interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 0x0 IRQ_TYPE_LEVEL_HIGH>; + ranges; + }; + + pcie@a,0 { + reg = <0x5000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + interrupt-parent = <&liointc1>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x0 0x0 0x0 0x0>; + interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 1 IRQ_TYPE_LEVEL_HIGH>; + ranges; + }; + + pcie@b,0 { + reg = <0x5800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + interrupt-parent = <&liointc1>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x0 0x0 0x0 0x0>; + interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 2 IRQ_TYPE_LEVEL_HIGH>; + ranges; + }; + + pcie@c,0 { + reg = <0x6000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + interrupt-parent = <&liointc1>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x0 0x0 0x0 0x0>; + interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 3 IRQ_TYPE_LEVEL_HIGH>; + ranges; + }; + + pcie@d,0 { + reg = <0x6800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + interrupt-parent = <&liointc1>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x0 0x0 0x0 0x0>; + interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 4 IRQ_TYPE_LEVEL_HIGH>; + ranges; + }; + + pcie@e,0 { + reg = <0x7000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + interrupt-parent = <&liointc1>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x0 0x0 0x0 0x0>; + interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 5 IRQ_TYPE_LEVEL_HIGH>; + ranges; + }; + }; + }; +}; diff --git a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts new file mode 100644 index 000000000000..dca91caf895e --- /dev/null +++ b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 Loongson Technology Corporation Limited + */ + +/dts-v1/; + +#include "loongson-2k2000.dtsi" + +/ { + compatible = "loongson,ls2k2000-ref", "loongson,ls2k2000"; + model = "Loongson-2K2000 Reference Board"; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + memory@200000 { + device_type = "memory"; + reg = <0x0 0x00200000 0x0 0x0ee00000>, + <0x0 0x90000000 0x0 0x70000000>; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + linux,cma { + compatible = "shared-dma-pool"; + reusable; + size = <0x0 0x2000000>; + linux,cma-default; + }; + }; +}; + +&sata { + status = "okay"; +}; + +&uart0 { + status = "okay"; +}; + +&rtc0 { + status = "okay"; +}; + +&xhci0 { + status = "okay"; +}; + +&xhci1 { + status = "okay"; +}; + +&gmac0 { + status = "okay"; +}; + +&gmac1 { + status = "okay"; +}; + +&gmac2 { + status = "okay"; +}; diff --git a/arch/loongarch/boot/dts/loongson-2k2000.dtsi b/arch/loongarch/boot/dts/loongson-2k2000.dtsi new file mode 100644 index 000000000000..a231949b5f55 --- /dev/null +++ b/arch/loongarch/boot/dts/loongson-2k2000.dtsi @@ -0,0 +1,300 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 Loongson Technology Corporation Limited + */ + +/dts-v1/; + +#include <dt-bindings/interrupt-controller/irq.h> + +/ { + #address-cells = <2>; + #size-cells = <2>; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@1 { + compatible = "loongson,la364"; + device_type = "cpu"; + reg = <0x0>; + clocks = <&cpu_clk>; + }; + + cpu1: cpu@2 { + compatible = "loongson,la364"; + device_type = "cpu"; + reg = <0x1>; + clocks = <&cpu_clk>; + }; + }; + + cpu_clk: cpu-clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <1400000000>; + }; + + cpuintc: interrupt-controller { + compatible = "loongson,cpu-interrupt-controller"; + #interrupt-cells = <1>; + interrupt-controller; + }; + + bus@10000000 { + compatible = "simple-bus"; + ranges = <0x0 0x10000000 0x0 0x10000000 0x0 0x10000000>, + <0x0 0x02000000 0x0 0x02000000 0x0 0x02000000>, + <0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>, + <0xfe 0x0 0xfe 0x0 0x0 0x40000000>; + #address-cells = <2>; + #size-cells = <2>; + + pmc: power-management@100d0000 { + compatible = "loongson,ls2k2000-pmc", "loongson,ls2k0500-pmc", "syscon"; + reg = <0x0 0x100d0000 0x0 0x58>; + interrupt-parent = <&eiointc>; + interrupts = <47>; + loongson,suspend-address = <0x0 0x1c000500>; + + syscon-reboot { + compatible = "syscon-reboot"; + offset = <0x30>; + mask = <0x1>; + }; + + syscon-poweroff { + compatible = "syscon-poweroff"; + regmap = <&pmc>; + offset = <0x14>; + mask = <0x3c00>; + value = <0x3c00>; + }; + }; + + liointc: interrupt-controller@1fe01400 { + compatible = "loongson,liointc-1.0"; + reg = <0x0 0x1fe01400 0x0 0x64>; + + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&cpuintc>; + interrupts = <2>; + interrupt-names = "int0"; + loongson,parent_int_map = <0xffffffff>, /* int0 */ + <0x00000000>, /* int1 */ + <0x00000000>, /* int2 */ + <0x00000000>; /* int3 */ + }; + + eiointc: interrupt-controller@1fe01600 { + compatible = "loongson,ls2k2000-eiointc"; + reg = <0x0 0x1fe01600 0x0 0xea00>; + interrupt-controller; + #interrupt-cells = <1>; + interrupt-parent = <&cpuintc>; + interrupts = <3>; + }; + + pic: interrupt-controller@10000000 { + compatible = "loongson,pch-pic-1.0"; + reg = <0x0 0x10000000 0x0 0x400>; + interrupt-controller; + #interrupt-cells = <2>; + loongson,pic-base-vec = <0>; + interrupt-parent = <&eiointc>; + }; + + msi: msi-controller@1fe01140 { + compatible = "loongson,pch-msi-1.0"; + reg = <0x0 0x1fe01140 0x0 0x8>; + msi-controller; + loongson,msi-base-vec = <64>; + loongson,msi-num-vecs = <192>; + interrupt-parent = <&eiointc>; + }; + + rtc0: rtc@100d0100 { + compatible = "loongson,ls2k2000-rtc", "loongson,ls7a-rtc"; + reg = <0x0 0x100d0100 0x0 0x100>; + interrupt-parent = <&pic>; + interrupts = <52 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + uart0: serial@1fe001e0 { + compatible = "ns16550a"; + reg = <0x0 0x1fe001e0 0x0 0x10>; + clock-frequency = <100000000>; + interrupt-parent = <&liointc>; + interrupts = <10 IRQ_TYPE_LEVEL_HIGH>; + no-loopback-test; + status = "disabled"; + }; + + pcie@1a000000 { + compatible = "loongson,ls2k-pci"; + reg = <0x0 0x1a000000 0x0 0x02000000>, + <0xfe 0x0 0x0 0x20000000>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + bus-range = <0x0 0xff>; + ranges = <0x01000000 0x0 0x00008000 0x0 0x18400000 0x0 0x00008000>, + <0x02000000 0x0 0x60000000 0x0 0x60000000 0x0 0x20000000>; + + gmac0: ethernet@3,0 { + reg = <0x1800 0x0 0x0 0x0 0x0>; + interrupts = <12 IRQ_TYPE_LEVEL_HIGH>; + interrupt-parent = <&pic>; + status = "disabled"; + }; + + gmac1: ethernet@3,1 { + reg = <0x1900 0x0 0x0 0x0 0x0>; + interrupts = <14 IRQ_TYPE_LEVEL_HIGH>; + interrupt-parent = <&pic>; + status = "disabled"; + }; + + gmac2: ethernet@3,2 { + reg = <0x1a00 0x0 0x0 0x0 0x0>; + interrupts = <17 IRQ_TYPE_LEVEL_HIGH>; + interrupt-parent = <&pic>; + status = "disabled"; + }; + + xhci0: usb@4,0 { + reg = <0x2000 0x0 0x0 0x0 0x0>; + interrupts = <48 IRQ_TYPE_LEVEL_HIGH>; + interrupt-parent = <&pic>; + status = "disabled"; + }; + + xhci1: usb@19,0 { + reg = <0xc800 0x0 0x0 0x0 0x0>; + interrupts = <22 IRQ_TYPE_LEVEL_HIGH>; + interrupt-parent = <&pic>; + status = "disabled"; + }; + + display@6,1 { + reg = <0x3100 0x0 0x0 0x0 0x0>; + interrupts = <28 IRQ_TYPE_LEVEL_HIGH>; + interrupt-parent = <&pic>; + status = "disabled"; + }; + + hda@7,0 { + reg = <0x3800 0x0 0x0 0x0 0x0>; + interrupts = <58 IRQ_TYPE_LEVEL_HIGH>; + interrupt-parent = <&pic>; + status = "disabled"; + }; + + sata: sata@8,0 { + reg = <0x4000 0x0 0x0 0x0 0x0>; + interrupts = <16 IRQ_TYPE_LEVEL_HIGH>; + interrupt-parent = <&pic>; + status = "disabled"; + }; + + pcie@9,0 { + reg = <0x4800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + interrupt-parent = <&pic>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x0 0x0 0x0 0x0>; + interrupt-map = <0x0 0x0 0x0 0x0 &pic 32 IRQ_TYPE_LEVEL_HIGH>; + ranges; + }; + + pcie@a,0 { + reg = <0x5000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + interrupt-parent = <&pic>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x0 0x0 0x0 0x0>; + interrupt-map = <0x0 0x0 0x0 0x0 &pic 33 IRQ_TYPE_LEVEL_HIGH>; + ranges; + }; + + pcie@b,0 { + reg = <0x5800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + interrupt-parent = <&pic>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x0 0x0 0x0 0x0>; + interrupt-map = <0x0 0x0 0x0 0x0 &pic 34 IRQ_TYPE_LEVEL_HIGH>; + ranges; + }; + + pcie@c,0 { + reg = <0x6000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + interrupt-parent = <&pic>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x0 0x0 0x0 0x0>; + interrupt-map = <0x0 0x0 0x0 0x0 &pic 35 IRQ_TYPE_LEVEL_HIGH>; + ranges; + }; + + pcie@d,0 { + reg = <0x6800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + interrupt-parent = <&pic>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x0 0x0 0x0 0x0>; + interrupt-map = <0x0 0x0 0x0 0x0 &pic 36 IRQ_TYPE_LEVEL_HIGH>; + ranges; + }; + + pcie@e,0 { + reg = <0x7000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + interrupt-parent = <&pic>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x0 0x0 0x0 0x0>; + interrupt-map = <0x0 0x0 0x0 0x0 &pic 37 IRQ_TYPE_LEVEL_HIGH>; + ranges; + }; + + pcie@f,0 { + reg = <0x7800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + interrupt-parent = <&pic>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x0 0x0 0x0 0x0>; + interrupt-map = <0x0 0x0 0x0 0x0 &pic 40 IRQ_TYPE_LEVEL_HIGH>; + ranges; + }; + + pcie@10,0 { + reg = <0x8000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + interrupt-parent = <&pic>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x0 0x0 0x0 0x0>; + interrupt-map = <0x0 0x0 0x0 0x0 &pic 30 IRQ_TYPE_LEVEL_HIGH>; + ranges; + }; + }; + }; +}; diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig index 60e331af9839..f18c2ba871ef 100644 --- a/arch/loongarch/configs/loongson3_defconfig +++ b/arch/loongarch/configs/loongson3_defconfig @@ -6,6 +6,8 @@ CONFIG_HIGH_RES_TIMERS=y CONFIG_BPF_SYSCALL=y CONFIG_BPF_JIT=y CONFIG_PREEMPT=y +CONFIG_PREEMPT_DYNAMIC=y +CONFIG_SCHED_CORE=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_TASKSTATS=y @@ -19,6 +21,7 @@ CONFIG_BLK_CGROUP=y CONFIG_CFS_BANDWIDTH=y CONFIG_RT_GROUP_SCHED=y CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_RDMA=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_HUGETLB=y CONFIG_CPUSETS=y @@ -26,6 +29,7 @@ CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y CONFIG_CGROUP_BPF=y +CONFIG_CGROUP_MISC=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_CHECKPOINT_RESTORE=y @@ -35,6 +39,8 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_KALLSYMS_ALL=y CONFIG_PERF_EVENTS=y +CONFIG_KEXEC=y +CONFIG_CRASH_DUMP=y CONFIG_LOONGARCH=y CONFIG_64BIT=y CONFIG_MACH_LOONGSON64=y @@ -44,13 +50,11 @@ CONFIG_DMI=y CONFIG_EFI=y CONFIG_SMP=y CONFIG_HOTPLUG_CPU=y -CONFIG_NR_CPUS=64 +CONFIG_NR_CPUS=256 CONFIG_NUMA=y CONFIG_CPU_HAS_FPU=y CONFIG_CPU_HAS_LSX=y CONFIG_CPU_HAS_LASX=y -CONFIG_KEXEC=y -CONFIG_CRASH_DUMP=y CONFIG_RANDOMIZE_BASE=y CONFIG_SUSPEND=y CONFIG_HIBERNATION=y @@ -62,10 +66,6 @@ CONFIG_ACPI_IPMI=m CONFIG_ACPI_HOTPLUG_CPU=y CONFIG_ACPI_PCI_SLOT=y CONFIG_ACPI_HOTPLUG_MEMORY=y -CONFIG_EFI_ZBOOT=y -CONFIG_EFI_GENERIC_STUB_INITRD_CMDLINE_LOADER=y -CONFIG_EFI_CAPSULE_LOADER=m -CONFIG_EFI_TEST=m CONFIG_VIRTUALIZATION=y CONFIG_KVM=m CONFIG_JUMP_LABEL=y @@ -74,10 +74,18 @@ CONFIG_MODULE_FORCE_LOAD=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y +CONFIG_BLK_DEV_ZONED=y CONFIG_BLK_DEV_THROTTLING=y +CONFIG_BLK_DEV_THROTTLING_LOW=y +CONFIG_BLK_WBT=y +CONFIG_BLK_CGROUP_IOLATENCY=y +CONFIG_BLK_CGROUP_FC_APPID=y +CONFIG_BLK_CGROUP_IOCOST=y +CONFIG_BLK_CGROUP_IOPRIO=y CONFIG_PARTITION_ADVANCED=y CONFIG_BSD_DISKLABEL=y CONFIG_UNIXWARE_DISKLABEL=y +CONFIG_CMDLINE_PARTITION=y CONFIG_IOSCHED_BFQ=y CONFIG_BFQ_GROUP_IOSCHED=y CONFIG_BINFMT_MISC=m @@ -93,6 +101,8 @@ CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_CMA=y +CONFIG_CMA_SYSFS=y CONFIG_USERFAULTFD=y CONFIG_NET=y CONFIG_PACKET=y @@ -128,6 +138,7 @@ CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y CONFIG_INET6_ESP=m CONFIG_IPV6_MROUTE=y +CONFIG_MPTCP=y CONFIG_NETWORK_PHY_TIMESTAMPING=y CONFIG_NETFILTER=y CONFIG_BRIDGE_NETFILTER=m @@ -352,6 +363,7 @@ CONFIG_PCIEAER=y CONFIG_PCI_IOV=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_SHPC=y +CONFIG_PCI_HOST_GENERIC=y CONFIG_PCCARD=m CONFIG_YENTA=m CONFIG_RAPIDIO=y @@ -365,6 +377,10 @@ CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_FW_LOADER_COMPRESS=y CONFIG_FW_LOADER_COMPRESS_ZSTD=y +CONFIG_EFI_ZBOOT=y +CONFIG_EFI_BOOTLOADER_CONTROL=m +CONFIG_EFI_CAPSULE_LOADER=m +CONFIG_EFI_TEST=m CONFIG_MTD=m CONFIG_MTD_BLOCK=m CONFIG_MTD_CFI=m @@ -586,6 +602,7 @@ CONFIG_RTW89_8852AE=m CONFIG_RTW89_8852CE=m CONFIG_ZD1211RW=m CONFIG_USB_NET_RNDIS_WLAN=m +CONFIG_USB4_NET=m CONFIG_INPUT_MOUSEDEV=y CONFIG_INPUT_MOUSEDEV_PSAUX=y CONFIG_INPUT_EVDEV=y @@ -691,6 +708,9 @@ CONFIG_SND_HDA_CODEC_SIGMATEL=y CONFIG_SND_HDA_CODEC_HDMI=y CONFIG_SND_HDA_CODEC_CONEXANT=y CONFIG_SND_USB_AUDIO=m +CONFIG_SND_SOC=m +CONFIG_SND_SOC_LOONGSON_CARD=m +CONFIG_SND_VIRTIO=m CONFIG_HIDRAW=y CONFIG_UHID=m CONFIG_HID_A4TECH=m @@ -738,6 +758,11 @@ CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_EFI=y CONFIG_RTC_DRV_LOONGSON=y CONFIG_DMADEVICES=y +CONFIG_LS2X_APB_DMA=y +CONFIG_UDMABUF=y +CONFIG_DMABUF_HEAPS=y +CONFIG_DMABUF_HEAPS_SYSTEM=y +CONFIG_DMABUF_HEAPS_CMA=y CONFIG_UIO=m CONFIG_UIO_PDRV_GENIRQ=m CONFIG_UIO_DMEM_GENIRQ=m @@ -778,7 +803,15 @@ CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y CONFIG_DEVFREQ_GOV_PERFORMANCE=y CONFIG_DEVFREQ_GOV_POWERSAVE=y CONFIG_DEVFREQ_GOV_USERSPACE=y +CONFIG_NTB=m +CONFIG_NTB_MSI=y +CONFIG_NTB_IDT=m +CONFIG_NTB_EPF=m +CONFIG_NTB_SWITCHTEC=m +CONFIG_NTB_PERF=m +CONFIG_NTB_TRANSPORT=m CONFIG_PWM=y +CONFIG_USB4=y CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y @@ -797,6 +830,10 @@ CONFIG_GFS2_FS_LOCKING_DLM=y CONFIG_OCFS2_FS=m CONFIG_BTRFS_FS=y CONFIG_BTRFS_FS_POSIX_ACL=y +CONFIG_F2FS_FS=m +CONFIG_F2FS_FS_SECURITY=y +CONFIG_F2FS_CHECK_FS=y +CONFIG_F2FS_FS_COMPRESSION=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA=y @@ -883,7 +920,6 @@ CONFIG_KEY_DH_OPERATIONS=y CONFIG_SECURITY=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y -CONFIG_SECURITY_SELINUX_DISABLE=y CONFIG_SECURITY_APPARMOR=y CONFIG_SECURITY_YAMA=y CONFIG_DEFAULT_SECURITY_DAC=y @@ -914,6 +950,9 @@ CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m CONFIG_CRYPTO_CRC32_LOONGARCH=m CONFIG_CRYPTO_DEV_VIRTIO=m +CONFIG_DMA_CMA=y +CONFIG_DMA_NUMA_CMA=y +CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y CONFIG_STRIP_ASM_SYMS=y CONFIG_MAGIC_SYSRQ=y diff --git a/arch/loongarch/include/asm/bootinfo.h b/arch/loongarch/include/asm/bootinfo.h index c60796869b2b..6d5846dd075c 100644 --- a/arch/loongarch/include/asm/bootinfo.h +++ b/arch/loongarch/include/asm/bootinfo.h @@ -24,13 +24,15 @@ struct loongson_board_info { const char *board_vendor; }; +#define NR_WORDS DIV_ROUND_UP(NR_CPUS, BITS_PER_LONG) + struct loongson_system_configuration { int nr_cpus; int nr_nodes; int boot_cpu_id; int cores_per_node; int cores_per_package; - unsigned long cores_io_master; + unsigned long cores_io_master[NR_WORDS]; unsigned long suspend_addr; const char *cpuname; }; @@ -42,7 +44,7 @@ extern struct loongson_system_configuration loongson_sysconf; static inline bool io_master(int cpu) { - return test_bit(cpu, &loongson_sysconf.cores_io_master); + return test_bit(cpu, loongson_sysconf.cores_io_master); } #endif /* _ASM_BOOTINFO_H */ diff --git a/arch/loongarch/include/asm/crash_core.h b/arch/loongarch/include/asm/crash_core.h new file mode 100644 index 000000000000..218bdbfa527b --- /dev/null +++ b/arch/loongarch/include/asm/crash_core.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _LOONGARCH_CRASH_CORE_H +#define _LOONGARCH_CRASH_CORE_H + +#define CRASH_ALIGN SZ_2M + +#define CRASH_ADDR_LOW_MAX SZ_4G +#define CRASH_ADDR_HIGH_MAX memblock_end_of_DRAM() + +extern phys_addr_t memblock_end_of_DRAM(void); + +#endif diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h index 9b16a3b8e706..f16bd42456e4 100644 --- a/arch/loongarch/include/asm/elf.h +++ b/arch/loongarch/include/asm/elf.h @@ -241,8 +241,6 @@ void loongarch_dump_regs64(u64 *uregs, const struct pt_regs *regs); do { \ current->thread.vdso = &vdso_info; \ \ - loongarch_set_personality_fcsr(state); \ - \ if (personality(current->personality) != PER_LINUX) \ set_personality(PER_LINUX); \ } while (0) @@ -259,7 +257,6 @@ do { \ clear_thread_flag(TIF_32BIT_ADDR); \ \ current->thread.vdso = &vdso_info; \ - loongarch_set_personality_fcsr(state); \ \ p = personality(current->personality); \ if (p != PER_LINUX32 && p != PER_LINUX) \ @@ -340,6 +337,4 @@ extern int arch_elf_pt_proc(void *ehdr, void *phdr, struct file *elf, extern int arch_check_elf(void *ehdr, bool has_interpreter, void *interp_ehdr, struct arch_elf_state *state); -extern void loongarch_set_personality_fcsr(struct arch_elf_state *state); - #endif /* _ASM_ELF_H */ diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h index a11996eb5892..de891c2c83d4 100644 --- a/arch/loongarch/include/asm/ftrace.h +++ b/arch/loongarch/include/asm/ftrace.h @@ -63,7 +63,7 @@ ftrace_regs_get_instruction_pointer(struct ftrace_regs *fregs) static __always_inline void ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip) { - regs_set_return_value(&fregs->regs, ip); + instruction_pointer_set(&fregs->regs, ip); } #define ftrace_regs_get_argument(fregs, n) \ diff --git a/arch/loongarch/include/asm/shmparam.h b/arch/loongarch/include/asm/shmparam.h deleted file mode 100644 index c9554f48d2df..000000000000 --- a/arch/loongarch/include/asm/shmparam.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2020-2022 Loongson Technology Corporation Limited - */ -#ifndef _ASM_SHMPARAM_H -#define _ASM_SHMPARAM_H - -#define __ARCH_FORCE_SHMLBA 1 - -#define SHMLBA SZ_64K /* attach addr a multiple of this */ - -#endif /* _ASM_SHMPARAM_H */ diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c index 8e00a754e548..b6b097bbf866 100644 --- a/arch/loongarch/kernel/acpi.c +++ b/arch/loongarch/kernel/acpi.c @@ -119,7 +119,7 @@ acpi_parse_eio_master(union acpi_subtable_headers *header, const unsigned long e return -EINVAL; core = eiointc->node * CORES_PER_EIO_NODE; - set_bit(core, &(loongson_sysconf.cores_io_master)); + set_bit(core, loongson_sysconf.cores_io_master); return 0; } diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c index acb5d3385675..000825406c1f 100644 --- a/arch/loongarch/kernel/efi.c +++ b/arch/loongarch/kernel/efi.c @@ -140,4 +140,6 @@ void __init efi_init(void) early_memunmap(tbl, sizeof(*tbl)); } + + efi_esrt_init(); } diff --git a/arch/loongarch/kernel/elf.c b/arch/loongarch/kernel/elf.c index 183e94fc9c69..0fa81ced28dc 100644 --- a/arch/loongarch/kernel/elf.c +++ b/arch/loongarch/kernel/elf.c @@ -23,8 +23,3 @@ int arch_check_elf(void *_ehdr, bool has_interpreter, void *_interp_ehdr, { return 0; } - -void loongarch_set_personality_fcsr(struct arch_elf_state *state) -{ - current->thread.fpu.fcsr = boot_cpu_data.fpu_csr0; -} diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c index 6b3bfb0092e6..2f1f5b08638f 100644 --- a/arch/loongarch/kernel/env.c +++ b/arch/loongarch/kernel/env.c @@ -5,13 +5,16 @@ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ #include <linux/acpi.h> +#include <linux/clk.h> #include <linux/efi.h> #include <linux/export.h> #include <linux/memblock.h> +#include <linux/of_clk.h> #include <asm/early_ioremap.h> #include <asm/bootinfo.h> #include <asm/loongson.h> #include <asm/setup.h> +#include <asm/time.h> u64 efi_system_table; struct loongson_system_configuration loongson_sysconf; @@ -36,7 +39,16 @@ void __init init_environ(void) static int __init init_cpu_fullname(void) { - int cpu; + struct device_node *root; + int cpu, ret; + char *model; + + /* Parsing cpuname from DTS model property */ + root = of_find_node_by_path("/"); + ret = of_property_read_string(root, "model", (const char **)&model); + of_node_put(root); + if (ret == 0) + loongson_sysconf.cpuname = strsep(&model, " "); if (loongson_sysconf.cpuname && !strncmp(loongson_sysconf.cpuname, "Loongson", 8)) { for (cpu = 0; cpu < NR_CPUS; cpu++) @@ -46,6 +58,26 @@ static int __init init_cpu_fullname(void) } arch_initcall(init_cpu_fullname); +static int __init fdt_cpu_clk_init(void) +{ + struct clk *clk; + struct device_node *np; + + np = of_get_cpu_node(0, NULL); + if (!np) + return -ENODEV; + + clk = of_clk_get(np, 0); + if (IS_ERR(clk)) + return -ENODEV; + + cpu_clock_freq = clk_get_rate(clk); + clk_put(clk); + + return 0; +} +late_initcall(fdt_cpu_clk_init); + static ssize_t boardinfo_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index 0ecab4216392..c4f7de2e2805 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -74,6 +74,11 @@ SYM_CODE_START(kernel_entry) # kernel entry point la.pcrel t0, fw_arg2 st.d a2, t0, 0 +#ifdef CONFIG_PAGE_SIZE_4KB + li.d t0, 0 + li.d t1, CSR_STFILL + csrxchg t0, t1, LOONGARCH_CSR_IMPCTL1 +#endif /* KSave3 used for percpu base, initialized as 0 */ csrwr zero, PERCPU_BASE_KS /* GPR21 used for percpu base (runtime), initialized as 0 */ @@ -126,6 +131,11 @@ SYM_CODE_START(smpboot_entry) JUMP_VIRT_ADDR t0, t1 +#ifdef CONFIG_PAGE_SIZE_4KB + li.d t0, 0 + li.d t1, CSR_STFILL + csrxchg t0, t1, LOONGARCH_CSR_IMPCTL1 +#endif /* Enable PG */ li.w t0, 0xb0 # PLV=0, IE=0, PG=1 csrwr t0, LOONGARCH_CSR_CRMD diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index 767d94cce0de..f2ff8b5d591e 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -85,6 +85,7 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) regs->csr_euen = euen; lose_fpu(0); lose_lbt(0); + current->thread.fpu.fcsr = boot_cpu_data.fpu_csr0; clear_thread_flag(TIF_LSX_CTX_LIVE); clear_thread_flag(TIF_LASX_CTX_LIVE); diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index d183a745fb85..edf2bba80130 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -252,38 +252,23 @@ static void __init arch_reserve_vmcore(void) #endif } -/* 2MB alignment for crash kernel regions */ -#define CRASH_ALIGN SZ_2M -#define CRASH_ADDR_MAX SZ_4G - -static void __init arch_parse_crashkernel(void) +static void __init arch_reserve_crashkernel(void) { -#ifdef CONFIG_KEXEC int ret; - unsigned long long total_mem; + unsigned long long low_size = 0; unsigned long long crash_base, crash_size; + char *cmdline = boot_command_line; + bool high = false; - total_mem = memblock_phys_mem_size(); - ret = parse_crashkernel(boot_command_line, total_mem, - &crash_size, &crash_base, - NULL, NULL); - if (ret < 0 || crash_size <= 0) + if (!IS_ENABLED(CONFIG_KEXEC_CORE)) return; - if (crash_base <= 0) { - crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, CRASH_ALIGN, CRASH_ADDR_MAX); - if (!crash_base) { - pr_warn("crashkernel reservation failed - No suitable area found.\n"); - return; - } - } else if (!memblock_phys_alloc_range(crash_size, CRASH_ALIGN, crash_base, crash_base + crash_size)) { - pr_warn("Invalid memory region reserved for crash kernel\n"); + ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), + &crash_size, &crash_base, &low_size, &high); + if (ret) return; - } - crashk_res.start = crash_base; - crashk_res.end = crash_base + crash_size - 1; -#endif + reserve_crashkernel_generic(cmdline, crash_size, crash_base, low_size, high); } static void __init fdt_setup(void) @@ -295,8 +280,12 @@ static void __init fdt_setup(void) if (acpi_os_get_root_pointer()) return; - /* Look for a device tree configuration table entry */ - fdt_pointer = efi_fdt_pointer(); + /* Prefer to use built-in dtb, checking its legality first. */ + if (!fdt_check_header(__dtb_start)) + fdt_pointer = __dtb_start; + else + fdt_pointer = efi_fdt_pointer(); /* Fallback to firmware dtb */ + if (!fdt_pointer || fdt_check_header(fdt_pointer)) return; @@ -330,7 +319,9 @@ static void __init bootcmdline_init(char **cmdline_p) if (boot_command_line[0]) strlcat(boot_command_line, " ", COMMAND_LINE_SIZE); - strlcat(boot_command_line, init_command_line, COMMAND_LINE_SIZE); + if (!strstr(boot_command_line, init_command_line)) + strlcat(boot_command_line, init_command_line, COMMAND_LINE_SIZE); + goto out; } #endif @@ -357,7 +348,7 @@ out: void __init platform_init(void) { arch_reserve_vmcore(); - arch_parse_crashkernel(); + arch_reserve_crashkernel(); #ifdef CONFIG_ACPI_TABLE_UPGRADE acpi_table_upgrade(); @@ -467,15 +458,6 @@ static void __init resource_init(void) request_resource(res, &data_resource); request_resource(res, &bss_resource); } - -#ifdef CONFIG_KEXEC - if (crashk_res.start < crashk_res.end) { - insert_resource(&iomem_resource, &crashk_res); - pr_info("Reserving %ldMB of memory at %ldMB for crashkernel\n", - (unsigned long)((crashk_res.end - crashk_res.start + 1) >> 20), - (unsigned long)(crashk_res.start >> 20)); - } -#endif } static int __init add_legacy_isa_io(struct fwnode_handle *fwnode, diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 5bca12d16e06..a16e3dbe9f09 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -208,7 +208,7 @@ static void __init fdt_smp_setup(void) } loongson_sysconf.nr_cpus = num_processors; - set_bit(0, &(loongson_sysconf.cores_io_master)); + set_bit(0, loongson_sysconf.cores_io_master); #endif } @@ -216,6 +216,9 @@ void __init loongson_smp_setup(void) { fdt_smp_setup(); + if (loongson_sysconf.cores_per_package == 0) + loongson_sysconf.cores_per_package = num_processors; + cpu_data[0].core = cpu_logical_map(0) % loongson_sysconf.cores_per_package; cpu_data[0].package = cpu_logical_map(0) / loongson_sysconf.cores_per_package; diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index 4fcd6cd6da23..e73323d759d0 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -201,6 +201,11 @@ bool bpf_jit_supports_kfunc_call(void) return true; } +bool bpf_jit_supports_far_kfunc_call(void) +{ + return true; +} + /* initialized on the first pass of build_body() */ static int out_offset = -1; static int emit_bpf_tail_call(struct jit_ctx *ctx) @@ -465,7 +470,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext const u8 dst = regmap[insn->dst_reg]; const s16 off = insn->off; const s32 imm = insn->imm; - const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm; const bool is32 = BPF_CLASS(insn->code) == BPF_ALU || BPF_CLASS(insn->code) == BPF_JMP32; switch (code) { @@ -923,8 +927,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext /* dst = imm64 */ case BPF_LD | BPF_IMM | BPF_DW: + { + const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm; + move_imm(ctx, dst, imm64, is32); return 1; + } /* dst = *(size *)(src + off) */ case BPF_LDX | BPF_MEM | BPF_B: diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h index ed12358c4783..9a71b0148461 100644 --- a/arch/m68k/include/asm/cacheflush_mm.h +++ b/arch/m68k/include/asm/cacheflush_mm.h @@ -191,6 +191,7 @@ extern void cache_push_v(unsigned long vaddr, int len); #define flush_cache_all() __flush_cache_all() #define flush_cache_vmap(start, end) flush_cache_all() +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) flush_cache_all() static inline void flush_cache_mm(struct mm_struct *mm) diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig index b51f738a39a0..4714074c8bd7 100644 --- a/arch/mips/configs/ip27_defconfig +++ b/arch/mips/configs/ip27_defconfig @@ -287,7 +287,8 @@ CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_QUOTA_NETLINK_INTERFACE=y CONFIG_FUSE_FS=m CONFIG_CUSE=m -CONFIG_FSCACHE=m +CONFIG_NETFS_SUPPORT=m +CONFIG_FSCACHE=y CONFIG_FSCACHE_STATS=y CONFIG_CACHEFILES=m CONFIG_PROC_KCORE=y diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig index 38f17b658421..3389e6e885d9 100644 --- a/arch/mips/configs/lemote2f_defconfig +++ b/arch/mips/configs/lemote2f_defconfig @@ -238,7 +238,8 @@ CONFIG_BTRFS_FS=m CONFIG_QUOTA=y CONFIG_QFMT_V2=m CONFIG_AUTOFS_FS=m -CONFIG_FSCACHE=m +CONFIG_NETFS_SUPPORT=m +CONFIG_FSCACHE=y CONFIG_CACHEFILES=m CONFIG_ISO9660_FS=m CONFIG_JOLIET=y diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig index 07839a4b397e..78f498752066 100644 --- a/arch/mips/configs/loongson3_defconfig +++ b/arch/mips/configs/loongson3_defconfig @@ -356,7 +356,8 @@ CONFIG_QFMT_V2=m CONFIG_AUTOFS_FS=y CONFIG_FUSE_FS=m CONFIG_VIRTIO_FS=m -CONFIG_FSCACHE=m +CONFIG_NETFS_SUPPORT=m +CONFIG_FSCACHE=y CONFIG_ISO9660_FS=m CONFIG_JOLIET=y CONFIG_MSDOS_FS=m diff --git a/arch/mips/configs/pic32mzda_defconfig b/arch/mips/configs/pic32mzda_defconfig index 166d2ad372d1..54774f90c23e 100644 --- a/arch/mips/configs/pic32mzda_defconfig +++ b/arch/mips/configs/pic32mzda_defconfig @@ -68,7 +68,8 @@ CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m -CONFIG_FSCACHE=m +CONFIG_NETFS_SUPPORT=m +CONFIG_FSCACHE=y CONFIG_ISO9660_FS=m CONFIG_JOLIET=y CONFIG_ZISOFS=y diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h index f36c2519ed97..1f14132b3fc9 100644 --- a/arch/mips/include/asm/cacheflush.h +++ b/arch/mips/include/asm/cacheflush.h @@ -97,6 +97,8 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end) __flush_cache_vmap(); } +#define flush_cache_vmap_early(start, end) do { } while (0) + extern void (*__flush_cache_vunmap)(void); static inline void flush_cache_vunmap(unsigned long start, unsigned long end) diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c index 3c4fc97b9f39..0f3cec663a12 100644 --- a/arch/mips/mm/dma-noncoherent.c +++ b/arch/mips/mm/dma-noncoherent.c @@ -138,7 +138,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { dev->dma_coherent = coherent; } diff --git a/arch/nios2/include/asm/cacheflush.h b/arch/nios2/include/asm/cacheflush.h index 348cea097792..81484a776b33 100644 --- a/arch/nios2/include/asm/cacheflush.h +++ b/arch/nios2/include/asm/cacheflush.h @@ -38,6 +38,7 @@ void flush_icache_pages(struct vm_area_struct *vma, struct page *page, #define flush_icache_pages flush_icache_pages #define flush_cache_vmap(start, end) flush_dcache_range(start, end) +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) flush_dcache_range(start, end) extern void copy_to_user_page(struct vm_area_struct *vma, struct page *page, diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index b4006f2a9705..ba4c05bc24d6 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -41,6 +41,7 @@ void flush_kernel_vmap_range(void *vaddr, int size); void invalidate_kernel_vmap_range(void *vaddr, int size); #define flush_cache_vmap(start, end) flush_cache_all() +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) flush_cache_all() void flush_dcache_folio(struct folio *folio); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index c729f60eaa00..b549499eb363 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -416,7 +416,9 @@ config NUMA depends on SMP && MMU select ARCH_SUPPORTS_NUMA_BALANCING select GENERIC_ARCH_NUMA + select HAVE_SETUP_PER_CPU_AREA select NEED_PER_CPU_EMBED_FIRST_CHUNK + select NEED_PER_CPU_PAGE_FIRST_CHUNK select OF_NUMA select USE_PERCPU_NUMA_NODE_ID help diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index 3cb53c4df27c..a129dac4521d 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -37,7 +37,8 @@ static inline void flush_dcache_page(struct page *page) flush_icache_mm(vma->vm_mm, 0) #ifdef CONFIG_64BIT -#define flush_cache_vmap(start, end) flush_tlb_kernel_range(start, end) +#define flush_cache_vmap(start, end) flush_tlb_kernel_range(start, end) +#define flush_cache_vmap_early(start, end) local_flush_tlb_kernel_range(start, end) #endif #ifndef CONFIG_SMP diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h index 8f3418c5f172..a60416bbe190 100644 --- a/arch/riscv/include/asm/tlbflush.h +++ b/arch/riscv/include/asm/tlbflush.h @@ -41,6 +41,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr); void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); void flush_tlb_kernel_range(unsigned long start, unsigned long end); +void local_flush_tlb_kernel_range(unsigned long start, unsigned long end); #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c index 4e4e469b8dd6..843107f834b2 100644 --- a/arch/riscv/mm/dma-noncoherent.c +++ b/arch/riscv/mm/dma-noncoherent.c @@ -129,7 +129,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size) } void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { WARN_TAINT(!coherent && riscv_cbom_block_size > ARCH_DMA_MINALIGN, TAINT_CPU_OUT_OF_SPEC, diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index e96251853037..c301c8d291d2 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -441,6 +441,14 @@ static void __init kasan_shallow_populate(void *start, void *end) kasan_shallow_populate_pgd(vaddr, vend); } +#ifdef CONFIG_KASAN_VMALLOC +void __init kasan_populate_early_vm_area_shadow(void *start, unsigned long size) +{ + kasan_populate(kasan_mem_to_shadow(start), + kasan_mem_to_shadow(start + size)); +} +#endif + static void __init create_tmp_mapping(void) { void *ptr; diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c index e6659d7368b3..8aadc5f71c93 100644 --- a/arch/riscv/mm/tlbflush.c +++ b/arch/riscv/mm/tlbflush.c @@ -66,6 +66,11 @@ static inline void local_flush_tlb_range_asid(unsigned long start, local_flush_tlb_range_threshold_asid(start, size, stride, asid); } +void local_flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + local_flush_tlb_range_asid(start, end, PAGE_SIZE, FLUSH_TLB_NO_ASID); +} + static void __ipi_flush_tlb_all(void *info) { local_flush_tlb_all(); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8f39f0424796..fe565f3a3a91 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -216,7 +216,6 @@ config S390 select HAVE_VIRT_CPU_ACCOUNTING_IDLE select IOMMU_HELPER if PCI select IOMMU_SUPPORT if PCI - select KEXEC select MMU_GATHER_MERGE_VMAS select MMU_GATHER_NO_GATHER select MMU_GATHER_RCU_TABLE_FREE @@ -443,7 +442,7 @@ config COMMAND_LINE_SIZE line. config COMPAT - def_bool y + def_bool n prompt "Kernel support for 31 bit emulation" select ARCH_WANT_OLD_COMPAT_IPC select COMPAT_OLD_SIGACTION @@ -454,7 +453,9 @@ config COMPAT Select this option if you want to enable your system kernel to handle system-calls from ELF binaries for 31 bit ESA. This option (and some other stuff like libraries and such) is needed for - executing 31 bit applications. It is safe to say "Y". + executing 31 bit applications. + + If unsure say N. config SMP def_bool y diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 85490d9373fc..cae2dd34fbb4 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -40,6 +40,7 @@ CONFIG_SCHED_AUTOGROUP=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set CONFIG_PROFILING=y +CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y CONFIG_CRASH_DUMP=y @@ -636,8 +637,9 @@ CONFIG_FUSE_FS=y CONFIG_CUSE=m CONFIG_VIRTIO_FS=m CONFIG_OVERLAY_FS=m +CONFIG_NETFS_SUPPORT=m CONFIG_NETFS_STATS=y -CONFIG_FSCACHE=m +CONFIG_FSCACHE=y CONFIG_CACHEFILES=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index fb690fbbf54b..42b988873e54 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -38,6 +38,7 @@ CONFIG_SCHED_AUTOGROUP=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set CONFIG_PROFILING=y +CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y CONFIG_CRASH_DUMP=y @@ -621,8 +622,9 @@ CONFIG_FUSE_FS=y CONFIG_CUSE=m CONFIG_VIRTIO_FS=m CONFIG_OVERLAY_FS=m +CONFIG_NETFS_SUPPORT=m CONFIG_NETFS_STATS=y -CONFIG_FSCACHE=m +CONFIG_FSCACHE=y CONFIG_CACHEFILES=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 47028450eee1..30d2a1687665 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -10,7 +10,6 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_CRASH_DUMP=y CONFIG_MARCH_Z13=y -# CONFIG_COMPAT is not set CONFIG_NR_CPUS=2 CONFIG_HZ_100=y # CONFIG_CHSC_SCH is not set diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h index 287bb88f7698..2686bee800e3 100644 --- a/arch/s390/include/asm/pci_io.h +++ b/arch/s390/include/asm/pci_io.h @@ -11,6 +11,8 @@ /* I/O size constraints */ #define ZPCI_MAX_READ_SIZE 8 #define ZPCI_MAX_WRITE_SIZE 128 +#define ZPCI_BOUNDARY_SIZE (1 << 12) +#define ZPCI_BOUNDARY_MASK (ZPCI_BOUNDARY_SIZE - 1) /* I/O Map */ #define ZPCI_IOMAP_SHIFT 48 @@ -125,16 +127,18 @@ out: int zpci_write_block(volatile void __iomem *dst, const void *src, unsigned long len); -static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max) +static inline int zpci_get_max_io_size(u64 src, u64 dst, int len, int max) { - int count = len > max ? max : len, size = 1; + int offset = dst & ZPCI_BOUNDARY_MASK; + int size; - while (!(src & 0x1) && !(dst & 0x1) && ((size << 1) <= count)) { - dst = dst >> 1; - src = src >> 1; - size = size << 1; - } - return size; + size = min3(len, ZPCI_BOUNDARY_SIZE - offset, max); + if (IS_ALIGNED(src, 8) && IS_ALIGNED(dst, 8) && IS_ALIGNED(size, 8)) + return size; + + if (size >= 8) + return 8; + return rounddown_pow_of_two(size); } static inline int zpci_memcpy_fromio(void *dst, @@ -144,9 +148,9 @@ static inline int zpci_memcpy_fromio(void *dst, int size, rc = 0; while (n > 0) { - size = zpci_get_max_write_size((u64 __force) src, - (u64) dst, n, - ZPCI_MAX_READ_SIZE); + size = zpci_get_max_io_size((u64 __force) src, + (u64) dst, n, + ZPCI_MAX_READ_SIZE); rc = zpci_read_single(dst, src, size); if (rc) break; @@ -166,9 +170,9 @@ static inline int zpci_memcpy_toio(volatile void __iomem *dst, return -EINVAL; while (n > 0) { - size = zpci_get_max_write_size((u64 __force) dst, - (u64) src, n, - ZPCI_MAX_WRITE_SIZE); + size = zpci_get_max_io_size((u64 __force) dst, + (u64) src, n, + ZPCI_MAX_WRITE_SIZE); if (size > 8) /* main path */ rc = zpci_write_block(dst, src, size); else diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c index 9e7c15fccfea..a4f3449cc814 100644 --- a/arch/s390/kernel/fpu.c +++ b/arch/s390/kernel/fpu.c @@ -208,7 +208,6 @@ void __load_fpu_regs(void) } clear_cpu_flag(CIF_FPU); } -EXPORT_SYMBOL(__load_fpu_regs); void load_fpu_regs(void) { diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c index 39a91b00438a..bf8a672b15a4 100644 --- a/arch/s390/kernel/perf_pai_crypto.c +++ b/arch/s390/kernel/perf_pai_crypto.c @@ -111,11 +111,11 @@ static void paicrypt_event_destroy(struct perf_event *event) mutex_unlock(&pai_reserve_mutex); } -static u64 paicrypt_getctr(struct paicrypt_map *cpump, int nr, bool kernel) +static u64 paicrypt_getctr(unsigned long *page, int nr, bool kernel) { if (kernel) nr += PAI_CRYPTO_MAXCTR; - return cpump->page[nr]; + return page[nr]; } /* Read the counter values. Return value from location in CMP. For event @@ -129,13 +129,13 @@ static u64 paicrypt_getdata(struct perf_event *event, bool kernel) int i; if (event->attr.config != PAI_CRYPTO_BASE) { - return paicrypt_getctr(cpump, + return paicrypt_getctr(cpump->page, event->attr.config - PAI_CRYPTO_BASE, kernel); } for (i = 1; i <= paicrypt_cnt; i++) { - u64 val = paicrypt_getctr(cpump, i, kernel); + u64 val = paicrypt_getctr(cpump->page, i, kernel); if (!val) continue; @@ -317,10 +317,14 @@ static void paicrypt_start(struct perf_event *event, int flags) * Events are added, deleted and re-added when 2 or more events * are active at the same time. */ - if (!event->hw.last_tag) { - event->hw.last_tag = 1; - sum = paicrypt_getall(event); /* Get current value */ - local64_set(&event->hw.prev_count, sum); + if (!event->attr.sample_period) { /* Counting */ + if (!event->hw.last_tag) { + event->hw.last_tag = 1; + sum = paicrypt_getall(event); /* Get current value */ + local64_set(&event->hw.prev_count, sum); + } + } else { /* Sampling */ + perf_sched_cb_inc(event->pmu); } } @@ -336,19 +340,18 @@ static int paicrypt_add(struct perf_event *event, int flags) local_ctl_set_bit(0, CR0_CRYPTOGRAPHY_COUNTER_BIT); } cpump->event = event; - if (flags & PERF_EF_START && !event->attr.sample_period) { - /* Only counting needs initial counter value */ + if (flags & PERF_EF_START) paicrypt_start(event, PERF_EF_RELOAD); - } event->hw.state = 0; - if (event->attr.sample_period) - perf_sched_cb_inc(event->pmu); return 0; } static void paicrypt_stop(struct perf_event *event, int flags) { - paicrypt_read(event); + if (!event->attr.sample_period) /* Counting */ + paicrypt_read(event); + else /* Sampling */ + perf_sched_cb_dec(event->pmu); event->hw.state = PERF_HES_STOPPED; } @@ -357,11 +360,7 @@ static void paicrypt_del(struct perf_event *event, int flags) struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr); struct paicrypt_map *cpump = mp->mapptr; - if (event->attr.sample_period) - perf_sched_cb_dec(event->pmu); - if (!event->attr.sample_period) - /* Only counting needs to read counter */ - paicrypt_stop(event, PERF_EF_UPDATE); + paicrypt_stop(event, PERF_EF_UPDATE); if (--cpump->active_events == 0) { local_ctl_clear_bit(0, CR0_CRYPTOGRAPHY_COUNTER_BIT); WRITE_ONCE(S390_lowcore.ccd, 0); @@ -373,8 +372,7 @@ static void paicrypt_del(struct perf_event *event, int flags) * 2 bytes: Number of counter * 8 bytes: Value of counter */ -static size_t paicrypt_copy(struct pai_userdata *userdata, - struct paicrypt_map *cpump, +static size_t paicrypt_copy(struct pai_userdata *userdata, unsigned long *page, bool exclude_user, bool exclude_kernel) { int i, outidx = 0; @@ -383,9 +381,9 @@ static size_t paicrypt_copy(struct pai_userdata *userdata, u64 val = 0; if (!exclude_kernel) - val += paicrypt_getctr(cpump, i, true); + val += paicrypt_getctr(page, i, true); if (!exclude_user) - val += paicrypt_getctr(cpump, i, false); + val += paicrypt_getctr(page, i, false); if (val) { userdata[outidx].num = i; userdata[outidx].value = val; @@ -395,25 +393,14 @@ static size_t paicrypt_copy(struct pai_userdata *userdata, return outidx * sizeof(struct pai_userdata); } -static int paicrypt_push_sample(void) +static int paicrypt_push_sample(size_t rawsize, struct paicrypt_map *cpump, + struct perf_event *event) { - struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr); - struct paicrypt_map *cpump = mp->mapptr; - struct perf_event *event = cpump->event; struct perf_sample_data data; struct perf_raw_record raw; struct pt_regs regs; - size_t rawsize; int overflow; - if (!cpump->event) /* No event active */ - return 0; - rawsize = paicrypt_copy(cpump->save, cpump, - cpump->event->attr.exclude_user, - cpump->event->attr.exclude_kernel); - if (!rawsize) /* No incremented counters */ - return 0; - /* Setup perf sample */ memset(®s, 0, sizeof(regs)); memset(&raw, 0, sizeof(raw)); @@ -444,6 +431,25 @@ static int paicrypt_push_sample(void) return overflow; } +/* Check if there is data to be saved on schedule out of a task. */ +static int paicrypt_have_sample(void) +{ + struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr); + struct paicrypt_map *cpump = mp->mapptr; + struct perf_event *event = cpump->event; + size_t rawsize; + int rc = 0; + + if (!event) /* No event active */ + return 0; + rawsize = paicrypt_copy(cpump->save, cpump->page, + cpump->event->attr.exclude_user, + cpump->event->attr.exclude_kernel); + if (rawsize) /* No incremented counters */ + rc = paicrypt_push_sample(rawsize, cpump, event); + return rc; +} + /* Called on schedule-in and schedule-out. No access to event structure, * but for sampling only event CRYPTO_ALL is allowed. */ @@ -453,7 +459,7 @@ static void paicrypt_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sch * results on schedule_out and if page was dirty, clear values. */ if (!sched_in) - paicrypt_push_sample(); + paicrypt_have_sample(); } /* Attribute definitions for paicrypt interface. As with other CPU diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c index e7013a2e8960..af7f2b538c8f 100644 --- a/arch/s390/kernel/perf_pai_ext.c +++ b/arch/s390/kernel/perf_pai_ext.c @@ -276,9 +276,9 @@ static int paiext_event_init(struct perf_event *event) return 0; } -static u64 paiext_getctr(struct paiext_map *cpump, int nr) +static u64 paiext_getctr(unsigned long *area, int nr) { - return cpump->area[nr]; + return area[nr]; } /* Read the counter values. Return value from location in buffer. For event @@ -292,10 +292,11 @@ static u64 paiext_getdata(struct perf_event *event) int i; if (event->attr.config != PAI_NNPA_BASE) - return paiext_getctr(cpump, event->attr.config - PAI_NNPA_BASE); + return paiext_getctr(cpump->area, + event->attr.config - PAI_NNPA_BASE); for (i = 1; i <= paiext_cnt; i++) - sum += paiext_getctr(cpump, i); + sum += paiext_getctr(cpump->area, i); return sum; } @@ -320,11 +321,15 @@ static void paiext_start(struct perf_event *event, int flags) { u64 sum; - if (event->hw.last_tag) - return; - event->hw.last_tag = 1; - sum = paiext_getall(event); /* Get current value */ - local64_set(&event->hw.prev_count, sum); + if (!event->attr.sample_period) { /* Counting */ + if (!event->hw.last_tag) { + event->hw.last_tag = 1; + sum = paiext_getall(event); /* Get current value */ + local64_set(&event->hw.prev_count, sum); + } + } else { /* Sampling */ + perf_sched_cb_inc(event->pmu); + } } static int paiext_add(struct perf_event *event, int flags) @@ -341,21 +346,19 @@ static int paiext_add(struct perf_event *event, int flags) debug_sprintf_event(paiext_dbg, 4, "%s 1508 %llx acc %llx\n", __func__, S390_lowcore.aicd, pcb->acc); } - if (flags & PERF_EF_START && !event->attr.sample_period) { - /* Only counting needs initial counter value */ + cpump->event = event; + if (flags & PERF_EF_START) paiext_start(event, PERF_EF_RELOAD); - } event->hw.state = 0; - if (event->attr.sample_period) { - cpump->event = event; - perf_sched_cb_inc(event->pmu); - } return 0; } static void paiext_stop(struct perf_event *event, int flags) { - paiext_read(event); + if (!event->attr.sample_period) /* Counting */ + paiext_read(event); + else /* Sampling */ + perf_sched_cb_dec(event->pmu); event->hw.state = PERF_HES_STOPPED; } @@ -365,12 +368,7 @@ static void paiext_del(struct perf_event *event, int flags) struct paiext_map *cpump = mp->mapptr; struct paiext_cb *pcb = cpump->paiext_cb; - if (event->attr.sample_period) - perf_sched_cb_dec(event->pmu); - if (!event->attr.sample_period) { - /* Only counting needs to read counter */ - paiext_stop(event, PERF_EF_UPDATE); - } + paiext_stop(event, PERF_EF_UPDATE); if (--cpump->active_events == 0) { /* Disable CPU instruction lookup for PAIE1 control block */ local_ctl_clear_bit(0, CR0_PAI_EXTENSION_BIT); @@ -386,13 +384,12 @@ static void paiext_del(struct perf_event *event, int flags) * 2 bytes: Number of counter * 8 bytes: Value of counter */ -static size_t paiext_copy(struct paiext_map *cpump) +static size_t paiext_copy(struct pai_userdata *userdata, unsigned long *area) { - struct pai_userdata *userdata = cpump->save; int i, outidx = 0; for (i = 1; i <= paiext_cnt; i++) { - u64 val = paiext_getctr(cpump, i); + u64 val = paiext_getctr(area, i); if (val) { userdata[outidx].num = i; @@ -418,21 +415,14 @@ static size_t paiext_copy(struct paiext_map *cpump) * sched_task() callback. That callback is not active after paiext_del() * returns and has deleted the event on that CPU. */ -static int paiext_push_sample(void) +static int paiext_push_sample(size_t rawsize, struct paiext_map *cpump, + struct perf_event *event) { - struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr); - struct paiext_map *cpump = mp->mapptr; - struct perf_event *event = cpump->event; struct perf_sample_data data; struct perf_raw_record raw; struct pt_regs regs; - size_t rawsize; int overflow; - rawsize = paiext_copy(cpump); - if (!rawsize) /* No incremented counters */ - return 0; - /* Setup perf sample */ memset(®s, 0, sizeof(regs)); memset(&raw, 0, sizeof(raw)); @@ -461,6 +451,23 @@ static int paiext_push_sample(void) return overflow; } +/* Check if there is data to be saved on schedule out of a task. */ +static int paiext_have_sample(void) +{ + struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr); + struct paiext_map *cpump = mp->mapptr; + struct perf_event *event = cpump->event; + size_t rawsize; + int rc = 0; + + if (!event) + return 0; + rawsize = paiext_copy(cpump->save, cpump->area); + if (rawsize) /* Incremented counters */ + rc = paiext_push_sample(rawsize, cpump, event); + return rc; +} + /* Called on schedule-in and schedule-out. No access to event structure, * but for sampling only event NNPA_ALL is allowed. */ @@ -470,7 +477,7 @@ static void paiext_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched * results on schedule_out and if page was dirty, clear values. */ if (!sched_in) - paiext_push_sample(); + paiext_have_sample(); } /* Attribute definitions for pai extension1 interface. As with other CPU diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 2e6754b62b20..f1897a8bb221 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -917,7 +917,6 @@ static int s390_fpregs_set(struct task_struct *target, else memcpy(&fprs, target->thread.fpu.fprs, sizeof(fprs)); - /* If setting FPC, must validate it first. */ if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) { u32 ufpc[2] = { target->thread.fpu.fpc, 0 }; rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ufpc, diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index ab4098886e56..ac4c78546d97 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -280,7 +280,6 @@ static void do_sigbus(struct pt_regs *regs) static void do_exception(struct pt_regs *regs, int access) { struct vm_area_struct *vma; - struct task_struct *tsk; unsigned long address; struct mm_struct *mm; enum fault_type type; @@ -289,7 +288,6 @@ static void do_exception(struct pt_regs *regs, int access) vm_fault_t fault; bool is_write; - tsk = current; /* * The instruction that caused the program check has * been nullified. Don't signal single step via SIGTRAP. @@ -297,7 +295,7 @@ static void do_exception(struct pt_regs *regs, int access) clear_thread_flag(TIF_PER_TRAP); if (kprobe_page_fault(regs, 14)) return; - mm = tsk->mm; + mm = current->mm; address = get_fault_address(regs); is_write = fault_is_write(regs); type = get_fault_type(regs); diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c index 588089332931..a90499c087f0 100644 --- a/arch/s390/pci/pci_mmio.c +++ b/arch/s390/pci/pci_mmio.c @@ -97,9 +97,9 @@ static inline int __memcpy_toio_inuser(void __iomem *dst, return -EINVAL; while (n > 0) { - size = zpci_get_max_write_size((u64 __force) dst, - (u64 __force) src, n, - ZPCI_MAX_WRITE_SIZE); + size = zpci_get_max_io_size((u64 __force) dst, + (u64 __force) src, n, + ZPCI_MAX_WRITE_SIZE); if (size > 8) /* main path */ rc = __pcistb_mio_inuser(dst, src, size, &status); else @@ -242,9 +242,9 @@ static inline int __memcpy_fromio_inuser(void __user *dst, u8 status; while (n > 0) { - size = zpci_get_max_write_size((u64 __force) src, - (u64 __force) dst, n, - ZPCI_MAX_READ_SIZE); + size = zpci_get_max_io_size((u64 __force) src, + (u64 __force) dst, n, + ZPCI_MAX_READ_SIZE); rc = __pcilg_mio_inuser(dst, src, size, &status); if (rc) break; diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig index cf59b98446e4..7b427c17fbfe 100644 --- a/arch/sh/configs/sdk7786_defconfig +++ b/arch/sh/configs/sdk7786_defconfig @@ -171,7 +171,8 @@ CONFIG_BTRFS_FS=y CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=y CONFIG_CUSE=m -CONFIG_FSCACHE=m +CONFIG_NETFS_SUPPORT=m +CONFIG_FSCACHE=y CONFIG_CACHEFILES=m CONFIG_ISO9660_FS=m CONFIG_JOLIET=y diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h index 878b6b551bd2..51112f54552b 100644 --- a/arch/sh/include/asm/cacheflush.h +++ b/arch/sh/include/asm/cacheflush.h @@ -90,6 +90,7 @@ extern void copy_from_user_page(struct vm_area_struct *vma, unsigned long len); #define flush_cache_vmap(start, end) local_flush_cache_all(NULL) +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) local_flush_cache_all(NULL) #define flush_dcache_mmap_lock(mapping) do { } while (0) diff --git a/arch/sparc/include/asm/cacheflush_32.h b/arch/sparc/include/asm/cacheflush_32.h index f3b7270bf71b..9fee0ccfccb8 100644 --- a/arch/sparc/include/asm/cacheflush_32.h +++ b/arch/sparc/include/asm/cacheflush_32.h @@ -48,6 +48,7 @@ static inline void flush_dcache_page(struct page *page) #define flush_dcache_mmap_unlock(mapping) do { } while (0) #define flush_cache_vmap(start, end) flush_cache_all() +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) flush_cache_all() /* When a context switch happens we must flush all user windows so that diff --git a/arch/sparc/include/asm/cacheflush_64.h b/arch/sparc/include/asm/cacheflush_64.h index 0e879004efff..2b1261b77ecd 100644 --- a/arch/sparc/include/asm/cacheflush_64.h +++ b/arch/sparc/include/asm/cacheflush_64.h @@ -75,6 +75,7 @@ void flush_ptrace_access(struct vm_area_struct *, struct page *, #define flush_dcache_mmap_unlock(mapping) do { } while (0) #define flush_cache_vmap(start, end) do { } while (0) +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) do { } while (0) #endif /* !__ASSEMBLY__ */ diff --git a/arch/sparc/kernel/pci_sabre.c b/arch/sparc/kernel/pci_sabre.c index 3c38ca40a22b..a84598568300 100644 --- a/arch/sparc/kernel/pci_sabre.c +++ b/arch/sparc/kernel/pci_sabre.c @@ -13,7 +13,10 @@ #include <linux/export.h> #include <linux/slab.h> #include <linux/interrupt.h> -#include <linux/of_device.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/platform_device.h> +#include <linux/property.h> #include <asm/apb.h> #include <asm/iommu.h> @@ -456,7 +459,6 @@ static void sabre_pbm_init(struct pci_pbm_info *pbm, static const struct of_device_id sabre_match[]; static int sabre_probe(struct platform_device *op) { - const struct of_device_id *match; const struct linux_prom64_registers *pr_regs; struct device_node *dp = op->dev.of_node; struct pci_pbm_info *pbm; @@ -466,8 +468,7 @@ static int sabre_probe(struct platform_device *op) const u32 *vdma; u64 clear_irq; - match = of_match_device(sabre_match, &op->dev); - hummingbird_p = match && (match->data != NULL); + hummingbird_p = (uintptr_t)device_get_match_data(&op->dev); if (!hummingbird_p) { struct device_node *cpu_dp; diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c index 23b47f7fdb1d..5d8dd4949586 100644 --- a/arch/sparc/kernel/pci_schizo.c +++ b/arch/sparc/kernel/pci_schizo.c @@ -11,7 +11,10 @@ #include <linux/slab.h> #include <linux/export.h> #include <linux/interrupt.h> -#include <linux/of_device.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/platform_device.h> +#include <linux/property.h> #include <linux/numa.h> #include <asm/iommu.h> @@ -1459,15 +1462,13 @@ out_err: return err; } -static const struct of_device_id schizo_match[]; static int schizo_probe(struct platform_device *op) { - const struct of_device_id *match; + unsigned long chip_type = (unsigned long)device_get_match_data(&op->dev); - match = of_match_device(schizo_match, &op->dev); - if (!match) + if (!chip_type) return -EINVAL; - return __schizo_init(op, (unsigned long)match->data); + return __schizo_init(op, chip_type); } /* The ordering of this table is very important. Some Tomatillo diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile index d08c3a0443f3..7f5eedf1f5e0 100644 --- a/arch/sparc/vdso/Makefile +++ b/arch/sparc/vdso/Makefile @@ -3,9 +3,6 @@ # Building vDSO images for sparc. # -VDSO64-$(CONFIG_SPARC64) := y -VDSOCOMPAT-$(CONFIG_COMPAT) := y - # files to link into the vdso vobjs-y := vdso-note.o vclock_gettime.o @@ -13,22 +10,15 @@ vobjs-y := vdso-note.o vclock_gettime.o obj-y += vma.o # vDSO images to build -vdso_img-$(VDSO64-y) += 64 -vdso_img-$(VDSOCOMPAT-y) += 32 +obj-$(CONFIG_SPARC64) += vdso-image-64.o +obj-$(CONFIG_COMPAT) += vdso-image-32.o -vobjs := $(foreach F,$(vobjs-y),$(obj)/$F) +vobjs := $(addprefix $(obj)/, $(vobjs-y)) $(obj)/vdso.o: $(obj)/vdso.so targets += vdso.lds $(vobjs-y) - -# Build the vDSO image C files and link them in. -vdso_img_objs := $(vdso_img-y:%=vdso-image-%.o) -vdso_img_cfiles := $(vdso_img-y:%=vdso-image-%.c) -vdso_img_sodbg := $(vdso_img-y:%=vdso%.so.dbg) -obj-y += $(vdso_img_objs) -targets += $(vdso_img_cfiles) -targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so) +targets += $(foreach x, 32 64, vdso-image-$(x).c vdso$(x).so vdso$(x).so.dbg) CPPFLAGS_vdso.lds += -P -C diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 00760fc30843..5edec175b9bf 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -72,6 +72,7 @@ config X86 select ARCH_HAS_CACHE_LINE_SIZE select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION select ARCH_HAS_CPU_FINALIZE_INIT + select ARCH_HAS_CPU_PASID if IOMMU_SVA select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE @@ -1969,6 +1970,11 @@ config INTEL_TDX_HOST depends on CPU_SUP_INTEL depends on X86_64 depends on KVM_INTEL + depends on X86_X2APIC + select ARCH_KEEP_MEMBLOCK + depends on CONTIG_ALLOC + depends on !KEXEC_CORE + depends on X86_MCE help Intel Trust Domain Extensions (TDX) protects guest VMs from malicious host and certain physical attacks. This option enables necessary TDX diff --git a/arch/x86/coco/tdx/tdx-shared.c b/arch/x86/coco/tdx/tdx-shared.c index 78e413269791..1655aa56a0a5 100644 --- a/arch/x86/coco/tdx/tdx-shared.c +++ b/arch/x86/coco/tdx/tdx-shared.c @@ -22,13 +22,13 @@ static unsigned long try_accept_one(phys_addr_t start, unsigned long len, */ switch (pg_level) { case PG_LEVEL_4K: - page_size = 0; + page_size = TDX_PS_4K; break; case PG_LEVEL_2M: - page_size = 1; + page_size = TDX_PS_2M; break; case PG_LEVEL_1G: - page_size = 2; + page_size = TDX_PS_1G; break; default: return 0; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 632c26cdeeda..29cb275a219d 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -198,6 +198,7 @@ #define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ #define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ #define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ +#define X86_FEATURE_TDX_HOST_PLATFORM ( 7*32+ 7) /* Platform supports being a TDX host */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ @@ -499,6 +500,7 @@ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ #define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ #define X86_BUG_GDS X86_BUG(30) /* CPU is affected by Gather Data Sampling */ +#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* CPU may incur #MC if non-TD software does partial write to TDX private memory */ /* BUG word 2 */ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 737a52b89e64..f1bd7b91b3c6 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -541,6 +541,9 @@ #define MSR_RELOAD_PMC0 0x000014c1 #define MSR_RELOAD_FIXED_CTR0 0x00001309 +/* KeyID partitioning between MKTME and TDX */ +#define MSR_IA32_MKTME_KEYID_PARTITIONING 0x00000087 + /* * AMD64 MSRs. Not complete. See the architecture manual for a more * complete list. diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h index ccce7ebd8677..fdfd41511b02 100644 --- a/arch/x86/include/asm/shared/tdx.h +++ b/arch/x86/include/asm/shared/tdx.h @@ -55,6 +55,12 @@ (TDX_RDX | TDX_RBX | TDX_RSI | TDX_RDI | TDX_R8 | TDX_R9 | \ TDX_R10 | TDX_R11 | TDX_R12 | TDX_R13 | TDX_R14 | TDX_R15) +/* TDX supported page sizes from the TDX module ABI. */ +#define TDX_PS_4K 0 +#define TDX_PS_2M 1 +#define TDX_PS_1G 2 +#define TDX_PS_NR (TDX_PS_1G + 1) + #ifndef __ASSEMBLY__ #include <linux/compiler_attributes.h> diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h index f3d5305a60fc..eba178996d84 100644 --- a/arch/x86/include/asm/tdx.h +++ b/arch/x86/include/asm/tdx.h @@ -24,8 +24,16 @@ #define TDX_SEAMCALL_GP (TDX_SW_ERROR | X86_TRAP_GP) #define TDX_SEAMCALL_UD (TDX_SW_ERROR | X86_TRAP_UD) +/* + * TDX module SEAMCALL leaf function error codes + */ +#define TDX_SUCCESS 0ULL +#define TDX_RND_NO_ENTROPY 0x8000020300000000ULL + #ifndef __ASSEMBLY__ +#include <uapi/asm/mce.h> + /* * Used by the #VE exception handler to gather the #VE exception * info from the TDX module. This is a software only structure @@ -83,6 +91,36 @@ static inline long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, u64 __seamcall(u64 fn, struct tdx_module_args *args); u64 __seamcall_ret(u64 fn, struct tdx_module_args *args); u64 __seamcall_saved_ret(u64 fn, struct tdx_module_args *args); +void tdx_init(void); + +#include <asm/archrandom.h> + +typedef u64 (*sc_func_t)(u64 fn, struct tdx_module_args *args); + +static inline u64 sc_retry(sc_func_t func, u64 fn, + struct tdx_module_args *args) +{ + int retry = RDRAND_RETRY_LOOPS; + u64 ret; + + do { + ret = func(fn, args); + } while (ret == TDX_RND_NO_ENTROPY && --retry); + + return ret; +} + +#define seamcall(_fn, _args) sc_retry(__seamcall, (_fn), (_args)) +#define seamcall_ret(_fn, _args) sc_retry(__seamcall_ret, (_fn), (_args)) +#define seamcall_saved_ret(_fn, _args) sc_retry(__seamcall_saved_ret, (_fn), (_args)) +int tdx_cpu_enable(void); +int tdx_enable(void); +const char *tdx_dump_mce_info(struct mce *m); +#else +static inline void tdx_init(void) { } +static inline int tdx_cpu_enable(void) { return -ENODEV; } +static inline int tdx_enable(void) { return -ENODEV; } +static inline const char *tdx_dump_mce_info(struct mce *m) { return NULL; } #endif /* CONFIG_INTEL_TDX_HOST */ #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 94bff381ef20..0b97bcde70c6 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -66,6 +66,7 @@ #include <asm/set_memory.h> #include <asm/traps.h> #include <asm/sev.h> +#include <asm/tdx.h> #include "cpu.h" @@ -1986,6 +1987,7 @@ static __init void identify_boot_cpu(void) setup_cr_pinning(); tsx_init(); + tdx_init(); lkgs_init(); } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index fd5ce12c4f9a..bc39252bc54f 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -53,6 +53,7 @@ #include <asm/mce.h> #include <asm/msr.h> #include <asm/reboot.h> +#include <asm/tdx.h> #include "internal.h" @@ -229,12 +230,20 @@ static void wait_for_panic(void) panic("Panicing machine check CPU died"); } +static const char *mce_dump_aux_info(struct mce *m) +{ + if (boot_cpu_has_bug(X86_BUG_TDX_PW_MCE)) + return tdx_dump_mce_info(m); + + return NULL; +} + static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) { struct llist_node *pending; struct mce_evt_llist *l; int apei_err = 0; - struct page *p; + const char *memmsg; /* * Allow instrumentation around external facilities usage. Not that it @@ -285,6 +294,11 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) } if (exp) pr_emerg(HW_ERR "Machine check: %s\n", exp); + + memmsg = mce_dump_aux_info(final); + if (memmsg) + pr_emerg(HW_ERR "Machine check: %s\n", memmsg); + if (!fake_panic) { if (panic_timeout == 0) panic_timeout = mca_cfg.panic_timeout; @@ -297,6 +311,7 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) */ if (kexec_crash_loaded()) { if (final && (final->status & MCI_STATUS_ADDRV)) { + struct page *p; p = pfn_to_online_page(final->addr >> PAGE_SHIFT); if (p) SetPageHWPoison(p); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 8ff2bf921519..a38d0c93a66e 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -1438,7 +1438,7 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id) memset(&curr_time, 0, sizeof(struct rtc_time)); if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) { - if (unlikely(mc146818_get_time(&curr_time) < 0)) { + if (unlikely(mc146818_get_time(&curr_time, 10) < 0)) { pr_err_ratelimited("unable to read current time from RTC\n"); return IRQ_HANDLED; } diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 1309b9b05338..2e7066980f3e 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -67,7 +67,7 @@ void mach_get_cmos_time(struct timespec64 *now) return; } - if (mc146818_get_time(&tm)) { + if (mc146818_get_time(&tm, 1000)) { pr_err("Unable to read current time from RTC\n"); now->tv_sec = now->tv_nsec = 0; return; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index ec2c21a1844e..84201071dfac 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1031,6 +1031,8 @@ void __init setup_arch(char **cmdline_p) * * Moreover, on machines with SandyBridge graphics or in setups that use * crashkernel the entire 1M is reserved anyway. + * + * Note the host kernel TDX also requires the first 1MB being reserved. */ x86_platform.realmode_reserve(); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index b0737a15c470..c3b2f863acf0 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -566,7 +566,7 @@ static bool fixup_iopl_exception(struct pt_regs *regs) */ static bool try_fixup_enqcmd_gp(void) { -#ifdef CONFIG_IOMMU_SVA +#ifdef CONFIG_ARCH_HAS_CPU_PASID u32 pasid; /* @@ -592,7 +592,7 @@ static bool try_fixup_enqcmd_gp(void) if (!mm_valid_pasid(current->mm)) return false; - pasid = current->mm->pasid; + pasid = mm_get_enqcmd_pasid(current->mm); /* * Did this thread already have its PASID activated? diff --git a/arch/x86/virt/vmx/tdx/Makefile b/arch/x86/virt/vmx/tdx/Makefile index 46ef8f73aebb..90da47eb85ee 100644 --- a/arch/x86/virt/vmx/tdx/Makefile +++ b/arch/x86/virt/vmx/tdx/Makefile @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-y += seamcall.o +obj-y += seamcall.o tdx.o diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c new file mode 100644 index 000000000000..4d6826a76f78 --- /dev/null +++ b/arch/x86/virt/vmx/tdx/tdx.c @@ -0,0 +1,1492 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright(c) 2023 Intel Corporation. + * + * Intel Trusted Domain Extensions (TDX) support + */ + +#define pr_fmt(fmt) "virt/tdx: " fmt + +#include <linux/types.h> +#include <linux/cache.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/printk.h> +#include <linux/cpu.h> +#include <linux/spinlock.h> +#include <linux/percpu-defs.h> +#include <linux/mutex.h> +#include <linux/list.h> +#include <linux/memblock.h> +#include <linux/memory.h> +#include <linux/minmax.h> +#include <linux/sizes.h> +#include <linux/pfn.h> +#include <linux/align.h> +#include <linux/sort.h> +#include <linux/log2.h> +#include <linux/acpi.h> +#include <linux/suspend.h> +#include <linux/acpi.h> +#include <asm/page.h> +#include <asm/special_insns.h> +#include <asm/msr-index.h> +#include <asm/msr.h> +#include <asm/cpufeature.h> +#include <asm/tdx.h> +#include <asm/intel-family.h> +#include <asm/processor.h> +#include <asm/mce.h> +#include "tdx.h" + +static u32 tdx_global_keyid __ro_after_init; +static u32 tdx_guest_keyid_start __ro_after_init; +static u32 tdx_nr_guest_keyids __ro_after_init; + +static DEFINE_PER_CPU(bool, tdx_lp_initialized); + +static struct tdmr_info_list tdx_tdmr_list; + +static enum tdx_module_status_t tdx_module_status; +static DEFINE_MUTEX(tdx_module_lock); + +/* All TDX-usable memory regions. Protected by mem_hotplug_lock. */ +static LIST_HEAD(tdx_memlist); + +typedef void (*sc_err_func_t)(u64 fn, u64 err, struct tdx_module_args *args); + +static inline void seamcall_err(u64 fn, u64 err, struct tdx_module_args *args) +{ + pr_err("SEAMCALL (0x%016llx) failed: 0x%016llx\n", fn, err); +} + +static inline void seamcall_err_ret(u64 fn, u64 err, + struct tdx_module_args *args) +{ + seamcall_err(fn, err, args); + pr_err("RCX 0x%016llx RDX 0x%016llx R08 0x%016llx\n", + args->rcx, args->rdx, args->r8); + pr_err("R09 0x%016llx R10 0x%016llx R11 0x%016llx\n", + args->r9, args->r10, args->r11); +} + +static inline int sc_retry_prerr(sc_func_t func, sc_err_func_t err_func, + u64 fn, struct tdx_module_args *args) +{ + u64 sret = sc_retry(func, fn, args); + + if (sret == TDX_SUCCESS) + return 0; + + if (sret == TDX_SEAMCALL_VMFAILINVALID) + return -ENODEV; + + if (sret == TDX_SEAMCALL_GP) + return -EOPNOTSUPP; + + if (sret == TDX_SEAMCALL_UD) + return -EACCES; + + err_func(fn, sret, args); + return -EIO; +} + +#define seamcall_prerr(__fn, __args) \ + sc_retry_prerr(__seamcall, seamcall_err, (__fn), (__args)) + +#define seamcall_prerr_ret(__fn, __args) \ + sc_retry_prerr(__seamcall_ret, seamcall_err_ret, (__fn), (__args)) + +/* + * Do the module global initialization once and return its result. + * It can be done on any cpu. It's always called with interrupts + * disabled. + */ +static int try_init_module_global(void) +{ + struct tdx_module_args args = {}; + static DEFINE_RAW_SPINLOCK(sysinit_lock); + static bool sysinit_done; + static int sysinit_ret; + + lockdep_assert_irqs_disabled(); + + raw_spin_lock(&sysinit_lock); + + if (sysinit_done) + goto out; + + /* RCX is module attributes and all bits are reserved */ + args.rcx = 0; + sysinit_ret = seamcall_prerr(TDH_SYS_INIT, &args); + + /* + * The first SEAMCALL also detects the TDX module, thus + * it can fail due to the TDX module is not loaded. + * Dump message to let the user know. + */ + if (sysinit_ret == -ENODEV) + pr_err("module not loaded\n"); + + sysinit_done = true; +out: + raw_spin_unlock(&sysinit_lock); + return sysinit_ret; +} + +/** + * tdx_cpu_enable - Enable TDX on local cpu + * + * Do one-time TDX module per-cpu initialization SEAMCALL (and TDX module + * global initialization SEAMCALL if not done) on local cpu to make this + * cpu be ready to run any other SEAMCALLs. + * + * Always call this function via IPI function calls. + * + * Return 0 on success, otherwise errors. + */ +int tdx_cpu_enable(void) +{ + struct tdx_module_args args = {}; + int ret; + + if (!boot_cpu_has(X86_FEATURE_TDX_HOST_PLATFORM)) + return -ENODEV; + + lockdep_assert_irqs_disabled(); + + if (__this_cpu_read(tdx_lp_initialized)) + return 0; + + /* + * The TDX module global initialization is the very first step + * to enable TDX. Need to do it first (if hasn't been done) + * before the per-cpu initialization. + */ + ret = try_init_module_global(); + if (ret) + return ret; + + ret = seamcall_prerr(TDH_SYS_LP_INIT, &args); + if (ret) + return ret; + + __this_cpu_write(tdx_lp_initialized, true); + + return 0; +} +EXPORT_SYMBOL_GPL(tdx_cpu_enable); + +/* + * Add a memory region as a TDX memory block. The caller must make sure + * all memory regions are added in address ascending order and don't + * overlap. + */ +static int add_tdx_memblock(struct list_head *tmb_list, unsigned long start_pfn, + unsigned long end_pfn, int nid) +{ + struct tdx_memblock *tmb; + + tmb = kmalloc(sizeof(*tmb), GFP_KERNEL); + if (!tmb) + return -ENOMEM; + + INIT_LIST_HEAD(&tmb->list); + tmb->start_pfn = start_pfn; + tmb->end_pfn = end_pfn; + tmb->nid = nid; + + /* @tmb_list is protected by mem_hotplug_lock */ + list_add_tail(&tmb->list, tmb_list); + return 0; +} + +static void free_tdx_memlist(struct list_head *tmb_list) +{ + /* @tmb_list is protected by mem_hotplug_lock */ + while (!list_empty(tmb_list)) { + struct tdx_memblock *tmb = list_first_entry(tmb_list, + struct tdx_memblock, list); + + list_del(&tmb->list); + kfree(tmb); + } +} + +/* + * Ensure that all memblock memory regions are convertible to TDX + * memory. Once this has been established, stash the memblock + * ranges off in a secondary structure because memblock is modified + * in memory hotplug while TDX memory regions are fixed. + */ +static int build_tdx_memlist(struct list_head *tmb_list) +{ + unsigned long start_pfn, end_pfn; + int i, nid, ret; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + /* + * The first 1MB is not reported as TDX convertible memory. + * Although the first 1MB is always reserved and won't end up + * to the page allocator, it is still in memblock's memory + * regions. Skip them manually to exclude them as TDX memory. + */ + start_pfn = max(start_pfn, PHYS_PFN(SZ_1M)); + if (start_pfn >= end_pfn) + continue; + + /* + * Add the memory regions as TDX memory. The regions in + * memblock has already guaranteed they are in address + * ascending order and don't overlap. + */ + ret = add_tdx_memblock(tmb_list, start_pfn, end_pfn, nid); + if (ret) + goto err; + } + + return 0; +err: + free_tdx_memlist(tmb_list); + return ret; +} + +static int read_sys_metadata_field(u64 field_id, u64 *data) +{ + struct tdx_module_args args = {}; + int ret; + + /* + * TDH.SYS.RD -- reads one global metadata field + * - RDX (in): the field to read + * - R8 (out): the field data + */ + args.rdx = field_id; + ret = seamcall_prerr_ret(TDH_SYS_RD, &args); + if (ret) + return ret; + + *data = args.r8; + + return 0; +} + +static int read_sys_metadata_field16(u64 field_id, + int offset, + struct tdx_tdmr_sysinfo *ts) +{ + u16 *ts_member = ((void *)ts) + offset; + u64 tmp; + int ret; + + if (WARN_ON_ONCE(MD_FIELD_ID_ELE_SIZE_CODE(field_id) != + MD_FIELD_ID_ELE_SIZE_16BIT)) + return -EINVAL; + + ret = read_sys_metadata_field(field_id, &tmp); + if (ret) + return ret; + + *ts_member = tmp; + + return 0; +} + +struct field_mapping { + u64 field_id; + int offset; +}; + +#define TD_SYSINFO_MAP(_field_id, _offset) \ + { .field_id = MD_FIELD_ID_##_field_id, \ + .offset = offsetof(struct tdx_tdmr_sysinfo, _offset) } + +/* Map TD_SYSINFO fields into 'struct tdx_tdmr_sysinfo': */ +static const struct field_mapping fields[] = { + TD_SYSINFO_MAP(MAX_TDMRS, max_tdmrs), + TD_SYSINFO_MAP(MAX_RESERVED_PER_TDMR, max_reserved_per_tdmr), + TD_SYSINFO_MAP(PAMT_4K_ENTRY_SIZE, pamt_entry_size[TDX_PS_4K]), + TD_SYSINFO_MAP(PAMT_2M_ENTRY_SIZE, pamt_entry_size[TDX_PS_2M]), + TD_SYSINFO_MAP(PAMT_1G_ENTRY_SIZE, pamt_entry_size[TDX_PS_1G]), +}; + +static int get_tdx_tdmr_sysinfo(struct tdx_tdmr_sysinfo *tdmr_sysinfo) +{ + int ret; + int i; + + /* Populate 'tdmr_sysinfo' fields using the mapping structure above: */ + for (i = 0; i < ARRAY_SIZE(fields); i++) { + ret = read_sys_metadata_field16(fields[i].field_id, + fields[i].offset, + tdmr_sysinfo); + if (ret) + return ret; + } + + return 0; +} + +/* Calculate the actual TDMR size */ +static int tdmr_size_single(u16 max_reserved_per_tdmr) +{ + int tdmr_sz; + + /* + * The actual size of TDMR depends on the maximum + * number of reserved areas. + */ + tdmr_sz = sizeof(struct tdmr_info); + tdmr_sz += sizeof(struct tdmr_reserved_area) * max_reserved_per_tdmr; + + return ALIGN(tdmr_sz, TDMR_INFO_ALIGNMENT); +} + +static int alloc_tdmr_list(struct tdmr_info_list *tdmr_list, + struct tdx_tdmr_sysinfo *tdmr_sysinfo) +{ + size_t tdmr_sz, tdmr_array_sz; + void *tdmr_array; + + tdmr_sz = tdmr_size_single(tdmr_sysinfo->max_reserved_per_tdmr); + tdmr_array_sz = tdmr_sz * tdmr_sysinfo->max_tdmrs; + + /* + * To keep things simple, allocate all TDMRs together. + * The buffer needs to be physically contiguous to make + * sure each TDMR is physically contiguous. + */ + tdmr_array = alloc_pages_exact(tdmr_array_sz, + GFP_KERNEL | __GFP_ZERO); + if (!tdmr_array) + return -ENOMEM; + + tdmr_list->tdmrs = tdmr_array; + + /* + * Keep the size of TDMR to find the target TDMR + * at a given index in the TDMR list. + */ + tdmr_list->tdmr_sz = tdmr_sz; + tdmr_list->max_tdmrs = tdmr_sysinfo->max_tdmrs; + tdmr_list->nr_consumed_tdmrs = 0; + + return 0; +} + +static void free_tdmr_list(struct tdmr_info_list *tdmr_list) +{ + free_pages_exact(tdmr_list->tdmrs, + tdmr_list->max_tdmrs * tdmr_list->tdmr_sz); +} + +/* Get the TDMR from the list at the given index. */ +static struct tdmr_info *tdmr_entry(struct tdmr_info_list *tdmr_list, + int idx) +{ + int tdmr_info_offset = tdmr_list->tdmr_sz * idx; + + return (void *)tdmr_list->tdmrs + tdmr_info_offset; +} + +#define TDMR_ALIGNMENT SZ_1G +#define TDMR_ALIGN_DOWN(_addr) ALIGN_DOWN((_addr), TDMR_ALIGNMENT) +#define TDMR_ALIGN_UP(_addr) ALIGN((_addr), TDMR_ALIGNMENT) + +static inline u64 tdmr_end(struct tdmr_info *tdmr) +{ + return tdmr->base + tdmr->size; +} + +/* + * Take the memory referenced in @tmb_list and populate the + * preallocated @tdmr_list, following all the special alignment + * and size rules for TDMR. + */ +static int fill_out_tdmrs(struct list_head *tmb_list, + struct tdmr_info_list *tdmr_list) +{ + struct tdx_memblock *tmb; + int tdmr_idx = 0; + + /* + * Loop over TDX memory regions and fill out TDMRs to cover them. + * To keep it simple, always try to use one TDMR to cover one + * memory region. + * + * In practice TDX supports at least 64 TDMRs. A 2-socket system + * typically only consumes less than 10 of those. This code is + * dumb and simple and may use more TMDRs than is strictly + * required. + */ + list_for_each_entry(tmb, tmb_list, list) { + struct tdmr_info *tdmr = tdmr_entry(tdmr_list, tdmr_idx); + u64 start, end; + + start = TDMR_ALIGN_DOWN(PFN_PHYS(tmb->start_pfn)); + end = TDMR_ALIGN_UP(PFN_PHYS(tmb->end_pfn)); + + /* + * A valid size indicates the current TDMR has already + * been filled out to cover the previous memory region(s). + */ + if (tdmr->size) { + /* + * Loop to the next if the current memory region + * has already been fully covered. + */ + if (end <= tdmr_end(tdmr)) + continue; + + /* Otherwise, skip the already covered part. */ + if (start < tdmr_end(tdmr)) + start = tdmr_end(tdmr); + + /* + * Create a new TDMR to cover the current memory + * region, or the remaining part of it. + */ + tdmr_idx++; + if (tdmr_idx >= tdmr_list->max_tdmrs) { + pr_warn("initialization failed: TDMRs exhausted.\n"); + return -ENOSPC; + } + + tdmr = tdmr_entry(tdmr_list, tdmr_idx); + } + + tdmr->base = start; + tdmr->size = end - start; + } + + /* @tdmr_idx is always the index of the last valid TDMR. */ + tdmr_list->nr_consumed_tdmrs = tdmr_idx + 1; + + /* + * Warn early that kernel is about to run out of TDMRs. + * + * This is an indication that TDMR allocation has to be + * reworked to be smarter to not run into an issue. + */ + if (tdmr_list->max_tdmrs - tdmr_list->nr_consumed_tdmrs < TDMR_NR_WARN) + pr_warn("consumed TDMRs reaching limit: %d used out of %d\n", + tdmr_list->nr_consumed_tdmrs, + tdmr_list->max_tdmrs); + + return 0; +} + +/* + * Calculate PAMT size given a TDMR and a page size. The returned + * PAMT size is always aligned up to 4K page boundary. + */ +static unsigned long tdmr_get_pamt_sz(struct tdmr_info *tdmr, int pgsz, + u16 pamt_entry_size) +{ + unsigned long pamt_sz, nr_pamt_entries; + + switch (pgsz) { + case TDX_PS_4K: + nr_pamt_entries = tdmr->size >> PAGE_SHIFT; + break; + case TDX_PS_2M: + nr_pamt_entries = tdmr->size >> PMD_SHIFT; + break; + case TDX_PS_1G: + nr_pamt_entries = tdmr->size >> PUD_SHIFT; + break; + default: + WARN_ON_ONCE(1); + return 0; + } + + pamt_sz = nr_pamt_entries * pamt_entry_size; + /* TDX requires PAMT size must be 4K aligned */ + pamt_sz = ALIGN(pamt_sz, PAGE_SIZE); + + return pamt_sz; +} + +/* + * Locate a NUMA node which should hold the allocation of the @tdmr + * PAMT. This node will have some memory covered by the TDMR. The + * relative amount of memory covered is not considered. + */ +static int tdmr_get_nid(struct tdmr_info *tdmr, struct list_head *tmb_list) +{ + struct tdx_memblock *tmb; + + /* + * A TDMR must cover at least part of one TMB. That TMB will end + * after the TDMR begins. But, that TMB may have started before + * the TDMR. Find the next 'tmb' that _ends_ after this TDMR + * begins. Ignore 'tmb' start addresses. They are irrelevant. + */ + list_for_each_entry(tmb, tmb_list, list) { + if (tmb->end_pfn > PHYS_PFN(tdmr->base)) + return tmb->nid; + } + + /* + * Fall back to allocating the TDMR's metadata from node 0 when + * no TDX memory block can be found. This should never happen + * since TDMRs originate from TDX memory blocks. + */ + pr_warn("TDMR [0x%llx, 0x%llx): unable to find local NUMA node for PAMT allocation, fallback to use node 0.\n", + tdmr->base, tdmr_end(tdmr)); + return 0; +} + +/* + * Allocate PAMTs from the local NUMA node of some memory in @tmb_list + * within @tdmr, and set up PAMTs for @tdmr. + */ +static int tdmr_set_up_pamt(struct tdmr_info *tdmr, + struct list_head *tmb_list, + u16 pamt_entry_size[]) +{ + unsigned long pamt_base[TDX_PS_NR]; + unsigned long pamt_size[TDX_PS_NR]; + unsigned long tdmr_pamt_base; + unsigned long tdmr_pamt_size; + struct page *pamt; + int pgsz, nid; + + nid = tdmr_get_nid(tdmr, tmb_list); + + /* + * Calculate the PAMT size for each TDX supported page size + * and the total PAMT size. + */ + tdmr_pamt_size = 0; + for (pgsz = TDX_PS_4K; pgsz < TDX_PS_NR; pgsz++) { + pamt_size[pgsz] = tdmr_get_pamt_sz(tdmr, pgsz, + pamt_entry_size[pgsz]); + tdmr_pamt_size += pamt_size[pgsz]; + } + + /* + * Allocate one chunk of physically contiguous memory for all + * PAMTs. This helps minimize the PAMT's use of reserved areas + * in overlapped TDMRs. + */ + pamt = alloc_contig_pages(tdmr_pamt_size >> PAGE_SHIFT, GFP_KERNEL, + nid, &node_online_map); + if (!pamt) + return -ENOMEM; + + /* + * Break the contiguous allocation back up into the + * individual PAMTs for each page size. + */ + tdmr_pamt_base = page_to_pfn(pamt) << PAGE_SHIFT; + for (pgsz = TDX_PS_4K; pgsz < TDX_PS_NR; pgsz++) { + pamt_base[pgsz] = tdmr_pamt_base; + tdmr_pamt_base += pamt_size[pgsz]; + } + + tdmr->pamt_4k_base = pamt_base[TDX_PS_4K]; + tdmr->pamt_4k_size = pamt_size[TDX_PS_4K]; + tdmr->pamt_2m_base = pamt_base[TDX_PS_2M]; + tdmr->pamt_2m_size = pamt_size[TDX_PS_2M]; + tdmr->pamt_1g_base = pamt_base[TDX_PS_1G]; + tdmr->pamt_1g_size = pamt_size[TDX_PS_1G]; + + return 0; +} + +static void tdmr_get_pamt(struct tdmr_info *tdmr, unsigned long *pamt_base, + unsigned long *pamt_size) +{ + unsigned long pamt_bs, pamt_sz; + + /* + * The PAMT was allocated in one contiguous unit. The 4K PAMT + * should always point to the beginning of that allocation. + */ + pamt_bs = tdmr->pamt_4k_base; + pamt_sz = tdmr->pamt_4k_size + tdmr->pamt_2m_size + tdmr->pamt_1g_size; + + WARN_ON_ONCE((pamt_bs & ~PAGE_MASK) || (pamt_sz & ~PAGE_MASK)); + + *pamt_base = pamt_bs; + *pamt_size = pamt_sz; +} + +static void tdmr_do_pamt_func(struct tdmr_info *tdmr, + void (*pamt_func)(unsigned long base, unsigned long size)) +{ + unsigned long pamt_base, pamt_size; + + tdmr_get_pamt(tdmr, &pamt_base, &pamt_size); + + /* Do nothing if PAMT hasn't been allocated for this TDMR */ + if (!pamt_size) + return; + + if (WARN_ON_ONCE(!pamt_base)) + return; + + pamt_func(pamt_base, pamt_size); +} + +static void free_pamt(unsigned long pamt_base, unsigned long pamt_size) +{ + free_contig_range(pamt_base >> PAGE_SHIFT, pamt_size >> PAGE_SHIFT); +} + +static void tdmr_free_pamt(struct tdmr_info *tdmr) +{ + tdmr_do_pamt_func(tdmr, free_pamt); +} + +static void tdmrs_free_pamt_all(struct tdmr_info_list *tdmr_list) +{ + int i; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) + tdmr_free_pamt(tdmr_entry(tdmr_list, i)); +} + +/* Allocate and set up PAMTs for all TDMRs */ +static int tdmrs_set_up_pamt_all(struct tdmr_info_list *tdmr_list, + struct list_head *tmb_list, + u16 pamt_entry_size[]) +{ + int i, ret = 0; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + ret = tdmr_set_up_pamt(tdmr_entry(tdmr_list, i), tmb_list, + pamt_entry_size); + if (ret) + goto err; + } + + return 0; +err: + tdmrs_free_pamt_all(tdmr_list); + return ret; +} + +/* + * Convert TDX private pages back to normal by using MOVDIR64B to + * clear these pages. Note this function doesn't flush cache of + * these TDX private pages. The caller should make sure of that. + */ +static void reset_tdx_pages(unsigned long base, unsigned long size) +{ + const void *zero_page = (const void *)page_address(ZERO_PAGE(0)); + unsigned long phys, end; + + end = base + size; + for (phys = base; phys < end; phys += 64) + movdir64b(__va(phys), zero_page); + + /* + * MOVDIR64B uses WC protocol. Use memory barrier to + * make sure any later user of these pages sees the + * updated data. + */ + mb(); +} + +static void tdmr_reset_pamt(struct tdmr_info *tdmr) +{ + tdmr_do_pamt_func(tdmr, reset_tdx_pages); +} + +static void tdmrs_reset_pamt_all(struct tdmr_info_list *tdmr_list) +{ + int i; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) + tdmr_reset_pamt(tdmr_entry(tdmr_list, i)); +} + +static unsigned long tdmrs_count_pamt_kb(struct tdmr_info_list *tdmr_list) +{ + unsigned long pamt_size = 0; + int i; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + unsigned long base, size; + + tdmr_get_pamt(tdmr_entry(tdmr_list, i), &base, &size); + pamt_size += size; + } + + return pamt_size / 1024; +} + +static int tdmr_add_rsvd_area(struct tdmr_info *tdmr, int *p_idx, u64 addr, + u64 size, u16 max_reserved_per_tdmr) +{ + struct tdmr_reserved_area *rsvd_areas = tdmr->reserved_areas; + int idx = *p_idx; + + /* Reserved area must be 4K aligned in offset and size */ + if (WARN_ON(addr & ~PAGE_MASK || size & ~PAGE_MASK)) + return -EINVAL; + + if (idx >= max_reserved_per_tdmr) { + pr_warn("initialization failed: TDMR [0x%llx, 0x%llx): reserved areas exhausted.\n", + tdmr->base, tdmr_end(tdmr)); + return -ENOSPC; + } + + /* + * Consume one reserved area per call. Make no effort to + * optimize or reduce the number of reserved areas which are + * consumed by contiguous reserved areas, for instance. + */ + rsvd_areas[idx].offset = addr - tdmr->base; + rsvd_areas[idx].size = size; + + *p_idx = idx + 1; + + return 0; +} + +/* + * Go through @tmb_list to find holes between memory areas. If any of + * those holes fall within @tdmr, set up a TDMR reserved area to cover + * the hole. + */ +static int tdmr_populate_rsvd_holes(struct list_head *tmb_list, + struct tdmr_info *tdmr, + int *rsvd_idx, + u16 max_reserved_per_tdmr) +{ + struct tdx_memblock *tmb; + u64 prev_end; + int ret; + + /* + * Start looking for reserved blocks at the + * beginning of the TDMR. + */ + prev_end = tdmr->base; + list_for_each_entry(tmb, tmb_list, list) { + u64 start, end; + + start = PFN_PHYS(tmb->start_pfn); + end = PFN_PHYS(tmb->end_pfn); + + /* Break if this region is after the TDMR */ + if (start >= tdmr_end(tdmr)) + break; + + /* Exclude regions before this TDMR */ + if (end < tdmr->base) + continue; + + /* + * Skip over memory areas that + * have already been dealt with. + */ + if (start <= prev_end) { + prev_end = end; + continue; + } + + /* Add the hole before this region */ + ret = tdmr_add_rsvd_area(tdmr, rsvd_idx, prev_end, + start - prev_end, + max_reserved_per_tdmr); + if (ret) + return ret; + + prev_end = end; + } + + /* Add the hole after the last region if it exists. */ + if (prev_end < tdmr_end(tdmr)) { + ret = tdmr_add_rsvd_area(tdmr, rsvd_idx, prev_end, + tdmr_end(tdmr) - prev_end, + max_reserved_per_tdmr); + if (ret) + return ret; + } + + return 0; +} + +/* + * Go through @tdmr_list to find all PAMTs. If any of those PAMTs + * overlaps with @tdmr, set up a TDMR reserved area to cover the + * overlapping part. + */ +static int tdmr_populate_rsvd_pamts(struct tdmr_info_list *tdmr_list, + struct tdmr_info *tdmr, + int *rsvd_idx, + u16 max_reserved_per_tdmr) +{ + int i, ret; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + struct tdmr_info *tmp = tdmr_entry(tdmr_list, i); + unsigned long pamt_base, pamt_size, pamt_end; + + tdmr_get_pamt(tmp, &pamt_base, &pamt_size); + /* Each TDMR must already have PAMT allocated */ + WARN_ON_ONCE(!pamt_size || !pamt_base); + + pamt_end = pamt_base + pamt_size; + /* Skip PAMTs outside of the given TDMR */ + if ((pamt_end <= tdmr->base) || + (pamt_base >= tdmr_end(tdmr))) + continue; + + /* Only mark the part within the TDMR as reserved */ + if (pamt_base < tdmr->base) + pamt_base = tdmr->base; + if (pamt_end > tdmr_end(tdmr)) + pamt_end = tdmr_end(tdmr); + + ret = tdmr_add_rsvd_area(tdmr, rsvd_idx, pamt_base, + pamt_end - pamt_base, + max_reserved_per_tdmr); + if (ret) + return ret; + } + + return 0; +} + +/* Compare function called by sort() for TDMR reserved areas */ +static int rsvd_area_cmp_func(const void *a, const void *b) +{ + struct tdmr_reserved_area *r1 = (struct tdmr_reserved_area *)a; + struct tdmr_reserved_area *r2 = (struct tdmr_reserved_area *)b; + + if (r1->offset + r1->size <= r2->offset) + return -1; + if (r1->offset >= r2->offset + r2->size) + return 1; + + /* Reserved areas cannot overlap. The caller must guarantee. */ + WARN_ON_ONCE(1); + return -1; +} + +/* + * Populate reserved areas for the given @tdmr, including memory holes + * (via @tmb_list) and PAMTs (via @tdmr_list). + */ +static int tdmr_populate_rsvd_areas(struct tdmr_info *tdmr, + struct list_head *tmb_list, + struct tdmr_info_list *tdmr_list, + u16 max_reserved_per_tdmr) +{ + int ret, rsvd_idx = 0; + + ret = tdmr_populate_rsvd_holes(tmb_list, tdmr, &rsvd_idx, + max_reserved_per_tdmr); + if (ret) + return ret; + + ret = tdmr_populate_rsvd_pamts(tdmr_list, tdmr, &rsvd_idx, + max_reserved_per_tdmr); + if (ret) + return ret; + + /* TDX requires reserved areas listed in address ascending order */ + sort(tdmr->reserved_areas, rsvd_idx, sizeof(struct tdmr_reserved_area), + rsvd_area_cmp_func, NULL); + + return 0; +} + +/* + * Populate reserved areas for all TDMRs in @tdmr_list, including memory + * holes (via @tmb_list) and PAMTs. + */ +static int tdmrs_populate_rsvd_areas_all(struct tdmr_info_list *tdmr_list, + struct list_head *tmb_list, + u16 max_reserved_per_tdmr) +{ + int i; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + int ret; + + ret = tdmr_populate_rsvd_areas(tdmr_entry(tdmr_list, i), + tmb_list, tdmr_list, max_reserved_per_tdmr); + if (ret) + return ret; + } + + return 0; +} + +/* + * Construct a list of TDMRs on the preallocated space in @tdmr_list + * to cover all TDX memory regions in @tmb_list based on the TDX module + * TDMR global information in @tdmr_sysinfo. + */ +static int construct_tdmrs(struct list_head *tmb_list, + struct tdmr_info_list *tdmr_list, + struct tdx_tdmr_sysinfo *tdmr_sysinfo) +{ + int ret; + + ret = fill_out_tdmrs(tmb_list, tdmr_list); + if (ret) + return ret; + + ret = tdmrs_set_up_pamt_all(tdmr_list, tmb_list, + tdmr_sysinfo->pamt_entry_size); + if (ret) + return ret; + + ret = tdmrs_populate_rsvd_areas_all(tdmr_list, tmb_list, + tdmr_sysinfo->max_reserved_per_tdmr); + if (ret) + tdmrs_free_pamt_all(tdmr_list); + + /* + * The tdmr_info_list is read-only from here on out. + * Ensure that these writes are seen by other CPUs. + * Pairs with a smp_rmb() in is_pamt_page(). + */ + smp_wmb(); + + return ret; +} + +static int config_tdx_module(struct tdmr_info_list *tdmr_list, u64 global_keyid) +{ + struct tdx_module_args args = {}; + u64 *tdmr_pa_array; + size_t array_sz; + int i, ret; + + /* + * TDMRs are passed to the TDX module via an array of physical + * addresses of each TDMR. The array itself also has certain + * alignment requirement. + */ + array_sz = tdmr_list->nr_consumed_tdmrs * sizeof(u64); + array_sz = roundup_pow_of_two(array_sz); + if (array_sz < TDMR_INFO_PA_ARRAY_ALIGNMENT) + array_sz = TDMR_INFO_PA_ARRAY_ALIGNMENT; + + tdmr_pa_array = kzalloc(array_sz, GFP_KERNEL); + if (!tdmr_pa_array) + return -ENOMEM; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) + tdmr_pa_array[i] = __pa(tdmr_entry(tdmr_list, i)); + + args.rcx = __pa(tdmr_pa_array); + args.rdx = tdmr_list->nr_consumed_tdmrs; + args.r8 = global_keyid; + ret = seamcall_prerr(TDH_SYS_CONFIG, &args); + + /* Free the array as it is not required anymore. */ + kfree(tdmr_pa_array); + + return ret; +} + +static int do_global_key_config(void *unused) +{ + struct tdx_module_args args = {}; + + return seamcall_prerr(TDH_SYS_KEY_CONFIG, &args); +} + +/* + * Attempt to configure the global KeyID on all physical packages. + * + * This requires running code on at least one CPU in each package. + * TDMR initialization) will fail will fail if any package in the + * system has no online CPUs. + * + * This code takes no affirmative steps to online CPUs. Callers (aka. + * KVM) can ensure success by ensuring sufficient CPUs are online and + * can run SEAMCALLs. + */ +static int config_global_keyid(void) +{ + cpumask_var_t packages; + int cpu, ret = -EINVAL; + + if (!zalloc_cpumask_var(&packages, GFP_KERNEL)) + return -ENOMEM; + + /* + * Hardware doesn't guarantee cache coherency across different + * KeyIDs. The kernel needs to flush PAMT's dirty cachelines + * (associated with KeyID 0) before the TDX module can use the + * global KeyID to access the PAMT. Given PAMTs are potentially + * large (~1/256th of system RAM), just use WBINVD. + */ + wbinvd_on_all_cpus(); + + for_each_online_cpu(cpu) { + /* + * The key configuration only needs to be done once per + * package and will return an error if configured more + * than once. Avoid doing it multiple times per package. + */ + if (cpumask_test_and_set_cpu(topology_physical_package_id(cpu), + packages)) + continue; + + /* + * TDH.SYS.KEY.CONFIG cannot run concurrently on + * different cpus. Do it one by one. + */ + ret = smp_call_on_cpu(cpu, do_global_key_config, NULL, true); + if (ret) + break; + } + + free_cpumask_var(packages); + return ret; +} + +static int init_tdmr(struct tdmr_info *tdmr) +{ + u64 next; + + /* + * Initializing a TDMR can be time consuming. To avoid long + * SEAMCALLs, the TDX module may only initialize a part of the + * TDMR in each call. + */ + do { + struct tdx_module_args args = { + .rcx = tdmr->base, + }; + int ret; + + ret = seamcall_prerr_ret(TDH_SYS_TDMR_INIT, &args); + if (ret) + return ret; + /* + * RDX contains 'next-to-initialize' address if + * TDH.SYS.TDMR.INIT did not fully complete and + * should be retried. + */ + next = args.rdx; + cond_resched(); + /* Keep making SEAMCALLs until the TDMR is done */ + } while (next < tdmr->base + tdmr->size); + + return 0; +} + +static int init_tdmrs(struct tdmr_info_list *tdmr_list) +{ + int i; + + /* + * This operation is costly. It can be parallelized, + * but keep it simple for now. + */ + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + int ret; + + ret = init_tdmr(tdmr_entry(tdmr_list, i)); + if (ret) + return ret; + } + + return 0; +} + +static int init_tdx_module(void) +{ + struct tdx_tdmr_sysinfo tdmr_sysinfo; + int ret; + + /* + * To keep things simple, assume that all TDX-protected memory + * will come from the page allocator. Make sure all pages in the + * page allocator are TDX-usable memory. + * + * Build the list of "TDX-usable" memory regions which cover all + * pages in the page allocator to guarantee that. Do it while + * holding mem_hotplug_lock read-lock as the memory hotplug code + * path reads the @tdx_memlist to reject any new memory. + */ + get_online_mems(); + + ret = build_tdx_memlist(&tdx_memlist); + if (ret) + goto out_put_tdxmem; + + ret = get_tdx_tdmr_sysinfo(&tdmr_sysinfo); + if (ret) + goto err_free_tdxmem; + + /* Allocate enough space for constructing TDMRs */ + ret = alloc_tdmr_list(&tdx_tdmr_list, &tdmr_sysinfo); + if (ret) + goto err_free_tdxmem; + + /* Cover all TDX-usable memory regions in TDMRs */ + ret = construct_tdmrs(&tdx_memlist, &tdx_tdmr_list, &tdmr_sysinfo); + if (ret) + goto err_free_tdmrs; + + /* Pass the TDMRs and the global KeyID to the TDX module */ + ret = config_tdx_module(&tdx_tdmr_list, tdx_global_keyid); + if (ret) + goto err_free_pamts; + + /* Config the key of global KeyID on all packages */ + ret = config_global_keyid(); + if (ret) + goto err_reset_pamts; + + /* Initialize TDMRs to complete the TDX module initialization */ + ret = init_tdmrs(&tdx_tdmr_list); + if (ret) + goto err_reset_pamts; + + pr_info("%lu KB allocated for PAMT\n", tdmrs_count_pamt_kb(&tdx_tdmr_list)); + +out_put_tdxmem: + /* + * @tdx_memlist is written here and read at memory hotplug time. + * Lock out memory hotplug code while building it. + */ + put_online_mems(); + return ret; + +err_reset_pamts: + /* + * Part of PAMTs may already have been initialized by the + * TDX module. Flush cache before returning PAMTs back + * to the kernel. + */ + wbinvd_on_all_cpus(); + /* + * According to the TDX hardware spec, if the platform + * doesn't have the "partial write machine check" + * erratum, any kernel read/write will never cause #MC + * in kernel space, thus it's OK to not convert PAMTs + * back to normal. But do the conversion anyway here + * as suggested by the TDX spec. + */ + tdmrs_reset_pamt_all(&tdx_tdmr_list); +err_free_pamts: + tdmrs_free_pamt_all(&tdx_tdmr_list); +err_free_tdmrs: + free_tdmr_list(&tdx_tdmr_list); +err_free_tdxmem: + free_tdx_memlist(&tdx_memlist); + goto out_put_tdxmem; +} + +static int __tdx_enable(void) +{ + int ret; + + ret = init_tdx_module(); + if (ret) { + pr_err("module initialization failed (%d)\n", ret); + tdx_module_status = TDX_MODULE_ERROR; + return ret; + } + + pr_info("module initialized\n"); + tdx_module_status = TDX_MODULE_INITIALIZED; + + return 0; +} + +/** + * tdx_enable - Enable TDX module to make it ready to run TDX guests + * + * This function assumes the caller has: 1) held read lock of CPU hotplug + * lock to prevent any new cpu from becoming online; 2) done both VMXON + * and tdx_cpu_enable() on all online cpus. + * + * This function requires there's at least one online cpu for each CPU + * package to succeed. + * + * This function can be called in parallel by multiple callers. + * + * Return 0 if TDX is enabled successfully, otherwise error. + */ +int tdx_enable(void) +{ + int ret; + + if (!boot_cpu_has(X86_FEATURE_TDX_HOST_PLATFORM)) + return -ENODEV; + + lockdep_assert_cpus_held(); + + mutex_lock(&tdx_module_lock); + + switch (tdx_module_status) { + case TDX_MODULE_UNINITIALIZED: + ret = __tdx_enable(); + break; + case TDX_MODULE_INITIALIZED: + /* Already initialized, great, tell the caller. */ + ret = 0; + break; + default: + /* Failed to initialize in the previous attempts */ + ret = -EINVAL; + break; + } + + mutex_unlock(&tdx_module_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(tdx_enable); + +static bool is_pamt_page(unsigned long phys) +{ + struct tdmr_info_list *tdmr_list = &tdx_tdmr_list; + int i; + + /* Ensure that all remote 'tdmr_list' writes are visible: */ + smp_rmb(); + + /* + * The TDX module is no longer returning TDX_SYS_NOT_READY and + * is initialized. The 'tdmr_list' was initialized long ago + * and is now read-only. + */ + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + unsigned long base, size; + + tdmr_get_pamt(tdmr_entry(tdmr_list, i), &base, &size); + + if (phys >= base && phys < (base + size)) + return true; + } + + return false; +} + +/* + * Return whether the memory page at the given physical address is TDX + * private memory or not. + * + * This can be imprecise for two known reasons: + * 1. PAMTs are private memory and exist before the TDX module is + * ready and TDH_PHYMEM_PAGE_RDMD works. This is a relatively + * short window that occurs once per boot. + * 2. TDH_PHYMEM_PAGE_RDMD reflects the TDX module's knowledge of the + * page. However, the page can still cause #MC until it has been + * fully converted to shared using 64-byte writes like MOVDIR64B. + * Buggy hosts might still leave #MC-causing memory in place which + * this function can not detect. + */ +static bool paddr_is_tdx_private(unsigned long phys) +{ + struct tdx_module_args args = { + .rcx = phys & PAGE_MASK, + }; + u64 sret; + + if (!boot_cpu_has(X86_FEATURE_TDX_HOST_PLATFORM)) + return false; + + /* Get page type from the TDX module */ + sret = __seamcall_ret(TDH_PHYMEM_PAGE_RDMD, &args); + + /* + * The SEAMCALL will not return success unless there is a + * working, "ready" TDX module. Assume an absence of TDX + * private pages until SEAMCALL is working. + */ + if (sret) + return false; + + /* + * SEAMCALL was successful -- read page type (via RCX): + * + * - PT_NDA: Page is not used by the TDX module + * - PT_RSVD: Reserved for Non-TDX use + * - Others: Page is used by the TDX module + * + * Note PAMT pages are marked as PT_RSVD but they are also TDX + * private memory. + */ + switch (args.rcx) { + case PT_NDA: + return false; + case PT_RSVD: + return is_pamt_page(phys); + default: + return true; + } +} + +/* + * Some TDX-capable CPUs have an erratum. A write to TDX private + * memory poisons that memory, and a subsequent read of that memory + * triggers #MC. + * + * Help distinguish erratum-triggered #MCs from a normal hardware one. + * Just print additional message to show such #MC may be result of the + * erratum. + */ +const char *tdx_dump_mce_info(struct mce *m) +{ + if (!m || !mce_is_memory_error(m) || !mce_usable_address(m)) + return NULL; + + if (!paddr_is_tdx_private(m->addr)) + return NULL; + + return "TDX private memory error. Possible kernel bug."; +} + +static __init int record_keyid_partitioning(u32 *tdx_keyid_start, + u32 *nr_tdx_keyids) +{ + u32 _nr_mktme_keyids, _tdx_keyid_start, _nr_tdx_keyids; + int ret; + + /* + * IA32_MKTME_KEYID_PARTIONING: + * Bit [31:0]: Number of MKTME KeyIDs. + * Bit [63:32]: Number of TDX private KeyIDs. + */ + ret = rdmsr_safe(MSR_IA32_MKTME_KEYID_PARTITIONING, &_nr_mktme_keyids, + &_nr_tdx_keyids); + if (ret || !_nr_tdx_keyids) + return -EINVAL; + + /* TDX KeyIDs start after the last MKTME KeyID. */ + _tdx_keyid_start = _nr_mktme_keyids + 1; + + *tdx_keyid_start = _tdx_keyid_start; + *nr_tdx_keyids = _nr_tdx_keyids; + + return 0; +} + +static bool is_tdx_memory(unsigned long start_pfn, unsigned long end_pfn) +{ + struct tdx_memblock *tmb; + + /* + * This check assumes that the start_pfn<->end_pfn range does not + * cross multiple @tdx_memlist entries. A single memory online + * event across multiple memblocks (from which @tdx_memlist + * entries are derived at the time of module initialization) is + * not possible. This is because memory offline/online is done + * on granularity of 'struct memory_block', and the hotpluggable + * memory region (one memblock) must be multiple of memory_block. + */ + list_for_each_entry(tmb, &tdx_memlist, list) { + if (start_pfn >= tmb->start_pfn && end_pfn <= tmb->end_pfn) + return true; + } + return false; +} + +static int tdx_memory_notifier(struct notifier_block *nb, unsigned long action, + void *v) +{ + struct memory_notify *mn = v; + + if (action != MEM_GOING_ONLINE) + return NOTIFY_OK; + + /* + * Empty list means TDX isn't enabled. Allow any memory + * to go online. + */ + if (list_empty(&tdx_memlist)) + return NOTIFY_OK; + + /* + * The TDX memory configuration is static and can not be + * changed. Reject onlining any memory which is outside of + * the static configuration whether it supports TDX or not. + */ + if (is_tdx_memory(mn->start_pfn, mn->start_pfn + mn->nr_pages)) + return NOTIFY_OK; + + return NOTIFY_BAD; +} + +static struct notifier_block tdx_memory_nb = { + .notifier_call = tdx_memory_notifier, +}; + +static void __init check_tdx_erratum(void) +{ + /* + * These CPUs have an erratum. A partial write from non-TD + * software (e.g. via MOVNTI variants or UC/WC mapping) to TDX + * private memory poisons that memory, and a subsequent read of + * that memory triggers #MC. + */ + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_SAPPHIRERAPIDS_X: + case INTEL_FAM6_EMERALDRAPIDS_X: + setup_force_cpu_bug(X86_BUG_TDX_PW_MCE); + } +} + +void __init tdx_init(void) +{ + u32 tdx_keyid_start, nr_tdx_keyids; + int err; + + err = record_keyid_partitioning(&tdx_keyid_start, &nr_tdx_keyids); + if (err) + return; + + pr_info("BIOS enabled: private KeyID range [%u, %u)\n", + tdx_keyid_start, tdx_keyid_start + nr_tdx_keyids); + + /* + * The TDX module itself requires one 'global KeyID' to protect + * its metadata. If there's only one TDX KeyID, there won't be + * any left for TDX guests thus there's no point to enable TDX + * at all. + */ + if (nr_tdx_keyids < 2) { + pr_err("initialization failed: too few private KeyIDs available.\n"); + return; + } + + /* + * At this point, hibernation_available() indicates whether or + * not hibernation support has been permanently disabled. + */ + if (hibernation_available()) { + pr_err("initialization failed: Hibernation support is enabled\n"); + return; + } + + err = register_memory_notifier(&tdx_memory_nb); + if (err) { + pr_err("initialization failed: register_memory_notifier() failed (%d)\n", + err); + return; + } + +#if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND) + pr_info("Disable ACPI S3. Turn off TDX in the BIOS to use ACPI S3.\n"); + acpi_suspend_lowlevel = NULL; +#endif + + /* + * Just use the first TDX KeyID as the 'global KeyID' and + * leave the rest for TDX guests. + */ + tdx_global_keyid = tdx_keyid_start; + tdx_guest_keyid_start = tdx_keyid_start + 1; + tdx_nr_guest_keyids = nr_tdx_keyids - 1; + + setup_force_cpu_cap(X86_FEATURE_TDX_HOST_PLATFORM); + + check_tdx_erratum(); +} diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h new file mode 100644 index 000000000000..b701f69485d3 --- /dev/null +++ b/arch/x86/virt/vmx/tdx/tdx.h @@ -0,0 +1,121 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _X86_VIRT_TDX_H +#define _X86_VIRT_TDX_H + +#include <linux/bits.h> + +/* + * This file contains both macros and data structures defined by the TDX + * architecture and Linux defined software data structures and functions. + * The two should not be mixed together for better readability. The + * architectural definitions come first. + */ + +/* + * TDX module SEAMCALL leaf functions + */ +#define TDH_PHYMEM_PAGE_RDMD 24 +#define TDH_SYS_KEY_CONFIG 31 +#define TDH_SYS_INIT 33 +#define TDH_SYS_RD 34 +#define TDH_SYS_LP_INIT 35 +#define TDH_SYS_TDMR_INIT 36 +#define TDH_SYS_CONFIG 45 + +/* TDX page types */ +#define PT_NDA 0x0 +#define PT_RSVD 0x1 + +/* + * Global scope metadata field ID. + * + * See Table "Global Scope Metadata", TDX module 1.5 ABI spec. + */ +#define MD_FIELD_ID_MAX_TDMRS 0x9100000100000008ULL +#define MD_FIELD_ID_MAX_RESERVED_PER_TDMR 0x9100000100000009ULL +#define MD_FIELD_ID_PAMT_4K_ENTRY_SIZE 0x9100000100000010ULL +#define MD_FIELD_ID_PAMT_2M_ENTRY_SIZE 0x9100000100000011ULL +#define MD_FIELD_ID_PAMT_1G_ENTRY_SIZE 0x9100000100000012ULL + +/* + * Sub-field definition of metadata field ID. + * + * See Table "MD_FIELD_ID (Metadata Field Identifier / Sequence Header) + * Definition", TDX module 1.5 ABI spec. + * + * - Bit 33:32: ELEMENT_SIZE_CODE -- size of a single element of metadata + * + * 0: 8 bits + * 1: 16 bits + * 2: 32 bits + * 3: 64 bits + */ +#define MD_FIELD_ID_ELE_SIZE_CODE(_field_id) \ + (((_field_id) & GENMASK_ULL(33, 32)) >> 32) + +#define MD_FIELD_ID_ELE_SIZE_16BIT 1 + +struct tdmr_reserved_area { + u64 offset; + u64 size; +} __packed; + +#define TDMR_INFO_ALIGNMENT 512 +#define TDMR_INFO_PA_ARRAY_ALIGNMENT 512 + +struct tdmr_info { + u64 base; + u64 size; + u64 pamt_1g_base; + u64 pamt_1g_size; + u64 pamt_2m_base; + u64 pamt_2m_size; + u64 pamt_4k_base; + u64 pamt_4k_size; + /* + * The actual number of reserved areas depends on the value of + * field MD_FIELD_ID_MAX_RESERVED_PER_TDMR in the TDX module + * global metadata. + */ + DECLARE_FLEX_ARRAY(struct tdmr_reserved_area, reserved_areas); +} __packed __aligned(TDMR_INFO_ALIGNMENT); + +/* + * Do not put any hardware-defined TDX structure representations below + * this comment! + */ + +/* Kernel defined TDX module status during module initialization. */ +enum tdx_module_status_t { + TDX_MODULE_UNINITIALIZED, + TDX_MODULE_INITIALIZED, + TDX_MODULE_ERROR +}; + +struct tdx_memblock { + struct list_head list; + unsigned long start_pfn; + unsigned long end_pfn; + int nid; +}; + +/* "TDMR info" part of "Global Scope Metadata" for constructing TDMRs */ +struct tdx_tdmr_sysinfo { + u16 max_tdmrs; + u16 max_reserved_per_tdmr; + u16 pamt_entry_size[TDX_PS_NR]; +}; + +/* Warn if kernel has less than TDMR_NR_WARN TDMRs after allocation */ +#define TDMR_NR_WARN 4 + +struct tdmr_info_list { + void *tdmrs; /* Flexible array to hold 'tdmr_info's */ + int nr_consumed_tdmrs; /* How many 'tdmr_info's are in use */ + + /* Metadata for finding target 'tdmr_info' and freeing @tdmrs */ + int tdmr_sz; /* Size of one 'tdmr_info' */ + int max_tdmrs; /* How many 'tdmr_info's are allocated */ +}; + +#endif diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h index 785a00ce83c1..38bcecb0e457 100644 --- a/arch/xtensa/include/asm/cacheflush.h +++ b/arch/xtensa/include/asm/cacheflush.h @@ -116,8 +116,9 @@ void flush_cache_page(struct vm_area_struct*, #define flush_cache_mm(mm) flush_cache_all() #define flush_cache_dup_mm(mm) flush_cache_mm(mm) -#define flush_cache_vmap(start,end) flush_cache_all() -#define flush_cache_vunmap(start,end) flush_cache_all() +#define flush_cache_vmap(start,end) flush_cache_all() +#define flush_cache_vmap_early(start,end) do { } while (0) +#define flush_cache_vunmap(start,end) flush_cache_all() void flush_dcache_folio(struct folio *folio); #define flush_dcache_folio flush_dcache_folio @@ -140,6 +141,7 @@ void local_flush_cache_page(struct vm_area_struct *vma, #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_vmap(start,end) do { } while (0) +#define flush_cache_vmap_early(start,end) do { } while (0) #define flush_cache_vunmap(start,end) do { } while (0) #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 diff --git a/block/bio-integrity.c b/block/bio-integrity.c index feef615e2c9c..c9a16fba58b9 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -336,7 +336,7 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes, if (nr_vecs > BIO_MAX_VECS) return -E2BIG; if (nr_vecs > UIO_FASTIOV) { - bvec = kcalloc(sizeof(*bvec), nr_vecs, GFP_KERNEL); + bvec = kcalloc(nr_vecs, sizeof(*bvec), GFP_KERNEL); if (!bvec) return -ENOMEM; pages = NULL; diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index e303fd317313..ff93c385ba5a 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -300,7 +300,7 @@ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) * @disk: gendisk the new blkg is associated with * @gfp_mask: allocation mask to use * - * Allocate a new blkg assocating @blkcg and @q. + * Allocate a new blkg associating @blkcg and @disk. */ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk, gfp_t gfp_mask) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 089fcb9cfce3..c8beec6d7df0 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1261,7 +1261,7 @@ static void weight_updated(struct ioc_gq *iocg, struct ioc_now *now) static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; - u64 last_period, cur_period; + u64 __maybe_unused last_period, cur_period; u64 vtime, vtarget; int i; diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 5cbeb9344f2f..94668e72ab09 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -479,23 +479,6 @@ out: return res; } -static int hctx_run_show(void *data, struct seq_file *m) -{ - struct blk_mq_hw_ctx *hctx = data; - - seq_printf(m, "%lu\n", hctx->run); - return 0; -} - -static ssize_t hctx_run_write(void *data, const char __user *buf, size_t count, - loff_t *ppos) -{ - struct blk_mq_hw_ctx *hctx = data; - - hctx->run = 0; - return count; -} - static int hctx_active_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; @@ -624,7 +607,6 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = { {"tags_bitmap", 0400, hctx_tags_bitmap_show}, {"sched_tags", 0400, hctx_sched_tags_show}, {"sched_tags_bitmap", 0400, hctx_sched_tags_bitmap_show}, - {"run", 0600, hctx_run_show, hctx_run_write}, {"active", 0400, hctx_active_show}, {"dispatch_busy", 0400, hctx_dispatch_busy_show}, {"type", 0400, hctx_type_show}, diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 67c95f31b15b..451a2c1f1f32 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -324,8 +324,6 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q))) return; - hctx->run++; - /* * A return of -EAGAIN is an indication that hctx->dispatch is not * empty and we must run again in order to avoid starving flushes. diff --git a/block/blk-mq.c b/block/blk-mq.c index c11c97afa0bc..aa87fcfda1ec 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -772,11 +772,16 @@ static void req_bio_endio(struct request *rq, struct bio *bio, /* * Partial zone append completions cannot be supported as the * BIO fragments may end up not being written sequentially. + * For such case, force the completed nbytes to be equal to + * the BIO size so that bio_advance() sets the BIO remaining + * size to 0 and we end up calling bio_endio() before returning. */ - if (bio->bi_iter.bi_size != nbytes) + if (bio->bi_iter.bi_size != nbytes) { bio->bi_status = BLK_STS_IOERR; - else + nbytes = bio->bi_iter.bi_size; + } else { bio->bi_iter.bi_sector = rq->__sector; + } } bio_advance(bio, nbytes); @@ -1860,6 +1865,22 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, __add_wait_queue(wq, wait); /* + * Add one explicit barrier since blk_mq_get_driver_tag() may + * not imply barrier in case of failure. + * + * Order adding us to wait queue and allocating driver tag. + * + * The pair is the one implied in sbitmap_queue_wake_up() which + * orders clearing sbitmap tag bits and waitqueue_active() in + * __sbitmap_queue_wake_up(), since waitqueue_active() is lockless + * + * Otherwise, re-order of adding wait queue and getting driver tag + * may cause __sbitmap_queue_wake_up() to wake up nothing because + * the waitqueue_active() may not observe us in wait queue. + */ + smp_mb(); + + /* * It's possible that a tag was freed in the window between the * allocation failure and adding the hardware queue to the wait * queue. @@ -2891,8 +2912,11 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, return NULL; } -/* return true if this @rq can be used for @bio */ -static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug, +/* + * Check if we can use the passed on request for submitting the passed in bio, + * and remove it from the request list if it can be used. + */ +static bool blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug, struct bio *bio) { enum hctx_type type = blk_mq_get_hctx_type(bio->bi_opf); @@ -2952,12 +2976,6 @@ void blk_mq_submit_bio(struct bio *bio) blk_status_t ret; bio = blk_queue_bounce(bio, q); - if (bio_may_exceed_limits(bio, &q->limits)) { - bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); - if (!bio) - return; - } - bio_set_ioprio(bio); if (plug) { @@ -2966,16 +2984,26 @@ void blk_mq_submit_bio(struct bio *bio) rq = NULL; } if (rq) { + if (unlikely(bio_may_exceed_limits(bio, &q->limits))) { + bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); + if (!bio) + return; + } if (!bio_integrity_prep(bio)) return; if (blk_mq_attempt_bio_merge(q, bio, nr_segs)) return; - if (blk_mq_can_use_cached_rq(rq, plug, bio)) + if (blk_mq_use_cached_rq(rq, plug, bio)) goto done; percpu_ref_get(&q->q_usage_counter); } else { if (unlikely(bio_queue_enter(bio))) return; + if (unlikely(bio_may_exceed_limits(bio, &q->limits))) { + bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); + if (!bio) + goto fail; + } if (!bio_integrity_prep(bio)) goto fail; } diff --git a/block/ioprio.c b/block/ioprio.c index b5a942519a79..73301a261429 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -139,32 +139,6 @@ out: return ret; } -/* - * If the task has set an I/O priority, use that. Otherwise, return - * the default I/O priority. - * - * Expected to be called for current task or with task_lock() held to keep - * io_context stable. - */ -int __get_task_ioprio(struct task_struct *p) -{ - struct io_context *ioc = p->io_context; - int prio; - - if (p != current) - lockdep_assert_held(&p->alloc_lock); - if (ioc) - prio = ioc->ioprio; - else - prio = IOPRIO_DEFAULT; - - if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE) - prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p), - task_nice_ioprio(p)); - return prio; -} -EXPORT_SYMBOL_GPL(__get_task_ioprio); - static int get_task_ioprio(struct task_struct *p) { int ret; diff --git a/block/partitions/core.c b/block/partitions/core.c index e6ac73617f3e..cab0d76a828e 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -562,8 +562,8 @@ static bool blk_add_partition(struct gendisk *disk, part = add_partition(disk, p, from, size, state->parts[p].flags, &state->parts[p].info); if (IS_ERR(part) && PTR_ERR(part) != -ENXIO) { - printk(KERN_ERR " %s: p%d could not be added: %ld\n", - disk->disk_name, p, -PTR_ERR(part)); + printk(KERN_ERR " %s: p%d could not be added: %pe\n", + disk->disk_name, p, part); return true; } diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index ab2a82cb1b0b..7b7c605166e0 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -26,6 +26,7 @@ #include <linux/interrupt.h> #include <linux/timer.h> #include <linux/cper.h> +#include <linux/cxl-event.h> #include <linux/platform_device.h> #include <linux/mutex.h> #include <linux/ratelimit.h> @@ -673,6 +674,78 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata, schedule_work(&entry->work); } +/* + * Only a single callback can be registered for CXL CPER events. + */ +static DECLARE_RWSEM(cxl_cper_rw_sem); +static cxl_cper_callback cper_callback; + +/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */ + +/* + * General Media Event Record + * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 + */ +#define CPER_SEC_CXL_GEN_MEDIA_GUID \ + GUID_INIT(0xfbcd0a77, 0xc260, 0x417f, \ + 0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6) + +/* + * DRAM Event Record + * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44 + */ +#define CPER_SEC_CXL_DRAM_GUID \ + GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, \ + 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24) + +/* + * Memory Module Event Record + * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45 + */ +#define CPER_SEC_CXL_MEM_MODULE_GUID \ + GUID_INIT(0xfe927475, 0xdd59, 0x4339, \ + 0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74) + +static void cxl_cper_post_event(enum cxl_event_type event_type, + struct cxl_cper_event_rec *rec) +{ + if (rec->hdr.length <= sizeof(rec->hdr) || + rec->hdr.length > sizeof(*rec)) { + pr_err(FW_WARN "CXL CPER Invalid section length (%u)\n", + rec->hdr.length); + return; + } + + if (!(rec->hdr.validation_bits & CPER_CXL_COMP_EVENT_LOG_VALID)) { + pr_err(FW_WARN "CXL CPER invalid event\n"); + return; + } + + guard(rwsem_read)(&cxl_cper_rw_sem); + if (cper_callback) + cper_callback(event_type, rec); +} + +int cxl_cper_register_callback(cxl_cper_callback callback) +{ + guard(rwsem_write)(&cxl_cper_rw_sem); + if (cper_callback) + return -EINVAL; + cper_callback = callback; + return 0; +} +EXPORT_SYMBOL_NS_GPL(cxl_cper_register_callback, CXL); + +int cxl_cper_unregister_callback(cxl_cper_callback callback) +{ + guard(rwsem_write)(&cxl_cper_rw_sem); + if (callback != cper_callback) + return -EINVAL; + cper_callback = NULL; + return 0; +} +EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_callback, CXL); + static bool ghes_do_proc(struct ghes *ghes, const struct acpi_hest_generic_status *estatus) { @@ -707,6 +780,22 @@ static bool ghes_do_proc(struct ghes *ghes, } else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) { queued = ghes_handle_arm_hw_error(gdata, sev, sync); + } else if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID)) { + struct cxl_cper_event_rec *rec = + acpi_hest_get_payload(gdata); + + cxl_cper_post_event(CXL_CPER_EVENT_GEN_MEDIA, rec); + } else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID)) { + struct cxl_cper_event_rec *rec = + acpi_hest_get_payload(gdata); + + cxl_cper_post_event(CXL_CPER_EVENT_DRAM, rec); + } else if (guid_equal(sec_type, + &CPER_SEC_CXL_MEM_MODULE_GUID)) { + struct cxl_cper_event_rec *rec = + acpi_hest_get_payload(gdata); + + cxl_cper_post_event(CXL_CPER_EVENT_MEM_MODULE, rec); } else { void *err = acpi_hest_get_payload(gdata); diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c index 9ef5f1bdcfdb..d6b85f0f6082 100644 --- a/drivers/acpi/numa/hmat.c +++ b/drivers/acpi/numa/hmat.c @@ -58,14 +58,22 @@ struct target_cache { struct node_cache_attrs cache_attrs; }; +enum { + NODE_ACCESS_CLASS_0 = 0, + NODE_ACCESS_CLASS_1, + NODE_ACCESS_CLASS_GENPORT_SINK, + NODE_ACCESS_CLASS_MAX, +}; + struct memory_target { struct list_head node; unsigned int memory_pxm; unsigned int processor_pxm; struct resource memregions; - struct node_hmem_attrs hmem_attrs[2]; + struct access_coordinate coord[NODE_ACCESS_CLASS_MAX]; struct list_head caches; struct node_cache_attrs cache_attrs; + u8 gen_port_device_handle[ACPI_SRAT_DEVICE_HANDLE_SIZE]; bool registered; }; @@ -100,6 +108,47 @@ static struct memory_target *find_mem_target(unsigned int mem_pxm) return NULL; } +static struct memory_target *acpi_find_genport_target(u32 uid) +{ + struct memory_target *target; + u32 target_uid; + u8 *uid_ptr; + + list_for_each_entry(target, &targets, node) { + uid_ptr = target->gen_port_device_handle + 8; + target_uid = *(u32 *)uid_ptr; + if (uid == target_uid) + return target; + } + + return NULL; +} + +/** + * acpi_get_genport_coordinates - Retrieve the access coordinates for a generic port + * @uid: ACPI unique id + * @coord: The access coordinates written back out for the generic port + * + * Return: 0 on success. Errno on failure. + * + * Only supports device handles that are ACPI. Assume ACPI0016 HID for CXL. + */ +int acpi_get_genport_coordinates(u32 uid, + struct access_coordinate *coord) +{ + struct memory_target *target; + + guard(mutex)(&target_lock); + target = acpi_find_genport_target(uid); + if (!target) + return -ENOENT; + + *coord = target->coord[NODE_ACCESS_CLASS_GENPORT_SINK]; + + return 0; +} +EXPORT_SYMBOL_NS_GPL(acpi_get_genport_coordinates, CXL); + static __init void alloc_memory_initiator(unsigned int cpu_pxm) { struct memory_initiator *initiator; @@ -120,8 +169,7 @@ static __init void alloc_memory_initiator(unsigned int cpu_pxm) list_add_tail(&initiator->node, &initiators); } -static __init void alloc_memory_target(unsigned int mem_pxm, - resource_size_t start, resource_size_t len) +static __init struct memory_target *alloc_target(unsigned int mem_pxm) { struct memory_target *target; @@ -129,7 +177,7 @@ static __init void alloc_memory_target(unsigned int mem_pxm, if (!target) { target = kzalloc(sizeof(*target), GFP_KERNEL); if (!target) - return; + return NULL; target->memory_pxm = mem_pxm; target->processor_pxm = PXM_INVAL; target->memregions = (struct resource) { @@ -142,6 +190,19 @@ static __init void alloc_memory_target(unsigned int mem_pxm, INIT_LIST_HEAD(&target->caches); } + return target; +} + +static __init void alloc_memory_target(unsigned int mem_pxm, + resource_size_t start, + resource_size_t len) +{ + struct memory_target *target; + + target = alloc_target(mem_pxm); + if (!target) + return; + /* * There are potentially multiple ranges per PXM, so record each * in the per-target memregions resource tree. @@ -152,6 +213,18 @@ static __init void alloc_memory_target(unsigned int mem_pxm, start, start + len, mem_pxm); } +static __init void alloc_genport_target(unsigned int mem_pxm, u8 *handle) +{ + struct memory_target *target; + + target = alloc_target(mem_pxm); + if (!target) + return; + + memcpy(target->gen_port_device_handle, handle, + ACPI_SRAT_DEVICE_HANDLE_SIZE); +} + static __init const char *hmat_data_type(u8 type) { switch (type) { @@ -228,24 +301,24 @@ static void hmat_update_target_access(struct memory_target *target, { switch (type) { case ACPI_HMAT_ACCESS_LATENCY: - target->hmem_attrs[access].read_latency = value; - target->hmem_attrs[access].write_latency = value; + target->coord[access].read_latency = value; + target->coord[access].write_latency = value; break; case ACPI_HMAT_READ_LATENCY: - target->hmem_attrs[access].read_latency = value; + target->coord[access].read_latency = value; break; case ACPI_HMAT_WRITE_LATENCY: - target->hmem_attrs[access].write_latency = value; + target->coord[access].write_latency = value; break; case ACPI_HMAT_ACCESS_BANDWIDTH: - target->hmem_attrs[access].read_bandwidth = value; - target->hmem_attrs[access].write_bandwidth = value; + target->coord[access].read_bandwidth = value; + target->coord[access].write_bandwidth = value; break; case ACPI_HMAT_READ_BANDWIDTH: - target->hmem_attrs[access].read_bandwidth = value; + target->coord[access].read_bandwidth = value; break; case ACPI_HMAT_WRITE_BANDWIDTH: - target->hmem_attrs[access].write_bandwidth = value; + target->coord[access].write_bandwidth = value; break; default: break; @@ -291,11 +364,28 @@ static __init void hmat_add_locality(struct acpi_hmat_locality *hmat_loc) } } +static __init void hmat_update_target(unsigned int tgt_pxm, unsigned int init_pxm, + u8 mem_hier, u8 type, u32 value) +{ + struct memory_target *target = find_mem_target(tgt_pxm); + + if (mem_hier != ACPI_HMAT_MEMORY) + return; + + if (target && target->processor_pxm == init_pxm) { + hmat_update_target_access(target, type, value, + NODE_ACCESS_CLASS_0); + /* If the node has a CPU, update access 1 */ + if (node_state(pxm_to_node(init_pxm), N_CPU)) + hmat_update_target_access(target, type, value, + NODE_ACCESS_CLASS_1); + } +} + static __init int hmat_parse_locality(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_hmat_locality *hmat_loc = (void *)header; - struct memory_target *target; unsigned int init, targ, total_size, ipds, tpds; u32 *inits, *targs, value; u16 *entries; @@ -336,15 +426,8 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header, inits[init], targs[targ], value, hmat_data_type_suffix(type)); - if (mem_hier == ACPI_HMAT_MEMORY) { - target = find_mem_target(targs[targ]); - if (target && target->processor_pxm == inits[init]) { - hmat_update_target_access(target, type, value, 0); - /* If the node has a CPU, update access 1 */ - if (node_state(pxm_to_node(inits[init]), N_CPU)) - hmat_update_target_access(target, type, value, 1); - } - } + hmat_update_target(targs[targ], inits[init], + mem_hier, type, value); } } @@ -491,6 +574,27 @@ static __init int srat_parse_mem_affinity(union acpi_subtable_headers *header, return 0; } +static __init int srat_parse_genport_affinity(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_srat_generic_affinity *ga = (void *)header; + + if (!ga) + return -EINVAL; + + if (!(ga->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED)) + return 0; + + /* Skip PCI device_handle for now */ + if (ga->device_handle_type != 0) + return 0; + + alloc_genport_target(ga->proximity_domain, + (u8 *)ga->device_handle); + + return 0; +} + static u32 hmat_initiator_perf(struct memory_target *target, struct memory_initiator *initiator, struct acpi_hmat_locality *hmat_loc) @@ -592,6 +696,11 @@ static void hmat_update_target_attrs(struct memory_target *target, u32 best = 0; int i; + /* Don't update for generic port if there's no device handle */ + if (access == NODE_ACCESS_CLASS_GENPORT_SINK && + !(*(u16 *)target->gen_port_device_handle)) + return; + bitmap_zero(p_nodes, MAX_NUMNODES); /* * If the Address Range Structure provides a local processor pxm, set @@ -661,6 +770,14 @@ static void __hmat_register_target_initiators(struct memory_target *target, } } +static void hmat_register_generic_target_initiators(struct memory_target *target) +{ + static DECLARE_BITMAP(p_nodes, MAX_NUMNODES); + + __hmat_register_target_initiators(target, p_nodes, + NODE_ACCESS_CLASS_GENPORT_SINK); +} + static void hmat_register_target_initiators(struct memory_target *target) { static DECLARE_BITMAP(p_nodes, MAX_NUMNODES); @@ -681,7 +798,7 @@ static void hmat_register_target_cache(struct memory_target *target) static void hmat_register_target_perf(struct memory_target *target, int access) { unsigned mem_nid = pxm_to_node(target->memory_pxm); - node_set_perf_attrs(mem_nid, &target->hmem_attrs[access], access); + node_set_perf_attrs(mem_nid, &target->coord[access], access); } static void hmat_register_target_devices(struct memory_target *target) @@ -713,6 +830,17 @@ static void hmat_register_target(struct memory_target *target) hmat_register_target_devices(target); /* + * Register generic port perf numbers. The nid may not be + * initialized and is still NUMA_NO_NODE. + */ + mutex_lock(&target_lock); + if (*(u16 *)target->gen_port_device_handle) { + hmat_register_generic_target_initiators(target); + target->registered = true; + } + mutex_unlock(&target_lock); + + /* * Skip offline nodes. This can happen when memory * marked EFI_MEMORY_SP, "specific purpose", is applied * to all the memory in a proximity domain leading to @@ -726,8 +854,8 @@ static void hmat_register_target(struct memory_target *target) if (!target->registered) { hmat_register_target_initiators(target); hmat_register_target_cache(target); - hmat_register_target_perf(target, 0); - hmat_register_target_perf(target, 1); + hmat_register_target_perf(target, NODE_ACCESS_CLASS_0); + hmat_register_target_perf(target, NODE_ACCESS_CLASS_1); target->registered = true; } mutex_unlock(&target_lock); @@ -765,7 +893,7 @@ static int hmat_set_default_dram_perf(void) int rc; int nid, pxm; struct memory_target *target; - struct node_hmem_attrs *attrs; + struct access_coordinate *attrs; if (!default_dram_type) return -EIO; @@ -775,7 +903,7 @@ static int hmat_set_default_dram_perf(void) target = find_mem_target(pxm); if (!target) continue; - attrs = &target->hmem_attrs[1]; + attrs = &target->coord[1]; rc = mt_set_default_dram_perf(nid, attrs, "ACPI HMAT"); if (rc) return rc; @@ -789,7 +917,7 @@ static int hmat_calculate_adistance(struct notifier_block *self, { static DECLARE_BITMAP(p_nodes, MAX_NUMNODES); struct memory_target *target; - struct node_hmem_attrs *perf; + struct access_coordinate *perf; int *adist = data; int pxm; @@ -802,7 +930,7 @@ static int hmat_calculate_adistance(struct notifier_block *self, hmat_update_target_attrs(target, p_nodes, 1); mutex_unlock(&target_lock); - perf = &target->hmem_attrs[1]; + perf = &target->coord[1]; if (mt_perf_to_adistance(perf, adist)) return NOTIFY_OK; @@ -870,6 +998,13 @@ static __init int hmat_init(void) ACPI_SRAT_TYPE_MEMORY_AFFINITY, srat_parse_mem_affinity, 0) < 0) goto out_put; + + if (acpi_table_parse_entries(ACPI_SIG_SRAT, + sizeof(struct acpi_table_srat), + ACPI_SRAT_TYPE_GENERIC_PORT_AFFINITY, + srat_parse_genport_affinity, 0) < 0) + goto out_put; + acpi_put_table(tbl); status = acpi_get_table(ACPI_SIG_HMAT, 0, &tbl); diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 0ba008773b00..e6ed1ba91e5c 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1561,8 +1561,7 @@ static inline const struct iommu_ops *acpi_iommu_fwspec_ops(struct device *dev) return fwspec ? fwspec->ops : NULL; } -static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev, - const u32 *id_in) +static int acpi_iommu_configure_id(struct device *dev, const u32 *id_in) { int err; const struct iommu_ops *ops; @@ -1576,7 +1575,7 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev, ops = acpi_iommu_fwspec_ops(dev); if (ops) { mutex_unlock(&iommu_probe_device_lock); - return ops; + return 0; } err = iort_iommu_configure_id(dev, id_in); @@ -1593,12 +1592,14 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev, /* Ignore all other errors apart from EPROBE_DEFER */ if (err == -EPROBE_DEFER) { - return ERR_PTR(err); + return err; } else if (err) { dev_dbg(dev, "Adding to IOMMU failed: %d\n", err); - return NULL; + return -ENODEV; } - return acpi_iommu_fwspec_ops(dev); + if (!acpi_iommu_fwspec_ops(dev)) + return -ENODEV; + return 0; } #else /* !CONFIG_IOMMU_API */ @@ -1610,10 +1611,9 @@ int acpi_iommu_fwspec_init(struct device *dev, u32 id, return -ENODEV; } -static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev, - const u32 *id_in) +static int acpi_iommu_configure_id(struct device *dev, const u32 *id_in) { - return NULL; + return -ENODEV; } #endif /* !CONFIG_IOMMU_API */ @@ -1627,7 +1627,7 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev, int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr, const u32 *input_id) { - const struct iommu_ops *iommu; + int ret; if (attr == DEV_DMA_NOT_SUPPORTED) { set_dma_ops(dev, &dma_dummy_ops); @@ -1636,12 +1636,16 @@ int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr, acpi_arch_dma_setup(dev); - iommu = acpi_iommu_configure_id(dev, input_id); - if (PTR_ERR(iommu) == -EPROBE_DEFER) + ret = acpi_iommu_configure_id(dev, input_id); + if (ret == -EPROBE_DEFER) return -EPROBE_DEFER; - arch_setup_dma_ops(dev, 0, U64_MAX, - iommu, attr == DEV_DMA_COHERENT); + /* + * Historically this routine doesn't fail driver probing due to errors + * in acpi_iommu_configure_id() + */ + + arch_setup_dma_ops(dev, 0, U64_MAX, attr == DEV_DMA_COHERENT); return 0; } diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index c1516337f668..b07f7d091d13 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -251,8 +251,9 @@ int __init_or_acpilib acpi_table_parse_entries_array( return -ENODEV; } - count = acpi_parse_entries_array(id, table_size, table_header, - proc, proc_num, max_entries); + count = acpi_parse_entries_array(id, table_size, + (union fw_table_header *)table_header, + proc, proc_num, max_entries); acpi_put_table(table_header); return count; diff --git a/drivers/base/node.c b/drivers/base/node.c index 433897eecbdc..1c05640461dd 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -74,14 +74,14 @@ static BIN_ATTR_RO(cpulist, CPULIST_FILE_MAX_BYTES); * @dev: Device for this memory access class * @list_node: List element in the node's access list * @access: The access class rank - * @hmem_attrs: Heterogeneous memory performance attributes + * @coord: Heterogeneous memory performance coordinates */ struct node_access_nodes { struct device dev; struct list_head list_node; unsigned int access; #ifdef CONFIG_HMEM_REPORTING - struct node_hmem_attrs hmem_attrs; + struct access_coordinate coord; #endif }; #define to_access_nodes(dev) container_of(dev, struct node_access_nodes, dev) @@ -167,7 +167,7 @@ static ssize_t property##_show(struct device *dev, \ char *buf) \ { \ return sysfs_emit(buf, "%u\n", \ - to_access_nodes(dev)->hmem_attrs.property); \ + to_access_nodes(dev)->coord.property); \ } \ static DEVICE_ATTR_RO(property) @@ -187,10 +187,10 @@ static struct attribute *access_attrs[] = { /** * node_set_perf_attrs - Set the performance values for given access class * @nid: Node identifier to be set - * @hmem_attrs: Heterogeneous memory performance attributes + * @coord: Heterogeneous memory performance coordinates * @access: The access class the for the given attributes */ -void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs, +void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord, unsigned int access) { struct node_access_nodes *c; @@ -205,7 +205,7 @@ void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs, if (!c) return; - c->hmem_attrs = *hmem_attrs; + c->coord = *coord; for (i = 0; access_attrs[i] != NULL; i++) { if (sysfs_add_file_to_group(&c->dev.kobj, access_attrs[i], "initiators")) { diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c index 72b7a92337b1..cd6e559648b2 100644 --- a/drivers/base/power/trace.c +++ b/drivers/base/power/trace.c @@ -120,7 +120,7 @@ static unsigned int read_magic_time(void) struct rtc_time time; unsigned int val; - if (mc146818_get_time(&time) < 0) { + if (mc146818_get_time(&time, 1000) < 0) { pr_err("Unable to read current time from RTC\n"); return 0; } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 146b32fa7b47..f8145499da38 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -165,39 +165,37 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file) return get_size(lo->lo_offset, lo->lo_sizelimit, file); } +/* + * We support direct I/O only if lo_offset is aligned with the logical I/O size + * of backing device, and the logical block size of loop is bigger than that of + * the backing device. + */ +static bool lo_bdev_can_use_dio(struct loop_device *lo, + struct block_device *backing_bdev) +{ + unsigned short sb_bsize = bdev_logical_block_size(backing_bdev); + + if (queue_logical_block_size(lo->lo_queue) < sb_bsize) + return false; + if (lo->lo_offset & (sb_bsize - 1)) + return false; + return true; +} + static void __loop_update_dio(struct loop_device *lo, bool dio) { struct file *file = lo->lo_backing_file; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - unsigned short sb_bsize = 0; - unsigned dio_align = 0; + struct inode *inode = file->f_mapping->host; + struct block_device *backing_bdev = NULL; bool use_dio; - if (inode->i_sb->s_bdev) { - sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev); - dio_align = sb_bsize - 1; - } + if (S_ISBLK(inode->i_mode)) + backing_bdev = I_BDEV(inode); + else if (inode->i_sb->s_bdev) + backing_bdev = inode->i_sb->s_bdev; - /* - * We support direct I/O only if lo_offset is aligned with the - * logical I/O size of backing device, and the logical block - * size of loop is bigger than the backing device's. - * - * TODO: the above condition may be loosed in the future, and - * direct I/O may be switched runtime at that time because most - * of requests in sane applications should be PAGE_SIZE aligned - */ - if (dio) { - if (queue_logical_block_size(lo->lo_queue) >= sb_bsize && - !(lo->lo_offset & dio_align) && - (file->f_mode & FMODE_CAN_ODIRECT)) - use_dio = true; - else - use_dio = false; - } else { - use_dio = false; - } + use_dio = dio && (file->f_mode & FMODE_CAN_ODIRECT) && + (!backing_bdev || lo_bdev_can_use_dio(lo, backing_bdev)); if (lo->use_dio == use_dio) return; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 4e72ec4e25ac..33a8f37bb6a1 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -508,7 +508,7 @@ static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send, struct iov_iter *iter, int msg_flags, int *sent) { int result; - struct msghdr msg; + struct msghdr msg = {} ; unsigned int noreclaim_flag; if (unlikely(!sock)) { @@ -524,10 +524,6 @@ static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send, do { sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC; sock->sk->sk_use_task_frag = false; - msg.msg_name = NULL; - msg.msg_namelen = 0; - msg.msg_control = NULL; - msg.msg_controllen = 0; msg.msg_flags = msg_flags | MSG_NOSIGNAL; if (send) diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 9f7695f00c2d..36755f263e8e 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1840,7 +1840,7 @@ static void null_del_dev(struct nullb *nullb) dev = nullb->dev; - ida_simple_remove(&nullb_indexes, nullb->index); + ida_free(&nullb_indexes, nullb->index); list_del_init(&nullb->list); @@ -2174,7 +2174,7 @@ static int null_add_dev(struct nullb_device *dev) blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q); mutex_lock(&lock); - rv = ida_simple_get(&nullb_indexes, 0, 0, GFP_KERNEL); + rv = ida_alloc(&nullb_indexes, GFP_KERNEL); if (rv < 0) { mutex_unlock(&lock); goto out_cleanup_zone; diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 3b6b9abb8ce1..5bf98fd6a651 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -367,8 +367,6 @@ static void virtblk_done(struct virtqueue *vq) blk_mq_complete_request(req); req_done = true; } - if (unlikely(virtqueue_is_broken(vq))) - break; } while (!virtqueue_enable_cb(vq)); /* In case queue is stopped waiting for more buffers. */ diff --git a/drivers/clk/qcom/gcc-x1e80100.c b/drivers/clk/qcom/gcc-x1e80100.c index 74db7fef237b..d7182d6e9783 100644 --- a/drivers/clk/qcom/gcc-x1e80100.c +++ b/drivers/clk/qcom/gcc-x1e80100.c @@ -4,8 +4,9 @@ */ #include <linux/clk-provider.h> +#include <linux/mod_devicetable.h> #include <linux/module.h> -#include <linux/of_device.h> +#include <linux/platform_device.h> #include <linux/regmap.h> #include <dt-bindings/clock/qcom,x1e80100-gcc.h> diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig index 8ea1d340e438..67998dbd1d46 100644 --- a/drivers/cxl/Kconfig +++ b/drivers/cxl/Kconfig @@ -5,6 +5,7 @@ menuconfig CXL_BUS select FW_LOADER select FW_UPLOAD select PCI_DOE + select FIRMWARE_TABLE help CXL is a bus that is electrically compatible with PCI Express, but layers three protocols on that signalling (CXL.io, CXL.cache, and @@ -54,8 +55,10 @@ config CXL_MEM_RAW_COMMANDS config CXL_ACPI tristate "CXL ACPI: Platform Support" depends on ACPI + depends on ACPI_NUMA default CXL_BUS select ACPI_TABLE_LIB + select ACPI_HMAT help Enable support for host managed device memory (HDM) resources published by a platform's ACPI CXL memory layout description. See diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index 2034eb4ce83f..dcf2b39e1048 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -6,6 +6,7 @@ #include <linux/kernel.h> #include <linux/acpi.h> #include <linux/pci.h> +#include <linux/node.h> #include <asm/div64.h> #include "cxlpci.h" #include "cxl.h" @@ -17,6 +18,10 @@ struct cxl_cxims_data { u64 xormaps[] __counted_by(nr_maps); }; +static const guid_t acpi_cxl_qtg_id_guid = + GUID_INIT(0xF365F9A6, 0xA7DE, 0x4071, + 0xA6, 0x6A, 0xB4, 0x0C, 0x0B, 0x4F, 0x8E, 0x52); + /* * Find a targets entry (n) in the host bridge interleave list. * CXL Specification 3.0 Table 9-22 @@ -194,6 +199,123 @@ struct cxl_cfmws_context { int id; }; +/** + * cxl_acpi_evaluate_qtg_dsm - Retrieve QTG ids via ACPI _DSM + * @handle: ACPI handle + * @coord: performance access coordinates + * @entries: number of QTG IDs to return + * @qos_class: int array provided by caller to return QTG IDs + * + * Return: number of QTG IDs returned, or -errno for errors + * + * Issue QTG _DSM with accompanied bandwidth and latency data in order to get + * the QTG IDs that are suitable for the performance point in order of most + * suitable to least suitable. Write back array of QTG IDs and return the + * actual number of QTG IDs written back. + */ +static int +cxl_acpi_evaluate_qtg_dsm(acpi_handle handle, struct access_coordinate *coord, + int entries, int *qos_class) +{ + union acpi_object *out_obj, *out_buf, *obj; + union acpi_object in_array[4] = { + [0].integer = { ACPI_TYPE_INTEGER, coord->read_latency }, + [1].integer = { ACPI_TYPE_INTEGER, coord->write_latency }, + [2].integer = { ACPI_TYPE_INTEGER, coord->read_bandwidth }, + [3].integer = { ACPI_TYPE_INTEGER, coord->write_bandwidth }, + }; + union acpi_object in_obj = { + .package = { + .type = ACPI_TYPE_PACKAGE, + .count = 4, + .elements = in_array, + }, + }; + int count, pkg_entries, i; + u16 max_qtg; + int rc; + + if (!entries) + return -EINVAL; + + out_obj = acpi_evaluate_dsm(handle, &acpi_cxl_qtg_id_guid, 1, 1, &in_obj); + if (!out_obj) + return -ENXIO; + + if (out_obj->type != ACPI_TYPE_PACKAGE) { + rc = -ENXIO; + goto out; + } + + /* Check Max QTG ID */ + obj = &out_obj->package.elements[0]; + if (obj->type != ACPI_TYPE_INTEGER) { + rc = -ENXIO; + goto out; + } + + max_qtg = obj->integer.value; + + /* It's legal to have 0 QTG entries */ + pkg_entries = out_obj->package.count; + if (pkg_entries <= 1) { + rc = 0; + goto out; + } + + /* Retrieve QTG IDs package */ + obj = &out_obj->package.elements[1]; + if (obj->type != ACPI_TYPE_PACKAGE) { + rc = -ENXIO; + goto out; + } + + pkg_entries = obj->package.count; + count = min(entries, pkg_entries); + for (i = 0; i < count; i++) { + u16 qtg_id; + + out_buf = &obj->package.elements[i]; + if (out_buf->type != ACPI_TYPE_INTEGER) { + rc = -ENXIO; + goto out; + } + + qtg_id = out_buf->integer.value; + if (qtg_id > max_qtg) + pr_warn("QTG ID %u greater than MAX %u\n", + qtg_id, max_qtg); + + qos_class[i] = qtg_id; + } + rc = count; + +out: + ACPI_FREE(out_obj); + return rc; +} + +static int cxl_acpi_qos_class(struct cxl_root *cxl_root, + struct access_coordinate *coord, int entries, + int *qos_class) +{ + struct device *dev = cxl_root->port.uport_dev; + acpi_handle handle; + + if (!dev_is_platform(dev)) + return -ENODEV; + + handle = ACPI_HANDLE(dev); + if (!handle) + return -ENODEV; + + return cxl_acpi_evaluate_qtg_dsm(handle, coord, entries, qos_class); +} + +static const struct cxl_root_ops acpi_root_ops = { + .qos_class = cxl_acpi_qos_class, +}; + static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, const unsigned long end) { @@ -389,8 +511,29 @@ static int cxl_get_chbs(struct device *dev, struct acpi_device *hb, return 0; } +static int get_genport_coordinates(struct device *dev, struct cxl_dport *dport) +{ + struct acpi_device *hb = to_cxl_host_bridge(NULL, dev); + u32 uid; + int rc; + + if (kstrtou32(acpi_device_uid(hb), 0, &uid)) + return -EINVAL; + + rc = acpi_get_genport_coordinates(uid, &dport->hb_coord); + if (rc < 0) + return rc; + + /* Adjust back to picoseconds from nanoseconds */ + dport->hb_coord.read_latency *= 1000; + dport->hb_coord.write_latency *= 1000; + + return 0; +} + static int add_host_bridge_dport(struct device *match, void *arg) { + int ret; acpi_status rc; struct device *bridge; struct cxl_dport *dport; @@ -440,6 +583,10 @@ static int add_host_bridge_dport(struct device *match, void *arg) if (IS_ERR(dport)) return PTR_ERR(dport); + ret = get_genport_coordinates(match, dport); + if (ret) + dev_dbg(match, "Failed to get generic port perf coordinates.\n"); + return 0; } @@ -656,6 +803,7 @@ static int cxl_acpi_probe(struct platform_device *pdev) { int rc; struct resource *cxl_res; + struct cxl_root *cxl_root; struct cxl_port *root_port; struct device *host = &pdev->dev; struct acpi_device *adev = ACPI_COMPANION(host); @@ -675,9 +823,10 @@ static int cxl_acpi_probe(struct platform_device *pdev) cxl_res->end = -1; cxl_res->flags = IORESOURCE_MEM; - root_port = devm_cxl_add_port(host, host, CXL_RESOURCE_NONE, NULL); - if (IS_ERR(root_port)) - return PTR_ERR(root_port); + cxl_root = devm_cxl_add_root(host, &acpi_root_ops); + if (IS_ERR(cxl_root)) + return PTR_ERR(cxl_root); + root_port = &cxl_root->port; rc = bus_for_each_dev(adev->dev.bus, NULL, root_port, add_host_bridge_dport); diff --git a/drivers/cxl/core/Makefile b/drivers/cxl/core/Makefile index 1f66b5d4d935..9259bcc6773c 100644 --- a/drivers/cxl/core/Makefile +++ b/drivers/cxl/core/Makefile @@ -13,5 +13,6 @@ cxl_core-y += mbox.o cxl_core-y += pci.o cxl_core-y += hdm.o cxl_core-y += pmu.o +cxl_core-y += cdat.o cxl_core-$(CONFIG_TRACING) += trace.o cxl_core-$(CONFIG_CXL_REGION) += region.o diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c new file mode 100644 index 000000000000..6fe11546889f --- /dev/null +++ b/drivers/cxl/core/cdat.c @@ -0,0 +1,521 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2023 Intel Corporation. All rights reserved. */ +#include <linux/acpi.h> +#include <linux/xarray.h> +#include <linux/fw_table.h> +#include <linux/node.h> +#include <linux/overflow.h> +#include "cxlpci.h" +#include "cxlmem.h" +#include "core.h" +#include "cxl.h" + +struct dsmas_entry { + struct range dpa_range; + u8 handle; + struct access_coordinate coord; + + int entries; + int qos_class; +}; + +static int cdat_dsmas_handler(union acpi_subtable_headers *header, void *arg, + const unsigned long end) +{ + struct acpi_cdat_header *hdr = &header->cdat; + struct acpi_cdat_dsmas *dsmas; + int size = sizeof(*hdr) + sizeof(*dsmas); + struct xarray *dsmas_xa = arg; + struct dsmas_entry *dent; + u16 len; + int rc; + + len = le16_to_cpu((__force __le16)hdr->length); + if (len != size || (unsigned long)hdr + len > end) { + pr_warn("Malformed DSMAS table length: (%u:%u)\n", size, len); + return -EINVAL; + } + + /* Skip common header */ + dsmas = (struct acpi_cdat_dsmas *)(hdr + 1); + + dent = kzalloc(sizeof(*dent), GFP_KERNEL); + if (!dent) + return -ENOMEM; + + dent->handle = dsmas->dsmad_handle; + dent->dpa_range.start = le64_to_cpu((__force __le64)dsmas->dpa_base_address); + dent->dpa_range.end = le64_to_cpu((__force __le64)dsmas->dpa_base_address) + + le64_to_cpu((__force __le64)dsmas->dpa_length) - 1; + + rc = xa_insert(dsmas_xa, dent->handle, dent, GFP_KERNEL); + if (rc) { + kfree(dent); + return rc; + } + + return 0; +} + +static void cxl_access_coordinate_set(struct access_coordinate *coord, + int access, unsigned int val) +{ + switch (access) { + case ACPI_HMAT_ACCESS_LATENCY: + coord->read_latency = val; + coord->write_latency = val; + break; + case ACPI_HMAT_READ_LATENCY: + coord->read_latency = val; + break; + case ACPI_HMAT_WRITE_LATENCY: + coord->write_latency = val; + break; + case ACPI_HMAT_ACCESS_BANDWIDTH: + coord->read_bandwidth = val; + coord->write_bandwidth = val; + break; + case ACPI_HMAT_READ_BANDWIDTH: + coord->read_bandwidth = val; + break; + case ACPI_HMAT_WRITE_BANDWIDTH: + coord->write_bandwidth = val; + break; + } +} + +static int cdat_dslbis_handler(union acpi_subtable_headers *header, void *arg, + const unsigned long end) +{ + struct acpi_cdat_header *hdr = &header->cdat; + struct acpi_cdat_dslbis *dslbis; + int size = sizeof(*hdr) + sizeof(*dslbis); + struct xarray *dsmas_xa = arg; + struct dsmas_entry *dent; + __le64 le_base; + __le16 le_val; + u64 val; + u16 len; + int rc; + + len = le16_to_cpu((__force __le16)hdr->length); + if (len != size || (unsigned long)hdr + len > end) { + pr_warn("Malformed DSLBIS table length: (%u:%u)\n", size, len); + return -EINVAL; + } + + /* Skip common header */ + dslbis = (struct acpi_cdat_dslbis *)(hdr + 1); + + /* Skip unrecognized data type */ + if (dslbis->data_type > ACPI_HMAT_WRITE_BANDWIDTH) + return 0; + + /* Not a memory type, skip */ + if ((dslbis->flags & ACPI_HMAT_MEMORY_HIERARCHY) != ACPI_HMAT_MEMORY) + return 0; + + dent = xa_load(dsmas_xa, dslbis->handle); + if (!dent) { + pr_warn("No matching DSMAS entry for DSLBIS entry.\n"); + return 0; + } + + le_base = (__force __le64)dslbis->entry_base_unit; + le_val = (__force __le16)dslbis->entry[0]; + rc = check_mul_overflow(le64_to_cpu(le_base), + le16_to_cpu(le_val), &val); + if (rc) + pr_warn("DSLBIS value overflowed.\n"); + + cxl_access_coordinate_set(&dent->coord, dslbis->data_type, val); + + return 0; +} + +static int cdat_table_parse_output(int rc) +{ + if (rc < 0) + return rc; + if (rc == 0) + return -ENOENT; + + return 0; +} + +static int cxl_cdat_endpoint_process(struct cxl_port *port, + struct xarray *dsmas_xa) +{ + int rc; + + rc = cdat_table_parse(ACPI_CDAT_TYPE_DSMAS, cdat_dsmas_handler, + dsmas_xa, port->cdat.table); + rc = cdat_table_parse_output(rc); + if (rc) + return rc; + + rc = cdat_table_parse(ACPI_CDAT_TYPE_DSLBIS, cdat_dslbis_handler, + dsmas_xa, port->cdat.table); + return cdat_table_parse_output(rc); +} + +static int cxl_port_perf_data_calculate(struct cxl_port *port, + struct xarray *dsmas_xa) +{ + struct access_coordinate c; + struct dsmas_entry *dent; + int valid_entries = 0; + unsigned long index; + int rc; + + rc = cxl_endpoint_get_perf_coordinates(port, &c); + if (rc) { + dev_dbg(&port->dev, "Failed to retrieve perf coordinates.\n"); + return rc; + } + + struct cxl_root *cxl_root __free(put_cxl_root) = find_cxl_root(port); + + if (!cxl_root) + return -ENODEV; + + if (!cxl_root->ops || !cxl_root->ops->qos_class) + return -EOPNOTSUPP; + + xa_for_each(dsmas_xa, index, dent) { + int qos_class; + + dent->coord.read_latency = dent->coord.read_latency + + c.read_latency; + dent->coord.write_latency = dent->coord.write_latency + + c.write_latency; + dent->coord.read_bandwidth = min_t(int, c.read_bandwidth, + dent->coord.read_bandwidth); + dent->coord.write_bandwidth = min_t(int, c.write_bandwidth, + dent->coord.write_bandwidth); + + dent->entries = 1; + rc = cxl_root->ops->qos_class(cxl_root, &dent->coord, 1, + &qos_class); + if (rc != 1) + continue; + + valid_entries++; + dent->qos_class = qos_class; + } + + if (!valid_entries) + return -ENOENT; + + return 0; +} + +static void add_perf_entry(struct device *dev, struct dsmas_entry *dent, + struct list_head *list) +{ + struct cxl_dpa_perf *dpa_perf; + + dpa_perf = kzalloc(sizeof(*dpa_perf), GFP_KERNEL); + if (!dpa_perf) + return; + + dpa_perf->dpa_range = dent->dpa_range; + dpa_perf->coord = dent->coord; + dpa_perf->qos_class = dent->qos_class; + list_add_tail(&dpa_perf->list, list); + dev_dbg(dev, + "DSMAS: dpa: %#llx qos: %d read_bw: %d write_bw %d read_lat: %d write_lat: %d\n", + dent->dpa_range.start, dpa_perf->qos_class, + dent->coord.read_bandwidth, dent->coord.write_bandwidth, + dent->coord.read_latency, dent->coord.write_latency); +} + +static void free_perf_ents(void *data) +{ + struct cxl_memdev_state *mds = data; + struct cxl_dpa_perf *dpa_perf, *n; + LIST_HEAD(discard); + + list_splice_tail_init(&mds->ram_perf_list, &discard); + list_splice_tail_init(&mds->pmem_perf_list, &discard); + list_for_each_entry_safe(dpa_perf, n, &discard, list) { + list_del(&dpa_perf->list); + kfree(dpa_perf); + } +} + +static void cxl_memdev_set_qos_class(struct cxl_dev_state *cxlds, + struct xarray *dsmas_xa) +{ + struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); + struct device *dev = cxlds->dev; + struct range pmem_range = { + .start = cxlds->pmem_res.start, + .end = cxlds->pmem_res.end, + }; + struct range ram_range = { + .start = cxlds->ram_res.start, + .end = cxlds->ram_res.end, + }; + struct dsmas_entry *dent; + unsigned long index; + + xa_for_each(dsmas_xa, index, dent) { + if (resource_size(&cxlds->ram_res) && + range_contains(&ram_range, &dent->dpa_range)) + add_perf_entry(dev, dent, &mds->ram_perf_list); + else if (resource_size(&cxlds->pmem_res) && + range_contains(&pmem_range, &dent->dpa_range)) + add_perf_entry(dev, dent, &mds->pmem_perf_list); + else + dev_dbg(dev, "no partition for dsmas dpa: %#llx\n", + dent->dpa_range.start); + } + + devm_add_action_or_reset(&cxlds->cxlmd->dev, free_perf_ents, mds); +} + +static int match_cxlrd_qos_class(struct device *dev, void *data) +{ + int dev_qos_class = *(int *)data; + struct cxl_root_decoder *cxlrd; + + if (!is_root_decoder(dev)) + return 0; + + cxlrd = to_cxl_root_decoder(dev); + if (cxlrd->qos_class == CXL_QOS_CLASS_INVALID) + return 0; + + if (cxlrd->qos_class == dev_qos_class) + return 1; + + return 0; +} + +static void cxl_qos_match(struct cxl_port *root_port, + struct list_head *work_list, + struct list_head *discard_list) +{ + struct cxl_dpa_perf *dpa_perf, *n; + + list_for_each_entry_safe(dpa_perf, n, work_list, list) { + int rc; + + if (dpa_perf->qos_class == CXL_QOS_CLASS_INVALID) + return; + + rc = device_for_each_child(&root_port->dev, + (void *)&dpa_perf->qos_class, + match_cxlrd_qos_class); + if (!rc) + list_move_tail(&dpa_perf->list, discard_list); + } +} + +static int match_cxlrd_hb(struct device *dev, void *data) +{ + struct device *host_bridge = data; + struct cxl_switch_decoder *cxlsd; + struct cxl_root_decoder *cxlrd; + + if (!is_root_decoder(dev)) + return 0; + + cxlrd = to_cxl_root_decoder(dev); + cxlsd = &cxlrd->cxlsd; + + guard(rwsem_read)(&cxl_region_rwsem); + for (int i = 0; i < cxlsd->nr_targets; i++) { + if (host_bridge == cxlsd->target[i]->dport_dev) + return 1; + } + + return 0; +} + +static void discard_dpa_perf(struct list_head *list) +{ + struct cxl_dpa_perf *dpa_perf, *n; + + list_for_each_entry_safe(dpa_perf, n, list, list) { + list_del(&dpa_perf->list); + kfree(dpa_perf); + } +} +DEFINE_FREE(dpa_perf, struct list_head *, if (!list_empty(_T)) discard_dpa_perf(_T)) + +static int cxl_qos_class_verify(struct cxl_memdev *cxlmd) +{ + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); + LIST_HEAD(__discard); + struct list_head *discard __free(dpa_perf) = &__discard; + struct cxl_port *root_port; + int rc; + + struct cxl_root *cxl_root __free(put_cxl_root) = + find_cxl_root(cxlmd->endpoint); + + if (!cxl_root) + return -ENODEV; + + root_port = &cxl_root->port; + + /* Check that the QTG IDs are all sane between end device and root decoders */ + cxl_qos_match(root_port, &mds->ram_perf_list, discard); + cxl_qos_match(root_port, &mds->pmem_perf_list, discard); + + /* Check to make sure that the device's host bridge is under a root decoder */ + rc = device_for_each_child(&root_port->dev, + (void *)cxlmd->endpoint->host_bridge, + match_cxlrd_hb); + if (!rc) { + list_splice_tail_init(&mds->ram_perf_list, discard); + list_splice_tail_init(&mds->pmem_perf_list, discard); + } + + return rc; +} + +static void discard_dsmas(struct xarray *xa) +{ + unsigned long index; + void *ent; + + xa_for_each(xa, index, ent) { + xa_erase(xa, index); + kfree(ent); + } + xa_destroy(xa); +} +DEFINE_FREE(dsmas, struct xarray *, if (_T) discard_dsmas(_T)) + +void cxl_endpoint_parse_cdat(struct cxl_port *port) +{ + struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev); + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct xarray __dsmas_xa; + struct xarray *dsmas_xa __free(dsmas) = &__dsmas_xa; + int rc; + + xa_init(&__dsmas_xa); + if (!port->cdat.table) + return; + + rc = cxl_cdat_endpoint_process(port, dsmas_xa); + if (rc < 0) { + dev_dbg(&port->dev, "Failed to parse CDAT: %d\n", rc); + return; + } + + rc = cxl_port_perf_data_calculate(port, dsmas_xa); + if (rc) { + dev_dbg(&port->dev, "Failed to do perf coord calculations.\n"); + return; + } + + cxl_memdev_set_qos_class(cxlds, dsmas_xa); + cxl_qos_class_verify(cxlmd); +} +EXPORT_SYMBOL_NS_GPL(cxl_endpoint_parse_cdat, CXL); + +static int cdat_sslbis_handler(union acpi_subtable_headers *header, void *arg, + const unsigned long end) +{ + struct acpi_cdat_sslbis *sslbis; + int size = sizeof(header->cdat) + sizeof(*sslbis); + struct cxl_port *port = arg; + struct device *dev = &port->dev; + struct acpi_cdat_sslbe *entry; + int remain, entries, i; + u16 len; + + len = le16_to_cpu((__force __le16)header->cdat.length); + remain = len - size; + if (!remain || remain % sizeof(*entry) || + (unsigned long)header + len > end) { + dev_warn(dev, "Malformed SSLBIS table length: (%u)\n", len); + return -EINVAL; + } + + /* Skip common header */ + sslbis = (struct acpi_cdat_sslbis *)((unsigned long)header + + sizeof(header->cdat)); + + /* Unrecognized data type, we can skip */ + if (sslbis->data_type > ACPI_HMAT_WRITE_BANDWIDTH) + return 0; + + entries = remain / sizeof(*entry); + entry = (struct acpi_cdat_sslbe *)((unsigned long)header + sizeof(*sslbis)); + + for (i = 0; i < entries; i++) { + u16 x = le16_to_cpu((__force __le16)entry->portx_id); + u16 y = le16_to_cpu((__force __le16)entry->porty_id); + __le64 le_base; + __le16 le_val; + struct cxl_dport *dport; + unsigned long index; + u16 dsp_id; + u64 val; + + switch (x) { + case ACPI_CDAT_SSLBIS_US_PORT: + dsp_id = y; + break; + case ACPI_CDAT_SSLBIS_ANY_PORT: + switch (y) { + case ACPI_CDAT_SSLBIS_US_PORT: + dsp_id = x; + break; + case ACPI_CDAT_SSLBIS_ANY_PORT: + dsp_id = ACPI_CDAT_SSLBIS_ANY_PORT; + break; + default: + dsp_id = y; + break; + } + break; + default: + dsp_id = x; + break; + } + + le_base = (__force __le64)sslbis->entry_base_unit; + le_val = (__force __le16)entry->latency_or_bandwidth; + + if (check_mul_overflow(le64_to_cpu(le_base), + le16_to_cpu(le_val), &val)) + dev_warn(dev, "SSLBIS value overflowed!\n"); + + xa_for_each(&port->dports, index, dport) { + if (dsp_id == ACPI_CDAT_SSLBIS_ANY_PORT || + dsp_id == dport->port_id) + cxl_access_coordinate_set(&dport->sw_coord, + sslbis->data_type, + val); + } + + entry++; + } + + return 0; +} + +void cxl_switch_parse_cdat(struct cxl_port *port) +{ + int rc; + + if (!port->cdat.table) + return; + + rc = cdat_table_parse(ACPI_CDAT_TYPE_SSLBIS, cdat_sslbis_handler, + port, port->cdat.table); + rc = cdat_table_parse_output(rc); + if (rc) + dev_dbg(&port->dev, "Failed to parse SSLBIS: %d\n", rc); +} +EXPORT_SYMBOL_NS_GPL(cxl_switch_parse_cdat, CXL); + +MODULE_IMPORT_NS(CXL); diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index 86d7ba23235e..3b64fb1b9ed0 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -88,4 +88,6 @@ enum cxl_poison_trace_type { CXL_POISON_TRACE_CLEAR, }; +long cxl_pci_get_latency(struct pci_dev *pdev); + #endif /* __CXL_CORE_H__ */ diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 36270dcfb42e..27166a411705 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -63,6 +63,7 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = { CXL_CMD(GET_SHUTDOWN_STATE, 0, 0x1, 0), CXL_CMD(SET_SHUTDOWN_STATE, 0x1, 0, 0), CXL_CMD(GET_SCAN_MEDIA_CAPS, 0x10, 0x4, 0), + CXL_CMD(GET_TIMESTAMP, 0, 0x8, 0), }; /* @@ -836,54 +837,37 @@ out: } EXPORT_SYMBOL_NS_GPL(cxl_enumerate_cmds, CXL); -/* - * General Media Event Record - * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 - */ -static const uuid_t gen_media_event_uuid = - UUID_INIT(0xfbcd0a77, 0xc260, 0x417f, - 0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6); - -/* - * DRAM Event Record - * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44 - */ -static const uuid_t dram_event_uuid = - UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, - 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24); - -/* - * Memory Module Event Record - * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45 - */ -static const uuid_t mem_mod_event_uuid = - UUID_INIT(0xfe927475, 0xdd59, 0x4339, - 0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74); - -static void cxl_event_trace_record(const struct cxl_memdev *cxlmd, - enum cxl_event_log_type type, - struct cxl_event_record_raw *record) +void cxl_event_trace_record(const struct cxl_memdev *cxlmd, + enum cxl_event_log_type type, + enum cxl_event_type event_type, + const uuid_t *uuid, union cxl_event *evt) { - uuid_t *id = &record->hdr.id; - - if (uuid_equal(id, &gen_media_event_uuid)) { - struct cxl_event_gen_media *rec = - (struct cxl_event_gen_media *)record; + if (event_type == CXL_CPER_EVENT_GEN_MEDIA) + trace_cxl_general_media(cxlmd, type, &evt->gen_media); + else if (event_type == CXL_CPER_EVENT_DRAM) + trace_cxl_dram(cxlmd, type, &evt->dram); + else if (event_type == CXL_CPER_EVENT_MEM_MODULE) + trace_cxl_memory_module(cxlmd, type, &evt->mem_module); + else + trace_cxl_generic_event(cxlmd, type, uuid, &evt->generic); +} +EXPORT_SYMBOL_NS_GPL(cxl_event_trace_record, CXL); - trace_cxl_general_media(cxlmd, type, rec); - } else if (uuid_equal(id, &dram_event_uuid)) { - struct cxl_event_dram *rec = (struct cxl_event_dram *)record; +static void __cxl_event_trace_record(const struct cxl_memdev *cxlmd, + enum cxl_event_log_type type, + struct cxl_event_record_raw *record) +{ + enum cxl_event_type ev_type = CXL_CPER_EVENT_GENERIC; + const uuid_t *uuid = &record->id; - trace_cxl_dram(cxlmd, type, rec); - } else if (uuid_equal(id, &mem_mod_event_uuid)) { - struct cxl_event_mem_module *rec = - (struct cxl_event_mem_module *)record; + if (uuid_equal(uuid, &CXL_EVENT_GEN_MEDIA_UUID)) + ev_type = CXL_CPER_EVENT_GEN_MEDIA; + else if (uuid_equal(uuid, &CXL_EVENT_DRAM_UUID)) + ev_type = CXL_CPER_EVENT_DRAM; + else if (uuid_equal(uuid, &CXL_EVENT_MEM_MODULE_UUID)) + ev_type = CXL_CPER_EVENT_MEM_MODULE; - trace_cxl_memory_module(cxlmd, type, rec); - } else { - /* For unknown record types print just the header */ - trace_cxl_generic_event(cxlmd, type, record); - } + cxl_event_trace_record(cxlmd, type, ev_type, uuid, &record->event); } static int cxl_clear_event_record(struct cxl_memdev_state *mds, @@ -926,7 +910,10 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, */ i = 0; for (cnt = 0; cnt < total; cnt++) { - payload->handles[i++] = get_pl->records[cnt].hdr.handle; + struct cxl_event_record_raw *raw = &get_pl->records[cnt]; + struct cxl_event_generic *gen = &raw->event.generic; + + payload->handles[i++] = gen->hdr.handle; dev_dbg(mds->cxlds.dev, "Event log '%d': Clearing %u\n", log, le16_to_cpu(payload->handles[i])); @@ -991,8 +978,8 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, break; for (i = 0; i < nr_rec; i++) - cxl_event_trace_record(cxlmd, type, - &payload->records[i]); + __cxl_event_trace_record(cxlmd, type, + &payload->records[i]); if (payload->flags & CXL_GET_EVENT_FLAG_OVERFLOW) trace_cxl_overflow(cxlmd, type, payload); @@ -1404,6 +1391,8 @@ struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev) mds->cxlds.reg_map.host = dev; mds->cxlds.reg_map.resource = CXL_RESOURCE_NONE; mds->cxlds.type = CXL_DEVTYPE_CLASSMEM; + INIT_LIST_HEAD(&mds->ram_perf_list); + INIT_LIST_HEAD(&mds->pmem_perf_list); return mds; } diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 2f43d368ba07..dae8802ecdb0 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -114,7 +114,7 @@ static DEVICE_ATTR_RO(serial); static ssize_t numa_node_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", dev_to_node(dev)); + return sysfs_emit(buf, "%d\n", dev_to_node(dev)); } static DEVICE_ATTR_RO(numa_node); diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 37e1652afbc7..6c9c8d92f8f7 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2021 Intel Corporation. All rights reserved. */ +#include <linux/units.h> #include <linux/io-64-nonatomic-lo-hi.h> #include <linux/device.h> #include <linux/delay.h> @@ -979,3 +980,38 @@ pci_ers_result_t cxl_error_detected(struct pci_dev *pdev, return PCI_ERS_RESULT_NEED_RESET; } EXPORT_SYMBOL_NS_GPL(cxl_error_detected, CXL); + +static int cxl_flit_size(struct pci_dev *pdev) +{ + if (cxl_pci_flit_256(pdev)) + return 256; + + return 68; +} + +/** + * cxl_pci_get_latency - calculate the link latency for the PCIe link + * @pdev: PCI device + * + * return: calculated latency or 0 for no latency + * + * CXL Memory Device SW Guide v1.0 2.11.4 Link latency calculation + * Link latency = LinkPropagationLatency + FlitLatency + RetimerLatency + * LinkProgationLatency is negligible, so 0 will be used + * RetimerLatency is assumed to be negligible and 0 will be used + * FlitLatency = FlitSize / LinkBandwidth + * FlitSize is defined by spec. CXL rev3.0 4.2.1. + * 68B flit is used up to 32GT/s. >32GT/s, 256B flit size is used. + * The FlitLatency is converted to picoseconds. + */ +long cxl_pci_get_latency(struct pci_dev *pdev) +{ + long bw; + + bw = pcie_link_speed_mbps(pdev); + if (bw < 0) + return 0; + bw /= BITS_PER_BYTE; + + return cxl_flit_size(pdev) * MEGA / bw; +} diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c index fc94f5240327..e69625a8d6a1 100644 --- a/drivers/cxl/core/pmem.c +++ b/drivers/cxl/core/pmem.c @@ -64,14 +64,14 @@ static int match_nvdimm_bridge(struct device *dev, void *data) struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_memdev *cxlmd) { - struct cxl_port *port = find_cxl_root(cxlmd->endpoint); + struct cxl_root *cxl_root __free(put_cxl_root) = + find_cxl_root(cxlmd->endpoint); struct device *dev; - if (!port) + if (!cxl_root) return NULL; - dev = device_find_child(&port->dev, NULL, match_nvdimm_bridge); - put_device(&port->dev); + dev = device_find_child(&cxl_root->port.dev, NULL, match_nvdimm_bridge); if (!dev) return NULL; diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index b7c93bb18f6e..e59d9d37aa65 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -9,6 +9,7 @@ #include <linux/pci.h> #include <linux/slab.h> #include <linux/idr.h> +#include <linux/node.h> #include <cxlmem.h> #include <cxlpci.h> #include <cxl.h> @@ -172,14 +173,10 @@ static ssize_t target_list_show(struct device *dev, { struct cxl_switch_decoder *cxlsd = to_cxl_switch_decoder(dev); ssize_t offset; - unsigned int seq; int rc; - do { - seq = read_seqbegin(&cxlsd->target_lock); - rc = emit_target_list(cxlsd, buf); - } while (read_seqretry(&cxlsd->target_lock, seq)); - + guard(rwsem_read)(&cxl_region_rwsem); + rc = emit_target_list(cxlsd, buf); if (rc < 0) return rc; offset = rc; @@ -541,7 +538,10 @@ static void cxl_port_release(struct device *dev) xa_destroy(&port->dports); xa_destroy(&port->regions); ida_free(&cxl_port_ida, port->id); - kfree(port); + if (is_cxl_root(port)) + kfree(to_cxl_root(port)); + else + kfree(port); } static ssize_t decoders_committed_show(struct device *dev, @@ -669,17 +669,31 @@ static struct lock_class_key cxl_port_key; static struct cxl_port *cxl_port_alloc(struct device *uport_dev, struct cxl_dport *parent_dport) { - struct cxl_port *port; + struct cxl_root *cxl_root __free(kfree) = NULL; + struct cxl_port *port, *_port __free(kfree) = NULL; struct device *dev; int rc; - port = kzalloc(sizeof(*port), GFP_KERNEL); - if (!port) - return ERR_PTR(-ENOMEM); + /* No parent_dport, root cxl_port */ + if (!parent_dport) { + cxl_root = kzalloc(sizeof(*cxl_root), GFP_KERNEL); + if (!cxl_root) + return ERR_PTR(-ENOMEM); + } else { + _port = kzalloc(sizeof(*port), GFP_KERNEL); + if (!_port) + return ERR_PTR(-ENOMEM); + } rc = ida_alloc(&cxl_port_ida, GFP_KERNEL); if (rc < 0) - goto err; + return ERR_PTR(rc); + + if (cxl_root) + port = &no_free_ptr(cxl_root)->port; + else + port = no_free_ptr(_port); + port->id = rc; port->uport_dev = uport_dev; @@ -731,10 +745,6 @@ static struct cxl_port *cxl_port_alloc(struct device *uport_dev, dev->type = &cxl_port_type; return port; - -err: - kfree(port); - return ERR_PTR(rc); } static int cxl_setup_comp_regs(struct device *host, struct cxl_register_map *map, @@ -841,6 +851,9 @@ static struct cxl_port *__devm_cxl_add_port(struct device *host, if (rc) return ERR_PTR(rc); + if (parent_dport && dev_is_pci(uport_dev)) + port->pci_latency = cxl_pci_get_latency(to_pci_dev(uport_dev)); + return port; err: @@ -884,6 +897,22 @@ struct cxl_port *devm_cxl_add_port(struct device *host, } EXPORT_SYMBOL_NS_GPL(devm_cxl_add_port, CXL); +struct cxl_root *devm_cxl_add_root(struct device *host, + const struct cxl_root_ops *ops) +{ + struct cxl_root *cxl_root; + struct cxl_port *port; + + port = devm_cxl_add_port(host, host, CXL_RESOURCE_NONE, NULL); + if (IS_ERR(port)) + return (struct cxl_root *)port; + + cxl_root = to_cxl_root(port); + cxl_root->ops = ops; + return cxl_root; +} +EXPORT_SYMBOL_NS_GPL(devm_cxl_add_root, CXL); + struct pci_bus *cxl_port_to_pci_bus(struct cxl_port *port) { /* There is no pci_bus associated with a CXL platform-root port */ @@ -939,7 +968,7 @@ static bool dev_is_cxl_root_child(struct device *dev) return false; } -struct cxl_port *find_cxl_root(struct cxl_port *port) +struct cxl_root *find_cxl_root(struct cxl_port *port) { struct cxl_port *iter = port; @@ -949,10 +978,19 @@ struct cxl_port *find_cxl_root(struct cxl_port *port) if (!iter) return NULL; get_device(&iter->dev); - return iter; + return to_cxl_root(iter); } EXPORT_SYMBOL_NS_GPL(find_cxl_root, CXL); +void put_cxl_root(struct cxl_root *cxl_root) +{ + if (!cxl_root) + return; + + put_device(&cxl_root->port.dev); +} +EXPORT_SYMBOL_NS_GPL(put_cxl_root, CXL); + static struct cxl_dport *find_dport(struct cxl_port *port, int id) { struct cxl_dport *dport; @@ -1108,6 +1146,9 @@ __devm_cxl_add_dport(struct cxl_port *port, struct device *dport_dev, if (rc) return ERR_PTR(rc); + if (dev_is_pci(dport_dev)) + dport->link_latency = cxl_pci_get_latency(to_pci_dev(dport_dev)); + return dport; } @@ -1633,7 +1674,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_mem_find_port, CXL); static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd, struct cxl_port *port, int *target_map) { - int i, rc = 0; + int i; if (!target_map) return 0; @@ -1643,19 +1684,16 @@ static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd, if (xa_empty(&port->dports)) return -EINVAL; - write_seqlock(&cxlsd->target_lock); - for (i = 0; i < cxlsd->nr_targets; i++) { + guard(rwsem_write)(&cxl_region_rwsem); + for (i = 0; i < cxlsd->cxld.interleave_ways; i++) { struct cxl_dport *dport = find_dport(port, target_map[i]); - if (!dport) { - rc = -ENXIO; - break; - } + if (!dport) + return -ENXIO; cxlsd->target[i] = dport; } - write_sequnlock(&cxlsd->target_lock); - return rc; + return 0; } struct cxl_dport *cxl_hb_modulo(struct cxl_root_decoder *cxlrd, int pos) @@ -1725,7 +1763,6 @@ static int cxl_switch_decoder_init(struct cxl_port *port, return -EINVAL; cxlsd->nr_targets = nr_targets; - seqlock_init(&cxlsd->target_lock); return cxl_decoder_init(port, &cxlsd->cxld); } @@ -2059,6 +2096,80 @@ bool schedule_cxl_memdev_detach(struct cxl_memdev *cxlmd) } EXPORT_SYMBOL_NS_GPL(schedule_cxl_memdev_detach, CXL); +static void combine_coordinates(struct access_coordinate *c1, + struct access_coordinate *c2) +{ + if (c2->write_bandwidth) + c1->write_bandwidth = min(c1->write_bandwidth, + c2->write_bandwidth); + c1->write_latency += c2->write_latency; + + if (c2->read_bandwidth) + c1->read_bandwidth = min(c1->read_bandwidth, + c2->read_bandwidth); + c1->read_latency += c2->read_latency; +} + +/** + * cxl_endpoint_get_perf_coordinates - Retrieve performance numbers stored in dports + * of CXL path + * @port: endpoint cxl_port + * @coord: output performance data + * + * Return: errno on failure, 0 on success. + */ +int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, + struct access_coordinate *coord) +{ + struct access_coordinate c = { + .read_bandwidth = UINT_MAX, + .write_bandwidth = UINT_MAX, + }; + struct cxl_port *iter = port; + struct cxl_dport *dport; + struct pci_dev *pdev; + unsigned int bw; + + if (!is_cxl_endpoint(port)) + return -EINVAL; + + dport = iter->parent_dport; + + /* + * Exit the loop when the parent port of the current port is cxl root. + * The iterative loop starts at the endpoint and gathers the + * latency of the CXL link from the current iter to the next downstream + * port each iteration. If the parent is cxl root then there is + * nothing to gather. + */ + while (iter && !is_cxl_root(to_cxl_port(iter->dev.parent))) { + combine_coordinates(&c, &dport->sw_coord); + c.write_latency += dport->link_latency; + c.read_latency += dport->link_latency; + + iter = to_cxl_port(iter->dev.parent); + dport = iter->parent_dport; + } + + /* Augment with the generic port (host bridge) perf data */ + combine_coordinates(&c, &dport->hb_coord); + + /* Get the calculated PCI paths bandwidth */ + pdev = to_pci_dev(port->uport_dev->parent); + bw = pcie_bandwidth_available(pdev, NULL, NULL, NULL); + if (bw == 0) + return -ENXIO; + bw /= BITS_PER_BYTE; + + c.write_bandwidth = min(c.write_bandwidth, bw); + c.read_bandwidth = min(c.read_bandwidth, bw); + + *coord = c; + + return 0; +} +EXPORT_SYMBOL_NS_GPL(cxl_endpoint_get_perf_coordinates, CXL); + /* for user tooling to ensure port disable work has completed */ static ssize_t flush_store(const struct bus_type *bus, const char *buf, size_t count) { diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 3e817a6f94c6..0f05692bfec3 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -397,7 +397,7 @@ static ssize_t interleave_ways_store(struct device *dev, return rc; /* - * Even for x3, x9, and x12 interleaves the region interleave must be a + * Even for x3, x6, and x12 interleaves the region interleave must be a * power of 2 multiple of the host bridge interleave. */ if (!is_power_of_2(val / cxld->interleave_ways) || @@ -552,8 +552,9 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size) res = alloc_free_mem_region(cxlrd->res, size, SZ_256M, dev_name(&cxlr->dev)); if (IS_ERR(res)) { - dev_dbg(&cxlr->dev, "failed to allocate HPA: %ld\n", - PTR_ERR(res)); + dev_dbg(&cxlr->dev, + "HPA allocation error (%ld) for size:%pap in %s %pr\n", + PTR_ERR(res), &size, cxlrd->res->name, cxlrd->res); return PTR_ERR(res); } @@ -2083,13 +2084,13 @@ static struct cxl_region *to_cxl_region(struct device *dev) return container_of(dev, struct cxl_region, dev); } -static void unregister_region(void *dev) +static void unregister_region(void *_cxlr) { - struct cxl_region *cxlr = to_cxl_region(dev); + struct cxl_region *cxlr = _cxlr; struct cxl_region_params *p = &cxlr->params; int i; - device_del(dev); + device_del(&cxlr->dev); /* * Now that region sysfs is shutdown, the parameter block is now @@ -2100,7 +2101,7 @@ static void unregister_region(void *dev) detach_target(cxlr, i); cxl_region_iomem_release(cxlr); - put_device(dev); + put_device(&cxlr->dev); } static struct lock_class_key cxl_region_key; diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h index a0b5819bc70b..89445435303a 100644 --- a/drivers/cxl/core/trace.h +++ b/drivers/cxl/core/trace.h @@ -181,6 +181,7 @@ TRACE_EVENT(cxl_overflow, * 1) Add CXL_EVT_TP_entry to TP_STRUCT__entry * 2) Use CXL_EVT_TP_fast_assign within TP_fast_assign; * pass the dev, log, and CXL event header + * NOTE: The uuid must be assigned by the specific trace event * 3) Use CXL_EVT_TP_printk() instead of TP_printk() * * See the generic_event tracepoint as an example. @@ -203,7 +204,6 @@ TRACE_EVENT(cxl_overflow, __assign_str(host, dev_name((cxlmd)->dev.parent)); \ __entry->log = (l); \ __entry->serial = (cxlmd)->cxlds->serial; \ - memcpy(&__entry->hdr_uuid, &(hdr).id, sizeof(uuid_t)); \ __entry->hdr_length = (hdr).length; \ __entry->hdr_flags = get_unaligned_le24((hdr).flags); \ __entry->hdr_handle = le16_to_cpu((hdr).handle); \ @@ -225,9 +225,9 @@ TRACE_EVENT(cxl_overflow, TRACE_EVENT(cxl_generic_event, TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log, - struct cxl_event_record_raw *rec), + const uuid_t *uuid, struct cxl_event_generic *gen_rec), - TP_ARGS(cxlmd, log, rec), + TP_ARGS(cxlmd, log, uuid, gen_rec), TP_STRUCT__entry( CXL_EVT_TP_entry @@ -235,8 +235,9 @@ TRACE_EVENT(cxl_generic_event, ), TP_fast_assign( - CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr); - memcpy(__entry->data, &rec->data, CXL_EVENT_RECORD_DATA_LENGTH); + CXL_EVT_TP_fast_assign(cxlmd, log, gen_rec->hdr); + memcpy(&__entry->hdr_uuid, uuid, sizeof(uuid_t)); + memcpy(__entry->data, gen_rec->data, CXL_EVENT_RECORD_DATA_LENGTH); ), CXL_EVT_TP_printk("%s", @@ -337,6 +338,7 @@ TRACE_EVENT(cxl_general_media, TP_fast_assign( CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr); + memcpy(&__entry->hdr_uuid, &CXL_EVENT_GEN_MEDIA_UUID, sizeof(uuid_t)); /* General Media */ __entry->dpa = le64_to_cpu(rec->phys_addr); @@ -423,6 +425,7 @@ TRACE_EVENT(cxl_dram, TP_fast_assign( CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr); + memcpy(&__entry->hdr_uuid, &CXL_EVENT_DRAM_UUID, sizeof(uuid_t)); /* DRAM */ __entry->dpa = le64_to_cpu(rec->phys_addr); @@ -570,6 +573,7 @@ TRACE_EVENT(cxl_memory_module, TP_fast_assign( CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr); + memcpy(&__entry->hdr_uuid, &CXL_EVENT_MEM_MODULE_UUID, sizeof(uuid_t)); /* Memory Module Event */ __entry->event_type = rec->event_type; diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 687043ece101..b6017c0c57b4 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -8,6 +8,7 @@ #include <linux/bitfield.h> #include <linux/bitops.h> #include <linux/log2.h> +#include <linux/node.h> #include <linux/io.h> /** @@ -412,7 +413,6 @@ struct cxl_endpoint_decoder { /** * struct cxl_switch_decoder - Switch specific CXL HDM Decoder * @cxld: base cxl_decoder object - * @target_lock: coordinate coherent reads of the target list * @nr_targets: number of elements in @target * @target: active ordered target list in current decoder configuration * @@ -424,7 +424,6 @@ struct cxl_endpoint_decoder { */ struct cxl_switch_decoder { struct cxl_decoder cxld; - seqlock_t target_lock; int nr_targets; struct cxl_dport *target[]; }; @@ -590,6 +589,7 @@ struct cxl_dax_region { * @depth: How deep this port is relative to the root. depth 0 is the root. * @cdat: Cached CDAT data * @cdat_available: Should a CDAT attribute be available in sysfs + * @pci_latency: Upstream latency in picoseconds */ struct cxl_port { struct device dev; @@ -612,6 +612,30 @@ struct cxl_port { size_t length; } cdat; bool cdat_available; + long pci_latency; +}; + +/** + * struct cxl_root - logical collection of root cxl_port items + * + * @port: cxl_port member + * @ops: cxl root operations + */ +struct cxl_root { + struct cxl_port port; + const struct cxl_root_ops *ops; +}; + +static inline struct cxl_root * +to_cxl_root(const struct cxl_port *port) +{ + return container_of(port, struct cxl_root, port); +} + +struct cxl_root_ops { + int (*qos_class)(struct cxl_root *cxl_root, + struct access_coordinate *coord, int entries, + int *qos_class); }; static inline struct cxl_dport * @@ -634,6 +658,9 @@ struct cxl_rcrb_info { * @rch: Indicate whether this dport was enumerated in RCH or VH mode * @port: reference to cxl_port that contains this downstream port * @regs: Dport parsed register blocks + * @sw_coord: access coordinates (performance) for switch from CDAT + * @hb_coord: access coordinates (performance) from ACPI generic port (host bridge) + * @link_latency: calculated PCIe downstream latency */ struct cxl_dport { struct device *dport_dev; @@ -643,6 +670,9 @@ struct cxl_dport { bool rch; struct cxl_port *port; struct cxl_regs regs; + struct access_coordinate sw_coord; + struct access_coordinate hb_coord; + long link_latency; }; /** @@ -700,7 +730,12 @@ struct cxl_port *devm_cxl_add_port(struct device *host, struct device *uport_dev, resource_size_t component_reg_phys, struct cxl_dport *parent_dport); -struct cxl_port *find_cxl_root(struct cxl_port *port); +struct cxl_root *devm_cxl_add_root(struct device *host, + const struct cxl_root_ops *ops); +struct cxl_root *find_cxl_root(struct cxl_port *port); +void put_cxl_root(struct cxl_root *cxl_root); +DEFINE_FREE(put_cxl_root, struct cxl_root *, if (_T) put_cxl_root(_T)) + int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd); void cxl_bus_rescan(void); void cxl_bus_drain(void); @@ -839,6 +874,12 @@ static inline struct cxl_dax_region *to_cxl_dax_region(struct device *dev) } #endif +void cxl_endpoint_parse_cdat(struct cxl_port *port); +void cxl_switch_parse_cdat(struct cxl_port *port); + +int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, + struct access_coordinate *coord); + /* * Unit test builds overrides this to __weak, find the 'strong' version * of these symbols in tools/testing/cxl/. diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index a2fcbca253f3..5303d6942b88 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -6,6 +6,8 @@ #include <linux/cdev.h> #include <linux/uuid.h> #include <linux/rcuwait.h> +#include <linux/cxl-event.h> +#include <linux/node.h> #include "cxl.h" /* CXL 2.0 8.2.8.5.1.1 Memory Device Status Register */ @@ -392,6 +394,20 @@ enum cxl_devtype { }; /** + * struct cxl_dpa_perf - DPA performance property entry + * @list - list entry + * @dpa_range - range for DPA address + * @coord - QoS performance data (i.e. latency, bandwidth) + * @qos_class - QoS Class cookies + */ +struct cxl_dpa_perf { + struct list_head list; + struct range dpa_range; + struct access_coordinate coord; + int qos_class; +}; + +/** * struct cxl_dev_state - The driver device state * * cxl_dev_state represents the CXL driver/device state. It provides an @@ -455,6 +471,8 @@ struct cxl_dev_state { * @security: security driver state info * @fw: firmware upload / activation state * @mbox_send: @dev specific transport for transmitting mailbox commands + * @ram_perf_list: performance data entries matched to RAM + * @pmem_perf_list: performance data entries matched to PMEM * * See CXL 3.0 8.2.9.8.2 Capacity Configuration and Label Storage for * details on capacity parameters. @@ -475,6 +493,10 @@ struct cxl_memdev_state { u64 active_persistent_bytes; u64 next_volatile_bytes; u64 next_persistent_bytes; + + struct list_head ram_perf_list; + struct list_head pmem_perf_list; + struct cxl_event_state event; struct cxl_poison_state poison; struct cxl_security_state security; @@ -503,6 +525,7 @@ enum cxl_opcode { CXL_MBOX_OP_GET_FW_INFO = 0x0200, CXL_MBOX_OP_TRANSFER_FW = 0x0201, CXL_MBOX_OP_ACTIVATE_FW = 0x0202, + CXL_MBOX_OP_GET_TIMESTAMP = 0x0300, CXL_MBOX_OP_SET_TIMESTAMP = 0x0301, CXL_MBOX_OP_GET_SUPPORTED_LOGS = 0x0400, CXL_MBOX_OP_GET_LOG = 0x0401, @@ -580,25 +603,28 @@ struct cxl_mbox_identify { } __packed; /* - * Common Event Record Format - * CXL rev 3.0 section 8.2.9.2.1; Table 8-42 + * General Media Event Record UUID + * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 */ -struct cxl_event_record_hdr { - uuid_t id; - u8 length; - u8 flags[3]; - __le16 handle; - __le16 related_handle; - __le64 timestamp; - u8 maint_op_class; - u8 reserved[15]; -} __packed; +#define CXL_EVENT_GEN_MEDIA_UUID \ + UUID_INIT(0xfbcd0a77, 0xc260, 0x417f, 0x85, 0xa9, 0x08, 0x8b, 0x16, \ + 0x21, 0xeb, 0xa6) -#define CXL_EVENT_RECORD_DATA_LENGTH 0x50 -struct cxl_event_record_raw { - struct cxl_event_record_hdr hdr; - u8 data[CXL_EVENT_RECORD_DATA_LENGTH]; -} __packed; +/* + * DRAM Event Record UUID + * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44 + */ +#define CXL_EVENT_DRAM_UUID \ + UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, \ + 0x5c, 0x96, 0x24) + +/* + * Memory Module Event Record UUID + * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45 + */ +#define CXL_EVENT_MEM_MODULE_UUID \ + UUID_INIT(0xfe927475, 0xdd59, 0x4339, 0xa5, 0x86, 0x79, 0xba, 0xb1, \ + 0x13, 0xb7, 0x74) /* * Get Event Records output payload @@ -641,74 +667,6 @@ struct cxl_mbox_clear_event_payload { } __packed; #define CXL_CLEAR_EVENT_MAX_HANDLES U8_MAX -/* - * General Media Event Record - * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 - */ -#define CXL_EVENT_GEN_MED_COMP_ID_SIZE 0x10 -struct cxl_event_gen_media { - struct cxl_event_record_hdr hdr; - __le64 phys_addr; - u8 descriptor; - u8 type; - u8 transaction_type; - u8 validity_flags[2]; - u8 channel; - u8 rank; - u8 device[3]; - u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE]; - u8 reserved[46]; -} __packed; - -/* - * DRAM Event Record - DER - * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44 - */ -#define CXL_EVENT_DER_CORRECTION_MASK_SIZE 0x20 -struct cxl_event_dram { - struct cxl_event_record_hdr hdr; - __le64 phys_addr; - u8 descriptor; - u8 type; - u8 transaction_type; - u8 validity_flags[2]; - u8 channel; - u8 rank; - u8 nibble_mask[3]; - u8 bank_group; - u8 bank; - u8 row[3]; - u8 column[2]; - u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE]; - u8 reserved[0x17]; -} __packed; - -/* - * Get Health Info Record - * CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100 - */ -struct cxl_get_health_info { - u8 health_status; - u8 media_status; - u8 add_status; - u8 life_used; - u8 device_temp[2]; - u8 dirty_shutdown_cnt[4]; - u8 cor_vol_err_cnt[4]; - u8 cor_per_err_cnt[4]; -} __packed; - -/* - * Memory Module Event Record - * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45 - */ -struct cxl_event_mem_module { - struct cxl_event_record_hdr hdr; - u8 event_type; - struct cxl_get_health_info info; - u8 reserved[0x3d]; -} __packed; - struct cxl_mbox_get_partition_info { __le64 active_volatile_cap; __le64 active_persistent_cap; @@ -866,6 +824,10 @@ void set_exclusive_cxl_commands(struct cxl_memdev_state *mds, void clear_exclusive_cxl_commands(struct cxl_memdev_state *mds, unsigned long *cmds); void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status); +void cxl_event_trace_record(const struct cxl_memdev *cxlmd, + enum cxl_event_log_type type, + enum cxl_event_type event_type, + const uuid_t *uuid, union cxl_event *evt); int cxl_set_timestamp(struct cxl_memdev_state *mds); int cxl_poison_state_init(struct cxl_memdev_state *mds); int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h index 0fa4799ea316..711b05d9a370 100644 --- a/drivers/cxl/cxlpci.h +++ b/drivers/cxl/cxlpci.h @@ -85,6 +85,19 @@ struct cdat_entry_header { __le16 length; } __packed; +/* + * CXL v3.0 6.2.3 Table 6-4 + * The table indicates that if PCIe Flit Mode is set, then CXL is in 256B flits + * mode, otherwise it's 68B flits mode. + */ +static inline bool cxl_pci_flit_256(struct pci_dev *pdev) +{ + u16 lnksta2; + + pcie_capability_read_word(pdev, PCI_EXP_LNKSTA2, &lnksta2); + return lnksta2 & PCI_EXP_LNKSTA2_FLIT; +} + int devm_cxl_port_enumerate_dports(struct cxl_port *port); struct cxl_dev_state; int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm, diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index e087febf9af0..c5c9d8e0d88d 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -215,23 +215,78 @@ static ssize_t trigger_poison_list_store(struct device *dev, } static DEVICE_ATTR_WO(trigger_poison_list); +static ssize_t ram_qos_class_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cxl_memdev *cxlmd = to_cxl_memdev(dev); + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); + struct cxl_dpa_perf *dpa_perf; + + if (!dev->driver) + return -ENOENT; + + if (list_empty(&mds->ram_perf_list)) + return -ENOENT; + + dpa_perf = list_first_entry(&mds->ram_perf_list, struct cxl_dpa_perf, + list); + + return sysfs_emit(buf, "%d\n", dpa_perf->qos_class); +} + +static struct device_attribute dev_attr_ram_qos_class = + __ATTR(qos_class, 0444, ram_qos_class_show, NULL); + +static ssize_t pmem_qos_class_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cxl_memdev *cxlmd = to_cxl_memdev(dev); + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); + struct cxl_dpa_perf *dpa_perf; + + if (!dev->driver) + return -ENOENT; + + if (list_empty(&mds->pmem_perf_list)) + return -ENOENT; + + dpa_perf = list_first_entry(&mds->pmem_perf_list, struct cxl_dpa_perf, + list); + + return sysfs_emit(buf, "%d\n", dpa_perf->qos_class); +} + +static struct device_attribute dev_attr_pmem_qos_class = + __ATTR(qos_class, 0444, pmem_qos_class_show, NULL); + static umode_t cxl_mem_visible(struct kobject *kobj, struct attribute *a, int n) { - if (a == &dev_attr_trigger_poison_list.attr) { - struct device *dev = kobj_to_dev(kobj); - struct cxl_memdev *cxlmd = to_cxl_memdev(dev); - struct cxl_memdev_state *mds = - to_cxl_memdev_state(cxlmd->cxlds); + struct device *dev = kobj_to_dev(kobj); + struct cxl_memdev *cxlmd = to_cxl_memdev(dev); + struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + if (a == &dev_attr_trigger_poison_list.attr) if (!test_bit(CXL_POISON_ENABLED_LIST, mds->poison.enabled_cmds)) return 0; - } + + if (a == &dev_attr_pmem_qos_class.attr) + if (list_empty(&mds->pmem_perf_list)) + return 0; + + if (a == &dev_attr_ram_qos_class.attr) + if (list_empty(&mds->ram_perf_list)) + return 0; + return a->mode; } static struct attribute *cxl_mem_attrs[] = { &dev_attr_trigger_poison_list.attr, + &dev_attr_ram_qos_class.attr, + &dev_attr_pmem_qos_class.attr, NULL }; diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 0155fb66b580..4fd1f207c84e 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2020 Intel Corporation. All rights reserved. */ +#include <asm-generic/unaligned.h> #include <linux/io-64-nonatomic-lo-hi.h> #include <linux/moduleparam.h> #include <linux/module.h> @@ -969,6 +970,61 @@ static struct pci_driver cxl_pci_driver = { }, }; +#define CXL_EVENT_HDR_FLAGS_REC_SEVERITY GENMASK(1, 0) +static void cxl_cper_event_call(enum cxl_event_type ev_type, + struct cxl_cper_event_rec *rec) +{ + struct cper_cxl_event_devid *device_id = &rec->hdr.device_id; + struct pci_dev *pdev __free(pci_dev_put) = NULL; + enum cxl_event_log_type log_type; + struct cxl_dev_state *cxlds; + unsigned int devfn; + u32 hdr_flags; + + devfn = PCI_DEVFN(device_id->device_num, device_id->func_num); + pdev = pci_get_domain_bus_and_slot(device_id->segment_num, + device_id->bus_num, devfn); + if (!pdev) + return; + + guard(pci_dev)(pdev); + if (pdev->driver != &cxl_pci_driver) + return; + + cxlds = pci_get_drvdata(pdev); + if (!cxlds) + return; + + /* Fabricate a log type */ + hdr_flags = get_unaligned_le24(rec->event.generic.hdr.flags); + log_type = FIELD_GET(CXL_EVENT_HDR_FLAGS_REC_SEVERITY, hdr_flags); + + cxl_event_trace_record(cxlds->cxlmd, log_type, ev_type, + &uuid_null, &rec->event); +} + +static int __init cxl_pci_driver_init(void) +{ + int rc; + + rc = cxl_cper_register_callback(cxl_cper_event_call); + if (rc) + return rc; + + rc = pci_register_driver(&cxl_pci_driver); + if (rc) + cxl_cper_unregister_callback(cxl_cper_event_call); + + return rc; +} + +static void __exit cxl_pci_driver_exit(void) +{ + pci_unregister_driver(&cxl_pci_driver); + cxl_cper_unregister_callback(cxl_cper_event_call); +} + +module_init(cxl_pci_driver_init); +module_exit(cxl_pci_driver_exit); MODULE_LICENSE("GPL v2"); -module_pci_driver(cxl_pci_driver); MODULE_IMPORT_NS(CXL); diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c index 47bc8e0b8590..97c21566677a 100644 --- a/drivers/cxl/port.c +++ b/drivers/cxl/port.c @@ -69,6 +69,8 @@ static int cxl_switch_port_probe(struct cxl_port *port) if (rc < 0) return rc; + cxl_switch_parse_cdat(port); + cxlhdm = devm_cxl_setup_hdm(port, NULL); if (!IS_ERR(cxlhdm)) return devm_cxl_enumerate_decoders(cxlhdm, NULL); @@ -109,6 +111,7 @@ static int cxl_endpoint_port_probe(struct cxl_port *port) /* Cache the data early to ensure is_visible() works */ read_cdat_data(port); + cxl_endpoint_parse_cdat(port); get_device(&cxlmd->dev); rc = devm_add_action_or_reset(&port->dev, schedule_detach, cxlmd); @@ -127,14 +130,15 @@ static int cxl_endpoint_port_probe(struct cxl_port *port) * This can't fail in practice as CXL root exit unregisters all * descendant ports and that in turn synchronizes with cxl_port_probe() */ - root = find_cxl_root(port); + struct cxl_root *cxl_root __free(put_cxl_root) = find_cxl_root(port); + + root = &cxl_root->port; /* * Now that all endpoint decoders are successfully enumerated, try to * assemble regions from committed decoders */ device_for_each_child(&port->dev, root, discover_region); - put_device(&root->dev); return 0; } diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c index fa4d4142a68a..88547a23825b 100644 --- a/drivers/dma/tegra186-gpc-dma.c +++ b/drivers/dma/tegra186-gpc-dma.c @@ -1348,8 +1348,8 @@ static int tegra_dma_program_sid(struct tegra_dma_channel *tdc, int stream_id) static int tegra_dma_probe(struct platform_device *pdev) { const struct tegra_dma_chip_data *cdata = NULL; - struct iommu_fwspec *iommu_spec; - unsigned int stream_id, i; + unsigned int i; + u32 stream_id; struct tegra_dma *tdma; int ret; @@ -1378,12 +1378,10 @@ static int tegra_dma_probe(struct platform_device *pdev) tdma->dma_dev.dev = &pdev->dev; - iommu_spec = dev_iommu_fwspec_get(&pdev->dev); - if (!iommu_spec) { + if (!tegra_dev_iommu_get_stream_id(&pdev->dev, &stream_id)) { dev_err(&pdev->dev, "Missing iommu stream-id\n"); return -EINVAL; } - stream_id = iommu_spec->ids[0] & 0xffff; ret = device_property_read_u32(&pdev->dev, "dma-channel-mask", &tdma->chan_mask); diff --git a/drivers/gpio/gpio-en7523.c b/drivers/gpio/gpio-en7523.c index f836a8db4c1d..69834db2c1cf 100644 --- a/drivers/gpio/gpio-en7523.c +++ b/drivers/gpio/gpio-en7523.c @@ -12,11 +12,11 @@ #define AIROHA_GPIO_MAX 32 /** - * airoha_gpio_ctrl - Airoha GPIO driver data + * struct airoha_gpio_ctrl - Airoha GPIO driver data * @gc: Associated gpio_chip instance. * @data: The data register. - * @dir0: The direction register for the lower 16 pins. - * @dir1: The direction register for the higher 16 pins. + * @dir: [0] The direction register for the lower 16 pins. + * [1]: The direction register for the higher 16 pins. * @output: The output enable register. */ struct airoha_gpio_ctrl { diff --git a/drivers/gpio/gpio-mlxbf3.c b/drivers/gpio/gpio-mlxbf3.c index 7a3e1760fc5b..d5906d419b0a 100644 --- a/drivers/gpio/gpio-mlxbf3.c +++ b/drivers/gpio/gpio-mlxbf3.c @@ -215,6 +215,8 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev) gs->gpio_clr_io + MLXBF_GPIO_FW_DATA_OUT_CLEAR, gs->gpio_set_io + MLXBF_GPIO_FW_OUTPUT_ENABLE_SET, gs->gpio_clr_io + MLXBF_GPIO_FW_OUTPUT_ENABLE_CLEAR, 0); + if (ret) + return dev_err_probe(dev, ret, "%s: bgpio_init() failed", __func__); gc->request = gpiochip_generic_request; gc->free = gpiochip_generic_free; diff --git a/drivers/gpio/gpio-rtd.c b/drivers/gpio/gpio-rtd.c index a7939bd0aa56..bf7f008f58d7 100644 --- a/drivers/gpio/gpio-rtd.c +++ b/drivers/gpio/gpio-rtd.c @@ -525,18 +525,21 @@ static int rtd_gpio_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct gpio_irq_chip *irq_chip; struct rtd_gpio *data; + int ret; data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; - data->irqs[0] = platform_get_irq(pdev, 0); - if (data->irqs[0] < 0) - return data->irqs[0]; + ret = platform_get_irq(pdev, 0); + if (ret < 0) + return ret; + data->irqs[0] = ret; - data->irqs[1] = platform_get_irq(pdev, 1); - if (data->irqs[1] < 0) - return data->irqs[1]; + ret = platform_get_irq(pdev, 1); + if (ret < 0) + return ret; + data->irqs[1] = ret; data->info = device_get_match_data(dev); if (!data->info) diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 402f7d99b0c1..e7770eedd146 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -184,7 +184,7 @@ static void of_gpio_try_fixup_polarity(const struct device_node *np, const char *propname; bool active_high; } gpios[] = { -#if !IS_ENABLED(CONFIG_LCD_HX8357) +#if IS_ENABLED(CONFIG_LCD_HX8357) /* * Himax LCD controllers used incorrectly named * "gpios-reset" property and also specified wrong @@ -478,7 +478,7 @@ static struct gpio_desc *of_find_gpio_rename(struct device_node *np, */ const char *compatible; } gpios[] = { -#if !IS_ENABLED(CONFIG_LCD_HX8357) +#if IS_ENABLED(CONFIG_LCD_HX8357) /* Himax LCD controllers used "gpios-reset" */ { "reset", "gpios-reset", "himax,hx8357" }, { "reset", "gpios-reset", "himax,hx8369" }, diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c index 4dbf298bb5dd..6bf5332136e5 100644 --- a/drivers/gpio/gpiolib-sysfs.c +++ b/drivers/gpio/gpiolib-sysfs.c @@ -768,25 +768,6 @@ int gpiochip_sysfs_register(struct gpio_device *gdev) return 0; } -int gpiochip_sysfs_register_all(void) -{ - struct gpio_device *gdev; - int ret; - - guard(rwsem_read)(&gpio_devices_sem); - - list_for_each_entry(gdev, &gpio_devices, list) { - if (gdev->mockdev) - continue; - - ret = gpiochip_sysfs_register(gdev); - if (ret) - return ret; - } - - return 0; -} - void gpiochip_sysfs_unregister(struct gpio_device *gdev) { struct gpio_desc *desc; @@ -811,7 +792,9 @@ void gpiochip_sysfs_unregister(struct gpio_device *gdev) static int __init gpiolib_sysfs_init(void) { - int status; + int status; + unsigned long flags; + struct gpio_device *gdev; status = class_register(&gpio_class); if (status < 0) @@ -823,6 +806,26 @@ static int __init gpiolib_sysfs_init(void) * We run before arch_initcall() so chip->dev nodes can have * registered, and so arch_initcall() can always gpiod_export(). */ - return gpiochip_sysfs_register_all(); + spin_lock_irqsave(&gpio_lock, flags); + list_for_each_entry(gdev, &gpio_devices, list) { + if (gdev->mockdev) + continue; + + /* + * TODO we yield gpio_lock here because + * gpiochip_sysfs_register() acquires a mutex. This is unsafe + * and needs to be fixed. + * + * Also it would be nice to use gpio_device_find() here so we + * can keep gpio_chips local to gpiolib.c, but the yield of + * gpio_lock prevents us from doing this. + */ + spin_unlock_irqrestore(&gpio_lock, flags); + status = gpiochip_sysfs_register(gdev); + spin_lock_irqsave(&gpio_lock, flags); + } + spin_unlock_irqrestore(&gpio_lock, flags); + + return status; } postcore_initcall(gpiolib_sysfs_init); diff --git a/drivers/gpio/gpiolib-sysfs.h b/drivers/gpio/gpiolib-sysfs.h index ab157cec0b4b..b794b396d6a5 100644 --- a/drivers/gpio/gpiolib-sysfs.h +++ b/drivers/gpio/gpiolib-sysfs.h @@ -8,7 +8,6 @@ struct gpio_device; #ifdef CONFIG_GPIO_SYSFS int gpiochip_sysfs_register(struct gpio_device *gdev); -int gpiochip_sysfs_register_all(void); void gpiochip_sysfs_unregister(struct gpio_device *gdev); #else @@ -18,11 +17,6 @@ static inline int gpiochip_sysfs_register(struct gpio_device *gdev) return 0; } -static inline int gpiochip_sysfs_register_all(void) -{ - return 0; -} - static inline void gpiochip_sysfs_unregister(struct gpio_device *gdev) { } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 4c93cf73a826..44c8f5743a24 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -2,7 +2,6 @@ #include <linux/acpi.h> #include <linux/bitmap.h> -#include <linux/cleanup.h> #include <linux/compat.h> #include <linux/debugfs.h> #include <linux/device.h> @@ -16,7 +15,6 @@ #include <linux/kernel.h> #include <linux/list.h> #include <linux/module.h> -#include <linux/mutex.h> #include <linux/of.h> #include <linux/pinctrl/consumer.h> #include <linux/seq_file.h> @@ -83,9 +81,7 @@ DEFINE_SPINLOCK(gpio_lock); static DEFINE_MUTEX(gpio_lookup_lock); static LIST_HEAD(gpio_lookup_list); - LIST_HEAD(gpio_devices); -DECLARE_RWSEM(gpio_devices_sem); static DEFINE_MUTEX(gpio_machine_hogs_mutex); static LIST_HEAD(gpio_machine_hogs); @@ -117,15 +113,20 @@ static inline void desc_set_label(struct gpio_desc *d, const char *label) struct gpio_desc *gpio_to_desc(unsigned gpio) { struct gpio_device *gdev; + unsigned long flags; + + spin_lock_irqsave(&gpio_lock, flags); - scoped_guard(rwsem_read, &gpio_devices_sem) { - list_for_each_entry(gdev, &gpio_devices, list) { - if (gdev->base <= gpio && - gdev->base + gdev->ngpio > gpio) - return &gdev->descs[gpio - gdev->base]; + list_for_each_entry(gdev, &gpio_devices, list) { + if (gdev->base <= gpio && + gdev->base + gdev->ngpio > gpio) { + spin_unlock_irqrestore(&gpio_lock, flags); + return &gdev->descs[gpio - gdev->base]; } } + spin_unlock_irqrestore(&gpio_lock, flags); + if (!gpio_is_valid(gpio)) pr_warn("invalid GPIO %d\n", gpio); @@ -398,21 +399,26 @@ static int gpiodev_add_to_list_unlocked(struct gpio_device *gdev) static struct gpio_desc *gpio_name_to_desc(const char * const name) { struct gpio_device *gdev; + unsigned long flags; if (!name) return NULL; - guard(rwsem_read)(&gpio_devices_sem); + spin_lock_irqsave(&gpio_lock, flags); list_for_each_entry(gdev, &gpio_devices, list) { struct gpio_desc *desc; for_each_gpio_desc(gdev->chip, desc) { - if (desc->name && !strcmp(desc->name, name)) + if (desc->name && !strcmp(desc->name, name)) { + spin_unlock_irqrestore(&gpio_lock, flags); return desc; + } } } + spin_unlock_irqrestore(&gpio_lock, flags); + return NULL; } @@ -807,6 +813,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, struct lock_class_key *request_key) { struct gpio_device *gdev; + unsigned long flags; unsigned int i; int base = 0; int ret = 0; @@ -871,46 +878,49 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, gdev->ngpio = gc->ngpio; - scoped_guard(rwsem_write, &gpio_devices_sem) { - /* - * TODO: this allocates a Linux GPIO number base in the global - * GPIO numberspace for this chip. In the long run we want to - * get *rid* of this numberspace and use only descriptors, but - * it may be a pipe dream. It will not happen before we get rid - * of the sysfs interface anyways. - */ - base = gc->base; + spin_lock_irqsave(&gpio_lock, flags); + /* + * TODO: this allocates a Linux GPIO number base in the global + * GPIO numberspace for this chip. In the long run we want to + * get *rid* of this numberspace and use only descriptors, but + * it may be a pipe dream. It will not happen before we get rid + * of the sysfs interface anyways. + */ + base = gc->base; + if (base < 0) { + base = gpiochip_find_base_unlocked(gc->ngpio); if (base < 0) { - base = gpiochip_find_base_unlocked(gc->ngpio); - if (base < 0) { - ret = base; - base = 0; - goto err_free_label; - } - /* - * TODO: it should not be necessary to reflect the assigned - * base outside of the GPIO subsystem. Go over drivers and - * see if anyone makes use of this, else drop this and assign - * a poison instead. - */ - gc->base = base; - } else { - dev_warn(&gdev->dev, - "Static allocation of GPIO base is deprecated, use dynamic allocation.\n"); - } - gdev->base = base; - - ret = gpiodev_add_to_list_unlocked(gdev); - if (ret) { - chip_err(gc, "GPIO integer space overlap, cannot add chip\n"); + spin_unlock_irqrestore(&gpio_lock, flags); + ret = base; + base = 0; goto err_free_label; } + /* + * TODO: it should not be necessary to reflect the assigned + * base outside of the GPIO subsystem. Go over drivers and + * see if anyone makes use of this, else drop this and assign + * a poison instead. + */ + gc->base = base; + } else { + dev_warn(&gdev->dev, + "Static allocation of GPIO base is deprecated, use dynamic allocation.\n"); + } + gdev->base = base; - for (i = 0; i < gc->ngpio; i++) - gdev->descs[i].gdev = gdev; + ret = gpiodev_add_to_list_unlocked(gdev); + if (ret) { + spin_unlock_irqrestore(&gpio_lock, flags); + chip_err(gc, "GPIO integer space overlap, cannot add chip\n"); + goto err_free_label; } + for (i = 0; i < gc->ngpio; i++) + gdev->descs[i].gdev = gdev; + + spin_unlock_irqrestore(&gpio_lock, flags); + BLOCKING_INIT_NOTIFIER_HEAD(&gdev->line_state_notifier); BLOCKING_INIT_NOTIFIER_HEAD(&gdev->device_notifier); init_rwsem(&gdev->sem); @@ -1001,8 +1011,9 @@ err_free_gpiochip_mask: goto err_print_message; } err_remove_from_list: - scoped_guard(rwsem_write, &gpio_devices_sem) - list_del(&gdev->list); + spin_lock_irqsave(&gpio_lock, flags); + list_del(&gdev->list); + spin_unlock_irqrestore(&gpio_lock, flags); err_free_label: kfree_const(gdev->label); err_free_descs: @@ -1065,7 +1076,7 @@ void gpiochip_remove(struct gpio_chip *gc) dev_crit(&gdev->dev, "REMOVING GPIOCHIP WITH GPIOS STILL REQUESTED\n"); - scoped_guard(rwsem_write, &gpio_devices_sem) + scoped_guard(spinlock_irqsave, &gpio_lock) list_del(&gdev->list); /* @@ -1114,7 +1125,7 @@ struct gpio_device *gpio_device_find(void *data, */ might_sleep(); - guard(rwsem_read)(&gpio_devices_sem); + guard(spinlock_irqsave)(&gpio_lock); list_for_each_entry(gdev, &gpio_devices, list) { if (gdev->chip && match(gdev->chip, data)) @@ -4725,33 +4736,35 @@ static void gpiolib_dbg_show(struct seq_file *s, struct gpio_device *gdev) static void *gpiolib_seq_start(struct seq_file *s, loff_t *pos) { + unsigned long flags; struct gpio_device *gdev = NULL; loff_t index = *pos; s->private = ""; - guard(rwsem_read)(&gpio_devices_sem); - - list_for_each_entry(gdev, &gpio_devices, list) { - if (index-- == 0) + spin_lock_irqsave(&gpio_lock, flags); + list_for_each_entry(gdev, &gpio_devices, list) + if (index-- == 0) { + spin_unlock_irqrestore(&gpio_lock, flags); return gdev; - } + } + spin_unlock_irqrestore(&gpio_lock, flags); return NULL; } static void *gpiolib_seq_next(struct seq_file *s, void *v, loff_t *pos) { + unsigned long flags; struct gpio_device *gdev = v; void *ret = NULL; - scoped_guard(rwsem_read, &gpio_devices_sem) { - if (list_is_last(&gdev->list, &gpio_devices)) - ret = NULL; - else - ret = list_first_entry(&gdev->list, struct gpio_device, - list); - } + spin_lock_irqsave(&gpio_lock, flags); + if (list_is_last(&gdev->list, &gpio_devices)) + ret = NULL; + else + ret = list_first_entry(&gdev->list, struct gpio_device, list); + spin_unlock_irqrestore(&gpio_lock, flags); s->private = "\n"; ++*pos; diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h index 97df54abf57a..a4a2520b5f31 100644 --- a/drivers/gpio/gpiolib.h +++ b/drivers/gpio/gpiolib.h @@ -15,7 +15,6 @@ #include <linux/gpio/consumer.h> /* for enum gpiod_flags */ #include <linux/gpio/driver.h> #include <linux/module.h> -#include <linux/mutex.h> #include <linux/notifier.h> #include <linux/rwsem.h> @@ -137,7 +136,6 @@ int gpiod_set_transitory(struct gpio_desc *desc, bool transitory); extern spinlock_t gpio_lock; extern struct list_head gpio_devices; -extern struct rw_semaphore gpio_devices_sem; void gpiod_line_state_notify(struct gpio_desc *desc, unsigned long action); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 9da14436a373..3d8a48f46b01 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -254,8 +254,6 @@ extern int amdgpu_agp; extern int amdgpu_wbrf; -extern int fw_bo_location; - #define AMDGPU_VM_MAX_NUM_CTX 4096 #define AMDGPU_SG_THRESHOLD (256*1024*1024) #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS 3000 @@ -1146,6 +1144,7 @@ struct amdgpu_device { bool debug_vm; bool debug_largebar; bool debug_disable_soft_recovery; + bool debug_use_vram_fw_buf; }; static inline uint32_t amdgpu_ip_version(const struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 067690ba7bff..77e263660288 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -138,6 +138,9 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work) amdgpu_device_gpu_recover(adev, NULL, &reset_context); } +static const struct drm_client_funcs kfd_client_funcs = { + .unregister = drm_client_release, +}; void amdgpu_amdkfd_device_init(struct amdgpu_device *adev) { int i; @@ -161,7 +164,7 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev) .enable_mes = adev->enable_mes, }; - ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd", NULL); + ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd", &kfd_client_funcs); if (ret) { dev_err(adev->dev, "Failed to init DRM client: %d\n", ret); return; @@ -695,10 +698,8 @@ err: void amdgpu_amdkfd_set_compute_idle(struct amdgpu_device *adev, bool idle) { enum amd_powergating_state state = idle ? AMD_PG_STATE_GATE : AMD_PG_STATE_UNGATE; - /* Temporary workaround to fix issues observed in some - * compute applications when GFXOFF is enabled on GFX11. - */ - if (IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) == 11) { + if (IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) == 11 && + ((adev->mes.kiq_version & AMDGPU_MES_VERSION_MASK) <= 64)) { pr_debug("GFXOFF is %s\n", idle ? "enabled" : "disabled"); amdgpu_gfx_off_ctrl(adev, idle); } else if ((IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) == 9) && diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index cf6ed5fce291..f262b9d89541 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -311,7 +311,7 @@ void amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(struct kgd_mem *mem); int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_bo *bo); int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info, - struct dma_fence **ef); + struct dma_fence __rcu **ef); int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct amdgpu_device *adev, struct kfd_vm_fault_info *info); int amdgpu_amdkfd_gpuvm_import_dmabuf_fd(struct amdgpu_device *adev, int fd, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index d17b2452cb1f..f183d7faeeec 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -2802,7 +2802,7 @@ unlock_out: put_task_struct(usertask); } -static void replace_eviction_fence(struct dma_fence **ef, +static void replace_eviction_fence(struct dma_fence __rcu **ef, struct dma_fence *new_ef) { struct dma_fence *old_ef = rcu_replace_pointer(*ef, new_ef, true @@ -2837,7 +2837,7 @@ static void replace_eviction_fence(struct dma_fence **ef, * 7. Add fence to all PD and PT BOs. * 8. Unreserve all BOs */ -int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef) +int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu **ef) { struct amdkfd_process_info *process_info = info; struct amdgpu_vm *peer_vm; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 5bb444bb36ce..b158d27d0a71 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1544,6 +1544,7 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev) return true; fw_ver = *((uint32_t *)adev->pm.fw->data + 69); + release_firmware(adev->pm.fw); if (fw_ver < 0x00160e00) return true; } @@ -5245,7 +5246,6 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle, struct amdgpu_device *tmp_adev = NULL; bool need_full_reset, skip_hw_reset, vram_lost = false; int r = 0; - bool gpu_reset_for_dev_remove = 0; /* Try reset handler method first */ tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device, @@ -5265,10 +5265,6 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle, test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags); skip_hw_reset = test_bit(AMDGPU_SKIP_HW_RESET, &reset_context->flags); - gpu_reset_for_dev_remove = - test_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context->flags) && - test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags); - /* * ASIC reset has to be done on all XGMI hive nodes ASAP * to allow proper links negotiation in FW (within 1 sec) @@ -5311,18 +5307,6 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle, amdgpu_ras_intr_cleared(); } - /* Since the mode1 reset affects base ip blocks, the - * phase1 ip blocks need to be resumed. Otherwise there - * will be a BIOS signature error and the psp bootloader - * can't load kdb on the next amdgpu install. - */ - if (gpu_reset_for_dev_remove) { - list_for_each_entry(tmp_adev, device_list_handle, reset_list) - amdgpu_device_ip_resume_phase1(tmp_adev); - - goto end; - } - list_for_each_entry(tmp_adev, device_list_handle, reset_list) { if (need_full_reset) { /* post card */ @@ -5559,11 +5543,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, int i, r = 0; bool need_emergency_restart = false; bool audio_suspended = false; - bool gpu_reset_for_dev_remove = false; - - gpu_reset_for_dev_remove = - test_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context->flags) && - test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags); /* * Special case: RAS triggered and full reset isn't supported @@ -5601,7 +5580,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, if (!amdgpu_sriov_vf(adev) && (adev->gmc.xgmi.num_physical_nodes > 1)) { list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) { list_add_tail(&tmp_adev->reset_list, &device_list); - if (gpu_reset_for_dev_remove && adev->shutdown) + if (adev->shutdown) tmp_adev->shutdown = true; } if (!list_is_first(&adev->reset_list, &device_list)) @@ -5686,10 +5665,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, retry: /* Rest of adevs pre asic reset from XGMI hive. */ list_for_each_entry(tmp_adev, device_list_handle, reset_list) { - if (gpu_reset_for_dev_remove) { - /* Workaroud for ASICs need to disable SMC first */ - amdgpu_device_smu_fini_early(tmp_adev); - } r = amdgpu_device_pre_asic_reset(tmp_adev, reset_context); /*TODO Should we stop ?*/ if (r) { @@ -5721,9 +5696,6 @@ retry: /* Rest of adevs pre asic reset from XGMI hive. */ r = amdgpu_do_asic_reset(device_list_handle, reset_context); if (r && r == -EAGAIN) goto retry; - - if (!r && gpu_reset_for_dev_remove) - goto recover_end; } skip_hw_reset: @@ -5779,7 +5751,6 @@ skip_sched_resume: amdgpu_ras_set_error_query_ready(tmp_adev, true); } -recover_end: tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device, reset_list); amdgpu_device_unlock_reset_domain(tmp_adev->reset_domain); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 0431eafa86b5..c7d60dd0fb97 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -1963,8 +1963,6 @@ static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev) amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block); break; case IP_VERSION(9, 4, 3): - if (!amdgpu_exp_hw_support) - return -EINVAL; amdgpu_device_ip_block_add(adev, &gfx_v9_4_3_ip_block); break; case IP_VERSION(10, 1, 10): diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 852cec98ff26..cc69005f5b46 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -128,6 +128,7 @@ enum AMDGPU_DEBUG_MASK { AMDGPU_DEBUG_VM = BIT(0), AMDGPU_DEBUG_LARGEBAR = BIT(1), AMDGPU_DEBUG_DISABLE_GPU_SOFT_RECOVERY = BIT(2), + AMDGPU_DEBUG_USE_VRAM_FW_BUF = BIT(3), }; unsigned int amdgpu_vram_limit = UINT_MAX; @@ -210,7 +211,6 @@ int amdgpu_seamless = -1; /* auto */ uint amdgpu_debug_mask; int amdgpu_agp = -1; /* auto */ int amdgpu_wbrf = -1; -int fw_bo_location = -1; static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work); @@ -990,10 +990,6 @@ MODULE_PARM_DESC(wbrf, "Enable Wifi RFI interference mitigation (0 = disabled, 1 = enabled, -1 = auto(default)"); module_param_named(wbrf, amdgpu_wbrf, int, 0444); -MODULE_PARM_DESC(fw_bo_location, - "location to put firmware bo for frontdoor loading (-1 = auto (default), 0 = on ram, 1 = on vram"); -module_param(fw_bo_location, int, 0644); - /* These devices are not supported by amdgpu. * They are supported by the mach64, r128, radeon drivers */ @@ -2122,6 +2118,11 @@ static void amdgpu_init_debug_options(struct amdgpu_device *adev) pr_info("debug: soft reset for GPU recovery disabled\n"); adev->debug_disable_soft_recovery = true; } + + if (amdgpu_debug_mask & AMDGPU_DEBUG_USE_VRAM_FW_BUF) { + pr_info("debug: place fw in vram for frontdoor loading\n"); + adev->debug_use_vram_fw_buf = true; + } } static unsigned long amdgpu_fix_asic_type(struct pci_dev *pdev, unsigned long flags) @@ -2233,6 +2234,8 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, pci_set_drvdata(pdev, ddev); + amdgpu_init_debug_options(adev); + ret = amdgpu_driver_load_kms(adev, flags); if (ret) goto err_pci; @@ -2313,8 +2316,6 @@ retry_init: amdgpu_get_secondary_funcs(adev); } - amdgpu_init_debug_options(adev); - return 0; err_pci: @@ -2336,38 +2337,6 @@ amdgpu_pci_remove(struct pci_dev *pdev) pm_runtime_forbid(dev->dev); } - if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 2) && - !amdgpu_sriov_vf(adev)) { - bool need_to_reset_gpu = false; - - if (adev->gmc.xgmi.num_physical_nodes > 1) { - struct amdgpu_hive_info *hive; - - hive = amdgpu_get_xgmi_hive(adev); - if (hive->device_remove_count == 0) - need_to_reset_gpu = true; - hive->device_remove_count++; - amdgpu_put_xgmi_hive(hive); - } else { - need_to_reset_gpu = true; - } - - /* Workaround for ASICs need to reset SMU. - * Called only when the first device is removed. - */ - if (need_to_reset_gpu) { - struct amdgpu_reset_context reset_context; - - adev->shutdown = true; - memset(&reset_context, 0, sizeof(reset_context)); - reset_context.method = AMD_RESET_METHOD_NONE; - reset_context.reset_req_dev = adev; - set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); - set_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context.flags); - amdgpu_device_gpu_recover(adev, NULL, &reset_context); - } - } - amdgpu_driver_unload_kms(dev); /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index d2f273d77e59..55784a9f26c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -1045,21 +1045,28 @@ int amdgpu_gmc_vram_checking(struct amdgpu_device *adev) * seconds, so here, we just pick up three parts for emulation. */ ret = memcmp(vram_ptr, cptr, 10); - if (ret) - return ret; + if (ret) { + ret = -EIO; + goto release_buffer; + } ret = memcmp(vram_ptr + (size / 2), cptr, 10); - if (ret) - return ret; + if (ret) { + ret = -EIO; + goto release_buffer; + } ret = memcmp(vram_ptr + size - 10, cptr, 10); - if (ret) - return ret; + if (ret) { + ret = -EIO; + goto release_buffer; + } +release_buffer: amdgpu_bo_free_kernel(&vram_bo, &vram_gpu, &vram_ptr); - return 0; + return ret; } static ssize_t current_memory_partition_show( diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c index 82608df43396..d79cb13e1aa8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c @@ -175,7 +175,6 @@ struct amdgpu_i2c_chan *amdgpu_i2c_create(struct drm_device *dev, i2c->rec = *rec; i2c->adapter.owner = THIS_MODULE; - i2c->adapter.class = I2C_CLASS_DDC; i2c->adapter.dev.parent = dev->dev; i2c->dev = dev; i2c_set_adapdata(&i2c->adapter, i2c); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index b5ebafd4a3ad..bf4f48fe438d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -1105,7 +1105,12 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) if (amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_AVG_POWER, (void *)&ui32, &ui32_size)) { - return -EINVAL; + /* fall back to input power for backwards compat */ + if (amdgpu_dpm_read_sensor(adev, + AMDGPU_PP_SENSOR_GPU_INPUT_POWER, + (void *)&ui32, &ui32_size)) { + return -EINVAL; + } } ui32 >>= 8; break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 2addbdf88394..0328616473f8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -466,7 +466,7 @@ static int psp_sw_init(void *handle) } ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG, - (amdgpu_sriov_vf(adev) || fw_bo_location == 1) ? + (amdgpu_sriov_vf(adev) || adev->debug_use_vram_fw_buf) ? AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT, &psp->fw_pri_bo, &psp->fw_pri_mc_addr, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index fc42fb6ee191..31823a30dea2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -305,11 +305,13 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f, return -EINVAL; data->head.block = block_id; - /* only ue and ce errors are supported */ + /* only ue, ce and poison errors are supported */ if (!memcmp("ue", err, 2)) data->head.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE; else if (!memcmp("ce", err, 2)) data->head.type = AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE; + else if (!memcmp("poison", err, 6)) + data->head.type = AMDGPU_RAS_ERROR__POISON; else return -EINVAL; @@ -431,9 +433,10 @@ static void amdgpu_ras_instance_mask_check(struct amdgpu_device *adev, * The block is one of: umc, sdma, gfx, etc. * see ras_block_string[] for details * - * The error type is one of: ue, ce, where, + * The error type is one of: ue, ce and poison where, * ue is multi-uncorrectable * ce is single-correctable + * poison is poison * * The sub-block is a the sub-block index, pass 0 if there is no sub-block. * The address and value are hexadecimal numbers, leading 0x is optional. @@ -1067,8 +1070,7 @@ static void amdgpu_ras_error_print_error_data(struct amdgpu_device *adev, mcm_info = &err_info->mcm_info; if (err_info->ce_count) { dev_info(adev->dev, "socket: %d, die: %d, " - "%lld new correctable hardware errors detected in %s block, " - "no user action is needed\n", + "%lld new correctable hardware errors detected in %s block\n", mcm_info->socket_id, mcm_info->die_id, err_info->ce_count, @@ -1080,8 +1082,7 @@ static void amdgpu_ras_error_print_error_data(struct amdgpu_device *adev, err_info = &err_node->err_info; mcm_info = &err_info->mcm_info; dev_info(adev->dev, "socket: %d, die: %d, " - "%lld correctable hardware errors detected in total in %s block, " - "no user action is needed\n", + "%lld correctable hardware errors detected in total in %s block\n", mcm_info->socket_id, mcm_info->die_id, err_info->ce_count, blk_name); } } @@ -1108,16 +1109,14 @@ static void amdgpu_ras_error_generate_report(struct amdgpu_device *adev, adev->smuio.funcs->get_die_id) { dev_info(adev->dev, "socket: %d, die: %d " "%ld correctable hardware errors " - "detected in %s block, no user " - "action is needed.\n", + "detected in %s block\n", adev->smuio.funcs->get_socket_id(adev), adev->smuio.funcs->get_die_id(adev), ras_mgr->err_data.ce_count, blk_name); } else { dev_info(adev->dev, "%ld correctable hardware errors " - "detected in %s block, no user " - "action is needed.\n", + "detected in %s block\n", ras_mgr->err_data.ce_count, blk_name); } @@ -1920,7 +1919,7 @@ static void amdgpu_ras_interrupt_poison_creation_handler(struct ras_manager *obj struct amdgpu_iv_entry *entry) { dev_info(obj->adev->dev, - "Poison is created, no user action is needed.\n"); + "Poison is created\n"); } static void amdgpu_ras_interrupt_umc_handler(struct ras_manager *obj, @@ -2920,6 +2919,11 @@ int amdgpu_ras_init(struct amdgpu_device *adev) amdgpu_ras_query_poison_mode(adev); + /* Packed socket_id to ras feature mask bits[31:29] */ + if (adev->smuio.funcs && + adev->smuio.funcs->get_socket_id) + con->features |= ((adev->smuio.funcs->get_socket_id(adev)) << 29); + /* Get RAS schema for particular SOC */ con->schema = amdgpu_get_ras_schema(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h index b0335a1c5e90..19899f6b9b2b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h @@ -32,7 +32,6 @@ enum AMDGPU_RESET_FLAGS { AMDGPU_NEED_FULL_RESET = 0, AMDGPU_SKIP_HW_RESET = 1, - AMDGPU_RESET_FOR_DEVICE_REMOVE = 2, }; struct amdgpu_reset_context { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c index d334e42fe0eb..3e12763e477a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c @@ -1062,7 +1062,7 @@ int amdgpu_ucode_create_bo(struct amdgpu_device *adev) { if (adev->firmware.load_type != AMDGPU_FW_LOAD_DIRECT) { amdgpu_bo_create_kernel(adev, adev->firmware.fw_size, PAGE_SIZE, - (amdgpu_sriov_vf(adev) || fw_bo_location == 1) ? + (amdgpu_sriov_vf(adev) || adev->debug_use_vram_fw_buf) ? AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT, &adev->firmware.fw_buf, &adev->firmware.fw_buf_mc, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index b6cd565562ad..4740dd65b99d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -116,7 +116,7 @@ struct amdgpu_mem_stats; #define AMDGPU_VM_FAULT_STOP_FIRST 1 #define AMDGPU_VM_FAULT_STOP_ALWAYS 2 -/* Reserve 4MB VRAM for page tables */ +/* How much VRAM be reserved for page tables */ #define AMDGPU_VM_RESERVED_VRAM (8ULL << 20) /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c index 6f149b54d4d3..b9a15d51eb5c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c @@ -59,11 +59,8 @@ static inline uint16_t complete_integer_division_u16( static uint16_t vpe_u1_8_from_fraction(uint16_t numerator, uint16_t denominator) { - bool arg1_negative = numerator < 0; - bool arg2_negative = denominator < 0; - - uint16_t arg1_value = (uint16_t)(arg1_negative ? -numerator : numerator); - uint16_t arg2_value = (uint16_t)(arg2_negative ? -denominator : denominator); + u16 arg1_value = numerator; + u16 arg2_value = denominator; uint16_t remainder; @@ -100,9 +97,6 @@ static uint16_t vpe_u1_8_from_fraction(uint16_t numerator, uint16_t denominator) res_value += summand; } - if (arg1_negative ^ arg2_negative) - res_value = -res_value; - return res_value; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h index 6cab882e8061..1592c63b3099 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h @@ -43,7 +43,6 @@ struct amdgpu_hive_info { } pstate; struct amdgpu_reset_domain *reset_domain; - uint32_t device_remove_count; atomic_t ras_recovery; }; diff --git a/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c b/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c index f0737fb3a999..d1bba9c64e16 100644 --- a/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c @@ -30,6 +30,8 @@ #define regATHUB_MISC_CNTL_V3_0_1 0x00d7 #define regATHUB_MISC_CNTL_V3_0_1_BASE_IDX 0 +#define regATHUB_MISC_CNTL_V3_3_0 0x00d8 +#define regATHUB_MISC_CNTL_V3_3_0_BASE_IDX 0 static uint32_t athub_v3_0_get_cg_cntl(struct amdgpu_device *adev) @@ -40,6 +42,9 @@ static uint32_t athub_v3_0_get_cg_cntl(struct amdgpu_device *adev) case IP_VERSION(3, 0, 1): data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_0_1); break; + case IP_VERSION(3, 3, 0): + data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_3_0); + break; default: data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL); break; @@ -53,6 +58,9 @@ static void athub_v3_0_set_cg_cntl(struct amdgpu_device *adev, uint32_t data) case IP_VERSION(3, 0, 1): WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_0_1, data); break; + case IP_VERSION(3, 3, 0): + WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_3_0, data); + break; default: WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL, data); break; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 73f6d7e72c73..d63cab294883 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3996,16 +3996,13 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) if (!amdgpu_sriov_vf(adev)) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", ucode_prefix); - err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw, fw_name); - /* don't check this. There are apparently firmwares in the wild with - * incorrect size in the header - */ - if (err == -ENODEV) - goto out; + err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev); if (err) - dev_dbg(adev->dev, - "gfx10: amdgpu_ucode_request() failed \"%s\"\n", - fw_name); + goto out; + + /* don't validate this firmware. There are apparently firmwares + * in the wild with incorrect size in the header + */ rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data; version_major = le16_to_cpu(rlc_hdr->header.header_version_major); version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 2fbcd9765980..0ea0866c261f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -115,7 +115,7 @@ static const struct soc15_reg_golden golden_settings_gc_11_5_0[] = { SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xfffffff3), SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL, 0xffffffff, 0xf37fff3f), SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL3, 0xfffffffb, 0x00f40188), - SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL4, 0xf0ffffff, 0x8000b007), + SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL4, 0xf0ffffff, 0x80009007), SOC15_REG_GOLDEN_VALUE(GC, 0, regPA_CL_ENHANCE, 0xf1ffffff, 0x00880007), SOC15_REG_GOLDEN_VALUE(GC, 0, regPC_CONFIG_CNTL_1, 0xffffffff, 0x00010000), SOC15_REG_GOLDEN_VALUE(GC, 0, regTA_CNTL_AUX, 0xf7f7ffff, 0x01030000), @@ -6383,6 +6383,9 @@ static int gfx_v11_0_get_cu_info(struct amdgpu_device *adev, mutex_lock(&adev->grbm_idx_mutex); for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { + bitmap = i * adev->gfx.config.max_sh_per_se + j; + if (!((gfx_v11_0_get_sa_active_bitmap(adev) >> bitmap) & 1)) + continue; mask = 1; counter = 0; gfx_v11_0_select_se_sh(adev, i, j, 0xffffffff, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c index 95d06da544e2..49aecdcee006 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c @@ -456,10 +456,12 @@ static void gfxhub_v1_2_xcc_gart_disable(struct amdgpu_device *adev, WREG32_SOC15_RLC(GC, GET_INST(GC, j), regMC_VM_MX_L1_TLB_CNTL, tmp); /* Setup L2 cache */ - tmp = RREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL); - tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_CACHE, 0); - WREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL, tmp); - WREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL3, 0); + if (!amdgpu_sriov_vf(adev)) { + tmp = RREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL); + tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_CACHE, 0); + WREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL, tmp); + WREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL3, 0); + } } } diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index 6d24c84924cb..19986ff6a48d 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -401,8 +401,7 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device if (err_data.ce_count) dev_info(adev->dev, "%ld correctable hardware " - "errors detected in %s block, " - "no user action is needed.\n", + "errors detected in %s block\n", obj->err_data.ce_count, get_ras_block_str(adev->nbio.ras_if)); diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c index 25a3da83e0fb..e90f33780803 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c @@ -597,8 +597,7 @@ static void nbio_v7_9_handle_ras_controller_intr_no_bifring(struct amdgpu_device if (err_data.ce_count) dev_info(adev->dev, "%ld correctable hardware " - "errors detected in %s block, " - "no user action is needed.\n", + "errors detected in %s block\n", obj->err_data.ce_count, get_ras_block_str(adev->nbio.ras_if)); diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c index 530549314ce4..a3ee3c4c650f 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c @@ -64,7 +64,7 @@ static void umc_v6_7_query_error_status_helper(struct amdgpu_device *adev, uint64_t reg_value; if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1) - dev_info(adev->dev, "Deferred error, no user action is needed.\n"); + dev_info(adev->dev, "Deferred error\n"); if (mc_umc_status) dev_info(adev->dev, "MCA STATUS 0x%llx, umc_reg_offset 0x%x\n", mc_umc_status, umc_reg_offset); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index d630100b9e91..f856901055d3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -1026,7 +1026,7 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev) } else { res = devm_request_free_mem_region(adev->dev, &iomem_resource, size); if (IS_ERR(res)) - return -ENOMEM; + return PTR_ERR(res); pgmap->range.start = res->start; pgmap->range.end = res->end; pgmap->type = MEMORY_DEVICE_PRIVATE; @@ -1042,10 +1042,10 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev) r = devm_memremap_pages(adev->dev, pgmap); if (IS_ERR(r)) { pr_err("failed to register HMM device memory\n"); - /* Disable SVM support capability */ - pgmap->type = 0; if (pgmap->type == MEMORY_DEVICE_PRIVATE) devm_release_mem_region(adev->dev, res->start, resource_size(res)); + /* Disable SVM support capability */ + pgmap->type = 0; return PTR_ERR(r); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 745024b31340..17fbedbf3651 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -917,7 +917,7 @@ struct kfd_process { * fence will be triggered during eviction and new one will be created * during restore */ - struct dma_fence *ef; + struct dma_fence __rcu *ef; /* Work items for evicting and restoring BOs */ struct delayed_work eviction_work; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 71df51fcc1b0..717a60d7a4ea 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1110,6 +1110,7 @@ static void kfd_process_wq_release(struct work_struct *work) { struct kfd_process *p = container_of(work, struct kfd_process, release_work); + struct dma_fence *ef; kfd_process_dequeue_from_all_devices(p); pqm_uninit(&p->pqm); @@ -1118,7 +1119,9 @@ static void kfd_process_wq_release(struct work_struct *work) * destroyed. This allows any BOs to be freed without * triggering pointless evictions or waiting for fences. */ - dma_fence_signal(p->ef); + synchronize_rcu(); + ef = rcu_access_pointer(p->ef); + dma_fence_signal(ef); kfd_process_remove_sysfs(p); @@ -1127,7 +1130,7 @@ static void kfd_process_wq_release(struct work_struct *work) svm_range_list_fini(p); kfd_process_destroy_pdds(p); - dma_fence_put(p->ef); + dma_fence_put(ef); kfd_event_free_process(p); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index ac84c4a2ca07..c50a0dc9c9c0 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -404,14 +404,9 @@ static void svm_range_bo_release(struct kref *kref) spin_lock(&svm_bo->list_lock); } spin_unlock(&svm_bo->list_lock); - if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base)) { - /* We're not in the eviction worker. - * Signal the fence and synchronize with any - * pending eviction work. - */ + if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base)) + /* We're not in the eviction worker. Signal the fence. */ dma_fence_signal(&svm_bo->eviction_fence->base); - cancel_work_sync(&svm_bo->eviction_work); - } dma_fence_put(&svm_bo->eviction_fence->base); amdgpu_bo_unref(&svm_bo->bo); kfree(svm_bo); @@ -2345,8 +2340,10 @@ retry: mutex_unlock(&svms->lock); mmap_write_unlock(mm); - /* Pairs with mmget in svm_range_add_list_work */ - mmput(mm); + /* Pairs with mmget in svm_range_add_list_work. If dropping the + * last mm refcount, schedule release work to avoid circular locking + */ + mmput_async(mm); spin_lock(&svms->deferred_list_lock); } @@ -2657,6 +2654,7 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr, { struct vm_area_struct *vma; struct interval_tree_node *node; + struct rb_node *rb_node; unsigned long start_limit, end_limit; vma = vma_lookup(p->mm, addr << PAGE_SHIFT); @@ -2676,16 +2674,15 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr, if (node) { end_limit = min(end_limit, node->start); /* Last range that ends before the fault address */ - node = container_of(rb_prev(&node->rb), - struct interval_tree_node, rb); + rb_node = rb_prev(&node->rb); } else { /* Last range must end before addr because * there was no range after addr */ - node = container_of(rb_last(&p->svms.objects.rb_root), - struct interval_tree_node, rb); + rb_node = rb_last(&p->svms.objects.rb_root); } - if (node) { + if (rb_node) { + node = container_of(rb_node, struct interval_tree_node, rb); if (node->last >= addr) { WARN(1, "Overlap with prev node and page fault addr\n"); return -EFAULT; @@ -3432,13 +3429,14 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange, int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence) { - if (!fence) - return -EINVAL; - - if (dma_fence_is_signaled(&fence->base)) - return 0; - - if (fence->svm_bo) { + /* Dereferencing fence->svm_bo is safe here because the fence hasn't + * signaled yet and we're under the protection of the fence->lock. + * After the fence is signaled in svm_range_bo_release, we cannot get + * here any more. + * + * Reference is dropped in svm_range_evict_svm_bo_worker. + */ + if (svm_bo_ref_unless_zero(fence->svm_bo)) { WRITE_ONCE(fence->svm_bo->evicting, 1); schedule_work(&fence->svm_bo->eviction_work); } @@ -3453,8 +3451,6 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work) int r = 0; svm_bo = container_of(work, struct svm_range_bo, eviction_work); - if (!svm_bo_ref_unless_zero(svm_bo)) - return; /* svm_bo was freed while eviction was pending */ if (mmget_not_zero(svm_bo->eviction_fence->mm)) { mm = svm_bo->eviction_fence->mm; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index f6575d7dee97..d4f525b66a09 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7615,7 +7615,6 @@ create_i2c(struct ddc_service *ddc_service, if (!i2c) return NULL; i2c->base.owner = THIS_MODULE; - i2c->base.class = I2C_CLASS_DDC; i2c->base.dev.parent = &adev->pdev->dev; i2c->base.algo = &amdgpu_dm_i2c_algo; snprintf(i2c->base.name, sizeof(i2c->base.name), "AMDGPU DM i2c hw bus %d", link_index); @@ -9293,10 +9292,10 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) if (!new_con_state->writeback_job) continue; - new_crtc_state = NULL; + new_crtc_state = drm_atomic_get_new_crtc_state(state, &acrtc->base); - if (acrtc) - new_crtc_state = drm_atomic_get_new_crtc_state(state, &acrtc->base); + if (!new_crtc_state) + continue; if (acrtc->wb_enabled) continue; @@ -10753,7 +10752,7 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, DRM_DEBUG_DRIVER("drm_dp_mst_atomic_check() failed\n"); goto fail; } - status = dc_validate_global_state(dc, dm_state->context, false); + status = dc_validate_global_state(dc, dm_state->context, true); if (status != DC_OK) { DRM_DEBUG_DRIVER("DC global validation failure: %s (%d)", dc_status_to_str(status), status); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c index 9b527bffe11a..c87b64e464ed 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c @@ -1239,7 +1239,7 @@ int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc, if (has_crtc_cm_degamma && ret != -EINVAL) { drm_dbg_kms(crtc->base.crtc->dev, "doesn't support plane and CRTC degamma at the same time\n"); - return -EINVAL; + return -EINVAL; } /* If we are here, it means we don't have plane degamma settings, check diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index eaf8d9f48244..85b7f58a7f35 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -979,6 +979,11 @@ int dm_helper_dmub_aux_transfer_sync( struct aux_payload *payload, enum aux_return_code_type *operation_result) { + if (!link->hpd_status) { + *operation_result = AUX_RET_ERROR_HPD_DISCON; + return -1; + } + return amdgpu_dm_process_dmub_aux_transfer_sync(ctx, link->link_index, payload, operation_result); } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c index 757528256326..a84f1e376dee 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c @@ -87,6 +87,20 @@ static const struct IP_BASE CLK_BASE = { { { { 0x00016C00, 0x02401800, 0, 0, 0, #define CLK1_CLK_PLL_REQ__PllSpineDiv_MASK 0x0000F000L #define CLK1_CLK_PLL_REQ__FbMult_frac_MASK 0xFFFF0000L +#define regCLK1_CLK2_BYPASS_CNTL 0x029c +#define regCLK1_CLK2_BYPASS_CNTL_BASE_IDX 0 + +#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL__SHIFT 0x0 +#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV__SHIFT 0x10 +#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL_MASK 0x00000007L +#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV_MASK 0x000F0000L + +#define regCLK6_0_CLK6_spll_field_8 0x464b +#define regCLK6_0_CLK6_spll_field_8_BASE_IDX 0 + +#define CLK6_0_CLK6_spll_field_8__spll_ssc_en__SHIFT 0xd +#define CLK6_0_CLK6_spll_field_8__spll_ssc_en_MASK 0x00002000L + #define REG(reg_name) \ (CLK_BASE.instance[0].segment[reg ## reg_name ## _BASE_IDX] + reg ## reg_name) @@ -131,35 +145,63 @@ static int dcn314_get_active_display_cnt_wa( return display_count; } -static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable) +static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, + bool safe_to_lower, bool disable) { struct dc *dc = clk_mgr_base->ctx->dc; int i; for (i = 0; i < dc->res_pool->pipe_count; ++i) { - struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + struct pipe_ctx *pipe = safe_to_lower + ? &context->res_ctx.pipe_ctx[i] + : &dc->current_state->res_ctx.pipe_ctx[i]; if (pipe->top_pipe || pipe->prev_odm_pipe) continue; if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal))) { - struct stream_encoder *stream_enc = pipe->stream_res.stream_enc; - if (disable) { - if (stream_enc && stream_enc->funcs->disable_fifo) - pipe->stream_res.stream_enc->funcs->disable_fifo(stream_enc); + if (pipe->stream_res.tg && pipe->stream_res.tg->funcs->immediate_disable_crtc) + pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); - pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); reset_sync_context_for_pipe(dc, context, i); } else { pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); - - if (stream_enc && stream_enc->funcs->enable_fifo) - pipe->stream_res.stream_enc->funcs->enable_fifo(stream_enc); } } } } +bool dcn314_is_spll_ssc_enabled(struct clk_mgr *clk_mgr_base) +{ + struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); + uint32_t ssc_enable; + + REG_GET(CLK6_0_CLK6_spll_field_8, spll_ssc_en, &ssc_enable); + + return ssc_enable == 1; +} + +void dcn314_init_clocks(struct clk_mgr *clk_mgr) +{ + struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr); + uint32_t ref_dtbclk = clk_mgr->clks.ref_dtbclk_khz; + + memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks)); + // Assumption is that boot state always supports pstate + clk_mgr->clks.ref_dtbclk_khz = ref_dtbclk; // restore ref_dtbclk + clk_mgr->clks.p_state_change_support = true; + clk_mgr->clks.prev_p_state_change_support = true; + clk_mgr->clks.pwr_state = DCN_PWR_STATE_UNKNOWN; + clk_mgr->clks.zstate_support = DCN_ZSTATE_SUPPORT_UNKNOWN; + + // to adjust dp_dto reference clock if ssc is enable otherwise to apply dprefclk + if (dcn314_is_spll_ssc_enabled(clk_mgr)) + clk_mgr->dp_dto_source_clock_in_khz = + dce_adjust_dp_ref_freq_for_ss(clk_mgr_int, clk_mgr->dprefclk_khz); + else + clk_mgr->dp_dto_source_clock_in_khz = clk_mgr->dprefclk_khz; +} + void dcn314_update_clocks(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool safe_to_lower) @@ -252,11 +294,11 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base, } if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { - dcn314_disable_otg_wa(clk_mgr_base, context, true); + dcn314_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; dcn314_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); - dcn314_disable_otg_wa(clk_mgr_base, context, false); + dcn314_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false); update_dispclk = true; } @@ -436,6 +478,11 @@ static DpmClocks314_t dummy_clocks; static struct dcn314_watermarks dummy_wms = { 0 }; +static struct dcn314_ss_info_table ss_info_table = { + .ss_divider = 1000, + .ss_percentage = {0, 0, 375, 375, 375} +}; + static void dcn314_build_watermark_ranges(struct clk_bw_params *bw_params, struct dcn314_watermarks *table) { int i, num_valid_sets; @@ -708,13 +755,31 @@ static struct clk_mgr_funcs dcn314_funcs = { .get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz, .get_dtb_ref_clk_frequency = dcn31_get_dtb_ref_freq_khz, .update_clocks = dcn314_update_clocks, - .init_clocks = dcn31_init_clocks, + .init_clocks = dcn314_init_clocks, .enable_pme_wa = dcn314_enable_pme_wa, .are_clock_states_equal = dcn314_are_clock_states_equal, .notify_wm_ranges = dcn314_notify_wm_ranges }; extern struct clk_mgr_funcs dcn3_fpga_funcs; +static void dcn314_read_ss_info_from_lut(struct clk_mgr_internal *clk_mgr) +{ + uint32_t clock_source; + //uint32_t ssc_enable; + + REG_GET(CLK1_CLK2_BYPASS_CNTL, CLK2_BYPASS_SEL, &clock_source); + //REG_GET(CLK6_0_CLK6_spll_field_8, spll_ssc_en, &ssc_enable); + + if (dcn314_is_spll_ssc_enabled(&clk_mgr->base) && (clock_source < ARRAY_SIZE(ss_info_table.ss_percentage))) { + clk_mgr->dprefclk_ss_percentage = ss_info_table.ss_percentage[clock_source]; + + if (clk_mgr->dprefclk_ss_percentage != 0) { + clk_mgr->ss_on_dprefclk = true; + clk_mgr->dprefclk_ss_divider = ss_info_table.ss_divider; + } + } +} + void dcn314_clk_mgr_construct( struct dc_context *ctx, struct clk_mgr_dcn314 *clk_mgr, @@ -782,6 +847,7 @@ void dcn314_clk_mgr_construct( clk_mgr->base.base.dprefclk_khz = 600000; clk_mgr->base.base.clks.ref_dtbclk_khz = 600000; dce_clock_read_ss_info(&clk_mgr->base); + dcn314_read_ss_info_from_lut(&clk_mgr->base); /*if bios enabled SS, driver needs to adjust dtb clock, only enable with correct bios*/ clk_mgr->base.base.bw_params = &dcn314_bw_params; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h index 171f84340eb2..002c28e80720 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h @@ -28,6 +28,8 @@ #define __DCN314_CLK_MGR_H__ #include "clk_mgr_internal.h" +#define DCN314_NUM_CLOCK_SOURCES 5 + struct dcn314_watermarks; struct dcn314_smu_watermark_set { @@ -40,9 +42,18 @@ struct clk_mgr_dcn314 { struct dcn314_smu_watermark_set smu_wm_set; }; +struct dcn314_ss_info_table { + uint32_t ss_divider; + uint32_t ss_percentage[DCN314_NUM_CLOCK_SOURCES]; +}; + bool dcn314_are_clock_states_equal(struct dc_clocks *a, struct dc_clocks *b); +bool dcn314_is_spll_ssc_enabled(struct clk_mgr *clk_mgr_base); + +void dcn314_init_clocks(struct clk_mgr *clk_mgr); + void dcn314_update_clocks(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool safe_to_lower); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 2d7205058c64..aa7c02ba948e 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -411,12 +411,9 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc, * avoid conflicting with firmware updates. */ if (dc->ctx->dce_version > DCE_VERSION_MAX) - if (dc->optimized_required) + if (dc->optimized_required || dc->wm_optimized_required) return false; - if (!memcmp(&stream->adjust, adjust, sizeof(*adjust))) - return true; - stream->adjust.v_total_max = adjust->v_total_max; stream->adjust.v_total_mid = adjust->v_total_mid; stream->adjust.v_total_mid_frame_num = adjust->v_total_mid_frame_num; @@ -2230,6 +2227,7 @@ void dc_post_update_surfaces_to_stream(struct dc *dc) } dc->optimized_required = false; + dc->wm_optimized_required = false; } bool dc_set_generic_gpio_for_stereo(bool enable, @@ -2652,6 +2650,8 @@ enum surface_update_type dc_check_update_surfaces_for_stream( } else if (memcmp(&dc->current_state->bw_ctx.bw.dcn.clk, &dc->clk_mgr->clks, offsetof(struct dc_clocks, prev_p_state_change_support)) != 0) { dc->optimized_required = true; } + + dc->optimized_required |= dc->wm_optimized_required; } return type; @@ -2859,6 +2859,9 @@ static void copy_stream_update_to_stream(struct dc *dc, if (update->vrr_active_fixed) stream->vrr_active_fixed = *update->vrr_active_fixed; + if (update->crtc_timing_adjust) + stream->adjust = *update->crtc_timing_adjust; + if (update->dpms_off) stream->dpms_off = *update->dpms_off; @@ -3519,7 +3522,7 @@ static void commit_planes_for_stream(struct dc *dc, top_pipe_to_program = resource_get_otg_master_for_stream( &context->res_ctx, stream); - + ASSERT(top_pipe_to_program != NULL); for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i]; @@ -4288,7 +4291,8 @@ static bool full_update_required(struct dc *dc, stream_update->mst_bw_update || stream_update->func_shaper || stream_update->lut3d_func || - stream_update->pending_test_pattern)) + stream_update->pending_test_pattern || + stream_update->crtc_timing_adjust)) return true; if (stream) { @@ -4341,6 +4345,8 @@ static bool should_commit_minimal_transition_for_windowed_mpo_odm(struct dc *dc, cur_pipe = resource_get_otg_master_for_stream(&dc->current_state->res_ctx, stream); new_pipe = resource_get_otg_master_for_stream(&context->res_ctx, stream); + if (!cur_pipe || !new_pipe) + return false; cur_is_odm_in_use = resource_get_odm_slice_count(cur_pipe) > 1; new_is_odm_in_use = resource_get_odm_slice_count(new_pipe) > 1; if (cur_is_odm_in_use == new_is_odm_in_use) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 57f0ddd15923..9fbdb09697fd 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -2194,6 +2194,10 @@ void resource_log_pipe_topology_update(struct dc *dc, struct dc_state *state) for (stream_idx = 0; stream_idx < state->stream_count; stream_idx++) { otg_master = resource_get_otg_master_for_stream( &state->res_ctx, state->streams[stream_idx]); + if (!otg_master || otg_master->stream_res.tg == NULL) { + DC_LOG_DC("topology update: otg_master NULL stream_idx %d!\n", stream_idx); + return; + } slice_count = resource_get_opp_heads_for_otg_master(otg_master, &state->res_ctx, opp_heads); for (slice_idx = 0; slice_idx < slice_count; slice_idx++) { @@ -4986,20 +4990,6 @@ enum dc_status update_dp_encoder_resources_for_test_harness(const struct dc *dc, return DC_OK; } -bool resource_subvp_in_use(struct dc *dc, - struct dc_state *context) -{ - uint32_t i; - - for (i = 0; i < dc->res_pool->pipe_count; i++) { - struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; - - if (dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_NONE) - return true; - } - return false; -} - bool check_subvp_sw_cursor_fallback_req(const struct dc *dc, struct dc_stream_state *stream) { if (!dc->debug.disable_subvp_high_refresh && is_subvp_high_refresh_candidate(stream)) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c index 460a8010c79f..88c6436b28b6 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c @@ -267,7 +267,8 @@ void dc_state_construct(struct dc *dc, struct dc_state *state) state->clk_mgr = dc->clk_mgr; /* Initialise DIG link encoder resource tracking variables. */ - link_enc_cfg_init(dc, state); + if (dc->res_pool) + link_enc_cfg_init(dc, state); } void dc_state_destruct(struct dc_state *state) @@ -433,8 +434,9 @@ bool dc_state_add_plane( otg_master_pipe = resource_get_otg_master_for_stream( &state->res_ctx, stream); - added = resource_append_dpp_pipes_for_plane_composition(state, - dc->current_state, pool, otg_master_pipe, plane_state); + if (otg_master_pipe) + added = resource_append_dpp_pipes_for_plane_composition(state, + dc->current_state, pool, otg_master_pipe, plane_state); if (added) { stream_status->plane_states[stream_status->plane_count] = diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index f30a341bc090..5d7aa882416b 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -51,7 +51,7 @@ struct aux_payload; struct set_config_cmd_payload; struct dmub_notification; -#define DC_VER "3.2.265" +#define DC_VER "3.2.266" #define MAX_SURFACES 3 #define MAX_PLANES 6 @@ -1036,6 +1036,7 @@ struct dc { /* Require to optimize clocks and bandwidth for added/removed planes */ bool optimized_required; + bool wm_optimized_required; bool idle_optimizations_allowed; bool enable_c20_dtm_b0; diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index a23eebd9933b..ee10941caa59 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -139,6 +139,7 @@ union stream_update_flags { uint32_t wb_update:1; uint32_t dsc_changed : 1; uint32_t mst_bw : 1; + uint32_t crtc_timing_adjust : 1; uint32_t fams_changed : 1; } bits; @@ -325,6 +326,7 @@ struct dc_stream_update { struct dc_3dlut *lut3d_func; struct test_pattern *pending_test_pattern; + struct dc_crtc_timing_adjust *crtc_timing_adjust; }; bool dc_is_stream_unchanged( diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index 4f276169e05a..b08ccb8c68bc 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -1140,23 +1140,25 @@ struct dc_panel_config { } ilr; }; +#define MAX_SINKS_PER_LINK 4 + /* * USB4 DPIA BW ALLOCATION STRUCTS */ struct dc_dpia_bw_alloc { - int sink_verified_bw; // The Verified BW that sink can allocated and use that has been verified already - int sink_allocated_bw; // The Actual Allocated BW that sink currently allocated - int sink_max_bw; // The Max BW that sink can require/support + int remote_sink_req_bw[MAX_SINKS_PER_LINK]; // BW requested by remote sinks + int link_verified_bw; // The Verified BW that link can allocated and use that has been verified already + int link_max_bw; // The Max BW that link can require/support + int allocated_bw; // The Actual Allocated BW for this DPIA int estimated_bw; // The estimated available BW for this DPIA int bw_granularity; // BW Granularity + int dp_overhead; // DP overhead in dp tunneling bool bw_alloc_enabled; // The BW Alloc Mode Support is turned ON for all 3: DP-Tx & Dpia & CM bool response_ready; // Response ready from the CM side uint8_t nrd_max_lane_count; // Non-reduced max lane count uint8_t nrd_max_link_rate; // Non-reduced max link rate }; -#define MAX_SINKS_PER_LINK 4 - enum dc_hpd_enable_select { HPD_EN_FOR_ALL_EDP = 0, HPD_EN_FOR_PRIMARY_EDP_ONLY, diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c index 140598f18bbd..f0458b8f00af 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c @@ -782,7 +782,7 @@ static void get_azalia_clock_info_dp( /*audio_dto_module = dpDtoSourceClockInkhz * 10,000; * [khz] ->[100Hz] */ azalia_clock_info->audio_dto_module = - pll_info->dp_dto_source_clock_in_khz * 10; + pll_info->audio_dto_source_clock_in_khz * 10; } void dce_aud_wall_dto_setup( diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c index 5d3f6fa1011e..970644b695cd 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c @@ -975,6 +975,9 @@ static bool dcn31_program_pix_clk( look_up_in_video_optimized_rate_tlb(pix_clk_params->requested_pix_clk_100hz / 10); struct bp_pixel_clock_parameters bp_pc_params = {0}; enum transmitter_color_depth bp_pc_colour_depth = TRANSMITTER_COLOR_DEPTH_24; + + if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0) + dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz; // For these signal types Driver to program DP_DTO without calling VBIOS Command table if (dc_is_dp_signal(pix_clk_params->signal_type) || dc_is_virtual_signal(pix_clk_params->signal_type)) { if (e) { @@ -1088,6 +1091,10 @@ static bool get_pixel_clk_frequency_100hz( struct dce110_clk_src *clk_src = TO_DCE110_CLK_SRC(clock_source); unsigned int clock_hz = 0; unsigned int modulo_hz = 0; + unsigned int dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dprefclk_khz; + + if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0) + dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz; if (clock_source->id == CLOCK_SOURCE_ID_DP_DTO) { clock_hz = REG_READ(PHASE[inst]); @@ -1100,7 +1107,7 @@ static bool get_pixel_clk_frequency_100hz( modulo_hz = REG_READ(MODULO[inst]); if (modulo_hz) *pixel_clk_khz = div_u64((uint64_t)clock_hz* - clock_source->ctx->dc->clk_mgr->dprefclk_khz*10, + dp_dto_ref_khz*10, modulo_hz); else *pixel_clk_khz = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c index e4a328b45c8a..87760600e154 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c @@ -183,6 +183,20 @@ bool dcn32_all_pipes_have_stream_and_plane(struct dc *dc, return true; } +bool dcn32_subvp_in_use(struct dc *dc, + struct dc_state *context) +{ + uint32_t i; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + + if (dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_NONE) + return true; + } + return false; +} + bool dcn32_mpo_in_use(struct dc_state *context) { uint32_t i; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index aa68d010cbfd..9f37f717a1f8 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -33,7 +33,6 @@ #include "dcn30/dcn30_resource.h" #include "link.h" #include "dc_state_priv.h" -#include "resource.h" #define DC_LOGGER_INIT(logger) @@ -292,7 +291,7 @@ int dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(struct dc *dc, /* for subvp + DRR case, if subvp pipes are still present we support pstate */ if (vba->DRAMClockChangeSupport[vlevel][vba->maxMpcComb] == dm_dram_clock_change_unsupported && - resource_subvp_in_use(dc, context)) + dcn32_subvp_in_use(dc, context)) vba->DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] = temp_clock_change_support; if (vlevel < context->bw_ctx.dml.vba.soc.num_states && @@ -2273,7 +2272,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, unsigned int dummy_latency_index = 0; int maxMpcComb = context->bw_ctx.dml.vba.maxMpcComb; unsigned int min_dram_speed_mts = context->bw_ctx.dml.vba.DRAMSpeed; - bool subvp_active = resource_subvp_in_use(dc, context); + bool subvp_in_use = dcn32_subvp_in_use(dc, context); unsigned int min_dram_speed_mts_margin; bool need_fclk_lat_as_dummy = false; bool is_subvp_p_drr = false; @@ -2282,7 +2281,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, dc_assert_fp_enabled(); /* need to find dummy latency index for subvp */ - if (subvp_active) { + if (subvp_in_use) { /* Override DRAMClockChangeSupport for SubVP + DRR case where the DRR cannot switch without stretching it's VBLANK */ if (!pstate_en) { context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][maxMpcComb] = dm_dram_clock_change_vblank_w_mall_sub_vp; @@ -2468,7 +2467,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, dc->clk_mgr->bw_params->clk_table.entries[min_dram_speed_mts_offset].memclk_mhz * 16; } - if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching && !subvp_active) { + if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching && !subvp_in_use) { /* find largest table entry that is lower than dram speed, * but lower than DPM0 still uses DPM0 */ @@ -3528,7 +3527,7 @@ void dcn32_set_clock_limits(const struct _vcs_dpi_soc_bounding_box_st *soc_bb) void dcn32_override_min_req_memclk(struct dc *dc, struct dc_state *context) { // WA: restrict FPO and SubVP to use first non-strobe mode (DCN32 BW issue) - if ((context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || resource_subvp_in_use(dc, context)) && + if ((context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || dcn32_subvp_in_use(dc, context)) && dc->dml.soc.num_chans <= 8) { int num_mclk_levels = dc->clk_mgr->bw_params->clk_table.num_entries_per_clk.num_memclk_levels; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c index 3d12dabd39e4..475c4ec43c01 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c @@ -166,9 +166,9 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = { .num_states = 5, .sr_exit_time_us = 14.0, .sr_enter_plus_exit_time_us = 16.0, - .sr_exit_z8_time_us = 525.0, - .sr_enter_plus_exit_z8_time_us = 715.0, - .fclk_change_latency_us = 20.0, + .sr_exit_z8_time_us = 210.0, + .sr_enter_plus_exit_z8_time_us = 320.0, + .fclk_change_latency_us = 24.0, .usr_retraining_latency_us = 2, .writeback_latency_us = 12.0, diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c index b95bf27f2fe2..9be5ebf3a8c0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c @@ -6229,7 +6229,7 @@ static void set_calculate_prefetch_schedule_params(struct display_mode_lib_st *m CalculatePrefetchSchedule_params->GPUVMEnable = mode_lib->ms.cache_display_cfg.plane.GPUVMEnable; CalculatePrefetchSchedule_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable; CalculatePrefetchSchedule_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels; - CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes; + CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024; CalculatePrefetchSchedule_params->DynamicMetadataEnable = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataEnable[k]; CalculatePrefetchSchedule_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled; CalculatePrefetchSchedule_params->DynamicMetadataLinesBeforeActiveRequired = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataLinesBeforeActiveRequired[k]; @@ -6329,7 +6329,7 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib) mode_lib->ms.NoOfDPPThisState, mode_lib->ms.dpte_group_bytes, s->HostVMInefficiencyFactor, - mode_lib->ms.soc.hostvm_min_page_size_kbytes, + mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024, mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels); s->NextMaxVStartup = s->MaxVStartupAllPlanes[j]; @@ -6542,7 +6542,7 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib) mode_lib->ms.cache_display_cfg.plane.HostVMEnable, mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels, mode_lib->ms.cache_display_cfg.plane.GPUVMEnable, - mode_lib->ms.soc.hostvm_min_page_size_kbytes, + mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024, mode_lib->ms.PDEAndMetaPTEBytesPerFrame[j][k], mode_lib->ms.MetaRowBytes[j][k], mode_lib->ms.DPTEBytesPerRow[j][k], @@ -7687,7 +7687,7 @@ dml_bool_t dml_core_mode_support(struct display_mode_lib_st *mode_lib) CalculateVMRowAndSwath_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels; CalculateVMRowAndSwath_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels; CalculateVMRowAndSwath_params->GPUVMMinPageSizeKBytes = mode_lib->ms.cache_display_cfg.plane.GPUVMMinPageSizeKBytes; - CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes; + CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024; CalculateVMRowAndSwath_params->PTEBufferModeOverrideEn = mode_lib->ms.cache_display_cfg.plane.PTEBufferModeOverrideEn; CalculateVMRowAndSwath_params->PTEBufferModeOverrideVal = mode_lib->ms.cache_display_cfg.plane.PTEBufferMode; CalculateVMRowAndSwath_params->PTEBufferSizeNotExceeded = mode_lib->ms.PTEBufferSizeNotExceededPerState; @@ -7957,7 +7957,7 @@ dml_bool_t dml_core_mode_support(struct display_mode_lib_st *mode_lib) UseMinimumDCFCLK_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels; UseMinimumDCFCLK_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable; UseMinimumDCFCLK_params->NumberOfActiveSurfaces = mode_lib->ms.num_active_planes; - UseMinimumDCFCLK_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes; + UseMinimumDCFCLK_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024; UseMinimumDCFCLK_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels; UseMinimumDCFCLK_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled; UseMinimumDCFCLK_params->ImmediateFlipRequirement = s->ImmediateFlipRequiredFinal; @@ -8699,7 +8699,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc CalculateVMRowAndSwath_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels; CalculateVMRowAndSwath_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels; CalculateVMRowAndSwath_params->GPUVMMinPageSizeKBytes = mode_lib->ms.cache_display_cfg.plane.GPUVMMinPageSizeKBytes; - CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes; + CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024; CalculateVMRowAndSwath_params->PTEBufferModeOverrideEn = mode_lib->ms.cache_display_cfg.plane.PTEBufferModeOverrideEn; CalculateVMRowAndSwath_params->PTEBufferModeOverrideVal = mode_lib->ms.cache_display_cfg.plane.PTEBufferMode; CalculateVMRowAndSwath_params->PTEBufferSizeNotExceeded = s->dummy_boolean_array[0]; @@ -8805,7 +8805,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc mode_lib->ms.cache_display_cfg.hw.DPPPerSurface, locals->dpte_group_bytes, s->HostVMInefficiencyFactor, - mode_lib->ms.soc.hostvm_min_page_size_kbytes, + mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024, mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels); locals->TCalc = 24.0 / locals->DCFCLKDeepSleep; @@ -8995,7 +8995,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc CalculatePrefetchSchedule_params->GPUVMEnable = mode_lib->ms.cache_display_cfg.plane.GPUVMEnable; CalculatePrefetchSchedule_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable; CalculatePrefetchSchedule_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels; - CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes; + CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024; CalculatePrefetchSchedule_params->DynamicMetadataEnable = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataEnable[k]; CalculatePrefetchSchedule_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled; CalculatePrefetchSchedule_params->DynamicMetadataLinesBeforeActiveRequired = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataLinesBeforeActiveRequired[k]; @@ -9240,7 +9240,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc mode_lib->ms.cache_display_cfg.plane.HostVMEnable, mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels, mode_lib->ms.cache_display_cfg.plane.GPUVMEnable, - mode_lib->ms.soc.hostvm_min_page_size_kbytes, + mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024, locals->PDEAndMetaPTEBytesFrame[k], locals->MetaRowByte[k], locals->PixelPTEBytesPerRow[k], @@ -9446,13 +9446,13 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc CalculateWatermarks_params->CompressedBufferSizeInkByte = locals->CompressedBufferSizeInkByte; // Output - CalculateWatermarks_params->Watermark = &s->dummy_watermark; // Watermarks *Watermark - CalculateWatermarks_params->DRAMClockChangeSupport = &mode_lib->ms.support.DRAMClockChangeSupport[0]; - CalculateWatermarks_params->MaxActiveDRAMClockChangeLatencySupported = &s->dummy_single_array[0][0]; // dml_float_t *MaxActiveDRAMClockChangeLatencySupported[] - CalculateWatermarks_params->SubViewportLinesNeededInMALL = &mode_lib->ms.SubViewportLinesNeededInMALL[j]; // dml_uint_t SubViewportLinesNeededInMALL[] - CalculateWatermarks_params->FCLKChangeSupport = &mode_lib->ms.support.FCLKChangeSupport[0]; - CalculateWatermarks_params->MaxActiveFCLKChangeLatencySupported = &s->dummy_single[0]; // dml_float_t *MaxActiveFCLKChangeLatencySupported - CalculateWatermarks_params->USRRetrainingSupport = &mode_lib->ms.support.USRRetrainingSupport[0]; + CalculateWatermarks_params->Watermark = &locals->Watermark; // Watermarks *Watermark + CalculateWatermarks_params->DRAMClockChangeSupport = &locals->DRAMClockChangeSupport; + CalculateWatermarks_params->MaxActiveDRAMClockChangeLatencySupported = locals->MaxActiveDRAMClockChangeLatencySupported; // dml_float_t *MaxActiveDRAMClockChangeLatencySupported[] + CalculateWatermarks_params->SubViewportLinesNeededInMALL = locals->SubViewportLinesNeededInMALL; // dml_uint_t SubViewportLinesNeededInMALL[] + CalculateWatermarks_params->FCLKChangeSupport = &locals->FCLKChangeSupport; + CalculateWatermarks_params->MaxActiveFCLKChangeLatencySupported = &locals->MaxActiveFCLKChangeLatencySupported; // dml_float_t *MaxActiveFCLKChangeLatencySupported + CalculateWatermarks_params->USRRetrainingSupport = &locals->USRRetrainingSupport; CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( &mode_lib->scratch, diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c index fa6a93dd9629..64d01a9cd68c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c @@ -626,8 +626,8 @@ static void populate_dml_output_cfg_from_stream_state(struct dml_output_cfg_st * if (is_dp2p0_output_encoder(pipe)) out->OutputEncoder[location] = dml_dp2p0; break; - out->OutputEncoder[location] = dml_edp; case SIGNAL_TYPE_EDP: + out->OutputEncoder[location] = dml_edp; break; case SIGNAL_TYPE_HDMI_TYPE_A: case SIGNAL_TYPE_DVI_SINGLE_LINK: diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index fb328cd06cea..5660f15da291 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -1354,7 +1354,7 @@ static void build_audio_output( if (state->clk_mgr && (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT || pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)) { - audio_output->pll_info.dp_dto_source_clock_in_khz = + audio_output->pll_info.audio_dto_source_clock_in_khz = state->clk_mgr->funcs->get_dp_ref_clk_frequency( state->clk_mgr); } diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c index 51dd2ae09b2a..6dd479e8a348 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c @@ -3076,7 +3076,7 @@ void dcn10_prepare_bandwidth( context, false); - dc->optimized_required |= hubbub->funcs->program_watermarks(hubbub, + dc->wm_optimized_required = hubbub->funcs->program_watermarks(hubbub, &context->bw_ctx.bw.dcn.watermarks, dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000, true); diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c index bc71a9b058fe..e931342fcf4c 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c @@ -1882,42 +1882,6 @@ static void dcn20_program_pipe( } } -static void update_vmin_vmax_fams(struct dc *dc, - struct dc_state *context) -{ - uint32_t i; - struct drr_params params = {0}; - bool subvp_in_use = resource_subvp_in_use(dc, context); - - for (i = 0; i < dc->res_pool->pipe_count; i++) { - struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; - - if (resource_is_pipe_type(pipe, OTG_MASTER) && - ((subvp_in_use && dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_PHANTOM && - pipe->stream->allow_freesync) || (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching && pipe->stream->fpo_in_use))) { - if (!pipe->stream->vrr_active_variable && !pipe->stream->vrr_active_fixed) { - struct timing_generator *tg = context->res_ctx.pipe_ctx[i].stream_res.tg; - - /* DRR should be configured already if we're in active variable - * or active fixed, so only program if we're not in this state - */ - params.vertical_total_min = pipe->stream->timing.v_total; - params.vertical_total_max = pipe->stream->timing.v_total; - tg->funcs->set_drr(tg, ¶ms); - } - } else { - if (resource_is_pipe_type(pipe, OTG_MASTER) && - !pipe->stream->vrr_active_variable && - !pipe->stream->vrr_active_fixed) { - struct timing_generator *tg = context->res_ctx.pipe_ctx[i].stream_res.tg; - params.vertical_total_min = 0; - params.vertical_total_max = 0; - tg->funcs->set_drr(tg, ¶ms); - } - } - } -} - void dcn20_program_front_end_for_ctx( struct dc *dc, struct dc_state *context) @@ -1994,7 +1958,6 @@ void dcn20_program_front_end_for_ctx( && context->res_ctx.pipe_ctx[i].stream) hws->funcs.blank_pixel_data(dc, &context->res_ctx.pipe_ctx[i], true); - update_vmin_vmax_fams(dc, context); /* Disconnect mpcc */ for (i = 0; i < dc->res_pool->pipe_count; i++) @@ -2196,10 +2159,10 @@ void dcn20_prepare_bandwidth( } /* program dchubbub watermarks: - * For assigning optimized_required, use |= operator since we don't want + * For assigning wm_optimized_required, use |= operator since we don't want * to clear the value if the optimize has not happened yet */ - dc->optimized_required |= hubbub->funcs->program_watermarks(hubbub, + dc->wm_optimized_required |= hubbub->funcs->program_watermarks(hubbub, &context->bw_ctx.bw.dcn.watermarks, dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000, false); @@ -2212,10 +2175,10 @@ void dcn20_prepare_bandwidth( if (hubbub->funcs->program_compbuf_size) { if (context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes) { compbuf_size_kb = context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes; - dc->optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.dml.ip.min_comp_buffer_size_kbytes); + dc->wm_optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.dml.ip.min_comp_buffer_size_kbytes); } else { compbuf_size_kb = context->bw_ctx.bw.dcn.compbuf_size_kb; - dc->optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.bw.dcn.compbuf_size_kb); + dc->wm_optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.bw.dcn.compbuf_size_kb); } hubbub->funcs->program_compbuf_size(hubbub, compbuf_size_kb, false); diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h index cbba39d251e5..17e014d3bdc8 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h @@ -333,6 +333,7 @@ struct clk_mgr { bool force_smu_not_present; bool dc_mode_softmax_enabled; int dprefclk_khz; // Used by program pixel clock in clock source funcs, need to figureout where this goes + int dp_dto_source_clock_in_khz; // Used to program DP DTO with ss adjustment on DCN314 int dentist_vco_freq_khz; struct clk_state_registers_and_bypass boot_snapshot; struct clk_bw_params *bw_params; diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h index 1d51fed12e20..c958ef37b78a 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/resource.h +++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h @@ -609,9 +609,6 @@ bool dc_resource_acquire_secondary_pipe_for_mpc_odm_legacy( struct pipe_ctx *sec_pipe, bool odm); -bool resource_subvp_in_use(struct dc *dc, - struct dc_state *context); - /* A test harness interface that modifies dp encoder resources in the given dc * state and bypasses the need to revalidate. The interface assumes that the * test harness interface is called with pre-validated link config stored in the diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c index 5fe8b4871c77..3cbfbf8d107e 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c @@ -900,11 +900,15 @@ bool link_set_dsc_pps_packet(struct pipe_ctx *pipe_ctx, bool enable, bool immedi { struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc; struct dc_stream_state *stream = pipe_ctx->stream; - DC_LOGGER_INIT(dsc->ctx->logger); - if (!pipe_ctx->stream->timing.flags.DSC || !dsc) + if (!pipe_ctx->stream->timing.flags.DSC) return false; + if (!dsc) + return false; + + DC_LOGGER_INIT(dsc->ctx->logger); + if (enable) { struct dsc_config dsc_cfg; uint8_t dsc_packed_pps[128]; @@ -2005,17 +2009,11 @@ static enum dc_status enable_link_dp(struct dc_state *state, } } - /* - * If the link is DP-over-USB4 do the following: - * - Train with fallback when enabling DPIA link. Conventional links are + /* Train with fallback when enabling DPIA link. Conventional links are * trained with fallback during sink detection. - * - Allocate only what the stream needs for bw in Gbps. Inform the CM - * in case stream needs more or less bw from what has been allocated - * earlier at plug time. */ - if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) do_fallback = true; - } /* * Temporary w/a to get DP2.0 link rates to work with SST. @@ -2197,6 +2195,32 @@ static enum dc_status enable_link( return status; } +static bool allocate_usb4_bandwidth_for_stream(struct dc_stream_state *stream, int bw) +{ + return true; +} + +static bool allocate_usb4_bandwidth(struct dc_stream_state *stream) +{ + bool ret; + + int bw = dc_bandwidth_in_kbps_from_timing(&stream->timing, + dc_link_get_highest_encoding_format(stream->sink->link)); + + ret = allocate_usb4_bandwidth_for_stream(stream, bw); + + return ret; +} + +static bool deallocate_usb4_bandwidth(struct dc_stream_state *stream) +{ + bool ret; + + ret = allocate_usb4_bandwidth_for_stream(stream, 0); + + return ret; +} + void link_set_dpms_off(struct pipe_ctx *pipe_ctx) { struct dc *dc = pipe_ctx->stream->ctx->dc; @@ -2232,6 +2256,9 @@ void link_set_dpms_off(struct pipe_ctx *pipe_ctx) update_psp_stream_config(pipe_ctx, true); dc->hwss.blank_stream(pipe_ctx); + if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) + deallocate_usb4_bandwidth(pipe_ctx->stream); + if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) deallocate_mst_payload(pipe_ctx); else if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT && @@ -2474,6 +2501,9 @@ void link_set_dpms_on( } } + if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) + allocate_usb4_bandwidth(pipe_ctx->stream); + if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) allocate_mst_payload(pipe_ctx); else if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT && diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c index b45fda96eaf6..8fe66c367850 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c @@ -346,23 +346,61 @@ enum dc_status link_validate_mode_timing( return DC_OK; } +/* + * This function calculates the bandwidth required for the stream timing + * and aggregates the stream bandwidth for the respective dpia link + * + * @stream: pointer to the dc_stream_state struct instance + * @num_streams: number of streams to be validated + * + * return: true if validation is succeeded + */ bool link_validate_dpia_bandwidth(const struct dc_stream_state *stream, const unsigned int num_streams) { - bool ret = true; - int bw_needed[MAX_DPIA_NUM]; - struct dc_link *link[MAX_DPIA_NUM]; - - if (!num_streams || num_streams > MAX_DPIA_NUM) - return ret; + int bw_needed[MAX_DPIA_NUM] = {0}; + struct dc_link *dpia_link[MAX_DPIA_NUM] = {0}; + int num_dpias = 0; for (uint8_t i = 0; i < num_streams; ++i) { + if (stream[i].signal == SIGNAL_TYPE_DISPLAY_PORT) { + /* new dpia sst stream, check whether it exceeds max dpia */ + if (num_dpias >= MAX_DPIA_NUM) + return false; - link[i] = stream[i].link; - bw_needed[i] = dc_bandwidth_in_kbps_from_timing(&stream[i].timing, - dc_link_get_highest_encoding_format(link[i])); + dpia_link[num_dpias] = stream[i].link; + bw_needed[num_dpias] = dc_bandwidth_in_kbps_from_timing(&stream[i].timing, + dc_link_get_highest_encoding_format(dpia_link[num_dpias])); + num_dpias++; + } else if (stream[i].signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { + uint8_t j = 0; + /* check whether its a known dpia link */ + for (; j < num_dpias; ++j) { + if (dpia_link[j] == stream[i].link) + break; + } + + if (j == num_dpias) { + /* new dpia mst stream, check whether it exceeds max dpia */ + if (num_dpias >= MAX_DPIA_NUM) + return false; + else { + dpia_link[j] = stream[i].link; + num_dpias++; + } + } + + bw_needed[j] += dc_bandwidth_in_kbps_from_timing(&stream[i].timing, + dc_link_get_highest_encoding_format(dpia_link[j])); + } } - ret = dpia_validate_usb4_bw(link, bw_needed, num_streams); + /* Include dp overheads */ + for (uint8_t i = 0; i < num_dpias; ++i) { + int dp_overhead = 0; + + dp_overhead = link_dp_dpia_get_dp_overhead_in_dp_tunneling(dpia_link[i]); + bw_needed[i] += dp_overhead; + } - return ret; + return dpia_validate_usb4_bw(dpia_link, bw_needed, num_dpias); } diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c index 982eda3c46f5..6af42ba9885c 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c @@ -82,25 +82,33 @@ bool dpia_query_hpd_status(struct dc_link *link) { union dmub_rb_cmd cmd = {0}; struct dc_dmub_srv *dmub_srv = link->ctx->dmub_srv; - bool is_hpd_high = false; /* prepare QUERY_HPD command */ cmd.query_hpd.header.type = DMUB_CMD__QUERY_HPD_STATE; cmd.query_hpd.data.instance = link->link_id.enum_id - ENUM_ID_1; cmd.query_hpd.data.ch_type = AUX_CHANNEL_DPIA; - /* Return HPD status reported by DMUB if query successfully executed. */ - if (dc_wake_and_execute_dmub_cmd(dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY) && - cmd.query_hpd.data.status == AUX_RET_SUCCESS) - is_hpd_high = cmd.query_hpd.data.result; - - DC_LOG_DEBUG("%s: link(%d) dpia(%d) cmd_status(%d) result(%d)\n", - __func__, - link->link_index, - link->link_id.enum_id - ENUM_ID_1, - cmd.query_hpd.data.status, - cmd.query_hpd.data.result); - - return is_hpd_high; + /* Query dpia hpd status from dmub */ + if (dc_wake_and_execute_dmub_cmd(dmub_srv->ctx, &cmd, + DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY) && + cmd.query_hpd.data.status == AUX_RET_SUCCESS) { + DC_LOG_DEBUG("%s: for link(%d) dpia(%d) success, current_hpd_status(%d) new_hpd_status(%d)\n", + __func__, + link->link_index, + link->link_id.enum_id - ENUM_ID_1, + link->hpd_status, + cmd.query_hpd.data.result); + link->hpd_status = cmd.query_hpd.data.result; + } else { + DC_LOG_ERROR("%s: for link(%d) dpia(%d) failed with status(%d), current_hpd_status(%d) new_hpd_status(0)\n", + __func__, + link->link_index, + link->link_id.enum_id - ENUM_ID_1, + cmd.query_hpd.data.status, + link->hpd_status); + link->hpd_status = false; + } + + return link->hpd_status; } diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c index a7aa8c9da868..dd0d2b206462 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c @@ -54,12 +54,18 @@ static bool get_bw_alloc_proceed_flag(struct dc_link *tmp) static void reset_bw_alloc_struct(struct dc_link *link) { link->dpia_bw_alloc_config.bw_alloc_enabled = false; - link->dpia_bw_alloc_config.sink_verified_bw = 0; - link->dpia_bw_alloc_config.sink_max_bw = 0; + link->dpia_bw_alloc_config.link_verified_bw = 0; + link->dpia_bw_alloc_config.link_max_bw = 0; + link->dpia_bw_alloc_config.allocated_bw = 0; link->dpia_bw_alloc_config.estimated_bw = 0; link->dpia_bw_alloc_config.bw_granularity = 0; + link->dpia_bw_alloc_config.dp_overhead = 0; link->dpia_bw_alloc_config.response_ready = false; - link->dpia_bw_alloc_config.sink_allocated_bw = 0; + link->dpia_bw_alloc_config.nrd_max_lane_count = 0; + link->dpia_bw_alloc_config.nrd_max_link_rate = 0; + for (int i = 0; i < MAX_SINKS_PER_LINK; i++) + link->dpia_bw_alloc_config.remote_sink_req_bw[i] = 0; + DC_LOG_DEBUG("reset usb4 bw alloc of link(%d)\n", link->link_index); } #define BW_GRANULARITY_0 4 // 0.25 Gbps @@ -210,8 +216,8 @@ static int get_host_router_total_dp_tunnel_bw(const struct dc *dc, uint8_t hr_in link_dpia_primary->dpia_bw_alloc_config.bw_alloc_enabled) && (link_dpia_secondary->hpd_status && link_dpia_secondary->dpia_bw_alloc_config.bw_alloc_enabled)) { - total_bw += link_dpia_primary->dpia_bw_alloc_config.estimated_bw + - link_dpia_secondary->dpia_bw_alloc_config.sink_allocated_bw; + total_bw += link_dpia_primary->dpia_bw_alloc_config.estimated_bw + + link_dpia_secondary->dpia_bw_alloc_config.allocated_bw; } else if (link_dpia_primary->hpd_status && link_dpia_primary->dpia_bw_alloc_config.bw_alloc_enabled) { total_bw = link_dpia_primary->dpia_bw_alloc_config.estimated_bw; @@ -264,7 +270,7 @@ static void set_usb4_req_bw_req(struct dc_link *link, int req_bw) /* Error check whether requested and allocated are equal */ req_bw = requested_bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity); - if (req_bw == link->dpia_bw_alloc_config.sink_allocated_bw) { + if (req_bw == link->dpia_bw_alloc_config.allocated_bw) { DC_LOG_ERROR("%s: Request bw equals to allocated bw for link(%d)\n", __func__, link->link_index); } @@ -387,9 +393,9 @@ void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t res DC_LOG_DEBUG("%s: BW REQ SUCCESS for DP-TX Request for link(%d)\n", __func__, link->link_index); DC_LOG_DEBUG("%s: current allocated_bw(%d), new allocated_bw(%d)\n", - __func__, link->dpia_bw_alloc_config.sink_allocated_bw, bw_needed); + __func__, link->dpia_bw_alloc_config.allocated_bw, bw_needed); - link->dpia_bw_alloc_config.sink_allocated_bw = bw_needed; + link->dpia_bw_alloc_config.allocated_bw = bw_needed; link->dpia_bw_alloc_config.response_ready = true; break; @@ -427,8 +433,8 @@ int dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pea if (link->hpd_status && peak_bw > 0) { // If DP over USB4 then we need to check BW allocation - link->dpia_bw_alloc_config.sink_max_bw = peak_bw; - set_usb4_req_bw_req(link, link->dpia_bw_alloc_config.sink_max_bw); + link->dpia_bw_alloc_config.link_max_bw = peak_bw; + set_usb4_req_bw_req(link, link->dpia_bw_alloc_config.link_max_bw); do { if (timeout > 0) @@ -440,8 +446,8 @@ int dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pea if (!timeout) ret = 0;// ERROR TIMEOUT waiting for response for allocating bw - else if (link->dpia_bw_alloc_config.sink_allocated_bw > 0) - ret = link->dpia_bw_alloc_config.sink_allocated_bw; + else if (link->dpia_bw_alloc_config.allocated_bw > 0) + ret = link->dpia_bw_alloc_config.allocated_bw; } //2. Cold Unplug else if (!link->hpd_status) @@ -450,7 +456,6 @@ int dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pea out: return ret; } - bool link_dp_dpia_allocate_usb4_bandwidth_for_stream(struct dc_link *link, int req_bw) { bool ret = false; @@ -458,7 +463,7 @@ bool link_dp_dpia_allocate_usb4_bandwidth_for_stream(struct dc_link *link, int r DC_LOG_DEBUG("%s: ENTER: link(%d), hpd_status(%d), current allocated_bw(%d), req_bw(%d)\n", __func__, link->link_index, link->hpd_status, - link->dpia_bw_alloc_config.sink_allocated_bw, req_bw); + link->dpia_bw_alloc_config.allocated_bw, req_bw); if (!get_bw_alloc_proceed_flag(link)) goto out; @@ -523,3 +528,30 @@ bool dpia_validate_usb4_bw(struct dc_link **link, int *bw_needed_per_dpia, const return ret; } + +int link_dp_dpia_get_dp_overhead_in_dp_tunneling(struct dc_link *link) +{ + int dp_overhead = 0, link_mst_overhead = 0; + + if (!get_bw_alloc_proceed_flag((link))) + return dp_overhead; + + /* if its mst link, add MTPH overhead */ + if ((link->type == dc_connection_mst_branch) && + !link->dpcd_caps.channel_coding_cap.bits.DP_128b_132b_SUPPORTED) { + /* For 8b/10b encoding: MTP is 64 time slots long, slot 0 is used for MTPH + * MST overhead is 1/64 of link bandwidth (excluding any overhead) + */ + const struct dc_link_settings *link_cap = + dc_link_get_link_cap(link); + uint32_t link_bw_in_kbps = (uint32_t)link_cap->link_rate * + (uint32_t)link_cap->lane_count * + LINK_RATE_REF_FREQ_IN_KHZ * 8; + link_mst_overhead = (link_bw_in_kbps / 64) + ((link_bw_in_kbps % 64) ? 1 : 0); + } + + /* add all the overheads */ + dp_overhead = link_mst_overhead; + + return dp_overhead; +} diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h index 981bc4eb6120..3b6d8494f9d5 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h @@ -99,4 +99,13 @@ void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t res */ bool dpia_validate_usb4_bw(struct dc_link **link, int *bw_needed, const unsigned int num_dpias); +/* + * Obtain all the DP overheads in dp tunneling for the dpia link + * + * @link: pointer to the dc_link struct instance + * + * return: DP overheads in DP tunneling + */ +int link_dp_dpia_get_dp_overhead_in_dp_tunneling(struct dc_link *link); + #endif /* DC_INC_LINK_DP_DPIA_BW_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c index 7f1196528218..046d3e205415 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c @@ -930,8 +930,8 @@ bool edp_get_replay_state(const struct dc_link *link, uint64_t *state) bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream) { /* To-do: Setup Replay */ - struct dc *dc = link->ctx->dc; - struct dmub_replay *replay = dc->res_pool->replay; + struct dc *dc; + struct dmub_replay *replay; int i; unsigned int panel_inst; struct replay_context replay_context = { 0 }; @@ -947,6 +947,10 @@ bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream if (!link) return false; + dc = link->ctx->dc; + + replay = dc->res_pool->replay; + if (!replay) return false; @@ -975,8 +979,7 @@ bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream replay_context.line_time_in_ns = lineTimeInNs; - if (replay) - link->replay_settings.replay_feature_enabled = + link->replay_settings.replay_feature_enabled = replay->funcs->replay_copy_settings(replay, link, &replay_context, panel_inst); if (link->replay_settings.replay_feature_enabled) { diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c index 91ea0d4da06a..823493543325 100644 --- a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c +++ b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c @@ -166,12 +166,6 @@ static bool optc32_disable_crtc(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); - /* disable otg request until end of the first line - * in the vertical blank region - */ - REG_UPDATE(OTG_CONTROL, - OTG_MASTER_EN, 0); - REG_UPDATE_5(OPTC_DATA_SOURCE_SELECT, OPTC_SEG0_SRC_SEL, 0xf, OPTC_SEG1_SRC_SEL, 0xf, @@ -179,6 +173,15 @@ static bool optc32_disable_crtc(struct timing_generator *optc) OPTC_SEG3_SRC_SEL, 0xf, OPTC_NUM_OF_INPUT_SEGMENT, 0); + REG_UPDATE(OPTC_MEMORY_CONFIG, + OPTC_MEM_SEL, 0); + + /* disable otg request until end of the first line + * in the vertical blank region + */ + REG_UPDATE(OTG_CONTROL, + OTG_MASTER_EN, 0); + REG_UPDATE(CONTROL, VTG0_ENABLE, 0); @@ -205,6 +208,13 @@ static void optc32_disable_phantom_otg(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); + REG_UPDATE_5(OPTC_DATA_SOURCE_SELECT, + OPTC_SEG0_SRC_SEL, 0xf, + OPTC_SEG1_SRC_SEL, 0xf, + OPTC_SEG2_SRC_SEL, 0xf, + OPTC_SEG3_SRC_SEL, 0xf, + OPTC_NUM_OF_INPUT_SEGMENT, 0); + REG_UPDATE(OTG_CONTROL, OTG_MASTER_EN, 0); } diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c index 08a59cf449ca..5b1547508850 100644 --- a/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c +++ b/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c @@ -138,12 +138,6 @@ static bool optc35_disable_crtc(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); - /* disable otg request until end of the first line - * in the vertical blank region - */ - REG_UPDATE(OTG_CONTROL, - OTG_MASTER_EN, 0); - REG_UPDATE_5(OPTC_DATA_SOURCE_SELECT, OPTC_SEG0_SRC_SEL, 0xf, OPTC_SEG1_SRC_SEL, 0xf, @@ -151,6 +145,15 @@ static bool optc35_disable_crtc(struct timing_generator *optc) OPTC_SEG3_SRC_SEL, 0xf, OPTC_NUM_OF_INPUT_SEGMENT, 0); + REG_UPDATE(OPTC_MEMORY_CONFIG, + OPTC_MEM_SEL, 0); + + /* disable otg request until end of the first line + * in the vertical blank region + */ + REG_UPDATE(OTG_CONTROL, + OTG_MASTER_EN, 0); + REG_UPDATE(CONTROL, VTG0_ENABLE, 0); diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c index ac04a9c9a3d8..c4d71e7f18af 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c @@ -1899,7 +1899,7 @@ int dcn32_populate_dml_pipes_from_context( static struct dc_cap_funcs cap_funcs = { .get_dcc_compression_cap = dcn20_get_dcc_compression_cap, - .get_subvp_en = resource_subvp_in_use, + .get_subvp_en = dcn32_subvp_in_use, }; void dcn32_calculate_wm_and_dlg(struct dc *dc, struct dc_state *context, diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h index 62611acd4bcb..0c87b0fabba7 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h @@ -131,6 +131,9 @@ void dcn32_merge_pipes_for_subvp(struct dc *dc, bool dcn32_all_pipes_have_stream_and_plane(struct dc *dc, struct dc_state *context); +bool dcn32_subvp_in_use(struct dc *dc, + struct dc_state *context); + bool dcn32_mpo_in_use(struct dc_state *context); bool dcn32_any_surfaces_rotated(struct dc *dc, struct dc_state *context); diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c index e1ab207c46f1..74412e5f03fe 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c @@ -1574,7 +1574,7 @@ static void dcn321_destroy_resource_pool(struct resource_pool **pool) static struct dc_cap_funcs cap_funcs = { .get_dcc_compression_cap = dcn20_get_dcc_compression_cap, - .get_subvp_en = resource_subvp_in_use, + .get_subvp_en = dcn32_subvp_in_use, }; static void dcn321_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params) diff --git a/drivers/gpu/drm/amd/display/include/audio_types.h b/drivers/gpu/drm/amd/display/include/audio_types.h index 66a54da0641c..915a031a43cb 100644 --- a/drivers/gpu/drm/amd/display/include/audio_types.h +++ b/drivers/gpu/drm/amd/display/include/audio_types.h @@ -64,7 +64,7 @@ enum audio_dto_source { /* PLL information required for AZALIA DTO calculation */ struct audio_pll_info { - uint32_t dp_dto_source_clock_in_khz; + uint32_t audio_dto_source_clock_in_khz; uint32_t feed_back_divider; enum audio_dto_source dto_source; bool ss_enabled; diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h index 7ee3d291120d..6f80bfa7e41a 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h @@ -8707,10 +8707,10 @@ #define regBIF_BX1_MM_CFGREGS_CNTL_BASE_IDX 2 #define regBIF_BX1_BX_RESET_CNTL 0x00f0 #define regBIF_BX1_BX_RESET_CNTL_BASE_IDX 2 -#define regBIF_BX1_INTERRUPT_CNTL 0x8e11 -#define regBIF_BX1_INTERRUPT_CNTL_BASE_IDX 5 -#define regBIF_BX1_INTERRUPT_CNTL2 0x8e12 -#define regBIF_BX1_INTERRUPT_CNTL2_BASE_IDX 5 +#define regBIF_BX1_INTERRUPT_CNTL 0x00f1 +#define regBIF_BX1_INTERRUPT_CNTL_BASE_IDX 2 +#define regBIF_BX1_INTERRUPT_CNTL2 0x00f2 +#define regBIF_BX1_INTERRUPT_CNTL2_BASE_IDX 2 #define regBIF_BX1_CLKREQB_PAD_CNTL 0x00f8 #define regBIF_BX1_CLKREQB_PAD_CNTL_BASE_IDX 2 #define regBIF_BX1_BIF_FEATURES_CONTROL_MISC 0x00fb diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index f3cb490fe79b..087d57850304 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -4349,11 +4349,19 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VDDNB, (void *)&value, &size)) seq_printf(m, "\t%u mV (VDDNB)\n", value); size = sizeof(uint32_t); - if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_AVG_POWER, (void *)&query, &size)) - seq_printf(m, "\t%u.%02u W (average GPU)\n", query >> 8, query & 0xff); + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_AVG_POWER, (void *)&query, &size)) { + if (adev->flags & AMD_IS_APU) + seq_printf(m, "\t%u.%02u W (average SoC including CPU)\n", query >> 8, query & 0xff); + else + seq_printf(m, "\t%u.%02u W (average SoC)\n", query >> 8, query & 0xff); + } size = sizeof(uint32_t); - if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_INPUT_POWER, (void *)&query, &size)) - seq_printf(m, "\t%u.%02u W (current GPU)\n", query >> 8, query & 0xff); + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_INPUT_POWER, (void *)&query, &size)) { + if (adev->flags & AMD_IS_APU) + seq_printf(m, "\t%u.%02u W (current SoC including CPU)\n", query >> 8, query & 0xff); + else + seq_printf(m, "\t%u.%02u W (current SoC)\n", query >> 8, query & 0xff); + } size = sizeof(value); seq_printf(m, "\n"); @@ -4379,9 +4387,9 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a /* VCN clocks */ if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCN_POWER_STATE, (void *)&value, &size)) { if (!value) { - seq_printf(m, "VCN: Disabled\n"); + seq_printf(m, "VCN: Powered down\n"); } else { - seq_printf(m, "VCN: Enabled\n"); + seq_printf(m, "VCN: Powered up\n"); if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size)) seq_printf(m, "\t%u MHz (DCLK)\n", value/100); if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size)) @@ -4393,9 +4401,9 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a /* UVD clocks */ if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_POWER, (void *)&value, &size)) { if (!value) { - seq_printf(m, "UVD: Disabled\n"); + seq_printf(m, "UVD: Powered down\n"); } else { - seq_printf(m, "UVD: Enabled\n"); + seq_printf(m, "UVD: Powered up\n"); if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size)) seq_printf(m, "\t%u MHz (DCLK)\n", value/100); if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size)) @@ -4407,9 +4415,9 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a /* VCE clocks */ if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_POWER, (void *)&value, &size)) { if (!value) { - seq_printf(m, "VCE: Disabled\n"); + seq_printf(m, "VCE: Powered down\n"); } else { - seq_printf(m, "VCE: Enabled\n"); + seq_printf(m, "VCE: Powered up\n"); if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_ECCLK, (void *)&value, &size)) seq_printf(m, "\t%u MHz (ECCLK)\n", value/100); } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c index f2a55c1413f5..17882f8dfdd3 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c @@ -200,7 +200,7 @@ static int get_platform_power_management_table( struct pp_hwmgr *hwmgr, ATOM_Tonga_PPM_Table *atom_ppm_table) { - struct phm_ppm_table *ptr = kzalloc(sizeof(ATOM_Tonga_PPM_Table), GFP_KERNEL); + struct phm_ppm_table *ptr = kzalloc(sizeof(*ptr), GFP_KERNEL); struct phm_ppt_v1_information *pp_table_information = (struct phm_ppt_v1_information *)(hwmgr->pptable); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index b1a8799e2dee..aa91730e4eaf 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -3999,6 +3999,7 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx, uint32_t sclk, mclk, activity_percent; uint32_t offset, val_vid; struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend); + struct amdgpu_device *adev = hwmgr->adev; /* size must be at least 4 bytes for all sensors */ if (*size < 4) @@ -4042,7 +4043,21 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx, *size = 4; return 0; case AMDGPU_PP_SENSOR_GPU_INPUT_POWER: - return smu7_get_gpu_power(hwmgr, (uint32_t *)value); + if ((adev->asic_type != CHIP_HAWAII) && + (adev->asic_type != CHIP_BONAIRE) && + (adev->asic_type != CHIP_FIJI) && + (adev->asic_type != CHIP_TONGA)) + return smu7_get_gpu_power(hwmgr, (uint32_t *)value); + else + return -EOPNOTSUPP; + case AMDGPU_PP_SENSOR_GPU_AVG_POWER: + if ((adev->asic_type != CHIP_HAWAII) && + (adev->asic_type != CHIP_BONAIRE) && + (adev->asic_type != CHIP_FIJI) && + (adev->asic_type != CHIP_TONGA)) + return -EOPNOTSUPP; + else + return smu7_get_gpu_power(hwmgr, (uint32_t *)value); case AMDGPU_PP_SENSOR_VDDGFX: if ((data->vr_config & VRCONF_VDDGFX_MASK) == (VR_SVI2_PLANE_2 << VRCONF_VDDGFX_SHIFT)) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index f1440869d1ce..dd9bcbd630a1 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -1530,7 +1530,6 @@ static int aldebaran_i2c_control_init(struct smu_context *smu) smu_i2c->port = 0; mutex_init(&smu_i2c->mutex); control->owner = THIS_MODULE; - control->class = I2C_CLASS_SPD; control->dev.parent = &adev->pdev->dev; control->algo = &aldebaran_i2c_algo; snprintf(control->name, sizeof(control->name), "AMDGPU SMU 0"); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 231122622a9c..a9b25faa63e4 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2696,7 +2696,6 @@ static int smu_v13_0_0_i2c_control_init(struct smu_context *smu) smu_i2c->port = i; mutex_init(&smu_i2c->mutex); control->owner = THIS_MODULE; - control->class = I2C_CLASS_SPD; control->dev.parent = &adev->pdev->dev; control->algo = &smu_v13_0_0_i2c_algo; snprintf(control->name, sizeof(control->name), "AMDGPU SMU %d", i); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 4ebc6b421c2c..3c98a8a0386a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -970,7 +970,9 @@ static int smu_v13_0_6_print_clks(struct smu_context *smu, char *buf, int size, if (i < (clocks.num_levels - 1)) clk2 = clocks.data[i + 1].clocks_in_khz / 1000; - if (curr_clk >= clk1 && curr_clk < clk2) { + if (curr_clk == clk1) { + level = i; + } else if (curr_clk >= clk1 && curr_clk < clk2) { level = (curr_clk - clk1) <= (clk2 - curr_clk) ? i : i + 1; @@ -1936,7 +1938,6 @@ static int smu_v13_0_6_i2c_control_init(struct smu_context *smu) smu_i2c->port = i; mutex_init(&smu_i2c->mutex); control->owner = THIS_MODULE; - control->class = I2C_CLASS_SPD; control->dev.parent = &adev->pdev->dev; control->algo = &smu_v13_0_6_i2c_algo; snprintf(control->name, sizeof(control->name), "AMDGPU SMU %d", i); @@ -2235,17 +2236,18 @@ static int smu_v13_0_6_mode2_reset(struct smu_context *smu) continue; } - if (ret) { - dev_err(adev->dev, - "failed to send mode2 message \tparam: 0x%08x error code %d\n", - SMU_RESET_MODE_2, ret); + if (ret) goto out; - } + } while (ret == -ETIME && timeout); out: mutex_unlock(&smu->message_lock); + if (ret) + dev_err(adev->dev, "failed to send mode2 reset, error code %d", + ret); + return ret; } diff --git a/drivers/gpu/drm/ast/ast_i2c.c b/drivers/gpu/drm/ast/ast_i2c.c index 0e845e7acd9b..e5d3f7121de4 100644 --- a/drivers/gpu/drm/ast/ast_i2c.c +++ b/drivers/gpu/drm/ast/ast_i2c.c @@ -120,7 +120,6 @@ struct ast_i2c_chan *ast_i2c_create(struct drm_device *dev) return NULL; i2c->adapter.owner = THIS_MODULE; - i2c->adapter.class = I2C_CLASS_DDC; i2c->adapter.dev.parent = dev->dev; i2c->dev = dev; i2c_set_adapdata(&i2c->adapter, i2c); diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index 52d91a0df85e..aca5bb0866f8 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -515,7 +515,6 @@ static struct i2c_adapter *dw_hdmi_i2c_adapter(struct dw_hdmi *hdmi) init_completion(&i2c->cmp); adap = &i2c->adap; - adap->class = I2C_CLASS_DDC; adap->owner = THIS_MODULE; adap->dev.parent = hdmi->dev; adap->algo = &dw_hdmi_algorithm; diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index d72b6f9a352c..b1ca3a1100da 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -2102,7 +2102,6 @@ int drm_dp_aux_register(struct drm_dp_aux *aux) if (!aux->ddc.algo) drm_dp_aux_init(aux); - aux->ddc.class = I2C_CLASS_DDC; aux->ddc.owner = THIS_MODULE; aux->ddc.dev.parent = aux->dev; diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index 8ca01a6bf645..bd6c24d4213c 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -5926,7 +5926,6 @@ static int drm_dp_mst_register_i2c_bus(struct drm_dp_mst_port *port) aux->ddc.algo_data = aux; aux->ddc.retries = 3; - aux->ddc.class = I2C_CLASS_DDC; aux->ddc.owner = THIS_MODULE; /* FIXME: set the kdev of the port's connector as parent */ aux->ddc.dev.parent = parent_dev; diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c index 8992a95076f2..dd1eb7e9877d 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_dp.c +++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c @@ -855,7 +855,6 @@ cdv_intel_dp_i2c_init(struct gma_connector *connector, memset(&intel_dp->adapter, '\0', sizeof (intel_dp->adapter)); intel_dp->adapter.owner = THIS_MODULE; - intel_dp->adapter.class = I2C_CLASS_DDC; strncpy (intel_dp->adapter.name, name, sizeof(intel_dp->adapter.name) - 1); intel_dp->adapter.name[sizeof(intel_dp->adapter.name) - 1] = '\0'; intel_dp->adapter.algo_data = &intel_dp->algo; diff --git a/drivers/gpu/drm/gma500/intel_gmbus.c b/drivers/gpu/drm/gma500/intel_gmbus.c index 09cedabf4776..aa45509859f2 100644 --- a/drivers/gpu/drm/gma500/intel_gmbus.c +++ b/drivers/gpu/drm/gma500/intel_gmbus.c @@ -411,7 +411,6 @@ int gma_intel_setup_gmbus(struct drm_device *dev) struct intel_gmbus *bus = &dev_priv->gmbus[i]; bus->adapter.owner = THIS_MODULE; - bus->adapter.class = I2C_CLASS_DDC; snprintf(bus->adapter.name, sizeof(bus->adapter.name), "gma500 gmbus %s", diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c b/drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c index fc9a34ed58bd..6daa6669ed23 100644 --- a/drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c +++ b/drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c @@ -168,7 +168,6 @@ static struct i2c_adapter oaktrail_hdmi_i2c_adapter = { .name = "oaktrail_hdmi_i2c", .nr = 3, .owner = THIS_MODULE, - .class = I2C_CLASS_DDC, .algo = &oaktrail_hdmi_i2c_algorithm, }; diff --git a/drivers/gpu/drm/gma500/psb_intel_sdvo.c b/drivers/gpu/drm/gma500/psb_intel_sdvo.c index d6fd5d726216..e4f914deceba 100644 --- a/drivers/gpu/drm/gma500/psb_intel_sdvo.c +++ b/drivers/gpu/drm/gma500/psb_intel_sdvo.c @@ -2426,7 +2426,6 @@ psb_intel_sdvo_init_ddc_proxy(struct psb_intel_sdvo *sdvo, struct drm_device *dev) { sdvo->ddc.owner = THIS_MODULE; - sdvo->ddc.class = I2C_CLASS_DDC; snprintf(sdvo->ddc.name, I2C_NAME_SIZE, "SDVO DDC proxy"); sdvo->ddc.dev.parent = dev->dev; sdvo->ddc.algo_data = sdvo; diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c index 410bd019bb35..e6e48651c15c 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c @@ -81,7 +81,6 @@ int hibmc_ddc_create(struct drm_device *drm_dev, struct hibmc_connector *connector) { connector->adapter.owner = THIS_MODULE; - connector->adapter.class = I2C_CLASS_DDC; snprintf(connector->adapter.name, I2C_NAME_SIZE, "HIS i2c bit bus"); connector->adapter.dev.parent = drm_dev->dev; i2c_set_adapdata(&connector->adapter, connector); diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.c b/drivers/gpu/drm/i915/display/intel_gmbus.c index 40d7b6f3f489..e9e4dcf345f9 100644 --- a/drivers/gpu/drm/i915/display/intel_gmbus.c +++ b/drivers/gpu/drm/i915/display/intel_gmbus.c @@ -899,7 +899,6 @@ int intel_gmbus_setup(struct drm_i915_private *i915) } bus->adapter.owner = THIS_MODULE; - bus->adapter.class = I2C_CLASS_DDC; snprintf(bus->adapter.name, sizeof(bus->adapter.name), "i915 gmbus %s", gmbus_pin->name); diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index 9218047495fb..acc6b6804105 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -3327,7 +3327,6 @@ intel_sdvo_init_ddc_proxy(struct intel_sdvo_ddc *ddc, ddc->ddc_bus = ddc_bus; ddc->ddc.owner = THIS_MODULE; - ddc->ddc.class = I2C_CLASS_DDC; snprintf(ddc->ddc.name, I2C_NAME_SIZE, "SDVO %c DDC%d", port_name(sdvo->base.port), ddc_bus); ddc->ddc.dev.parent = &pdev->dev; diff --git a/drivers/gpu/drm/loongson/lsdc_i2c.c b/drivers/gpu/drm/loongson/lsdc_i2c.c index 9625d0b1d0b4..ce90c25536d2 100644 --- a/drivers/gpu/drm/loongson/lsdc_i2c.c +++ b/drivers/gpu/drm/loongson/lsdc_i2c.c @@ -154,7 +154,6 @@ int lsdc_create_i2c_chan(struct drm_device *ddev, adapter = &li2c->adapter; adapter->algo_data = &li2c->bit; adapter->owner = THIS_MODULE; - adapter->class = I2C_CLASS_DDC; adapter->dev.parent = ddev->dev; adapter->nr = -1; diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c index d675c954befe..54e46e440e0f 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c @@ -297,7 +297,6 @@ static int mtk_hdmi_ddc_probe(struct platform_device *pdev) strscpy(ddc->adap.name, "mediatek-hdmi-ddc", sizeof(ddc->adap.name)); ddc->adap.owner = THIS_MODULE; - ddc->adap.class = I2C_CLASS_DDC; ddc->adap.algo = &mtk_hdmi_ddc_algorithm; ddc->adap.retries = 3; ddc->adap.dev.of_node = dev->of_node; diff --git a/drivers/gpu/drm/mgag200/mgag200_i2c.c b/drivers/gpu/drm/mgag200/mgag200_i2c.c index 0c48bdf3e7f8..423eb302be7e 100644 --- a/drivers/gpu/drm/mgag200/mgag200_i2c.c +++ b/drivers/gpu/drm/mgag200/mgag200_i2c.c @@ -106,7 +106,6 @@ int mgag200_i2c_init(struct mga_device *mdev, struct mga_i2c_chan *i2c) i2c->data = BIT(info->i2c.data_bit); i2c->clock = BIT(info->i2c.clock_bit); i2c->adapter.owner = THIS_MODULE; - i2c->adapter.class = I2C_CLASS_DDC; i2c->adapter.dev.parent = dev->dev; i2c->dev = dev; i2c_set_adapdata(&i2c->adapter, i2c); diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c b/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c index de182c004843..7aa500d24240 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c @@ -249,7 +249,6 @@ struct i2c_adapter *msm_hdmi_i2c_init(struct hdmi *hdmi) i2c->owner = THIS_MODULE; - i2c->class = I2C_CLASS_DDC; snprintf(i2c->name, sizeof(i2c->name), "msm hdmi i2c"); i2c->dev.parent = &hdmi->pdev->dev; i2c->algo = &msm_hdmi_i2c_algorithm; diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.c b/drivers/gpu/drm/nouveau/nouveau_vmm.c index a6602c012671..3dda885df5b2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c @@ -108,6 +108,9 @@ nouveau_vma_new(struct nouveau_bo *nvbo, struct nouveau_vmm *vmm, } else { ret = nvif_vmm_get(&vmm->vmm, PTES, false, mem->mem.page, 0, mem->mem.size, &tmp); + if (ret) + goto done; + vma->addr = tmp.addr; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c index e7e8fdf3adab..29682722b0b3 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c @@ -28,19 +28,14 @@ static void gp10b_ltc_init(struct nvkm_ltc *ltc) { struct nvkm_device *device = ltc->subdev.device; - struct iommu_fwspec *spec; + u32 sid; nvkm_wr32(device, 0x17e27c, ltc->ltc_nr); nvkm_wr32(device, 0x17e000, ltc->ltc_nr); nvkm_wr32(device, 0x100800, ltc->ltc_nr); - spec = dev_iommu_fwspec_get(device->dev); - if (spec) { - u32 sid = spec->ids[0] & 0xffff; - - /* stream ID */ + if (tegra_dev_iommu_get_stream_id(device->dev, &sid)) nvkm_wr32(device, 0x160000, sid << 2); - } } static const struct nvkm_ltc_func diff --git a/drivers/gpu/drm/radeon/radeon_i2c.c b/drivers/gpu/drm/radeon/radeon_i2c.c index 314d066e68e9..3d174390a8af 100644 --- a/drivers/gpu/drm/radeon/radeon_i2c.c +++ b/drivers/gpu/drm/radeon/radeon_i2c.c @@ -918,7 +918,6 @@ struct radeon_i2c_chan *radeon_i2c_create(struct drm_device *dev, i2c->rec = *rec; i2c->adapter.owner = THIS_MODULE; - i2c->adapter.class = I2C_CLASS_DDC; i2c->adapter.dev.parent = dev->dev; i2c->dev = dev; i2c_set_adapdata(&i2c->adapter, i2c); diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c index f6d819803c0e..e6fbe040ccf6 100644 --- a/drivers/gpu/drm/rockchip/inno_hdmi.c +++ b/drivers/gpu/drm/rockchip/inno_hdmi.c @@ -792,7 +792,6 @@ static struct i2c_adapter *inno_hdmi_i2c_adapter(struct inno_hdmi *hdmi) init_completion(&i2c->cmp); adap = &i2c->adap; - adap->class = I2C_CLASS_DDC; adap->owner = THIS_MODULE; adap->dev.parent = hdmi->dev; adap->dev.of_node = hdmi->dev->of_node; diff --git a/drivers/gpu/drm/rockchip/rk3066_hdmi.c b/drivers/gpu/drm/rockchip/rk3066_hdmi.c index 62e6d8187de7..95cd1b49eda8 100644 --- a/drivers/gpu/drm/rockchip/rk3066_hdmi.c +++ b/drivers/gpu/drm/rockchip/rk3066_hdmi.c @@ -715,7 +715,6 @@ static struct i2c_adapter *rk3066_hdmi_i2c_adapter(struct rk3066_hdmi *hdmi) init_completion(&i2c->cmpltn); adap = &i2c->adap; - adap->class = I2C_CLASS_DDC; adap->owner = THIS_MODULE; adap->dev.parent = hdmi->dev; adap->dev.of_node = hdmi->dev->of_node; diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_i2c.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_i2c.c index d1a65a921f5a..f5f62eb0eeca 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi_i2c.c +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_i2c.c @@ -302,7 +302,6 @@ int sun4i_hdmi_i2c_create(struct device *dev, struct sun4i_hdmi *hdmi) return -ENOMEM; adap->owner = THIS_MODULE; - adap->class = I2C_CLASS_DDC; adap->algo = &sun4i_hdmi_i2c_algorithm; strscpy(adap->name, "sun4i_hdmi_i2c adapter", sizeof(adap->name)); i2c_set_adapdata(adap, hdmi); diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig index 1cced50d8d8c..e36ae1f0d885 100644 --- a/drivers/gpu/drm/xe/Kconfig +++ b/drivers/gpu/drm/xe/Kconfig @@ -47,7 +47,7 @@ config DRM_XE config DRM_XE_DISPLAY bool "Enable display support" - depends on DRM_XE && EXPERT && DRM_XE=m + depends on DRM_XE && DRM_XE=m select FB_IOMEM_HELPERS select I2C select I2C_ALGOBIT diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index 53bd2a8ba1ae..efcf0ab7a1a6 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -17,7 +17,6 @@ subdir-ccflags-y += $(call cc-option, -Wunused-const-variable) subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned) subdir-ccflags-y += $(call cc-option, -Wformat-overflow) subdir-ccflags-y += $(call cc-option, -Wformat-truncation) -subdir-ccflags-y += $(call cc-option, -Wstringop-overflow) subdir-ccflags-y += $(call cc-option, -Wstringop-truncation) # The following turn off the warnings enabled by -Wextra ifeq ($(findstring 2, $(KBUILD_EXTRA_WARN)),) diff --git a/drivers/gpu/drm/xe/tests/xe_bo.c b/drivers/gpu/drm/xe/tests/xe_bo.c index 412b2e7ce40c..3436fd9cf2b2 100644 --- a/drivers/gpu/drm/xe/tests/xe_bo.c +++ b/drivers/gpu/drm/xe/tests/xe_bo.c @@ -125,14 +125,13 @@ static void ccs_test_run_tile(struct xe_device *xe, struct xe_tile *tile, bo = xe_bo_create_user(xe, NULL, NULL, SZ_1M, DRM_XE_GEM_CPU_CACHING_WC, ttm_bo_type_device, bo_flags); - - xe_bo_lock(bo, false); - if (IS_ERR(bo)) { KUNIT_FAIL(test, "Failed to create bo.\n"); return; } + xe_bo_lock(bo, false); + kunit_info(test, "Verifying that CCS data is cleared on creation.\n"); ret = ccs_test_migrate(tile, bo, false, 0ULL, 0xdeadbeefdeadbeefULL, test); diff --git a/drivers/gpu/drm/xe/tests/xe_migrate.c b/drivers/gpu/drm/xe/tests/xe_migrate.c index 7a32faa2f688..a6523df0f1d3 100644 --- a/drivers/gpu/drm/xe/tests/xe_migrate.c +++ b/drivers/gpu/drm/xe/tests/xe_migrate.c @@ -331,7 +331,7 @@ static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test) xe_res_first_sg(xe_bo_sg(pt), 0, pt->size, &src_it); emit_pte(m, bb, NUM_KERNEL_PDE - 1, xe_bo_is_vram(pt), false, - &src_it, XE_PAGE_SIZE, pt); + &src_it, XE_PAGE_SIZE, pt->ttm.resource); run_sanity_job(m, xe, bb, bb->len, "Writing PTE for our fake PT", test); diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 8e4a3b1f6b93..0b0e262e2166 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -125,9 +125,9 @@ static struct xe_mem_region *res_to_mem_region(struct ttm_resource *res) static void try_add_system(struct xe_device *xe, struct xe_bo *bo, u32 bo_flags, u32 *c) { - xe_assert(xe, *c < ARRAY_SIZE(bo->placements)); - if (bo_flags & XE_BO_CREATE_SYSTEM_BIT) { + xe_assert(xe, *c < ARRAY_SIZE(bo->placements)); + bo->placements[*c] = (struct ttm_place) { .mem_type = XE_PL_TT, }; @@ -145,6 +145,8 @@ static void add_vram(struct xe_device *xe, struct xe_bo *bo, struct xe_mem_region *vram; u64 io_size; + xe_assert(xe, *c < ARRAY_SIZE(bo->placements)); + vram = to_xe_ttm_vram_mgr(ttm_manager_type(&xe->ttm, mem_type))->vram; xe_assert(xe, vram && vram->usable_size); io_size = vram->io_size; @@ -175,8 +177,6 @@ static void add_vram(struct xe_device *xe, struct xe_bo *bo, static void try_add_vram(struct xe_device *xe, struct xe_bo *bo, u32 bo_flags, u32 *c) { - xe_assert(xe, *c < ARRAY_SIZE(bo->placements)); - if (bo->props.preferred_gt == XE_GT1) { if (bo_flags & XE_BO_CREATE_VRAM1_BIT) add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c); @@ -193,9 +193,9 @@ static void try_add_vram(struct xe_device *xe, struct xe_bo *bo, static void try_add_stolen(struct xe_device *xe, struct xe_bo *bo, u32 bo_flags, u32 *c) { - xe_assert(xe, *c < ARRAY_SIZE(bo->placements)); - if (bo_flags & XE_BO_CREATE_STOLEN_BIT) { + xe_assert(xe, *c < ARRAY_SIZE(bo->placements)); + bo->placements[*c] = (struct ttm_place) { .mem_type = XE_PL_STOLEN, .flags = bo_flags & (XE_BO_CREATE_PINNED_BIT | @@ -442,7 +442,7 @@ static int xe_ttm_io_mem_reserve(struct ttm_device *bdev, if (vram->mapping && mem->placement & TTM_PL_FLAG_CONTIGUOUS) - mem->bus.addr = (u8 *)vram->mapping + + mem->bus.addr = (u8 __force *)vram->mapping + mem->bus.offset; mem->bus.offset += vram->io_start; @@ -734,7 +734,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, /* Create a new VMAP once kernel BO back in VRAM */ if (!ret && resource_is_vram(new_mem)) { struct xe_mem_region *vram = res_to_mem_region(new_mem); - void *new_addr = vram->mapping + + void __iomem *new_addr = vram->mapping + (new_mem->start << PAGE_SHIFT); if (XE_WARN_ON(new_mem->start == XE_BO_INVALID_OFFSET)) { diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index d9ae77fe7382..b8d8da546670 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -484,7 +484,7 @@ int xe_device_probe(struct xe_device *xe) err = xe_device_set_has_flat_ccs(xe); if (err) - return err; + goto err_irq_shutdown; err = xe_mmio_probe_vram(xe); if (err) diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index c45ef17b3473..5dc9127a2029 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -97,7 +97,7 @@ struct xe_mem_region { */ resource_size_t actual_physical_size; /** @mapping: pointer to VRAM mappable space */ - void *__iomem mapping; + void __iomem *mapping; }; /** @@ -146,7 +146,7 @@ struct xe_tile { size_t size; /** @regs: pointer to tile's MMIO space (starting with registers) */ - void *regs; + void __iomem *regs; } mmio; /** @@ -159,7 +159,7 @@ struct xe_tile { size_t size; /** @regs: pointer to tile's additional MMIO-extension space */ - void *regs; + void __iomem *regs; } mmio_ext; /** @mem: memory management info for tile */ @@ -301,7 +301,7 @@ struct xe_device { /** @size: size of MMIO space for device */ size_t size; /** @regs: pointer to MMIO space for device */ - void *regs; + void __iomem *regs; } mmio; /** @mem: memory info for device */ diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index d30c0d0689bc..b853feed9ccc 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -115,7 +115,7 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) struct xe_sched_job *job; struct dma_fence *rebind_fence; struct xe_vm *vm; - bool write_locked; + bool write_locked, skip_retry = false; ktime_t end = 0; int err = 0; @@ -227,7 +227,8 @@ retry: } if (xe_exec_queue_is_lr(q) && xe_exec_queue_ring_full(q)) { - err = -EWOULDBLOCK; + err = -EWOULDBLOCK; /* Aliased to -EAGAIN */ + skip_retry = true; goto err_exec; } @@ -337,7 +338,7 @@ err_unlock_list: up_write(&vm->lock); else up_read(&vm->lock); - if (err == -EAGAIN) + if (err == -EAGAIN && !skip_retry) goto retry; err_syncs: for (i = 0; i < num_syncs; i++) diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 44fe8097b7cd..bcfc4127c7c5 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -67,6 +67,11 @@ static struct xe_exec_queue *__xe_exec_queue_create(struct xe_device *xe, q->sched_props.timeslice_us = hwe->eclass->sched_props.timeslice_us; q->sched_props.preempt_timeout_us = hwe->eclass->sched_props.preempt_timeout_us; + if (q->flags & EXEC_QUEUE_FLAG_KERNEL && + q->flags & EXEC_QUEUE_FLAG_HIGH_PRIORITY) + q->sched_props.priority = XE_EXEC_QUEUE_PRIORITY_KERNEL; + else + q->sched_props.priority = XE_EXEC_QUEUE_PRIORITY_NORMAL; if (xe_exec_queue_is_parallel(q)) { q->parallel.composite_fence_ctx = dma_fence_context_alloc(1); diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index 3d7e704ec3d9..8d4b7feb8c30 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -52,8 +52,6 @@ struct xe_exec_queue { struct xe_vm *vm; /** @class: class of this exec queue */ enum xe_engine_class class; - /** @priority: priority of this exec queue */ - enum xe_exec_queue_priority priority; /** * @logical_mask: logical mask of where job submitted to exec queue can run */ @@ -84,6 +82,8 @@ struct xe_exec_queue { #define EXEC_QUEUE_FLAG_VM BIT(4) /* child of VM queue for multi-tile VM jobs */ #define EXEC_QUEUE_FLAG_BIND_ENGINE_CHILD BIT(5) +/* kernel exec_queue only, set priority to highest level */ +#define EXEC_QUEUE_FLAG_HIGH_PRIORITY BIT(6) /** * @flags: flags for this exec queue, should statically setup aside from ban @@ -142,6 +142,8 @@ struct xe_exec_queue { u32 timeslice_us; /** @preempt_timeout_us: preemption timeout in micro-seconds */ u32 preempt_timeout_us; + /** @priority: priority of this exec queue */ + enum xe_exec_queue_priority priority; } sched_props; /** @compute: compute exec queue state */ diff --git a/drivers/gpu/drm/xe/xe_gt_freq.c b/drivers/gpu/drm/xe/xe_gt_freq.c index 3adfa6686e7c..e5b0f4ecdbe8 100644 --- a/drivers/gpu/drm/xe/xe_gt_freq.c +++ b/drivers/gpu/drm/xe/xe_gt_freq.c @@ -196,6 +196,9 @@ void xe_gt_freq_init(struct xe_gt *gt) struct xe_device *xe = gt_to_xe(gt); int err; + if (xe->info.skip_guc_pc) + return; + gt->freq = kobject_create_and_add("freq0", gt->sysfs); if (!gt->freq) { drm_warn(&xe->drm, "failed to add freq0 directory to %s\n", diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c index 482cb0df9f15..0a61390c64a7 100644 --- a/drivers/gpu/drm/xe/xe_guc.c +++ b/drivers/gpu/drm/xe/xe_guc.c @@ -60,7 +60,12 @@ static u32 guc_ctl_debug_flags(struct xe_guc *guc) static u32 guc_ctl_feature_flags(struct xe_guc *guc) { - return GUC_CTL_ENABLE_SLPC; + u32 flags = 0; + + if (!guc_to_xe(guc)->info.skip_guc_pc) + flags |= GUC_CTL_ENABLE_SLPC; + + return flags; } static u32 guc_ctl_log_params_flags(struct xe_guc *guc) diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index 21ac68e3246f..54ffcfcdd41f 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -421,7 +421,7 @@ static void init_policies(struct xe_guc *guc, struct xe_exec_queue *q) { struct exec_queue_policy policy; struct xe_device *xe = guc_to_xe(guc); - enum xe_exec_queue_priority prio = q->priority; + enum xe_exec_queue_priority prio = q->sched_props.priority; u32 timeslice_us = q->sched_props.timeslice_us; u32 preempt_timeout_us = q->sched_props.preempt_timeout_us; @@ -1231,7 +1231,6 @@ static int guc_exec_queue_init(struct xe_exec_queue *q) err = xe_sched_entity_init(&ge->entity, sched); if (err) goto err_sched; - q->priority = XE_EXEC_QUEUE_PRIORITY_NORMAL; if (xe_exec_queue_is_lr(q)) INIT_WORK(&q->guc->lr_tdr, xe_guc_exec_queue_lr_cleanup); @@ -1301,15 +1300,15 @@ static int guc_exec_queue_set_priority(struct xe_exec_queue *q, { struct xe_sched_msg *msg; - if (q->priority == priority || exec_queue_killed_or_banned(q)) + if (q->sched_props.priority == priority || exec_queue_killed_or_banned(q)) return 0; msg = kmalloc(sizeof(*msg), GFP_KERNEL); if (!msg) return -ENOMEM; + q->sched_props.priority = priority; guc_exec_queue_add_msg(q, msg, SET_SCHED_PROPS); - q->priority = priority; return 0; } diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index adf1dab5eba2..e05e9e7282b6 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -62,6 +62,8 @@ struct xe_migrate { * out of the pt_bo. */ struct drm_suballoc_manager vm_update_sa; + /** @min_chunk_size: For dgfx, Minimum chunk size */ + u64 min_chunk_size; }; #define MAX_PREEMPTDISABLE_TRANSFER SZ_8M /* Around 1ms. */ @@ -344,7 +346,8 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile) m->q = xe_exec_queue_create(xe, vm, logical_mask, 1, hwe, EXEC_QUEUE_FLAG_KERNEL | - EXEC_QUEUE_FLAG_PERMANENT); + EXEC_QUEUE_FLAG_PERMANENT | + EXEC_QUEUE_FLAG_HIGH_PRIORITY); } else { m->q = xe_exec_queue_create_class(xe, primary_gt, vm, XE_ENGINE_CLASS_COPY, @@ -355,8 +358,6 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile) xe_vm_close_and_put(vm); return ERR_CAST(m->q); } - if (xe->info.has_usm) - m->q->priority = XE_EXEC_QUEUE_PRIORITY_KERNEL; mutex_init(&m->job_mutex); @@ -364,6 +365,19 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile) if (err) return ERR_PTR(err); + if (IS_DGFX(xe)) { + if (xe_device_has_flat_ccs(xe)) + /* min chunk size corresponds to 4K of CCS Metadata */ + m->min_chunk_size = SZ_4K * SZ_64K / + xe_device_ccs_bytes(xe, SZ_64K); + else + /* Somewhat arbitrary to avoid a huge amount of blits */ + m->min_chunk_size = SZ_64K; + m->min_chunk_size = roundup_pow_of_two(m->min_chunk_size); + drm_dbg(&xe->drm, "Migrate min chunk size is 0x%08llx\n", + (unsigned long long)m->min_chunk_size); + } + return m; } @@ -375,16 +389,35 @@ static u64 max_mem_transfer_per_pass(struct xe_device *xe) return MAX_PREEMPTDISABLE_TRANSFER; } -static u64 xe_migrate_res_sizes(struct xe_device *xe, struct xe_res_cursor *cur) +static u64 xe_migrate_res_sizes(struct xe_migrate *m, struct xe_res_cursor *cur) { - /* - * For VRAM we use identity mapped pages so we are limited to current - * cursor size. For system we program the pages ourselves so we have no - * such limitation. - */ - return min_t(u64, max_mem_transfer_per_pass(xe), - mem_type_is_vram(cur->mem_type) ? cur->size : - cur->remaining); + struct xe_device *xe = tile_to_xe(m->tile); + u64 size = min_t(u64, max_mem_transfer_per_pass(xe), cur->remaining); + + if (mem_type_is_vram(cur->mem_type)) { + /* + * VRAM we want to blit in chunks with sizes aligned to + * min_chunk_size in order for the offset to CCS metadata to be + * page-aligned. If it's the last chunk it may be smaller. + * + * Another constraint is that we need to limit the blit to + * the VRAM block size, unless size is smaller than + * min_chunk_size. + */ + u64 chunk = max_t(u64, cur->size, m->min_chunk_size); + + size = min_t(u64, size, chunk); + if (size > m->min_chunk_size) + size = round_down(size, m->min_chunk_size); + } + + return size; +} + +static bool xe_migrate_allow_identity(u64 size, const struct xe_res_cursor *cur) +{ + /* If the chunk is not fragmented, allow identity map. */ + return cur->size >= size; } static u32 pte_update_size(struct xe_migrate *m, @@ -397,7 +430,12 @@ static u32 pte_update_size(struct xe_migrate *m, u32 cmds = 0; *L0_pt = pt_ofs; - if (!is_vram) { + if (is_vram && xe_migrate_allow_identity(*L0, cur)) { + /* Offset into identity map. */ + *L0_ofs = xe_migrate_vram_ofs(tile_to_xe(m->tile), + cur->start + vram_region_gpu_offset(res)); + cmds += cmd_size; + } else { /* Clip L0 to available size */ u64 size = min(*L0, (u64)avail_pts * SZ_2M); u64 num_4k_pages = DIV_ROUND_UP(size, XE_PAGE_SIZE); @@ -413,11 +451,6 @@ static u32 pte_update_size(struct xe_migrate *m, /* Each chunk has a single blit command */ cmds += cmd_size; - } else { - /* Offset into identity map. */ - *L0_ofs = xe_migrate_vram_ofs(tile_to_xe(m->tile), - cur->start + vram_region_gpu_offset(res)); - cmds += cmd_size; } return cmds; @@ -427,10 +460,10 @@ static void emit_pte(struct xe_migrate *m, struct xe_bb *bb, u32 at_pt, bool is_vram, bool is_comp_pte, struct xe_res_cursor *cur, - u32 size, struct xe_bo *bo) + u32 size, struct ttm_resource *res) { struct xe_device *xe = tile_to_xe(m->tile); - + struct xe_vm *vm = m->q->vm; u16 pat_index; u32 ptes; u64 ofs = at_pt * XE_PAGE_SIZE; @@ -443,13 +476,6 @@ static void emit_pte(struct xe_migrate *m, else pat_index = xe->pat.idx[XE_CACHE_WB]; - /* - * FIXME: Emitting VRAM PTEs to L0 PTs is forbidden. Currently - * we're only emitting VRAM PTEs during sanity tests, so when - * that's moved to a Kunit test, we should condition VRAM PTEs - * on running tests. - */ - ptes = DIV_ROUND_UP(size, XE_PAGE_SIZE); while (ptes) { @@ -469,20 +495,22 @@ static void emit_pte(struct xe_migrate *m, addr = xe_res_dma(cur) & PAGE_MASK; if (is_vram) { - /* Is this a 64K PTE entry? */ - if ((m->q->vm->flags & XE_VM_FLAG_64K) && - !(cur_ofs & (16 * 8 - 1))) { - xe_tile_assert(m->tile, IS_ALIGNED(addr, SZ_64K)); + if (vm->flags & XE_VM_FLAG_64K) { + u64 va = cur_ofs * XE_PAGE_SIZE / 8; + + xe_assert(xe, (va & (SZ_64K - 1)) == + (addr & (SZ_64K - 1))); + flags |= XE_PTE_PS64; } - addr += vram_region_gpu_offset(bo->ttm.resource); + addr += vram_region_gpu_offset(res); devmem = true; } - addr = m->q->vm->pt_ops->pte_encode_addr(m->tile->xe, - addr, pat_index, - 0, devmem, flags); + addr = vm->pt_ops->pte_encode_addr(m->tile->xe, + addr, pat_index, + 0, devmem, flags); bb->cs[bb->len++] = lower_32_bits(addr); bb->cs[bb->len++] = upper_32_bits(addr); @@ -694,8 +722,8 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m, bool usm = xe->info.has_usm; u32 avail_pts = max_mem_transfer_per_pass(xe) / LEVEL0_PAGE_TABLE_ENCODE_SIZE; - src_L0 = xe_migrate_res_sizes(xe, &src_it); - dst_L0 = xe_migrate_res_sizes(xe, &dst_it); + src_L0 = xe_migrate_res_sizes(m, &src_it); + dst_L0 = xe_migrate_res_sizes(m, &dst_it); drm_dbg(&xe->drm, "Pass %u, sizes: %llu & %llu\n", pass++, src_L0, dst_L0); @@ -716,6 +744,7 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m, &ccs_ofs, &ccs_pt, 0, 2 * avail_pts, avail_pts); + xe_assert(xe, IS_ALIGNED(ccs_it.start, PAGE_SIZE)); } /* Add copy commands size here */ @@ -728,20 +757,20 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m, goto err_sync; } - if (!src_is_vram) - emit_pte(m, bb, src_L0_pt, src_is_vram, true, &src_it, src_L0, - src_bo); - else + if (src_is_vram && xe_migrate_allow_identity(src_L0, &src_it)) xe_res_next(&src_it, src_L0); - - if (!dst_is_vram) - emit_pte(m, bb, dst_L0_pt, dst_is_vram, true, &dst_it, src_L0, - dst_bo); else + emit_pte(m, bb, src_L0_pt, src_is_vram, true, &src_it, src_L0, + src); + + if (dst_is_vram && xe_migrate_allow_identity(src_L0, &dst_it)) xe_res_next(&dst_it, src_L0); + else + emit_pte(m, bb, dst_L0_pt, dst_is_vram, true, &dst_it, src_L0, + dst); if (copy_system_ccs) - emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src_bo); + emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src); bb->cs[bb->len++] = MI_BATCH_BUFFER_END; update_idx = bb->len; @@ -950,7 +979,7 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m, bool usm = xe->info.has_usm; u32 avail_pts = max_mem_transfer_per_pass(xe) / LEVEL0_PAGE_TABLE_ENCODE_SIZE; - clear_L0 = xe_migrate_res_sizes(xe, &src_it); + clear_L0 = xe_migrate_res_sizes(m, &src_it); drm_dbg(&xe->drm, "Pass %u, size: %llu\n", pass++, clear_L0); @@ -977,12 +1006,12 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m, size -= clear_L0; /* Preemption is enabled again by the ring ops. */ - if (!clear_vram) { - emit_pte(m, bb, clear_L0_pt, clear_vram, true, &src_it, clear_L0, - bo); - } else { + if (clear_vram && xe_migrate_allow_identity(clear_L0, &src_it)) xe_res_next(&src_it, clear_L0); - } + else + emit_pte(m, bb, clear_L0_pt, clear_vram, true, &src_it, clear_L0, + dst); + bb->cs[bb->len++] = MI_BATCH_BUFFER_END; update_idx = bb->len; diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c index f660cfb79f50..c8c5d74b6e90 100644 --- a/drivers/gpu/drm/xe/xe_mmio.c +++ b/drivers/gpu/drm/xe/xe_mmio.c @@ -303,7 +303,7 @@ void xe_mmio_probe_tiles(struct xe_device *xe) u8 id, tile_count = xe->info.tile_count; struct xe_gt *gt = xe_root_mmio_gt(xe); struct xe_tile *tile; - void *regs; + void __iomem *regs; u32 mtcfg; if (tile_count == 1) diff --git a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c index d2b00d0bf1e2..e5d7d5e2bec1 100644 --- a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c +++ b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c @@ -31,7 +31,7 @@ struct xe_ttm_stolen_mgr { /* GPU base offset */ resource_size_t stolen_base; - void *__iomem mapping; + void __iomem *mapping; }; static inline struct xe_ttm_stolen_mgr * @@ -275,7 +275,7 @@ static int __xe_ttm_stolen_io_mem_reserve_bar2(struct xe_device *xe, drm_WARN_ON(&xe->drm, !(mem->placement & TTM_PL_FLAG_CONTIGUOUS)); if (mem->placement & TTM_PL_FLAG_CONTIGUOUS && mgr->mapping) - mem->bus.addr = (u8 *)mgr->mapping + mem->bus.offset; + mem->bus.addr = (u8 __force *)mgr->mapping + mem->bus.offset; mem->bus.offset += mgr->io_base; mem->bus.is_iomem = true; diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 0cfe7289b97e..10b6995fbf29 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -335,13 +335,13 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q) down_write(&vm->lock); err = drm_gpuvm_exec_lock(&vm_exec); if (err) - return err; + goto out_up_write; pfence = xe_preempt_fence_create(q, q->compute.context, ++q->compute.seqno); if (!pfence) { err = -ENOMEM; - goto out_unlock; + goto out_fini; } list_add(&q->compute.link, &vm->preempt.exec_queues); @@ -364,8 +364,9 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q) up_read(&vm->userptr.notifier_lock); -out_unlock: +out_fini: drm_exec_fini(exec); +out_up_write: up_write(&vm->lock); return err; @@ -2063,9 +2064,11 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo, if (err) return ERR_PTR(err); - vm_bo = drm_gpuvm_bo_find(&vm->gpuvm, obj); - if (!vm_bo) - break; + vm_bo = drm_gpuvm_bo_obtain(&vm->gpuvm, obj); + if (IS_ERR(vm_bo)) { + xe_bo_unlock(bo); + return ERR_CAST(vm_bo); + } ops = drm_gpuvm_bo_unmap_ops_create(vm_bo); drm_gpuvm_bo_put(vm_bo); diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 4372f5d146ab..0285a74363b3 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -488,7 +488,7 @@ void hv_setup_dma_ops(struct device *dev, bool coherent) * Hyper-V does not offer a vIOMMU in the guest * VM, so pass 0/NULL for the IOMMU settings */ - arch_setup_dma_ops(dev, 0, 0, NULL, coherent); + arch_setup_dma_ops(dev, 0, 0, coherent); } EXPORT_SYMBOL_GPL(hv_setup_dma_ops); diff --git a/drivers/hwmon/npcm750-pwm-fan.c b/drivers/hwmon/npcm750-pwm-fan.c index d9733da8ea34..904816abb7c4 100644 --- a/drivers/hwmon/npcm750-pwm-fan.c +++ b/drivers/hwmon/npcm750-pwm-fan.c @@ -195,6 +195,7 @@ struct npcm7xx_cooling_device { struct npcm7xx_pwm_fan_data { void __iomem *pwm_base; void __iomem *fan_base; + int pwm_modules; unsigned long pwm_clk_freq; unsigned long fan_clk_freq; struct clk *pwm_clk; @@ -710,7 +711,7 @@ static u32 npcm7xx_pwm_init(struct npcm7xx_pwm_fan_data *data) /* Setting PWM Prescale Register value register to both modules */ prescale_val |= (prescale_val << NPCM7XX_PWM_PRESCALE_SHIFT_CH01); - for (m = 0; m < NPCM7XX_PWM_MAX_MODULES ; m++) { + for (m = 0; m < data->pwm_modules; m++) { iowrite32(prescale_val, NPCM7XX_PWM_REG_PR(data->pwm_base, m)); iowrite32(NPCM7XX_PWM_PRESCALE2_DEFAULT, NPCM7XX_PWM_REG_CSR(data->pwm_base, m)); @@ -946,6 +947,8 @@ static int npcm7xx_pwm_fan_probe(struct platform_device *pdev) if (!data->info) return -EINVAL; + data->pwm_modules = data->info->pwm_max_channel / NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE; + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pwm"); if (!res) { dev_err(dev, "pwm resource not found\n"); @@ -983,7 +986,7 @@ static int npcm7xx_pwm_fan_probe(struct platform_device *pdev) output_freq = npcm7xx_pwm_init(data); npcm7xx_fan_init(data); - for (cnt = 0; cnt < NPCM7XX_PWM_MAX_MODULES ; cnt++) + for (cnt = 0; cnt < data->pwm_modules; cnt++) mutex_init(&data->pwm_lock[cnt]); for (i = 0; i < NPCM7XX_FAN_MAX_MODULE; i++) { diff --git a/drivers/i2c/busses/i2c-ali1535.c b/drivers/i2c/busses/i2c-ali1535.c index ee83c4581bce..461eb23f9d47 100644 --- a/drivers/i2c/busses/i2c-ali1535.c +++ b/drivers/i2c/busses/i2c-ali1535.c @@ -477,7 +477,7 @@ static const struct i2c_algorithm smbus_algorithm = { static struct i2c_adapter ali1535_adapter = { .owner = THIS_MODULE, - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON, .algo = &smbus_algorithm, }; diff --git a/drivers/i2c/busses/i2c-ali1563.c b/drivers/i2c/busses/i2c-ali1563.c index 55a9e93fbfeb..307fb0666ecb 100644 --- a/drivers/i2c/busses/i2c-ali1563.c +++ b/drivers/i2c/busses/i2c-ali1563.c @@ -390,7 +390,7 @@ static const struct i2c_algorithm ali1563_algorithm = { static struct i2c_adapter ali1563_adapter = { .owner = THIS_MODULE, - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON, .algo = &ali1563_algorithm, }; diff --git a/drivers/i2c/busses/i2c-ali15x3.c b/drivers/i2c/busses/i2c-ali15x3.c index 0231c5be6354..d2fa30deb054 100644 --- a/drivers/i2c/busses/i2c-ali15x3.c +++ b/drivers/i2c/busses/i2c-ali15x3.c @@ -461,7 +461,7 @@ static const struct i2c_algorithm smbus_algorithm = { static struct i2c_adapter ali15x3_adapter = { .owner = THIS_MODULE, - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON, .algo = &smbus_algorithm, }; diff --git a/drivers/i2c/busses/i2c-amd756.c b/drivers/i2c/busses/i2c-amd756.c index ef1307a258e9..208310db906d 100644 --- a/drivers/i2c/busses/i2c-amd756.c +++ b/drivers/i2c/busses/i2c-amd756.c @@ -285,7 +285,7 @@ static const struct i2c_algorithm smbus_algorithm = { struct i2c_adapter amd756_smbus = { .owner = THIS_MODULE, - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON, .algo = &smbus_algorithm, }; diff --git a/drivers/i2c/busses/i2c-amd8111.c b/drivers/i2c/busses/i2c-amd8111.c index 1ed7e945bb6d..42a9b1221065 100644 --- a/drivers/i2c/busses/i2c-amd8111.c +++ b/drivers/i2c/busses/i2c-amd8111.c @@ -449,7 +449,7 @@ static int amd8111_probe(struct pci_dev *dev, const struct pci_device_id *id) smbus->adapter.owner = THIS_MODULE; snprintf(smbus->adapter.name, sizeof(smbus->adapter.name), "SMBus2 AMD8111 adapter at %04x", smbus->base); - smbus->adapter.class = I2C_CLASS_HWMON | I2C_CLASS_SPD; + smbus->adapter.class = I2C_CLASS_HWMON; smbus->adapter.algo = &smbus_algorithm; smbus->adapter.algo_data = smbus; diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c index 9a664abf734d..4404b4aac676 100644 --- a/drivers/i2c/busses/i2c-cpm.c +++ b/drivers/i2c/busses/i2c-cpm.c @@ -658,7 +658,7 @@ static int cpm_i2c_probe(struct platform_device *ofdev) /* register new adapter to i2c module... */ data = of_get_property(ofdev->dev.of_node, "linux,i2c-index", &len); - cpm->adap.nr = (data && len == 4) ? be32_to_cpup(data) : -1; + cpm->adap.nr = (data && len == 4) ? *data : -1; result = i2c_add_numbered_adapter(&cpm->adap); if (result < 0) diff --git a/drivers/i2c/busses/i2c-elektor.c b/drivers/i2c/busses/i2c-elektor.c index b0f50dce9d0f..cfe8665cacd2 100644 --- a/drivers/i2c/busses/i2c-elektor.c +++ b/drivers/i2c/busses/i2c-elektor.c @@ -188,7 +188,7 @@ static struct i2c_algo_pcf_data pcf_isa_data = { static struct i2c_adapter pcf_isa_ops = { .owner = THIS_MODULE, - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON, .algo_data = &pcf_isa_data, .name = "i2c-elektor", }; diff --git a/drivers/i2c/busses/i2c-gpio.c b/drivers/i2c/busses/i2c-gpio.c index fb35a75fe0e3..4f1411b1a775 100644 --- a/drivers/i2c/busses/i2c-gpio.c +++ b/drivers/i2c/busses/i2c-gpio.c @@ -25,7 +25,6 @@ struct i2c_gpio_private_data { struct i2c_algo_bit_data bit_data; struct i2c_gpio_platform_data pdata; #ifdef CONFIG_I2C_GPIO_FAULT_INJECTOR - struct dentry *debug_dir; /* these must be protected by bus lock */ struct completion scl_irq_completion; u64 scl_irq_data; @@ -72,7 +71,6 @@ static int i2c_gpio_getscl(void *data) } #ifdef CONFIG_I2C_GPIO_FAULT_INJECTOR -static struct dentry *i2c_gpio_debug_dir; #define setsda(bd, val) ((bd)->setsda((bd)->data, val)) #define setscl(bd, val) ((bd)->setscl((bd)->data, val)) @@ -258,41 +256,23 @@ static void i2c_gpio_fault_injector_init(struct platform_device *pdev) { struct i2c_gpio_private_data *priv = platform_get_drvdata(pdev); - /* - * If there will be a debugfs-dir per i2c adapter somewhen, put the - * 'fault-injector' dir there. Until then, we have a global dir with - * all adapters as subdirs. - */ - if (!i2c_gpio_debug_dir) - i2c_gpio_debug_dir = debugfs_create_dir("i2c-fault-injector", NULL); - - priv->debug_dir = debugfs_create_dir(pdev->name, i2c_gpio_debug_dir); - init_completion(&priv->scl_irq_completion); - debugfs_create_file_unsafe("incomplete_address_phase", 0200, priv->debug_dir, + debugfs_create_file_unsafe("incomplete_address_phase", 0200, priv->adap.debugfs, priv, &fops_incomplete_addr_phase); - debugfs_create_file_unsafe("incomplete_write_byte", 0200, priv->debug_dir, + debugfs_create_file_unsafe("incomplete_write_byte", 0200, priv->adap.debugfs, priv, &fops_incomplete_write_byte); if (priv->bit_data.getscl) { - debugfs_create_file_unsafe("inject_panic", 0200, priv->debug_dir, + debugfs_create_file_unsafe("inject_panic", 0200, priv->adap.debugfs, priv, &fops_inject_panic); - debugfs_create_file_unsafe("lose_arbitration", 0200, priv->debug_dir, + debugfs_create_file_unsafe("lose_arbitration", 0200, priv->adap.debugfs, priv, &fops_lose_arbitration); } - debugfs_create_file_unsafe("scl", 0600, priv->debug_dir, priv, &fops_scl); - debugfs_create_file_unsafe("sda", 0600, priv->debug_dir, priv, &fops_sda); -} - -static void i2c_gpio_fault_injector_exit(struct platform_device *pdev) -{ - struct i2c_gpio_private_data *priv = platform_get_drvdata(pdev); - - debugfs_remove_recursive(priv->debug_dir); + debugfs_create_file_unsafe("scl", 0600, priv->adap.debugfs, priv, &fops_scl); + debugfs_create_file_unsafe("sda", 0600, priv->adap.debugfs, priv, &fops_sda); } #else static inline void i2c_gpio_fault_injector_init(struct platform_device *pdev) {} -static inline void i2c_gpio_fault_injector_exit(struct platform_device *pdev) {} #endif /* CONFIG_I2C_GPIO_FAULT_INJECTOR*/ /* Get i2c-gpio properties from DT or ACPI table */ @@ -444,7 +424,7 @@ static int i2c_gpio_probe(struct platform_device *pdev) snprintf(adap->name, sizeof(adap->name), "i2c-gpio%d", pdev->id); adap->algo_data = bit_data; - adap->class = I2C_CLASS_HWMON | I2C_CLASS_SPD; + adap->class = I2C_CLASS_HWMON; adap->dev.parent = dev; device_set_node(&adap->dev, fwnode); @@ -475,8 +455,6 @@ static void i2c_gpio_remove(struct platform_device *pdev) struct i2c_gpio_private_data *priv; struct i2c_adapter *adap; - i2c_gpio_fault_injector_exit(pdev); - priv = platform_get_drvdata(pdev); adap = &priv->adap; diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 070999139c6d..3932e8d96a17 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1230,8 +1230,10 @@ static const struct { * Additional individual entries were added after verification. */ { "Latitude 5480", 0x29 }, + { "Precision 3540", 0x29 }, { "Vostro V131", 0x1d }, { "Vostro 5568", 0x29 }, + { "XPS 15 7590", 0x29 }, }; static void register_dell_lis3lv02d_i2c_device(struct i801_priv *priv) diff --git a/drivers/i2c/busses/i2c-ibm_iic.c b/drivers/i2c/busses/i2c-ibm_iic.c index 408820319ec4..7fb87b78923e 100644 --- a/drivers/i2c/busses/i2c-ibm_iic.c +++ b/drivers/i2c/busses/i2c-ibm_iic.c @@ -739,7 +739,7 @@ static int iic_probe(struct platform_device *ofdev) adap->dev.of_node = of_node_get(np); strscpy(adap->name, "IBM IIC", sizeof(adap->name)); i2c_set_adapdata(adap, dev); - adap->class = I2C_CLASS_HWMON | I2C_CLASS_SPD; + adap->class = I2C_CLASS_HWMON; adap->algo = &iic_algo; adap->timeout = HZ; diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 1775a79aeba2..88a053987403 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -1401,7 +1401,7 @@ static int i2c_imx_init_recovery_info(struct imx_i2c_struct *i2c_imx, PINCTRL_STATE_DEFAULT); i2c_imx->pinctrl_pins_gpio = pinctrl_lookup_state(i2c_imx->pinctrl, "gpio"); - rinfo->sda_gpiod = devm_gpiod_get(&pdev->dev, "sda", GPIOD_IN); + rinfo->sda_gpiod = devm_gpiod_get_optional(&pdev->dev, "sda", GPIOD_IN); rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN); if (PTR_ERR(rinfo->sda_gpiod) == -EPROBE_DEFER || diff --git a/drivers/i2c/busses/i2c-iop3xx.c b/drivers/i2c/busses/i2c-iop3xx.c index f2f7ebeeaecb..2e5f0165c3d3 100644 --- a/drivers/i2c/busses/i2c-iop3xx.c +++ b/drivers/i2c/busses/i2c-iop3xx.c @@ -478,7 +478,7 @@ iop3xx_i2c_probe(struct platform_device *pdev) memcpy(new_adapter->name, pdev->name, strlen(pdev->name)); new_adapter->owner = THIS_MODULE; - new_adapter->class = I2C_CLASS_HWMON | I2C_CLASS_SPD; + new_adapter->class = I2C_CLASS_HWMON; new_adapter->dev.parent = &pdev->dev; new_adapter->dev.of_node = pdev->dev.of_node; new_adapter->nr = pdev->id; diff --git a/drivers/i2c/busses/i2c-isch.c b/drivers/i2c/busses/i2c-isch.c index 1dc1ceaa4443..416a9968ed28 100644 --- a/drivers/i2c/busses/i2c-isch.c +++ b/drivers/i2c/busses/i2c-isch.c @@ -249,7 +249,7 @@ static const struct i2c_algorithm smbus_algorithm = { static struct i2c_adapter sch_adapter = { .owner = THIS_MODULE, - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON, .algo = &smbus_algorithm, }; diff --git a/drivers/i2c/busses/i2c-kempld.c b/drivers/i2c/busses/i2c-kempld.c index e01d75308288..c3a529a73b5b 100644 --- a/drivers/i2c/busses/i2c-kempld.c +++ b/drivers/i2c/busses/i2c-kempld.c @@ -283,8 +283,7 @@ static const struct i2c_algorithm kempld_i2c_algorithm = { static const struct i2c_adapter kempld_i2c_adapter = { .owner = THIS_MODULE, .name = "i2c-kempld", - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD | - I2C_CLASS_DEPRECATED, + .class = I2C_CLASS_HWMON | I2C_CLASS_DEPRECATED, .algo = &kempld_i2c_algorithm, }; diff --git a/drivers/i2c/busses/i2c-mlxcpld.c b/drivers/i2c/busses/i2c-mlxcpld.c index 6fec64ea67fb..099291a0411d 100644 --- a/drivers/i2c/busses/i2c-mlxcpld.c +++ b/drivers/i2c/busses/i2c-mlxcpld.c @@ -477,7 +477,7 @@ static const struct i2c_adapter_quirks mlxcpld_i2c_quirks_ext2 = { static struct i2c_adapter mlxcpld_i2c_adapter = { .owner = THIS_MODULE, .name = "i2c-mlxcpld", - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON, .algo = &mlxcpld_i2c_algo, .quirks = &mlxcpld_i2c_quirks, .retries = MLXCPLD_I2C_RETR_NUM, diff --git a/drivers/i2c/busses/i2c-nforce2.c b/drivers/i2c/busses/i2c-nforce2.c index 38d203d93eee..fab662e6bc08 100644 --- a/drivers/i2c/busses/i2c-nforce2.c +++ b/drivers/i2c/busses/i2c-nforce2.c @@ -349,7 +349,7 @@ static int nforce2_probe_smb(struct pci_dev *dev, int bar, int alt_reg, return -EBUSY; } smbus->adapter.owner = THIS_MODULE; - smbus->adapter.class = I2C_CLASS_HWMON | I2C_CLASS_SPD; + smbus->adapter.class = I2C_CLASS_HWMON; smbus->adapter.algo = &smbus_algorithm; smbus->adapter.algo_data = smbus; smbus->adapter.dev.parent = &dev->dev; diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c index ae4bae63ad4f..54181b3f1919 100644 --- a/drivers/i2c/busses/i2c-npcm7xx.c +++ b/drivers/i2c/busses/i2c-npcm7xx.c @@ -326,7 +326,6 @@ struct npcm_i2c { u8 slv_rd_buf[MAX_I2C_HW_FIFO_SIZE]; u8 slv_wr_buf[MAX_I2C_HW_FIFO_SIZE]; #endif - struct dentry *debugfs; /* debugfs device directory */ u64 ber_cnt; u64 rec_succ_cnt; u64 rec_fail_cnt; @@ -2250,27 +2249,15 @@ static const struct i2c_algorithm npcm_i2c_algo = { #endif }; -/* i2c debugfs directory: used to keep health monitor of i2c devices */ -static struct dentry *npcm_i2c_debugfs_dir; - static void npcm_i2c_init_debugfs(struct platform_device *pdev, struct npcm_i2c *bus) { - struct dentry *d; - - if (!npcm_i2c_debugfs_dir) - return; - d = debugfs_create_dir(dev_name(&pdev->dev), npcm_i2c_debugfs_dir); - if (IS_ERR_OR_NULL(d)) - return; - debugfs_create_u64("ber_cnt", 0444, d, &bus->ber_cnt); - debugfs_create_u64("nack_cnt", 0444, d, &bus->nack_cnt); - debugfs_create_u64("rec_succ_cnt", 0444, d, &bus->rec_succ_cnt); - debugfs_create_u64("rec_fail_cnt", 0444, d, &bus->rec_fail_cnt); - debugfs_create_u64("timeout_cnt", 0444, d, &bus->timeout_cnt); - debugfs_create_u64("tx_complete_cnt", 0444, d, &bus->tx_complete_cnt); - - bus->debugfs = d; + debugfs_create_u64("ber_cnt", 0444, bus->adap.debugfs, &bus->ber_cnt); + debugfs_create_u64("nack_cnt", 0444, bus->adap.debugfs, &bus->nack_cnt); + debugfs_create_u64("rec_succ_cnt", 0444, bus->adap.debugfs, &bus->rec_succ_cnt); + debugfs_create_u64("rec_fail_cnt", 0444, bus->adap.debugfs, &bus->rec_fail_cnt); + debugfs_create_u64("timeout_cnt", 0444, bus->adap.debugfs, &bus->timeout_cnt); + debugfs_create_u64("tx_complete_cnt", 0444, bus->adap.debugfs, &bus->tx_complete_cnt); } static int npcm_i2c_probe_bus(struct platform_device *pdev) @@ -2362,7 +2349,6 @@ static void npcm_i2c_remove_bus(struct platform_device *pdev) unsigned long lock_flags; struct npcm_i2c *bus = platform_get_drvdata(pdev); - debugfs_remove_recursive(bus->debugfs); spin_lock_irqsave(&bus->lock, lock_flags); npcm_i2c_disable(bus); spin_unlock_irqrestore(&bus->lock, lock_flags); @@ -2385,28 +2371,7 @@ static struct platform_driver npcm_i2c_bus_driver = { } }; -static int __init npcm_i2c_init(void) -{ - int ret; - - npcm_i2c_debugfs_dir = debugfs_create_dir("npcm_i2c", NULL); - - ret = platform_driver_register(&npcm_i2c_bus_driver); - if (ret) { - debugfs_remove_recursive(npcm_i2c_debugfs_dir); - return ret; - } - - return 0; -} -module_init(npcm_i2c_init); - -static void __exit npcm_i2c_exit(void) -{ - platform_driver_unregister(&npcm_i2c_bus_driver); - debugfs_remove_recursive(npcm_i2c_debugfs_dir); -} -module_exit(npcm_i2c_exit); +module_platform_driver(npcm_i2c_bus_driver); MODULE_AUTHOR("Avi Fishman <avi.fishman@gmail.com>"); MODULE_AUTHOR("Tali Perry <tali.perry@nuvoton.com>"); diff --git a/drivers/i2c/busses/i2c-pasemi-pci.c b/drivers/i2c/busses/i2c-pasemi-pci.c index cfc89e04eb94..77f90c7436ed 100644 --- a/drivers/i2c/busses/i2c-pasemi-pci.c +++ b/drivers/i2c/busses/i2c-pasemi-pci.c @@ -56,7 +56,7 @@ static int pasemi_smb_pci_probe(struct pci_dev *dev, if (!smbus->ioaddr) return -EBUSY; - smbus->adapter.class = I2C_CLASS_HWMON | I2C_CLASS_SPD; + smbus->adapter.class = I2C_CLASS_HWMON; error = pasemi_i2c_common_probe(smbus); if (error) return error; diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c index 809fbd014cd6..6a0392172b2f 100644 --- a/drivers/i2c/busses/i2c-piix4.c +++ b/drivers/i2c/busses/i2c-piix4.c @@ -943,7 +943,7 @@ static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba, } adap->owner = THIS_MODULE; - adap->class = I2C_CLASS_HWMON | I2C_CLASS_SPD; + adap->class = I2C_CLASS_HWMON; adap->algo = sb800_main ? &piix4_smbus_algorithm_sb800 : &smbus_algorithm; diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index 829ac053bbb7..828aa2ea0fe4 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -89,6 +89,7 @@ #define TMDMAE BIT(0) /* DMA Master Transmitted Enable */ /* ICCCR2 */ +#define FMPE BIT(7) /* Fast Mode Plus Enable */ #define CDFD BIT(2) /* CDF Disable */ #define HLSE BIT(1) /* HIGH/LOW Separate Control Enable */ #define SME BIT(0) /* SCL Mask Enable */ @@ -122,16 +123,18 @@ #define ID_NACK BIT(4) #define ID_EPROTO BIT(5) /* persistent flags */ +#define ID_P_FMPLUS BIT(27) #define ID_P_NOT_ATOMIC BIT(28) #define ID_P_HOST_NOTIFY BIT(29) #define ID_P_NO_RXDMA BIT(30) /* HW forbids RXDMA sometimes */ #define ID_P_PM_BLOCKED BIT(31) -#define ID_P_MASK GENMASK(31, 28) +#define ID_P_MASK GENMASK(31, 27) enum rcar_i2c_type { I2C_RCAR_GEN1, I2C_RCAR_GEN2, I2C_RCAR_GEN3, + I2C_RCAR_GEN4, }; struct rcar_i2c_priv { @@ -148,6 +151,7 @@ struct rcar_i2c_priv { u32 icccr; u16 schd; u16 scld; + u8 smd; u8 recovery_icmcr; /* protected by adapter lock */ enum rcar_i2c_type devtype; struct i2c_client *slave; @@ -239,9 +243,14 @@ static void rcar_i2c_init(struct rcar_i2c_priv *priv) if (priv->devtype < I2C_RCAR_GEN3) { rcar_i2c_write(priv, ICCCR, priv->icccr); } else { - rcar_i2c_write(priv, ICCCR2, CDFD | HLSE | SME); + u32 icccr2 = CDFD | HLSE | SME; + + if (priv->flags & ID_P_FMPLUS) + icccr2 |= FMPE; + + rcar_i2c_write(priv, ICCCR2, icccr2); rcar_i2c_write(priv, ICCCR, priv->icccr); - rcar_i2c_write(priv, ICMPR, RCAR_DEFAULT_SMD); + rcar_i2c_write(priv, ICMPR, priv->smd); rcar_i2c_write(priv, ICHPR, priv->schd); rcar_i2c_write(priv, ICLPR, priv->scld); rcar_i2c_write(priv, ICFBSCR, TCYC17); @@ -278,6 +287,7 @@ static int rcar_i2c_clock_calculate(struct rcar_i2c_priv *priv) /* Fall back to previously used values if not supplied */ i2c_parse_fw_timings(dev, &t, false); + priv->smd = RCAR_DEFAULT_SMD; /* * calculate SCL clock @@ -303,6 +313,11 @@ static int rcar_i2c_clock_calculate(struct rcar_i2c_priv *priv) if (cdf >= 1U << cdf_width) goto err_no_val; + if (t.bus_freq_hz > I2C_MAX_FAST_MODE_FREQ && priv->devtype >= I2C_RCAR_GEN4) + priv->flags |= ID_P_FMPLUS; + else + priv->flags &= ~ID_P_FMPLUS; + /* On Gen3+, we use cdf only for the filters, not as a SCL divider */ ick = rate / (priv->devtype < I2C_RCAR_GEN3 ? (cdf + 1) : 1); @@ -344,30 +359,30 @@ static int rcar_i2c_clock_calculate(struct rcar_i2c_priv *priv) * x as a base value for the SCLD/SCHD ratio: * * SCL = clkp / (8 + 2 * SMD + SCLD + SCHD + F[(ticf + tr + intd) * clkp]) - * SCL = clkp / (8 + 2 * RCAR_DEFAULT_SMD + RCAR_SCLD_RATIO * x + * SCL = clkp / (8 + 2 * SMD + RCAR_SCLD_RATIO * x * + RCAR_SCHD_RATIO * x + F[...]) * * with: sum_ratio = RCAR_SCLD_RATIO + RCAR_SCHD_RATIO - * and: smd = RCAR_DEFAULT_SMD * * SCL = clkp / (8 + 2 * smd + sum_ratio * x + F[...]) * 8 + 2 * smd + sum_ratio * x + F[...] = clkp / SCL * x = ((clkp / SCL) - 8 - 2 * smd - F[...]) / sum_ratio */ x = DIV_ROUND_UP(rate, t.bus_freq_hz ?: 1); - x = DIV_ROUND_UP(x - 8 - 2 * RCAR_DEFAULT_SMD - round, sum_ratio); - scl = rate / (8 + 2 * RCAR_DEFAULT_SMD + sum_ratio * x + round); + x = DIV_ROUND_UP(x - 8 - 2 * priv->smd - round, sum_ratio); + scl = rate / (8 + 2 * priv->smd + sum_ratio * x + round); - /* Bail out if values don't fit into 16 bit or SMD became too large */ - if (x * RCAR_SCLD_RATIO > 0xffff || RCAR_DEFAULT_SMD > x * RCAR_SCHD_RATIO) + if (x == 0 || x * RCAR_SCLD_RATIO > 0xffff) goto err_no_val; priv->icccr = cdf; priv->schd = RCAR_SCHD_RATIO * x; priv->scld = RCAR_SCLD_RATIO * x; + if (priv->smd >= priv->schd) + priv->smd = priv->schd - 1; - dev_dbg(dev, "clk %u/%u(%lu), round %u, CDF: %u SCHD %u SCLD %u\n", - scl, t.bus_freq_hz, rate, round, cdf, priv->schd, priv->scld); + dev_dbg(dev, "clk %u/%u(%lu), round %u, CDF: %u SCHD %u SCLD %u SMD %u\n", + scl, t.bus_freq_hz, rate, round, cdf, priv->schd, priv->scld, priv->smd); } return 0; @@ -431,8 +446,8 @@ static void rcar_i2c_cleanup_dma(struct rcar_i2c_priv *priv, bool terminate) dma_unmap_single(chan->device->dev, sg_dma_address(&priv->sg), sg_dma_len(&priv->sg), priv->dma_direction); - /* Gen3 can only do one RXDMA per transfer and we just completed it */ - if (priv->devtype == I2C_RCAR_GEN3 && + /* Gen3+ can only do one RXDMA per transfer and we just completed it */ + if (priv->devtype >= I2C_RCAR_GEN3 && priv->dma_direction == DMA_FROM_DEVICE) priv->flags |= ID_P_NO_RXDMA; @@ -886,8 +901,8 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap, if (ret < 0) goto out; - /* Gen3 needs a reset before allowing RXDMA once */ - if (priv->devtype == I2C_RCAR_GEN3) { + /* Gen3+ needs a reset. That also allows RXDMA once */ + if (priv->devtype >= I2C_RCAR_GEN3) { priv->flags &= ~ID_P_NO_RXDMA; ret = rcar_i2c_do_reset(priv); if (ret) @@ -1072,10 +1087,12 @@ static const struct of_device_id rcar_i2c_dt_ids[] = { { .compatible = "renesas,i2c-r8a7794", .data = (void *)I2C_RCAR_GEN2 }, { .compatible = "renesas,i2c-r8a7795", .data = (void *)I2C_RCAR_GEN3 }, { .compatible = "renesas,i2c-r8a7796", .data = (void *)I2C_RCAR_GEN3 }, + /* S4 has no FM+ bit */ + { .compatible = "renesas,i2c-r8a779f0", .data = (void *)I2C_RCAR_GEN3 }, { .compatible = "renesas,rcar-gen1-i2c", .data = (void *)I2C_RCAR_GEN1 }, { .compatible = "renesas,rcar-gen2-i2c", .data = (void *)I2C_RCAR_GEN2 }, { .compatible = "renesas,rcar-gen3-i2c", .data = (void *)I2C_RCAR_GEN3 }, - { .compatible = "renesas,rcar-gen4-i2c", .data = (void *)I2C_RCAR_GEN3 }, + { .compatible = "renesas,rcar-gen4-i2c", .data = (void *)I2C_RCAR_GEN4 }, {}, }; MODULE_DEVICE_TABLE(of, rcar_i2c_dt_ids); @@ -1151,7 +1168,7 @@ static int rcar_i2c_probe(struct platform_device *pdev) if (of_property_read_bool(dev->of_node, "smbus")) priv->flags |= ID_P_HOST_NOTIFY; - if (priv->devtype == I2C_RCAR_GEN3) { + if (priv->devtype >= I2C_RCAR_GEN3) { priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL); if (IS_ERR(priv->rstc)) { ret = PTR_ERR(priv->rstc); diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c index 4362db7c5789..086fdf262e7b 100644 --- a/drivers/i2c/busses/i2c-rk3x.c +++ b/drivers/i2c/busses/i2c-rk3x.c @@ -1295,8 +1295,12 @@ static int rk3x_i2c_probe(struct platform_device *pdev) return -EINVAL; } - /* 27+i: write mask, 11+i: value */ - value = BIT(27 + bus_nr) | BIT(11 + bus_nr); + /* rv1126 i2c2 uses non-sequential write mask 20, value 4 */ + if (i2c->soc_data == &rv1126_soc_data && bus_nr == 2) + value = BIT(20) | BIT(4); + else + /* 27+i: write mask, 11+i: value */ + value = BIT(27 + bus_nr) | BIT(11 + bus_nr); ret = regmap_write(grf, i2c->soc_data->grf_offset, value); if (ret != 0) { diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c index c56886af724e..275f7c42165c 100644 --- a/drivers/i2c/busses/i2c-s3c2410.c +++ b/drivers/i2c/busses/i2c-s3c2410.c @@ -76,6 +76,7 @@ #define QUIRK_HDMIPHY (1 << 1) #define QUIRK_NO_GPIO (1 << 2) #define QUIRK_POLL (1 << 3) +#define QUIRK_ATOMIC (1 << 4) /* Max time to wait for bus to become idle after a xfer (in us) */ #define S3C2410_IDLE_TIMEOUT 5000 @@ -174,7 +175,7 @@ static inline void s3c24xx_i2c_master_complete(struct s3c24xx_i2c *i2c, int ret) if (ret) i2c->msg_idx = ret; - if (!(i2c->quirks & QUIRK_POLL)) + if (!(i2c->quirks & (QUIRK_POLL | QUIRK_ATOMIC))) wake_up(&i2c->wait); } @@ -216,8 +217,17 @@ static bool is_ack(struct s3c24xx_i2c *i2c) int tries; for (tries = 50; tries; --tries) { - if (readl(i2c->regs + S3C2410_IICCON) - & S3C2410_IICCON_IRQPEND) { + unsigned long tmp = readl(i2c->regs + S3C2410_IICCON); + + if (!(tmp & S3C2410_IICCON_ACKEN)) { + /* + * Wait a bit for the bus to stabilize, + * delay estimated experimentally. + */ + usleep_range(100, 200); + return true; + } + if (tmp & S3C2410_IICCON_IRQPEND) { if (!(readl(i2c->regs + S3C2410_IICSTAT) & S3C2410_IICSTAT_LASTBIT)) return true; @@ -270,16 +280,6 @@ static void s3c24xx_i2c_message_start(struct s3c24xx_i2c *i2c, stat |= S3C2410_IICSTAT_START; writel(stat, i2c->regs + S3C2410_IICSTAT); - - if (i2c->quirks & QUIRK_POLL) { - while ((i2c->msg_num != 0) && is_ack(i2c)) { - i2c_s3c_irq_nextbyte(i2c, stat); - stat = readl(i2c->regs + S3C2410_IICSTAT); - - if (stat & S3C2410_IICSTAT_ARBITR) - dev_err(i2c->dev, "deal with arbitration loss\n"); - } - } } static inline void s3c24xx_i2c_stop(struct s3c24xx_i2c *i2c, int ret) @@ -685,7 +685,7 @@ static void s3c24xx_i2c_wait_idle(struct s3c24xx_i2c *i2c) static int s3c24xx_i2c_doxfer(struct s3c24xx_i2c *i2c, struct i2c_msg *msgs, int num) { - unsigned long timeout; + unsigned long timeout = 0; int ret; ret = s3c24xx_i2c_set_master(i2c); @@ -704,17 +704,20 @@ static int s3c24xx_i2c_doxfer(struct s3c24xx_i2c *i2c, s3c24xx_i2c_enable_irq(i2c); s3c24xx_i2c_message_start(i2c, msgs); - if (i2c->quirks & QUIRK_POLL) { - ret = i2c->msg_idx; + if (i2c->quirks & (QUIRK_POLL | QUIRK_ATOMIC)) { + while ((i2c->msg_num != 0) && is_ack(i2c)) { + unsigned long stat = readl(i2c->regs + S3C2410_IICSTAT); - if (ret != num) - dev_dbg(i2c->dev, "incomplete xfer (%d)\n", ret); + i2c_s3c_irq_nextbyte(i2c, stat); - goto out; + stat = readl(i2c->regs + S3C2410_IICSTAT); + if (stat & S3C2410_IICSTAT_ARBITR) + dev_err(i2c->dev, "deal with arbitration loss\n"); + } + } else { + timeout = wait_event_timeout(i2c->wait, i2c->msg_num == 0, HZ * 5); } - timeout = wait_event_timeout(i2c->wait, i2c->msg_num == 0, HZ * 5); - ret = i2c->msg_idx; /* @@ -773,6 +776,21 @@ static int s3c24xx_i2c_xfer(struct i2c_adapter *adap, return -EREMOTEIO; } +static int s3c24xx_i2c_xfer_atomic(struct i2c_adapter *adap, + struct i2c_msg *msgs, int num) +{ + struct s3c24xx_i2c *i2c = (struct s3c24xx_i2c *)adap->algo_data; + int ret; + + disable_irq(i2c->irq); + i2c->quirks |= QUIRK_ATOMIC; + ret = s3c24xx_i2c_xfer(adap, msgs, num); + i2c->quirks &= ~QUIRK_ATOMIC; + enable_irq(i2c->irq); + + return ret; +} + /* declare our i2c functionality */ static u32 s3c24xx_i2c_func(struct i2c_adapter *adap) { @@ -783,6 +801,7 @@ static u32 s3c24xx_i2c_func(struct i2c_adapter *adap) /* i2c bus registration info */ static const struct i2c_algorithm s3c24xx_i2c_algorithm = { .master_xfer = s3c24xx_i2c_xfer, + .master_xfer_atomic = s3c24xx_i2c_xfer_atomic, .functionality = s3c24xx_i2c_func, }; diff --git a/drivers/i2c/busses/i2c-scmi.c b/drivers/i2c/busses/i2c-scmi.c index 421735acfa14..d7af8e0d7599 100644 --- a/drivers/i2c/busses/i2c-scmi.c +++ b/drivers/i2c/busses/i2c-scmi.c @@ -385,7 +385,7 @@ static int smbus_cmi_probe(struct platform_device *device) smbus_cmi->adapter.owner = THIS_MODULE; smbus_cmi->adapter.algo = &acpi_smbus_cmi_algorithm; smbus_cmi->adapter.algo_data = smbus_cmi; - smbus_cmi->adapter.class = I2C_CLASS_HWMON | I2C_CLASS_SPD; + smbus_cmi->adapter.class = I2C_CLASS_HWMON; smbus_cmi->adapter.dev.parent = &device->dev; ret = i2c_add_adapter(&smbus_cmi->adapter); diff --git a/drivers/i2c/busses/i2c-sh7760.c b/drivers/i2c/busses/i2c-sh7760.c index 1ad2a26156d1..8a043f5fca1e 100644 --- a/drivers/i2c/busses/i2c-sh7760.c +++ b/drivers/i2c/busses/i2c-sh7760.c @@ -477,7 +477,7 @@ static int sh7760_i2c_probe(struct platform_device *pdev) id->adap.nr = pdev->id; id->adap.algo = &sh7760_i2c_algo; - id->adap.class = I2C_CLASS_HWMON | I2C_CLASS_SPD; + id->adap.class = I2C_CLASS_HWMON; id->adap.retries = 3; id->adap.algo_data = id; id->adap.dev.parent = &pdev->dev; diff --git a/drivers/i2c/busses/i2c-sibyte.c b/drivers/i2c/busses/i2c-sibyte.c index 8f71f01cb169..49f8f4f1b0f0 100644 --- a/drivers/i2c/busses/i2c-sibyte.c +++ b/drivers/i2c/busses/i2c-sibyte.c @@ -142,7 +142,7 @@ static struct i2c_algo_sibyte_data sibyte_board_data[2] = { static struct i2c_adapter sibyte_board_adapter[2] = { { .owner = THIS_MODULE, - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON, .algo = NULL, .algo_data = &sibyte_board_data[0], .nr = 0, @@ -150,7 +150,7 @@ static struct i2c_adapter sibyte_board_adapter[2] = { }, { .owner = THIS_MODULE, - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON, .algo = NULL, .algo_data = &sibyte_board_data[1], .nr = 1, diff --git a/drivers/i2c/busses/i2c-sis5595.c b/drivers/i2c/busses/i2c-sis5595.c index 486f1e9dfb74..32476dc10ad6 100644 --- a/drivers/i2c/busses/i2c-sis5595.c +++ b/drivers/i2c/busses/i2c-sis5595.c @@ -353,7 +353,7 @@ static const struct i2c_algorithm smbus_algorithm = { static struct i2c_adapter sis5595_adapter = { .owner = THIS_MODULE, - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON, .algo = &smbus_algorithm, }; diff --git a/drivers/i2c/busses/i2c-sis630.c b/drivers/i2c/busses/i2c-sis630.c index 87d56250d78a..3505cf29cedd 100644 --- a/drivers/i2c/busses/i2c-sis630.c +++ b/drivers/i2c/busses/i2c-sis630.c @@ -493,7 +493,7 @@ static const struct i2c_algorithm smbus_algorithm = { static struct i2c_adapter sis630_adapter = { .owner = THIS_MODULE, - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON, .algo = &smbus_algorithm, .retries = 3 }; diff --git a/drivers/i2c/busses/i2c-sis96x.c b/drivers/i2c/busses/i2c-sis96x.c index cde8003985a5..77529dda6fcd 100644 --- a/drivers/i2c/busses/i2c-sis96x.c +++ b/drivers/i2c/busses/i2c-sis96x.c @@ -228,7 +228,7 @@ static const struct i2c_algorithm smbus_algorithm = { static struct i2c_adapter sis96x_adapter = { .owner = THIS_MODULE, - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON, .algo = &smbus_algorithm, }; diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c index 983509936727..01210452216b 100644 --- a/drivers/i2c/busses/i2c-stm32f7.c +++ b/drivers/i2c/busses/i2c-stm32f7.c @@ -50,6 +50,7 @@ #define STM32F7_I2C_TXDR 0x28 /* STM32F7 I2C control 1 */ +#define STM32_I2C_CR1_FMP BIT(24) #define STM32F7_I2C_CR1_PECEN BIT(23) #define STM32F7_I2C_CR1_ALERTEN BIT(22) #define STM32F7_I2C_CR1_SMBHEN BIT(20) @@ -226,6 +227,8 @@ struct stm32f7_i2c_spec { * @rise_time: Rise time (ns) * @fall_time: Fall time (ns) * @fmp_clr_offset: Fast Mode Plus clear register offset from set register + * @single_it_line: Only a single IT line is used for both events/errors + * @fmp_cr1_bit: Fast Mode Plus control is done via a bit in CR1 */ struct stm32f7_i2c_setup { u32 speed_freq; @@ -233,6 +236,8 @@ struct stm32f7_i2c_setup { u32 rise_time; u32 fall_time; u32 fmp_clr_offset; + bool single_it_line; + bool fmp_cr1_bit; }; /** @@ -418,6 +423,13 @@ static const struct stm32f7_i2c_setup stm32mp13_setup = { .fmp_clr_offset = 0x4, }; +static const struct stm32f7_i2c_setup stm32mp25_setup = { + .rise_time = STM32F7_I2C_RISE_TIME_DEFAULT, + .fall_time = STM32F7_I2C_FALL_TIME_DEFAULT, + .single_it_line = true, + .fmp_cr1_bit = true, +}; + static inline void stm32f7_i2c_set_bits(void __iomem *reg, u32 mask) { writel_relaxed(readl_relaxed(reg) | mask, reg); @@ -1419,15 +1431,13 @@ static bool stm32f7_i2c_is_slave_busy(struct stm32f7_i2c_dev *i2c_dev) return i == busy; } -static irqreturn_t stm32f7_i2c_slave_isr_event(struct stm32f7_i2c_dev *i2c_dev) +static irqreturn_t stm32f7_i2c_slave_isr_event(struct stm32f7_i2c_dev *i2c_dev, u32 status) { void __iomem *base = i2c_dev->base; - u32 cr2, status, mask; + u32 cr2, mask; u8 val; int ret; - status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR); - /* Slave transmitter mode */ if (status & STM32F7_I2C_ISR_TXIS) { i2c_slave_event(i2c_dev->slave_running, @@ -1494,23 +1504,81 @@ static irqreturn_t stm32f7_i2c_slave_isr_event(struct stm32f7_i2c_dev *i2c_dev) return IRQ_HANDLED; } -static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data) +static irqreturn_t stm32f7_i2c_handle_isr_errs(struct stm32f7_i2c_dev *i2c_dev, u32 status) { - struct stm32f7_i2c_dev *i2c_dev = data; struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg; - struct stm32_i2c_dma *dma = i2c_dev->dma; + u16 addr = f7_msg->addr; void __iomem *base = i2c_dev->base; - u32 status, mask; - int ret = IRQ_HANDLED; + struct device *dev = i2c_dev->dev; + struct stm32_i2c_dma *dma = i2c_dev->dma; - /* Check if the interrupt if for a slave device */ - if (!i2c_dev->master_mode) { - ret = stm32f7_i2c_slave_isr_event(i2c_dev); - return ret; + /* Bus error */ + if (status & STM32F7_I2C_ISR_BERR) { + dev_err(dev, "Bus error accessing addr 0x%x\n", addr); + writel_relaxed(STM32F7_I2C_ICR_BERRCF, base + STM32F7_I2C_ICR); + stm32f7_i2c_release_bus(&i2c_dev->adap); + f7_msg->result = -EIO; + } + + /* Arbitration loss */ + if (status & STM32F7_I2C_ISR_ARLO) { + dev_dbg(dev, "Arbitration loss accessing addr 0x%x\n", addr); + writel_relaxed(STM32F7_I2C_ICR_ARLOCF, base + STM32F7_I2C_ICR); + f7_msg->result = -EAGAIN; + } + + if (status & STM32F7_I2C_ISR_PECERR) { + dev_err(dev, "PEC error in reception accessing addr 0x%x\n", addr); + writel_relaxed(STM32F7_I2C_ICR_PECCF, base + STM32F7_I2C_ICR); + f7_msg->result = -EINVAL; } + if (status & STM32F7_I2C_ISR_ALERT) { + dev_dbg(dev, "SMBus alert received\n"); + writel_relaxed(STM32F7_I2C_ICR_ALERTCF, base + STM32F7_I2C_ICR); + i2c_handle_smbus_alert(i2c_dev->alert->ara); + return IRQ_HANDLED; + } + + if (!i2c_dev->slave_running) { + u32 mask; + /* Disable interrupts */ + if (stm32f7_i2c_is_slave_registered(i2c_dev)) + mask = STM32F7_I2C_XFER_IRQ_MASK; + else + mask = STM32F7_I2C_ALL_IRQ_MASK; + stm32f7_i2c_disable_irq(i2c_dev, mask); + } + + /* Disable dma */ + if (i2c_dev->use_dma) { + stm32f7_i2c_disable_dma_req(i2c_dev); + dmaengine_terminate_async(dma->chan_using); + } + + i2c_dev->master_mode = false; + complete(&i2c_dev->complete); + + return IRQ_HANDLED; +} + +#define STM32F7_ERR_EVENTS (STM32F7_I2C_ISR_BERR | STM32F7_I2C_ISR_ARLO |\ + STM32F7_I2C_ISR_PECERR | STM32F7_I2C_ISR_ALERT) +static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data) +{ + struct stm32f7_i2c_dev *i2c_dev = data; + u32 status; + status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR); + /* + * Check if the interrupt is for a slave device or related + * to errors flags (in case of single it line mode) + */ + if (!i2c_dev->master_mode || + (i2c_dev->setup.single_it_line && (status & STM32F7_ERR_EVENTS))) + return IRQ_WAKE_THREAD; + /* Tx empty */ if (status & STM32F7_I2C_ISR_TXIS) stm32f7_i2c_write_tx_data(i2c_dev); @@ -1519,6 +1587,33 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data) if (status & STM32F7_I2C_ISR_RXNE) stm32f7_i2c_read_rx_data(i2c_dev); + /* Wake up the thread if other flags are raised */ + if (status & + (STM32F7_I2C_ISR_NACKF | STM32F7_I2C_ISR_STOPF | + STM32F7_I2C_ISR_TC | STM32F7_I2C_ISR_TCR)) + return IRQ_WAKE_THREAD; + + return IRQ_HANDLED; +} + +static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data) +{ + struct stm32f7_i2c_dev *i2c_dev = data; + struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg; + struct stm32_i2c_dma *dma = i2c_dev->dma; + void __iomem *base = i2c_dev->base; + u32 status, mask; + int ret; + + status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR); + + if (!i2c_dev->master_mode) + return stm32f7_i2c_slave_isr_event(i2c_dev, status); + + /* Handle errors in case of this handler is used for events/errors */ + if (i2c_dev->setup.single_it_line && (status & STM32F7_ERR_EVENTS)) + return stm32f7_i2c_handle_isr_errs(i2c_dev, status); + /* NACK received */ if (status & STM32F7_I2C_ISR_NACKF) { dev_dbg(i2c_dev->dev, "<%s>: Receive NACK (addr %x)\n", @@ -1531,33 +1626,28 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data) f7_msg->result = -ENXIO; } - /* STOP detection flag */ - if (status & STM32F7_I2C_ISR_STOPF) { - /* Disable interrupts */ - if (stm32f7_i2c_is_slave_registered(i2c_dev)) - mask = STM32F7_I2C_XFER_IRQ_MASK; + if (status & STM32F7_I2C_ISR_TCR) { + if (f7_msg->smbus) + stm32f7_i2c_smbus_reload(i2c_dev); else - mask = STM32F7_I2C_ALL_IRQ_MASK; - stm32f7_i2c_disable_irq(i2c_dev, mask); - - /* Clear STOP flag */ - writel_relaxed(STM32F7_I2C_ICR_STOPCF, base + STM32F7_I2C_ICR); - - if (i2c_dev->use_dma && !f7_msg->result) { - ret = IRQ_WAKE_THREAD; - } else { - i2c_dev->master_mode = false; - complete(&i2c_dev->complete); - } + stm32f7_i2c_reload(i2c_dev); } /* Transfer complete */ if (status & STM32F7_I2C_ISR_TC) { + /* Wait for dma transfer completion before sending next message */ + if (i2c_dev->use_dma && !f7_msg->result) { + ret = wait_for_completion_timeout(&i2c_dev->dma->dma_complete, HZ); + if (!ret) { + dev_dbg(i2c_dev->dev, "<%s>: Timed out\n", __func__); + stm32f7_i2c_disable_dma_req(i2c_dev); + dmaengine_terminate_async(dma->chan_using); + f7_msg->result = -ETIMEDOUT; + } + } if (f7_msg->stop) { mask = STM32F7_I2C_CR2_STOP; stm32f7_i2c_set_bits(base + STM32F7_I2C_CR2, mask); - } else if (i2c_dev->use_dma && !f7_msg->result) { - ret = IRQ_WAKE_THREAD; } else if (f7_msg->smbus) { stm32f7_i2c_smbus_rep_start(i2c_dev); } else { @@ -1567,47 +1657,18 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data) } } - if (status & STM32F7_I2C_ISR_TCR) { - if (f7_msg->smbus) - stm32f7_i2c_smbus_reload(i2c_dev); + /* STOP detection flag */ + if (status & STM32F7_I2C_ISR_STOPF) { + /* Disable interrupts */ + if (stm32f7_i2c_is_slave_registered(i2c_dev)) + mask = STM32F7_I2C_XFER_IRQ_MASK; else - stm32f7_i2c_reload(i2c_dev); - } - - return ret; -} - -static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data) -{ - struct stm32f7_i2c_dev *i2c_dev = data; - struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg; - struct stm32_i2c_dma *dma = i2c_dev->dma; - u32 status; - int ret; - - /* - * Wait for dma transfer completion before sending next message or - * notity the end of xfer to the client - */ - ret = wait_for_completion_timeout(&i2c_dev->dma->dma_complete, HZ); - if (!ret) { - dev_dbg(i2c_dev->dev, "<%s>: Timed out\n", __func__); - stm32f7_i2c_disable_dma_req(i2c_dev); - dmaengine_terminate_async(dma->chan_using); - f7_msg->result = -ETIMEDOUT; - } + mask = STM32F7_I2C_ALL_IRQ_MASK; + stm32f7_i2c_disable_irq(i2c_dev, mask); - status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR); + /* Clear STOP flag */ + writel_relaxed(STM32F7_I2C_ICR_STOPCF, base + STM32F7_I2C_ICR); - if (status & STM32F7_I2C_ISR_TC) { - if (f7_msg->smbus) { - stm32f7_i2c_smbus_rep_start(i2c_dev); - } else { - i2c_dev->msg_id++; - i2c_dev->msg++; - stm32f7_i2c_xfer_msg(i2c_dev, i2c_dev->msg); - } - } else { i2c_dev->master_mode = false; complete(&i2c_dev->complete); } @@ -1615,68 +1676,14 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data) return IRQ_HANDLED; } -static irqreturn_t stm32f7_i2c_isr_error(int irq, void *data) +static irqreturn_t stm32f7_i2c_isr_error_thread(int irq, void *data) { struct stm32f7_i2c_dev *i2c_dev = data; - struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg; - void __iomem *base = i2c_dev->base; - struct device *dev = i2c_dev->dev; - struct stm32_i2c_dma *dma = i2c_dev->dma; u32 status; status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR); - /* Bus error */ - if (status & STM32F7_I2C_ISR_BERR) { - dev_err(dev, "<%s>: Bus error accessing addr 0x%x\n", - __func__, f7_msg->addr); - writel_relaxed(STM32F7_I2C_ICR_BERRCF, base + STM32F7_I2C_ICR); - stm32f7_i2c_release_bus(&i2c_dev->adap); - f7_msg->result = -EIO; - } - - /* Arbitration loss */ - if (status & STM32F7_I2C_ISR_ARLO) { - dev_dbg(dev, "<%s>: Arbitration loss accessing addr 0x%x\n", - __func__, f7_msg->addr); - writel_relaxed(STM32F7_I2C_ICR_ARLOCF, base + STM32F7_I2C_ICR); - f7_msg->result = -EAGAIN; - } - - if (status & STM32F7_I2C_ISR_PECERR) { - dev_err(dev, "<%s>: PEC error in reception accessing addr 0x%x\n", - __func__, f7_msg->addr); - writel_relaxed(STM32F7_I2C_ICR_PECCF, base + STM32F7_I2C_ICR); - f7_msg->result = -EINVAL; - } - - if (status & STM32F7_I2C_ISR_ALERT) { - dev_dbg(dev, "<%s>: SMBus alert received\n", __func__); - writel_relaxed(STM32F7_I2C_ICR_ALERTCF, base + STM32F7_I2C_ICR); - i2c_handle_smbus_alert(i2c_dev->alert->ara); - return IRQ_HANDLED; - } - - if (!i2c_dev->slave_running) { - u32 mask; - /* Disable interrupts */ - if (stm32f7_i2c_is_slave_registered(i2c_dev)) - mask = STM32F7_I2C_XFER_IRQ_MASK; - else - mask = STM32F7_I2C_ALL_IRQ_MASK; - stm32f7_i2c_disable_irq(i2c_dev, mask); - } - - /* Disable dma */ - if (i2c_dev->use_dma) { - stm32f7_i2c_disable_dma_req(i2c_dev); - dmaengine_terminate_async(dma->chan_using); - } - - i2c_dev->master_mode = false; - complete(&i2c_dev->complete); - - return IRQ_HANDLED; + return stm32f7_i2c_handle_isr_errs(i2c_dev, status); } static int stm32f7_i2c_wait_polling(struct stm32f7_i2c_dev *i2c_dev) @@ -2012,23 +2019,27 @@ static int stm32f7_i2c_unreg_slave(struct i2c_client *slave) static int stm32f7_i2c_write_fm_plus_bits(struct stm32f7_i2c_dev *i2c_dev, bool enable) { - int ret; + int ret = 0; if (i2c_dev->bus_rate <= I2C_MAX_FAST_MODE_FREQ || - IS_ERR_OR_NULL(i2c_dev->regmap)) + (!i2c_dev->setup.fmp_cr1_bit && IS_ERR_OR_NULL(i2c_dev->regmap))) /* Optional */ return 0; - if (i2c_dev->fmp_sreg == i2c_dev->fmp_creg) - ret = regmap_update_bits(i2c_dev->regmap, - i2c_dev->fmp_sreg, - i2c_dev->fmp_mask, - enable ? i2c_dev->fmp_mask : 0); - else - ret = regmap_write(i2c_dev->regmap, - enable ? i2c_dev->fmp_sreg : - i2c_dev->fmp_creg, - i2c_dev->fmp_mask); + if (i2c_dev->setup.fmp_cr1_bit) { + if (enable) + stm32f7_i2c_set_bits(i2c_dev->base + STM32F7_I2C_CR1, STM32_I2C_CR1_FMP); + else + stm32f7_i2c_clr_bits(i2c_dev->base + STM32F7_I2C_CR1, STM32_I2C_CR1_FMP); + } else { + if (i2c_dev->fmp_sreg == i2c_dev->fmp_creg) + ret = regmap_update_bits(i2c_dev->regmap, i2c_dev->fmp_sreg, + i2c_dev->fmp_mask, enable ? i2c_dev->fmp_mask : 0); + else + ret = regmap_write(i2c_dev->regmap, + enable ? i2c_dev->fmp_sreg : i2c_dev->fmp_creg, + i2c_dev->fmp_mask); + } return ret; } @@ -2162,6 +2173,13 @@ static int stm32f7_i2c_probe(struct platform_device *pdev) if (!i2c_dev) return -ENOMEM; + setup = of_device_get_match_data(&pdev->dev); + if (!setup) { + dev_err(&pdev->dev, "Can't get device data\n"); + return -ENODEV; + } + i2c_dev->setup = *setup; + i2c_dev->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(i2c_dev->base)) return PTR_ERR(i2c_dev->base); @@ -2171,10 +2189,6 @@ static int stm32f7_i2c_probe(struct platform_device *pdev) if (irq_event < 0) return irq_event; - irq_error = platform_get_irq(pdev, 1); - if (irq_error < 0) - return irq_error; - i2c_dev->wakeup_src = of_property_read_bool(pdev->dev.of_node, "wakeup-source"); @@ -2199,26 +2213,22 @@ static int stm32f7_i2c_probe(struct platform_device *pdev) stm32f7_i2c_isr_event_thread, IRQF_ONESHOT, pdev->name, i2c_dev); - if (ret) { - dev_err(&pdev->dev, "Failed to request irq event %i\n", - irq_event); - return ret; - } - - ret = devm_request_irq(&pdev->dev, irq_error, stm32f7_i2c_isr_error, 0, - pdev->name, i2c_dev); - if (ret) { - dev_err(&pdev->dev, "Failed to request irq error %i\n", - irq_error); - return ret; - } - - setup = of_device_get_match_data(&pdev->dev); - if (!setup) { - dev_err(&pdev->dev, "Can't get device data\n"); - return -ENODEV; + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to request irq event\n"); + + if (!i2c_dev->setup.single_it_line) { + irq_error = platform_get_irq(pdev, 1); + if (irq_error < 0) + return irq_error; + + ret = devm_request_threaded_irq(&pdev->dev, irq_error, + NULL, + stm32f7_i2c_isr_error_thread, + IRQF_ONESHOT, + pdev->name, i2c_dev); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to request irq error\n"); } - i2c_dev->setup = *setup; ret = stm32f7_i2c_setup_timing(i2c_dev, &i2c_dev->setup); if (ret) @@ -2226,9 +2236,12 @@ static int stm32f7_i2c_probe(struct platform_device *pdev) /* Setup Fast mode plus if necessary */ if (i2c_dev->bus_rate > I2C_MAX_FAST_MODE_FREQ) { - ret = stm32f7_i2c_setup_fm_plus_bits(pdev, i2c_dev); - if (ret) - return ret; + if (!i2c_dev->setup.fmp_cr1_bit) { + ret = stm32f7_i2c_setup_fm_plus_bits(pdev, i2c_dev); + if (ret) + return ret; + } + ret = stm32f7_i2c_write_fm_plus_bits(i2c_dev, true); if (ret) return ret; @@ -2507,6 +2520,7 @@ static const struct of_device_id stm32f7_i2c_match[] = { { .compatible = "st,stm32f7-i2c", .data = &stm32f7_setup}, { .compatible = "st,stm32mp15-i2c", .data = &stm32mp15_setup}, { .compatible = "st,stm32mp13-i2c", .data = &stm32mp13_setup}, + { .compatible = "st,stm32mp25-i2c", .data = &stm32mp25_setup}, {}, }; MODULE_DEVICE_TABLE(of, stm32f7_i2c_match); diff --git a/drivers/i2c/busses/i2c-via.c b/drivers/i2c/busses/i2c-via.c index ad4f09c7f027..7ed29992a97f 100644 --- a/drivers/i2c/busses/i2c-via.c +++ b/drivers/i2c/busses/i2c-via.c @@ -70,7 +70,7 @@ static struct i2c_algo_bit_data bit_data = { static struct i2c_adapter vt586b_adapter = { .owner = THIS_MODULE, - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON, .name = "VIA i2c", .algo_data = &bit_data, }; diff --git a/drivers/i2c/busses/i2c-viapro.c b/drivers/i2c/busses/i2c-viapro.c index 970ccdcbb889..2cc7bba3b8bf 100644 --- a/drivers/i2c/busses/i2c-viapro.c +++ b/drivers/i2c/busses/i2c-viapro.c @@ -304,7 +304,7 @@ static const struct i2c_algorithm smbus_algorithm = { static struct i2c_adapter vt596_adapter = { .owner = THIS_MODULE, - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON, .algo = &smbus_algorithm, }; diff --git a/drivers/i2c/busses/i2c-wmt.c b/drivers/i2c/busses/i2c-wmt.c index 76118abc6e10..ec2a8da134e5 100644 --- a/drivers/i2c/busses/i2c-wmt.c +++ b/drivers/i2c/busses/i2c-wmt.c @@ -74,9 +74,6 @@ #define MCR_APB_96M 7 #define MCR_APB_166M 12 -#define I2C_MODE_STANDARD 0 -#define I2C_MODE_FAST 1 - #define WMT_I2C_TIMEOUT (msecs_to_jiffies(1000)) struct wmt_i2c_dev { @@ -85,7 +82,7 @@ struct wmt_i2c_dev { struct device *dev; void __iomem *base; struct clk *clk; - int mode; + u16 tcr; int irq; u16 cmd_status; }; @@ -109,6 +106,12 @@ static int wmt_i2c_wait_bus_not_busy(struct wmt_i2c_dev *i2c_dev) static int wmt_check_status(struct wmt_i2c_dev *i2c_dev) { int ret = 0; + unsigned long wait_result; + + wait_result = wait_for_completion_timeout(&i2c_dev->complete, + msecs_to_jiffies(500)); + if (!wait_result) + return -ETIMEDOUT; if (i2c_dev->cmd_status & ISR_NACK_ADDR) ret = -EIO; @@ -119,21 +122,13 @@ static int wmt_check_status(struct wmt_i2c_dev *i2c_dev) return ret; } -static int wmt_i2c_write(struct i2c_adapter *adap, struct i2c_msg *pmsg, +static int wmt_i2c_write(struct wmt_i2c_dev *i2c_dev, struct i2c_msg *pmsg, int last) { - struct wmt_i2c_dev *i2c_dev = i2c_get_adapdata(adap); - u16 val, tcr_val; + u16 val, tcr_val = i2c_dev->tcr; int ret; - unsigned long wait_result; int xfer_len = 0; - if (!(pmsg->flags & I2C_M_NOSTART)) { - ret = wmt_i2c_wait_bus_not_busy(i2c_dev); - if (ret < 0) - return ret; - } - if (pmsg->len == 0) { /* * We still need to run through the while (..) once, so @@ -148,20 +143,12 @@ static int wmt_i2c_write(struct i2c_adapter *adap, struct i2c_msg *pmsg, if (!(pmsg->flags & I2C_M_NOSTART)) { val = readw(i2c_dev->base + REG_CR); val &= ~CR_TX_END; - writew(val, i2c_dev->base + REG_CR); - - val = readw(i2c_dev->base + REG_CR); val |= CR_CPU_RDY; writew(val, i2c_dev->base + REG_CR); } reinit_completion(&i2c_dev->complete); - if (i2c_dev->mode == I2C_MODE_STANDARD) - tcr_val = TCR_STANDARD_MODE; - else - tcr_val = TCR_FAST_MODE; - tcr_val |= (TCR_MASTER_WRITE | (pmsg->addr & TCR_SLAVE_ADDR_MASK)); writew(tcr_val, i2c_dev->base + REG_TCR); @@ -173,12 +160,6 @@ static int wmt_i2c_write(struct i2c_adapter *adap, struct i2c_msg *pmsg, } while (xfer_len < pmsg->len) { - wait_result = wait_for_completion_timeout(&i2c_dev->complete, - msecs_to_jiffies(500)); - - if (wait_result == 0) - return -ETIMEDOUT; - ret = wmt_check_status(i2c_dev); if (ret) return ret; @@ -210,47 +191,24 @@ static int wmt_i2c_write(struct i2c_adapter *adap, struct i2c_msg *pmsg, return 0; } -static int wmt_i2c_read(struct i2c_adapter *adap, struct i2c_msg *pmsg, - int last) +static int wmt_i2c_read(struct wmt_i2c_dev *i2c_dev, struct i2c_msg *pmsg) { - struct wmt_i2c_dev *i2c_dev = i2c_get_adapdata(adap); - u16 val, tcr_val; + u16 val, tcr_val = i2c_dev->tcr; int ret; - unsigned long wait_result; u32 xfer_len = 0; - if (!(pmsg->flags & I2C_M_NOSTART)) { - ret = wmt_i2c_wait_bus_not_busy(i2c_dev); - if (ret < 0) - return ret; - } - - val = readw(i2c_dev->base + REG_CR); - val &= ~CR_TX_END; - writew(val, i2c_dev->base + REG_CR); - val = readw(i2c_dev->base + REG_CR); - val &= ~CR_TX_NEXT_NO_ACK; - writew(val, i2c_dev->base + REG_CR); + val &= ~(CR_TX_END | CR_TX_NEXT_NO_ACK); - if (!(pmsg->flags & I2C_M_NOSTART)) { - val = readw(i2c_dev->base + REG_CR); + if (!(pmsg->flags & I2C_M_NOSTART)) val |= CR_CPU_RDY; - writew(val, i2c_dev->base + REG_CR); - } - if (pmsg->len == 1) { - val = readw(i2c_dev->base + REG_CR); + if (pmsg->len == 1) val |= CR_TX_NEXT_NO_ACK; - writew(val, i2c_dev->base + REG_CR); - } - reinit_completion(&i2c_dev->complete); + writew(val, i2c_dev->base + REG_CR); - if (i2c_dev->mode == I2C_MODE_STANDARD) - tcr_val = TCR_STANDARD_MODE; - else - tcr_val = TCR_FAST_MODE; + reinit_completion(&i2c_dev->complete); tcr_val |= TCR_MASTER_READ | (pmsg->addr & TCR_SLAVE_ADDR_MASK); @@ -263,12 +221,6 @@ static int wmt_i2c_read(struct i2c_adapter *adap, struct i2c_msg *pmsg, } while (xfer_len < pmsg->len) { - wait_result = wait_for_completion_timeout(&i2c_dev->complete, - msecs_to_jiffies(500)); - - if (!wait_result) - return -ETIMEDOUT; - ret = wmt_check_status(i2c_dev); if (ret) return ret; @@ -276,15 +228,10 @@ static int wmt_i2c_read(struct i2c_adapter *adap, struct i2c_msg *pmsg, pmsg->buf[xfer_len] = readw(i2c_dev->base + REG_CDR) >> 8; xfer_len++; - if (xfer_len == pmsg->len - 1) { - val = readw(i2c_dev->base + REG_CR); - val |= (CR_TX_NEXT_NO_ACK | CR_CPU_RDY); - writew(val, i2c_dev->base + REG_CR); - } else { - val = readw(i2c_dev->base + REG_CR); - val |= CR_CPU_RDY; - writew(val, i2c_dev->base + REG_CR); - } + val = readw(i2c_dev->base + REG_CR) | CR_CPU_RDY; + if (xfer_len == pmsg->len - 1) + val |= CR_TX_NEXT_NO_ACK; + writew(val, i2c_dev->base + REG_CR); } return 0; @@ -295,17 +242,22 @@ static int wmt_i2c_xfer(struct i2c_adapter *adap, int num) { struct i2c_msg *pmsg; - int i, is_last; + int i; int ret = 0; + struct wmt_i2c_dev *i2c_dev = i2c_get_adapdata(adap); for (i = 0; ret >= 0 && i < num; i++) { - is_last = ((i + 1) == num); - pmsg = &msgs[i]; + if (!(pmsg->flags & I2C_M_NOSTART)) { + ret = wmt_i2c_wait_bus_not_busy(i2c_dev); + if (ret < 0) + return ret; + } + if (pmsg->flags & I2C_M_RD) - ret = wmt_i2c_read(adap, pmsg, is_last); + ret = wmt_i2c_read(i2c_dev, pmsg); else - ret = wmt_i2c_write(adap, pmsg, is_last); + ret = wmt_i2c_write(i2c_dev, pmsg, (i + 1) == num); } return (ret < 0) ? ret : i; @@ -359,10 +311,10 @@ static int wmt_i2c_reset_hardware(struct wmt_i2c_dev *i2c_dev) readw(i2c_dev->base + REG_CSR); /* read clear */ writew(ISR_WRITE_ALL, i2c_dev->base + REG_ISR); - if (i2c_dev->mode == I2C_MODE_STANDARD) - writew(SCL_TIMEOUT(128) | TR_STD, i2c_dev->base + REG_TR); - else + if (i2c_dev->tcr == TCR_FAST_MODE) writew(SCL_TIMEOUT(128) | TR_HS, i2c_dev->base + REG_TR); + else + writew(SCL_TIMEOUT(128) | TR_STD, i2c_dev->base + REG_TR); return 0; } @@ -395,10 +347,9 @@ static int wmt_i2c_probe(struct platform_device *pdev) return PTR_ERR(i2c_dev->clk); } - i2c_dev->mode = I2C_MODE_STANDARD; err = of_property_read_u32(np, "clock-frequency", &clk_rate); if (!err && (clk_rate == I2C_MAX_FAST_MODE_FREQ)) - i2c_dev->mode = I2C_MODE_FAST; + i2c_dev->tcr = TCR_FAST_MODE; i2c_dev->dev = &pdev->dev; diff --git a/drivers/i2c/busses/scx200_acb.c b/drivers/i2c/busses/scx200_acb.c index 83c1db610f54..3648382b885a 100644 --- a/drivers/i2c/busses/scx200_acb.c +++ b/drivers/i2c/busses/scx200_acb.c @@ -427,7 +427,7 @@ static struct scx200_acb_iface *scx200_create_iface(const char *text, snprintf(adapter->name, sizeof(adapter->name), "%s ACB%d", text, index); adapter->owner = THIS_MODULE; adapter->algo = &scx200_acb_algorithm; - adapter->class = I2C_CLASS_HWMON | I2C_CLASS_SPD; + adapter->class = I2C_CLASS_HWMON; adapter->dev.parent = dev; mutex_init(&iface->mutex); diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index eac90a3cf61a..3bd48d4b6318 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -16,6 +16,7 @@ #include <linux/acpi.h> #include <linux/clk/clk-conf.h> #include <linux/completion.h> +#include <linux/debugfs.h> #include <linux/delay.h> #include <linux/err.h> #include <linux/errno.h> @@ -67,6 +68,8 @@ static int i2c_detect(struct i2c_adapter *adapter, struct i2c_driver *driver); static DEFINE_STATIC_KEY_FALSE(i2c_trace_msg_key); static bool is_registered; +static struct dentry *i2c_debugfs_root; + int i2c_transfer_trace_reg(void) { static_branch_inc(&i2c_trace_msg_key); @@ -689,7 +692,7 @@ static struct attribute *i2c_dev_attrs[] = { }; ATTRIBUTE_GROUPS(i2c_dev); -struct bus_type i2c_bus_type = { +const struct bus_type i2c_bus_type = { .name = "i2c", .match = i2c_device_match, .probe = i2c_device_probe, @@ -1524,6 +1527,8 @@ static int i2c_register_adapter(struct i2c_adapter *adap) goto out_list; } + adap->debugfs = debugfs_create_dir(dev_name(&adap->dev), i2c_debugfs_root); + res = i2c_setup_smbus_alert(adap); if (res) goto out_reg; @@ -1563,6 +1568,7 @@ static int i2c_register_adapter(struct i2c_adapter *adap) return 0; out_reg: + debugfs_remove_recursive(adap->debugfs); init_completion(&adap->dev_released); device_unregister(&adap->dev); wait_for_completion(&adap->dev_released); @@ -1764,6 +1770,8 @@ void i2c_del_adapter(struct i2c_adapter *adap) i2c_host_notify_irq_teardown(adap); + debugfs_remove_recursive(adap->debugfs); + /* wait until all references to the device are gone * * FIXME: This is old code and should ideally be replaced by an @@ -2061,6 +2069,8 @@ static int __init i2c_init(void) is_registered = true; + i2c_debugfs_root = debugfs_create_dir("i2c", NULL); + #ifdef CONFIG_I2C_COMPAT i2c_adapter_compat_class = class_compat_register("i2c-adapter"); if (!i2c_adapter_compat_class) { @@ -2099,6 +2109,7 @@ static void __exit i2c_exit(void) #ifdef CONFIG_I2C_COMPAT class_compat_unregister(i2c_adapter_compat_class); #endif + debugfs_remove_recursive(i2c_debugfs_root); bus_unregister(&i2c_bus_type); tracepoint_synchronize_unregister(); } diff --git a/drivers/i2c/i2c-smbus.c b/drivers/i2c/i2c-smbus.c index 138c3f5e0093..74807c6db596 100644 --- a/drivers/i2c/i2c-smbus.c +++ b/drivers/i2c/i2c-smbus.c @@ -308,8 +308,8 @@ EXPORT_SYMBOL_GPL(i2c_free_slave_host_notify_device); * target systems are the same. * Restrictions to automatic SPD instantiation: * - Only works if all filled slots have the same memory type - * - Only works for DDR2, DDR3 and DDR4 for now - * - Only works on systems with 1 to 4 memory slots + * - Only works for DDR, DDR2, DDR3 and DDR4 for now + * - Only works on systems with 1 to 8 memory slots */ #if IS_ENABLED(CONFIG_DMI) void i2c_register_spd(struct i2c_adapter *adap) @@ -354,9 +354,9 @@ void i2c_register_spd(struct i2c_adapter *adap) dev_info(&adap->dev, "%d/%d memory slots populated (from DMI)\n", dimm_count, slot_count); - if (slot_count > 4) { + if (slot_count > 8) { dev_warn(&adap->dev, - "Systems with more than 4 memory slots not supported yet, not instantiating SPD\n"); + "Systems with more than 8 memory slots not supported yet, not instantiating SPD\n"); return; } diff --git a/drivers/i2c/i2c-stub.c b/drivers/i2c/i2c-stub.c index d642cad219d9..09e7b7bf4c5f 100644 --- a/drivers/i2c/i2c-stub.c +++ b/drivers/i2c/i2c-stub.c @@ -308,7 +308,7 @@ static const struct i2c_algorithm smbus_algorithm = { static struct i2c_adapter stub_adapter = { .owner = THIS_MODULE, - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON, .algo = &smbus_algorithm, .name = "SMBus stub driver", }; diff --git a/drivers/i2c/muxes/i2c-mux-reg.c b/drivers/i2c/muxes/i2c-mux-reg.c index 9efc1ed01577..8489971babd3 100644 --- a/drivers/i2c/muxes/i2c-mux-reg.c +++ b/drivers/i2c/muxes/i2c-mux-reg.c @@ -159,7 +159,6 @@ static int i2c_mux_reg_probe(struct platform_device *pdev) struct regmux *mux; struct i2c_adapter *parent; struct resource *res; - unsigned int class; int i, ret, nr; mux = devm_kzalloc(&pdev->dev, sizeof(*mux), GFP_KERNEL); @@ -213,9 +212,8 @@ static int i2c_mux_reg_probe(struct platform_device *pdev) for (i = 0; i < mux->data.n_values; i++) { nr = mux->data.base_nr ? (mux->data.base_nr + i) : 0; - class = mux->data.classes ? mux->data.classes[i] : 0; - ret = i2c_mux_add_adapter(muxc, nr, mux->data.values[i], class); + ret = i2c_mux_add_adapter(muxc, nr, mux->data.values[i], 0); if (ret) goto err_del_mux_adapters; } diff --git a/drivers/input/input.c b/drivers/input/input.c index 8c5fdb0f858a..f71ea4fb173f 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -1365,8 +1365,8 @@ static ssize_t input_dev_show_##name(struct device *dev, \ { \ struct input_dev *input_dev = to_input_dev(dev); \ \ - return scnprintf(buf, PAGE_SIZE, "%s\n", \ - input_dev->name ? input_dev->name : ""); \ + return sysfs_emit(buf, "%s\n", \ + input_dev->name ? input_dev->name : ""); \ } \ static DEVICE_ATTR(name, S_IRUGO, input_dev_show_##name, NULL) @@ -1458,7 +1458,7 @@ static ssize_t inhibited_show(struct device *dev, { struct input_dev *input_dev = to_input_dev(dev); - return scnprintf(buf, PAGE_SIZE, "%d\n", input_dev->inhibited); + return sysfs_emit(buf, "%d\n", input_dev->inhibited); } static ssize_t inhibited_store(struct device *dev, @@ -1505,7 +1505,7 @@ static ssize_t input_dev_show_id_##name(struct device *dev, \ char *buf) \ { \ struct input_dev *input_dev = to_input_dev(dev); \ - return scnprintf(buf, PAGE_SIZE, "%04x\n", input_dev->id.name); \ + return sysfs_emit(buf, "%04x\n", input_dev->id.name); \ } \ static DEVICE_ATTR(name, S_IRUGO, input_dev_show_id_##name, NULL) diff --git a/drivers/input/joystick/Kconfig b/drivers/input/joystick/Kconfig index ac6925ce8366..7755e5b454d2 100644 --- a/drivers/input/joystick/Kconfig +++ b/drivers/input/joystick/Kconfig @@ -412,4 +412,14 @@ config JOYSTICK_SENSEHAT To compile this driver as a module, choose M here: the module will be called sensehat_joystick. +config JOYSTICK_SEESAW + tristate "Adafruit Mini I2C Gamepad with Seesaw" + depends on I2C + select INPUT_SPARSEKMAP + help + Say Y here if you want to use the Adafruit Mini I2C Gamepad. + + To compile this driver as a module, choose M here: the module will be + called adafruit-seesaw. + endif diff --git a/drivers/input/joystick/Makefile b/drivers/input/joystick/Makefile index 3937535f0098..9976f596a920 100644 --- a/drivers/input/joystick/Makefile +++ b/drivers/input/joystick/Makefile @@ -28,6 +28,7 @@ obj-$(CONFIG_JOYSTICK_N64) += n64joy.o obj-$(CONFIG_JOYSTICK_PSXPAD_SPI) += psxpad-spi.o obj-$(CONFIG_JOYSTICK_PXRC) += pxrc.o obj-$(CONFIG_JOYSTICK_QWIIC) += qwiic-joystick.o +obj-$(CONFIG_JOYSTICK_SEESAW) += adafruit-seesaw.o obj-$(CONFIG_JOYSTICK_SENSEHAT) += sensehat-joystick.o obj-$(CONFIG_JOYSTICK_SIDEWINDER) += sidewinder.o obj-$(CONFIG_JOYSTICK_SPACEBALL) += spaceball.o diff --git a/drivers/input/joystick/adafruit-seesaw.c b/drivers/input/joystick/adafruit-seesaw.c new file mode 100644 index 000000000000..1b9279f024cc --- /dev/null +++ b/drivers/input/joystick/adafruit-seesaw.c @@ -0,0 +1,315 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2023 Anshul Dalal <anshulusr@gmail.com> + * + * Driver for Adafruit Mini I2C Gamepad + * + * Based on the work of: + * Oleh Kravchenko (Sparkfun Qwiic Joystick driver) + * + * Datasheet: https://cdn-learn.adafruit.com/downloads/pdf/gamepad-qt.pdf + * Product page: https://www.adafruit.com/product/5743 + * Firmware and hardware sources: https://github.com/adafruit/Adafruit_Seesaw + * + * TODO: + * - Add interrupt support + */ + +#include <asm/unaligned.h> +#include <linux/bits.h> +#include <linux/delay.h> +#include <linux/i2c.h> +#include <linux/input.h> +#include <linux/input/sparse-keymap.h> +#include <linux/kernel.h> +#include <linux/module.h> + +#define SEESAW_DEVICE_NAME "seesaw-gamepad" + +#define SEESAW_ADC_BASE 0x0900 + +#define SEESAW_GPIO_DIRCLR_BULK 0x0103 +#define SEESAW_GPIO_BULK 0x0104 +#define SEESAW_GPIO_BULK_SET 0x0105 +#define SEESAW_GPIO_PULLENSET 0x010b + +#define SEESAW_STATUS_HW_ID 0x0001 +#define SEESAW_STATUS_SWRST 0x007f + +#define SEESAW_ADC_OFFSET 0x07 + +#define SEESAW_BUTTON_A 0x05 +#define SEESAW_BUTTON_B 0x01 +#define SEESAW_BUTTON_X 0x06 +#define SEESAW_BUTTON_Y 0x02 +#define SEESAW_BUTTON_START 0x10 +#define SEESAW_BUTTON_SELECT 0x00 + +#define SEESAW_ANALOG_X 0x0e +#define SEESAW_ANALOG_Y 0x0f + +#define SEESAW_JOYSTICK_MAX_AXIS 1023 +#define SEESAW_JOYSTICK_FUZZ 2 +#define SEESAW_JOYSTICK_FLAT 4 + +#define SEESAW_GAMEPAD_POLL_INTERVAL_MS 16 +#define SEESAW_GAMEPAD_POLL_MIN 8 +#define SEESAW_GAMEPAD_POLL_MAX 32 + +static const unsigned long SEESAW_BUTTON_MASK = + BIT(SEESAW_BUTTON_A) | BIT(SEESAW_BUTTON_B) | BIT(SEESAW_BUTTON_X) | + BIT(SEESAW_BUTTON_Y) | BIT(SEESAW_BUTTON_START) | + BIT(SEESAW_BUTTON_SELECT); + +struct seesaw_gamepad { + struct input_dev *input_dev; + struct i2c_client *i2c_client; +}; + +struct seesaw_data { + u16 x; + u16 y; + u32 button_state; +}; + +static const struct key_entry seesaw_buttons_new[] = { + { KE_KEY, SEESAW_BUTTON_A, .keycode = BTN_SOUTH }, + { KE_KEY, SEESAW_BUTTON_B, .keycode = BTN_EAST }, + { KE_KEY, SEESAW_BUTTON_X, .keycode = BTN_NORTH }, + { KE_KEY, SEESAW_BUTTON_Y, .keycode = BTN_WEST }, + { KE_KEY, SEESAW_BUTTON_START, .keycode = BTN_START }, + { KE_KEY, SEESAW_BUTTON_SELECT, .keycode = BTN_SELECT }, + { KE_END, 0 } +}; + +static int seesaw_register_read(struct i2c_client *client, u16 reg, void *buf, + int count) +{ + __be16 register_buf = cpu_to_be16(reg); + struct i2c_msg message_buf[2] = { + { + .addr = client->addr, + .flags = client->flags, + .len = sizeof(register_buf), + .buf = (u8 *)®ister_buf, + }, + { + .addr = client->addr, + .flags = client->flags | I2C_M_RD, + .len = count, + .buf = (u8 *)buf, + }, + }; + int ret; + + ret = i2c_transfer(client->adapter, message_buf, + ARRAY_SIZE(message_buf)); + if (ret < 0) + return ret; + + return 0; +} + +static int seesaw_register_write_u8(struct i2c_client *client, u16 reg, + u8 value) +{ + u8 write_buf[sizeof(reg) + sizeof(value)]; + int ret; + + put_unaligned_be16(reg, write_buf); + write_buf[sizeof(reg)] = value; + + ret = i2c_master_send(client, write_buf, sizeof(write_buf)); + if (ret < 0) + return ret; + + return 0; +} + +static int seesaw_register_write_u32(struct i2c_client *client, u16 reg, + u32 value) +{ + u8 write_buf[sizeof(reg) + sizeof(value)]; + int ret; + + put_unaligned_be16(reg, write_buf); + put_unaligned_be32(value, write_buf + sizeof(reg)); + ret = i2c_master_send(client, write_buf, sizeof(write_buf)); + if (ret < 0) + return ret; + + return 0; +} + +static int seesaw_read_data(struct i2c_client *client, struct seesaw_data *data) +{ + __be16 adc_data; + __be32 read_buf; + int err; + + err = seesaw_register_read(client, SEESAW_GPIO_BULK, + &read_buf, sizeof(read_buf)); + if (err) + return err; + + data->button_state = ~be32_to_cpu(read_buf); + + err = seesaw_register_read(client, + SEESAW_ADC_BASE | + (SEESAW_ADC_OFFSET + SEESAW_ANALOG_X), + &adc_data, sizeof(adc_data)); + if (err) + return err; + /* + * ADC reads left as max and right as 0, must be reversed since kernel + * expects reports in opposite order. + */ + data->x = SEESAW_JOYSTICK_MAX_AXIS - be16_to_cpu(adc_data); + + err = seesaw_register_read(client, + SEESAW_ADC_BASE | + (SEESAW_ADC_OFFSET + SEESAW_ANALOG_Y), + &adc_data, sizeof(adc_data)); + if (err) + return err; + + data->y = be16_to_cpu(adc_data); + + return 0; +} + +static void seesaw_poll(struct input_dev *input) +{ + struct seesaw_gamepad *private = input_get_drvdata(input); + struct seesaw_data data; + int err, i; + + err = seesaw_read_data(private->i2c_client, &data); + if (err) { + dev_err_ratelimited(&input->dev, + "failed to read joystick state: %d\n", err); + return; + } + + input_report_abs(input, ABS_X, data.x); + input_report_abs(input, ABS_Y, data.y); + + for_each_set_bit(i, &SEESAW_BUTTON_MASK, + BITS_PER_TYPE(SEESAW_BUTTON_MASK)) { + if (!sparse_keymap_report_event(input, i, + data.button_state & BIT(i), + false)) + dev_err_ratelimited(&input->dev, + "failed to report keymap event"); + } + + input_sync(input); +} + +static int seesaw_probe(struct i2c_client *client) +{ + struct seesaw_gamepad *seesaw; + u8 hardware_id; + int err; + + err = seesaw_register_write_u8(client, SEESAW_STATUS_SWRST, 0xFF); + if (err) + return err; + + /* Wait for the registers to reset before proceeding */ + usleep_range(10000, 15000); + + seesaw = devm_kzalloc(&client->dev, sizeof(*seesaw), GFP_KERNEL); + if (!seesaw) + return -ENOMEM; + + err = seesaw_register_read(client, SEESAW_STATUS_HW_ID, + &hardware_id, sizeof(hardware_id)); + if (err) + return err; + + dev_dbg(&client->dev, "Adafruit Seesaw Gamepad, Hardware ID: %02x\n", + hardware_id); + + /* Set Pin Mode to input and enable pull-up resistors */ + err = seesaw_register_write_u32(client, SEESAW_GPIO_DIRCLR_BULK, + SEESAW_BUTTON_MASK); + if (err) + return err; + err = seesaw_register_write_u32(client, SEESAW_GPIO_PULLENSET, + SEESAW_BUTTON_MASK); + if (err) + return err; + err = seesaw_register_write_u32(client, SEESAW_GPIO_BULK_SET, + SEESAW_BUTTON_MASK); + if (err) + return err; + + seesaw->i2c_client = client; + seesaw->input_dev = devm_input_allocate_device(&client->dev); + if (!seesaw->input_dev) + return -ENOMEM; + + seesaw->input_dev->id.bustype = BUS_I2C; + seesaw->input_dev->name = "Adafruit Seesaw Gamepad"; + seesaw->input_dev->phys = "i2c/" SEESAW_DEVICE_NAME; + input_set_drvdata(seesaw->input_dev, seesaw); + input_set_abs_params(seesaw->input_dev, ABS_X, + 0, SEESAW_JOYSTICK_MAX_AXIS, + SEESAW_JOYSTICK_FUZZ, SEESAW_JOYSTICK_FLAT); + input_set_abs_params(seesaw->input_dev, ABS_Y, + 0, SEESAW_JOYSTICK_MAX_AXIS, + SEESAW_JOYSTICK_FUZZ, SEESAW_JOYSTICK_FLAT); + + err = sparse_keymap_setup(seesaw->input_dev, seesaw_buttons_new, NULL); + if (err) { + dev_err(&client->dev, + "failed to set up input device keymap: %d\n", err); + return err; + } + + err = input_setup_polling(seesaw->input_dev, seesaw_poll); + if (err) { + dev_err(&client->dev, "failed to set up polling: %d\n", err); + return err; + } + + input_set_poll_interval(seesaw->input_dev, + SEESAW_GAMEPAD_POLL_INTERVAL_MS); + input_set_max_poll_interval(seesaw->input_dev, SEESAW_GAMEPAD_POLL_MAX); + input_set_min_poll_interval(seesaw->input_dev, SEESAW_GAMEPAD_POLL_MIN); + + err = input_register_device(seesaw->input_dev); + if (err) { + dev_err(&client->dev, "failed to register joystick: %d\n", err); + return err; + } + + return 0; +} + +static const struct i2c_device_id seesaw_id_table[] = { + { SEESAW_DEVICE_NAME }, + { /* Sentinel */ } +}; +MODULE_DEVICE_TABLE(i2c, seesaw_id_table); + +static const struct of_device_id seesaw_of_table[] = { + { .compatible = "adafruit,seesaw-gamepad"}, + { /* Sentinel */ } +}; +MODULE_DEVICE_TABLE(of, seesaw_of_table); + +static struct i2c_driver seesaw_driver = { + .driver = { + .name = SEESAW_DEVICE_NAME, + .of_match_table = seesaw_of_table, + }, + .id_table = seesaw_id_table, + .probe = seesaw_probe, +}; +module_i2c_driver(seesaw_driver); + +MODULE_AUTHOR("Anshul Dalal <anshulusr@gmail.com>"); +MODULE_DESCRIPTION("Adafruit Mini I2C Gamepad driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/input/joystick/as5011.c b/drivers/input/joystick/as5011.c index bf8b1cc0ea9c..f1822c19a289 100644 --- a/drivers/input/joystick/as5011.c +++ b/drivers/input/joystick/as5011.c @@ -13,7 +13,7 @@ #include <linux/i2c.h> #include <linux/interrupt.h> #include <linux/input.h> -#include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/delay.h> #include <linux/input/as5011.h> #include <linux/slab.h> @@ -61,7 +61,7 @@ MODULE_LICENSE("GPL"); struct as5011_device { struct input_dev *input_dev; struct i2c_client *i2c_client; - unsigned int button_gpio; + struct gpio_desc *button_gpiod; unsigned int button_irq; unsigned int axis_irq; }; @@ -114,7 +114,7 @@ static int as5011_i2c_read(struct i2c_client *client, static irqreturn_t as5011_button_interrupt(int irq, void *dev_id) { struct as5011_device *as5011 = dev_id; - int val = gpio_get_value_cansleep(as5011->button_gpio); + int val = gpiod_get_value_cansleep(as5011->button_gpiod); input_report_key(as5011->input_dev, BTN_JOYSTICK, !val); input_sync(as5011->input_dev); @@ -248,7 +248,6 @@ static int as5011_probe(struct i2c_client *client) as5011->i2c_client = client; as5011->input_dev = input_dev; - as5011->button_gpio = plat_data->button_gpio; as5011->axis_irq = plat_data->axis_irq; input_dev->name = "Austria Microsystem as5011 joystick"; @@ -262,18 +261,20 @@ static int as5011_probe(struct i2c_client *client) input_set_abs_params(as5011->input_dev, ABS_Y, AS5011_MIN_AXIS, AS5011_MAX_AXIS, AS5011_FUZZ, AS5011_FLAT); - error = gpio_request(as5011->button_gpio, "AS5011 button"); - if (error < 0) { - dev_err(&client->dev, "Failed to request button gpio\n"); + as5011->button_gpiod = devm_gpiod_get(&client->dev, NULL, GPIOD_IN); + if (IS_ERR(as5011->button_gpiod)) { + error = PTR_ERR(as5011->button_gpiod); + dev_err(&client->dev, "Failed to request button GPIO\n"); goto err_free_mem; } + gpiod_set_consumer_name(as5011->button_gpiod, "AS5011 button"); - irq = gpio_to_irq(as5011->button_gpio); + irq = gpiod_to_irq(as5011->button_gpiod); if (irq < 0) { dev_err(&client->dev, "Failed to get irq number for button gpio\n"); error = irq; - goto err_free_button_gpio; + goto err_free_mem; } as5011->button_irq = irq; @@ -286,7 +287,7 @@ static int as5011_probe(struct i2c_client *client) if (error < 0) { dev_err(&client->dev, "Can't allocate button irq %d\n", as5011->button_irq); - goto err_free_button_gpio; + goto err_free_mem; } error = as5011_configure_chip(as5011, plat_data); @@ -317,8 +318,6 @@ err_free_axis_irq: free_irq(as5011->axis_irq, as5011); err_free_button_irq: free_irq(as5011->button_irq, as5011); -err_free_button_gpio: - gpio_free(as5011->button_gpio); err_free_mem: input_free_device(input_dev); kfree(as5011); @@ -332,7 +331,6 @@ static void as5011_remove(struct i2c_client *client) free_irq(as5011->axis_irq, as5011); free_irq(as5011->button_irq, as5011); - gpio_free(as5011->button_gpio); input_unregister_device(as5011->input_dev); kfree(as5011); diff --git a/drivers/input/joystick/pxrc.c b/drivers/input/joystick/pxrc.c index ea2bf5951d67..52d9eab667b7 100644 --- a/drivers/input/joystick/pxrc.c +++ b/drivers/input/joystick/pxrc.c @@ -5,15 +5,17 @@ * Copyright (C) 2018 Marcus Folkesson <marcus.folkesson@gmail.com> */ -#include <linux/kernel.h> +#include <linux/cleanup.h> #include <linux/errno.h> -#include <linux/slab.h> +#include <linux/input.h> +#include <linux/kernel.h> #include <linux/module.h> +#include <linux/mutex.h> +#include <linux/slab.h> #include <linux/uaccess.h> + #include <linux/usb.h> #include <linux/usb/input.h> -#include <linux/mutex.h> -#include <linux/input.h> #define PXRC_VENDOR_ID 0x1781 #define PXRC_PRODUCT_ID 0x0898 @@ -81,33 +83,28 @@ exit: static int pxrc_open(struct input_dev *input) { struct pxrc *pxrc = input_get_drvdata(input); - int retval; + int error; - mutex_lock(&pxrc->pm_mutex); - retval = usb_submit_urb(pxrc->urb, GFP_KERNEL); - if (retval) { + guard(mutex)(&pxrc->pm_mutex); + error = usb_submit_urb(pxrc->urb, GFP_KERNEL); + if (error) { dev_err(&pxrc->intf->dev, "%s - usb_submit_urb failed, error: %d\n", - __func__, retval); - retval = -EIO; - goto out; + __func__, error); + return -EIO; } pxrc->is_open = true; - -out: - mutex_unlock(&pxrc->pm_mutex); - return retval; + return 0; } static void pxrc_close(struct input_dev *input) { struct pxrc *pxrc = input_get_drvdata(input); - mutex_lock(&pxrc->pm_mutex); + guard(mutex)(&pxrc->pm_mutex); usb_kill_urb(pxrc->urb); pxrc->is_open = false; - mutex_unlock(&pxrc->pm_mutex); } static void pxrc_free_urb(void *_pxrc) @@ -208,10 +205,9 @@ static int pxrc_suspend(struct usb_interface *intf, pm_message_t message) { struct pxrc *pxrc = usb_get_intfdata(intf); - mutex_lock(&pxrc->pm_mutex); + guard(mutex)(&pxrc->pm_mutex); if (pxrc->is_open) usb_kill_urb(pxrc->urb); - mutex_unlock(&pxrc->pm_mutex); return 0; } @@ -219,14 +215,12 @@ static int pxrc_suspend(struct usb_interface *intf, pm_message_t message) static int pxrc_resume(struct usb_interface *intf) { struct pxrc *pxrc = usb_get_intfdata(intf); - int retval = 0; - mutex_lock(&pxrc->pm_mutex); + guard(mutex)(&pxrc->pm_mutex); if (pxrc->is_open && usb_submit_urb(pxrc->urb, GFP_KERNEL) < 0) - retval = -EIO; + return -EIO; - mutex_unlock(&pxrc->pm_mutex); - return retval; + return 0; } static int pxrc_pre_reset(struct usb_interface *intf) diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index e2c1848182de..b1244d7df6cc 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -1670,7 +1670,7 @@ static int xpad_led_probe(struct usb_xpad *xpad) if (!led) return -ENOMEM; - xpad->pad_nr = ida_simple_get(&xpad_pad_seq, 0, 0, GFP_KERNEL); + xpad->pad_nr = ida_alloc(&xpad_pad_seq, GFP_KERNEL); if (xpad->pad_nr < 0) { error = xpad->pad_nr; goto err_free_mem; @@ -1693,7 +1693,7 @@ static int xpad_led_probe(struct usb_xpad *xpad) return 0; err_free_id: - ida_simple_remove(&xpad_pad_seq, xpad->pad_nr); + ida_free(&xpad_pad_seq, xpad->pad_nr); err_free_mem: kfree(led); xpad->led = NULL; @@ -1706,7 +1706,7 @@ static void xpad_led_disconnect(struct usb_xpad *xpad) if (xpad_led) { led_classdev_unregister(&xpad_led->led_cdev); - ida_simple_remove(&xpad_pad_seq, xpad->pad_nr); + ida_free(&xpad_pad_seq, xpad->pad_nr); kfree(xpad_led); } } diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c index 786f00f6b7fd..13ef6284223d 100644 --- a/drivers/input/keyboard/atkbd.c +++ b/drivers/input/keyboard/atkbd.c @@ -791,9 +791,9 @@ static bool atkbd_is_portable_device(void) * not work. So in this case simply assume a keyboard is connected to avoid * confusing some laptop keyboards. * - * Skipping ATKBD_CMD_GETID ends up using a fake keyboard id. Using a fake id is - * ok in translated mode, only atkbd_select_set() checks atkbd->id and in - * translated mode that is a no-op. + * Skipping ATKBD_CMD_GETID ends up using a fake keyboard id. Using the standard + * 0xab83 id is ok in translated mode, only atkbd_select_set() checks atkbd->id + * and in translated mode that is a no-op. */ static bool atkbd_skip_getid(struct atkbd *atkbd) { @@ -811,6 +811,7 @@ static int atkbd_probe(struct atkbd *atkbd) { struct ps2dev *ps2dev = &atkbd->ps2dev; unsigned char param[2]; + bool skip_getid; /* * Some systems, where the bit-twiddling when testing the io-lines of the @@ -832,7 +833,8 @@ static int atkbd_probe(struct atkbd *atkbd) */ param[0] = param[1] = 0xa5; /* initialize with invalid values */ - if (atkbd_skip_getid(atkbd) || ps2_command(ps2dev, param, ATKBD_CMD_GETID)) { + skip_getid = atkbd_skip_getid(atkbd); + if (skip_getid || ps2_command(ps2dev, param, ATKBD_CMD_GETID)) { /* * If the get ID command was skipped or failed, we check if we can at least set @@ -842,7 +844,7 @@ static int atkbd_probe(struct atkbd *atkbd) param[0] = 0; if (ps2_command(ps2dev, param, ATKBD_CMD_SETLEDS)) return -1; - atkbd->id = 0xabba; + atkbd->id = skip_getid ? 0xab83 : 0xabba; return 0; } diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c index 1b4937dce672..52fba9ee7c1d 100644 --- a/drivers/input/keyboard/cap11xx.c +++ b/drivers/input/keyboard/cap11xx.c @@ -10,10 +10,11 @@ #include <linux/interrupt.h> #include <linux/input.h> #include <linux/leds.h> -#include <linux/of_irq.h> +#include <linux/of.h> #include <linux/regmap.h> #include <linux/i2c.h> #include <linux/gpio/consumer.h> +#include <linux/bitfield.h> #define CAP11XX_REG_MAIN_CONTROL 0x00 #define CAP11XX_REG_MAIN_CONTROL_GAIN_SHIFT (6) @@ -24,6 +25,7 @@ #define CAP11XX_REG_NOISE_FLAG_STATUS 0x0a #define CAP11XX_REG_SENOR_DELTA(X) (0x10 + (X)) #define CAP11XX_REG_SENSITIVITY_CONTROL 0x1f +#define CAP11XX_REG_SENSITIVITY_CONTROL_DELTA_SENSE_MASK 0x70 #define CAP11XX_REG_CONFIG 0x20 #define CAP11XX_REG_SENSOR_ENABLE 0x21 #define CAP11XX_REG_SENSOR_CONFIG 0x22 @@ -32,6 +34,7 @@ #define CAP11XX_REG_CALIBRATION 0x26 #define CAP11XX_REG_INT_ENABLE 0x27 #define CAP11XX_REG_REPEAT_RATE 0x28 +#define CAP11XX_REG_SIGNAL_GUARD_ENABLE 0x29 #define CAP11XX_REG_MT_CONFIG 0x2a #define CAP11XX_REG_MT_PATTERN_CONFIG 0x2b #define CAP11XX_REG_MT_PATTERN 0x2d @@ -47,6 +50,8 @@ #define CAP11XX_REG_SENSOR_BASE_CNT(X) (0x50 + (X)) #define CAP11XX_REG_LED_POLARITY 0x73 #define CAP11XX_REG_LED_OUTPUT_CONTROL 0x74 +#define CAP11XX_REG_CALIB_SENSITIVITY_CONFIG 0x80 +#define CAP11XX_REG_CALIB_SENSITIVITY_CONFIG2 0x81 #define CAP11XX_REG_LED_DUTY_CYCLE_1 0x90 #define CAP11XX_REG_LED_DUTY_CYCLE_2 0x91 @@ -78,12 +83,20 @@ struct cap11xx_led { struct cap11xx_priv { struct regmap *regmap; + struct device *dev; struct input_dev *idev; + const struct cap11xx_hw_model *model; + u8 id; struct cap11xx_led *leds; int num_leds; /* config */ + u8 analog_gain; + u8 sensitivity_delta_sense; + u8 signal_guard_inputs_mask; + u32 thresholds[8]; + u32 calib_sensitivities[8]; u32 keycodes[]; }; @@ -160,9 +173,6 @@ static bool cap11xx_volatile_reg(struct device *dev, unsigned int reg) case CAP11XX_REG_SENOR_DELTA(3): case CAP11XX_REG_SENOR_DELTA(4): case CAP11XX_REG_SENOR_DELTA(5): - case CAP11XX_REG_PRODUCT_ID: - case CAP11XX_REG_MANUFACTURER_ID: - case CAP11XX_REG_REVISION: return true; } @@ -177,10 +187,179 @@ static const struct regmap_config cap11xx_regmap_config = { .reg_defaults = cap11xx_reg_defaults, .num_reg_defaults = ARRAY_SIZE(cap11xx_reg_defaults), - .cache_type = REGCACHE_RBTREE, + .cache_type = REGCACHE_MAPLE, .volatile_reg = cap11xx_volatile_reg, }; +static int cap11xx_write_calib_sens_config_1(struct cap11xx_priv *priv) +{ + return regmap_write(priv->regmap, + CAP11XX_REG_CALIB_SENSITIVITY_CONFIG, + (priv->calib_sensitivities[3] << 6) | + (priv->calib_sensitivities[2] << 4) | + (priv->calib_sensitivities[1] << 2) | + priv->calib_sensitivities[0]); +} + +static int cap11xx_write_calib_sens_config_2(struct cap11xx_priv *priv) +{ + return regmap_write(priv->regmap, + CAP11XX_REG_CALIB_SENSITIVITY_CONFIG2, + (priv->calib_sensitivities[7] << 6) | + (priv->calib_sensitivities[6] << 4) | + (priv->calib_sensitivities[5] << 2) | + priv->calib_sensitivities[4]); +} + +static int cap11xx_init_keys(struct cap11xx_priv *priv) +{ + struct device_node *node = priv->dev->of_node; + struct device *dev = priv->dev; + int i, error; + u32 u32_val; + + if (!node) { + dev_err(dev, "Corresponding DT entry is not available\n"); + return -ENODEV; + } + + if (!of_property_read_u32(node, "microchip,sensor-gain", &u32_val)) { + if (priv->model->no_gain) { + dev_warn(dev, + "This model doesn't support 'sensor-gain'\n"); + } else if (is_power_of_2(u32_val) && u32_val <= 8) { + priv->analog_gain = (u8)ilog2(u32_val); + + error = regmap_update_bits(priv->regmap, + CAP11XX_REG_MAIN_CONTROL, + CAP11XX_REG_MAIN_CONTROL_GAIN_MASK, + priv->analog_gain << CAP11XX_REG_MAIN_CONTROL_GAIN_SHIFT); + if (error) + return error; + } else { + dev_err(dev, "Invalid sensor-gain value %u\n", u32_val); + return -EINVAL; + } + } + + if (of_property_read_bool(node, "microchip,irq-active-high")) { + if (priv->id == CAP1106 || + priv->id == CAP1126 || + priv->id == CAP1188) { + error = regmap_update_bits(priv->regmap, + CAP11XX_REG_CONFIG2, + CAP11XX_REG_CONFIG2_ALT_POL, + 0); + if (error) + return error; + } else { + dev_warn(dev, + "This model doesn't support 'irq-active-high'\n"); + } + } + + if (!of_property_read_u32(node, "microchip,sensitivity-delta-sense", &u32_val)) { + if (!is_power_of_2(u32_val) || u32_val > 128) { + dev_err(dev, "Invalid sensitivity-delta-sense value %u\n", u32_val); + return -EINVAL; + } + + priv->sensitivity_delta_sense = (u8)ilog2(u32_val); + u32_val = ~(FIELD_PREP(CAP11XX_REG_SENSITIVITY_CONTROL_DELTA_SENSE_MASK, + priv->sensitivity_delta_sense)); + + error = regmap_update_bits(priv->regmap, + CAP11XX_REG_SENSITIVITY_CONTROL, + CAP11XX_REG_SENSITIVITY_CONTROL_DELTA_SENSE_MASK, + u32_val); + if (error) + return error; + } + + if (!of_property_read_u32_array(node, "microchip,input-threshold", + priv->thresholds, priv->model->num_channels)) { + for (i = 0; i < priv->model->num_channels; i++) { + if (priv->thresholds[i] > 127) { + dev_err(dev, "Invalid input-threshold value %u\n", + priv->thresholds[i]); + return -EINVAL; + } + + error = regmap_write(priv->regmap, + CAP11XX_REG_SENSOR_THRESH(i), + priv->thresholds[i]); + if (error) + return error; + } + } + + if (!of_property_read_u32_array(node, "microchip,calib-sensitivity", + priv->calib_sensitivities, + priv->model->num_channels)) { + if (priv->id == CAP1293 || priv->id == CAP1298) { + for (i = 0; i < priv->model->num_channels; i++) { + if (!is_power_of_2(priv->calib_sensitivities[i]) || + priv->calib_sensitivities[i] > 4) { + dev_err(dev, "Invalid calib-sensitivity value %u\n", + priv->calib_sensitivities[i]); + return -EINVAL; + } + priv->calib_sensitivities[i] = ilog2(priv->calib_sensitivities[i]); + } + + error = cap11xx_write_calib_sens_config_1(priv); + if (error) + return error; + + if (priv->id == CAP1298) { + error = cap11xx_write_calib_sens_config_2(priv); + if (error) + return error; + } + } else { + dev_warn(dev, + "This model doesn't support 'calib-sensitivity'\n"); + } + } + + for (i = 0; i < priv->model->num_channels; i++) { + if (!of_property_read_u32_index(node, "microchip,signal-guard", + i, &u32_val)) { + if (u32_val > 1) + return -EINVAL; + if (u32_val) + priv->signal_guard_inputs_mask |= 0x01 << i; + } + } + + if (priv->signal_guard_inputs_mask) { + if (priv->id == CAP1293 || priv->id == CAP1298) { + error = regmap_write(priv->regmap, + CAP11XX_REG_SIGNAL_GUARD_ENABLE, + priv->signal_guard_inputs_mask); + if (error) + return error; + } else { + dev_warn(dev, + "This model doesn't support 'signal-guard'\n"); + } + } + + /* Provide some useful defaults */ + for (i = 0; i < priv->model->num_channels; i++) + priv->keycodes[i] = KEY_A + i; + + of_property_read_u32_array(node, "linux,keycodes", + priv->keycodes, priv->model->num_channels); + + /* Disable autorepeat. The Linux input system has its own handling. */ + error = regmap_write(priv->regmap, CAP11XX_REG_REPEAT_RATE, 0); + if (error) + return error; + + return 0; +} + static irqreturn_t cap11xx_thread_func(int irq_num, void *data) { struct cap11xx_priv *priv = data; @@ -332,11 +511,9 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client) const struct i2c_device_id *id = i2c_client_get_device_id(i2c_client); struct device *dev = &i2c_client->dev; struct cap11xx_priv *priv; - struct device_node *node; const struct cap11xx_hw_model *cap; - int i, error, irq, gain = 0; + int i, error; unsigned int val, rev; - u32 gain32; if (id->driver_data >= ARRAY_SIZE(cap11xx_devices)) { dev_err(dev, "Invalid device ID %lu\n", id->driver_data); @@ -355,6 +532,8 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client) if (!priv) return -ENOMEM; + priv->dev = dev; + priv->regmap = devm_regmap_init_i2c(i2c_client, &cap11xx_regmap_config); if (IS_ERR(priv->regmap)) return PTR_ERR(priv->regmap); @@ -384,50 +563,15 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client) return error; dev_info(dev, "CAP11XX detected, model %s, revision 0x%02x\n", - id->name, rev); - node = dev->of_node; - - if (!of_property_read_u32(node, "microchip,sensor-gain", &gain32)) { - if (cap->no_gain) - dev_warn(dev, - "This version doesn't support sensor gain\n"); - else if (is_power_of_2(gain32) && gain32 <= 8) - gain = ilog2(gain32); - else - dev_err(dev, "Invalid sensor-gain value %d\n", gain32); - } + id->name, rev); - if (id->driver_data == CAP1106 || - id->driver_data == CAP1126 || - id->driver_data == CAP1188) { - if (of_property_read_bool(node, "microchip,irq-active-high")) { - error = regmap_update_bits(priv->regmap, - CAP11XX_REG_CONFIG2, - CAP11XX_REG_CONFIG2_ALT_POL, - 0); - if (error) - return error; - } - } - - /* Provide some useful defaults */ - for (i = 0; i < cap->num_channels; i++) - priv->keycodes[i] = KEY_A + i; - - of_property_read_u32_array(node, "linux,keycodes", - priv->keycodes, cap->num_channels); + priv->model = cap; + priv->id = id->driver_data; - if (!cap->no_gain) { - error = regmap_update_bits(priv->regmap, - CAP11XX_REG_MAIN_CONTROL, - CAP11XX_REG_MAIN_CONTROL_GAIN_MASK, - gain << CAP11XX_REG_MAIN_CONTROL_GAIN_SHIFT); - if (error) - return error; - } + dev_info(dev, "CAP11XX device detected, model %s, revision 0x%02x\n", + id->name, rev); - /* Disable autorepeat. The Linux input system has its own handling. */ - error = regmap_write(priv->regmap, CAP11XX_REG_REPEAT_RATE, 0); + error = cap11xx_init_keys(priv); if (error) return error; @@ -439,7 +583,7 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client) priv->idev->id.bustype = BUS_I2C; priv->idev->evbit[0] = BIT_MASK(EV_KEY); - if (of_property_read_bool(node, "autorepeat")) + if (of_property_read_bool(dev->of_node, "autorepeat")) __set_bit(EV_REP, priv->idev->evbit); for (i = 0; i < cap->num_channels; i++) @@ -474,13 +618,8 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client) if (error) return error; - irq = irq_of_parse_and_map(node, 0); - if (!irq) { - dev_err(dev, "Unable to parse or map IRQ\n"); - return -ENXIO; - } - - error = devm_request_threaded_irq(dev, irq, NULL, cap11xx_thread_func, + error = devm_request_threaded_irq(dev, i2c_client->irq, + NULL, cap11xx_thread_func, IRQF_ONESHOT, dev_name(dev), priv); if (error) return error; diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c index 2e7c2c046e67..9f3bcd41cf67 100644 --- a/drivers/input/keyboard/gpio_keys.c +++ b/drivers/input/keyboard/gpio_keys.c @@ -45,7 +45,9 @@ struct gpio_button_data { unsigned int software_debounce; /* in msecs, for GPIO-driven buttons */ unsigned int irq; + unsigned int wakeirq; unsigned int wakeup_trigger_type; + spinlock_t lock; bool disabled; bool key_pressed; @@ -511,6 +513,7 @@ static int gpio_keys_setup_key(struct platform_device *pdev, struct gpio_button_data *bdata = &ddata->data[idx]; irq_handler_t isr; unsigned long irqflags; + const char *wakedesc; int irq; int error; @@ -575,15 +578,23 @@ static int gpio_keys_setup_key(struct platform_device *pdev, !gpiod_cansleep(bdata->gpiod); } + /* + * If an interrupt was specified, use it instead of the gpio + * interrupt and use the gpio for reading the state. A separate + * interrupt may be used as the main button interrupt for + * runtime PM to detect events also in deeper idle states. If a + * dedicated wakeirq is used for system suspend only, see below + * for bdata->wakeirq setup. + */ if (button->irq) { bdata->irq = button->irq; } else { irq = gpiod_to_irq(bdata->gpiod); if (irq < 0) { error = irq; - dev_err(dev, - "Unable to get irq number for GPIO %d, error %d\n", - button->gpio, error); + dev_err_probe(dev, error, + "Unable to get irq number for GPIO %d\n", + button->gpio); return error; } bdata->irq = irq; @@ -672,6 +683,36 @@ static int gpio_keys_setup_key(struct platform_device *pdev, return error; } + if (!button->wakeirq) + return 0; + + /* Use :wakeup suffix like drivers/base/power/wakeirq.c does */ + wakedesc = devm_kasprintf(dev, GFP_KERNEL, "%s:wakeup", desc); + if (!wakedesc) + return -ENOMEM; + + bdata->wakeirq = button->wakeirq; + irqflags |= IRQF_NO_SUSPEND; + + /* + * Wakeirq shares the handler with the main interrupt, it's only + * active during system suspend. See gpio_keys_button_enable_wakeup() + * and gpio_keys_button_disable_wakeup(). + */ + error = devm_request_any_context_irq(dev, bdata->wakeirq, isr, + irqflags, wakedesc, bdata); + if (error < 0) { + dev_err(dev, "Unable to claim wakeirq %d; error %d\n", + bdata->irq, error); + return error; + } + + /* + * Disable wakeirq until suspend. IRQF_NO_AUTOEN won't work if + * IRQF_SHARED was set based on !button->can_disable. + */ + disable_irq(bdata->wakeirq); + return 0; } @@ -728,7 +769,7 @@ gpio_keys_get_devtree_pdata(struct device *dev) struct gpio_keys_platform_data *pdata; struct gpio_keys_button *button; struct fwnode_handle *child; - int nbuttons; + int nbuttons, irq; nbuttons = device_get_child_node_count(dev); if (nbuttons == 0) @@ -750,9 +791,19 @@ gpio_keys_get_devtree_pdata(struct device *dev) device_property_read_string(dev, "label", &pdata->name); device_for_each_child_node(dev, child) { - if (is_of_node(child)) - button->irq = - irq_of_parse_and_map(to_of_node(child), 0); + if (is_of_node(child)) { + irq = of_irq_get_byname(to_of_node(child), "irq"); + if (irq > 0) + button->irq = irq; + + irq = of_irq_get_byname(to_of_node(child), "wakeup"); + if (irq > 0) + button->wakeirq = irq; + + if (!button->irq && !button->wakeirq) + button->irq = + irq_of_parse_and_map(to_of_node(child), 0); + } if (fwnode_property_read_u32(child, "linux,code", &button->code)) { @@ -921,6 +972,11 @@ gpio_keys_button_enable_wakeup(struct gpio_button_data *bdata) } } + if (bdata->wakeirq) { + enable_irq(bdata->wakeirq); + disable_irq(bdata->irq); + } + return 0; } @@ -929,6 +985,11 @@ gpio_keys_button_disable_wakeup(struct gpio_button_data *bdata) { int error; + if (bdata->wakeirq) { + enable_irq(bdata->irq); + disable_irq(bdata->wakeirq); + } + /* * The trigger type is always both edges for gpio-based keys and we do * not support changing wakeup trigger for interrupt-based keys. diff --git a/drivers/input/keyboard/omap-keypad.c b/drivers/input/keyboard/omap-keypad.c index 454fb8675657..16f936db7305 100644 --- a/drivers/input/keyboard/omap-keypad.c +++ b/drivers/input/keyboard/omap-keypad.c @@ -21,7 +21,6 @@ #include <linux/mutex.h> #include <linux/errno.h> #include <linux/slab.h> -#include <linux/gpio.h> #include <linux/platform_data/gpio-omap.h> #include <linux/platform_data/keypad-omap.h> #include <linux/soc/ti/omap1-io.h> @@ -49,9 +48,6 @@ struct omap_kp { static DECLARE_TASKLET_DISABLED_OLD(kp_tasklet, omap_kp_tasklet); -static unsigned int *row_gpios; -static unsigned int *col_gpios; - static irqreturn_t omap_kp_interrupt(int irq, void *dev_id) { /* disable keyboard interrupt and schedule for handling */ @@ -180,7 +176,7 @@ static int omap_kp_probe(struct platform_device *pdev) struct omap_kp *omap_kp; struct input_dev *input_dev; struct omap_kp_platform_data *pdata = dev_get_platdata(&pdev->dev); - int i, col_idx, row_idx, ret; + int ret; unsigned int row_shift, keycodemax; if (!pdata->rows || !pdata->cols || !pdata->keymap_data) { @@ -209,17 +205,9 @@ static int omap_kp_probe(struct platform_device *pdev) if (pdata->delay) omap_kp->delay = pdata->delay; - if (pdata->row_gpios && pdata->col_gpios) { - row_gpios = pdata->row_gpios; - col_gpios = pdata->col_gpios; - } - omap_kp->rows = pdata->rows; omap_kp->cols = pdata->cols; - col_idx = 0; - row_idx = 0; - timer_setup(&omap_kp->timer, omap_kp_timer, 0); /* get the irq and init timer*/ @@ -276,11 +264,6 @@ err4: err3: device_remove_file(&pdev->dev, &dev_attr_enable); err2: - for (i = row_idx - 1; i >= 0; i--) - gpio_free(row_gpios[i]); - for (i = col_idx - 1; i >= 0; i--) - gpio_free(col_gpios[i]); - kfree(omap_kp); input_free_device(input_dev); diff --git a/drivers/input/keyboard/omap4-keypad.c b/drivers/input/keyboard/omap4-keypad.c index d3f8688fdd9c..040b340995d8 100644 --- a/drivers/input/keyboard/omap4-keypad.c +++ b/drivers/input/keyboard/omap4-keypad.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/interrupt.h> #include <linux/platform_device.h> +#include <linux/clk.h> #include <linux/errno.h> #include <linux/io.h> #include <linux/of.h> @@ -83,6 +84,7 @@ struct omap4_keypad { bool no_autorepeat; u64 keys; unsigned short *keymap; + struct clk *fck; }; static int kbd_readl(struct omap4_keypad *keypad_data, u32 offset) @@ -209,6 +211,10 @@ static int omap4_keypad_open(struct input_dev *input) if (error) return error; + error = clk_prepare_enable(keypad_data->fck); + if (error) + goto out; + disable_irq(keypad_data->irq); kbd_writel(keypad_data, OMAP4_KBD_CTRL, @@ -226,10 +232,11 @@ static int omap4_keypad_open(struct input_dev *input) enable_irq(keypad_data->irq); +out: pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); - return 0; + return error; } static void omap4_keypad_stop(struct omap4_keypad *keypad_data) @@ -258,6 +265,7 @@ static void omap4_keypad_close(struct input_dev *input) disable_irq(keypad_data->irq); omap4_keypad_stop(keypad_data); enable_irq(keypad_data->irq); + clk_disable_unprepare(keypad_data->fck); pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); @@ -356,6 +364,11 @@ static int omap4_keypad_probe(struct platform_device *pdev) } keypad_data->irq = irq; + keypad_data->fck = devm_clk_get(&pdev->dev, "fck"); + if (IS_ERR(keypad_data->fck)) + return dev_err_probe(&pdev->dev, PTR_ERR(keypad_data->fck), + "unable to get fck"); + mutex_init(&keypad_data->lock); platform_set_drvdata(pdev, keypad_data); diff --git a/drivers/input/keyboard/qt1050.c b/drivers/input/keyboard/qt1050.c index 6953097db445..b51dfcd76038 100644 --- a/drivers/input/keyboard/qt1050.c +++ b/drivers/input/keyboard/qt1050.c @@ -213,7 +213,7 @@ static struct regmap_config qt1050_regmap_config = { .val_bits = 8, .max_register = QT1050_RES_CAL, - .cache_type = REGCACHE_RBTREE, + .cache_type = REGCACHE_MAPLE, .wr_table = &qt1050_writeable_table, .rd_table = &qt1050_readable_table, diff --git a/drivers/input/keyboard/tca6416-keypad.c b/drivers/input/keyboard/tca6416-keypad.c index 8af59ced1ec2..677bc4baa5d1 100644 --- a/drivers/input/keyboard/tca6416-keypad.c +++ b/drivers/input/keyboard/tca6416-keypad.c @@ -14,7 +14,6 @@ #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/workqueue.h> -#include <linux/gpio.h> #include <linux/i2c.h> #include <linux/input.h> #include <linux/tca6416_keypad.h> diff --git a/drivers/input/misc/da9063_onkey.c b/drivers/input/misc/da9063_onkey.c index 74808bae326a..c338765e0ecd 100644 --- a/drivers/input/misc/da9063_onkey.c +++ b/drivers/input/misc/da9063_onkey.c @@ -9,11 +9,12 @@ #include <linux/errno.h> #include <linux/input.h> #include <linux/interrupt.h> +#include <linux/mod_devicetable.h> #include <linux/platform_device.h> #include <linux/pm_wakeirq.h> +#include <linux/property.h> #include <linux/workqueue.h> #include <linux/regmap.h> -#include <linux/of.h> #include <linux/mfd/da9063/core.h> #include <linux/mfd/da9063/registers.h> #include <linux/mfd/da9062/core.h> @@ -74,13 +75,6 @@ static const struct da906x_chip_config da9062_regs = { .name = "da9062-onkey", }; -static const struct of_device_id da9063_compatible_reg_id_table[] = { - { .compatible = "dlg,da9063-onkey", .data = &da9063_regs }, - { .compatible = "dlg,da9062-onkey", .data = &da9062_regs }, - { }, -}; -MODULE_DEVICE_TABLE(of, da9063_compatible_reg_id_table); - static void da9063_poll_on(struct work_struct *work) { struct da9063_onkey *onkey = container_of(work, @@ -187,56 +181,43 @@ static irqreturn_t da9063_onkey_irq_handler(int irq, void *data) static int da9063_onkey_probe(struct platform_device *pdev) { struct da9063_onkey *onkey; - const struct of_device_id *match; - int irq; int error; - - match = of_match_node(da9063_compatible_reg_id_table, - pdev->dev.of_node); - if (!match) - return -ENXIO; + int irq; onkey = devm_kzalloc(&pdev->dev, sizeof(struct da9063_onkey), GFP_KERNEL); - if (!onkey) { - dev_err(&pdev->dev, "Failed to allocate memory.\n"); + if (!onkey) return -ENOMEM; - } - onkey->config = match->data; + onkey->config = device_get_match_data(&pdev->dev); + if (!onkey->config) + return -ENXIO; + onkey->dev = &pdev->dev; onkey->regmap = dev_get_regmap(pdev->dev.parent, NULL); - if (!onkey->regmap) { - dev_err(&pdev->dev, "Parent regmap unavailable.\n"); - return -ENXIO; - } + if (!onkey->regmap) + return dev_err_probe(&pdev->dev, -ENXIO, + "Parent regmap unavailable.\n"); - onkey->key_power = !of_property_read_bool(pdev->dev.of_node, - "dlg,disable-key-power"); + onkey->key_power = !device_property_read_bool(&pdev->dev, + "dlg,disable-key-power"); onkey->input = devm_input_allocate_device(&pdev->dev); - if (!onkey->input) { - dev_err(&pdev->dev, "Failed to allocated input device.\n"); + if (!onkey->input) return -ENOMEM; - } onkey->input->name = onkey->config->name; snprintf(onkey->phys, sizeof(onkey->phys), "%s/input0", onkey->config->name); onkey->input->phys = onkey->phys; - onkey->input->dev.parent = &pdev->dev; input_set_capability(onkey->input, EV_KEY, KEY_POWER); error = devm_delayed_work_autocancel(&pdev->dev, &onkey->work, da9063_poll_on); - if (error) { - dev_err(&pdev->dev, - "Failed to add cancel poll action: %d\n", - error); + if (error) return error; - } irq = platform_get_irq_byname(pdev, "ONKEY"); if (irq < 0) @@ -246,11 +227,9 @@ static int da9063_onkey_probe(struct platform_device *pdev) NULL, da9063_onkey_irq_handler, IRQF_TRIGGER_LOW | IRQF_ONESHOT, "ONKEY", onkey); - if (error) { - dev_err(&pdev->dev, - "Failed to request IRQ %d: %d\n", irq, error); - return error; - } + if (error) + return dev_err_probe(&pdev->dev, error, + "Failed to allocate onkey IRQ\n"); error = dev_pm_set_wake_irq(&pdev->dev, irq); if (error) @@ -261,15 +240,19 @@ static int da9063_onkey_probe(struct platform_device *pdev) device_init_wakeup(&pdev->dev, true); error = input_register_device(onkey->input); - if (error) { - dev_err(&pdev->dev, - "Failed to register input device: %d\n", error); + if (error) return error; - } return 0; } +static const struct of_device_id da9063_compatible_reg_id_table[] = { + { .compatible = "dlg,da9063-onkey", .data = &da9063_regs }, + { .compatible = "dlg,da9062-onkey", .data = &da9062_regs }, + { } +}; +MODULE_DEVICE_TABLE(of, da9063_compatible_reg_id_table); + static struct platform_driver da9063_onkey_driver = { .probe = da9063_onkey_probe, .driver = { diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c index b2f1292e27ef..6e8cc28debd9 100644 --- a/drivers/input/misc/ims-pcu.c +++ b/drivers/input/misc/ims-pcu.c @@ -1050,7 +1050,7 @@ static ssize_t ims_pcu_attribute_show(struct device *dev, container_of(dattr, struct ims_pcu_attribute, dattr); char *field = (char *)pcu + attr->field_offset; - return scnprintf(buf, PAGE_SIZE, "%.*s\n", attr->field_length, field); + return sysfs_emit(buf, "%.*s\n", attr->field_length, field); } static ssize_t ims_pcu_attribute_store(struct device *dev, @@ -1206,7 +1206,7 @@ ims_pcu_update_firmware_status_show(struct device *dev, struct usb_interface *intf = to_usb_interface(dev); struct ims_pcu *pcu = usb_get_intfdata(intf); - return scnprintf(buf, PAGE_SIZE, "%d\n", pcu->update_firmware_status); + return sysfs_emit(buf, "%d\n", pcu->update_firmware_status); } static DEVICE_ATTR(update_firmware_status, S_IRUGO, @@ -1309,7 +1309,7 @@ static ssize_t ims_pcu_ofn_reg_data_show(struct device *dev, if (error) return error; - return scnprintf(buf, PAGE_SIZE, "%x\n", data); + return sysfs_emit(buf, "%x\n", data); } static ssize_t ims_pcu_ofn_reg_data_store(struct device *dev, @@ -1344,7 +1344,7 @@ static ssize_t ims_pcu_ofn_reg_addr_show(struct device *dev, int error; mutex_lock(&pcu->cmd_mutex); - error = scnprintf(buf, PAGE_SIZE, "%x\n", pcu->ofn_reg_addr); + error = sysfs_emit(buf, "%x\n", pcu->ofn_reg_addr); mutex_unlock(&pcu->cmd_mutex); return error; @@ -1397,7 +1397,7 @@ static ssize_t ims_pcu_ofn_bit_show(struct device *dev, if (error) return error; - return scnprintf(buf, PAGE_SIZE, "%d\n", !!(data & (1 << attr->nr))); + return sysfs_emit(buf, "%d\n", !!(data & (1 << attr->nr))); } static ssize_t ims_pcu_ofn_bit_store(struct device *dev, diff --git a/drivers/input/misc/iqs269a.c b/drivers/input/misc/iqs269a.c index 3c636c75e8a1..cd14ff9f57cf 100644 --- a/drivers/input/misc/iqs269a.c +++ b/drivers/input/misc/iqs269a.c @@ -9,6 +9,7 @@ * axial sliders presented by the device. */ +#include <linux/bits.h> #include <linux/completion.h> #include <linux/delay.h> #include <linux/device.h> @@ -26,6 +27,8 @@ #define IQS269_VER_INFO 0x00 #define IQS269_VER_INFO_PROD_NUM 0x4F +#define IQS269_VER_INFO_FW_NUM_2 0x03 +#define IQS269_VER_INFO_FW_NUM_3 0x10 #define IQS269_SYS_FLAGS 0x02 #define IQS269_SYS_FLAGS_SHOW_RESET BIT(15) @@ -53,6 +56,7 @@ #define IQS269_SYS_SETTINGS_ULP_UPDATE_MASK GENMASK(10, 8) #define IQS269_SYS_SETTINGS_ULP_UPDATE_SHIFT 8 #define IQS269_SYS_SETTINGS_ULP_UPDATE_MAX 7 +#define IQS269_SYS_SETTINGS_SLIDER_SWIPE BIT(7) #define IQS269_SYS_SETTINGS_RESEED_OFFSET BIT(6) #define IQS269_SYS_SETTINGS_EVENT_MODE BIT(5) #define IQS269_SYS_SETTINGS_EVENT_MODE_LP BIT(4) @@ -69,6 +73,7 @@ #define IQS269_FILT_STR_MAX 3 #define IQS269_EVENT_MASK_SYS BIT(6) +#define IQS269_EVENT_MASK_GESTURE BIT(3) #define IQS269_EVENT_MASK_DEEP BIT(2) #define IQS269_EVENT_MASK_TOUCH BIT(1) #define IQS269_EVENT_MASK_PROX BIT(0) @@ -97,6 +102,15 @@ #define IQS269_MISC_B_TRACKING_UI_ENABLE BIT(4) #define IQS269_MISC_B_FILT_STR_SLIDER GENMASK(1, 0) +#define IQS269_TOUCH_HOLD_SLIDER_SEL 0x89 +#define IQS269_TOUCH_HOLD_DEFAULT 0x14 +#define IQS269_TOUCH_HOLD_MS_MIN 256 +#define IQS269_TOUCH_HOLD_MS_MAX 65280 + +#define IQS269_TIMEOUT_TAP_MS_MAX 4080 +#define IQS269_TIMEOUT_SWIPE_MS_MAX 4080 +#define IQS269_THRESH_SWIPE_MAX 255 + #define IQS269_CHx_ENG_A_MEAS_CAP_SIZE BIT(15) #define IQS269_CHx_ENG_A_RX_GND_INACTIVE BIT(13) #define IQS269_CHx_ENG_A_LOCAL_CAP_SIZE BIT(12) @@ -142,6 +156,10 @@ #define IQS269_MAX_REG 0xFF +#define IQS269_OTP_OPTION_DEFAULT 0x00 +#define IQS269_OTP_OPTION_TWS 0xD0 +#define IQS269_OTP_OPTION_HOLD BIT(7) + #define IQS269_NUM_CH 8 #define IQS269_NUM_SL 2 @@ -175,6 +193,20 @@ enum iqs269_event_id { IQS269_EVENT_DEEP_UP, }; +enum iqs269_slider_id { + IQS269_SLIDER_NONE, + IQS269_SLIDER_KEY, + IQS269_SLIDER_RAW, +}; + +enum iqs269_gesture_id { + IQS269_GESTURE_TAP, + IQS269_GESTURE_HOLD, + IQS269_GESTURE_FLICK_POS, + IQS269_GESTURE_FLICK_NEG, + IQS269_NUM_GESTURES, +}; + struct iqs269_switch_desc { unsigned int code; bool enabled; @@ -234,7 +266,7 @@ struct iqs269_ver_info { u8 prod_num; u8 sw_num; u8 hw_num; - u8 padding; + u8 fw_num; } __packed; struct iqs269_ch_reg { @@ -285,16 +317,42 @@ struct iqs269_private { struct regmap *regmap; struct mutex lock; struct iqs269_switch_desc switches[ARRAY_SIZE(iqs269_events)]; + struct iqs269_ver_info ver_info; struct iqs269_sys_reg sys_reg; struct completion ati_done; struct input_dev *keypad; struct input_dev *slider[IQS269_NUM_SL]; unsigned int keycode[ARRAY_SIZE(iqs269_events) * IQS269_NUM_CH]; + unsigned int sl_code[IQS269_NUM_SL][IQS269_NUM_GESTURES]; + unsigned int otp_option; unsigned int ch_num; bool hall_enable; bool ati_current; }; +static enum iqs269_slider_id iqs269_slider_type(struct iqs269_private *iqs269, + int slider_num) +{ + int i; + + /* + * Slider 1 is unavailable if the touch-and-hold option is enabled via + * OTP. In that case, the channel selection register is repurposed for + * the touch-and-hold timer ceiling. + */ + if (slider_num && (iqs269->otp_option & IQS269_OTP_OPTION_HOLD)) + return IQS269_SLIDER_NONE; + + if (!iqs269->sys_reg.slider_select[slider_num]) + return IQS269_SLIDER_NONE; + + for (i = 0; i < IQS269_NUM_GESTURES; i++) + if (iqs269->sl_code[slider_num][i] != KEY_RESERVED) + return IQS269_SLIDER_KEY; + + return IQS269_SLIDER_RAW; +} + static int iqs269_ati_mode_set(struct iqs269_private *iqs269, unsigned int ch_num, unsigned int mode) { @@ -525,7 +583,8 @@ static int iqs269_parse_chan(struct iqs269_private *iqs269, if (fwnode_property_present(ch_node, "azoteq,slider0-select")) iqs269->sys_reg.slider_select[0] |= BIT(reg); - if (fwnode_property_present(ch_node, "azoteq,slider1-select")) + if (fwnode_property_present(ch_node, "azoteq,slider1-select") && + !(iqs269->otp_option & IQS269_OTP_OPTION_HOLD)) iqs269->sys_reg.slider_select[1] |= BIT(reg); ch_reg = &iqs269->sys_reg.ch_reg[reg]; @@ -950,7 +1009,43 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269) sys_reg->blocking = 0; sys_reg->slider_select[0] = 0; - sys_reg->slider_select[1] = 0; + + /* + * If configured via OTP to do so, the device asserts a pulse on the + * GPIO4 pin for approximately 60 ms once a selected channel is held + * in a state of touch for a configurable length of time. + * + * In that case, the register used for slider 1 channel selection is + * repurposed for the touch-and-hold timer ceiling. + */ + if (iqs269->otp_option & IQS269_OTP_OPTION_HOLD) { + if (!device_property_read_u32(&client->dev, + "azoteq,touch-hold-ms", &val)) { + if (val < IQS269_TOUCH_HOLD_MS_MIN || + val > IQS269_TOUCH_HOLD_MS_MAX) { + dev_err(&client->dev, + "Invalid touch-and-hold ceiling: %u\n", + val); + return -EINVAL; + } + + sys_reg->slider_select[1] = val / 256; + } else if (iqs269->ver_info.fw_num < IQS269_VER_INFO_FW_NUM_3) { + /* + * The default touch-and-hold timer ceiling initially + * read from early revisions of silicon is invalid if + * the device experienced a soft reset between power- + * on and the read operation. + * + * To protect against this case, explicitly cache the + * default value so that it is restored each time the + * device is re-initialized. + */ + sys_reg->slider_select[1] = IQS269_TOUCH_HOLD_DEFAULT; + } + } else { + sys_reg->slider_select[1] = 0; + } sys_reg->event_mask = ~((u8)IQS269_EVENT_MASK_SYS); @@ -1004,6 +1099,76 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269) general |= (val << IQS269_SYS_SETTINGS_ULP_UPDATE_SHIFT); } + if (device_property_present(&client->dev, "linux,keycodes")) { + int scale = 1; + int count = device_property_count_u32(&client->dev, + "linux,keycodes"); + if (count > IQS269_NUM_GESTURES * IQS269_NUM_SL) { + dev_err(&client->dev, "Too many keycodes present\n"); + return -EINVAL; + } else if (count < 0) { + dev_err(&client->dev, "Failed to count keycodes: %d\n", + count); + return count; + } + + error = device_property_read_u32_array(&client->dev, + "linux,keycodes", + *iqs269->sl_code, count); + if (error) { + dev_err(&client->dev, "Failed to read keycodes: %d\n", + error); + return error; + } + + if (device_property_present(&client->dev, + "azoteq,gesture-swipe")) + general |= IQS269_SYS_SETTINGS_SLIDER_SWIPE; + + /* + * Early revisions of silicon use a more granular step size for + * tap and swipe gesture timeouts; scale them appropriately. + */ + if (iqs269->ver_info.fw_num < IQS269_VER_INFO_FW_NUM_3) + scale = 4; + + if (!device_property_read_u32(&client->dev, + "azoteq,timeout-tap-ms", &val)) { + if (val > IQS269_TIMEOUT_TAP_MS_MAX / scale) { + dev_err(&client->dev, "Invalid timeout: %u\n", + val); + return -EINVAL; + } + + sys_reg->timeout_tap = val / (16 / scale); + } + + if (!device_property_read_u32(&client->dev, + "azoteq,timeout-swipe-ms", + &val)) { + if (val > IQS269_TIMEOUT_SWIPE_MS_MAX / scale) { + dev_err(&client->dev, "Invalid timeout: %u\n", + val); + return -EINVAL; + } + + sys_reg->timeout_swipe = val / (16 / scale); + } + + if (!device_property_read_u32(&client->dev, + "azoteq,thresh-swipe", &val)) { + if (val > IQS269_THRESH_SWIPE_MAX) { + dev_err(&client->dev, "Invalid threshold: %u\n", + val); + return -EINVAL; + } + + sys_reg->thresh_swipe = val; + } + + sys_reg->event_mask &= ~IQS269_EVENT_MASK_GESTURE; + } + general &= ~IQS269_SYS_SETTINGS_RESEED_OFFSET; if (device_property_present(&client->dev, "azoteq,reseed-offset")) general |= IQS269_SYS_SETTINGS_RESEED_OFFSET; @@ -1012,10 +1177,11 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269) /* * As per the datasheet, enable streaming during normal-power mode if - * either slider is in use. In that case, the device returns to event - * mode during low-power mode. + * raw coordinates will be read from either slider. In that case, the + * device returns to event mode during low-power mode. */ - if (sys_reg->slider_select[0] || sys_reg->slider_select[1]) + if (iqs269_slider_type(iqs269, 0) == IQS269_SLIDER_RAW || + iqs269_slider_type(iqs269, 1) == IQS269_SLIDER_RAW) general |= IQS269_SYS_SETTINGS_EVENT_MODE_LP; general |= IQS269_SYS_SETTINGS_REDO_ATI; @@ -1026,12 +1192,30 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269) return 0; } +static const struct reg_sequence iqs269_tws_init[] = { + { IQS269_TOUCH_HOLD_SLIDER_SEL, IQS269_TOUCH_HOLD_DEFAULT }, + { 0xF0, 0x580F }, + { 0xF0, 0x59EF }, +}; + static int iqs269_dev_init(struct iqs269_private *iqs269) { int error; mutex_lock(&iqs269->lock); + /* + * Early revisions of silicon require the following workaround in order + * to restore any OTP-enabled functionality after a soft reset. + */ + if (iqs269->otp_option == IQS269_OTP_OPTION_TWS && + iqs269->ver_info.fw_num < IQS269_VER_INFO_FW_NUM_3) { + error = regmap_multi_reg_write(iqs269->regmap, iqs269_tws_init, + ARRAY_SIZE(iqs269_tws_init)); + if (error) + goto err_mutex; + } + error = regmap_update_bits(iqs269->regmap, IQS269_HALL_UI, IQS269_HALL_UI_ENABLE, iqs269->hall_enable ? ~0 : 0); @@ -1106,19 +1290,37 @@ static int iqs269_input_init(struct iqs269_private *iqs269) } for (i = 0; i < IQS269_NUM_SL; i++) { - if (!iqs269->sys_reg.slider_select[i]) + if (iqs269_slider_type(iqs269, i) == IQS269_SLIDER_NONE) continue; iqs269->slider[i] = devm_input_allocate_device(&client->dev); if (!iqs269->slider[i]) return -ENOMEM; + iqs269->slider[i]->keycodemax = ARRAY_SIZE(iqs269->sl_code[i]); + iqs269->slider[i]->keycode = iqs269->sl_code[i]; + iqs269->slider[i]->keycodesize = sizeof(**iqs269->sl_code); + iqs269->slider[i]->name = i ? "iqs269a_slider_1" : "iqs269a_slider_0"; iqs269->slider[i]->id.bustype = BUS_I2C; - input_set_capability(iqs269->slider[i], EV_KEY, BTN_TOUCH); - input_set_abs_params(iqs269->slider[i], ABS_X, 0, 255, 0, 0); + for (j = 0; j < IQS269_NUM_GESTURES; j++) + if (iqs269->sl_code[i][j] != KEY_RESERVED) + input_set_capability(iqs269->slider[i], EV_KEY, + iqs269->sl_code[i][j]); + + /* + * Present the slider as a narrow trackpad if one or more chan- + * nels have been selected to participate, but no gestures have + * been mapped to a keycode. + */ + if (iqs269_slider_type(iqs269, i) == IQS269_SLIDER_RAW) { + input_set_capability(iqs269->slider[i], + EV_KEY, BTN_TOUCH); + input_set_abs_params(iqs269->slider[i], + ABS_X, 0, 255, 0, 0); + } error = input_register_device(iqs269->slider[i]); if (error) { @@ -1167,28 +1369,62 @@ static int iqs269_report(struct iqs269_private *iqs269) if (be16_to_cpu(flags.system) & IQS269_SYS_FLAGS_IN_ATI) return 0; - error = regmap_raw_read(iqs269->regmap, IQS269_SLIDER_X, slider_x, - sizeof(slider_x)); - if (error) { - dev_err(&client->dev, "Failed to read slider position: %d\n", - error); - return error; + if (iqs269_slider_type(iqs269, 0) == IQS269_SLIDER_RAW || + iqs269_slider_type(iqs269, 1) == IQS269_SLIDER_RAW) { + error = regmap_raw_read(iqs269->regmap, IQS269_SLIDER_X, + slider_x, sizeof(slider_x)); + if (error) { + dev_err(&client->dev, + "Failed to read slider position: %d\n", error); + return error; + } } for (i = 0; i < IQS269_NUM_SL; i++) { - if (!iqs269->sys_reg.slider_select[i]) + flags.gesture >>= (i * IQS269_NUM_GESTURES); + + switch (iqs269_slider_type(iqs269, i)) { + case IQS269_SLIDER_NONE: continue; - /* - * Report BTN_TOUCH if any channel that participates in the - * slider is in a state of touch. - */ - if (flags.states[IQS269_ST_OFFS_TOUCH] & - iqs269->sys_reg.slider_select[i]) { - input_report_key(iqs269->slider[i], BTN_TOUCH, 1); - input_report_abs(iqs269->slider[i], ABS_X, slider_x[i]); - } else { - input_report_key(iqs269->slider[i], BTN_TOUCH, 0); + case IQS269_SLIDER_KEY: + for (j = 0; j < IQS269_NUM_GESTURES; j++) + input_report_key(iqs269->slider[i], + iqs269->sl_code[i][j], + flags.gesture & BIT(j)); + + if (!(flags.gesture & (BIT(IQS269_GESTURE_FLICK_NEG) | + BIT(IQS269_GESTURE_FLICK_POS) | + BIT(IQS269_GESTURE_TAP)))) + break; + + input_sync(iqs269->slider[i]); + + /* + * Momentary gestures are followed by a complementary + * release cycle so as to emulate a full keystroke. + */ + for (j = 0; j < IQS269_NUM_GESTURES; j++) + if (j != IQS269_GESTURE_HOLD) + input_report_key(iqs269->slider[i], + iqs269->sl_code[i][j], + 0); + break; + + case IQS269_SLIDER_RAW: + /* + * The slider is considered to be in a state of touch + * if any selected channels are in a state of touch. + */ + state = flags.states[IQS269_ST_OFFS_TOUCH]; + state &= iqs269->sys_reg.slider_select[i]; + + input_report_key(iqs269->slider[i], BTN_TOUCH, state); + + if (state) + input_report_abs(iqs269->slider[i], + ABS_X, slider_x[i]); + break; } input_sync(iqs269->slider[i]); @@ -1286,7 +1522,7 @@ static ssize_t counts_show(struct device *dev, if (error) return error; - return scnprintf(buf, PAGE_SIZE, "%u\n", le16_to_cpu(counts)); + return sysfs_emit(buf, "%u\n", le16_to_cpu(counts)); } static ssize_t hall_bin_show(struct device *dev, @@ -1324,7 +1560,7 @@ static ssize_t hall_bin_show(struct device *dev, return -EINVAL; } - return scnprintf(buf, PAGE_SIZE, "%u\n", val); + return sysfs_emit(buf, "%u\n", val); } static ssize_t hall_enable_show(struct device *dev, @@ -1332,7 +1568,7 @@ static ssize_t hall_enable_show(struct device *dev, { struct iqs269_private *iqs269 = dev_get_drvdata(dev); - return scnprintf(buf, PAGE_SIZE, "%u\n", iqs269->hall_enable); + return sysfs_emit(buf, "%u\n", iqs269->hall_enable); } static ssize_t hall_enable_store(struct device *dev, @@ -1362,7 +1598,7 @@ static ssize_t ch_number_show(struct device *dev, { struct iqs269_private *iqs269 = dev_get_drvdata(dev); - return scnprintf(buf, PAGE_SIZE, "%u\n", iqs269->ch_num); + return sysfs_emit(buf, "%u\n", iqs269->ch_num); } static ssize_t ch_number_store(struct device *dev, @@ -1391,8 +1627,7 @@ static ssize_t rx_enable_show(struct device *dev, struct iqs269_private *iqs269 = dev_get_drvdata(dev); struct iqs269_ch_reg *ch_reg = iqs269->sys_reg.ch_reg; - return scnprintf(buf, PAGE_SIZE, "%u\n", - ch_reg[iqs269->ch_num].rx_enable); + return sysfs_emit(buf, "%u\n", ch_reg[iqs269->ch_num].rx_enable); } static ssize_t rx_enable_store(struct device *dev, @@ -1432,7 +1667,7 @@ static ssize_t ati_mode_show(struct device *dev, if (error) return error; - return scnprintf(buf, PAGE_SIZE, "%u\n", val); + return sysfs_emit(buf, "%u\n", val); } static ssize_t ati_mode_store(struct device *dev, @@ -1465,7 +1700,7 @@ static ssize_t ati_base_show(struct device *dev, if (error) return error; - return scnprintf(buf, PAGE_SIZE, "%u\n", val); + return sysfs_emit(buf, "%u\n", val); } static ssize_t ati_base_store(struct device *dev, @@ -1498,7 +1733,7 @@ static ssize_t ati_target_show(struct device *dev, if (error) return error; - return scnprintf(buf, PAGE_SIZE, "%u\n", val); + return sysfs_emit(buf, "%u\n", val); } static ssize_t ati_target_store(struct device *dev, @@ -1525,9 +1760,9 @@ static ssize_t ati_trigger_show(struct device *dev, { struct iqs269_private *iqs269 = dev_get_drvdata(dev); - return scnprintf(buf, PAGE_SIZE, "%u\n", - iqs269->ati_current && - completion_done(&iqs269->ati_done)); + return sysfs_emit(buf, "%u\n", + iqs269->ati_current && + completion_done(&iqs269->ati_done)); } static ssize_t ati_trigger_store(struct device *dev, @@ -1596,7 +1831,6 @@ static const struct regmap_config iqs269_regmap_config = { static int iqs269_probe(struct i2c_client *client) { - struct iqs269_ver_info ver_info; struct iqs269_private *iqs269; int error; @@ -1618,14 +1852,16 @@ static int iqs269_probe(struct i2c_client *client) mutex_init(&iqs269->lock); init_completion(&iqs269->ati_done); - error = regmap_raw_read(iqs269->regmap, IQS269_VER_INFO, &ver_info, - sizeof(ver_info)); + iqs269->otp_option = (uintptr_t)device_get_match_data(&client->dev); + + error = regmap_raw_read(iqs269->regmap, IQS269_VER_INFO, + &iqs269->ver_info, sizeof(iqs269->ver_info)); if (error) return error; - if (ver_info.prod_num != IQS269_VER_INFO_PROD_NUM) { + if (iqs269->ver_info.prod_num != IQS269_VER_INFO_PROD_NUM) { dev_err(&client->dev, "Unrecognized product number: 0x%02X\n", - ver_info.prod_num); + iqs269->ver_info.prod_num); return -EINVAL; } @@ -1728,7 +1964,18 @@ static int iqs269_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(iqs269_pm, iqs269_suspend, iqs269_resume); static const struct of_device_id iqs269_of_match[] = { - { .compatible = "azoteq,iqs269a" }, + { + .compatible = "azoteq,iqs269a", + .data = (void *)IQS269_OTP_OPTION_DEFAULT, + }, + { + .compatible = "azoteq,iqs269a-00", + .data = (void *)IQS269_OTP_OPTION_DEFAULT, + }, + { + .compatible = "azoteq,iqs269a-d0", + .data = (void *)IQS269_OTP_OPTION_TWS, + }, { } }; MODULE_DEVICE_TABLE(of, iqs269_of_match); diff --git a/drivers/input/misc/max77693-haptic.c b/drivers/input/misc/max77693-haptic.c index 80f4416ffe2f..0e646f1b257b 100644 --- a/drivers/input/misc/max77693-haptic.c +++ b/drivers/input/misc/max77693-haptic.c @@ -307,7 +307,7 @@ static int max77693_haptic_probe(struct platform_device *pdev) haptic->suspend_state = false; /* Variant-specific init */ - haptic->dev_type = platform_get_device_id(pdev)->driver_data; + haptic->dev_type = max77693->type; switch (haptic->dev_type) { case TYPE_MAX77693: haptic->regmap_haptic = max77693->regmap_haptic; @@ -406,16 +406,24 @@ static DEFINE_SIMPLE_DEV_PM_OPS(max77693_haptic_pm_ops, max77693_haptic_resume); static const struct platform_device_id max77693_haptic_id[] = { - { "max77693-haptic", TYPE_MAX77693 }, - { "max77843-haptic", TYPE_MAX77843 }, + { "max77693-haptic", }, + { "max77843-haptic", }, {}, }; MODULE_DEVICE_TABLE(platform, max77693_haptic_id); +static const struct of_device_id of_max77693_haptic_dt_match[] = { + { .compatible = "maxim,max77693-haptic", }, + { .compatible = "maxim,max77843-haptic", }, + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, of_max77693_haptic_dt_match); + static struct platform_driver max77693_haptic_driver = { .driver = { .name = "max77693-haptic", .pm = pm_sleep_ptr(&max77693_haptic_pm_ops), + .of_match_table = of_max77693_haptic_dt_match, }, .probe = max77693_haptic_probe, .id_table = max77693_haptic_id, diff --git a/drivers/input/mouse/cyapa.c b/drivers/input/mouse/cyapa.c index a84098448f5b..5979deabe23d 100644 --- a/drivers/input/mouse/cyapa.c +++ b/drivers/input/mouse/cyapa.c @@ -756,16 +756,16 @@ static ssize_t cyapa_show_suspend_scanrate(struct device *dev, switch (pwr_cmd) { case PWR_MODE_BTN_ONLY: - len = scnprintf(buf, PAGE_SIZE, "%s\n", BTN_ONLY_MODE_NAME); + len = sysfs_emit(buf, "%s\n", BTN_ONLY_MODE_NAME); break; case PWR_MODE_OFF: - len = scnprintf(buf, PAGE_SIZE, "%s\n", OFF_MODE_NAME); + len = sysfs_emit(buf, "%s\n", OFF_MODE_NAME); break; default: - len = scnprintf(buf, PAGE_SIZE, "%u\n", - cyapa->gen == CYAPA_GEN3 ? + len = sysfs_emit(buf, "%u\n", + cyapa->gen == CYAPA_GEN3 ? cyapa_pwr_cmd_to_sleep_time(pwr_cmd) : sleep_time); break; @@ -877,8 +877,8 @@ static ssize_t cyapa_show_rt_suspend_scanrate(struct device *dev, mutex_unlock(&cyapa->state_sync_lock); - return scnprintf(buf, PAGE_SIZE, "%u\n", - cyapa->gen == CYAPA_GEN3 ? + return sysfs_emit(buf, "%u\n", + cyapa->gen == CYAPA_GEN3 ? cyapa_pwr_cmd_to_sleep_time(pwr_cmd) : sleep_time); } @@ -988,8 +988,8 @@ static ssize_t cyapa_show_fm_ver(struct device *dev, error = mutex_lock_interruptible(&cyapa->state_sync_lock); if (error) return error; - error = scnprintf(buf, PAGE_SIZE, "%d.%d\n", cyapa->fw_maj_ver, - cyapa->fw_min_ver); + error = sysfs_emit(buf, "%d.%d\n", + cyapa->fw_maj_ver, cyapa->fw_min_ver); mutex_unlock(&cyapa->state_sync_lock); return error; } @@ -1004,7 +1004,7 @@ static ssize_t cyapa_show_product_id(struct device *dev, error = mutex_lock_interruptible(&cyapa->state_sync_lock); if (error) return error; - size = scnprintf(buf, PAGE_SIZE, "%s\n", cyapa->product_id); + size = sysfs_emit(buf, "%s\n", cyapa->product_id); mutex_unlock(&cyapa->state_sync_lock); return size; } @@ -1209,8 +1209,8 @@ static ssize_t cyapa_show_mode(struct device *dev, if (error) return error; - size = scnprintf(buf, PAGE_SIZE, "gen%d %s\n", - cyapa->gen, cyapa_state_to_string(cyapa)); + size = sysfs_emit(buf, "gen%d %s\n", + cyapa->gen, cyapa_state_to_string(cyapa)); mutex_unlock(&cyapa->state_sync_lock); return size; diff --git a/drivers/input/mouse/cyapa_gen3.c b/drivers/input/mouse/cyapa_gen3.c index a97f4acb6452..60c83bc71d84 100644 --- a/drivers/input/mouse/cyapa_gen3.c +++ b/drivers/input/mouse/cyapa_gen3.c @@ -860,7 +860,7 @@ static ssize_t cyapa_gen3_show_baseline(struct device *dev, dev_dbg(dev, "Baseline report successful. Max: %d Min: %d\n", max_baseline, min_baseline); - ret = scnprintf(buf, PAGE_SIZE, "%d %d\n", max_baseline, min_baseline); + ret = sysfs_emit(buf, "%d %d\n", max_baseline, min_baseline); out: return ret; diff --git a/drivers/input/mouse/cyapa_gen5.c b/drivers/input/mouse/cyapa_gen5.c index abf42f77b4c5..2e6bcb07257e 100644 --- a/drivers/input/mouse/cyapa_gen5.c +++ b/drivers/input/mouse/cyapa_gen5.c @@ -2418,12 +2418,12 @@ resume_scanning: return resume_error ? resume_error : error; /* 12. Output data strings */ - size = scnprintf(buf, PAGE_SIZE, "%d %d %d %d %d %d %d %d %d %d %d ", + size = sysfs_emit(buf, "%d %d %d %d %d %d %d %d %d %d %d ", gidac_mutual_min, gidac_mutual_max, gidac_mutual_ave, lidac_mutual_min, lidac_mutual_max, lidac_mutual_ave, gidac_self_rx, gidac_self_tx, lidac_self_min, lidac_self_max, lidac_self_ave); - size += scnprintf(buf + size, PAGE_SIZE - size, + size += sysfs_emit_at(buf, size, "%d %d %d %d %d %d %d %d %d %d %d %d %d %d %d %d %d %d\n", raw_cap_mutual_min, raw_cap_mutual_max, raw_cap_mutual_ave, raw_cap_self_min, raw_cap_self_max, raw_cap_self_ave, diff --git a/drivers/input/mouse/cyapa_gen6.c b/drivers/input/mouse/cyapa_gen6.c index 0caaf3e64215..4ffe08fee10c 100644 --- a/drivers/input/mouse/cyapa_gen6.c +++ b/drivers/input/mouse/cyapa_gen6.c @@ -629,14 +629,14 @@ static ssize_t cyapa_gen6_show_baseline(struct device *dev, if (error) goto resume_scanning; - size = scnprintf(buf, PAGE_SIZE, "%d %d %d %d %d %d ", - data[0], /* RX Attenuator Mutual */ - data[1], /* IDAC Mutual */ - data[2], /* RX Attenuator Self RX */ - data[3], /* IDAC Self RX */ - data[4], /* RX Attenuator Self TX */ - data[5] /* IDAC Self TX */ - ); + size = sysfs_emit(buf, "%d %d %d %d %d %d ", + data[0], /* RX Attenuator Mutual */ + data[1], /* IDAC Mutual */ + data[2], /* RX Attenuator Self RX */ + data[3], /* IDAC Self RX */ + data[4], /* RX Attenuator Self TX */ + data[5] /* IDAC Self TX */ + ); /* 3. Read Attenuator Trim. */ data_len = sizeof(data); @@ -648,8 +648,8 @@ static ssize_t cyapa_gen6_show_baseline(struct device *dev, /* set attenuator trim values. */ for (i = 0; i < data_len; i++) - size += scnprintf(buf + size, PAGE_SIZE - size, "%d ", data[i]); - size += scnprintf(buf + size, PAGE_SIZE - size, "\n"); + size += sysfs_emit_at(buf, size, "%d ", data[i]); + size += sysfs_emit_at(buf, size, "\n"); resume_scanning: /* 4. Resume Scanning*/ diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index 148a601396f9..8a72c200ccb5 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -572,7 +572,7 @@ static ssize_t elan_sysfs_read_fw_checksum(struct device *dev, struct i2c_client *client = to_i2c_client(dev); struct elan_tp_data *data = i2c_get_clientdata(client); - return sprintf(buf, "0x%04x\n", data->fw_checksum); + return sysfs_emit(buf, "0x%04x\n", data->fw_checksum); } static ssize_t elan_sysfs_read_product_id(struct device *dev, @@ -582,8 +582,8 @@ static ssize_t elan_sysfs_read_product_id(struct device *dev, struct i2c_client *client = to_i2c_client(dev); struct elan_tp_data *data = i2c_get_clientdata(client); - return sprintf(buf, ETP_PRODUCT_ID_FORMAT_STRING "\n", - data->product_id); + return sysfs_emit(buf, ETP_PRODUCT_ID_FORMAT_STRING "\n", + data->product_id); } static ssize_t elan_sysfs_read_fw_ver(struct device *dev, @@ -593,7 +593,7 @@ static ssize_t elan_sysfs_read_fw_ver(struct device *dev, struct i2c_client *client = to_i2c_client(dev); struct elan_tp_data *data = i2c_get_clientdata(client); - return sprintf(buf, "%d.0\n", data->fw_version); + return sysfs_emit(buf, "%d.0\n", data->fw_version); } static ssize_t elan_sysfs_read_sm_ver(struct device *dev, @@ -603,7 +603,7 @@ static ssize_t elan_sysfs_read_sm_ver(struct device *dev, struct i2c_client *client = to_i2c_client(dev); struct elan_tp_data *data = i2c_get_clientdata(client); - return sprintf(buf, "%d.0\n", data->sm_version); + return sysfs_emit(buf, "%d.0\n", data->sm_version); } static ssize_t elan_sysfs_read_iap_ver(struct device *dev, @@ -613,7 +613,7 @@ static ssize_t elan_sysfs_read_iap_ver(struct device *dev, struct i2c_client *client = to_i2c_client(dev); struct elan_tp_data *data = i2c_get_clientdata(client); - return sprintf(buf, "%d.0\n", data->iap_version); + return sysfs_emit(buf, "%d.0\n", data->iap_version); } static ssize_t elan_sysfs_update_fw(struct device *dev, @@ -754,7 +754,7 @@ static ssize_t elan_sysfs_read_mode(struct device *dev, if (error) return error; - return sprintf(buf, "%d\n", (int)mode); + return sysfs_emit(buf, "%d\n", (int)mode); } static DEVICE_ATTR(product_id, S_IRUGO, elan_sysfs_read_product_id, NULL); @@ -858,7 +858,7 @@ static ssize_t min_show(struct device *dev, goto out; } - retval = snprintf(buf, PAGE_SIZE, "%d", data->min_baseline); + retval = sysfs_emit(buf, "%d", data->min_baseline); out: mutex_unlock(&data->sysfs_mutex); @@ -881,7 +881,7 @@ static ssize_t max_show(struct device *dev, goto out; } - retval = snprintf(buf, PAGE_SIZE, "%d", data->max_baseline); + retval = sysfs_emit(buf, "%d", data->max_baseline); out: mutex_unlock(&data->sysfs_mutex); diff --git a/drivers/input/mouse/navpoint.c b/drivers/input/mouse/navpoint.c index c00dc1275da2..ba757783c258 100644 --- a/drivers/input/mouse/navpoint.c +++ b/drivers/input/mouse/navpoint.c @@ -10,7 +10,7 @@ #include <linux/platform_device.h> #include <linux/clk.h> #include <linux/delay.h> -#include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/input.h> #include <linux/input/navpoint.h> #include <linux/interrupt.h> @@ -32,7 +32,7 @@ struct navpoint { struct ssp_device *ssp; struct input_dev *input; struct device *dev; - int gpio; + struct gpio_desc *gpiod; int index; u8 data[1 + HEADER_LENGTH(0xff)]; }; @@ -170,16 +170,14 @@ static void navpoint_up(struct navpoint *navpoint) dev_err(navpoint->dev, "timeout waiting for SSSR[CSS] to clear\n"); - if (gpio_is_valid(navpoint->gpio)) - gpio_set_value(navpoint->gpio, 1); + gpiod_set_value(navpoint->gpiod, 1); } static void navpoint_down(struct navpoint *navpoint) { struct ssp_device *ssp = navpoint->ssp; - if (gpio_is_valid(navpoint->gpio)) - gpio_set_value(navpoint->gpio, 0); + gpiod_set_value(navpoint->gpiod, 0); pxa_ssp_write_reg(ssp, SSCR0, 0); @@ -216,18 +214,9 @@ static int navpoint_probe(struct platform_device *pdev) return -EINVAL; } - if (gpio_is_valid(pdata->gpio)) { - error = gpio_request_one(pdata->gpio, GPIOF_OUT_INIT_LOW, - "SYNAPTICS_ON"); - if (error) - return error; - } - ssp = pxa_ssp_request(pdata->port, pdev->name); - if (!ssp) { - error = -ENODEV; - goto err_free_gpio; - } + if (!ssp) + return -ENODEV; /* HaRET does not disable devices before jumping into Linux */ if (pxa_ssp_read_reg(ssp, SSCR0) & SSCR0_SSE) { @@ -242,10 +231,18 @@ static int navpoint_probe(struct platform_device *pdev) goto err_free_mem; } + navpoint->gpiod = gpiod_get_optional(&pdev->dev, + NULL, GPIOD_OUT_LOW); + if (IS_ERR(navpoint->gpiod)) { + error = PTR_ERR(navpoint->gpiod); + dev_err(&pdev->dev, "error getting GPIO\n"); + goto err_free_mem; + } + gpiod_set_consumer_name(navpoint->gpiod, "SYNAPTICS_ON"); + navpoint->ssp = ssp; navpoint->input = input; navpoint->dev = &pdev->dev; - navpoint->gpio = pdata->gpio; input->name = pdev->name; input->dev.parent = &pdev->dev; @@ -288,17 +285,12 @@ err_free_mem: input_free_device(input); kfree(navpoint); pxa_ssp_free(ssp); -err_free_gpio: - if (gpio_is_valid(pdata->gpio)) - gpio_free(pdata->gpio); return error; } static void navpoint_remove(struct platform_device *pdev) { - const struct navpoint_platform_data *pdata = - dev_get_platdata(&pdev->dev); struct navpoint *navpoint = platform_get_drvdata(pdev); struct ssp_device *ssp = navpoint->ssp; @@ -308,9 +300,6 @@ static void navpoint_remove(struct platform_device *pdev) kfree(navpoint); pxa_ssp_free(ssp); - - if (gpio_is_valid(pdata->gpio)) - gpio_free(pdata->gpio); } static int navpoint_suspend(struct device *dev) diff --git a/drivers/input/rmi4/rmi_f01.c b/drivers/input/rmi4/rmi_f01.c index d7603c50f864..cc1d4b424640 100644 --- a/drivers/input/rmi4/rmi_f01.c +++ b/drivers/input/rmi4/rmi_f01.c @@ -267,8 +267,7 @@ static ssize_t rmi_driver_manufacturer_id_show(struct device *dev, struct rmi_driver_data *data = dev_get_drvdata(dev); struct f01_data *f01 = dev_get_drvdata(&data->f01_container->dev); - return scnprintf(buf, PAGE_SIZE, "%d\n", - f01->properties.manufacturer_id); + return sysfs_emit(buf, "%d\n", f01->properties.manufacturer_id); } static DEVICE_ATTR(manufacturer_id, 0444, @@ -280,7 +279,7 @@ static ssize_t rmi_driver_dom_show(struct device *dev, struct rmi_driver_data *data = dev_get_drvdata(dev); struct f01_data *f01 = dev_get_drvdata(&data->f01_container->dev); - return scnprintf(buf, PAGE_SIZE, "%s\n", f01->properties.dom); + return sysfs_emit(buf, "%s\n", f01->properties.dom); } static DEVICE_ATTR(date_of_manufacture, 0444, rmi_driver_dom_show, NULL); @@ -292,7 +291,7 @@ static ssize_t rmi_driver_product_id_show(struct device *dev, struct rmi_driver_data *data = dev_get_drvdata(dev); struct f01_data *f01 = dev_get_drvdata(&data->f01_container->dev); - return scnprintf(buf, PAGE_SIZE, "%s\n", f01->properties.product_id); + return sysfs_emit(buf, "%s\n", f01->properties.product_id); } static DEVICE_ATTR(product_id, 0444, rmi_driver_product_id_show, NULL); @@ -304,7 +303,7 @@ static ssize_t rmi_driver_firmware_id_show(struct device *dev, struct rmi_driver_data *data = dev_get_drvdata(dev); struct f01_data *f01 = dev_get_drvdata(&data->f01_container->dev); - return scnprintf(buf, PAGE_SIZE, "%d\n", f01->properties.firmware_id); + return sysfs_emit(buf, "%d\n", f01->properties.firmware_id); } static DEVICE_ATTR(firmware_id, 0444, rmi_driver_firmware_id_show, NULL); @@ -318,8 +317,8 @@ static ssize_t rmi_driver_package_id_show(struct device *dev, u32 package_id = f01->properties.package_id; - return scnprintf(buf, PAGE_SIZE, "%04x.%04x\n", - package_id & 0xffff, (package_id >> 16) & 0xffff); + return sysfs_emit(buf, "%04x.%04x\n", + package_id & 0xffff, (package_id >> 16) & 0xffff); } static DEVICE_ATTR(package_id, 0444, rmi_driver_package_id_show, NULL); diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c index a2c4b3b87f93..542a31448c8f 100644 --- a/drivers/input/touchscreen/atmel_mxt_ts.c +++ b/drivers/input/touchscreen/atmel_mxt_ts.c @@ -2818,8 +2818,8 @@ static ssize_t mxt_fw_version_show(struct device *dev, { struct mxt_data *data = dev_get_drvdata(dev); struct mxt_info *info = data->info; - return scnprintf(buf, PAGE_SIZE, "%u.%u.%02X\n", - info->version >> 4, info->version & 0xf, info->build); + return sysfs_emit(buf, "%u.%u.%02X\n", + info->version >> 4, info->version & 0xf, info->build); } /* Hardware Version is returned as FamilyID.VariantID */ @@ -2828,8 +2828,7 @@ static ssize_t mxt_hw_version_show(struct device *dev, { struct mxt_data *data = dev_get_drvdata(dev); struct mxt_info *info = data->info; - return scnprintf(buf, PAGE_SIZE, "%u.%u\n", - info->family_id, info->variant_id); + return sysfs_emit(buf, "%u.%u\n", info->family_id, info->variant_id); } static ssize_t mxt_show_instance(char *buf, int count, @@ -2839,19 +2838,18 @@ static ssize_t mxt_show_instance(char *buf, int count, int i; if (mxt_obj_instances(object) > 1) - count += scnprintf(buf + count, PAGE_SIZE - count, - "Instance %u\n", instance); + count += sysfs_emit_at(buf, count, "Instance %u\n", instance); for (i = 0; i < mxt_obj_size(object); i++) - count += scnprintf(buf + count, PAGE_SIZE - count, - "\t[%2u]: %02x (%d)\n", i, val[i], val[i]); - count += scnprintf(buf + count, PAGE_SIZE - count, "\n"); + count += sysfs_emit_at(buf, count, "\t[%2u]: %02x (%d)\n", + i, val[i], val[i]); + count += sysfs_emit_at(buf, count, "\n"); return count; } static ssize_t mxt_object_show(struct device *dev, - struct device_attribute *attr, char *buf) + struct device_attribute *attr, char *buf) { struct mxt_data *data = dev_get_drvdata(dev); struct mxt_object *object; @@ -2872,8 +2870,7 @@ static ssize_t mxt_object_show(struct device *dev, if (!mxt_object_readable(object->type)) continue; - count += scnprintf(buf + count, PAGE_SIZE - count, - "T%u:\n", object->type); + count += sysfs_emit_at(buf, count, "T%u:\n", object->type); for (j = 0; j < mxt_obj_instances(object); j++) { u16 size = mxt_obj_size(object); diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index 3e102bcc4a1c..2a1db1134476 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -431,7 +431,7 @@ static ssize_t edt_ft5x06_setting_show(struct device *dev, *field = val; } - count = scnprintf(buf, PAGE_SIZE, "%d\n", val); + count = sysfs_emit(buf, "%d\n", val); out: mutex_unlock(&tsdata->mutex); return error ?: count; diff --git a/drivers/input/touchscreen/hideep.c b/drivers/input/touchscreen/hideep.c index 0f58258306bf..eae90676f4e5 100644 --- a/drivers/input/touchscreen/hideep.c +++ b/drivers/input/touchscreen/hideep.c @@ -928,8 +928,7 @@ static ssize_t hideep_fw_version_show(struct device *dev, ssize_t len; mutex_lock(&ts->dev_mutex); - len = scnprintf(buf, PAGE_SIZE, "%04x\n", - be16_to_cpu(ts->dwz_info.release_ver)); + len = sysfs_emit(buf, "%04x\n", be16_to_cpu(ts->dwz_info.release_ver)); mutex_unlock(&ts->dev_mutex); return len; @@ -943,8 +942,7 @@ static ssize_t hideep_product_id_show(struct device *dev, ssize_t len; mutex_lock(&ts->dev_mutex); - len = scnprintf(buf, PAGE_SIZE, "%04x\n", - be16_to_cpu(ts->dwz_info.product_id)); + len = sysfs_emit(buf, "%04x\n", be16_to_cpu(ts->dwz_info.product_id)); mutex_unlock(&ts->dev_mutex); return len; diff --git a/drivers/input/touchscreen/hycon-hy46xx.c b/drivers/input/touchscreen/hycon-hy46xx.c index d0f257989fd6..2e01d87977c1 100644 --- a/drivers/input/touchscreen/hycon-hy46xx.c +++ b/drivers/input/touchscreen/hycon-hy46xx.c @@ -202,7 +202,7 @@ static ssize_t hycon_hy46xx_setting_show(struct device *dev, *field = val; } - count = scnprintf(buf, PAGE_SIZE, "%d\n", val); + count = sysfs_emit(buf, "%d\n", val); out: mutex_unlock(&tsdata->mutex); diff --git a/drivers/input/touchscreen/ilitek_ts_i2c.c b/drivers/input/touchscreen/ilitek_ts_i2c.c index 90c4934e750a..fc4e39b6651a 100644 --- a/drivers/input/touchscreen/ilitek_ts_i2c.c +++ b/drivers/input/touchscreen/ilitek_ts_i2c.c @@ -512,12 +512,12 @@ static ssize_t firmware_version_show(struct device *dev, struct i2c_client *client = to_i2c_client(dev); struct ilitek_ts_data *ts = i2c_get_clientdata(client); - return scnprintf(buf, PAGE_SIZE, - "fw version: [%02X%02X.%02X%02X.%02X%02X.%02X%02X]\n", - ts->firmware_ver[0], ts->firmware_ver[1], - ts->firmware_ver[2], ts->firmware_ver[3], - ts->firmware_ver[4], ts->firmware_ver[5], - ts->firmware_ver[6], ts->firmware_ver[7]); + return sysfs_emit(buf, + "fw version: [%02X%02X.%02X%02X.%02X%02X.%02X%02X]\n", + ts->firmware_ver[0], ts->firmware_ver[1], + ts->firmware_ver[2], ts->firmware_ver[3], + ts->firmware_ver[4], ts->firmware_ver[5], + ts->firmware_ver[6], ts->firmware_ver[7]); } static DEVICE_ATTR_RO(firmware_version); @@ -527,8 +527,8 @@ static ssize_t product_id_show(struct device *dev, struct i2c_client *client = to_i2c_client(dev); struct ilitek_ts_data *ts = i2c_get_clientdata(client); - return scnprintf(buf, PAGE_SIZE, "product id: [%04X], module: [%s]\n", - ts->mcu_ver, ts->product_id); + return sysfs_emit(buf, "product id: [%04X], module: [%s]\n", + ts->mcu_ver, ts->product_id); } static DEVICE_ATTR_RO(product_id); diff --git a/drivers/input/touchscreen/iqs5xx.c b/drivers/input/touchscreen/iqs5xx.c index a3f4fb85bee5..4d226118f3cc 100644 --- a/drivers/input/touchscreen/iqs5xx.c +++ b/drivers/input/touchscreen/iqs5xx.c @@ -943,12 +943,12 @@ static ssize_t fw_info_show(struct device *dev, if (!iqs5xx->dev_id_info.bl_status) return -ENODATA; - return scnprintf(buf, PAGE_SIZE, "%u.%u.%u.%u:%u.%u\n", - be16_to_cpu(iqs5xx->dev_id_info.prod_num), - be16_to_cpu(iqs5xx->dev_id_info.proj_num), - iqs5xx->dev_id_info.major_ver, - iqs5xx->dev_id_info.minor_ver, - iqs5xx->exp_file[0], iqs5xx->exp_file[1]); + return sysfs_emit(buf, "%u.%u.%u.%u:%u.%u\n", + be16_to_cpu(iqs5xx->dev_id_info.prod_num), + be16_to_cpu(iqs5xx->dev_id_info.proj_num), + iqs5xx->dev_id_info.major_ver, + iqs5xx->dev_id_info.minor_ver, + iqs5xx->exp_file[0], iqs5xx->exp_file[1]); } static DEVICE_ATTR_WO(fw_file); diff --git a/drivers/input/touchscreen/iqs7211.c b/drivers/input/touchscreen/iqs7211.c index dc084f873762..f0a56cde899e 100644 --- a/drivers/input/touchscreen/iqs7211.c +++ b/drivers/input/touchscreen/iqs7211.c @@ -2401,12 +2401,12 @@ static ssize_t fw_info_show(struct device *dev, { struct iqs7211_private *iqs7211 = dev_get_drvdata(dev); - return scnprintf(buf, PAGE_SIZE, "%u.%u.%u.%u:%u.%u\n", - le16_to_cpu(iqs7211->ver_info.prod_num), - le32_to_cpu(iqs7211->ver_info.patch), - le16_to_cpu(iqs7211->ver_info.major), - le16_to_cpu(iqs7211->ver_info.minor), - iqs7211->exp_file[1], iqs7211->exp_file[0]); + return sysfs_emit(buf, "%u.%u.%u.%u:%u.%u\n", + le16_to_cpu(iqs7211->ver_info.prod_num), + le32_to_cpu(iqs7211->ver_info.patch), + le16_to_cpu(iqs7211->ver_info.major), + le16_to_cpu(iqs7211->ver_info.minor), + iqs7211->exp_file[1], iqs7211->exp_file[0]); } static DEVICE_ATTR_RO(fw_info); diff --git a/drivers/input/touchscreen/melfas_mip4.c b/drivers/input/touchscreen/melfas_mip4.c index aa325486f618..78e1c63e530e 100644 --- a/drivers/input/touchscreen/melfas_mip4.c +++ b/drivers/input/touchscreen/melfas_mip4.c @@ -1336,9 +1336,9 @@ static ssize_t mip4_sysfs_read_fw_version(struct device *dev, /* Take lock to prevent racing with firmware update */ mutex_lock(&ts->input->mutex); - count = snprintf(buf, PAGE_SIZE, "%04X %04X %04X %04X\n", - ts->fw_version.boot, ts->fw_version.core, - ts->fw_version.app, ts->fw_version.param); + count = sysfs_emit(buf, "%04X %04X %04X %04X\n", + ts->fw_version.boot, ts->fw_version.core, + ts->fw_version.app, ts->fw_version.param); mutex_unlock(&ts->input->mutex); @@ -1362,8 +1362,8 @@ static ssize_t mip4_sysfs_read_hw_version(struct device *dev, * product_name shows the name or version of the hardware * paired with current firmware in the chip. */ - count = snprintf(buf, PAGE_SIZE, "%.*s\n", - (int)sizeof(ts->product_name), ts->product_name); + count = sysfs_emit(buf, "%.*s\n", + (int)sizeof(ts->product_name), ts->product_name); mutex_unlock(&ts->input->mutex); @@ -1382,7 +1382,7 @@ static ssize_t mip4_sysfs_read_product_id(struct device *dev, mutex_lock(&ts->input->mutex); - count = snprintf(buf, PAGE_SIZE, "%04X\n", ts->product_id); + count = sysfs_emit(buf, "%04X\n", ts->product_id); mutex_unlock(&ts->input->mutex); @@ -1401,8 +1401,8 @@ static ssize_t mip4_sysfs_read_ic_name(struct device *dev, mutex_lock(&ts->input->mutex); - count = snprintf(buf, PAGE_SIZE, "%.*s\n", - (int)sizeof(ts->ic_name), ts->ic_name); + count = sysfs_emit(buf, "%.*s\n", + (int)sizeof(ts->ic_name), ts->ic_name); mutex_unlock(&ts->input->mutex); diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c index d6d04b9f04fc..60354ebc7242 100644 --- a/drivers/input/touchscreen/usbtouchscreen.c +++ b/drivers/input/touchscreen/usbtouchscreen.c @@ -456,8 +456,8 @@ static ssize_t mtouch_firmware_rev_show(struct device *dev, struct usbtouch_usb *usbtouch = usb_get_intfdata(intf); struct mtouch_priv *priv = usbtouch->priv; - return scnprintf(output, PAGE_SIZE, "%1x.%1x\n", - priv->fw_rev_major, priv->fw_rev_minor); + return sysfs_emit(output, "%1x.%1x\n", + priv->fw_rev_major, priv->fw_rev_minor); } static DEVICE_ATTR(firmware_rev, 0444, mtouch_firmware_rev_show, NULL); diff --git a/drivers/input/touchscreen/wdt87xx_i2c.c b/drivers/input/touchscreen/wdt87xx_i2c.c index 128341a6696b..32c7be54434c 100644 --- a/drivers/input/touchscreen/wdt87xx_i2c.c +++ b/drivers/input/touchscreen/wdt87xx_i2c.c @@ -887,7 +887,7 @@ static ssize_t config_csum_show(struct device *dev, cfg_csum = wdt->param.xmls_id1; cfg_csum = (cfg_csum << 16) | wdt->param.xmls_id2; - return scnprintf(buf, PAGE_SIZE, "%x\n", cfg_csum); + return sysfs_emit(buf, "%x\n", cfg_csum); } static ssize_t fw_version_show(struct device *dev, @@ -896,7 +896,7 @@ static ssize_t fw_version_show(struct device *dev, struct i2c_client *client = to_i2c_client(dev); struct wdt87xx_data *wdt = i2c_get_clientdata(client); - return scnprintf(buf, PAGE_SIZE, "%x\n", wdt->param.fw_id); + return sysfs_emit(buf, "%x\n", wdt->param.fw_id); } static ssize_t plat_id_show(struct device *dev, @@ -905,7 +905,7 @@ static ssize_t plat_id_show(struct device *dev, struct i2c_client *client = to_i2c_client(dev); struct wdt87xx_data *wdt = i2c_get_clientdata(client); - return scnprintf(buf, PAGE_SIZE, "%x\n", wdt->param.plat_id); + return sysfs_emit(buf, "%x\n", wdt->param.plat_id); } static ssize_t update_config_store(struct device *dev, diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c index 5be5112845e1..5680075f0bb8 100644 --- a/drivers/input/touchscreen/zforce_ts.c +++ b/drivers/input/touchscreen/zforce_ts.c @@ -20,6 +20,7 @@ #include <linux/device.h> #include <linux/sysfs.h> #include <linux/input/mt.h> +#include <linux/input/touchscreen.h> #include <linux/platform_data/zforce_ts.h> #include <linux/regulator/consumer.h> #include <linux/of.h> @@ -106,6 +107,7 @@ struct zforce_point { struct zforce_ts { struct i2c_client *client; struct input_dev *input; + struct touchscreen_properties prop; const struct zforce_ts_platdata *pdata; char phys[32]; @@ -266,7 +268,6 @@ static int zforce_setconfig(struct zforce_ts *ts, char b1) static int zforce_start(struct zforce_ts *ts) { struct i2c_client *client = ts->client; - const struct zforce_ts_platdata *pdata = ts->pdata; int ret; dev_dbg(&client->dev, "starting device\n"); @@ -277,7 +278,7 @@ static int zforce_start(struct zforce_ts *ts) return ret; } - ret = zforce_resolution(ts, pdata->x_max, pdata->y_max); + ret = zforce_resolution(ts, ts->prop.max_x, ts->prop.max_y); if (ret) { dev_err(&client->dev, "Unable to set resolution, %d\n", ret); goto error; @@ -337,7 +338,6 @@ static int zforce_stop(struct zforce_ts *ts) static int zforce_touch_event(struct zforce_ts *ts, u8 *payload) { struct i2c_client *client = ts->client; - const struct zforce_ts_platdata *pdata = ts->pdata; struct zforce_point point; int count, i, num = 0; @@ -355,8 +355,8 @@ static int zforce_touch_event(struct zforce_ts *ts, u8 *payload) point.coord_y = payload[9 * i + 4] << 8 | payload[9 * i + 3]; - if (point.coord_x > pdata->x_max || - point.coord_y > pdata->y_max) { + if (point.coord_x > ts->prop.max_x || + point.coord_y > ts->prop.max_y) { dev_warn(&client->dev, "coordinates (%d,%d) invalid\n", point.coord_x, point.coord_y); point.coord_x = point.coord_y = 0; @@ -390,10 +390,9 @@ static int zforce_touch_event(struct zforce_ts *ts, u8 *payload) point.state != STATE_UP); if (point.state != STATE_UP) { - input_report_abs(ts->input, ABS_MT_POSITION_X, - point.coord_x); - input_report_abs(ts->input, ABS_MT_POSITION_Y, - point.coord_y); + touchscreen_report_pos(ts->input, &ts->prop, + point.coord_x, point.coord_y, + true); input_report_abs(ts->input, ABS_MT_TOUCH_MAJOR, point.area_major); input_report_abs(ts->input, ABS_MT_TOUCH_MINOR, @@ -719,15 +718,8 @@ static struct zforce_ts_platdata *zforce_parse_dt(struct device *dev) return ERR_PTR(-ENOMEM); } - if (of_property_read_u32(np, "x-size", &pdata->x_max)) { - dev_err(dev, "failed to get x-size property\n"); - return ERR_PTR(-EINVAL); - } - - if (of_property_read_u32(np, "y-size", &pdata->y_max)) { - dev_err(dev, "failed to get y-size property\n"); - return ERR_PTR(-EINVAL); - } + of_property_read_u32(np, "x-size", &pdata->x_max); + of_property_read_u32(np, "y-size", &pdata->y_max); return pdata; } @@ -856,6 +848,12 @@ static int zforce_probe(struct i2c_client *client) input_set_abs_params(input_dev, ABS_MT_POSITION_Y, 0, pdata->y_max, 0, 0); + touchscreen_parse_properties(input_dev, true, &ts->prop); + if (ts->prop.max_x == 0 || ts->prop.max_y == 0) { + dev_err(&client->dev, "no size specified\n"); + return -EINVAL; + } + input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR, 0, ZFORCE_MAX_AREA, 0, 0); input_set_abs_params(input_dev, ABS_MT_TOUCH_MINOR, 0, diff --git a/drivers/input/vivaldi-fmap.c b/drivers/input/vivaldi-fmap.c index 6dae83d96806..0d29ec014e2f 100644 --- a/drivers/input/vivaldi-fmap.c +++ b/drivers/input/vivaldi-fmap.c @@ -27,10 +27,10 @@ ssize_t vivaldi_function_row_physmap_show(const struct vivaldi_data *data, return 0; for (i = 0; i < data->num_function_row_keys; i++) - size += scnprintf(buf + size, PAGE_SIZE - size, - "%s%02X", size ? " " : "", physmap[i]); + size += sysfs_emit_at(buf, size, + "%s%02X", size ? " " : "", physmap[i]); if (size) - size += scnprintf(buf + size, PAGE_SIZE - size, "\n"); + size += sysfs_emit_at(buf, size, "\n"); return size; } diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 7673bb82945b..9a29d742617e 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -160,6 +160,7 @@ config IOMMU_DMA # Shared Virtual Addressing config IOMMU_SVA + select IOMMU_MM_DATA bool config FSL_PAMU diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 86be1edd50ee..8b3601f285fd 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -53,10 +53,16 @@ int amd_iommu_pdev_enable_cap_pri(struct pci_dev *pdev); void amd_iommu_pdev_disable_cap_pri(struct pci_dev *pdev); int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid, u64 address); +/* + * This function flushes all internal caches of + * the IOMMU used by this driver. + */ +void amd_iommu_flush_all_caches(struct amd_iommu *iommu); void amd_iommu_update_and_flush_device_table(struct protection_domain *domain); void amd_iommu_domain_update(struct protection_domain *domain); void amd_iommu_domain_flush_complete(struct protection_domain *domain); -void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain); +void amd_iommu_domain_flush_pages(struct protection_domain *domain, + u64 address, size_t size); int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid); int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid, unsigned long cr3); diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 90b7d7950a9e..809d74faa1a5 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -902,12 +902,6 @@ extern int amd_iommu_max_glx_val; extern u64 amd_iommu_efr; extern u64 amd_iommu_efr2; -/* - * This function flushes all internal caches of - * the IOMMU used by this driver. - */ -void iommu_flush_all_caches(struct amd_iommu *iommu); - static inline int get_ioapic_devid(int id) { struct devid_map *entry; diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 64bcf3df37ee..c83bd0c2a1c9 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -2223,7 +2223,7 @@ static int __init amd_iommu_init_pci(void) init_device_table_dma(pci_seg); for_each_iommu(iommu) - iommu_flush_all_caches(iommu); + amd_iommu_flush_all_caches(iommu); print_iommu_info(); @@ -2773,7 +2773,7 @@ static void early_enable_iommu(struct amd_iommu *iommu) iommu_enable_xt(iommu); iommu_enable_irtcachedis(iommu); iommu_enable(iommu); - iommu_flush_all_caches(iommu); + amd_iommu_flush_all_caches(iommu); } /* @@ -2829,7 +2829,7 @@ static void early_enable_iommus(void) iommu_enable_xt(iommu); iommu_enable_irtcachedis(iommu); iommu_set_device_table(iommu); - iommu_flush_all_caches(iommu); + amd_iommu_flush_all_caches(iommu); } } } @@ -3293,7 +3293,7 @@ static int __init state_next(void) uninit_device_table_dma(pci_seg); for_each_iommu(iommu) - iommu_flush_all_caches(iommu); + amd_iommu_flush_all_caches(iommu); } } return ret; diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c index 6c0621f6f572..2a0d1e97e52f 100644 --- a/drivers/iommu/amd/io_pgtable.c +++ b/drivers/iommu/amd/io_pgtable.c @@ -369,6 +369,8 @@ static int iommu_v1_map_pages(struct io_pgtable_ops *ops, unsigned long iova, bool updated = false; u64 __pte, *pte; int ret, i, count; + size_t size = pgcount << __ffs(pgsize); + unsigned long o_iova = iova; BUG_ON(!IS_ALIGNED(iova, pgsize)); BUG_ON(!IS_ALIGNED(paddr, pgsize)); @@ -424,8 +426,7 @@ out: * Updates and flushing already happened in * increase_address_space(). */ - amd_iommu_domain_flush_tlb_pde(dom); - amd_iommu_domain_flush_complete(dom); + amd_iommu_domain_flush_pages(dom, o_iova, size); spin_unlock_irqrestore(&dom->lock, flags); } diff --git a/drivers/iommu/amd/io_pgtable_v2.c b/drivers/iommu/amd/io_pgtable_v2.c index f818a7e254d4..6d69ba60744f 100644 --- a/drivers/iommu/amd/io_pgtable_v2.c +++ b/drivers/iommu/amd/io_pgtable_v2.c @@ -244,7 +244,6 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova, unsigned long mapped_size = 0; unsigned long o_iova = iova; size_t size = pgcount << __ffs(pgsize); - int count = 0; int ret = 0; bool updated = false; @@ -265,19 +264,14 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova, *pte = set_pte_attr(paddr, map_size, prot); - count++; iova += map_size; paddr += map_size; mapped_size += map_size; } out: - if (updated) { - if (count > 1) - amd_iommu_flush_tlb(&pdom->domain, 0); - else - amd_iommu_flush_page(&pdom->domain, 0, o_iova); - } + if (updated) + amd_iommu_domain_flush_pages(pdom, o_iova, size); if (mapped) *mapped += mapped_size; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index b9a0523cbb0a..4283dd8191f0 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -64,7 +64,7 @@ LIST_HEAD(hpet_map); LIST_HEAD(acpihid_map); const struct iommu_ops amd_iommu_ops; -const struct iommu_dirty_ops amd_dirty_ops; +static const struct iommu_dirty_ops amd_dirty_ops; int amd_iommu_max_glx_val = -1; @@ -85,6 +85,11 @@ static void detach_device(struct device *dev); * ****************************************************************************/ +static inline bool pdom_is_v2_pgtbl_mode(struct protection_domain *pdom) +{ + return (pdom && (pdom->flags & PD_IOMMUV2_MASK)); +} + static inline int get_acpihid_device_id(struct device *dev, struct acpihid_map_entry **entry) { @@ -551,8 +556,6 @@ static void amd_iommu_uninit_device(struct device *dev) if (dev_data->domain) detach_device(dev); - dev_iommu_priv_set(dev, NULL); - /* * We keep dev_data around for unplugged devices and reuse it when the * device is re-plugged - not doing so would introduce a ton of races. @@ -1124,68 +1127,44 @@ static inline u64 build_inv_address(u64 address, size_t size) } static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address, - size_t size, u16 domid, int pde) + size_t size, u16 domid, + ioasid_t pasid, bool gn) { u64 inv_address = build_inv_address(address, size); memset(cmd, 0, sizeof(*cmd)); + cmd->data[1] |= domid; cmd->data[2] = lower_32_bits(inv_address); cmd->data[3] = upper_32_bits(inv_address); + /* PDE bit - we want to flush everything, not only the PTEs */ + cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK; + if (gn) { + cmd->data[0] |= pasid; + cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK; + } CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES); - if (pde) /* PDE bit - we want to flush everything, not only the PTEs */ - cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK; } static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep, - u64 address, size_t size) + u64 address, size_t size, + ioasid_t pasid, bool gn) { u64 inv_address = build_inv_address(address, size); memset(cmd, 0, sizeof(*cmd)); + cmd->data[0] = devid; cmd->data[0] |= (qdep & 0xff) << 24; cmd->data[1] = devid; cmd->data[2] = lower_32_bits(inv_address); cmd->data[3] = upper_32_bits(inv_address); - CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES); -} - -static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, u32 pasid, - u64 address, bool size) -{ - memset(cmd, 0, sizeof(*cmd)); - - address &= ~(0xfffULL); - - cmd->data[0] = pasid; - cmd->data[1] = domid; - cmd->data[2] = lower_32_bits(address); - cmd->data[3] = upper_32_bits(address); - cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK; - cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK; - if (size) - cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK; - CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES); -} - -static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, u32 pasid, - int qdep, u64 address, bool size) -{ - memset(cmd, 0, sizeof(*cmd)); - - address &= ~(0xfffULL); + if (gn) { + cmd->data[0] |= ((pasid >> 8) & 0xff) << 16; + cmd->data[1] |= (pasid & 0xff) << 16; + cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK; + } - cmd->data[0] = devid; - cmd->data[0] |= ((pasid >> 8) & 0xff) << 16; - cmd->data[0] |= (qdep & 0xff) << 24; - cmd->data[1] = devid; - cmd->data[1] |= (pasid & 0xff) << 16; - cmd->data[2] = lower_32_bits(address); - cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK; - cmd->data[3] = upper_32_bits(address); - if (size) - cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK; CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES); } @@ -1341,7 +1320,7 @@ static void amd_iommu_flush_tlb_all(struct amd_iommu *iommu) for (dom_id = 0; dom_id <= last_bdf; ++dom_id) { struct iommu_cmd cmd; build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, - dom_id, 1); + dom_id, IOMMU_NO_PASID, false); iommu_queue_command(iommu, &cmd); } @@ -1353,7 +1332,7 @@ static void amd_iommu_flush_tlb_domid(struct amd_iommu *iommu, u32 dom_id) struct iommu_cmd cmd; build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, - dom_id, 1); + dom_id, IOMMU_NO_PASID, false); iommu_queue_command(iommu, &cmd); iommu_completion_wait(iommu); @@ -1392,7 +1371,7 @@ static void amd_iommu_flush_irt_all(struct amd_iommu *iommu) iommu_completion_wait(iommu); } -void iommu_flush_all_caches(struct amd_iommu *iommu) +void amd_iommu_flush_all_caches(struct amd_iommu *iommu) { if (check_feature(FEATURE_IA)) { amd_iommu_flush_all(iommu); @@ -1406,8 +1385,8 @@ void iommu_flush_all_caches(struct amd_iommu *iommu) /* * Command send function for flushing on-device TLB */ -static int device_flush_iotlb(struct iommu_dev_data *dev_data, - u64 address, size_t size) +static int device_flush_iotlb(struct iommu_dev_data *dev_data, u64 address, + size_t size, ioasid_t pasid, bool gn) { struct amd_iommu *iommu; struct iommu_cmd cmd; @@ -1418,7 +1397,8 @@ static int device_flush_iotlb(struct iommu_dev_data *dev_data, if (!iommu) return -EINVAL; - build_inv_iotlb_pages(&cmd, dev_data->devid, qdep, address, size); + build_inv_iotlb_pages(&cmd, dev_data->devid, qdep, address, + size, pasid, gn); return iommu_queue_command(iommu, &cmd); } @@ -1464,8 +1444,11 @@ static int device_flush_dte(struct iommu_dev_data *dev_data) return ret; } - if (dev_data->ats_enabled) - ret = device_flush_iotlb(dev_data, 0, ~0UL); + if (dev_data->ats_enabled) { + /* Invalidate the entire contents of an IOTLB */ + ret = device_flush_iotlb(dev_data, 0, ~0UL, + IOMMU_NO_PASID, false); + } return ret; } @@ -1476,13 +1459,18 @@ static int device_flush_dte(struct iommu_dev_data *dev_data) * page. Otherwise it flushes the whole TLB of the IOMMU. */ static void __domain_flush_pages(struct protection_domain *domain, - u64 address, size_t size, int pde) + u64 address, size_t size) { struct iommu_dev_data *dev_data; struct iommu_cmd cmd; int ret = 0, i; + ioasid_t pasid = IOMMU_NO_PASID; + bool gn = false; + + if (pdom_is_v2_pgtbl_mode(domain)) + gn = true; - build_inv_iommu_pages(&cmd, address, size, domain->id, pde); + build_inv_iommu_pages(&cmd, address, size, domain->id, pasid, gn); for (i = 0; i < amd_iommu_get_num_iommus(); ++i) { if (!domain->dev_iommu[i]) @@ -1500,17 +1488,21 @@ static void __domain_flush_pages(struct protection_domain *domain, if (!dev_data->ats_enabled) continue; - ret |= device_flush_iotlb(dev_data, address, size); + ret |= device_flush_iotlb(dev_data, address, size, pasid, gn); } WARN_ON(ret); } -static void domain_flush_pages(struct protection_domain *domain, - u64 address, size_t size, int pde) +void amd_iommu_domain_flush_pages(struct protection_domain *domain, + u64 address, size_t size) { if (likely(!amd_iommu_np_cache)) { - __domain_flush_pages(domain, address, size, pde); + __domain_flush_pages(domain, address, size); + + /* Wait until IOMMU TLB and all device IOTLB flushes are complete */ + amd_iommu_domain_flush_complete(domain); + return; } @@ -1543,16 +1535,20 @@ static void domain_flush_pages(struct protection_domain *domain, flush_size = 1ul << min_alignment; - __domain_flush_pages(domain, address, flush_size, pde); + __domain_flush_pages(domain, address, flush_size); address += flush_size; size -= flush_size; } + + /* Wait until IOMMU TLB and all device IOTLB flushes are complete */ + amd_iommu_domain_flush_complete(domain); } /* Flush the whole IO/TLB for a given protection domain - including PDE */ -void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain) +static void amd_iommu_domain_flush_all(struct protection_domain *domain) { - domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 1); + amd_iommu_domain_flush_pages(domain, 0, + CMD_INV_IOMMU_ALL_PAGES_ADDRESS); } void amd_iommu_domain_flush_complete(struct protection_domain *domain) @@ -1579,8 +1575,7 @@ static void domain_flush_np_cache(struct protection_domain *domain, unsigned long flags; spin_lock_irqsave(&domain->lock, flags); - domain_flush_pages(domain, iova, size, 1); - amd_iommu_domain_flush_complete(domain); + amd_iommu_domain_flush_pages(domain, iova, size); spin_unlock_irqrestore(&domain->lock, flags); } } @@ -1858,11 +1853,8 @@ static void do_detach(struct iommu_dev_data *dev_data) /* Flush the DTE entry */ device_flush_dte(dev_data); - /* Flush IOTLB */ - amd_iommu_domain_flush_tlb_pde(domain); - - /* Wait for the flushes to finish */ - amd_iommu_domain_flush_complete(domain); + /* Flush IOTLB and wait for the flushes to finish */ + amd_iommu_domain_flush_all(domain); /* decrease reference counters - needs to happen after the flushes */ domain->dev_iommu[iommu->index] -= 1; @@ -1896,15 +1888,6 @@ static int attach_device(struct device *dev, do_attach(dev_data, domain); - /* - * We might boot into a crash-kernel here. The crashed kernel - * left the caches in the IOMMU dirty. So we have to flush - * here to evict all dirty stuff. - */ - amd_iommu_domain_flush_tlb_pde(domain); - - amd_iommu_domain_flush_complete(domain); - out: spin_unlock(&dev_data->lock); @@ -2048,8 +2031,7 @@ void amd_iommu_domain_update(struct protection_domain *domain) amd_iommu_update_and_flush_device_table(domain); /* Flush domain TLB(s) and wait for completion */ - amd_iommu_domain_flush_tlb_pde(domain); - amd_iommu_domain_flush_complete(domain); + amd_iommu_domain_flush_all(domain); } /***************************************************************************** @@ -2482,10 +2464,9 @@ static int amd_iommu_set_dirty_tracking(struct iommu_domain *domain, } /* Flush IOTLB to mark IOPTE dirty on the next translation(s) */ - if (domain_flush) { - amd_iommu_domain_flush_tlb_pde(pdomain); - amd_iommu_domain_flush_complete(pdomain); - } + if (domain_flush) + amd_iommu_domain_flush_all(pdomain); + pdomain->dirty_tracking = enable; spin_unlock_irqrestore(&pdomain->lock, flags); @@ -2588,8 +2569,7 @@ static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain) unsigned long flags; spin_lock_irqsave(&dom->lock, flags); - amd_iommu_domain_flush_tlb_pde(dom); - amd_iommu_domain_flush_complete(dom); + amd_iommu_domain_flush_all(dom); spin_unlock_irqrestore(&dom->lock, flags); } @@ -2600,8 +2580,8 @@ static void amd_iommu_iotlb_sync(struct iommu_domain *domain, unsigned long flags; spin_lock_irqsave(&dom->lock, flags); - domain_flush_pages(dom, gather->start, gather->end - gather->start + 1, 1); - amd_iommu_domain_flush_complete(dom); + amd_iommu_domain_flush_pages(dom, gather->start, + gather->end - gather->start + 1); spin_unlock_irqrestore(&dom->lock, flags); } @@ -2635,7 +2615,7 @@ static bool amd_iommu_enforce_cache_coherency(struct iommu_domain *domain) return true; } -const struct iommu_dirty_ops amd_dirty_ops = { +static const struct iommu_dirty_ops amd_dirty_ops = { .set_dirty_tracking = amd_iommu_set_dirty_tracking, .read_and_clear_dirty = amd_iommu_read_and_clear_dirty, }; @@ -2666,7 +2646,7 @@ const struct iommu_ops amd_iommu_ops = { }; static int __flush_pasid(struct protection_domain *domain, u32 pasid, - u64 address, bool size) + u64 address, size_t size) { struct iommu_dev_data *dev_data; struct iommu_cmd cmd; @@ -2675,7 +2655,7 @@ static int __flush_pasid(struct protection_domain *domain, u32 pasid, if (!(domain->flags & PD_IOMMUV2_MASK)) return -EINVAL; - build_inv_iommu_pasid(&cmd, domain->id, pasid, address, size); + build_inv_iommu_pages(&cmd, address, size, domain->id, pasid, true); /* * IOMMU TLB needs to be flushed before Device TLB to @@ -2709,8 +2689,8 @@ static int __flush_pasid(struct protection_domain *domain, u32 pasid, iommu = rlookup_amd_iommu(dev_data->dev); if (!iommu) continue; - build_inv_iotlb_pasid(&cmd, dev_data->devid, pasid, - qdep, address, size); + build_inv_iotlb_pages(&cmd, dev_data->devid, qdep, + address, size, pasid, true); ret = iommu_queue_command(iommu, &cmd); if (ret != 0) @@ -2730,7 +2710,7 @@ out: static int __amd_iommu_flush_page(struct protection_domain *domain, u32 pasid, u64 address) { - return __flush_pasid(domain, pasid, address, false); + return __flush_pasid(domain, pasid, address, PAGE_SIZE); } int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid, @@ -2749,8 +2729,7 @@ int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid, static int __amd_iommu_flush_tlb(struct protection_domain *domain, u32 pasid) { - return __flush_pasid(domain, pasid, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, - true); + return __flush_pasid(domain, pasid, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS); } int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid) @@ -3111,8 +3090,8 @@ out: return index; } -static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index, - struct irte_ga *irte) +static int __modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index, + struct irte_ga *irte) { struct irq_remap_table *table; struct irte_ga *entry; @@ -3139,6 +3118,18 @@ static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index, raw_spin_unlock_irqrestore(&table->lock, flags); + return 0; +} + +static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index, + struct irte_ga *irte) +{ + bool ret; + + ret = __modify_irte_ga(iommu, devid, index, irte); + if (ret) + return ret; + iommu_flush_irt_and_complete(iommu, devid); return 0; @@ -3822,8 +3813,8 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data) } entry->lo.fields_vapic.is_run = is_run; - return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid, - ir_data->irq_2_irte.index, entry); + return __modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid, + ir_data->irq_2_irte.index, entry); } EXPORT_SYMBOL(amd_iommu_update_ga); #endif diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c index ee05f4824bfa..ef3ee95706da 100644 --- a/drivers/iommu/apple-dart.c +++ b/drivers/iommu/apple-dart.c @@ -81,6 +81,7 @@ #define DART_T8020_TCR_BYPASS_DAPF BIT(12) #define DART_T8020_TTBR 0x200 +#define DART_T8020_USB4_TTBR 0x400 #define DART_T8020_TTBR_VALID BIT(31) #define DART_T8020_TTBR_ADDR_FIELD_SHIFT 0 #define DART_T8020_TTBR_SHIFT 12 @@ -368,12 +369,14 @@ apple_dart_t8020_hw_stream_command(struct apple_dart_stream_map *stream_map, u32 command) { unsigned long flags; - int ret; + int ret, i; u32 command_reg; spin_lock_irqsave(&stream_map->dart->lock, flags); - writel(stream_map->sidmap[0], stream_map->dart->regs + DART_T8020_STREAM_SELECT); + for (i = 0; i < BITS_TO_U32(stream_map->dart->num_streams); i++) + writel(stream_map->sidmap[i], + stream_map->dart->regs + DART_T8020_STREAM_SELECT + 4 * i); writel(command, stream_map->dart->regs + DART_T8020_STREAM_COMMAND); ret = readl_poll_timeout_atomic( @@ -740,7 +743,6 @@ static void apple_dart_release_device(struct device *dev) { struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev); - dev_iommu_priv_set(dev, NULL); kfree(cfg); } @@ -908,7 +910,7 @@ static struct iommu_group *apple_dart_device_group(struct device *dev) ret = apple_dart_merge_master_cfg(group_master_cfg, cfg); if (ret) { - dev_err(dev, "Failed to merge DART IOMMU grups.\n"); + dev_err(dev, "Failed to merge DART IOMMU groups.\n"); iommu_group_put(group); res = ERR_PTR(ret); goto out; @@ -1215,6 +1217,33 @@ static const struct apple_dart_hw apple_dart_hw_t8103 = { .ttbr_shift = DART_T8020_TTBR_SHIFT, .ttbr_count = 4, }; + +static const struct apple_dart_hw apple_dart_hw_t8103_usb4 = { + .type = DART_T8020, + .irq_handler = apple_dart_t8020_irq, + .invalidate_tlb = apple_dart_t8020_hw_invalidate_tlb, + .oas = 36, + .fmt = APPLE_DART, + .max_sid_count = 64, + + .enable_streams = DART_T8020_STREAMS_ENABLE, + .lock = DART_T8020_CONFIG, + .lock_bit = DART_T8020_CONFIG_LOCK, + + .error = DART_T8020_ERROR, + + .tcr = DART_T8020_TCR, + .tcr_enabled = DART_T8020_TCR_TRANSLATE_ENABLE, + .tcr_disabled = 0, + .tcr_bypass = 0, + + .ttbr = DART_T8020_USB4_TTBR, + .ttbr_valid = DART_T8020_TTBR_VALID, + .ttbr_addr_field_shift = DART_T8020_TTBR_ADDR_FIELD_SHIFT, + .ttbr_shift = DART_T8020_TTBR_SHIFT, + .ttbr_count = 4, +}; + static const struct apple_dart_hw apple_dart_hw_t6000 = { .type = DART_T6000, .irq_handler = apple_dart_t8020_irq, @@ -1272,7 +1301,7 @@ static __maybe_unused int apple_dart_suspend(struct device *dev) unsigned int sid, idx; for (sid = 0; sid < dart->num_streams; sid++) { - dart->save_tcr[sid] = readl_relaxed(dart->regs + DART_TCR(dart, sid)); + dart->save_tcr[sid] = readl(dart->regs + DART_TCR(dart, sid)); for (idx = 0; idx < dart->hw->ttbr_count; idx++) dart->save_ttbr[sid][idx] = readl(dart->regs + DART_TTBR(dart, sid, idx)); @@ -1307,6 +1336,7 @@ static DEFINE_SIMPLE_DEV_PM_OPS(apple_dart_pm_ops, apple_dart_suspend, apple_dar static const struct of_device_id apple_dart_of_match[] = { { .compatible = "apple,t8103-dart", .data = &apple_dart_hw_t8103 }, + { .compatible = "apple,t8103-usb4-dart", .data = &apple_dart_hw_t8103_usb4 }, { .compatible = "apple,t8110-dart", .data = &apple_dart_hw_t8110 }, { .compatible = "apple,t6000-dart", .data = &apple_dart_hw_t6000 }, {}, diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c index 353248ab18e7..05722121f00e 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c @@ -246,7 +246,8 @@ static void arm_smmu_mm_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn, smmu_domain); } - arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, start, size); + arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), start, + size); } static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm) @@ -264,10 +265,11 @@ static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm) * DMA may still be running. Keep the cd valid to avoid C_BAD_CD events, * but disable translation. */ - arm_smmu_update_ctx_desc_devices(smmu_domain, mm->pasid, &quiet_cd); + arm_smmu_update_ctx_desc_devices(smmu_domain, mm_get_enqcmd_pasid(mm), + &quiet_cd); arm_smmu_tlb_inv_asid(smmu_domain->smmu, smmu_mn->cd->asid); - arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0); + arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), 0, 0); smmu_mn->cleared = true; mutex_unlock(&sva_lock); @@ -325,10 +327,13 @@ arm_smmu_mmu_notifier_get(struct arm_smmu_domain *smmu_domain, spin_lock_irqsave(&smmu_domain->devices_lock, flags); list_for_each_entry(master, &smmu_domain->devices, domain_head) { - ret = arm_smmu_write_ctx_desc(master, mm->pasid, cd); + ret = arm_smmu_write_ctx_desc(master, mm_get_enqcmd_pasid(mm), + cd); if (ret) { - list_for_each_entry_from_reverse(master, &smmu_domain->devices, domain_head) - arm_smmu_write_ctx_desc(master, mm->pasid, NULL); + list_for_each_entry_from_reverse( + master, &smmu_domain->devices, domain_head) + arm_smmu_write_ctx_desc( + master, mm_get_enqcmd_pasid(mm), NULL); break; } } @@ -358,7 +363,8 @@ static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn) list_del(&smmu_mn->list); - arm_smmu_update_ctx_desc_devices(smmu_domain, mm->pasid, NULL); + arm_smmu_update_ctx_desc_devices(smmu_domain, mm_get_enqcmd_pasid(mm), + NULL); /* * If we went through clear(), we've already invalidated, and no @@ -366,7 +372,8 @@ static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn) */ if (!smmu_mn->cleared) { arm_smmu_tlb_inv_asid(smmu_domain->smmu, cd->asid); - arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0); + arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), 0, + 0); } /* Frees smmu_mn */ diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 7445454c2af2..0ffb1cf17e0b 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -1063,6 +1063,7 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid, bool cd_live; __le64 *cdptr; struct arm_smmu_ctx_desc_cfg *cd_table = &master->cd_table; + struct arm_smmu_device *smmu = master->smmu; if (WARN_ON(ssid >= (1 << cd_table->s1cdmax))) return -E2BIG; @@ -1077,6 +1078,8 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid, if (!cd) { /* (5) */ val = 0; } else if (cd == &quiet_cd) { /* (4) */ + if (!(smmu->features & ARM_SMMU_FEAT_STALL_FORCE)) + val &= ~(CTXDESC_CD_0_S | CTXDESC_CD_0_R); val |= CTXDESC_CD_0_TCR_EPD0; } else if (cd_live) { /* (3) */ val &= ~CTXDESC_CD_0_ASID; @@ -1249,7 +1252,7 @@ static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid) } static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, - __le64 *dst) + struct arm_smmu_ste *dst) { /* * This is hideously complicated, but we only really care about @@ -1267,12 +1270,12 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, * 2. Write everything apart from dword 0, sync, write dword 0, sync * 3. Update Config, sync */ - u64 val = le64_to_cpu(dst[0]); + u64 val = le64_to_cpu(dst->data[0]); bool ste_live = false; - struct arm_smmu_device *smmu = NULL; + struct arm_smmu_device *smmu = master->smmu; struct arm_smmu_ctx_desc_cfg *cd_table = NULL; struct arm_smmu_s2_cfg *s2_cfg = NULL; - struct arm_smmu_domain *smmu_domain = NULL; + struct arm_smmu_domain *smmu_domain = master->domain; struct arm_smmu_cmdq_ent prefetch_cmd = { .opcode = CMDQ_OP_PREFETCH_CFG, .prefetch = { @@ -1280,18 +1283,12 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, }, }; - if (master) { - smmu_domain = master->domain; - smmu = master->smmu; - } - if (smmu_domain) { switch (smmu_domain->stage) { case ARM_SMMU_DOMAIN_S1: cd_table = &master->cd_table; break; case ARM_SMMU_DOMAIN_S2: - case ARM_SMMU_DOMAIN_NESTED: s2_cfg = &smmu_domain->s2_cfg; break; default: @@ -1325,10 +1322,10 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, else val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS); - dst[0] = cpu_to_le64(val); - dst[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG, + dst->data[0] = cpu_to_le64(val); + dst->data[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG, STRTAB_STE_1_SHCFG_INCOMING)); - dst[2] = 0; /* Nuke the VMID */ + dst->data[2] = 0; /* Nuke the VMID */ /* * The SMMU can perform negative caching, so we must sync * the STE regardless of whether the old value was live. @@ -1343,7 +1340,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, STRTAB_STE_1_STRW_EL2 : STRTAB_STE_1_STRW_NSEL1; BUG_ON(ste_live); - dst[1] = cpu_to_le64( + dst->data[1] = cpu_to_le64( FIELD_PREP(STRTAB_STE_1_S1DSS, STRTAB_STE_1_S1DSS_SSID0) | FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) | FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) | @@ -1352,7 +1349,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, if (smmu->features & ARM_SMMU_FEAT_STALLS && !master->stall_enabled) - dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD); + dst->data[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD); val |= (cd_table->cdtab_dma & STRTAB_STE_0_S1CTXPTR_MASK) | FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS) | @@ -1362,7 +1359,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, if (s2_cfg) { BUG_ON(ste_live); - dst[2] = cpu_to_le64( + dst->data[2] = cpu_to_le64( FIELD_PREP(STRTAB_STE_2_S2VMID, s2_cfg->vmid) | FIELD_PREP(STRTAB_STE_2_VTCR, s2_cfg->vtcr) | #ifdef __BIG_ENDIAN @@ -1371,18 +1368,18 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 | STRTAB_STE_2_S2R); - dst[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK); + dst->data[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK); val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS); } if (master->ats_enabled) - dst[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS, + dst->data[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS, STRTAB_STE_1_EATS_TRANS)); arm_smmu_sync_ste_for_sid(smmu, sid); /* See comment in arm_smmu_write_ctx_desc() */ - WRITE_ONCE(dst[0], cpu_to_le64(val)); + WRITE_ONCE(dst->data[0], cpu_to_le64(val)); arm_smmu_sync_ste_for_sid(smmu, sid); /* It's likely that we'll want to use the new STE soon */ @@ -1390,7 +1387,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd); } -static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent, bool force) +static void arm_smmu_init_bypass_stes(struct arm_smmu_ste *strtab, + unsigned int nent, bool force) { unsigned int i; u64 val = STRTAB_STE_0_V; @@ -1401,11 +1399,11 @@ static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent, bool fo val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS); for (i = 0; i < nent; ++i) { - strtab[0] = cpu_to_le64(val); - strtab[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG, - STRTAB_STE_1_SHCFG_INCOMING)); - strtab[2] = 0; - strtab += STRTAB_STE_DWORDS; + strtab->data[0] = cpu_to_le64(val); + strtab->data[1] = cpu_to_le64(FIELD_PREP( + STRTAB_STE_1_SHCFG, STRTAB_STE_1_SHCFG_INCOMING)); + strtab->data[2] = 0; + strtab++; } } @@ -2171,7 +2169,6 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain) fmt = ARM_64_LPAE_S1; finalise_stage_fn = arm_smmu_domain_finalise_s1; break; - case ARM_SMMU_DOMAIN_NESTED: case ARM_SMMU_DOMAIN_S2: ias = smmu->ias; oas = smmu->oas; @@ -2209,26 +2206,23 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain) return 0; } -static __le64 *arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid) +static struct arm_smmu_ste * +arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid) { - __le64 *step; struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg; if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) { - struct arm_smmu_strtab_l1_desc *l1_desc; - int idx; + unsigned int idx1, idx2; /* Two-level walk */ - idx = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS; - l1_desc = &cfg->l1_desc[idx]; - idx = (sid & ((1 << STRTAB_SPLIT) - 1)) * STRTAB_STE_DWORDS; - step = &l1_desc->l2ptr[idx]; + idx1 = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS; + idx2 = sid & ((1 << STRTAB_SPLIT) - 1); + return &cfg->l1_desc[idx1].l2ptr[idx2]; } else { /* Simple linear lookup */ - step = &cfg->strtab[sid * STRTAB_STE_DWORDS]; + return (struct arm_smmu_ste *)&cfg + ->strtab[sid * STRTAB_STE_DWORDS]; } - - return step; } static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master) @@ -2238,7 +2232,8 @@ static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master) for (i = 0; i < master->num_streams; ++i) { u32 sid = master->streams[i].id; - __le64 *step = arm_smmu_get_step_for_sid(smmu, sid); + struct arm_smmu_ste *step = + arm_smmu_get_step_for_sid(smmu, sid); /* Bridged PCI devices may end up with duplicated IDs */ for (j = 0; j < i; j++) @@ -2649,9 +2644,6 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev) struct arm_smmu_master *master; struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - if (!fwspec || fwspec->ops != &arm_smmu_ops) - return ERR_PTR(-ENODEV); - if (WARN_ON_ONCE(dev_iommu_priv_get(dev))) return ERR_PTR(-EBUSY); @@ -2698,7 +2690,6 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev) err_free_master: kfree(master); - dev_iommu_priv_set(dev, NULL); return ERR_PTR(ret); } @@ -2742,7 +2733,7 @@ static int arm_smmu_enable_nesting(struct iommu_domain *domain) if (smmu_domain->smmu) ret = -EPERM; else - smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED; + smmu_domain->stage = ARM_SMMU_DOMAIN_S2; mutex_unlock(&smmu_domain->init_mutex); return ret; @@ -3769,7 +3760,7 @@ static void arm_smmu_rmr_install_bypass_ste(struct arm_smmu_device *smmu) iort_get_rmr_sids(dev_fwnode(smmu->dev), &rmr_list); list_for_each_entry(e, &rmr_list, list) { - __le64 *step; + struct arm_smmu_ste *step; struct iommu_iort_rmr_data *rmr; int ret, i; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index 925ac6a47bce..65fb388d5173 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -206,6 +206,11 @@ #define STRTAB_L1_DESC_L2PTR_MASK GENMASK_ULL(51, 6) #define STRTAB_STE_DWORDS 8 + +struct arm_smmu_ste { + __le64 data[STRTAB_STE_DWORDS]; +}; + #define STRTAB_STE_0_V (1UL << 0) #define STRTAB_STE_0_CFG GENMASK_ULL(3, 1) #define STRTAB_STE_0_CFG_ABORT 0 @@ -571,7 +576,7 @@ struct arm_smmu_priq { struct arm_smmu_strtab_l1_desc { u8 span; - __le64 *l2ptr; + struct arm_smmu_ste *l2ptr; dma_addr_t l2ptr_dma; }; @@ -710,7 +715,6 @@ struct arm_smmu_master { enum arm_smmu_domain_stage { ARM_SMMU_DOMAIN_S1 = 0, ARM_SMMU_DOMAIN_S2, - ARM_SMMU_DOMAIN_NESTED, ARM_SMMU_DOMAIN_BYPASS, }; diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index 549ae4dba3a6..8b04ece00420 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -243,8 +243,10 @@ static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain, static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = { { .compatible = "qcom,adreno" }, + { .compatible = "qcom,adreno-gmu" }, { .compatible = "qcom,mdp4" }, { .compatible = "qcom,mdss" }, + { .compatible = "qcom,qcm2290-mdss" }, { .compatible = "qcom,sc7180-mdss" }, { .compatible = "qcom,sc7180-mss-pil" }, { .compatible = "qcom,sc7280-mdss" }, diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index d6d1a2a55cc0..68b6bc5e7c71 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -82,6 +82,23 @@ static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu) pm_runtime_put_autosuspend(smmu->dev); } +static void arm_smmu_rpm_use_autosuspend(struct arm_smmu_device *smmu) +{ + /* + * Setup an autosuspend delay to avoid bouncing runpm state. + * Otherwise, if a driver for a suspended consumer device + * unmaps buffers, it will runpm resume/suspend for each one. + * + * For example, when used by a GPU device, when an application + * or game exits, it can trigger unmapping 100s or 1000s of + * buffers. With a runpm cycle for each buffer, that adds up + * to 5-10sec worth of reprogramming the context bank, while + * the system appears to be locked up to the user. + */ + pm_runtime_set_autosuspend_delay(smmu->dev, 20); + pm_runtime_use_autosuspend(smmu->dev); +} + static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom) { return container_of(dom, struct arm_smmu_domain, domain); @@ -392,8 +409,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev) { u32 fsr, fsynr, cbfrsynra; unsigned long iova; - struct iommu_domain *domain = dev; - struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + struct arm_smmu_domain *smmu_domain = dev; struct arm_smmu_device *smmu = smmu_domain->smmu; int idx = smmu_domain->cfg.cbndx; int ret; @@ -406,7 +422,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev) iova = arm_smmu_cb_readq(smmu, idx, ARM_SMMU_CB_FAR); cbfrsynra = arm_smmu_gr1_read(smmu, ARM_SMMU_GR1_CBFRSYNRA(idx)); - ret = report_iommu_fault(domain, NULL, iova, + ret = report_iommu_fault(&smmu_domain->domain, NULL, iova, fsynr & ARM_SMMU_FSYNR0_WNR ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ); if (ret == -ENOSYS) @@ -607,7 +623,7 @@ static int arm_smmu_alloc_context_bank(struct arm_smmu_domain *smmu_domain, return __arm_smmu_alloc_bitmap(smmu->context_map, start, smmu->num_context_banks); } -static int arm_smmu_init_domain_context(struct iommu_domain *domain, +static int arm_smmu_init_domain_context(struct arm_smmu_domain *smmu_domain, struct arm_smmu_device *smmu, struct device *dev) { @@ -616,7 +632,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, struct io_pgtable_ops *pgtbl_ops; struct io_pgtable_cfg pgtbl_cfg; enum io_pgtable_fmt fmt; - struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + struct iommu_domain *domain = &smmu_domain->domain; struct arm_smmu_cfg *cfg = &smmu_domain->cfg; irqreturn_t (*context_fault)(int irq, void *dev); @@ -624,12 +640,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, if (smmu_domain->smmu) goto out_unlock; - if (domain->type == IOMMU_DOMAIN_IDENTITY) { - smmu_domain->stage = ARM_SMMU_DOMAIN_BYPASS; - smmu_domain->smmu = smmu; - goto out_unlock; - } - /* * Mapping the requested stage onto what we support is surprisingly * complicated, mainly because the spec allows S1+S2 SMMUs without @@ -796,8 +806,8 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, else context_fault = arm_smmu_context_fault; - ret = devm_request_irq(smmu->dev, irq, context_fault, - IRQF_SHARED, "arm-smmu-context-fault", domain); + ret = devm_request_irq(smmu->dev, irq, context_fault, IRQF_SHARED, + "arm-smmu-context-fault", smmu_domain); if (ret < 0) { dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n", cfg->irptndx, irq); @@ -818,14 +828,13 @@ out_unlock: return ret; } -static void arm_smmu_destroy_domain_context(struct iommu_domain *domain) +static void arm_smmu_destroy_domain_context(struct arm_smmu_domain *smmu_domain) { - struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct arm_smmu_device *smmu = smmu_domain->smmu; struct arm_smmu_cfg *cfg = &smmu_domain->cfg; int ret, irq; - if (!smmu || domain->type == IOMMU_DOMAIN_IDENTITY) + if (!smmu) return; ret = arm_smmu_rpm_get(smmu); @@ -841,7 +850,7 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain) if (cfg->irptndx != ARM_SMMU_INVALID_IRPTNDX) { irq = smmu->irqs[cfg->irptndx]; - devm_free_irq(smmu->dev, irq, domain); + devm_free_irq(smmu->dev, irq, smmu_domain); } free_io_pgtable_ops(smmu_domain->pgtbl_ops); @@ -850,14 +859,10 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain) arm_smmu_rpm_put(smmu); } -static struct iommu_domain *arm_smmu_domain_alloc(unsigned type) +static struct iommu_domain *arm_smmu_domain_alloc_paging(struct device *dev) { struct arm_smmu_domain *smmu_domain; - if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_IDENTITY) { - if (using_legacy_binding || type != IOMMU_DOMAIN_DMA) - return NULL; - } /* * Allocate the domain and initialise some of its data structures. * We can't really do anything meaningful until we've added a @@ -870,6 +875,15 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type) mutex_init(&smmu_domain->init_mutex); spin_lock_init(&smmu_domain->cb_lock); + if (dev) { + struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev); + + if (arm_smmu_init_domain_context(smmu_domain, cfg->smmu, dev)) { + kfree(smmu_domain); + return NULL; + } + } + return &smmu_domain->domain; } @@ -881,7 +895,7 @@ static void arm_smmu_domain_free(struct iommu_domain *domain) * Free the domain resources. We assume that all devices have * already been detached. */ - arm_smmu_destroy_domain_context(domain); + arm_smmu_destroy_domain_context(smmu_domain); kfree(smmu_domain); } @@ -1081,21 +1095,14 @@ static void arm_smmu_master_free_smes(struct arm_smmu_master_cfg *cfg, mutex_unlock(&smmu->stream_map_mutex); } -static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain, - struct arm_smmu_master_cfg *cfg, - struct iommu_fwspec *fwspec) +static void arm_smmu_master_install_s2crs(struct arm_smmu_master_cfg *cfg, + enum arm_smmu_s2cr_type type, + u8 cbndx, struct iommu_fwspec *fwspec) { - struct arm_smmu_device *smmu = smmu_domain->smmu; + struct arm_smmu_device *smmu = cfg->smmu; struct arm_smmu_s2cr *s2cr = smmu->s2crs; - u8 cbndx = smmu_domain->cfg.cbndx; - enum arm_smmu_s2cr_type type; int i, idx; - if (smmu_domain->stage == ARM_SMMU_DOMAIN_BYPASS) - type = S2CR_TYPE_BYPASS; - else - type = S2CR_TYPE_TRANS; - for_each_cfg_sme(cfg, fwspec, i, idx) { if (type == s2cr[idx].type && cbndx == s2cr[idx].cbndx) continue; @@ -1105,7 +1112,6 @@ static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain, s2cr[idx].cbndx = cbndx; arm_smmu_write_s2cr(smmu, idx); } - return 0; } static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) @@ -1116,11 +1122,6 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) struct arm_smmu_device *smmu; int ret; - if (!fwspec || fwspec->ops != &arm_smmu_ops) { - dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n"); - return -ENXIO; - } - /* * FIXME: The arch/arm DMA API code tries to attach devices to its own * domains between of_xlate() and probe_device() - we have no way to cope @@ -1139,7 +1140,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) return ret; /* Ensure that the domain is finalised */ - ret = arm_smmu_init_domain_context(domain, smmu, dev); + ret = arm_smmu_init_domain_context(smmu_domain, smmu, dev); if (ret < 0) goto rpm_put; @@ -1153,27 +1154,66 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) } /* Looks ok, so add the device to the domain */ - ret = arm_smmu_domain_add_master(smmu_domain, cfg, fwspec); - - /* - * Setup an autosuspend delay to avoid bouncing runpm state. - * Otherwise, if a driver for a suspended consumer device - * unmaps buffers, it will runpm resume/suspend for each one. - * - * For example, when used by a GPU device, when an application - * or game exits, it can trigger unmapping 100s or 1000s of - * buffers. With a runpm cycle for each buffer, that adds up - * to 5-10sec worth of reprogramming the context bank, while - * the system appears to be locked up to the user. - */ - pm_runtime_set_autosuspend_delay(smmu->dev, 20); - pm_runtime_use_autosuspend(smmu->dev); - + arm_smmu_master_install_s2crs(cfg, S2CR_TYPE_TRANS, + smmu_domain->cfg.cbndx, fwspec); + arm_smmu_rpm_use_autosuspend(smmu); rpm_put: arm_smmu_rpm_put(smmu); return ret; } +static int arm_smmu_attach_dev_type(struct device *dev, + enum arm_smmu_s2cr_type type) +{ + struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev); + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + struct arm_smmu_device *smmu; + int ret; + + if (!cfg) + return -ENODEV; + smmu = cfg->smmu; + + ret = arm_smmu_rpm_get(smmu); + if (ret < 0) + return ret; + + arm_smmu_master_install_s2crs(cfg, type, 0, fwspec); + arm_smmu_rpm_use_autosuspend(smmu); + arm_smmu_rpm_put(smmu); + return 0; +} + +static int arm_smmu_attach_dev_identity(struct iommu_domain *domain, + struct device *dev) +{ + return arm_smmu_attach_dev_type(dev, S2CR_TYPE_BYPASS); +} + +static const struct iommu_domain_ops arm_smmu_identity_ops = { + .attach_dev = arm_smmu_attach_dev_identity, +}; + +static struct iommu_domain arm_smmu_identity_domain = { + .type = IOMMU_DOMAIN_IDENTITY, + .ops = &arm_smmu_identity_ops, +}; + +static int arm_smmu_attach_dev_blocked(struct iommu_domain *domain, + struct device *dev) +{ + return arm_smmu_attach_dev_type(dev, S2CR_TYPE_FAULT); +} + +static const struct iommu_domain_ops arm_smmu_blocked_ops = { + .attach_dev = arm_smmu_attach_dev_blocked, +}; + +static struct iommu_domain arm_smmu_blocked_domain = { + .type = IOMMU_DOMAIN_BLOCKED, + .ops = &arm_smmu_blocked_ops, +}; + static int arm_smmu_map_pages(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t pgsize, size_t pgcount, int prot, gfp_t gfp, size_t *mapped) @@ -1357,10 +1397,8 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev) fwspec = dev_iommu_fwspec_get(dev); if (ret) goto out_free; - } else if (fwspec && fwspec->ops == &arm_smmu_ops) { - smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode); } else { - return ERR_PTR(-ENODEV); + smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode); } ret = -EINVAL; @@ -1427,7 +1465,6 @@ static void arm_smmu_release_device(struct device *dev) arm_smmu_rpm_put(cfg->smmu); - dev_iommu_priv_set(dev, NULL); kfree(cfg); } @@ -1560,8 +1597,10 @@ static int arm_smmu_def_domain_type(struct device *dev) } static struct iommu_ops arm_smmu_ops = { + .identity_domain = &arm_smmu_identity_domain, + .blocked_domain = &arm_smmu_blocked_domain, .capable = arm_smmu_capable, - .domain_alloc = arm_smmu_domain_alloc, + .domain_alloc_paging = arm_smmu_domain_alloc_paging, .probe_device = arm_smmu_probe_device, .release_device = arm_smmu_release_device, .probe_finalize = arm_smmu_probe_finalize, @@ -2161,7 +2200,8 @@ static int arm_smmu_device_probe(struct platform_device *pdev) return err; } - err = iommu_device_register(&smmu->iommu, &arm_smmu_ops, dev); + err = iommu_device_register(&smmu->iommu, &arm_smmu_ops, + using_legacy_binding ? NULL : dev); if (err) { dev_err(dev, "Failed to register iommu\n"); iommu_device_sysfs_remove(&smmu->iommu); diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h index 703fd5817ec1..836ed6799a80 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.h +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h @@ -361,7 +361,6 @@ enum arm_smmu_domain_stage { ARM_SMMU_DOMAIN_S1 = 0, ARM_SMMU_DOMAIN_S2, ARM_SMMU_DOMAIN_NESTED, - ARM_SMMU_DOMAIN_BYPASS, }; struct arm_smmu_domain { diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c index 97b2122032b2..17a1c163fef6 100644 --- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c +++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c @@ -79,16 +79,6 @@ static struct qcom_iommu_domain *to_qcom_iommu_domain(struct iommu_domain *dom) static const struct iommu_ops qcom_iommu_ops; -static struct qcom_iommu_dev * to_iommu(struct device *dev) -{ - struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - - if (!fwspec || fwspec->ops != &qcom_iommu_ops) - return NULL; - - return dev_iommu_priv_get(dev); -} - static struct qcom_iommu_ctx * to_ctx(struct qcom_iommu_domain *d, unsigned asid) { struct qcom_iommu_dev *qcom_iommu = d->iommu; @@ -372,7 +362,7 @@ static void qcom_iommu_domain_free(struct iommu_domain *domain) static int qcom_iommu_attach_dev(struct iommu_domain *domain, struct device *dev) { - struct qcom_iommu_dev *qcom_iommu = to_iommu(dev); + struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev); struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain); int ret; @@ -404,7 +394,7 @@ static int qcom_iommu_identity_attach(struct iommu_domain *identity_domain, struct iommu_domain *domain = iommu_get_domain_for_dev(dev); struct qcom_iommu_domain *qcom_domain; struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct qcom_iommu_dev *qcom_iommu = to_iommu(dev); + struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev); unsigned int i; if (domain == identity_domain || !domain) @@ -535,7 +525,7 @@ static bool qcom_iommu_capable(struct device *dev, enum iommu_cap cap) static struct iommu_device *qcom_iommu_probe_device(struct device *dev) { - struct qcom_iommu_dev *qcom_iommu = to_iommu(dev); + struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev); struct device_link *link; if (!qcom_iommu) @@ -900,8 +890,16 @@ static void qcom_iommu_device_remove(struct platform_device *pdev) static int __maybe_unused qcom_iommu_resume(struct device *dev) { struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(dev); + int ret; + + ret = clk_bulk_prepare_enable(CLK_NUM, qcom_iommu->clks); + if (ret < 0) + return ret; + + if (dev->pm_domain) + return qcom_scm_restore_sec_cfg(qcom_iommu->sec_id, 0); - return clk_bulk_prepare_enable(CLK_NUM, qcom_iommu->clks); + return ret; } static int __maybe_unused qcom_iommu_suspend(struct device *dev) diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index e59f50e11ea8..50ccc4f1ef81 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -29,6 +29,7 @@ #include <linux/spinlock.h> #include <linux/swiotlb.h> #include <linux/vmalloc.h> +#include <trace/events/swiotlb.h> #include "dma-iommu.h" @@ -1156,6 +1157,8 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, return DMA_MAPPING_ERROR; } + trace_swiotlb_bounced(dev, phys, size); + aligned_size = iova_align(iovad, size); phys = swiotlb_tbl_map_single(dev, phys, size, aligned_size, iova_mask(iovad), dir, attrs); diff --git a/drivers/iommu/intel/debugfs.c b/drivers/iommu/intel/debugfs.c index dee61e513be6..86b506af7daa 100644 --- a/drivers/iommu/intel/debugfs.c +++ b/drivers/iommu/intel/debugfs.c @@ -106,9 +106,6 @@ static const struct iommu_regset iommu_regs_64[] = { IOMMU_REGSET_ENTRY(MTRR_PHYSMASK8), IOMMU_REGSET_ENTRY(MTRR_PHYSBASE9), IOMMU_REGSET_ENTRY(MTRR_PHYSMASK9), - IOMMU_REGSET_ENTRY(VCCAP), - IOMMU_REGSET_ENTRY(VCMD), - IOMMU_REGSET_ENTRY(VCRSP), }; static struct dentry *intel_iommu_debug; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 897159dba47d..6fb5f6fceea1 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -46,9 +46,6 @@ #define DEFAULT_DOMAIN_ADDRESS_WIDTH 57 -#define MAX_AGAW_WIDTH 64 -#define MAX_AGAW_PFN_WIDTH (MAX_AGAW_WIDTH - VTD_PAGE_SHIFT) - #define __DOMAIN_MAX_PFN(gaw) ((((uint64_t)1) << ((gaw) - VTD_PAGE_SHIFT)) - 1) #define __DOMAIN_MAX_ADDR(gaw) ((((uint64_t)1) << (gaw)) - 1) @@ -63,74 +60,6 @@ #define IOVA_PFN(addr) ((addr) >> PAGE_SHIFT) -/* page table handling */ -#define LEVEL_STRIDE (9) -#define LEVEL_MASK (((u64)1 << LEVEL_STRIDE) - 1) - -static inline int agaw_to_level(int agaw) -{ - return agaw + 2; -} - -static inline int agaw_to_width(int agaw) -{ - return min_t(int, 30 + agaw * LEVEL_STRIDE, MAX_AGAW_WIDTH); -} - -static inline int width_to_agaw(int width) -{ - return DIV_ROUND_UP(width - 30, LEVEL_STRIDE); -} - -static inline unsigned int level_to_offset_bits(int level) -{ - return (level - 1) * LEVEL_STRIDE; -} - -static inline int pfn_level_offset(u64 pfn, int level) -{ - return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK; -} - -static inline u64 level_mask(int level) -{ - return -1ULL << level_to_offset_bits(level); -} - -static inline u64 level_size(int level) -{ - return 1ULL << level_to_offset_bits(level); -} - -static inline u64 align_to_level(u64 pfn, int level) -{ - return (pfn + level_size(level) - 1) & level_mask(level); -} - -static inline unsigned long lvl_to_nr_pages(unsigned int lvl) -{ - return 1UL << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH); -} - -/* VT-d pages must always be _smaller_ than MM pages. Otherwise things - are never going to work. */ -static inline unsigned long mm_to_dma_pfn_start(unsigned long mm_pfn) -{ - return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT); -} -static inline unsigned long mm_to_dma_pfn_end(unsigned long mm_pfn) -{ - return ((mm_pfn + 1) << (PAGE_SHIFT - VTD_PAGE_SHIFT)) - 1; -} -static inline unsigned long page_to_dma_pfn(struct page *pg) -{ - return mm_to_dma_pfn_start(page_to_pfn(pg)); -} -static inline unsigned long virt_to_dma_pfn(void *p) -{ - return page_to_dma_pfn(virt_to_page(p)); -} - static void __init check_tylersburg_isoch(void); static int rwbf_quirk; @@ -168,78 +97,6 @@ static phys_addr_t root_entry_uctp(struct root_entry *re) return re->hi & VTD_PAGE_MASK; } -static inline void context_set_present(struct context_entry *context) -{ - context->lo |= 1; -} - -static inline void context_set_fault_enable(struct context_entry *context) -{ - context->lo &= (((u64)-1) << 2) | 1; -} - -static inline void context_set_translation_type(struct context_entry *context, - unsigned long value) -{ - context->lo &= (((u64)-1) << 4) | 3; - context->lo |= (value & 3) << 2; -} - -static inline void context_set_address_root(struct context_entry *context, - unsigned long value) -{ - context->lo &= ~VTD_PAGE_MASK; - context->lo |= value & VTD_PAGE_MASK; -} - -static inline void context_set_address_width(struct context_entry *context, - unsigned long value) -{ - context->hi |= value & 7; -} - -static inline void context_set_domain_id(struct context_entry *context, - unsigned long value) -{ - context->hi |= (value & ((1 << 16) - 1)) << 8; -} - -static inline void context_set_pasid(struct context_entry *context) -{ - context->lo |= CONTEXT_PASIDE; -} - -static inline int context_domain_id(struct context_entry *c) -{ - return((c->hi >> 8) & 0xffff); -} - -static inline void context_clear_entry(struct context_entry *context) -{ - context->lo = 0; - context->hi = 0; -} - -static inline bool context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn) -{ - if (!iommu->copied_tables) - return false; - - return test_bit(((long)bus << 8) | devfn, iommu->copied_tables); -} - -static inline void -set_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn) -{ - set_bit(((long)bus << 8) | devfn, iommu->copied_tables); -} - -static inline void -clear_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn) -{ - clear_bit(((long)bus << 8) | devfn, iommu->copied_tables); -} - /* * This domain is a statically identity mapping domain. * 1. This domain creats a static 1:1 mapping to all usable memory. @@ -383,13 +240,12 @@ void free_pgtable_page(void *vaddr) free_page((unsigned long)vaddr); } -static inline int domain_type_is_si(struct dmar_domain *domain) +static int domain_type_is_si(struct dmar_domain *domain) { return domain->domain.type == IOMMU_DOMAIN_IDENTITY; } -static inline int domain_pfn_supported(struct dmar_domain *domain, - unsigned long pfn) +static int domain_pfn_supported(struct dmar_domain *domain, unsigned long pfn) { int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; @@ -451,7 +307,7 @@ int iommu_calculate_agaw(struct intel_iommu *iommu) return __iommu_calculate_agaw(iommu, DEFAULT_DOMAIN_ADDRESS_WIDTH); } -static inline bool iommu_paging_structure_coherency(struct intel_iommu *iommu) +static bool iommu_paging_structure_coherency(struct intel_iommu *iommu) { return sm_supported(iommu) ? ecap_smpwc(iommu->ecap) : ecap_coherent(iommu->ecap); @@ -703,7 +559,7 @@ static bool iommu_is_dummy(struct intel_iommu *iommu, struct device *dev) return false; } -struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn) +static struct intel_iommu *device_lookup_iommu(struct device *dev, u8 *bus, u8 *devfn) { struct dmar_drhd_unit *drhd = NULL; struct pci_dev *pdev = NULL; @@ -1574,9 +1430,8 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, } /* Notification for newly created mappings */ -static inline void __mapping_notify_one(struct intel_iommu *iommu, - struct dmar_domain *domain, - unsigned long pfn, unsigned int pages) +static void __mapping_notify_one(struct intel_iommu *iommu, struct dmar_domain *domain, + unsigned long pfn, unsigned int pages) { /* * It's a non-present to present mapping. Only flush if caching mode @@ -1843,7 +1698,7 @@ void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu) spin_unlock(&iommu->lock); } -static inline int guestwidth_to_adjustwidth(int gaw) +static int guestwidth_to_adjustwidth(int gaw) { int agaw; int r = (gaw - 12) % 9; @@ -1877,7 +1732,7 @@ static void domain_exit(struct dmar_domain *domain) * Value of X in the PDTS field of a scalable mode context entry * indicates PASID directory with 2^(X + 7) entries. */ -static inline unsigned long context_get_sm_pds(struct pasid_table *table) +static unsigned long context_get_sm_pds(struct pasid_table *table) { unsigned long pds, max_pde; @@ -1889,38 +1744,6 @@ static inline unsigned long context_get_sm_pds(struct pasid_table *table) return pds - 7; } -/* - * Set the RID_PASID field of a scalable mode context entry. The - * IOMMU hardware will use the PASID value set in this field for - * DMA translations of DMA requests without PASID. - */ -static inline void -context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid) -{ - context->hi |= pasid & ((1 << 20) - 1); -} - -/* - * Set the DTE(Device-TLB Enable) field of a scalable mode context - * entry. - */ -static inline void context_set_sm_dte(struct context_entry *context) -{ - context->lo |= BIT_ULL(2); -} - -/* - * Set the PRE(Page Request Enable) field of a scalable mode context - * entry. - */ -static inline void context_set_sm_pre(struct context_entry *context) -{ - context->lo |= BIT_ULL(4); -} - -/* Convert value to context PASID directory size field coding. */ -#define context_pdts(pds) (((pds) & 0x7) << 9) - static int domain_context_mapping_one(struct dmar_domain *domain, struct intel_iommu *iommu, struct pasid_table *table, @@ -2081,14 +1904,11 @@ static int domain_context_mapping_cb(struct pci_dev *pdev, static int domain_context_mapping(struct dmar_domain *domain, struct device *dev) { + struct device_domain_info *info = dev_iommu_priv_get(dev); struct domain_context_mapping_data data; + struct intel_iommu *iommu = info->iommu; + u8 bus = info->bus, devfn = info->devfn; struct pasid_table *table; - struct intel_iommu *iommu; - u8 bus, devfn; - - iommu = device_to_iommu(dev, &bus, &devfn); - if (!iommu) - return -ENODEV; table = intel_pasid_get_table(dev); @@ -2105,18 +1925,15 @@ domain_context_mapping(struct dmar_domain *domain, struct device *dev) } /* Returns a number of VTD pages, but aligned to MM page size */ -static inline unsigned long aligned_nrpages(unsigned long host_addr, - size_t size) +static unsigned long aligned_nrpages(unsigned long host_addr, size_t size) { host_addr &= ~PAGE_MASK; return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT; } /* Return largest possible superpage level for a given mapping */ -static inline int hardware_largepage_caps(struct dmar_domain *domain, - unsigned long iov_pfn, - unsigned long phy_pfn, - unsigned long pages) +static int hardware_largepage_caps(struct dmar_domain *domain, unsigned long iov_pfn, + unsigned long phy_pfn, unsigned long pages) { int support, level = 1; unsigned long pfnmerge; @@ -2449,15 +2266,10 @@ static int dmar_domain_attach_device(struct dmar_domain *domain, struct device *dev) { struct device_domain_info *info = dev_iommu_priv_get(dev); - struct intel_iommu *iommu; + struct intel_iommu *iommu = info->iommu; unsigned long flags; - u8 bus, devfn; int ret; - iommu = device_to_iommu(dev, &bus, &devfn); - if (!iommu) - return -ENODEV; - ret = domain_attach_iommu(domain, iommu); if (ret) return ret; @@ -2470,7 +2282,7 @@ static int dmar_domain_attach_device(struct dmar_domain *domain, if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) { /* Setup the PASID entry for requests without PASID: */ if (hw_pass_through && domain_type_is_si(domain)) - ret = intel_pasid_setup_pass_through(iommu, domain, + ret = intel_pasid_setup_pass_through(iommu, dev, IOMMU_NO_PASID); else if (domain->use_first_level) ret = domain_setup_first_level(iommu, domain, dev, @@ -3615,7 +3427,7 @@ void intel_iommu_shutdown(void) up_write(&dmar_global_lock); } -static inline struct intel_iommu *dev_to_intel_iommu(struct device *dev) +static struct intel_iommu *dev_to_intel_iommu(struct device *dev) { struct iommu_device *iommu_dev = dev_to_iommu_device(dev); @@ -3694,7 +3506,7 @@ const struct attribute_group *intel_iommu_groups[] = { NULL, }; -static inline bool has_external_pci(void) +static bool has_external_pci(void) { struct pci_dev *pdev = NULL; @@ -4119,14 +3931,11 @@ static void intel_iommu_domain_free(struct iommu_domain *domain) int prepare_domain_attach_device(struct iommu_domain *domain, struct device *dev) { + struct device_domain_info *info = dev_iommu_priv_get(dev); struct dmar_domain *dmar_domain = to_dmar_domain(domain); - struct intel_iommu *iommu; + struct intel_iommu *iommu = info->iommu; int addr_width; - iommu = device_to_iommu(dev, NULL, NULL); - if (!iommu) - return -ENODEV; - if (dmar_domain->force_snooping && !ecap_sc_support(iommu->ecap)) return -EINVAL; @@ -4403,7 +4212,7 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev) u8 bus, devfn; int ret; - iommu = device_to_iommu(dev, &bus, &devfn); + iommu = device_lookup_iommu(dev, &bus, &devfn); if (!iommu || !iommu->iommu.ops) return ERR_PTR(-ENODEV); @@ -4461,7 +4270,6 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev) ret = intel_pasid_alloc_table(dev); if (ret) { dev_err(dev, "PASID table allocation failed\n"); - dev_iommu_priv_set(dev, NULL); kfree(info); return ERR_PTR(ret); } @@ -4479,7 +4287,6 @@ static void intel_iommu_release_device(struct device *dev) dmar_remove_one_dev_info(dev); intel_pasid_free_table(dev); intel_iommu_debugfs_remove_dev(info); - dev_iommu_priv_set(dev, NULL); kfree(info); set_dma_ops(dev, NULL); } @@ -4739,8 +4546,9 @@ static int intel_iommu_iotlb_sync_map(struct iommu_domain *domain, static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid) { - struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL); + struct device_domain_info *info = dev_iommu_priv_get(dev); struct dev_pasid_info *curr, *dev_pasid = NULL; + struct intel_iommu *iommu = info->iommu; struct dmar_domain *dmar_domain; struct iommu_domain *domain; unsigned long flags; @@ -4811,8 +4619,7 @@ static int intel_iommu_set_dev_pasid(struct iommu_domain *domain, goto out_free; if (domain_type_is_si(dmar_domain)) - ret = intel_pasid_setup_pass_through(iommu, dmar_domain, - dev, pasid); + ret = intel_pasid_setup_pass_through(iommu, dev, pasid); else if (dmar_domain->use_first_level) ret = domain_setup_first_level(iommu, dmar_domain, dev, pasid); diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index ce030c5b5772..d02f916d8e59 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -140,9 +140,6 @@ #define DMAR_ECEO_REG 0x408 #define DMAR_ECRSP_REG 0x410 #define DMAR_ECCAP_REG 0x430 -#define DMAR_VCCAP_REG 0xe30 /* Virtual command capability register */ -#define DMAR_VCMD_REG 0xe00 /* Virtual command register */ -#define DMAR_VCRSP_REG 0xe10 /* Virtual command response register */ #define DMAR_IQER_REG_IQEI(reg) FIELD_GET(GENMASK_ULL(3, 0), reg) #define DMAR_IQER_REG_ITESID(reg) FIELD_GET(GENMASK_ULL(47, 32), reg) @@ -854,6 +851,181 @@ static inline bool context_present(struct context_entry *context) return (context->lo & 1); } +#define LEVEL_STRIDE (9) +#define LEVEL_MASK (((u64)1 << LEVEL_STRIDE) - 1) +#define MAX_AGAW_WIDTH (64) +#define MAX_AGAW_PFN_WIDTH (MAX_AGAW_WIDTH - VTD_PAGE_SHIFT) + +static inline int agaw_to_level(int agaw) +{ + return agaw + 2; +} + +static inline int agaw_to_width(int agaw) +{ + return min_t(int, 30 + agaw * LEVEL_STRIDE, MAX_AGAW_WIDTH); +} + +static inline int width_to_agaw(int width) +{ + return DIV_ROUND_UP(width - 30, LEVEL_STRIDE); +} + +static inline unsigned int level_to_offset_bits(int level) +{ + return (level - 1) * LEVEL_STRIDE; +} + +static inline int pfn_level_offset(u64 pfn, int level) +{ + return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK; +} + +static inline u64 level_mask(int level) +{ + return -1ULL << level_to_offset_bits(level); +} + +static inline u64 level_size(int level) +{ + return 1ULL << level_to_offset_bits(level); +} + +static inline u64 align_to_level(u64 pfn, int level) +{ + return (pfn + level_size(level) - 1) & level_mask(level); +} + +static inline unsigned long lvl_to_nr_pages(unsigned int lvl) +{ + return 1UL << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH); +} + +/* VT-d pages must always be _smaller_ than MM pages. Otherwise things + are never going to work. */ +static inline unsigned long mm_to_dma_pfn_start(unsigned long mm_pfn) +{ + return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT); +} +static inline unsigned long mm_to_dma_pfn_end(unsigned long mm_pfn) +{ + return ((mm_pfn + 1) << (PAGE_SHIFT - VTD_PAGE_SHIFT)) - 1; +} +static inline unsigned long page_to_dma_pfn(struct page *pg) +{ + return mm_to_dma_pfn_start(page_to_pfn(pg)); +} +static inline unsigned long virt_to_dma_pfn(void *p) +{ + return page_to_dma_pfn(virt_to_page(p)); +} + +static inline void context_set_present(struct context_entry *context) +{ + context->lo |= 1; +} + +static inline void context_set_fault_enable(struct context_entry *context) +{ + context->lo &= (((u64)-1) << 2) | 1; +} + +static inline void context_set_translation_type(struct context_entry *context, + unsigned long value) +{ + context->lo &= (((u64)-1) << 4) | 3; + context->lo |= (value & 3) << 2; +} + +static inline void context_set_address_root(struct context_entry *context, + unsigned long value) +{ + context->lo &= ~VTD_PAGE_MASK; + context->lo |= value & VTD_PAGE_MASK; +} + +static inline void context_set_address_width(struct context_entry *context, + unsigned long value) +{ + context->hi |= value & 7; +} + +static inline void context_set_domain_id(struct context_entry *context, + unsigned long value) +{ + context->hi |= (value & ((1 << 16) - 1)) << 8; +} + +static inline void context_set_pasid(struct context_entry *context) +{ + context->lo |= CONTEXT_PASIDE; +} + +static inline int context_domain_id(struct context_entry *c) +{ + return((c->hi >> 8) & 0xffff); +} + +static inline void context_clear_entry(struct context_entry *context) +{ + context->lo = 0; + context->hi = 0; +} + +#ifdef CONFIG_INTEL_IOMMU +static inline bool context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn) +{ + if (!iommu->copied_tables) + return false; + + return test_bit(((long)bus << 8) | devfn, iommu->copied_tables); +} + +static inline void +set_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn) +{ + set_bit(((long)bus << 8) | devfn, iommu->copied_tables); +} + +static inline void +clear_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn) +{ + clear_bit(((long)bus << 8) | devfn, iommu->copied_tables); +} +#endif /* CONFIG_INTEL_IOMMU */ + +/* + * Set the RID_PASID field of a scalable mode context entry. The + * IOMMU hardware will use the PASID value set in this field for + * DMA translations of DMA requests without PASID. + */ +static inline void +context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid) +{ + context->hi |= pasid & ((1 << 20) - 1); +} + +/* + * Set the DTE(Device-TLB Enable) field of a scalable mode context + * entry. + */ +static inline void context_set_sm_dte(struct context_entry *context) +{ + context->lo |= BIT_ULL(2); +} + +/* + * Set the PRE(Page Request Enable) field of a scalable mode context + * entry. + */ +static inline void context_set_sm_pre(struct context_entry *context) +{ + context->lo |= BIT_ULL(4); +} + +/* Convert value to context PASID directory size field coding. */ +#define context_pdts(pds) (((pds) & 0x7) << 9) + struct dmar_drhd_unit *dmar_find_matched_drhd_unit(struct pci_dev *dev); int dmar_enable_qi(struct intel_iommu *iommu); @@ -900,7 +1072,6 @@ int dmar_ir_support(void); void *alloc_pgtable_page(int node, gfp_t gfp); void free_pgtable_page(void *vaddr); void iommu_flush_write_buffer(struct intel_iommu *iommu); -struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn); struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent, const struct iommu_user_data *user_data); diff --git a/drivers/iommu/intel/nested.c b/drivers/iommu/intel/nested.c index b5a5563ab32c..f26c7f1c46cc 100644 --- a/drivers/iommu/intel/nested.c +++ b/drivers/iommu/intel/nested.c @@ -73,9 +73,97 @@ static void intel_nested_domain_free(struct iommu_domain *domain) kfree(to_dmar_domain(domain)); } +static void nested_flush_dev_iotlb(struct dmar_domain *domain, u64 addr, + unsigned int mask) +{ + struct device_domain_info *info; + unsigned long flags; + u16 sid, qdep; + + spin_lock_irqsave(&domain->lock, flags); + list_for_each_entry(info, &domain->devices, link) { + if (!info->ats_enabled) + continue; + sid = info->bus << 8 | info->devfn; + qdep = info->ats_qdep; + qi_flush_dev_iotlb(info->iommu, sid, info->pfsid, + qdep, addr, mask); + quirk_extra_dev_tlb_flush(info, addr, mask, + IOMMU_NO_PASID, qdep); + } + spin_unlock_irqrestore(&domain->lock, flags); +} + +static void intel_nested_flush_cache(struct dmar_domain *domain, u64 addr, + unsigned long npages, bool ih) +{ + struct iommu_domain_info *info; + unsigned int mask; + unsigned long i; + + xa_for_each(&domain->iommu_array, i, info) + qi_flush_piotlb(info->iommu, + domain_id_iommu(domain, info->iommu), + IOMMU_NO_PASID, addr, npages, ih); + + if (!domain->has_iotlb_device) + return; + + if (npages == U64_MAX) + mask = 64 - VTD_PAGE_SHIFT; + else + mask = ilog2(__roundup_pow_of_two(npages)); + + nested_flush_dev_iotlb(domain, addr, mask); +} + +static int intel_nested_cache_invalidate_user(struct iommu_domain *domain, + struct iommu_user_data_array *array) +{ + struct dmar_domain *dmar_domain = to_dmar_domain(domain); + struct iommu_hwpt_vtd_s1_invalidate inv_entry; + u32 index, processed = 0; + int ret = 0; + + if (array->type != IOMMU_HWPT_INVALIDATE_DATA_VTD_S1) { + ret = -EINVAL; + goto out; + } + + for (index = 0; index < array->entry_num; index++) { + ret = iommu_copy_struct_from_user_array(&inv_entry, array, + IOMMU_HWPT_INVALIDATE_DATA_VTD_S1, + index, __reserved); + if (ret) + break; + + if ((inv_entry.flags & ~IOMMU_VTD_INV_FLAGS_LEAF) || + inv_entry.__reserved) { + ret = -EOPNOTSUPP; + break; + } + + if (!IS_ALIGNED(inv_entry.addr, VTD_PAGE_SIZE) || + ((inv_entry.npages == U64_MAX) && inv_entry.addr)) { + ret = -EINVAL; + break; + } + + intel_nested_flush_cache(dmar_domain, inv_entry.addr, + inv_entry.npages, + inv_entry.flags & IOMMU_VTD_INV_FLAGS_LEAF); + processed++; + } + +out: + array->entry_num = processed; + return ret; +} + static const struct iommu_domain_ops intel_nested_domain_ops = { .attach_dev = intel_nested_attach_dev, .free = intel_nested_domain_free, + .cache_invalidate_user = intel_nested_cache_invalidate_user, }; struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent, diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index 74e8e4c17e81..3239cefa4c33 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -26,63 +26,6 @@ */ u32 intel_pasid_max_id = PASID_MAX; -int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid) -{ - unsigned long flags; - u8 status_code; - int ret = 0; - u64 res; - - raw_spin_lock_irqsave(&iommu->register_lock, flags); - dmar_writeq(iommu->reg + DMAR_VCMD_REG, VCMD_CMD_ALLOC); - IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq, - !(res & VCMD_VRSP_IP), res); - raw_spin_unlock_irqrestore(&iommu->register_lock, flags); - - status_code = VCMD_VRSP_SC(res); - switch (status_code) { - case VCMD_VRSP_SC_SUCCESS: - *pasid = VCMD_VRSP_RESULT_PASID(res); - break; - case VCMD_VRSP_SC_NO_PASID_AVAIL: - pr_info("IOMMU: %s: No PASID available\n", iommu->name); - ret = -ENOSPC; - break; - default: - ret = -ENODEV; - pr_warn("IOMMU: %s: Unexpected error code %d\n", - iommu->name, status_code); - } - - return ret; -} - -void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid) -{ - unsigned long flags; - u8 status_code; - u64 res; - - raw_spin_lock_irqsave(&iommu->register_lock, flags); - dmar_writeq(iommu->reg + DMAR_VCMD_REG, - VCMD_CMD_OPERAND(pasid) | VCMD_CMD_FREE); - IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq, - !(res & VCMD_VRSP_IP), res); - raw_spin_unlock_irqrestore(&iommu->register_lock, flags); - - status_code = VCMD_VRSP_SC(res); - switch (status_code) { - case VCMD_VRSP_SC_SUCCESS: - break; - case VCMD_VRSP_SC_INVALID_PASID: - pr_info("IOMMU: %s: Invalid PASID\n", iommu->name); - break; - default: - pr_warn("IOMMU: %s: Unexpected error code %d\n", - iommu->name, status_code); - } -} - /* * Per device pasid table management: */ @@ -230,30 +173,6 @@ retry: /* * Interfaces for PASID table entry manipulation: */ -static inline void pasid_clear_entry(struct pasid_entry *pe) -{ - WRITE_ONCE(pe->val[0], 0); - WRITE_ONCE(pe->val[1], 0); - WRITE_ONCE(pe->val[2], 0); - WRITE_ONCE(pe->val[3], 0); - WRITE_ONCE(pe->val[4], 0); - WRITE_ONCE(pe->val[5], 0); - WRITE_ONCE(pe->val[6], 0); - WRITE_ONCE(pe->val[7], 0); -} - -static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe) -{ - WRITE_ONCE(pe->val[0], PASID_PTE_FPD); - WRITE_ONCE(pe->val[1], 0); - WRITE_ONCE(pe->val[2], 0); - WRITE_ONCE(pe->val[3], 0); - WRITE_ONCE(pe->val[4], 0); - WRITE_ONCE(pe->val[5], 0); - WRITE_ONCE(pe->val[6], 0); - WRITE_ONCE(pe->val[7], 0); -} - static void intel_pasid_clear_entry(struct device *dev, u32 pasid, bool fault_ignore) { @@ -269,192 +188,6 @@ intel_pasid_clear_entry(struct device *dev, u32 pasid, bool fault_ignore) pasid_clear_entry(pe); } -static inline void pasid_set_bits(u64 *ptr, u64 mask, u64 bits) -{ - u64 old; - - old = READ_ONCE(*ptr); - WRITE_ONCE(*ptr, (old & ~mask) | bits); -} - -static inline u64 pasid_get_bits(u64 *ptr) -{ - return READ_ONCE(*ptr); -} - -/* - * Setup the DID(Domain Identifier) field (Bit 64~79) of scalable mode - * PASID entry. - */ -static inline void -pasid_set_domain_id(struct pasid_entry *pe, u64 value) -{ - pasid_set_bits(&pe->val[1], GENMASK_ULL(15, 0), value); -} - -/* - * Get domain ID value of a scalable mode PASID entry. - */ -static inline u16 -pasid_get_domain_id(struct pasid_entry *pe) -{ - return (u16)(READ_ONCE(pe->val[1]) & GENMASK_ULL(15, 0)); -} - -/* - * Setup the SLPTPTR(Second Level Page Table Pointer) field (Bit 12~63) - * of a scalable mode PASID entry. - */ -static inline void -pasid_set_slptr(struct pasid_entry *pe, u64 value) -{ - pasid_set_bits(&pe->val[0], VTD_PAGE_MASK, value); -} - -/* - * Setup the AW(Address Width) field (Bit 2~4) of a scalable mode PASID - * entry. - */ -static inline void -pasid_set_address_width(struct pasid_entry *pe, u64 value) -{ - pasid_set_bits(&pe->val[0], GENMASK_ULL(4, 2), value << 2); -} - -/* - * Setup the PGTT(PASID Granular Translation Type) field (Bit 6~8) - * of a scalable mode PASID entry. - */ -static inline void -pasid_set_translation_type(struct pasid_entry *pe, u64 value) -{ - pasid_set_bits(&pe->val[0], GENMASK_ULL(8, 6), value << 6); -} - -/* - * Enable fault processing by clearing the FPD(Fault Processing - * Disable) field (Bit 1) of a scalable mode PASID entry. - */ -static inline void pasid_set_fault_enable(struct pasid_entry *pe) -{ - pasid_set_bits(&pe->val[0], 1 << 1, 0); -} - -/* - * Enable second level A/D bits by setting the SLADE (Second Level - * Access Dirty Enable) field (Bit 9) of a scalable mode PASID - * entry. - */ -static inline void pasid_set_ssade(struct pasid_entry *pe) -{ - pasid_set_bits(&pe->val[0], 1 << 9, 1 << 9); -} - -/* - * Disable second level A/D bits by clearing the SLADE (Second Level - * Access Dirty Enable) field (Bit 9) of a scalable mode PASID - * entry. - */ -static inline void pasid_clear_ssade(struct pasid_entry *pe) -{ - pasid_set_bits(&pe->val[0], 1 << 9, 0); -} - -/* - * Checks if second level A/D bits specifically the SLADE (Second Level - * Access Dirty Enable) field (Bit 9) of a scalable mode PASID - * entry is set. - */ -static inline bool pasid_get_ssade(struct pasid_entry *pe) -{ - return pasid_get_bits(&pe->val[0]) & (1 << 9); -} - -/* - * Setup the SRE(Supervisor Request Enable) field (Bit 128) of a - * scalable mode PASID entry. - */ -static inline void pasid_set_sre(struct pasid_entry *pe) -{ - pasid_set_bits(&pe->val[2], 1 << 0, 1); -} - -/* - * Setup the WPE(Write Protect Enable) field (Bit 132) of a - * scalable mode PASID entry. - */ -static inline void pasid_set_wpe(struct pasid_entry *pe) -{ - pasid_set_bits(&pe->val[2], 1 << 4, 1 << 4); -} - -/* - * Setup the P(Present) field (Bit 0) of a scalable mode PASID - * entry. - */ -static inline void pasid_set_present(struct pasid_entry *pe) -{ - pasid_set_bits(&pe->val[0], 1 << 0, 1); -} - -/* - * Setup Page Walk Snoop bit (Bit 87) of a scalable mode PASID - * entry. - */ -static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value) -{ - pasid_set_bits(&pe->val[1], 1 << 23, value << 23); -} - -/* - * Setup No Execute Enable bit (Bit 133) of a scalable mode PASID - * entry. It is required when XD bit of the first level page table - * entry is about to be set. - */ -static inline void pasid_set_nxe(struct pasid_entry *pe) -{ - pasid_set_bits(&pe->val[2], 1 << 5, 1 << 5); -} - -/* - * Setup the Page Snoop (PGSNP) field (Bit 88) of a scalable mode - * PASID entry. - */ -static inline void -pasid_set_pgsnp(struct pasid_entry *pe) -{ - pasid_set_bits(&pe->val[1], 1ULL << 24, 1ULL << 24); -} - -/* - * Setup the First Level Page table Pointer field (Bit 140~191) - * of a scalable mode PASID entry. - */ -static inline void -pasid_set_flptr(struct pasid_entry *pe, u64 value) -{ - pasid_set_bits(&pe->val[2], VTD_PAGE_MASK, value); -} - -/* - * Setup the First Level Paging Mode field (Bit 130~131) of a - * scalable mode PASID entry. - */ -static inline void -pasid_set_flpm(struct pasid_entry *pe, u64 value) -{ - pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2); -} - -/* - * Setup the Extended Access Flag Enable (EAFE) field (Bit 135) - * of a scalable mode PASID entry. - */ -static inline void pasid_set_eafe(struct pasid_entry *pe) -{ - pasid_set_bits(&pe->val[2], 1 << 7, 1 << 7); -} - static void pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu, u16 did, u32 pasid) @@ -613,9 +346,9 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu, * Skip top levels of page tables for iommu which has less agaw * than default. Unnecessary for PT mode. */ -static inline int iommu_skip_agaw(struct dmar_domain *domain, - struct intel_iommu *iommu, - struct dma_pte **pgd) +static int iommu_skip_agaw(struct dmar_domain *domain, + struct intel_iommu *iommu, + struct dma_pte **pgd) { int agaw; @@ -767,7 +500,6 @@ int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu, * Set up the scalable mode pasid entry for passthrough translation type. */ int intel_pasid_setup_pass_through(struct intel_iommu *iommu, - struct dmar_domain *domain, struct device *dev, u32 pasid) { u16 did = FLPT_DEFAULT_DID; diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h index dd37611175cc..8d40d4c66e31 100644 --- a/drivers/iommu/intel/pasid.h +++ b/drivers/iommu/intel/pasid.h @@ -22,16 +22,6 @@ #define is_pasid_enabled(entry) (((entry)->lo >> 3) & 0x1) #define get_pasid_dir_size(entry) (1 << ((((entry)->lo >> 9) & 0x7) + 7)) -/* Virtual command interface for enlightened pasid management. */ -#define VCMD_CMD_ALLOC 0x1 -#define VCMD_CMD_FREE 0x2 -#define VCMD_VRSP_IP 0x1 -#define VCMD_VRSP_SC(e) (((e) & 0xff) >> 1) -#define VCMD_VRSP_SC_SUCCESS 0 -#define VCMD_VRSP_SC_NO_PASID_AVAIL 16 -#define VCMD_VRSP_SC_INVALID_PASID 16 -#define VCMD_VRSP_RESULT_PASID(e) (((e) >> 16) & 0xfffff) -#define VCMD_CMD_OPERAND(e) ((e) << 16) /* * Domain ID reserved for pasid entries programmed for first-level * only and pass-through transfer modes. @@ -96,6 +86,216 @@ static inline u16 pasid_pte_get_pgtt(struct pasid_entry *pte) return (u16)((READ_ONCE(pte->val[0]) >> 6) & 0x7); } +static inline void pasid_clear_entry(struct pasid_entry *pe) +{ + WRITE_ONCE(pe->val[0], 0); + WRITE_ONCE(pe->val[1], 0); + WRITE_ONCE(pe->val[2], 0); + WRITE_ONCE(pe->val[3], 0); + WRITE_ONCE(pe->val[4], 0); + WRITE_ONCE(pe->val[5], 0); + WRITE_ONCE(pe->val[6], 0); + WRITE_ONCE(pe->val[7], 0); +} + +static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe) +{ + WRITE_ONCE(pe->val[0], PASID_PTE_FPD); + WRITE_ONCE(pe->val[1], 0); + WRITE_ONCE(pe->val[2], 0); + WRITE_ONCE(pe->val[3], 0); + WRITE_ONCE(pe->val[4], 0); + WRITE_ONCE(pe->val[5], 0); + WRITE_ONCE(pe->val[6], 0); + WRITE_ONCE(pe->val[7], 0); +} + +static inline void pasid_set_bits(u64 *ptr, u64 mask, u64 bits) +{ + u64 old; + + old = READ_ONCE(*ptr); + WRITE_ONCE(*ptr, (old & ~mask) | bits); +} + +static inline u64 pasid_get_bits(u64 *ptr) +{ + return READ_ONCE(*ptr); +} + +/* + * Setup the DID(Domain Identifier) field (Bit 64~79) of scalable mode + * PASID entry. + */ +static inline void +pasid_set_domain_id(struct pasid_entry *pe, u64 value) +{ + pasid_set_bits(&pe->val[1], GENMASK_ULL(15, 0), value); +} + +/* + * Get domain ID value of a scalable mode PASID entry. + */ +static inline u16 +pasid_get_domain_id(struct pasid_entry *pe) +{ + return (u16)(READ_ONCE(pe->val[1]) & GENMASK_ULL(15, 0)); +} + +/* + * Setup the SLPTPTR(Second Level Page Table Pointer) field (Bit 12~63) + * of a scalable mode PASID entry. + */ +static inline void +pasid_set_slptr(struct pasid_entry *pe, u64 value) +{ + pasid_set_bits(&pe->val[0], VTD_PAGE_MASK, value); +} + +/* + * Setup the AW(Address Width) field (Bit 2~4) of a scalable mode PASID + * entry. + */ +static inline void +pasid_set_address_width(struct pasid_entry *pe, u64 value) +{ + pasid_set_bits(&pe->val[0], GENMASK_ULL(4, 2), value << 2); +} + +/* + * Setup the PGTT(PASID Granular Translation Type) field (Bit 6~8) + * of a scalable mode PASID entry. + */ +static inline void +pasid_set_translation_type(struct pasid_entry *pe, u64 value) +{ + pasid_set_bits(&pe->val[0], GENMASK_ULL(8, 6), value << 6); +} + +/* + * Enable fault processing by clearing the FPD(Fault Processing + * Disable) field (Bit 1) of a scalable mode PASID entry. + */ +static inline void pasid_set_fault_enable(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[0], 1 << 1, 0); +} + +/* + * Enable second level A/D bits by setting the SLADE (Second Level + * Access Dirty Enable) field (Bit 9) of a scalable mode PASID + * entry. + */ +static inline void pasid_set_ssade(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[0], 1 << 9, 1 << 9); +} + +/* + * Disable second level A/D bits by clearing the SLADE (Second Level + * Access Dirty Enable) field (Bit 9) of a scalable mode PASID + * entry. + */ +static inline void pasid_clear_ssade(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[0], 1 << 9, 0); +} + +/* + * Checks if second level A/D bits specifically the SLADE (Second Level + * Access Dirty Enable) field (Bit 9) of a scalable mode PASID + * entry is set. + */ +static inline bool pasid_get_ssade(struct pasid_entry *pe) +{ + return pasid_get_bits(&pe->val[0]) & (1 << 9); +} + +/* + * Setup the SRE(Supervisor Request Enable) field (Bit 128) of a + * scalable mode PASID entry. + */ +static inline void pasid_set_sre(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[2], 1 << 0, 1); +} + +/* + * Setup the WPE(Write Protect Enable) field (Bit 132) of a + * scalable mode PASID entry. + */ +static inline void pasid_set_wpe(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[2], 1 << 4, 1 << 4); +} + +/* + * Setup the P(Present) field (Bit 0) of a scalable mode PASID + * entry. + */ +static inline void pasid_set_present(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[0], 1 << 0, 1); +} + +/* + * Setup Page Walk Snoop bit (Bit 87) of a scalable mode PASID + * entry. + */ +static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value) +{ + pasid_set_bits(&pe->val[1], 1 << 23, value << 23); +} + +/* + * Setup No Execute Enable bit (Bit 133) of a scalable mode PASID + * entry. It is required when XD bit of the first level page table + * entry is about to be set. + */ +static inline void pasid_set_nxe(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[2], 1 << 5, 1 << 5); +} + +/* + * Setup the Page Snoop (PGSNP) field (Bit 88) of a scalable mode + * PASID entry. + */ +static inline void +pasid_set_pgsnp(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[1], 1ULL << 24, 1ULL << 24); +} + +/* + * Setup the First Level Page table Pointer field (Bit 140~191) + * of a scalable mode PASID entry. + */ +static inline void +pasid_set_flptr(struct pasid_entry *pe, u64 value) +{ + pasid_set_bits(&pe->val[2], VTD_PAGE_MASK, value); +} + +/* + * Setup the First Level Paging Mode field (Bit 130~131) of a + * scalable mode PASID entry. + */ +static inline void +pasid_set_flpm(struct pasid_entry *pe, u64 value) +{ + pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2); +} + +/* + * Setup the Extended Access Flag Enable (EAFE) field (Bit 135) + * of a scalable mode PASID entry. + */ +static inline void pasid_set_eafe(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[2], 1 << 7, 1 << 7); +} + extern unsigned int intel_pasid_max_id; int intel_pasid_alloc_table(struct device *dev); void intel_pasid_free_table(struct device *dev); @@ -111,15 +311,12 @@ int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu, struct device *dev, u32 pasid, bool enabled); int intel_pasid_setup_pass_through(struct intel_iommu *iommu, - struct dmar_domain *domain, struct device *dev, u32 pasid); int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev, u32 pasid, struct dmar_domain *domain); void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev, u32 pasid, bool fault_ignore); -int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid); -void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid); void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu, struct device *dev, u32 pasid); #endif /* __INTEL_PASID_H */ diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index ac12f76c1212..40edd282903f 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -316,21 +316,22 @@ out: } static int intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev, - struct mm_struct *mm) + struct iommu_domain *domain, ioasid_t pasid) { struct device_domain_info *info = dev_iommu_priv_get(dev); + struct mm_struct *mm = domain->mm; struct intel_svm_dev *sdev; struct intel_svm *svm; unsigned long sflags; int ret = 0; - svm = pasid_private_find(mm->pasid); + svm = pasid_private_find(pasid); if (!svm) { svm = kzalloc(sizeof(*svm), GFP_KERNEL); if (!svm) return -ENOMEM; - svm->pasid = mm->pasid; + svm->pasid = pasid; svm->mm = mm; INIT_LIST_HEAD_RCU(&svm->devs); @@ -368,7 +369,7 @@ static int intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev, /* Setup the pasid table: */ sflags = cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0; - ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, mm->pasid, + ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, pasid, FLPT_DEFAULT_DID, sflags); if (ret) goto free_sdev; @@ -382,7 +383,7 @@ free_sdev: free_svm: if (list_empty(&svm->devs)) { mmu_notifier_unregister(&svm->notifier, mm); - pasid_private_remove(mm->pasid); + pasid_private_remove(pasid); kfree(svm); } @@ -392,14 +393,9 @@ free_svm: void intel_svm_remove_dev_pasid(struct device *dev, u32 pasid) { struct intel_svm_dev *sdev; - struct intel_iommu *iommu; struct intel_svm *svm; struct mm_struct *mm; - iommu = device_to_iommu(dev, NULL, NULL); - if (!iommu) - return; - if (pasid_to_svm_sdev(dev, pasid, &svm, &sdev)) return; mm = svm->mm; @@ -750,25 +746,16 @@ int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt, struct iommu_page_response *msg) { + struct device_domain_info *info = dev_iommu_priv_get(dev); + struct intel_iommu *iommu = info->iommu; + u8 bus = info->bus, devfn = info->devfn; struct iommu_fault_page_request *prm; - struct intel_iommu *iommu; bool private_present; bool pasid_present; bool last_page; - u8 bus, devfn; int ret = 0; u16 sid; - if (!dev || !dev_is_pci(dev)) - return -ENODEV; - - iommu = device_to_iommu(dev, &bus, &devfn); - if (!iommu) - return -ENODEV; - - if (!msg || !evt) - return -EINVAL; - prm = &evt->fault.prm; sid = PCI_DEVID(bus, devfn); pasid_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID; @@ -822,9 +809,8 @@ static int intel_svm_set_dev_pasid(struct iommu_domain *domain, { struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_iommu *iommu = info->iommu; - struct mm_struct *mm = domain->mm; - return intel_svm_bind_mm(iommu, dev, mm); + return intel_svm_bind_mm(iommu, dev, domain, pasid); } static void intel_svm_domain_free(struct iommu_domain *domain) diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 72dcdd468cf3..f7828a7aad41 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -188,20 +188,28 @@ static dma_addr_t __arm_lpae_dma_addr(void *pages) } static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp, - struct io_pgtable_cfg *cfg) + struct io_pgtable_cfg *cfg, + void *cookie) { struct device *dev = cfg->iommu_dev; int order = get_order(size); - struct page *p; dma_addr_t dma; void *pages; VM_BUG_ON((gfp & __GFP_HIGHMEM)); - p = alloc_pages_node(dev_to_node(dev), gfp | __GFP_ZERO, order); - if (!p) + + if (cfg->alloc) { + pages = cfg->alloc(cookie, size, gfp); + } else { + struct page *p; + + p = alloc_pages_node(dev_to_node(dev), gfp | __GFP_ZERO, order); + pages = p ? page_address(p) : NULL; + } + + if (!pages) return NULL; - pages = page_address(p); if (!cfg->coherent_walk) { dma = dma_map_single(dev, pages, size, DMA_TO_DEVICE); if (dma_mapping_error(dev, dma)) @@ -220,18 +228,28 @@ static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp, out_unmap: dev_err(dev, "Cannot accommodate DMA translation for IOMMU page tables\n"); dma_unmap_single(dev, dma, size, DMA_TO_DEVICE); + out_free: - __free_pages(p, order); + if (cfg->free) + cfg->free(cookie, pages, size); + else + free_pages((unsigned long)pages, order); + return NULL; } static void __arm_lpae_free_pages(void *pages, size_t size, - struct io_pgtable_cfg *cfg) + struct io_pgtable_cfg *cfg, + void *cookie) { if (!cfg->coherent_walk) dma_unmap_single(cfg->iommu_dev, __arm_lpae_dma_addr(pages), size, DMA_TO_DEVICE); - free_pages((unsigned long)pages, get_order(size)); + + if (cfg->free) + cfg->free(cookie, pages, size); + else + free_pages((unsigned long)pages, get_order(size)); } static void __arm_lpae_sync_pte(arm_lpae_iopte *ptep, int num_entries, @@ -373,13 +391,13 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova, /* Grab a pointer to the next level */ pte = READ_ONCE(*ptep); if (!pte) { - cptep = __arm_lpae_alloc_pages(tblsz, gfp, cfg); + cptep = __arm_lpae_alloc_pages(tblsz, gfp, cfg, data->iop.cookie); if (!cptep) return -ENOMEM; pte = arm_lpae_install_table(cptep, ptep, 0, data); if (pte) - __arm_lpae_free_pages(cptep, tblsz, cfg); + __arm_lpae_free_pages(cptep, tblsz, cfg, data->iop.cookie); } else if (!cfg->coherent_walk && !(pte & ARM_LPAE_PTE_SW_SYNC)) { __arm_lpae_sync_pte(ptep, 1, cfg); } @@ -524,7 +542,7 @@ static void __arm_lpae_free_pgtable(struct arm_lpae_io_pgtable *data, int lvl, __arm_lpae_free_pgtable(data, lvl + 1, iopte_deref(pte, data)); } - __arm_lpae_free_pages(start, table_size, &data->iop.cfg); + __arm_lpae_free_pages(start, table_size, &data->iop.cfg, data->iop.cookie); } static void arm_lpae_free_pgtable(struct io_pgtable *iop) @@ -552,7 +570,7 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS)) return 0; - tablep = __arm_lpae_alloc_pages(tablesz, GFP_ATOMIC, cfg); + tablep = __arm_lpae_alloc_pages(tablesz, GFP_ATOMIC, cfg, data->iop.cookie); if (!tablep) return 0; /* Bytes unmapped */ @@ -575,7 +593,7 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, pte = arm_lpae_install_table(tablep, ptep, blk_pte, data); if (pte != blk_pte) { - __arm_lpae_free_pages(tablep, tablesz, cfg); + __arm_lpae_free_pages(tablep, tablesz, cfg, data->iop.cookie); /* * We may race against someone unmapping another part of this * block, but anything else is invalid. We can't misinterpret @@ -882,7 +900,7 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie) /* Looking good; allocate a pgd */ data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data), - GFP_KERNEL, cfg); + GFP_KERNEL, cfg, cookie); if (!data->pgd) goto out_free_data; @@ -984,7 +1002,7 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie) /* Allocate pgd pages */ data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data), - GFP_KERNEL, cfg); + GFP_KERNEL, cfg, cookie); if (!data->pgd) goto out_free_data; @@ -1059,7 +1077,7 @@ arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie) << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV)); data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data), GFP_KERNEL, - cfg); + cfg, cookie); if (!data->pgd) goto out_free_data; @@ -1080,26 +1098,31 @@ out_free_data: } struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = { + .caps = IO_PGTABLE_CAP_CUSTOM_ALLOCATOR, .alloc = arm_64_lpae_alloc_pgtable_s1, .free = arm_lpae_free_pgtable, }; struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns = { + .caps = IO_PGTABLE_CAP_CUSTOM_ALLOCATOR, .alloc = arm_64_lpae_alloc_pgtable_s2, .free = arm_lpae_free_pgtable, }; struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns = { + .caps = IO_PGTABLE_CAP_CUSTOM_ALLOCATOR, .alloc = arm_32_lpae_alloc_pgtable_s1, .free = arm_lpae_free_pgtable, }; struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s2_init_fns = { + .caps = IO_PGTABLE_CAP_CUSTOM_ALLOCATOR, .alloc = arm_32_lpae_alloc_pgtable_s2, .free = arm_lpae_free_pgtable, }; struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns = { + .caps = IO_PGTABLE_CAP_CUSTOM_ALLOCATOR, .alloc = arm_mali_lpae_alloc_pgtable, .free = arm_lpae_free_pgtable, }; diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c index b843fcd365d2..8841c1487f00 100644 --- a/drivers/iommu/io-pgtable.c +++ b/drivers/iommu/io-pgtable.c @@ -34,6 +34,26 @@ io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] = { #endif }; +static int check_custom_allocator(enum io_pgtable_fmt fmt, + struct io_pgtable_cfg *cfg) +{ + /* No custom allocator, no need to check the format. */ + if (!cfg->alloc && !cfg->free) + return 0; + + /* When passing a custom allocator, both the alloc and free + * functions should be provided. + */ + if (!cfg->alloc || !cfg->free) + return -EINVAL; + + /* Make sure the format supports custom allocators. */ + if (io_pgtable_init_table[fmt]->caps & IO_PGTABLE_CAP_CUSTOM_ALLOCATOR) + return 0; + + return -EINVAL; +} + struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt, struct io_pgtable_cfg *cfg, void *cookie) @@ -44,6 +64,9 @@ struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt, if (fmt >= IO_PGTABLE_NUM_FMTS) return NULL; + if (check_custom_allocator(fmt, cfg)) + return NULL; + fns = io_pgtable_init_table[fmt]; if (!fns) return NULL; diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index b78671a8a914..c3fc9201d0be 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -12,32 +12,42 @@ static DEFINE_MUTEX(iommu_sva_lock); /* Allocate a PASID for the mm within range (inclusive) */ -static int iommu_sva_alloc_pasid(struct mm_struct *mm, struct device *dev) +static struct iommu_mm_data *iommu_alloc_mm_data(struct mm_struct *mm, struct device *dev) { + struct iommu_mm_data *iommu_mm; ioasid_t pasid; - int ret = 0; + + lockdep_assert_held(&iommu_sva_lock); if (!arch_pgtable_dma_compat(mm)) - return -EBUSY; + return ERR_PTR(-EBUSY); - mutex_lock(&iommu_sva_lock); + iommu_mm = mm->iommu_mm; /* Is a PASID already associated with this mm? */ - if (mm_valid_pasid(mm)) { - if (mm->pasid >= dev->iommu->max_pasids) - ret = -EOVERFLOW; - goto out; + if (iommu_mm) { + if (iommu_mm->pasid >= dev->iommu->max_pasids) + return ERR_PTR(-EOVERFLOW); + return iommu_mm; } + iommu_mm = kzalloc(sizeof(struct iommu_mm_data), GFP_KERNEL); + if (!iommu_mm) + return ERR_PTR(-ENOMEM); + pasid = iommu_alloc_global_pasid(dev); if (pasid == IOMMU_PASID_INVALID) { - ret = -ENOSPC; - goto out; + kfree(iommu_mm); + return ERR_PTR(-ENOSPC); } - mm->pasid = pasid; - ret = 0; -out: - mutex_unlock(&iommu_sva_lock); - return ret; + iommu_mm->pasid = pasid; + INIT_LIST_HEAD(&iommu_mm->sva_domains); + /* + * Make sure the write to mm->iommu_mm is not reordered in front of + * initialization to iommu_mm fields. If it does, readers may see a + * valid iommu_mm with uninitialized values. + */ + smp_store_release(&mm->iommu_mm, iommu_mm); + return iommu_mm; } /** @@ -58,57 +68,60 @@ out: */ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) { + struct iommu_mm_data *iommu_mm; struct iommu_domain *domain; struct iommu_sva *handle; int ret; + mutex_lock(&iommu_sva_lock); + /* Allocate mm->pasid if necessary. */ - ret = iommu_sva_alloc_pasid(mm, dev); - if (ret) - return ERR_PTR(ret); + iommu_mm = iommu_alloc_mm_data(mm, dev); + if (IS_ERR(iommu_mm)) { + ret = PTR_ERR(iommu_mm); + goto out_unlock; + } handle = kzalloc(sizeof(*handle), GFP_KERNEL); - if (!handle) - return ERR_PTR(-ENOMEM); - - mutex_lock(&iommu_sva_lock); - /* Search for an existing domain. */ - domain = iommu_get_domain_for_dev_pasid(dev, mm->pasid, - IOMMU_DOMAIN_SVA); - if (IS_ERR(domain)) { - ret = PTR_ERR(domain); + if (!handle) { + ret = -ENOMEM; goto out_unlock; } - if (domain) { - domain->users++; - goto out; + /* Search for an existing domain. */ + list_for_each_entry(domain, &mm->iommu_mm->sva_domains, next) { + ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid); + if (!ret) { + domain->users++; + goto out; + } } /* Allocate a new domain and set it on device pasid. */ domain = iommu_sva_domain_alloc(dev, mm); if (!domain) { ret = -ENOMEM; - goto out_unlock; + goto out_free_handle; } - ret = iommu_attach_device_pasid(domain, dev, mm->pasid); + ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid); if (ret) goto out_free_domain; domain->users = 1; + list_add(&domain->next, &mm->iommu_mm->sva_domains); + out: mutex_unlock(&iommu_sva_lock); handle->dev = dev; handle->domain = domain; - return handle; out_free_domain: iommu_domain_free(domain); +out_free_handle: + kfree(handle); out_unlock: mutex_unlock(&iommu_sva_lock); - kfree(handle); - return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(iommu_sva_bind_device); @@ -124,12 +137,13 @@ EXPORT_SYMBOL_GPL(iommu_sva_bind_device); void iommu_sva_unbind_device(struct iommu_sva *handle) { struct iommu_domain *domain = handle->domain; - ioasid_t pasid = domain->mm->pasid; + struct iommu_mm_data *iommu_mm = domain->mm->iommu_mm; struct device *dev = handle->dev; mutex_lock(&iommu_sva_lock); + iommu_detach_device_pasid(domain, dev, iommu_mm->pasid); if (--domain->users == 0) { - iommu_detach_device_pasid(domain, dev, pasid); + list_del(&domain->next); iommu_domain_free(domain); } mutex_unlock(&iommu_sva_lock); @@ -141,7 +155,7 @@ u32 iommu_sva_get_pasid(struct iommu_sva *handle) { struct iommu_domain *domain = handle->domain; - return domain->mm->pasid; + return mm_get_enqcmd_pasid(domain->mm); } EXPORT_SYMBOL_GPL(iommu_sva_get_pasid); @@ -205,8 +219,11 @@ out_put_mm: void mm_pasid_drop(struct mm_struct *mm) { - if (likely(!mm_valid_pasid(mm))) + struct iommu_mm_data *iommu_mm = mm->iommu_mm; + + if (!iommu_mm) return; - iommu_free_global_pasid(mm->pasid); + iommu_free_global_pasid(iommu_mm->pasid); + kfree(iommu_mm); } diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 33e2a9b5d339..68e648b55767 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -148,7 +148,7 @@ struct iommu_group_attribute iommu_group_attr_##_name = \ static LIST_HEAD(iommu_device_list); static DEFINE_SPINLOCK(iommu_device_lock); -static struct bus_type * const iommu_buses[] = { +static const struct bus_type * const iommu_buses[] = { &platform_bus_type, #ifdef CONFIG_PCI &pci_bus_type, @@ -257,13 +257,6 @@ int iommu_device_register(struct iommu_device *iommu, /* We need to be able to take module references appropriately */ if (WARN_ON(is_module_address((unsigned long)ops) && !ops->owner)) return -EINVAL; - /* - * Temporarily enforce global restriction to a single driver. This was - * already the de-facto behaviour, since any possible combination of - * existing drivers would compete for at least the PCI or platform bus. - */ - if (iommu_buses[0]->iommu_ops && iommu_buses[0]->iommu_ops != ops) - return -EBUSY; iommu->ops = ops; if (hwdev) @@ -273,10 +266,8 @@ int iommu_device_register(struct iommu_device *iommu, list_add_tail(&iommu->list, &iommu_device_list); spin_unlock(&iommu_device_lock); - for (int i = 0; i < ARRAY_SIZE(iommu_buses) && !err; i++) { - iommu_buses[i]->iommu_ops = ops; + for (int i = 0; i < ARRAY_SIZE(iommu_buses) && !err; i++) err = bus_iommu_probe(iommu_buses[i]); - } if (err) iommu_device_unregister(iommu); return err; @@ -329,7 +320,6 @@ int iommu_device_register_bus(struct iommu_device *iommu, list_add_tail(&iommu->list, &iommu_device_list); spin_unlock(&iommu_device_lock); - bus->iommu_ops = ops; err = bus_iommu_probe(bus); if (err) { iommu_device_unregister_bus(iommu, bus, nb); @@ -344,6 +334,8 @@ static struct dev_iommu *dev_iommu_get(struct device *dev) { struct dev_iommu *param = dev->iommu; + lockdep_assert_held(&iommu_probe_device_lock); + if (param) return param; @@ -368,6 +360,15 @@ static void dev_iommu_free(struct device *dev) kfree(param); } +/* + * Internal equivalent of device_iommu_mapped() for when we care that a device + * actually has API ops, and don't want false positives from VFIO-only groups. + */ +static bool dev_has_iommu(struct device *dev) +{ + return dev->iommu && dev->iommu->iommu_dev; +} + static u32 dev_iommu_get_max_pasids(struct device *dev) { u32 max_pasids = 0, bits = 0; @@ -386,6 +387,15 @@ static u32 dev_iommu_get_max_pasids(struct device *dev) return min_t(u32, max_pasids, dev->iommu->iommu_dev->max_pasids); } +void dev_iommu_priv_set(struct device *dev, void *priv) +{ + /* FSL_PAMU does something weird */ + if (!IS_ENABLED(CONFIG_FSL_PAMU)) + lockdep_assert_held(&iommu_probe_device_lock); + dev->iommu->priv = priv; +} +EXPORT_SYMBOL_GPL(dev_iommu_priv_set); + /* * Init the dev->iommu and dev->iommu_group in the struct device and get the * driver probed @@ -489,11 +499,26 @@ DEFINE_MUTEX(iommu_probe_device_lock); static int __iommu_probe_device(struct device *dev, struct list_head *group_list) { - const struct iommu_ops *ops = dev->bus->iommu_ops; + const struct iommu_ops *ops; + struct iommu_fwspec *fwspec; struct iommu_group *group; struct group_device *gdev; int ret; + /* + * For FDT-based systems and ACPI IORT/VIOT, drivers register IOMMU + * instances with non-NULL fwnodes, and client devices should have been + * identified with a fwspec by this point. Otherwise, we can currently + * assume that only one of Intel, AMD, s390, PAMU or legacy SMMUv2 can + * be present, and that any of their registered instances has suitable + * ops for probing, and thus cheekily co-opt the same mechanism. + */ + fwspec = dev_iommu_fwspec_get(dev); + if (fwspec && fwspec->ops) + ops = fwspec->ops; + else + ops = iommu_ops_from_fwnode(NULL); + if (!ops) return -ENODEV; /* @@ -618,7 +643,7 @@ static void __iommu_group_remove_device(struct device *dev) list_del(&device->list); __iommu_group_free_device(group, device); - if (dev->iommu && dev->iommu->iommu_dev) + if (dev_has_iommu(dev)) iommu_deinit_device(dev); else dev->iommu_group = NULL; @@ -817,7 +842,7 @@ int iommu_get_group_resv_regions(struct iommu_group *group, * Non-API groups still expose reserved_regions in sysfs, * so filter out calls that get here that way. */ - if (!device->dev->iommu) + if (!dev_has_iommu(device->dev)) break; INIT_LIST_HEAD(&dev_resv_regions); @@ -1223,6 +1248,12 @@ void iommu_group_remove_device(struct device *dev) } EXPORT_SYMBOL_GPL(iommu_group_remove_device); +static struct device *iommu_group_first_dev(struct iommu_group *group) +{ + lockdep_assert_held(&group->mutex); + return list_first_entry(&group->devices, struct group_device, list)->dev; +} + /** * iommu_group_for_each_dev - iterate over each device in the group * @group: the group @@ -1751,30 +1782,13 @@ __iommu_group_alloc_default_domain(struct iommu_group *group, int req_type) } /* - * Returns the iommu_ops for the devices in an iommu group. - * - * It is assumed that all devices in an iommu group are managed by a single - * IOMMU unit. Therefore, this returns the dev_iommu_ops of the first device - * in the group. - */ -static const struct iommu_ops *group_iommu_ops(struct iommu_group *group) -{ - struct group_device *device = - list_first_entry(&group->devices, struct group_device, list); - - lockdep_assert_held(&group->mutex); - - return dev_iommu_ops(device->dev); -} - -/* * req_type of 0 means "auto" which means to select a domain based on * iommu_def_domain_type or what the driver actually supports. */ static struct iommu_domain * iommu_group_alloc_default_domain(struct iommu_group *group, int req_type) { - const struct iommu_ops *ops = group_iommu_ops(group); + const struct iommu_ops *ops = dev_iommu_ops(iommu_group_first_dev(group)); struct iommu_domain *dom; lockdep_assert_held(&group->mutex); @@ -1854,7 +1868,7 @@ static int iommu_bus_notifier(struct notifier_block *nb, static int iommu_get_def_domain_type(struct iommu_group *group, struct device *dev, int cur_type) { - const struct iommu_ops *ops = group_iommu_ops(group); + const struct iommu_ops *ops = dev_iommu_ops(dev); int type; if (!ops->def_domain_type) @@ -2003,9 +2017,28 @@ int bus_iommu_probe(const struct bus_type *bus) return 0; } +/** + * iommu_present() - make platform-specific assumptions about an IOMMU + * @bus: bus to check + * + * Do not use this function. You want device_iommu_mapped() instead. + * + * Return: true if some IOMMU is present and aware of devices on the given bus; + * in general it may not be the only IOMMU, and it may not have anything to do + * with whatever device you are ultimately interested in. + */ bool iommu_present(const struct bus_type *bus) { - return bus->iommu_ops != NULL; + bool ret = false; + + for (int i = 0; i < ARRAY_SIZE(iommu_buses); i++) { + if (iommu_buses[i] == bus) { + spin_lock(&iommu_device_lock); + ret = !list_empty(&iommu_device_list); + spin_unlock(&iommu_device_lock); + } + } + return ret; } EXPORT_SYMBOL_GPL(iommu_present); @@ -2021,7 +2054,7 @@ bool device_iommu_capable(struct device *dev, enum iommu_cap cap) { const struct iommu_ops *ops; - if (!dev->iommu || !dev->iommu->iommu_dev) + if (!dev_has_iommu(dev)) return false; ops = dev_iommu_ops(dev); @@ -2107,6 +2140,7 @@ static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops, return ERR_PTR(-ENOMEM); domain->type = type; + domain->owner = ops; /* * If not already set, assume all sizes by default; the driver * may override this later @@ -2132,21 +2166,37 @@ static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops, static struct iommu_domain * __iommu_group_domain_alloc(struct iommu_group *group, unsigned int type) { - struct device *dev = - list_first_entry(&group->devices, struct group_device, list) - ->dev; + struct device *dev = iommu_group_first_dev(group); - return __iommu_domain_alloc(group_iommu_ops(group), dev, type); + return __iommu_domain_alloc(dev_iommu_ops(dev), dev, type); +} + +static int __iommu_domain_alloc_dev(struct device *dev, void *data) +{ + const struct iommu_ops **ops = data; + + if (!dev_has_iommu(dev)) + return 0; + + if (WARN_ONCE(*ops && *ops != dev_iommu_ops(dev), + "Multiple IOMMU drivers present for bus %s, which the public IOMMU API can't fully support yet. You will still need to disable one or more for this to work, sorry!\n", + dev_bus_name(dev))) + return -EBUSY; + + *ops = dev_iommu_ops(dev); + return 0; } struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus) { + const struct iommu_ops *ops = NULL; + int err = bus_for_each_dev(bus, NULL, &ops, __iommu_domain_alloc_dev); struct iommu_domain *domain; - if (bus == NULL || bus->iommu_ops == NULL) + if (err || !ops) return NULL; - domain = __iommu_domain_alloc(bus->iommu_ops, NULL, - IOMMU_DOMAIN_UNMANAGED); + + domain = __iommu_domain_alloc(ops, NULL, IOMMU_DOMAIN_UNMANAGED); if (IS_ERR(domain)) return NULL; return domain; @@ -2284,10 +2334,16 @@ struct iommu_domain *iommu_get_dma_domain(struct device *dev) static int __iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group) { + struct device *dev; + if (group->domain && group->domain != group->default_domain && group->domain != group->blocking_domain) return -EBUSY; + dev = iommu_group_first_dev(group); + if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner) + return -EINVAL; + return __iommu_group_set_domain(group, domain); } @@ -3004,8 +3060,8 @@ EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids); */ int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat) { - if (dev->iommu && dev->iommu->iommu_dev) { - const struct iommu_ops *ops = dev->iommu->iommu_dev->ops; + if (dev_has_iommu(dev)) { + const struct iommu_ops *ops = dev_iommu_ops(dev); if (ops->dev_enable_feat) return ops->dev_enable_feat(dev, feat); @@ -3020,8 +3076,8 @@ EXPORT_SYMBOL_GPL(iommu_dev_enable_feature); */ int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat) { - if (dev->iommu && dev->iommu->iommu_dev) { - const struct iommu_ops *ops = dev->iommu->iommu_dev->ops; + if (dev_has_iommu(dev)) { + const struct iommu_ops *ops = dev_iommu_ops(dev); if (ops->dev_disable_feat) return ops->dev_disable_feat(dev, feat); @@ -3481,6 +3537,9 @@ int iommu_attach_device_pasid(struct iommu_domain *domain, if (!group) return -ENODEV; + if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner) + return -EINVAL; + mutex_lock(&group->mutex); curr = xa_cmpxchg(&group->pasid_array, pasid, NULL, domain, GFP_KERNEL); if (curr) { @@ -3569,6 +3628,7 @@ struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, domain->type = IOMMU_DOMAIN_SVA; mmgrab(mm); domain->mm = mm; + domain->owner = ops; domain->iopf_handler = iommu_sva_handle_iopf; domain->fault_data = mm; diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index cbb5df0a6c32..3f3f1fa1a0a9 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -135,6 +135,7 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, hwpt->domain = NULL; goto out_abort; } + hwpt->domain->owner = ops; } else { hwpt->domain = iommu_domain_alloc(idev->dev->bus); if (!hwpt->domain) { @@ -233,6 +234,7 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx, hwpt->domain = NULL; goto out_abort; } + hwpt->domain->owner = ops; if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) { rc = -EINVAL; @@ -371,3 +373,44 @@ int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd) iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj); return rc; } + +int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd) +{ + struct iommu_hwpt_invalidate *cmd = ucmd->cmd; + struct iommu_user_data_array data_array = { + .type = cmd->data_type, + .uptr = u64_to_user_ptr(cmd->data_uptr), + .entry_len = cmd->entry_len, + .entry_num = cmd->entry_num, + }; + struct iommufd_hw_pagetable *hwpt; + u32 done_num = 0; + int rc; + + if (cmd->__reserved) { + rc = -EOPNOTSUPP; + goto out; + } + + if (cmd->entry_num && (!cmd->data_uptr || !cmd->entry_len)) { + rc = -EINVAL; + goto out; + } + + hwpt = iommufd_get_hwpt_nested(ucmd, cmd->hwpt_id); + if (IS_ERR(hwpt)) { + rc = PTR_ERR(hwpt); + goto out; + } + + rc = hwpt->domain->ops->cache_invalidate_user(hwpt->domain, + &data_array); + done_num = data_array.entry_num; + + iommufd_put_object(ucmd->ictx, &hwpt->obj); +out: + cmd->entry_num = done_num; + if (iommufd_ucmd_respond(ucmd, sizeof(*cmd))) + return -EFAULT; + return rc; +} diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index abae041e256f..991f864d1f9b 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -328,6 +328,15 @@ iommufd_get_hwpt_paging(struct iommufd_ucmd *ucmd, u32 id) IOMMUFD_OBJ_HWPT_PAGING), struct iommufd_hwpt_paging, common.obj); } + +static inline struct iommufd_hw_pagetable * +iommufd_get_hwpt_nested(struct iommufd_ucmd *ucmd, u32 id) +{ + return container_of(iommufd_get_object(ucmd->ictx, id, + IOMMUFD_OBJ_HWPT_NESTED), + struct iommufd_hw_pagetable, obj); +} + int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd); int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd); @@ -345,6 +354,7 @@ void iommufd_hwpt_paging_abort(struct iommufd_object *obj); void iommufd_hwpt_nested_destroy(struct iommufd_object *obj); void iommufd_hwpt_nested_abort(struct iommufd_object *obj); int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd); +int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd); static inline void iommufd_hw_pagetable_put(struct iommufd_ctx *ictx, struct iommufd_hw_pagetable *hwpt) diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h index 7910fbe1962d..482d4059f5db 100644 --- a/drivers/iommu/iommufd/iommufd_test.h +++ b/drivers/iommu/iommufd/iommufd_test.h @@ -21,6 +21,7 @@ enum { IOMMU_TEST_OP_ACCESS_REPLACE_IOAS, IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS, IOMMU_TEST_OP_DIRTY, + IOMMU_TEST_OP_MD_CHECK_IOTLB, }; enum { @@ -121,6 +122,10 @@ struct iommu_test_cmd { __aligned_u64 uptr; __aligned_u64 out_nr_dirty; } dirty; + struct { + __u32 id; + __u32 iotlb; + } check_iotlb; }; __u32 last; }; @@ -148,4 +153,22 @@ struct iommu_hwpt_selftest { __u32 iotlb; }; +/* Should not be equal to any defined value in enum iommu_hwpt_invalidate_data_type */ +#define IOMMU_HWPT_INVALIDATE_DATA_SELFTEST 0xdeadbeef +#define IOMMU_HWPT_INVALIDATE_DATA_SELFTEST_INVALID 0xdadbeef + +/** + * struct iommu_hwpt_invalidate_selftest - Invalidation data for Mock driver + * (IOMMU_HWPT_INVALIDATE_DATA_SELFTEST) + * @flags: Invalidate flags + * @iotlb_id: Invalidate iotlb entry index + * + * If IOMMU_TEST_INVALIDATE_ALL is set in @flags, @iotlb_id will be ignored + */ +struct iommu_hwpt_invalidate_selftest { +#define IOMMU_TEST_INVALIDATE_FLAG_ALL (1 << 0) + __u32 flags; + __u32 iotlb_id; +}; + #endif diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index c9091e46d208..39b32932c61e 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -322,6 +322,7 @@ union ucmd_buffer { struct iommu_hw_info info; struct iommu_hwpt_alloc hwpt; struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap; + struct iommu_hwpt_invalidate cache; struct iommu_hwpt_set_dirty_tracking set_dirty_tracking; struct iommu_ioas_alloc alloc; struct iommu_ioas_allow_iovas allow_iovas; @@ -360,6 +361,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { __reserved), IOCTL_OP(IOMMU_HWPT_GET_DIRTY_BITMAP, iommufd_hwpt_get_dirty_bitmap, struct iommu_hwpt_get_dirty_bitmap, data), + IOCTL_OP(IOMMU_HWPT_INVALIDATE, iommufd_hwpt_invalidate, + struct iommu_hwpt_invalidate, __reserved), IOCTL_OP(IOMMU_HWPT_SET_DIRTY_TRACKING, iommufd_hwpt_set_dirty_tracking, struct iommu_hwpt_set_dirty_tracking, __reserved), IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl, diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 022ef8f55088..d9e9920c7eba 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -25,6 +25,19 @@ static struct iommu_domain_ops domain_nested_ops; size_t iommufd_test_memory_limit = 65536; +struct mock_bus_type { + struct bus_type bus; + struct notifier_block nb; +}; + +static struct mock_bus_type iommufd_mock_bus_type = { + .bus = { + .name = "iommufd_mock", + }, +}; + +static atomic_t mock_dev_num; + enum { MOCK_DIRTY_TRACK = 1, MOCK_IO_PAGE_SIZE = PAGE_SIZE / 2, @@ -437,6 +450,8 @@ static struct iommu_device mock_iommu_device = { static struct iommu_device *mock_probe_device(struct device *dev) { + if (dev->bus != &iommufd_mock_bus_type.bus) + return ERR_PTR(-ENODEV); return &mock_iommu_device; } @@ -473,9 +488,59 @@ static void mock_domain_free_nested(struct iommu_domain *domain) kfree(mock_nested); } +static int +mock_domain_cache_invalidate_user(struct iommu_domain *domain, + struct iommu_user_data_array *array) +{ + struct mock_iommu_domain_nested *mock_nested = + container_of(domain, struct mock_iommu_domain_nested, domain); + struct iommu_hwpt_invalidate_selftest inv; + u32 processed = 0; + int i = 0, j; + int rc = 0; + + if (array->type != IOMMU_HWPT_INVALIDATE_DATA_SELFTEST) { + rc = -EINVAL; + goto out; + } + + for ( ; i < array->entry_num; i++) { + rc = iommu_copy_struct_from_user_array(&inv, array, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + i, iotlb_id); + if (rc) + break; + + if (inv.flags & ~IOMMU_TEST_INVALIDATE_FLAG_ALL) { + rc = -EOPNOTSUPP; + break; + } + + if (inv.iotlb_id > MOCK_NESTED_DOMAIN_IOTLB_ID_MAX) { + rc = -EINVAL; + break; + } + + if (inv.flags & IOMMU_TEST_INVALIDATE_FLAG_ALL) { + /* Invalidate all mock iotlb entries and ignore iotlb_id */ + for (j = 0; j < MOCK_NESTED_DOMAIN_IOTLB_NUM; j++) + mock_nested->iotlb[j] = 0; + } else { + mock_nested->iotlb[inv.iotlb_id] = 0; + } + + processed++; + } + +out: + array->entry_num = processed; + return rc; +} + static struct iommu_domain_ops domain_nested_ops = { .free = mock_domain_free_nested, .attach_dev = mock_domain_nop_attach, + .cache_invalidate_user = mock_domain_cache_invalidate_user, }; static inline struct iommufd_hw_pagetable * @@ -526,19 +591,6 @@ get_md_pagetable_nested(struct iommufd_ucmd *ucmd, u32 mockpt_id, return hwpt; } -struct mock_bus_type { - struct bus_type bus; - struct notifier_block nb; -}; - -static struct mock_bus_type iommufd_mock_bus_type = { - .bus = { - .name = "iommufd_mock", - }, -}; - -static atomic_t mock_dev_num; - static void mock_dev_release(struct device *dev) { struct mock_dev *mdev = container_of(dev, struct mock_dev, dev); @@ -793,6 +845,28 @@ static int iommufd_test_md_check_refs(struct iommufd_ucmd *ucmd, return 0; } +static int iommufd_test_md_check_iotlb(struct iommufd_ucmd *ucmd, + u32 mockpt_id, unsigned int iotlb_id, + u32 iotlb) +{ + struct mock_iommu_domain_nested *mock_nested; + struct iommufd_hw_pagetable *hwpt; + int rc = 0; + + hwpt = get_md_pagetable_nested(ucmd, mockpt_id, &mock_nested); + if (IS_ERR(hwpt)) + return PTR_ERR(hwpt); + + mock_nested = container_of(hwpt->domain, + struct mock_iommu_domain_nested, domain); + + if (iotlb_id > MOCK_NESTED_DOMAIN_IOTLB_ID_MAX || + mock_nested->iotlb[iotlb_id] != iotlb) + rc = -EINVAL; + iommufd_put_object(ucmd->ictx, &hwpt->obj); + return rc; +} + struct selftest_access { struct iommufd_access *access; struct file *file; @@ -1274,6 +1348,10 @@ int iommufd_test(struct iommufd_ucmd *ucmd) return iommufd_test_md_check_refs( ucmd, u64_to_user_ptr(cmd->check_refs.uptr), cmd->check_refs.length, cmd->check_refs.refs); + case IOMMU_TEST_OP_MD_CHECK_IOTLB: + return iommufd_test_md_check_iotlb(ucmd, cmd->id, + cmd->check_iotlb.id, + cmd->check_iotlb.iotlb); case IOMMU_TEST_OP_CREATE_ACCESS: return iommufd_test_create_access(ucmd, cmd->id, cmd->create_access.flags); diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 75279500a4a8..7abe9e85a570 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -863,16 +863,11 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain, static struct iommu_device *mtk_iommu_probe_device(struct device *dev) { struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct mtk_iommu_data *data; + struct mtk_iommu_data *data = dev_iommu_priv_get(dev); struct device_link *link; struct device *larbdev; unsigned int larbid, larbidx, i; - if (!fwspec || fwspec->ops != &mtk_iommu_ops) - return ERR_PTR(-ENODEV); /* Not a iommu client device */ - - data = dev_iommu_priv_get(dev); - if (!MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) return &data->iommu; diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index 67e044c1a7d9..25b41222abae 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -481,9 +481,6 @@ static struct iommu_device *mtk_iommu_v1_probe_device(struct device *dev) idx++; } - if (!fwspec || fwspec->ops != &mtk_iommu_v1_ops) - return ERR_PTR(-ENODEV); /* Not a iommu client device */ - data = dev_iommu_priv_get(dev); /* Link the consumer device with the smi-larb device(supplier) */ diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c index 35ba090f3b5e..719652b60840 100644 --- a/drivers/iommu/of_iommu.c +++ b/drivers/iommu/of_iommu.c @@ -17,8 +17,6 @@ #include <linux/slab.h> #include <linux/fsl/mc.h> -#define NO_IOMMU 1 - static int of_iommu_xlate(struct device *dev, struct of_phandle_args *iommu_spec) { @@ -29,7 +27,7 @@ static int of_iommu_xlate(struct device *dev, ops = iommu_ops_from_fwnode(fwnode); if ((ops && !ops->of_xlate) || !of_device_is_available(iommu_spec->np)) - return NO_IOMMU; + return -ENODEV; ret = iommu_fwspec_init(dev, &iommu_spec->np->fwnode, ops); if (ret) @@ -61,7 +59,7 @@ static int of_iommu_configure_dev_id(struct device_node *master_np, "iommu-map-mask", &iommu_spec.np, iommu_spec.args); if (err) - return err == -ENODEV ? NO_IOMMU : err; + return err; err = of_iommu_xlate(dev, &iommu_spec); of_node_put(iommu_spec.np); @@ -72,7 +70,7 @@ static int of_iommu_configure_dev(struct device_node *master_np, struct device *dev) { struct of_phandle_args iommu_spec; - int err = NO_IOMMU, idx = 0; + int err = -ENODEV, idx = 0; while (!of_parse_phandle_with_args(master_np, "iommus", "#iommu-cells", @@ -107,16 +105,21 @@ static int of_iommu_configure_device(struct device_node *master_np, of_iommu_configure_dev(master_np, dev); } -const struct iommu_ops *of_iommu_configure(struct device *dev, - struct device_node *master_np, - const u32 *id) +/* + * Returns: + * 0 on success, an iommu was configured + * -ENODEV if the device does not have any IOMMU + * -EPROBEDEFER if probing should be tried again + * -errno fatal errors + */ +int of_iommu_configure(struct device *dev, struct device_node *master_np, + const u32 *id) { - const struct iommu_ops *ops = NULL; struct iommu_fwspec *fwspec; - int err = NO_IOMMU; + int err; if (!master_np) - return NULL; + return -ENODEV; /* Serialise to make dev->iommu stable under our potential fwspec */ mutex_lock(&iommu_probe_device_lock); @@ -124,7 +127,7 @@ const struct iommu_ops *of_iommu_configure(struct device *dev, if (fwspec) { if (fwspec->ops) { mutex_unlock(&iommu_probe_device_lock); - return fwspec->ops; + return 0; } /* In the deferred case, start again from scratch */ iommu_fwspec_free(dev); @@ -147,36 +150,21 @@ const struct iommu_ops *of_iommu_configure(struct device *dev, } else { err = of_iommu_configure_device(master_np, dev, id); } - - /* - * Two success conditions can be represented by non-negative err here: - * >0 : there is no IOMMU, or one was unavailable for non-fatal reasons - * 0 : we found an IOMMU, and dev->fwspec is initialised appropriately - * <0 : any actual error - */ - if (!err) { - /* The fwspec pointer changed, read it again */ - fwspec = dev_iommu_fwspec_get(dev); - ops = fwspec->ops; - } mutex_unlock(&iommu_probe_device_lock); - /* - * If we have reason to believe the IOMMU driver missed the initial - * probe for dev, replay it to get things in order. - */ - if (!err && dev->bus) - err = iommu_probe_device(dev); - - /* Ignore all other errors apart from EPROBE_DEFER */ - if (err == -EPROBE_DEFER) { - ops = ERR_PTR(err); - } else if (err < 0) { - dev_dbg(dev, "Adding to IOMMU failed: %d\n", err); - ops = NULL; - } + if (err == -ENODEV || err == -EPROBE_DEFER) + return err; + if (err) + goto err_log; - return ops; + err = iommu_probe_device(dev); + if (err) + goto err_log; + return 0; + +err_log: + dev_dbg(dev, "Adding to IOMMU failed: %pe\n", ERR_PTR(err)); + return err; } static enum iommu_resv_type __maybe_unused @@ -260,7 +248,14 @@ void of_iommu_get_resv_regions(struct device *dev, struct list_head *list) phys_addr_t iova; size_t length; + if (of_dma_is_coherent(dev->of_node)) + prot |= IOMMU_CACHE; + maps = of_translate_dma_region(np, maps, &iova, &length); + if (length == 0) { + dev_warn(dev, "Cannot reserve IOVA region of 0 size\n"); + continue; + } type = iommu_resv_region_get_type(dev, &phys, iova, length); region = iommu_alloc_resv_region(iova, length, prot, type, diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index c66b070841dd..c9528065a59a 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1719,7 +1719,6 @@ static void omap_iommu_release_device(struct device *dev) if (!dev->of_node || !arch_data) return; - dev_iommu_priv_set(dev, NULL); kfree(arch_data); } diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c index 2eb9fb46703b..537359f10997 100644 --- a/drivers/iommu/sprd-iommu.c +++ b/drivers/iommu/sprd-iommu.c @@ -385,13 +385,7 @@ static phys_addr_t sprd_iommu_iova_to_phys(struct iommu_domain *domain, static struct iommu_device *sprd_iommu_probe_device(struct device *dev) { - struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct sprd_iommu_device *sdev; - - if (!fwspec || fwspec->ops != &sprd_iommu_ops) - return ERR_PTR(-ENODEV); - - sdev = dev_iommu_priv_get(dev); + struct sprd_iommu_device *sdev = dev_iommu_priv_get(dev); return &sdev->iommu; } diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 379ebe03efb6..34db37fd9675 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -843,7 +843,7 @@ static int viommu_map_pages(struct iommu_domain *domain, unsigned long iova, .flags = cpu_to_le32(flags), }; - ret = viommu_send_req_sync(vdomain->viommu, &map, sizeof(map)); + ret = viommu_add_req(vdomain->viommu, &map, sizeof(map)); if (ret) { viommu_del_mappings(vdomain, iova, end); return ret; @@ -912,6 +912,33 @@ static void viommu_iotlb_sync(struct iommu_domain *domain, viommu_sync_req(vdomain->viommu); } +static int viommu_iotlb_sync_map(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ + struct viommu_domain *vdomain = to_viommu_domain(domain); + + /* + * May be called before the viommu is initialized including + * while creating direct mapping + */ + if (!vdomain->nr_endpoints) + return 0; + return viommu_sync_req(vdomain->viommu); +} + +static void viommu_flush_iotlb_all(struct iommu_domain *domain) +{ + struct viommu_domain *vdomain = to_viommu_domain(domain); + + /* + * May be called before the viommu is initialized including + * while creating direct mapping + */ + if (!vdomain->nr_endpoints) + return; + viommu_sync_req(vdomain->viommu); +} + static void viommu_get_resv_regions(struct device *dev, struct list_head *head) { struct iommu_resv_region *entry, *new_entry, *msi = NULL; @@ -969,9 +996,6 @@ static struct iommu_device *viommu_probe_device(struct device *dev) struct viommu_dev *viommu = NULL; struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - if (!fwspec || fwspec->ops != &viommu_ops) - return ERR_PTR(-ENODEV); - viommu = viommu_get_by_fwnode(fwspec->iommu_fwnode); if (!viommu) return ERR_PTR(-ENODEV); @@ -1037,6 +1061,8 @@ static bool viommu_capable(struct device *dev, enum iommu_cap cap) switch (cap) { case IOMMU_CAP_CACHE_COHERENCY: return true; + case IOMMU_CAP_DEFERRED_FLUSH: + return true; default: return false; } @@ -1057,7 +1083,9 @@ static struct iommu_ops viommu_ops = { .map_pages = viommu_map_pages, .unmap_pages = viommu_unmap_pages, .iova_to_phys = viommu_iova_to_phys, + .flush_iotlb_all = viommu_flush_iotlb_all, .iotlb_sync = viommu_iotlb_sync, + .iotlb_sync_map = viommu_iotlb_sync_map, .free = viommu_domain_free, } }; diff --git a/drivers/md/md.c b/drivers/md/md.c index 0a2bd72a6d76..2266358d8074 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8132,6 +8132,19 @@ static void status_unused(struct seq_file *seq) seq_printf(seq, "\n"); } +static void status_personalities(struct seq_file *seq) +{ + struct md_personality *pers; + + seq_puts(seq, "Personalities : "); + spin_lock(&pers_lock); + list_for_each_entry(pers, &pers_list, list) + seq_printf(seq, "[%s] ", pers->name); + + spin_unlock(&pers_lock); + seq_puts(seq, "\n"); +} + static int status_resync(struct seq_file *seq, struct mddev *mddev) { sector_t max_sectors, resync, res; @@ -8273,20 +8286,10 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev) static void *md_seq_start(struct seq_file *seq, loff_t *pos) __acquires(&all_mddevs_lock) { - struct md_personality *pers; - - seq_puts(seq, "Personalities : "); - spin_lock(&pers_lock); - list_for_each_entry(pers, &pers_list, list) - seq_printf(seq, "[%s] ", pers->name); - - spin_unlock(&pers_lock); - seq_puts(seq, "\n"); seq->poll_event = atomic_read(&md_event_count); - spin_lock(&all_mddevs_lock); - return seq_list_start(&all_mddevs, *pos); + return seq_list_start_head(&all_mddevs, *pos); } static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos) @@ -8297,16 +8300,23 @@ static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void md_seq_stop(struct seq_file *seq, void *v) __releases(&all_mddevs_lock) { - status_unused(seq); spin_unlock(&all_mddevs_lock); } static int md_seq_show(struct seq_file *seq, void *v) { - struct mddev *mddev = list_entry(v, struct mddev, all_mddevs); + struct mddev *mddev; sector_t sectors; struct md_rdev *rdev; + if (v == &all_mddevs) { + status_personalities(seq); + if (list_empty(&all_mddevs)) + status_unused(seq); + return 0; + } + + mddev = list_entry(v, struct mddev, all_mddevs); if (!mddev_get(mddev)) return 0; @@ -8382,6 +8392,10 @@ static int md_seq_show(struct seq_file *seq, void *v) } spin_unlock(&mddev->lock); spin_lock(&all_mddevs_lock); + + if (mddev == list_last_entry(&all_mddevs, struct mddev, all_mddevs)) + status_unused(seq); + if (atomic_dec_and_test(&mddev->active)) __mddev_put(mddev); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index aaa434f0c175..24f0d799fd98 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1968,12 +1968,12 @@ static void end_sync_write(struct bio *bio) } static int r1_sync_page_io(struct md_rdev *rdev, sector_t sector, - int sectors, struct page *page, int rw) + int sectors, struct page *page, blk_opf_t rw) { if (sync_page_io(rdev, sector, sectors << 9, page, rw, false)) /* success */ return 1; - if (rw == WRITE) { + if (rw == REQ_OP_WRITE) { set_bit(WriteErrorSeen, &rdev->flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) @@ -2090,7 +2090,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio) rdev = conf->mirrors[d].rdev; if (r1_sync_page_io(rdev, sect, s, pages[idx], - WRITE) == 0) { + REQ_OP_WRITE) == 0) { r1_bio->bios[d]->bi_end_io = NULL; rdev_dec_pending(rdev, mddev); } @@ -2105,7 +2105,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio) rdev = conf->mirrors[d].rdev; if (r1_sync_page_io(rdev, sect, s, pages[idx], - READ) != 0) + REQ_OP_READ) != 0) atomic_add(s, &rdev->corrected_errors); } sectors -= s; @@ -2321,7 +2321,7 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio) !test_bit(Faulty, &rdev->flags)) { atomic_inc(&rdev->nr_pending); r1_sync_page_io(rdev, sect, s, - conf->tmppage, WRITE); + conf->tmppage, REQ_OP_WRITE); rdev_dec_pending(rdev, mddev); } } @@ -2335,7 +2335,7 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio) !test_bit(Faulty, &rdev->flags)) { atomic_inc(&rdev->nr_pending); if (r1_sync_page_io(rdev, sect, s, - conf->tmppage, READ)) { + conf->tmppage, REQ_OP_READ)) { atomic_add(s, &rdev->corrected_errors); pr_info("md/raid1:%s: read error corrected (%d sectors at %llu on %pg)\n", mdname(mddev), s, diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c b/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c index bd38ce444232..46676f2c89c7 100644 --- a/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c +++ b/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c @@ -289,7 +289,7 @@ static const struct i2c_algorithm netup_i2c_algorithm = { static const struct i2c_adapter netup_i2c_adapter = { .owner = THIS_MODULE, .name = NETUP_UNIDVB_NAME, - .class = I2C_CLASS_HWMON | I2C_CLASS_SPD, + .class = I2C_CLASS_HWMON, .algo = &netup_i2c_algorithm, }; diff --git a/drivers/memory/tegra/tegra186.c b/drivers/memory/tegra/tegra186.c index 0ff014a9d3cd..1b3183951bfe 100644 --- a/drivers/memory/tegra/tegra186.c +++ b/drivers/memory/tegra/tegra186.c @@ -114,9 +114,12 @@ static void tegra186_mc_client_sid_override(struct tegra_mc *mc, static int tegra186_mc_probe_device(struct tegra_mc *mc, struct device *dev) { #if IS_ENABLED(CONFIG_IOMMU_API) - struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); struct of_phandle_args args; unsigned int i, index = 0; + u32 sid; + + if (!tegra_dev_iommu_get_stream_id(dev, &sid)) + return 0; while (!of_parse_phandle_with_args(dev->of_node, "interconnects", "#interconnect-cells", index, &args)) { @@ -124,11 +127,10 @@ static int tegra186_mc_probe_device(struct tegra_mc *mc, struct device *dev) for (i = 0; i < mc->soc->num_clients; i++) { const struct tegra_mc_client *client = &mc->soc->clients[i]; - if (client->id == args.args[0]) { - u32 sid = fwspec->ids[0] & MC_SID_STREAMID_OVERRIDE_MASK; - - tegra186_mc_client_sid_override(mc, client, sid); - } + if (client->id == args.args[0]) + tegra186_mc_client_sid_override( + mc, client, + sid & MC_SID_STREAMID_OVERRIDE_MASK); } } diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index a5dcd7a13468..572333ead5fb 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -18,6 +18,7 @@ #include <linux/module.h> #include <linux/mutex.h> #include <linux/nvmem-provider.h> +#include <linux/of.h> #include <linux/of_device.h> #include <linux/pm_runtime.h> #include <linux/property.h> @@ -242,7 +243,7 @@ static const struct i2c_device_id at24_ids[] = { }; MODULE_DEVICE_TABLE(i2c, at24_ids); -static const struct of_device_id at24_of_match[] = { +static const struct of_device_id __maybe_unused at24_of_match[] = { { .compatible = "atmel,24c00", .data = &at24_data_24c00 }, { .compatible = "atmel,24c01", .data = &at24_data_24c01 }, { .compatible = "atmel,24cs01", .data = &at24_data_24cs01 }, @@ -835,7 +836,7 @@ static struct i2c_driver at24_driver = { .driver = { .name = "at24", .pm = &at24_pm_ops, - .of_match_table = at24_of_match, + .of_match_table = of_match_ptr(at24_of_match), .acpi_match_table = ACPI_PTR(at24_acpi_ids), }, .probe = at24_probe, diff --git a/drivers/net/amt.c b/drivers/net/amt.c index 53415e83821c..68e79b1272f6 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -11,7 +11,7 @@ #include <linux/net.h> #include <linux/igmp.h> #include <linux/workqueue.h> -#include <net/sch_generic.h> +#include <net/pkt_sched.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/udp.h> @@ -80,11 +80,11 @@ static struct mld2_grec mldv2_zero_grec; static struct amt_skb_cb *amt_skb_cb(struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(struct amt_skb_cb) + sizeof(struct qdisc_skb_cb) > + BUILD_BUG_ON(sizeof(struct amt_skb_cb) + sizeof(struct tc_skb_cb) > sizeof_field(struct sk_buff, cb)); return (struct amt_skb_cb *)((void *)skb->cb + - sizeof(struct qdisc_skb_cb)); + sizeof(struct tc_skb_cb)); } static void __amt_source_gc_work(void) diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c index f44ba2600415..e2ec69aa46e5 100644 --- a/drivers/net/can/c_can/c_can_platform.c +++ b/drivers/net/can/c_can/c_can_platform.c @@ -30,9 +30,9 @@ #include <linux/io.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> +#include <linux/property.h> #include <linux/clk.h> #include <linux/of.h> -#include <linux/of_device.h> #include <linux/mfd/syscon.h> #include <linux/regmap.h> @@ -259,22 +259,13 @@ static int c_can_plat_probe(struct platform_device *pdev) void __iomem *addr; struct net_device *dev; struct c_can_priv *priv; - const struct of_device_id *match; struct resource *mem; int irq; struct clk *clk; const struct c_can_driver_data *drvdata; struct device_node *np = pdev->dev.of_node; - match = of_match_device(c_can_of_table, &pdev->dev); - if (match) { - drvdata = match->data; - } else if (pdev->id_entry->driver_data) { - drvdata = (struct c_can_driver_data *) - platform_get_device_id(pdev)->driver_data; - } else { - return -ENODEV; - } + drvdata = device_get_match_data(&pdev->dev); /* get the appropriate clk */ clk = devm_clk_get(&pdev->dev, NULL); diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c index d15f85a40c1e..8ea7f2795551 100644 --- a/drivers/net/can/flexcan/flexcan-core.c +++ b/drivers/net/can/flexcan/flexcan-core.c @@ -23,11 +23,11 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/of.h> -#include <linux/of_device.h> #include <linux/pinctrl/consumer.h> #include <linux/platform_device.h> #include <linux/can/platform/flexcan.h> #include <linux/pm_runtime.h> +#include <linux/property.h> #include <linux/regmap.h> #include <linux/regulator/consumer.h> @@ -2034,7 +2034,6 @@ MODULE_DEVICE_TABLE(platform, flexcan_id_table); static int flexcan_probe(struct platform_device *pdev) { - const struct of_device_id *of_id; const struct flexcan_devtype_data *devtype_data; struct net_device *dev; struct flexcan_priv *priv; @@ -2090,14 +2089,7 @@ static int flexcan_probe(struct platform_device *pdev) if (IS_ERR(regs)) return PTR_ERR(regs); - of_id = of_match_device(flexcan_of_match, &pdev->dev); - if (of_id) - devtype_data = of_id->data; - else if (platform_get_device_id(pdev)->driver_data) - devtype_data = (struct flexcan_devtype_data *) - platform_get_device_id(pdev)->driver_data; - else - return -ENODEV; + devtype_data = device_get_match_data(&pdev->dev); if ((devtype_data->quirks & FLEXCAN_QUIRK_SUPPORT_FD) && !((devtype_data->quirks & diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c index 4837df6efa92..5b3d69c3b6b6 100644 --- a/drivers/net/can/mscan/mpc5xxx_can.c +++ b/drivers/net/can/mscan/mpc5xxx_can.c @@ -12,8 +12,10 @@ #include <linux/module.h> #include <linux/interrupt.h> #include <linux/platform_device.h> +#include <linux/property.h> #include <linux/netdevice.h> #include <linux/can/dev.h> +#include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> #include <linux/of_platform.h> @@ -290,7 +292,7 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev) int irq, mscan_clksrc = 0; int err = -ENOMEM; - data = of_device_get_match_data(&ofdev->dev); + data = device_get_match_data(&ofdev->dev); if (!data) return -EINVAL; @@ -351,13 +353,11 @@ exit_unmap_mem: static void mpc5xxx_can_remove(struct platform_device *ofdev) { - const struct of_device_id *match; const struct mpc5xxx_can_data *data; struct net_device *dev = platform_get_drvdata(ofdev); struct mscan_priv *priv = netdev_priv(dev); - match = of_match_device(mpc5xxx_can_table, &ofdev->dev); - data = match ? match->data : NULL; + data = device_get_match_data(&ofdev->dev); unregister_mscandev(dev); if (data && data->put_clock) diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index abe58f103043..3722eaa84234 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -20,8 +20,8 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/of.h> -#include <linux/of_device.h> #include <linux/platform_device.h> +#include <linux/property.h> #include <linux/skbuff.h> #include <linux/spinlock.h> #include <linux/string.h> @@ -1726,8 +1726,7 @@ static int xcan_probe(struct platform_device *pdev) struct net_device *ndev; struct xcan_priv *priv; struct phy *transceiver; - const struct of_device_id *of_id; - const struct xcan_devtype_data *devtype = &xcan_axi_data; + const struct xcan_devtype_data *devtype; void __iomem *addr; int ret; int rx_max, tx_max; @@ -1741,9 +1740,7 @@ static int xcan_probe(struct platform_device *pdev) goto err; } - of_id = of_match_device(xcan_of_match, &pdev->dev); - if (of_id && of_id->data) - devtype = of_id->data; + devtype = device_get_match_data(&pdev->dev); hw_tx_max_property = devtype->flags & XCAN_FLAG_TX_MAILBOXES ? "tx-mailbox-count" : "tx-fifo-depth"; diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index dd50502e2122..ae70eac3be28 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -1135,6 +1135,8 @@ static int vsc73xx_gpio_probe(struct vsc73xx *vsc) vsc->gc.label = devm_kasprintf(vsc->dev, GFP_KERNEL, "VSC%04x", vsc->chipid); + if (!vsc->gc.label) + return -ENOMEM; vsc->gc.ngpio = 4; vsc->gc.owner = THIS_MODULE; vsc->gc.parent = vsc->dev; diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c index 068ed52b66c9..b3c81a2e9d46 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c @@ -1490,7 +1490,7 @@ int cn23xx_get_vf_stats(struct octeon_device *oct, int vfidx, mbox_cmd.q_no = vfidx * oct->sriov_info.rings_per_vf; mbox_cmd.recv_len = 0; mbox_cmd.recv_status = 0; - mbox_cmd.fn = (octeon_mbox_callback_t)cn23xx_get_vf_stats_callback; + mbox_cmd.fn = cn23xx_get_vf_stats_callback; ctx.stats = stats; atomic_set(&ctx.status, 0); mbox_cmd.fn_arg = (void *)&ctx; diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c index dd5d80fee24f..d2fcb3da484e 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c @@ -429,7 +429,7 @@ int cn23xx_octeon_pfvf_handshake(struct octeon_device *oct) mbox_cmd.q_no = 0; mbox_cmd.recv_len = 0; mbox_cmd.recv_status = 0; - mbox_cmd.fn = (octeon_mbox_callback_t)octeon_pfvf_hs_callback; + mbox_cmd.fn = octeon_pfvf_hs_callback; mbox_cmd.fn_arg = &status; octeon_mbox_write(oct, &mbox_cmd); diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h index d92bd7e16477..9ac85d22c615 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h @@ -57,7 +57,10 @@ union octeon_mbox_message { } s; }; -typedef void (*octeon_mbox_callback_t)(void *, void *, void *); +struct octeon_mbox_cmd; + +typedef void (*octeon_mbox_callback_t)(struct octeon_device *, + struct octeon_mbox_cmd *, void *); struct octeon_mbox_cmd { union octeon_mbox_message msg; diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 18a1c3b6d72c..c8f35d4de271 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -5,6 +5,7 @@ #define _I40E_ADMINQ_CMD_H_ #include <linux/bits.h> +#include <linux/types.h> /* This header file defines the i40e Admin Queue commands and is shared between * i40e Firmware and Software. diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.h b/drivers/net/ethernet/intel/i40e/i40e_diag.h index ece3a6b9a5c6..ab20202a3da3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_diag.h +++ b/drivers/net/ethernet/intel/i40e/i40e_diag.h @@ -4,6 +4,7 @@ #ifndef _I40E_DIAG_H_ #define _I40E_DIAG_H_ +#include <linux/types.h> #include "i40e_adminq_cmd.h" /* forward-declare the HW struct for the compiler */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c index 4728ba34b0e3..76218f1cb459 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c @@ -506,6 +506,7 @@ u32 rpm2_get_lmac_fifo_len(void *rpmd, int lmac_id) rpm_t *rpm = rpmd; u8 num_lmacs; u32 fifo_len; + u16 max_lmac; lmac_info = rpm_read(rpm, 0, RPM2_CMRX_RX_LMACS); /* LMACs are divided into two groups and each group @@ -513,7 +514,11 @@ u32 rpm2_get_lmac_fifo_len(void *rpmd, int lmac_id) * Group0 lmac_id range {0..3} * Group1 lmac_id range {4..7} */ - fifo_len = rpm->mac_ops->fifo_len / 2; + max_lmac = (rpm_read(rpm, 0, CGX_CONST) >> 24) & 0xFF; + if (max_lmac > 4) + fifo_len = rpm->mac_ops->fifo_len / 2; + else + fifo_len = rpm->mac_ops->fifo_len; if (lmac_id < 4) { num_lmacs = hweight8(lmac_info & 0xF); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c index 4c98950380d5..d231f4d2888b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c @@ -301,6 +301,7 @@ mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core, unsigned long *p_index) { unsigned int num_rows, entry_size; + unsigned long index; /* We only allow allocations of entire rows */ if (num_erps % erp_core->num_erp_banks != 0) @@ -309,10 +310,11 @@ mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core, entry_size = erp_core->erpt_entries_size[region_type]; num_rows = num_erps / erp_core->num_erp_banks; - *p_index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size); - if (*p_index == 0) + index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size); + if (!index) return -ENOBUFS; - *p_index -= MLXSW_SP_ACL_ERP_GENALLOC_OFFSET; + + *p_index = index - MLXSW_SP_ACL_ERP_GENALLOC_OFFSET; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index d50786b0a6ce..50ea1eff02b2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -681,13 +681,13 @@ static void mlxsw_sp_acl_tcam_region_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_region *region) { + struct mlxsw_sp_acl_tcam *tcam = mlxsw_sp_acl_to_tcam(mlxsw_sp->acl); const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; ops->region_fini(mlxsw_sp, region->priv); mlxsw_sp_acl_tcam_region_disable(mlxsw_sp, region); mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region); - mlxsw_sp_acl_tcam_region_id_put(region->group->tcam, - region->id); + mlxsw_sp_acl_tcam_region_id_put(tcam, region->id); kfree(region); } @@ -1564,6 +1564,8 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, tcam->max_groups = max_groups; tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_GROUP_SIZE); + tcam->max_group_size = min_t(unsigned int, tcam->max_group_size, + MLXSW_REG_PAGT_ACL_MAX_NUM); err = ops->init(mlxsw_sp, tcam->priv, tcam); if (err) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 2c255ed9b8a9..7164f9e6370f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -11472,6 +11472,13 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_register_netevent_notifier; + mlxsw_sp->router->netdevice_nb.notifier_call = + mlxsw_sp_router_netdevice_event; + err = register_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp), + &mlxsw_sp->router->netdevice_nb); + if (err) + goto err_register_netdev_notifier; + mlxsw_sp->router->nexthop_nb.notifier_call = mlxsw_sp_nexthop_obj_event; err = register_nexthop_notifier(mlxsw_sp_net(mlxsw_sp), @@ -11487,22 +11494,15 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_register_fib_notifier; - mlxsw_sp->router->netdevice_nb.notifier_call = - mlxsw_sp_router_netdevice_event; - err = register_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp), - &mlxsw_sp->router->netdevice_nb); - if (err) - goto err_register_netdev_notifier; - return 0; -err_register_netdev_notifier: - unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), - &mlxsw_sp->router->fib_nb); err_register_fib_notifier: unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp), &mlxsw_sp->router->nexthop_nb); err_register_nexthop_notifier: + unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp), + &router->netdevice_nb); +err_register_netdev_notifier: unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); err_register_netevent_notifier: unregister_inet6addr_validator_notifier(&router->inet6addr_valid_nb); @@ -11550,11 +11550,11 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_sp_router *router = mlxsw_sp->router; - unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp), - &router->netdevice_nb); unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), &router->fib_nb); unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp), &router->nexthop_nb); + unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp), + &router->netdevice_nb); unregister_netevent_notifier(&router->netevent_nb); unregister_inet6addr_validator_notifier(&router->inet6addr_valid_nb); unregister_inetaddr_validator_notifier(&router->inetaddr_valid_nb); diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 61d8bfd12d5f..55408f16fbbc 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -414,6 +414,7 @@ static const u64 fix_mac[] = { END_SIGN }; +MODULE_DESCRIPTION("Neterion 10GbE driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 39d24e07f306..5b69b9268c75 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -396,7 +396,7 @@ nla_put_failure: struct rtnl_link_ops rmnet_link_ops __read_mostly = { .kind = "rmnet", - .maxtype = __IFLA_RMNET_MAX, + .maxtype = IFLA_RMNET_MAX, .priv_size = sizeof(struct rmnet_priv), .setup = rmnet_vnd_setup, .validate = rmnet_rtnl_validate, diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 8649b3e90edb..0e3731f50fc2 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1949,7 +1949,7 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) struct ravb_tstamp_skb *ts_skb; struct ravb_tx_desc *desc; unsigned long flags; - u32 dma_addr; + dma_addr_t dma_addr; void *buffer; u32 entry; u32 len; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 9f89acf31050..f155e4841c62 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -267,6 +267,7 @@ struct stmmac_priv { u32 msg_enable; int wolopts; int wol_irq; + bool wol_irq_disabled; int clk_csr; struct timer_list eee_ctrl_timer; int lpi_irq; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index dd05437b51f9..42d27b97dd1d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -321,8 +321,9 @@ static int stmmac_ethtool_get_link_ksettings(struct net_device *dev, { struct stmmac_priv *priv = netdev_priv(dev); - if (priv->hw->pcs & STMMAC_PCS_RGMII || - priv->hw->pcs & STMMAC_PCS_SGMII) { + if (!(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS) && + (priv->hw->pcs & STMMAC_PCS_RGMII || + priv->hw->pcs & STMMAC_PCS_SGMII)) { struct rgmii_adv adv; u32 supported, advertising, lp_advertising; @@ -407,8 +408,9 @@ stmmac_ethtool_set_link_ksettings(struct net_device *dev, { struct stmmac_priv *priv = netdev_priv(dev); - if (priv->hw->pcs & STMMAC_PCS_RGMII || - priv->hw->pcs & STMMAC_PCS_SGMII) { + if (!(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS) && + (priv->hw->pcs & STMMAC_PCS_RGMII || + priv->hw->pcs & STMMAC_PCS_SGMII)) { /* Only support ANE */ if (cmd->base.autoneg != AUTONEG_ENABLE) return -EINVAL; @@ -830,10 +832,16 @@ static int stmmac_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) if (wol->wolopts) { pr_info("stmmac: wakeup enable\n"); device_set_wakeup_enable(priv->device, 1); - enable_irq_wake(priv->wol_irq); + /* Avoid unbalanced enable_irq_wake calls */ + if (priv->wol_irq_disabled) + enable_irq_wake(priv->wol_irq); + priv->wol_irq_disabled = false; } else { device_set_wakeup_enable(priv->device, 0); - disable_irq_wake(priv->wol_irq); + /* Avoid unbalanced disable_irq_wake calls */ + if (!priv->wol_irq_disabled) + disable_irq_wake(priv->wol_irq); + priv->wol_irq_disabled = true; } mutex_lock(&priv->lock); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 47de466e432c..a0e46369ae15 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3628,6 +3628,7 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev) /* Request the Wake IRQ in case of another line * is used for WoL */ + priv->wol_irq_disabled = true; if (priv->wol_irq > 0 && priv->wol_irq != dev->irq) { int_name = priv->int_name_wol; sprintf(int_name, "%s:%s", dev->name, "wol"); @@ -4435,6 +4436,28 @@ dma_map_err: } /** + * stmmac_has_ip_ethertype() - Check if packet has IP ethertype + * @skb: socket buffer to check + * + * Check if a packet has an ethertype that will trigger the IP header checks + * and IP/TCP checksum engine of the stmmac core. + * + * Return: true if the ethertype can trigger the checksum engine, false + * otherwise + */ +static bool stmmac_has_ip_ethertype(struct sk_buff *skb) +{ + int depth = 0; + __be16 proto; + + proto = __vlan_get_protocol(skb, eth_header_parse_protocol(skb), + &depth); + + return (depth <= ETH_HLEN) && + (proto == htons(ETH_P_IP) || proto == htons(ETH_P_IPV6)); +} + +/** * stmmac_xmit - Tx entry point of the driver * @skb : the socket buffer * @dev : device pointer @@ -4498,9 +4521,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) /* DWMAC IPs can be synthesized to support tx coe only for a few tx * queues. In that case, checksum offloading for those queues that don't * support tx coe needs to fallback to software checksum calculation. + * + * Packets that won't trigger the COE e.g. most DSA-tagged packets will + * also have to be checksummed in software. */ if (csum_insertion && - priv->plat->tx_queues_cfg[queue].coe_unsupported) { + (priv->plat->tx_queues_cfg[queue].coe_unsupported || + !stmmac_has_ip_ethertype(skb))) { if (unlikely(skb_checksum_help(skb))) goto dma_map_err; csum_insertion = !csum_insertion; @@ -5065,7 +5092,7 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue, stmmac_rx_vlan(priv->dev, skb); skb->protocol = eth_type_trans(skb, priv->dev); - if (unlikely(!coe)) + if (unlikely(!coe) || !stmmac_has_ip_ethertype(skb)) skb_checksum_none_assert(skb); else skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -5588,7 +5615,7 @@ drain_data: skb->protocol = eth_type_trans(skb, priv->dev); - if (unlikely(!coe)) + if (unlikely(!coe) || !stmmac_has_ip_ethertype(skb)) skb_checksum_none_assert(skb); else skb->ip_summed = CHECKSUM_UNNECESSARY; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index faa0561e988e..9d2f4ac783e4 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -56,7 +56,7 @@ #define AM65_CPSW_MAX_PORTS 8 #define AM65_CPSW_MIN_PACKET_SIZE VLAN_ETH_ZLEN -#define AM65_CPSW_MAX_PACKET_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) +#define AM65_CPSW_MAX_PACKET_SIZE 2024 #define AM65_CPSW_REG_CTL 0x004 #define AM65_CPSW_REG_STAT_PORT_EN 0x014 @@ -2244,7 +2244,8 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx) eth_hw_addr_set(port->ndev, port->slave.mac_addr); port->ndev->min_mtu = AM65_CPSW_MIN_PACKET_SIZE; - port->ndev->max_mtu = AM65_CPSW_MAX_PACKET_SIZE; + port->ndev->max_mtu = AM65_CPSW_MAX_PACKET_SIZE - + (VLAN_ETH_HLEN + ETH_FCS_LEN); port->ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_CSUM | diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig index 23cd610bd376..85cdbdd44fec 100644 --- a/drivers/net/ethernet/wangxun/Kconfig +++ b/drivers/net/ethernet/wangxun/Kconfig @@ -26,7 +26,7 @@ config NGBE tristate "Wangxun(R) GbE PCI Express adapters support" depends on PCI select LIBWX - select PHYLIB + select PHYLINK help This driver supports Wangxun(R) GbE PCI Express family of adapters. diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index 23355cc408fd..8706223a6e5a 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -2769,4 +2769,5 @@ void wx_set_ring(struct wx *wx, u32 new_tx_count, } EXPORT_SYMBOL(wx_set_ring); +MODULE_DESCRIPTION("Common library for Wangxun(R) Ethernet drivers."); MODULE_LICENSE("GPL"); diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index aecaf5f44374..77e8250282a5 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -369,6 +369,12 @@ static int nsim_init_netdevsim_vf(struct netdevsim *ns) return err; } +static void nsim_exit_netdevsim(struct netdevsim *ns) +{ + nsim_udp_tunnels_info_destroy(ns->netdev); + mock_phc_destroy(ns->phc); +} + struct netdevsim * nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) { @@ -417,8 +423,7 @@ void nsim_destroy(struct netdevsim *ns) } rtnl_unlock(); if (nsim_dev_port_is_pf(ns->nsim_dev_port)) - nsim_udp_tunnels_info_destroy(dev); - mock_phc_destroy(ns->phc); + nsim_exit_netdevsim(ns); free_netdev(dev); } diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index d2aa3d0695e3..81c20eb4b54b 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -3338,8 +3338,10 @@ static int lan8814_probe(struct phy_device *phydev) #define LAN8841_ADC_CHANNEL_MASK 198 #define LAN8841_PTP_RX_PARSE_L2_ADDR_EN 370 #define LAN8841_PTP_RX_PARSE_IP_ADDR_EN 371 +#define LAN8841_PTP_RX_VERSION 374 #define LAN8841_PTP_TX_PARSE_L2_ADDR_EN 434 #define LAN8841_PTP_TX_PARSE_IP_ADDR_EN 435 +#define LAN8841_PTP_TX_VERSION 438 #define LAN8841_PTP_CMD_CTL 256 #define LAN8841_PTP_CMD_CTL_PTP_ENABLE BIT(2) #define LAN8841_PTP_CMD_CTL_PTP_DISABLE BIT(1) @@ -3383,6 +3385,12 @@ static int lan8841_config_init(struct phy_device *phydev) phy_write_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG, LAN8841_PTP_RX_PARSE_IP_ADDR_EN, 0); + /* Disable checking for minorVersionPTP field */ + phy_write_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG, + LAN8841_PTP_RX_VERSION, 0xff00); + phy_write_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG, + LAN8841_PTP_TX_VERSION, 0xff00); + /* 100BT Clause 40 improvenent errata */ phy_write_mmd(phydev, LAN8841_MMD_ANALOG_REG, LAN8841_ANALOG_CONTROL_1, @@ -4839,6 +4847,7 @@ static struct phy_driver ksphy_driver[] = { .flags = PHY_POLL_CABLE_TEST, .driver_data = &ksz9131_type, .probe = kszphy_probe, + .soft_reset = genphy_soft_reset, .config_init = ksz9131_config_init, .config_intr = kszphy_config_intr, .config_aneg = ksz9131_config_aneg, diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index 6fa679b36290..db39dec7f247 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -151,10 +151,6 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned int br_min, br_nom, br_max; __ETHTOOL_DECLARE_LINK_MODE_MASK(modes) = { 0, }; - phylink_set(modes, Autoneg); - phylink_set(modes, Pause); - phylink_set(modes, Asym_Pause); - /* Decode the bitrate information to MBd */ br_min = br_nom = br_max = 0; if (id->base.br_nominal) { @@ -339,6 +335,10 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, } } + phylink_set(modes, Autoneg); + phylink_set(modes, Pause); + phylink_set(modes, Asym_Pause); + if (bus->sfp_quirk && bus->sfp_quirk->modes) bus->sfp_quirk->modes(id, modes, interfaces); diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c index ba93bab948e0..18df7ca66198 100644 --- a/drivers/net/slip/slhc.c +++ b/drivers/net/slip/slhc.c @@ -752,4 +752,5 @@ EXPORT_SYMBOL(slhc_compress); EXPORT_SYMBOL(slhc_uncompress); EXPORT_SYMBOL(slhc_toss); +MODULE_DESCRIPTION("Compression helpers for SLIP (serial line)"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index e4280e37fec9..0aba3569ccc0 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -1437,5 +1437,6 @@ out: } #endif +MODULE_DESCRIPTION("SLIP (serial line) protocol module"); MODULE_LICENSE("GPL"); MODULE_ALIAS_LDISC(N_SLIP); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 3cb8aa193884..d7ce4a1011ea 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -4295,10 +4295,11 @@ static int virtnet_find_vqs(struct virtnet_info *vi) { vq_callback_t **callbacks; struct virtqueue **vqs; - int ret = -ENOMEM; - int i, total_vqs; const char **names; + int ret = -ENOMEM; + int total_vqs; bool *ctx; + u16 i; /* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by * possible N-1 RX/TX queue pairs used in multiqueue mode, followed by @@ -4335,8 +4336,8 @@ static int virtnet_find_vqs(struct virtnet_info *vi) for (i = 0; i < vi->max_queue_pairs; i++) { callbacks[rxq2vq(i)] = skb_recv_done; callbacks[txq2vq(i)] = skb_xmit_done; - sprintf(vi->rq[i].name, "input.%d", i); - sprintf(vi->sq[i].name, "output.%d", i); + sprintf(vi->rq[i].name, "input.%u", i); + sprintf(vi->sq[i].name, "output.%u", i); names[rxq2vq(i)] = vi->rq[i].name; names[txq2vq(i)] = vi->sq[i].name; if (ctx) diff --git a/drivers/net/wan/slic_ds26522.c b/drivers/net/wan/slic_ds26522.c index 8a51cfcff99e..cbb99fc5ea9f 100644 --- a/drivers/net/wan/slic_ds26522.c +++ b/drivers/net/wan/slic_ds26522.c @@ -28,6 +28,7 @@ static struct spi_device *g_spi; +MODULE_DESCRIPTION("Slic Maxim DS26522 driver"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Zhao Qiang<B45475@freescale.com>"); diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c index a92eb172f0e7..4ceced5cefcf 100644 --- a/drivers/nvdimm/virtio_pmem.c +++ b/drivers/nvdimm/virtio_pmem.c @@ -29,12 +29,27 @@ static int init_vq(struct virtio_pmem *vpmem) return 0; }; +static int virtio_pmem_validate(struct virtio_device *vdev) +{ + struct virtio_shm_region shm_reg; + + if (virtio_has_feature(vdev, VIRTIO_PMEM_F_SHMEM_REGION) && + !virtio_get_shm_region(vdev, &shm_reg, (u8)VIRTIO_PMEM_SHMEM_REGION_ID) + ) { + dev_notice(&vdev->dev, "failed to get shared memory region %d\n", + VIRTIO_PMEM_SHMEM_REGION_ID); + __virtio_clear_bit(vdev, VIRTIO_PMEM_F_SHMEM_REGION); + } + return 0; +} + static int virtio_pmem_probe(struct virtio_device *vdev) { struct nd_region_desc ndr_desc = {}; struct nd_region *nd_region; struct virtio_pmem *vpmem; struct resource res; + struct virtio_shm_region shm_reg; int err = 0; if (!vdev->config->get) { @@ -57,10 +72,16 @@ static int virtio_pmem_probe(struct virtio_device *vdev) goto out_err; } - virtio_cread_le(vpmem->vdev, struct virtio_pmem_config, - start, &vpmem->start); - virtio_cread_le(vpmem->vdev, struct virtio_pmem_config, - size, &vpmem->size); + if (virtio_has_feature(vdev, VIRTIO_PMEM_F_SHMEM_REGION)) { + virtio_get_shm_region(vdev, &shm_reg, (u8)VIRTIO_PMEM_SHMEM_REGION_ID); + vpmem->start = shm_reg.addr; + vpmem->size = shm_reg.len; + } else { + virtio_cread_le(vpmem->vdev, struct virtio_pmem_config, + start, &vpmem->start); + virtio_cread_le(vpmem->vdev, struct virtio_pmem_config, + size, &vpmem->size); + } res.start = vpmem->start; res.end = vpmem->start + vpmem->size - 1; @@ -122,10 +143,17 @@ static void virtio_pmem_remove(struct virtio_device *vdev) virtio_reset_device(vdev); } +static unsigned int features[] = { + VIRTIO_PMEM_F_SHMEM_REGION, +}; + static struct virtio_driver virtio_pmem_driver = { + .feature_table = features, + .feature_table_size = ARRAY_SIZE(features), .driver.name = KBUILD_MODNAME, .driver.owner = THIS_MODULE, .id_table = id_table, + .validate = virtio_pmem_validate, .probe = virtio_pmem_probe, .remove = virtio_pmem_remove, }; diff --git a/drivers/nvme/common/keyring.c b/drivers/nvme/common/keyring.c index ee341b83eeba..a5c0431c101c 100644 --- a/drivers/nvme/common/keyring.c +++ b/drivers/nvme/common/keyring.c @@ -111,7 +111,7 @@ static struct key *nvme_tls_psk_lookup(struct key *keyring, * should be preferred to 'generated' PSKs, * and SHA-384 should be preferred to SHA-256. */ -struct nvme_tls_psk_priority_list { +static struct nvme_tls_psk_priority_list { bool generated; enum nvme_tcp_tls_cipher cipher; } nvme_tls_psk_prio[] = { diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 0af612387083..85ab0fcf9e88 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1740,13 +1740,13 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk, struct nvme_ns_head *head) { struct request_queue *queue = disk->queue; - u32 size = queue_logical_block_size(queue); + u32 max_discard_sectors; - if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX)) - ctrl->max_discard_sectors = - nvme_lba_to_sect(head, ctrl->dmrsl); - - if (ctrl->max_discard_sectors == 0) { + if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX)) { + max_discard_sectors = nvme_lba_to_sect(head, ctrl->dmrsl); + } else if (ctrl->oncs & NVME_CTRL_ONCS_DSM) { + max_discard_sectors = UINT_MAX; + } else { blk_queue_max_discard_sectors(queue, 0); return; } @@ -1754,14 +1754,22 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk, BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) < NVME_DSM_MAX_RANGES); - queue->limits.discard_granularity = size; - - /* If discard is already enabled, don't reset queue limits */ + /* + * If discard is already enabled, don't reset queue limits. + * + * This works around the fact that the block layer can't cope well with + * updating the hardware limits when overridden through sysfs. This is + * harmless because discard limits in NVMe are purely advisory. + */ if (queue->limits.max_discard_sectors) return; - blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors); - blk_queue_max_discard_segments(queue, ctrl->max_discard_segments); + blk_queue_max_discard_sectors(queue, max_discard_sectors); + if (ctrl->dmrl) + blk_queue_max_discard_segments(queue, ctrl->dmrl); + else + blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES); + queue->limits.discard_granularity = queue_logical_block_size(queue); if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES) blk_queue_max_write_zeroes_sectors(queue, UINT_MAX); @@ -2930,14 +2938,6 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl) struct nvme_id_ctrl_nvm *id; int ret; - if (ctrl->oncs & NVME_CTRL_ONCS_DSM) { - ctrl->max_discard_sectors = UINT_MAX; - ctrl->max_discard_segments = NVME_DSM_MAX_RANGES; - } else { - ctrl->max_discard_sectors = 0; - ctrl->max_discard_segments = 0; - } - /* * Even though NVMe spec explicitly states that MDTS is not applicable * to the write-zeroes, we are cautious and limit the size to the @@ -2967,8 +2967,7 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl) if (ret) goto free_data; - if (id->dmrl) - ctrl->max_discard_segments = id->dmrl; + ctrl->dmrl = id->dmrl; ctrl->dmrsl = le32_to_cpu(id->dmrsl); if (id->wzsl) ctrl->max_zeroes_sectors = nvme_mps_to_sectors(ctrl, id->wzsl); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 4be7f6822966..030c80818240 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -303,14 +303,13 @@ struct nvme_ctrl { u32 max_hw_sectors; u32 max_segments; u32 max_integrity_segments; - u32 max_discard_sectors; - u32 max_discard_segments; u32 max_zeroes_sectors; #ifdef CONFIG_BLK_DEV_ZONED u32 max_zone_append; #endif u16 crdt[3]; u16 oncs; + u8 dmrl; u32 dmrsl; u16 oacs; u16 sqsize; @@ -932,6 +931,10 @@ extern struct device_attribute dev_attr_ana_grpid; extern struct device_attribute dev_attr_ana_state; extern struct device_attribute subsys_attr_iopolicy; +static inline bool nvme_disk_is_ns_head(struct gendisk *disk) +{ + return disk->fops == &nvme_ns_head_ops; +} #else #define multipath false static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) @@ -1009,6 +1012,10 @@ static inline void nvme_mpath_start_request(struct request *rq) static inline void nvme_mpath_end_request(struct request *rq) { } +static inline bool nvme_disk_is_ns_head(struct gendisk *disk) +{ + return false; +} #endif /* CONFIG_NVME_MULTIPATH */ int nvme_revalidate_zones(struct nvme_ns *ns); @@ -1037,7 +1044,10 @@ static inline int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf) static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev) { - return dev_to_disk(dev)->private_data; + struct gendisk *disk = dev_to_disk(dev); + + WARN_ON(nvme_disk_is_ns_head(disk)); + return disk->private_data; } #ifdef CONFIG_NVME_HWMON diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 61af7ff1a9d6..c1d6357ec98a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1284,6 +1284,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) struct request *abort_req; struct nvme_command cmd = { }; u32 csts = readl(dev->bar + NVME_REG_CSTS); + u8 opcode; /* If PCI error recovery process is happening, we cannot reset or * the recovery mechanism will surely fail. @@ -1310,8 +1311,8 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) { dev_warn(dev->ctrl.device, - "I/O %d QID %d timeout, completion polled\n", - req->tag, nvmeq->qid); + "I/O tag %d (%04x) QID %d timeout, completion polled\n", + req->tag, nvme_cid(req), nvmeq->qid); return BLK_EH_DONE; } @@ -1327,8 +1328,8 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) fallthrough; case NVME_CTRL_DELETING: dev_warn_ratelimited(dev->ctrl.device, - "I/O %d QID %d timeout, disable controller\n", - req->tag, nvmeq->qid); + "I/O tag %d (%04x) QID %d timeout, disable controller\n", + req->tag, nvme_cid(req), nvmeq->qid); nvme_req(req)->flags |= NVME_REQ_CANCELLED; nvme_dev_disable(dev, true); return BLK_EH_DONE; @@ -1343,10 +1344,12 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) * command was already aborted once before and still hasn't been * returned to the driver, or if this is the admin queue. */ + opcode = nvme_req(req)->cmd->common.opcode; if (!nvmeq->qid || iod->aborted) { dev_warn(dev->ctrl.device, - "I/O %d QID %d timeout, reset controller\n", - req->tag, nvmeq->qid); + "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, reset controller\n", + req->tag, nvme_cid(req), opcode, + nvme_opcode_str(nvmeq->qid, opcode, 0), nvmeq->qid); nvme_req(req)->flags |= NVME_REQ_CANCELLED; goto disable; } @@ -1362,10 +1365,10 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) cmd.abort.sqid = cpu_to_le16(nvmeq->qid); dev_warn(nvmeq->dev->ctrl.device, - "I/O %d (%s) QID %d timeout, aborting\n", - req->tag, - nvme_get_opcode_str(nvme_req(req)->cmd->common.opcode), - nvmeq->qid); + "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, aborting req_op:%s(%u) size:%u\n", + req->tag, nvme_cid(req), opcode, nvme_get_opcode_str(opcode), + nvmeq->qid, blk_op_str(req_op(req)), req_op(req), + blk_rq_bytes(req)); abort_req = blk_mq_alloc_request(dev->ctrl.admin_q, nvme_req_op(&cmd), BLK_MQ_REQ_NOWAIT); @@ -2743,10 +2746,10 @@ static void nvme_reset_work(struct work_struct *work) * controller around but remove all namespaces. */ if (dev->online_queues > 1) { + nvme_dbbuf_set(dev); nvme_unquiesce_io_queues(&dev->ctrl); nvme_wait_freeze(&dev->ctrl); nvme_pci_update_nr_queues(dev); - nvme_dbbuf_set(dev); nvme_unfreeze(&dev->ctrl); } else { dev_warn(dev->ctrl.device, "IO queues lost\n"); @@ -3408,6 +3411,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x1c5c, 0x174a), /* SK Hynix P31 SSD */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1c5c, 0x1D59), /* SK Hynix BC901 */ + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x15b7, 0x2001), /* Sandisk Skyhawk */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x1d97, 0x2263), /* SPCC */ diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c index 391b1465ebfd..fc3eed00f9ff 100644 --- a/drivers/nvme/host/pr.c +++ b/drivers/nvme/host/pr.c @@ -98,7 +98,7 @@ static int nvme_send_pr_command(struct block_device *bdev, struct nvme_command *c, void *data, unsigned int data_len) { if (IS_ENABLED(CONFIG_NVME_MULTIPATH) && - bdev->bd_disk->fops == &nvme_ns_head_ops) + nvme_disk_is_ns_head(bdev->bd_disk)) return nvme_send_ns_head_pr_command(bdev, c, data, data_len); return nvme_send_ns_pr_command(bdev->bd_disk->private_data, c, data, diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index c89503da24d7..11dde0d83044 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1946,9 +1946,14 @@ static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq) struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); struct nvme_rdma_queue *queue = req->queue; struct nvme_rdma_ctrl *ctrl = queue->ctrl; - - dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n", - rq->tag, nvme_rdma_queue_idx(queue)); + u8 opcode = req->req.cmd->common.opcode; + u8 fctype = req->req.cmd->fabrics.fctype; + int qid = nvme_rdma_queue_idx(queue); + + dev_warn(ctrl->ctrl.device, + "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout\n", + rq->tag, nvme_cid(rq), opcode, + nvme_opcode_str(qid, opcode, fctype), qid); if (nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_LIVE) { /* diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c index ac24ad102380..754e91111042 100644 --- a/drivers/nvme/host/sysfs.c +++ b/drivers/nvme/host/sysfs.c @@ -39,10 +39,9 @@ static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev) { struct gendisk *disk = dev_to_disk(dev); - if (disk->fops == &nvme_bdev_ops) - return nvme_get_ns_from_dev(dev)->head; - else + if (nvme_disk_is_ns_head(disk)) return disk->private_data; + return nvme_get_ns_from_dev(dev)->head; } static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, @@ -233,7 +232,8 @@ static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj, } #ifdef CONFIG_NVME_MULTIPATH if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) { - if (dev_to_disk(dev)->fops != &nvme_bdev_ops) /* per-path attr */ + /* per-path attr */ + if (nvme_disk_is_ns_head(dev_to_disk(dev))) return 0; if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl)) return 0; diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 08805f027810..d058d990532b 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1922,14 +1922,13 @@ static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl) ctrl->opts->subsysnqn); if (!pskid) { dev_err(ctrl->device, "no valid PSK found\n"); - ret = -ENOKEY; - goto out_free_queue; + return -ENOKEY; } } ret = nvme_tcp_alloc_queue(ctrl, 0, pskid); if (ret) - goto out_free_queue; + return ret; ret = nvme_tcp_alloc_async_req(to_tcp_ctrl(ctrl)); if (ret) @@ -2433,9 +2432,9 @@ static enum blk_eh_timer_return nvme_tcp_timeout(struct request *rq) int qid = nvme_tcp_queue_id(req->queue); dev_warn(ctrl->device, - "queue %d: timeout cid %#x type %d opcode %#x (%s)\n", - nvme_tcp_queue_id(req->queue), nvme_cid(rq), pdu->hdr.type, - opc, nvme_opcode_str(qid, opc, fctype)); + "I/O tag %d (%04x) type %d opcode %#x (%s) QID %d timeout\n", + rq->tag, nvme_cid(rq), pdu->hdr.type, opc, + nvme_opcode_str(qid, opc, fctype), qid); if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) { /* diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index bd59990b5250..bda7a3009e85 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1031,7 +1031,7 @@ nvmet_fc_match_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle) list_for_each_entry(host, &tgtport->host_list, host_list) { if (host->hosthandle == hosthandle && !host->invalid) { if (nvmet_fc_hostport_get(host)) - return (host); + return host; } } diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index c65a73433c05..ead349af30f1 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -995,11 +995,6 @@ fcloop_nport_free(struct kref *ref) { struct fcloop_nport *nport = container_of(ref, struct fcloop_nport, ref); - unsigned long flags; - - spin_lock_irqsave(&fcloop_lock, flags); - list_del(&nport->nport_list); - spin_unlock_irqrestore(&fcloop_lock, flags); kfree(nport); } @@ -1357,6 +1352,8 @@ __unlink_remote_port(struct fcloop_nport *nport) nport->tport->remoteport = NULL; nport->rport = NULL; + list_del(&nport->nport_list); + return rport; } diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 4597bca43a6d..667f9c04f35d 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -37,6 +37,8 @@ #define NVMET_RDMA_MAX_MDTS 8 #define NVMET_RDMA_MAX_METADATA_MDTS 5 +#define NVMET_RDMA_BACKLOG 128 + struct nvmet_rdma_srq; struct nvmet_rdma_cmd { @@ -1583,8 +1585,19 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, } if (queue->host_qid == 0) { - /* Let inflight controller teardown complete */ - flush_workqueue(nvmet_wq); + struct nvmet_rdma_queue *q; + int pending = 0; + + /* Check for pending controller teardown */ + mutex_lock(&nvmet_rdma_queue_mutex); + list_for_each_entry(q, &nvmet_rdma_queue_list, queue_list) { + if (q->nvme_sq.ctrl == queue->nvme_sq.ctrl && + q->state == NVMET_RDMA_Q_DISCONNECTING) + pending++; + } + mutex_unlock(&nvmet_rdma_queue_mutex); + if (pending > NVMET_RDMA_BACKLOG) + return NVME_SC_CONNECT_CTRL_BUSY; } ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn); @@ -1880,7 +1893,7 @@ static int nvmet_rdma_enable_port(struct nvmet_rdma_port *port) goto out_destroy_id; } - ret = rdma_listen(cm_id, 128); + ret = rdma_listen(cm_id, NVMET_RDMA_BACKLOG); if (ret) { pr_err("listening to %pISpcs failed (%d)\n", addr, ret); goto out_destroy_id; diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 4cc27856aa8f..6a1e6bb80062 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -24,6 +24,8 @@ #include "nvmet.h" #define NVMET_TCP_DEF_INLINE_DATA_SIZE (4 * PAGE_SIZE) +#define NVMET_TCP_MAXH2CDATA 0x400000 /* 16M arbitrary limit */ +#define NVMET_TCP_BACKLOG 128 static int param_store_val(const char *str, int *val, int min, int max) { @@ -923,7 +925,7 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue) icresp->hdr.pdo = 0; icresp->hdr.plen = cpu_to_le32(icresp->hdr.hlen); icresp->pfv = cpu_to_le16(NVME_TCP_PFV_1_0); - icresp->maxdata = cpu_to_le32(0x400000); /* 16M arbitrary limit */ + icresp->maxdata = cpu_to_le32(NVMET_TCP_MAXH2CDATA); icresp->cpda = 0; if (queue->hdr_digest) icresp->digest |= NVME_TCP_HDR_DIGEST_ENABLE; @@ -978,13 +980,13 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) { struct nvme_tcp_data_pdu *data = &queue->pdu.data; struct nvmet_tcp_cmd *cmd; + unsigned int exp_data_len; if (likely(queue->nr_cmds)) { if (unlikely(data->ttag >= queue->nr_cmds)) { pr_err("queue %d: received out of bound ttag %u, nr_cmds %u\n", queue->idx, data->ttag, queue->nr_cmds); - nvmet_tcp_fatal_error(queue); - return -EPROTO; + goto err_proto; } cmd = &queue->cmds[data->ttag]; } else { @@ -995,19 +997,32 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) pr_err("ttag %u unexpected data offset %u (expected %u)\n", data->ttag, le32_to_cpu(data->data_offset), cmd->rbytes_done); - /* FIXME: use path and transport errors */ - nvmet_req_complete(&cmd->req, - NVME_SC_INVALID_FIELD | NVME_SC_DNR); - return -EPROTO; + goto err_proto; } + exp_data_len = le32_to_cpu(data->hdr.plen) - + nvmet_tcp_hdgst_len(queue) - + nvmet_tcp_ddgst_len(queue) - + sizeof(*data); + cmd->pdu_len = le32_to_cpu(data->data_length); + if (unlikely(cmd->pdu_len != exp_data_len || + cmd->pdu_len == 0 || + cmd->pdu_len > NVMET_TCP_MAXH2CDATA)) { + pr_err("H2CData PDU len %u is invalid\n", cmd->pdu_len); + goto err_proto; + } cmd->pdu_recv = 0; nvmet_tcp_build_pdu_iovec(cmd); queue->cmd = cmd; queue->rcv_state = NVMET_TCP_RECV_DATA; return 0; + +err_proto: + /* FIXME: use proper transport errors */ + nvmet_tcp_fatal_error(queue); + return -EPROTO; } static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) @@ -1768,7 +1783,7 @@ static int nvmet_tcp_try_peek_pdu(struct nvmet_tcp_queue *queue) (int)sizeof(struct nvme_tcp_icreq_pdu)); if (hdr->type == nvme_tcp_icreq && hdr->hlen == sizeof(struct nvme_tcp_icreq_pdu) && - hdr->plen == (__le32)sizeof(struct nvme_tcp_icreq_pdu)) { + hdr->plen == cpu_to_le32(sizeof(struct nvme_tcp_icreq_pdu))) { pr_debug("queue %d: icreq detected\n", queue->idx); return len; @@ -2053,7 +2068,7 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport) goto err_sock; } - ret = kernel_listen(port->sock, 128); + ret = kernel_listen(port->sock, NVMET_TCP_BACKLOG); if (ret) { pr_err("failed to listen %d on port sock\n", ret); goto err_sock; @@ -2119,8 +2134,19 @@ static u16 nvmet_tcp_install_queue(struct nvmet_sq *sq) container_of(sq, struct nvmet_tcp_queue, nvme_sq); if (sq->qid == 0) { - /* Let inflight controller teardown complete */ - flush_workqueue(nvmet_wq); + struct nvmet_tcp_queue *q; + int pending = 0; + + /* Check for pending controller teardown */ + mutex_lock(&nvmet_tcp_queue_mutex); + list_for_each_entry(q, &nvmet_tcp_queue_list, queue_list) { + if (q->nvme_sq.ctrl == sq->ctrl && + q->state == NVMET_TCP_Q_DISCONNECTING) + pending++; + } + mutex_unlock(&nvmet_tcp_queue_mutex); + if (pending > NVMET_TCP_BACKLOG) + return NVME_SC_CONNECT_CTRL_BUSY; } queue->nr_cmds = sq->size * 2; diff --git a/drivers/nvme/target/trace.c b/drivers/nvme/target/trace.c index bff454d46255..6ee1f3db81d0 100644 --- a/drivers/nvme/target/trace.c +++ b/drivers/nvme/target/trace.c @@ -211,7 +211,7 @@ const char *nvmet_trace_disk_name(struct trace_seq *p, char *name) return ret; } -const char *nvmet_trace_ctrl_name(struct trace_seq *p, struct nvmet_ctrl *ctrl) +const char *nvmet_trace_ctrl_id(struct trace_seq *p, u16 ctrl_id) { const char *ret = trace_seq_buffer_ptr(p); @@ -224,8 +224,8 @@ const char *nvmet_trace_ctrl_name(struct trace_seq *p, struct nvmet_ctrl *ctrl) * If we can know the extra data of the connect command in this stage, * we can update this print statement later. */ - if (ctrl) - trace_seq_printf(p, "%d", ctrl->cntlid); + if (ctrl_id) + trace_seq_printf(p, "%d", ctrl_id); else trace_seq_printf(p, "_"); trace_seq_putc(p, 0); diff --git a/drivers/nvme/target/trace.h b/drivers/nvme/target/trace.h index 6109b3806b12..7f7ebf9558e5 100644 --- a/drivers/nvme/target/trace.h +++ b/drivers/nvme/target/trace.h @@ -32,18 +32,24 @@ const char *nvmet_trace_parse_fabrics_cmd(struct trace_seq *p, u8 fctype, nvmet_trace_parse_nvm_cmd(p, opcode, cdw10) : \ nvmet_trace_parse_admin_cmd(p, opcode, cdw10))) -const char *nvmet_trace_ctrl_name(struct trace_seq *p, struct nvmet_ctrl *ctrl); -#define __print_ctrl_name(ctrl) \ - nvmet_trace_ctrl_name(p, ctrl) +const char *nvmet_trace_ctrl_id(struct trace_seq *p, u16 ctrl_id); +#define __print_ctrl_id(ctrl_id) \ + nvmet_trace_ctrl_id(p, ctrl_id) const char *nvmet_trace_disk_name(struct trace_seq *p, char *name); #define __print_disk_name(name) \ nvmet_trace_disk_name(p, name) #ifndef TRACE_HEADER_MULTI_READ -static inline struct nvmet_ctrl *nvmet_req_to_ctrl(struct nvmet_req *req) +static inline u16 nvmet_req_to_ctrl_id(struct nvmet_req *req) { - return req->sq->ctrl; + /* + * The queue and controller pointers are not valid until an association + * has been established. + */ + if (!req->sq || !req->sq->ctrl) + return 0; + return req->sq->ctrl->cntlid; } static inline void __assign_req_name(char *name, struct nvmet_req *req) @@ -53,8 +59,7 @@ static inline void __assign_req_name(char *name, struct nvmet_req *req) return; } - strncpy(name, req->ns->device_path, - min_t(size_t, DISK_NAME_LEN, strlen(req->ns->device_path))); + strscpy_pad(name, req->ns->device_path, DISK_NAME_LEN); } #endif @@ -63,7 +68,7 @@ TRACE_EVENT(nvmet_req_init, TP_ARGS(req, cmd), TP_STRUCT__entry( __field(struct nvme_command *, cmd) - __field(struct nvmet_ctrl *, ctrl) + __field(u16, ctrl_id) __array(char, disk, DISK_NAME_LEN) __field(int, qid) __field(u16, cid) @@ -76,7 +81,7 @@ TRACE_EVENT(nvmet_req_init, ), TP_fast_assign( __entry->cmd = cmd; - __entry->ctrl = nvmet_req_to_ctrl(req); + __entry->ctrl_id = nvmet_req_to_ctrl_id(req); __assign_req_name(__entry->disk, req); __entry->qid = req->sq->qid; __entry->cid = cmd->common.command_id; @@ -85,12 +90,12 @@ TRACE_EVENT(nvmet_req_init, __entry->flags = cmd->common.flags; __entry->nsid = le32_to_cpu(cmd->common.nsid); __entry->metadata = le64_to_cpu(cmd->common.metadata); - memcpy(__entry->cdw10, &cmd->common.cdw10, + memcpy(__entry->cdw10, &cmd->common.cdws, sizeof(__entry->cdw10)); ), TP_printk("nvmet%s: %sqid=%d, cmdid=%u, nsid=%u, flags=%#x, " "meta=%#llx, cmd=(%s, %s)", - __print_ctrl_name(__entry->ctrl), + __print_ctrl_id(__entry->ctrl_id), __print_disk_name(__entry->disk), __entry->qid, __entry->cid, __entry->nsid, __entry->flags, __entry->metadata, @@ -104,7 +109,7 @@ TRACE_EVENT(nvmet_req_complete, TP_PROTO(struct nvmet_req *req), TP_ARGS(req), TP_STRUCT__entry( - __field(struct nvmet_ctrl *, ctrl) + __field(u16, ctrl_id) __array(char, disk, DISK_NAME_LEN) __field(int, qid) __field(int, cid) @@ -112,7 +117,7 @@ TRACE_EVENT(nvmet_req_complete, __field(u16, status) ), TP_fast_assign( - __entry->ctrl = nvmet_req_to_ctrl(req); + __entry->ctrl_id = nvmet_req_to_ctrl_id(req); __entry->qid = req->cq->qid; __entry->cid = req->cqe->command_id; __entry->result = le64_to_cpu(req->cqe->result.u64); @@ -120,7 +125,7 @@ TRACE_EVENT(nvmet_req_complete, __assign_req_name(__entry->disk, req); ), TP_printk("nvmet%s: %sqid=%d, cmdid=%u, res=%#llx, status=%#x", - __print_ctrl_name(__entry->ctrl), + __print_ctrl_id(__entry->ctrl_id), __print_disk_name(__entry->disk), __entry->qid, __entry->cid, __entry->result, __entry->status) diff --git a/drivers/of/device.c b/drivers/of/device.c index 6e9572c4af83..de89f9906375 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -93,12 +93,12 @@ of_dma_set_restricted_buffer(struct device *dev, struct device_node *np) int of_dma_configure_id(struct device *dev, struct device_node *np, bool force_dma, const u32 *id) { - const struct iommu_ops *iommu; const struct bus_dma_region *map = NULL; struct device_node *bus_np; u64 dma_start = 0; u64 mask, end, size = 0; bool coherent; + int iommu_ret; int ret; if (np == dev->of_node) @@ -181,21 +181,29 @@ int of_dma_configure_id(struct device *dev, struct device_node *np, dev_dbg(dev, "device is%sdma coherent\n", coherent ? " " : " not "); - iommu = of_iommu_configure(dev, np, id); - if (PTR_ERR(iommu) == -EPROBE_DEFER) { + iommu_ret = of_iommu_configure(dev, np, id); + if (iommu_ret == -EPROBE_DEFER) { /* Don't touch range map if it wasn't set from a valid dma-ranges */ if (!ret) dev->dma_range_map = NULL; kfree(map); return -EPROBE_DEFER; - } + } else if (iommu_ret == -ENODEV) { + dev_dbg(dev, "device is not behind an iommu\n"); + } else if (iommu_ret) { + dev_err(dev, "iommu configuration for device failed with %pe\n", + ERR_PTR(iommu_ret)); - dev_dbg(dev, "device is%sbehind an iommu\n", - iommu ? " " : " not "); + /* + * Historically this routine doesn't fail driver probing + * due to errors in of_iommu_configure() + */ + } else + dev_dbg(dev, "device is behind an iommu\n"); - arch_setup_dma_ops(dev, dma_start, size, iommu, coherent); + arch_setup_dma_ops(dev, dma_start, size, coherent); - if (!iommu) + if (iommu_ret) of_dma_set_restricted_buffer(dev, np); return 0; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 43e11c9502d1..d8f11a078924 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -6295,6 +6295,41 @@ int pcie_set_mps(struct pci_dev *dev, int mps) } EXPORT_SYMBOL(pcie_set_mps); +static enum pci_bus_speed to_pcie_link_speed(u16 lnksta) +{ + return pcie_link_speed[FIELD_GET(PCI_EXP_LNKSTA_CLS, lnksta)]; +} + +int pcie_link_speed_mbps(struct pci_dev *pdev) +{ + u16 lnksta; + int err; + + err = pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnksta); + if (err) + return err; + + switch (to_pcie_link_speed(lnksta)) { + case PCIE_SPEED_2_5GT: + return 2500; + case PCIE_SPEED_5_0GT: + return 5000; + case PCIE_SPEED_8_0GT: + return 8000; + case PCIE_SPEED_16_0GT: + return 16000; + case PCIE_SPEED_32_0GT: + return 32000; + case PCIE_SPEED_64_0GT: + return 64000; + default: + break; + } + + return -EINVAL; +} +EXPORT_SYMBOL(pcie_link_speed_mbps); + /** * pcie_bandwidth_available - determine minimum link settings of a PCIe * device and its bandwidth limitation @@ -6328,8 +6363,7 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev, while (dev) { pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta); - next_speed = pcie_link_speed[FIELD_GET(PCI_EXP_LNKSTA_CLS, - lnksta)]; + next_speed = to_pcie_link_speed(lnksta); next_width = FIELD_GET(PCI_EXP_LNKSTA_NLW, lnksta); next_bw = next_width * PCIE_SPEED2MBS_ENC(next_speed); diff --git a/drivers/phy/mediatek/phy-mtk-tphy.c b/drivers/phy/mediatek/phy-mtk-tphy.c index 05eab9014132..a4746f6cb8a1 100644 --- a/drivers/phy/mediatek/phy-mtk-tphy.c +++ b/drivers/phy/mediatek/phy-mtk-tphy.c @@ -185,6 +185,10 @@ #define P3D_RG_CDR_BIR_LTD1 GENMASK(28, 24) #define P3D_RG_CDR_BIR_LTD0 GENMASK(12, 8) +#define U3P_U3_PHYD_TOP1 0x100 +#define P3D_RG_PHY_MODE GENMASK(2, 1) +#define P3D_RG_FORCE_PHY_MODE BIT(0) + #define U3P_U3_PHYD_RXDET1 0x128 #define P3D_RG_RXDET_STB2_SET GENMASK(17, 9) @@ -327,6 +331,7 @@ struct mtk_phy_instance { int discth; int pre_emphasis; bool bc12_en; + bool type_force_mode; }; struct mtk_tphy { @@ -768,6 +773,23 @@ static void u3_phy_instance_init(struct mtk_tphy *tphy, void __iomem *phya = u3_banks->phya; void __iomem *phyd = u3_banks->phyd; + if (instance->type_force_mode) { + /* force phy as usb mode, default is pcie rc mode */ + mtk_phy_update_field(phyd + U3P_U3_PHYD_TOP1, P3D_RG_PHY_MODE, 1); + mtk_phy_set_bits(phyd + U3P_U3_PHYD_TOP1, P3D_RG_FORCE_PHY_MODE); + /* power down phy by ip and pipe reset */ + mtk_phy_set_bits(u3_banks->chip + U3P_U3_CHIP_GPIO_CTLD, + P3C_FORCE_IP_SW_RST | P3C_MCU_BUS_CK_GATE_EN); + mtk_phy_set_bits(u3_banks->chip + U3P_U3_CHIP_GPIO_CTLE, + P3C_RG_SWRST_U3_PHYD | P3C_RG_SWRST_U3_PHYD_FORCE_EN); + udelay(10); + /* power on phy again */ + mtk_phy_clear_bits(u3_banks->chip + U3P_U3_CHIP_GPIO_CTLD, + P3C_FORCE_IP_SW_RST | P3C_MCU_BUS_CK_GATE_EN); + mtk_phy_clear_bits(u3_banks->chip + U3P_U3_CHIP_GPIO_CTLE, + P3C_RG_SWRST_U3_PHYD | P3C_RG_SWRST_U3_PHYD_FORCE_EN); + } + /* gating PCIe Analog XTAL clock */ mtk_phy_set_bits(u3_banks->spllc + U3P_SPLLC_XTALCTL3, XC3_RG_U3_XTAL_RX_PWD | XC3_RG_U3_FRC_XTAL_RX_PWD); @@ -1120,6 +1142,9 @@ static void phy_parse_property(struct mtk_tphy *tphy, { struct device *dev = &instance->phy->dev; + if (instance->type == PHY_TYPE_USB3) + instance->type_force_mode = device_property_read_bool(dev, "mediatek,force-mode"); + if (instance->type != PHY_TYPE_USB2) return; diff --git a/drivers/phy/phy-can-transceiver.c b/drivers/phy/phy-can-transceiver.c index 840b7f8a31c5..ee4ce4249698 100644 --- a/drivers/phy/phy-can-transceiver.c +++ b/drivers/phy/phy-can-transceiver.c @@ -6,11 +6,11 @@ * */ #include <linux/of.h> -#include<linux/phy/phy.h> -#include<linux/platform_device.h> -#include<linux/module.h> -#include<linux/gpio.h> -#include<linux/gpio/consumer.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/module.h> +#include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/mux/consumer.h> struct can_transceiver_data { diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index 96a0b1e111f3..d9be6a4d5383 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -959,7 +959,7 @@ struct phy *phy_create(struct device *dev, struct device_node *node, if (!phy) return ERR_PTR(-ENOMEM); - id = ida_simple_get(&phy_ida, 0, 0, GFP_KERNEL); + id = ida_alloc(&phy_ida, GFP_KERNEL); if (id < 0) { dev_err(dev, "unable to get id\n"); ret = id; @@ -1232,7 +1232,7 @@ static void phy_release(struct device *dev) dev_vdbg(dev, "releasing '%s'\n", dev_name(dev)); debugfs_remove_recursive(phy->debugfs); regulator_put(phy->pwr); - ida_simple_remove(&phy_ida, phy->id); + ida_free(&phy_ida, phy->id); kfree(phy); } diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index f6c727249104..1ad10110dd25 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -1203,6 +1203,127 @@ static const struct qmp_phy_init_tbl sc8280xp_usb43dp_pcs_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07), }; +static const struct qmp_phy_init_tbl x1e80100_usb43dp_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x62), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0xc2), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE1, 0xc2), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE1, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_BUF_ENABLE, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x1a), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_CFG, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x1a), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x41), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x82), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MSB_MODE0, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x82), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MSB_MODE1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE0, 0x55), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE0, 0x55), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE1, 0x55), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE1, 0x55), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE1, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE0, 0xba), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE0, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE1, 0xba), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x13), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_HS_SWITCH_SEL_1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CORE_CLK_DIV_MODE0, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0xa0), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x76), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO_MODE1, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE0, 0x20), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE1, 0x20), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_INITVAL2, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAXVAL2, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SVS_MODE_CLK_SEL, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x0a), +}; + +static const struct qmp_phy_init_tbl x1e80100_usb43dp_tx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_LANE_MODE_1, 0x05), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_LANE_MODE_2, 0x50), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_LANE_MODE_3, 0x50), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_TX, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_RX, 0x0a), +}; + +static const struct qmp_phy_init_tbl x1e80100_usb43dp_rx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_SIGDET_CNTRL, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_SIGDET_DEGLITCH_CNTRL, 0x0e), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_SIGDET_ENABLES, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B0, 0xc3), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B1, 0xc3), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B2, 0xd8), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B3, 0x9e), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B4, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B5, 0xb6), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B6, 0x64), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B0, 0xd6), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B1, 0xee), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B2, 0x18), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B3, 0x9a), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B4, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B5, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B6, 0xe3), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_IVCM_CAL_CODE_OVERRIDE, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_RX_IVCM_CAL_CTRL2, 0x80), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_RX_SUMMER_CAL_SPD_MODE, 0x2f), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_DFE_CTLE_POST_CAL_OFFSET, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_PI_CONTROLS, 0x15), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_PI_CTRL1, 0xd0), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_PI_CTRL2, 0x48), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_SB2_GAIN2_RATE2, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_RX_IVCM_POSTCAL_OFFSET, 0x7c), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_VGA_CAL_CNTRL1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_VGA_CAL_MAN_VAL, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_DFE_DAC_ENABLE1, 0x88), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_DFE_3, 0x45), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_GM_CAL, 0x0d), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_FO_GAIN_RATE2, 0x09), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_SO_GAIN_RATE2, 0x05), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_Q_PI_INTRINSIC_BIAS_RATE32, 0x2f), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_RX_BKUP_CTRL1, 0x14), +}; + +static const struct qmp_phy_init_tbl x1e80100_usb43dp_pcs_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG1, 0xc4), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG2, 0x89), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG3, 0x20), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG6, 0x13), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_REFGEN_REQ_CONFIG1, 0x21), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_RX_SIGDET_LVL, 0x55), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_CDR_RESET_TIME, 0x0a), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_ALIGN_DETECT_CONFIG1, 0xd4), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_ALIGN_DETECT_CONFIG2, 0x30), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_PCS_TX_RX_CONFIG, 0x0c), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG1, 0x4b), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG5, 0x10), +}; + +static const struct qmp_phy_init_tbl x1e80100_usb43dp_pcs_usb_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL, 0xf8), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07), +}; + /* list of regulators */ struct qmp_regulator_data { const char *name; @@ -1682,6 +1803,51 @@ static const struct qmp_phy_cfg sc8280xp_usb43dpphy_cfg = { .regs = qmp_v5_5nm_usb3phy_regs_layout, }; +static const struct qmp_phy_cfg x1e80100_usb3dpphy_cfg = { + .offsets = &qmp_combo_offsets_v5, + + .serdes_tbl = x1e80100_usb43dp_serdes_tbl, + .serdes_tbl_num = ARRAY_SIZE(x1e80100_usb43dp_serdes_tbl), + .tx_tbl = x1e80100_usb43dp_tx_tbl, + .tx_tbl_num = ARRAY_SIZE(x1e80100_usb43dp_tx_tbl), + .rx_tbl = x1e80100_usb43dp_rx_tbl, + .rx_tbl_num = ARRAY_SIZE(x1e80100_usb43dp_rx_tbl), + .pcs_tbl = x1e80100_usb43dp_pcs_tbl, + .pcs_tbl_num = ARRAY_SIZE(x1e80100_usb43dp_pcs_tbl), + .pcs_usb_tbl = x1e80100_usb43dp_pcs_usb_tbl, + .pcs_usb_tbl_num = ARRAY_SIZE(x1e80100_usb43dp_pcs_usb_tbl), + + .dp_serdes_tbl = qmp_v6_dp_serdes_tbl, + .dp_serdes_tbl_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl), + .dp_tx_tbl = qmp_v6_dp_tx_tbl, + .dp_tx_tbl_num = ARRAY_SIZE(qmp_v6_dp_tx_tbl), + + .serdes_tbl_rbr = qmp_v6_dp_serdes_tbl_rbr, + .serdes_tbl_rbr_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_rbr), + .serdes_tbl_hbr = qmp_v6_dp_serdes_tbl_hbr, + .serdes_tbl_hbr_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr), + .serdes_tbl_hbr2 = qmp_v6_dp_serdes_tbl_hbr2, + .serdes_tbl_hbr2_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr2), + .serdes_tbl_hbr3 = qmp_v6_dp_serdes_tbl_hbr3, + .serdes_tbl_hbr3_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr3), + + .swing_hbr_rbr = &qmp_dp_v5_voltage_swing_hbr_rbr, + .pre_emphasis_hbr_rbr = &qmp_dp_v5_pre_emphasis_hbr_rbr, + .swing_hbr3_hbr2 = &qmp_dp_v5_voltage_swing_hbr3_hbr2, + .pre_emphasis_hbr3_hbr2 = &qmp_dp_v5_pre_emphasis_hbr3_hbr2, + + .dp_aux_init = qmp_v4_dp_aux_init, + .configure_dp_tx = qmp_v4_configure_dp_tx, + .configure_dp_phy = qmp_v4_configure_dp_phy, + .calibrate_dp_phy = qmp_v4_calibrate_dp_phy, + + .reset_list = msm8996_usb3phy_reset_l, + .num_resets = ARRAY_SIZE(msm8996_usb3phy_reset_l), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), + .regs = qmp_v45_usb3phy_regs_layout, +}; + static const struct qmp_phy_cfg sm6350_usb3dpphy_cfg = { .offsets = &qmp_combo_offsets_v3, @@ -3518,6 +3684,14 @@ static const struct of_device_id qmp_combo_of_match_table[] = { .compatible = "qcom,sm8550-qmp-usb3-dp-phy", .data = &sm8550_usb3dpphy_cfg, }, + { + .compatible = "qcom,sm8650-qmp-usb3-dp-phy", + .data = &sm8550_usb3dpphy_cfg, + }, + { + .compatible = "qcom,x1e80100-qmp-usb3-dp-phy", + .data = &x1e80100_usb3dpphy_cfg, + }, { } }; MODULE_DEVICE_TABLE(of, qmp_combo_of_match_table); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c index b64598ac59f4..2af7115ef968 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c @@ -1909,6 +1909,35 @@ static const struct qmp_phy_init_tbl sm8550_qmp_gen4x2_pcie_pcs_misc_tbl[] = { QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G4_FOM_EQ_CONFIG5, 0xf2), }; +static const struct qmp_phy_init_tbl sm8650_qmp_gen4x2_pcie_rx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_FO_GAIN_RATE_2, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_FO_GAIN_RATE_3, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_PI_CONTROLS, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_SO_ACC_DEFAULT_VAL_RATE3, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_IVCM_CAL_CTRL2, 0x82), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_DFE_3, 0x05), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_VGA_CAL_MAN_VAL, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_GM_CAL, 0x0d), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_EQU_ADAPTOR_CNTRL4, 0x0b), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_SIGDET_ENABLES, 0x1c), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_PHPRE_CTRL, 0x20), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B0, 0xd3), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B1, 0xd3), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B2, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B3, 0x9a), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B4, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B5, 0xb6), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B6, 0xee), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B0, 0x23), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B1, 0x9b), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B2, 0x60), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B3, 0xdf), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B4, 0x43), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B5, 0x76), + QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B6, 0xff), +}; + static const struct qmp_phy_init_tbl sa8775p_qmp_gen4x2_pcie_serdes_alt_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V5_COM_BIAS_EN_CLKBUFLR_EN, 0x14), QMP_PHY_INIT_CFG(QSERDES_V5_COM_PLL_IVCO, 0x0f), @@ -3047,6 +3076,36 @@ static const struct qmp_phy_cfg sm8550_qmp_gen4x2_pciephy_cfg = { .has_nocsr_reset = true, }; +static const struct qmp_phy_cfg sm8650_qmp_gen4x2_pciephy_cfg = { + .lanes = 2, + + .offsets = &qmp_pcie_offsets_v6_20, + + .tbls = { + .serdes = sm8550_qmp_gen4x2_pcie_serdes_tbl, + .serdes_num = ARRAY_SIZE(sm8550_qmp_gen4x2_pcie_serdes_tbl), + .tx = sm8550_qmp_gen4x2_pcie_tx_tbl, + .tx_num = ARRAY_SIZE(sm8550_qmp_gen4x2_pcie_tx_tbl), + .rx = sm8650_qmp_gen4x2_pcie_rx_tbl, + .rx_num = ARRAY_SIZE(sm8650_qmp_gen4x2_pcie_rx_tbl), + .pcs = sm8550_qmp_gen4x2_pcie_pcs_tbl, + .pcs_num = ARRAY_SIZE(sm8550_qmp_gen4x2_pcie_pcs_tbl), + .pcs_misc = sm8550_qmp_gen4x2_pcie_pcs_misc_tbl, + .pcs_misc_num = ARRAY_SIZE(sm8550_qmp_gen4x2_pcie_pcs_misc_tbl), + .ln_shrd = sm8550_qmp_gen4x2_pcie_ln_shrd_tbl, + .ln_shrd_num = ARRAY_SIZE(sm8550_qmp_gen4x2_pcie_ln_shrd_tbl), + }, + .reset_list = sdm845_pciephy_reset_l, + .num_resets = ARRAY_SIZE(sdm845_pciephy_reset_l), + .vreg_list = sm8550_qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(sm8550_qmp_phy_vreg_l), + .regs = pciephy_v5_regs_layout, + + .pwrdn_ctrl = SW_PWRDN | REFCLK_DRV_DSBL, + .phy_status = PHYSTATUS_4_20, + .has_nocsr_reset = true, +}; + static const struct qmp_phy_cfg sa8775p_qmp_gen4x2_pciephy_cfg = { .lanes = 2, .offsets = &qmp_pcie_offsets_v5_20, @@ -3820,6 +3879,12 @@ static const struct of_device_id qmp_pcie_of_match_table[] = { }, { .compatible = "qcom,sm8550-qmp-gen4x2-pcie-phy", .data = &sm8550_qmp_gen4x2_pciephy_cfg, + }, { + .compatible = "qcom,sm8650-qmp-gen3x2-pcie-phy", + .data = &sm8550_qmp_gen3x2_pciephy_cfg, + }, { + .compatible = "qcom,sm8650-qmp-gen4x2-pcie-phy", + .data = &sm8650_qmp_gen4x2_pciephy_cfg, }, { }, }; diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-ufs-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-ufs-v6.h index c23d5e41e25b..fe6c450f6123 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-ufs-v6.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-ufs-v6.h @@ -12,6 +12,7 @@ #define QPHY_V6_PCS_UFS_SW_RESET 0x008 #define QPHY_V6_PCS_UFS_TIMER_20US_CORECLK_STEPS_MSB 0x00c #define QPHY_V6_PCS_UFS_TIMER_20US_CORECLK_STEPS_LSB 0x010 +#define QPHY_V6_PCS_UFS_PCS_CTRL1 0x020 #define QPHY_V6_PCS_UFS_PLL_CNTL 0x02c #define QPHY_V6_PCS_UFS_TX_LARGE_AMP_DRV_LVL 0x030 #define QPHY_V6_PCS_UFS_TX_SMALL_AMP_DRV_LVL 0x038 diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-usb-v7.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-usb-v7.h new file mode 100644 index 000000000000..24368d45ae76 --- /dev/null +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-usb-v7.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023, Linaro Limited + */ + +#ifndef QCOM_PHY_QMP_PCS_USB_V7_H_ +#define QCOM_PHY_QMP_PCS_USB_V7_H_ + +#define QPHY_V7_PCS_USB3_POWER_STATE_CONFIG1 0x00 +#define QPHY_V7_PCS_USB3_AUTONOMOUS_MODE_CTRL 0x08 +#define QPHY_V7_PCS_USB3_LFPS_RXTERM_IRQ_CLEAR 0x14 +#define QPHY_V7_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL 0x18 +#define QPHY_V7_PCS_USB3_RXEQTRAINING_DFE_TIME_S2 0x3c +#define QPHY_V7_PCS_USB3_RCVR_DTCT_DLY_U3_L 0x40 +#define QPHY_V7_PCS_USB3_RCVR_DTCT_DLY_U3_H 0x44 + +#endif diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v7.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v7.h new file mode 100644 index 000000000000..c7759892ed2e --- /dev/null +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v7.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023, Linaro Limited + */ + +#ifndef QCOM_PHY_QMP_PCS_V7_H_ +#define QCOM_PHY_QMP_PCS_V7_H_ + +/* Only for QMP V7 PHY - USB/PCIe PCS registers */ +#define QPHY_V7_PCS_SW_RESET 0x000 +#define QPHY_V7_PCS_PCS_STATUS1 0x014 +#define QPHY_V7_PCS_POWER_DOWN_CONTROL 0x040 +#define QPHY_V7_PCS_START_CONTROL 0x044 +#define QPHY_V7_PCS_POWER_STATE_CONFIG1 0x090 +#define QPHY_V7_PCS_LOCK_DETECT_CONFIG1 0x0c4 +#define QPHY_V7_PCS_LOCK_DETECT_CONFIG2 0x0c8 +#define QPHY_V7_PCS_LOCK_DETECT_CONFIG3 0x0cc +#define QPHY_V7_PCS_LOCK_DETECT_CONFIG6 0x0d8 +#define QPHY_V7_PCS_REFGEN_REQ_CONFIG1 0x0dc +#define QPHY_V7_PCS_RX_SIGDET_LVL 0x188 +#define QPHY_V7_PCS_RCVR_DTCT_DLY_P1U2_L 0x190 +#define QPHY_V7_PCS_RCVR_DTCT_DLY_P1U2_H 0x194 +#define QPHY_V7_PCS_RATE_SLEW_CNTRL1 0x198 +#define QPHY_V7_PCS_CDR_RESET_TIME 0x1b0 +#define QPHY_V7_PCS_ALIGN_DETECT_CONFIG1 0x1c0 +#define QPHY_V7_PCS_ALIGN_DETECT_CONFIG2 0x1c4 +#define QPHY_V7_PCS_PCS_TX_RX_CONFIG 0x1d0 +#define QPHY_V7_PCS_EQ_CONFIG1 0x1dc +#define QPHY_V7_PCS_EQ_CONFIG2 0x1e0 +#define QPHY_V7_PCS_EQ_CONFIG5 0x1ec + +#endif diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v6.h index f420f8faf16a..ec7291424dd1 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v6.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v6.h @@ -22,6 +22,8 @@ #define QSERDES_V6_COM_DIV_FRAC_START2_MODE1 0x34 #define QSERDES_V6_COM_DIV_FRAC_START3_MODE1 0x38 #define QSERDES_V6_COM_HSCLK_SEL_1 0x3c +#define QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE1 0x40 +#define QSERDES_V6_COM_INTEGLOOP_GAIN1_MODE1 0x44 #define QSERDES_V6_COM_VCO_TUNE1_MODE1 0x48 #define QSERDES_V6_COM_VCO_TUNE2_MODE1 0x4c #define QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE1 0x50 @@ -48,6 +50,7 @@ #define QSERDES_V6_COM_VCO_TUNE2_MODE0 0xac #define QSERDES_V6_COM_BG_TIMER 0xbc #define QSERDES_V6_COM_SSC_EN_CENTER 0xc0 +#define QSERDES_V6_COM_SSC_ADJ_PER1 0xc4 #define QSERDES_V6_COM_SSC_PER1 0xcc #define QSERDES_V6_COM_SSC_PER2 0xd0 #define QSERDES_V6_COM_PLL_POST_DIV_MUX 0xd8 @@ -56,6 +59,7 @@ #define QSERDES_V6_COM_SYS_CLK_CTRL 0xe4 #define QSERDES_V6_COM_SYSCLK_BUF_ENABLE 0xe8 #define QSERDES_V6_COM_PLL_IVCO 0xf4 +#define QSERDES_V6_COM_PLL_IVCO_MODE1 0xf8 #define QSERDES_V6_COM_SYSCLK_EN_SEL 0x110 #define QSERDES_V6_COM_RESETSM_CNTRL 0x118 #define QSERDES_V6_COM_LOCK_CMP_EN 0x120 @@ -63,6 +67,7 @@ #define QSERDES_V6_COM_VCO_TUNE_CTRL 0x13c #define QSERDES_V6_COM_VCO_TUNE_MAP 0x140 #define QSERDES_V6_COM_VCO_TUNE_INITVAL2 0x148 +#define QSERDES_V6_COM_VCO_TUNE_MAXVAL2 0x158 #define QSERDES_V6_COM_CLK_SELECT 0x164 #define QSERDES_V6_COM_CORE_CLK_EN 0x170 #define QSERDES_V6_COM_CMN_CONFIG_1 0x174 diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v7.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v7.h new file mode 100644 index 000000000000..7430f4921477 --- /dev/null +++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v7.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023, Linaro Limited + */ + +#ifndef QCOM_PHY_QMP_QSERDES_COM_V7_H_ +#define QCOM_PHY_QMP_QSERDES_COM_V7_H_ + +/* Only for QMP V7 PHY - QSERDES COM registers */ + +#define QSERDES_V7_COM_SSC_STEP_SIZE1_MODE1 0x00 +#define QSERDES_V7_COM_SSC_STEP_SIZE2_MODE1 0x04 +#define QSERDES_V7_COM_CP_CTRL_MODE1 0x10 +#define QSERDES_V7_COM_PLL_RCTRL_MODE1 0x14 +#define QSERDES_V7_COM_PLL_CCTRL_MODE1 0x18 +#define QSERDES_V7_COM_CORECLK_DIV_MODE1 0x1c +#define QSERDES_V7_COM_LOCK_CMP1_MODE1 0x20 +#define QSERDES_V7_COM_LOCK_CMP2_MODE1 0x24 +#define QSERDES_V7_COM_DEC_START_MODE1 0x28 +#define QSERDES_V7_COM_DEC_START_MSB_MODE1 0x2c +#define QSERDES_V7_COM_DIV_FRAC_START1_MODE1 0x30 +#define QSERDES_V7_COM_DIV_FRAC_START2_MODE1 0x34 +#define QSERDES_V7_COM_DIV_FRAC_START3_MODE1 0x38 +#define QSERDES_V7_COM_HSCLK_SEL_1 0x3c +#define QSERDES_V7_COM_INTEGLOOP_GAIN0_MODE1 0x40 +#define QSERDES_V7_COM_INTEGLOOP_GAIN1_MODE1 0x44 +#define QSERDES_V7_COM_VCO_TUNE1_MODE1 0x48 +#define QSERDES_V7_COM_VCO_TUNE2_MODE1 0x4c +#define QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE1_MODE1 0x50 +#define QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE2_MODE1 0x54 +#define QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE1_MODE0 0x58 +#define QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE2_MODE0 0x5c +#define QSERDES_V7_COM_SSC_STEP_SIZE1_MODE0 0x60 +#define QSERDES_V7_COM_SSC_STEP_SIZE2_MODE0 0x64 +#define QSERDES_V7_COM_CP_CTRL_MODE0 0x70 +#define QSERDES_V7_COM_PLL_RCTRL_MODE0 0x74 +#define QSERDES_V7_COM_PLL_CCTRL_MODE0 0x78 +#define QSERDES_V7_COM_PLL_CORE_CLK_DIV_MODE0 0x7c +#define QSERDES_V7_COM_LOCK_CMP1_MODE0 0x80 +#define QSERDES_V7_COM_LOCK_CMP2_MODE0 0x84 +#define QSERDES_V7_COM_DEC_START_MODE0 0x88 +#define QSERDES_V7_COM_DEC_START_MSB_MODE0 0x8c +#define QSERDES_V7_COM_DIV_FRAC_START1_MODE0 0x90 +#define QSERDES_V7_COM_DIV_FRAC_START2_MODE0 0x94 +#define QSERDES_V7_COM_DIV_FRAC_START3_MODE0 0x98 +#define QSERDES_V7_COM_HSCLK_HS_SWITCH_SEL_1 0x9c +#define QSERDES_V7_COM_INTEGLOOP_GAIN0_MODE0 0xa0 +#define QSERDES_V7_COM_INTEGLOOP_GAIN1_MODE0 0xa4 +#define QSERDES_V7_COM_VCO_TUNE1_MODE0 0xa8 +#define QSERDES_V7_COM_VCO_TUNE2_MODE0 0xac +#define QSERDES_V7_COM_BG_TIMER 0xbc +#define QSERDES_V7_COM_SSC_EN_CENTER 0xc0 +#define QSERDES_V7_COM_SSC_ADJ_PER1 0xc4 +#define QSERDES_V7_COM_SSC_PER1 0xcc +#define QSERDES_V7_COM_SSC_PER2 0xd0 +#define QSERDES_V7_COM_PLL_POST_DIV_MUX 0xd8 +#define QSERDES_V7_COM_PLL_BIAS_EN_CLK_BUFLR_EN 0xdc +#define QSERDES_V7_COM_CLK_ENABLE1 0xe0 +#define QSERDES_V7_COM_SYS_CLK_CTRL 0xe4 +#define QSERDES_V7_COM_SYSCLK_BUF_ENABLE 0xe8 +#define QSERDES_V7_COM_PLL_IVCO 0xf4 +#define QSERDES_V7_COM_PLL_IVCO_MODE1 0xf8 +#define QSERDES_V7_COM_SYSCLK_EN_SEL 0x110 +#define QSERDES_V7_COM_RESETSM_CNTRL 0x118 +#define QSERDES_V7_COM_LOCK_CMP_EN 0x120 +#define QSERDES_V7_COM_LOCK_CMP_CFG 0x124 +#define QSERDES_V7_COM_VCO_TUNE_CTRL 0x13c +#define QSERDES_V7_COM_VCO_TUNE_MAP 0x140 +#define QSERDES_V7_COM_VCO_TUNE_INITVAL2 0x148 +#define QSERDES_V7_COM_VCO_TUNE_MAXVAL2 0x158 +#define QSERDES_V7_COM_CLK_SELECT 0x164 +#define QSERDES_V7_COM_CORE_CLK_EN 0x170 +#define QSERDES_V7_COM_CMN_CONFIG_1 0x174 +#define QSERDES_V7_COM_SVS_MODE_CLK_SEL 0x17c +#define QSERDES_V7_COM_CMN_MISC_1 0x184 +#define QSERDES_V7_COM_CMN_MODE 0x188 +#define QSERDES_V7_COM_PLL_VCO_DC_LEVEL_CTRL 0x198 +#define QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_1 0x1a4 +#define QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_2 0x1a8 +#define QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_3 0x1ac +#define QSERDES_V7_COM_ADDITIONAL_MISC 0x1b4 +#define QSERDES_V7_COM_ADDITIONAL_MISC_2 0x1b8 +#define QSERDES_V7_COM_ADDITIONAL_MISC_3 0x1bc +#define QSERDES_V7_COM_CMN_STATUS 0x1d0 +#define QSERDES_V7_COM_C_READY_STATUS 0x1f8 + +#endif diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-ufs-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-ufs-v6.h index 15bcb4ba9139..35d497fd9f9a 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-ufs-v6.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-ufs-v6.h @@ -10,10 +10,18 @@ #define QSERDES_UFS_V6_TX_RES_CODE_LANE_RX 0x2c #define QSERDES_UFS_V6_TX_RES_CODE_LANE_OFFSET_TX 0x30 #define QSERDES_UFS_V6_TX_RES_CODE_LANE_OFFSET_RX 0x34 +#define QSERDES_UFS_V6_TX_LANE_MODE_1 0x7c +#define QSERDES_UFS_V6_TX_FR_DCC_CTRL 0x108 #define QSERDES_UFS_V6_RX_UCDR_FASTLOCK_FO_GAIN_RATE2 0x08 #define QSERDES_UFS_V6_RX_UCDR_FASTLOCK_FO_GAIN_RATE4 0x10 +#define QSERDES_UFS_V6_RX_UCDR_SO_SATURATION 0x28 +#define QSERDES_UFS_V6_RX_UCDR_PI_CTRL1 0x58 +#define QSERDES_UFS_V6_RX_RX_TERM_BW_CTRL0 0xc4 +#define QSERDES_UFS_V6_RX_UCDR_FO_GAIN_RATE2 0xd4 +#define QSERDES_UFS_V6_RX_UCDR_FO_GAIN_RATE4 0xdc #define QSERDES_UFS_V6_RX_VGA_CAL_MAN_VAL 0x178 +#define QSERDES_UFS_V6_RX_INTERFACE_MODE 0x1e0 #define QSERDES_UFS_V6_RX_MODE_RATE_0_1_B0 0x208 #define QSERDES_UFS_V6_RX_MODE_RATE_0_1_B1 0x20c #define QSERDES_UFS_V6_RX_MODE_RATE_0_1_B3 0x214 diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h index 8883e1de730e..23ffcfae9efa 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h @@ -23,6 +23,7 @@ #define QSERDES_V6_TX_PARRATE_REC_DETECT_IDLE_EN 0x60 #define QSERDES_V6_TX_BIST_PATTERN7 0x7c #define QSERDES_V6_TX_LANE_MODE_1 0x84 +#define QSERDES_V6_TX_LANE_MODE_2 0x88 #define QSERDES_V6_TX_LANE_MODE_3 0x8c #define QSERDES_V6_TX_LANE_MODE_4 0x90 #define QSERDES_V6_TX_LANE_MODE_5 0x94 diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_20.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_20.h index 5385a8b60970..6ed5339fd2ea 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_20.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_20.h @@ -15,10 +15,13 @@ #define QSERDES_V6_20_RX_UCDR_FO_GAIN_RATE_2 0x08 #define QSERDES_V6_20_RX_UCDR_FO_GAIN_RATE_3 0x0c +#define QSERDES_V6_20_RX_UCDR_SO_GAIN_RATE_2 0x18 #define QSERDES_V6_20_RX_UCDR_PI_CONTROLS 0x20 #define QSERDES_V6_20_RX_UCDR_SO_ACC_DEFAULT_VAL_RATE3 0x34 #define QSERDES_V6_20_RX_IVCM_CAL_CTRL2 0x9c #define QSERDES_V6_20_RX_IVCM_POSTCAL_OFFSET 0xa0 +#define QSERDES_V6_20_RX_DFE_1 0xac +#define QSERDES_V6_20_RX_DFE_2 0xb0 #define QSERDES_V6_20_RX_DFE_3 0xb4 #define QSERDES_V6_20_RX_VGA_CAL_MAN_VAL 0xe8 #define QSERDES_V6_20_RX_GM_CAL 0x10c @@ -41,5 +44,6 @@ #define QSERDES_V6_20_RX_MODE_RATE3_B4 0x220 #define QSERDES_V6_20_RX_MODE_RATE3_B5 0x224 #define QSERDES_V6_20_RX_MODE_RATE3_B6 0x228 +#define QSERDES_V6_20_RX_BKUP_CTRL1 0x22c #endif diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h new file mode 100644 index 000000000000..a814ad11af07 --- /dev/null +++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023, Linaro Limited + */ + +#ifndef QCOM_PHY_QMP_QSERDES_TXRX_V6_N4_H_ +#define QCOM_PHY_QMP_QSERDES_TXRX_V6_N4_H_ + +#define QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_TX 0x30 +#define QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_RX 0x34 +#define QSERDES_V6_N4_TX_LANE_MODE_1 0x78 +#define QSERDES_V6_N4_TX_LANE_MODE_2 0x7c +#define QSERDES_V6_N4_TX_LANE_MODE_3 0x80 + +#define QSERDES_V6_N4_RX_UCDR_FO_GAIN_RATE2 0x8 +#define QSERDES_V6_N4_RX_UCDR_SO_GAIN_RATE2 0x18 +#define QSERDES_V6_N4_RX_UCDR_PI_CONTROLS 0x20 +#define QSERDES_V6_N4_RX_IVCM_CAL_CODE_OVERRIDE 0x94 +#define QSERDES_V6_N4_RX_RX_IVCM_CAL_CTRL2 0x9c +#define QSERDES_V6_N4_RX_RX_IVCM_POSTCAL_OFFSET 0xa0 +#define QSERDES_V6_N4_RX_DFE_3 0xb4 +#define QSERDES_V6_N4_RX_VGA_CAL_CNTRL1 0xe0 +#define QSERDES_V6_N4_RX_VGA_CAL_MAN_VAL 0xe8 +#define QSERDES_V6_N4_RX_GM_CAL 0x10c +#define QSERDES_V6_N4_RX_SIGDET_ENABLES 0x148 +#define QSERDES_V6_N4_RX_SIGDET_CNTRL 0x14c +#define QSERDES_V6_N4_RX_SIGDET_DEGLITCH_CNTRL 0x154 +#define QSERDES_V6_N4_RX_DFE_CTLE_POST_CAL_OFFSET 0x194 +#define QSERDES_V6_N4_RX_Q_PI_INTRINSIC_BIAS_RATE32 0x1dc +#define QSERDES_V6_N4_RX_UCDR_PI_CTRL1 0x23c +#define QSERDES_V6_N4_RX_UCDR_PI_CTRL2 0x240 +#define QSERDES_V6_N4_RX_UCDR_SB2_GAIN2_RATE2 0x27c +#define QSERDES_V6_N4_RX_DFE_DAC_ENABLE1 0x298 +#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B0 0x2b8 +#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B1 0x2bc +#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B2 0x2c0 +#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B3 0x2c4 +#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B4 0x2c8 +#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B5 0x2cc +#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B6 0x2d0 +#define QSERDES_V6_N4_RX_MODE_RATE2_B0 0x2d4 +#define QSERDES_V6_N4_RX_MODE_RATE2_B1 0x2d8 +#define QSERDES_V6_N4_RX_MODE_RATE2_B2 0x2dc +#define QSERDES_V6_N4_RX_MODE_RATE2_B3 0x2e0 +#define QSERDES_V6_N4_RX_MODE_RATE2_B4 0x2e4 +#define QSERDES_V6_N4_RX_MODE_RATE2_B5 0x2e8 +#define QSERDES_V6_N4_RX_MODE_RATE2_B6 0x2ec +#define QSERDES_V6_N4_RX_RX_SUMMER_CAL_SPD_MODE 0x30c +#define QSERDES_V6_N4_RX_RX_BKUP_CTRL1 0x310 + +#endif diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v7.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v7.h new file mode 100644 index 000000000000..91f865b11347 --- /dev/null +++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v7.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023, Linaro Limited + */ + +#ifndef QCOM_PHY_QMP_QSERDES_TXRX_V7_H_ +#define QCOM_PHY_QMP_QSERDES_TXRX_V7_H_ + +#define QSERDES_V7_TX_CLKBUF_ENABLE 0x08 +#define QSERDES_V7_TX_RESET_TSYNC_EN 0x1c +#define QSERDES_V7_TX_PRE_STALL_LDO_BOOST_EN 0x20 +#define QSERDES_V7_TX_TX_BAND 0x24 +#define QSERDES_V7_TX_INTERFACE_SELECT 0x2c +#define QSERDES_V7_TX_RES_CODE_LANE_TX 0x34 +#define QSERDES_V7_TX_RES_CODE_LANE_RX 0x38 +#define QSERDES_V7_TX_RES_CODE_LANE_OFFSET_TX 0x3c +#define QSERDES_V7_TX_RES_CODE_LANE_OFFSET_RX 0x40 +#define QSERDES_V7_TX_PARRATE_REC_DETECT_IDLE_EN 0x60 +#define QSERDES_V7_TX_BIST_PATTERN7 0x7c +#define QSERDES_V7_TX_LANE_MODE_1 0x84 +#define QSERDES_V7_TX_LANE_MODE_2 0x88 +#define QSERDES_V7_TX_LANE_MODE_3 0x8c +#define QSERDES_V7_TX_LANE_MODE_4 0x90 +#define QSERDES_V7_TX_LANE_MODE_5 0x94 +#define QSERDES_V7_TX_RCV_DETECT_LVL_2 0xa4 +#define QSERDES_V7_TX_TRAN_DRVR_EMP_EN 0xc0 +#define QSERDES_V7_TX_TX_INTERFACE_MODE 0xc4 +#define QSERDES_V7_TX_VMODE_CTRL1 0xc8 +#define QSERDES_V7_TX_PI_QEC_CTRL 0xe4 + +#define QSERDES_V7_RX_UCDR_FO_GAIN 0x08 +#define QSERDES_V7_RX_UCDR_SO_GAIN 0x14 +#define QSERDES_V7_RX_UCDR_FASTLOCK_FO_GAIN 0x30 +#define QSERDES_V7_RX_UCDR_SO_SATURATION_AND_ENABLE 0x34 +#define QSERDES_V7_RX_UCDR_FASTLOCK_COUNT_LOW 0x3c +#define QSERDES_V7_RX_UCDR_FASTLOCK_COUNT_HIGH 0x40 +#define QSERDES_V7_RX_UCDR_PI_CONTROLS 0x44 +#define QSERDES_V7_RX_UCDR_SB2_THRESH1 0x4c +#define QSERDES_V7_RX_UCDR_SB2_THRESH2 0x50 +#define QSERDES_V7_RX_UCDR_SB2_GAIN1 0x54 +#define QSERDES_V7_RX_UCDR_SB2_GAIN2 0x58 +#define QSERDES_V7_RX_AUX_DATA_TCOARSE_TFINE 0x60 +#define QSERDES_V7_RX_TX_ADAPT_POST_THRESH 0xcc +#define QSERDES_V7_RX_VGA_CAL_CNTRL1 0xd4 +#define QSERDES_V7_RX_VGA_CAL_CNTRL2 0xd8 +#define QSERDES_V7_RX_GM_CAL 0xdc +#define QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL2 0xec +#define QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL3 0xf0 +#define QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL4 0xf4 +#define QSERDES_V7_RX_RX_IDAC_TSETTLE_LOW 0xf8 +#define QSERDES_V7_RX_RX_IDAC_TSETTLE_HIGH 0xfc +#define QSERDES_V7_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1 0x110 +#define QSERDES_V7_RX_SIDGET_ENABLES 0x118 +#define QSERDES_V7_RX_SIGDET_CNTRL 0x11c +#define QSERDES_V7_RX_SIGDET_DEGLITCH_CNTRL 0x124 +#define QSERDES_V7_RX_RX_MODE_00_LOW 0x15c +#define QSERDES_V7_RX_RX_MODE_00_HIGH 0x160 +#define QSERDES_V7_RX_RX_MODE_00_HIGH2 0x164 +#define QSERDES_V7_RX_RX_MODE_00_HIGH3 0x168 +#define QSERDES_V7_RX_RX_MODE_00_HIGH4 0x16c +#define QSERDES_V7_RX_RX_MODE_01_LOW 0x170 +#define QSERDES_V7_RX_RX_MODE_01_HIGH 0x174 +#define QSERDES_V7_RX_RX_MODE_01_HIGH2 0x178 +#define QSERDES_V7_RX_RX_MODE_01_HIGH3 0x17c +#define QSERDES_V7_RX_RX_MODE_01_HIGH4 0x180 +#define QSERDES_V7_RX_RX_MODE_10_LOW 0x184 +#define QSERDES_V7_RX_RX_MODE_10_HIGH 0x188 +#define QSERDES_V7_RX_RX_MODE_10_HIGH2 0x18c +#define QSERDES_V7_RX_RX_MODE_10_HIGH3 0x190 +#define QSERDES_V7_RX_RX_MODE_10_HIGH4 0x194 +#define QSERDES_V7_RX_DFE_EN_TIMER 0x1a0 +#define QSERDES_V7_RX_DFE_CTLE_POST_CAL_OFFSET 0x1a4 +#define QSERDES_V7_RX_DCC_CTRL1 0x1a8 +#define QSERDES_V7_RX_VTH_CODE 0x1b0 +#define QSERDES_V7_RX_SIGDET_CAL_CTRL1 0x1e4 +#define QSERDES_V7_RX_SIGDET_CAL_TRIM 0x1f8 + +#endif diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c index 514fa14df634..3c2e6255e26f 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c @@ -763,22 +763,26 @@ static const struct qmp_phy_init_tbl sm8550_ufsphy_serdes[] = { QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x14), QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x7f), QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x06), - QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x4c), - QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x0a), - QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x18), - QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x14), - QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x99), - QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x4c), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x18), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x99), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x07), +}; + +static const struct qmp_phy_init_tbl sm8550_ufsphy_hs_b_serdes[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x44), }; static const struct qmp_phy_init_tbl sm8550_ufsphy_tx[] = { - QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_1, 0x05), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_TX_LANE_MODE_1, 0x05), QMP_PHY_INIT_CFG(QSERDES_UFS_V6_TX_RES_CODE_LANE_OFFSET_TX, 0x07), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_TX_FR_DCC_CTRL, 0x4c), }; static const struct qmp_phy_init_tbl sm8550_ufsphy_rx[] = { - QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_FASTLOCK_FO_GAIN_RATE2, 0x0c), - QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_FASTLOCK_FO_GAIN_RATE4, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_FO_GAIN_RATE2, 0x0c), QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_VGA_CAL_MAN_VAL, 0x0e), QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE_0_1_B0, 0xc2), @@ -801,6 +805,69 @@ static const struct qmp_phy_init_tbl sm8550_ufsphy_pcs[] = { QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_MID_TERM_CTRL1, 0x43), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PLL_CNTL, 0x2b), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_MULTI_LANE_CTRL1, 0x02), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_HSGEAR_CAPABILITY, 0x04), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_HSGEAR_CAPABILITY, 0x04), +}; + +static const struct qmp_phy_init_tbl sm8650_ufsphy_serdes[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0xd9), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x11), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_HS_SWITCH_SEL_1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x44), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_INITVAL2, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x41), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x18), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x7f), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x4c), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x18), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x99), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x07), +}; + +static const struct qmp_phy_init_tbl sm8650_ufsphy_tx[] = { + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_TX_LANE_MODE_1, 0x05), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_TX_RES_CODE_LANE_OFFSET_TX, 0x07), +}; + +static const struct qmp_phy_init_tbl sm8650_ufsphy_rx[] = { + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_FO_GAIN_RATE2, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_FO_GAIN_RATE4, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_VGA_CAL_MAN_VAL, 0x0e), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE_0_1_B0, 0xc2), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE_0_1_B1, 0xc2), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE_0_1_B3, 0x1a), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE_0_1_B6, 0x60), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE2_B3, 0x9e), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE2_B6, 0x60), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE3_B3, 0x9e), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE3_B4, 0x0e), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE3_B5, 0x36), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE3_B8, 0x02), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE4_B3, 0xb9), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE4_B6, 0xff), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_SO_SATURATION, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_PI_CTRL1, 0x94), + QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_RX_TERM_BW_CTRL0, 0xfa), +}; + +static const struct qmp_phy_init_tbl sm8650_ufsphy_pcs[] = { + QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_MULTI_LANE_CTRL1, 0x00), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_MID_TERM_CTRL1, 0x43), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PCS_CTRL1, 0xc1), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PLL_CNTL, 0x33), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_HSGEAR_CAPABILITY, 0x04), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_HSGEAR_CAPABILITY, 0x04), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_LARGE_AMP_DRV_LVL, 0x0f), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_SIGDET_CTRL2, 0x69), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_MULTI_LANE_CTRL1, 0x02), }; struct qmp_ufs_offsets { @@ -1296,6 +1363,32 @@ static const struct qmp_phy_cfg sm8550_ufsphy_cfg = { .pcs = sm8550_ufsphy_pcs, .pcs_num = ARRAY_SIZE(sm8550_ufsphy_pcs), }, + .tbls_hs_b = { + .serdes = sm8550_ufsphy_hs_b_serdes, + .serdes_num = ARRAY_SIZE(sm8550_ufsphy_hs_b_serdes), + }, + .clk_list = sdm845_ufs_phy_clk_l, + .num_clks = ARRAY_SIZE(sdm845_ufs_phy_clk_l), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), + .regs = ufsphy_v6_regs_layout, +}; + +static const struct qmp_phy_cfg sm8650_ufsphy_cfg = { + .lanes = 2, + + .offsets = &qmp_ufs_offsets_v6, + + .tbls = { + .serdes = sm8650_ufsphy_serdes, + .serdes_num = ARRAY_SIZE(sm8650_ufsphy_serdes), + .tx = sm8650_ufsphy_tx, + .tx_num = ARRAY_SIZE(sm8650_ufsphy_tx), + .rx = sm8650_ufsphy_rx, + .rx_num = ARRAY_SIZE(sm8650_ufsphy_rx), + .pcs = sm8650_ufsphy_pcs, + .pcs_num = ARRAY_SIZE(sm8650_ufsphy_pcs), + }, .clk_list = sdm845_ufs_phy_clk_l, .num_clks = ARRAY_SIZE(sdm845_ufs_phy_clk_l), .vreg_list = qmp_phy_vreg_l, @@ -1826,6 +1919,9 @@ static const struct of_device_id qmp_ufs_of_match_table[] = { }, { .compatible = "qcom,sm8550-qmp-ufs-phy", .data = &sm8550_ufsphy_cfg, + }, { + .compatible = "qcom,sm8650-qmp-ufs-phy", + .data = &sm8650_ufsphy_cfg, }, { }, }; diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c index 02f156298e77..243cc2b9a0fb 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c @@ -24,6 +24,8 @@ #include "phy-qcom-qmp-pcs-misc-v4.h" #include "phy-qcom-qmp-pcs-usb-v4.h" #include "phy-qcom-qmp-pcs-usb-v5.h" +#include "phy-qcom-qmp-pcs-usb-v6.h" +#include "phy-qcom-qmp-pcs-usb-v7.h" /* QPHY_SW_RESET bit */ #define SW_RESET BIT(0) @@ -151,6 +153,28 @@ static const unsigned int qmp_v5_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR] = QPHY_V5_PCS_USB3_LFPS_RXTERM_IRQ_CLEAR, }; +static const unsigned int qmp_v6_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { + [QPHY_SW_RESET] = QPHY_V6_PCS_SW_RESET, + [QPHY_START_CTRL] = QPHY_V6_PCS_START_CONTROL, + [QPHY_PCS_STATUS] = QPHY_V6_PCS_PCS_STATUS1, + [QPHY_PCS_POWER_DOWN_CONTROL] = QPHY_V6_PCS_POWER_DOWN_CONTROL, + + /* In PCS_USB */ + [QPHY_PCS_AUTONOMOUS_MODE_CTRL] = QPHY_V6_PCS_USB3_AUTONOMOUS_MODE_CTRL, + [QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR] = QPHY_V6_PCS_USB3_LFPS_RXTERM_IRQ_CLEAR, +}; + +static const unsigned int qmp_v7_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { + [QPHY_SW_RESET] = QPHY_V7_PCS_SW_RESET, + [QPHY_START_CTRL] = QPHY_V7_PCS_START_CONTROL, + [QPHY_PCS_STATUS] = QPHY_V7_PCS_PCS_STATUS1, + [QPHY_PCS_POWER_DOWN_CONTROL] = QPHY_V7_PCS_POWER_DOWN_CONTROL, + + /* In PCS_USB */ + [QPHY_PCS_AUTONOMOUS_MODE_CTRL] = QPHY_V7_PCS_USB3_AUTONOMOUS_MODE_CTRL, + [QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR] = QPHY_V7_PCS_USB3_LFPS_RXTERM_IRQ_CLEAR, +}; + static const struct qmp_phy_init_tbl ipq9574_usb3_serdes_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_COM_SYSCLK_EN_SEL, 0x1a), QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CLKBUFLR_EN, 0x08), @@ -871,6 +895,134 @@ static const struct qmp_phy_init_tbl sdx65_usb3_uniphy_rx_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V5_RX_SIGDET_ENABLES, 0x00), }; +static const struct qmp_phy_init_tbl sdx75_usb3_uniphy_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE1, 0x9e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE1, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x2e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x82), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x82), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE1, 0xab), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE1, 0xea), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE1, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE1, 0x25), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE1, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE1, 0xb7), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE1, 0x1e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0xb7), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x1e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0x9e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x12), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x82), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE0, 0xab), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE0, 0xea), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE0, 0x25), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE0, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x0e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x31), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_BUF_ENABLE, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x1a), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_CFG, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0x20), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_1, 0xb6), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_2, 0x4b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_3, 0x37), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_ADDITIONAL_MISC, 0x0c), +}; + +static const struct qmp_phy_init_tbl sdx75_usb3_uniphy_tx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_TX_RES_CODE_LANE_TX, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_TX_RES_CODE_LANE_RX, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_TX_RES_CODE_LANE_OFFSET_TX, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_V6_TX_RES_CODE_LANE_OFFSET_RX, 0x09), + QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_1, 0xf5), + QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_3, 0x3f), + QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_4, 0x3f), + QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_5, 0x5f), + QMP_PHY_INIT_CFG(QSERDES_V6_TX_RCV_DETECT_LVL_2, 0x12), + QMP_PHY_INIT_CFG(QSERDES_V6_TX_PI_QEC_CTRL, 0x21), +}; + +static const struct qmp_phy_init_tbl sdx75_usb3_uniphy_rx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_FO_GAIN, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SO_GAIN, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_FASTLOCK_FO_GAIN, 0x2f), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x7f), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_FASTLOCK_COUNT_LOW, 0xff), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_FASTLOCK_COUNT_HIGH, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_PI_CONTROLS, 0x99), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SB2_THRESH1, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SB2_THRESH2, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SB2_GAIN1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SB2_GAIN2, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_AUX_DATA_TCOARSE_TFINE, 0xa0), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_VGA_CAL_CNTRL1, 0x54), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_VGA_CAL_CNTRL2, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_GM_CAL, 0x13), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_EQU_ADAPTOR_CNTRL3, 0x4a), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_EQU_ADAPTOR_CNTRL4, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_IDAC_TSETTLE_LOW, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_IDAC_TSETTLE_HIGH, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1, 0x47), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_SIGDET_CNTRL, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_SIGDET_DEGLITCH_CNTRL, 0x0e), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_LOW, 0x3f), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_HIGH, 0xbf), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_HIGH2, 0xff), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_HIGH3, 0xdf), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_HIGH4, 0xed), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_LOW, 0xdc), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_HIGH, 0x5c), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_HIGH2, 0x9c), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_HIGH3, 0x1d), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_HIGH4, 0x09), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_DFE_EN_TIMER, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_DCC_CTRL1, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_VTH_CODE, 0x10), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_SIGDET_CAL_CTRL1, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_RX_SIGDET_CAL_TRIM, 0x08), +}; + +static const struct qmp_phy_init_tbl sdx75_usb3_uniphy_pcs_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG1, 0xc4), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG2, 0x89), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG3, 0x20), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG6, 0x13), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_REFGEN_REQ_CONFIG1, 0x21), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_RX_SIGDET_LVL, 0xaa), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_CDR_RESET_TIME, 0x0a), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_ALIGN_DETECT_CONFIG1, 0x88), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_ALIGN_DETECT_CONFIG2, 0x13), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_PCS_TX_RX_CONFIG, 0x0c), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG1, 0x4b), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG5, 0x10), +}; + +static const struct qmp_phy_init_tbl sdx75_usb3_uniphy_pcs_usb_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL, 0xf8), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_RCVR_DTCT_DLY_U3_L, 0x40), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_RCVR_DTCT_DLY_U3_H, 0x00), +}; + static const struct qmp_phy_init_tbl sm8350_usb3_uniphy_tx_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V5_TX_LANE_MODE_1, 0xa5), QMP_PHY_INIT_CFG(QSERDES_V5_TX_LANE_MODE_2, 0x82), @@ -1161,6 +1313,134 @@ static const struct qmp_phy_init_tbl sa8775p_usb3_uniphy_pcs_usb_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_POWER_STATE_CONFIG1, 0x6f), }; +static const struct qmp_phy_init_tbl x1e80100_usb3_uniphy_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_STEP_SIZE1_MODE1, 0xc0), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_STEP_SIZE2_MODE1, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_CP_CTRL_MODE1, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_PLL_RCTRL_MODE1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_PLL_CCTRL_MODE1, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_CORECLK_DIV_MODE1, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_LOCK_CMP1_MODE1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_LOCK_CMP2_MODE1, 0x41), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_DEC_START_MODE1, 0x41), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START1_MODE1, 0x55), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START2_MODE1, 0x75), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START3_MODE1, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_HSCLK_SEL_1, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_VCO_TUNE1_MODE1, 0x25), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_VCO_TUNE2_MODE1, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE1_MODE1, 0x5c), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE2_MODE1, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0x5c), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_STEP_SIZE1_MODE0, 0xc0), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_STEP_SIZE2_MODE0, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_CP_CTRL_MODE0, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_PLL_RCTRL_MODE0, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_PLL_CCTRL_MODE0, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_LOCK_CMP1_MODE0, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_LOCK_CMP2_MODE0, 0x1a), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_DEC_START_MODE0, 0x41), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START1_MODE0, 0x55), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START2_MODE0, 0x75), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START3_MODE0, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_VCO_TUNE1_MODE0, 0x25), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_VCO_TUNE2_MODE0, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_BG_TIMER, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_PER1, 0x62), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_PER2, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_SYSCLK_BUF_ENABLE, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_SYSCLK_EN_SEL, 0x1a), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_LOCK_CMP_CFG, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_VCO_TUNE_MAP, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_CORE_CLK_EN, 0x20), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_CMN_CONFIG_1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_1, 0xb6), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_2, 0x4b), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_3, 0x37), + QMP_PHY_INIT_CFG(QSERDES_V7_COM_ADDITIONAL_MISC, 0x0c), +}; + +static const struct qmp_phy_init_tbl x1e80100_usb3_uniphy_tx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V7_TX_RES_CODE_LANE_TX, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V7_TX_RES_CODE_LANE_RX, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V7_TX_RES_CODE_LANE_OFFSET_TX, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_V7_TX_RES_CODE_LANE_OFFSET_RX, 0x09), + QMP_PHY_INIT_CFG(QSERDES_V7_TX_LANE_MODE_1, 0xf5), + QMP_PHY_INIT_CFG(QSERDES_V7_TX_LANE_MODE_3, 0x3f), + QMP_PHY_INIT_CFG(QSERDES_V7_TX_LANE_MODE_4, 0x3f), + QMP_PHY_INIT_CFG(QSERDES_V7_TX_LANE_MODE_5, 0x5f), + QMP_PHY_INIT_CFG(QSERDES_V7_TX_RCV_DETECT_LVL_2, 0x12), + QMP_PHY_INIT_CFG(QSERDES_V7_TX_PI_QEC_CTRL, 0x21), +}; + +static const struct qmp_phy_init_tbl x1e80100_usb3_uniphy_rx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_FO_GAIN, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SO_GAIN, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_FASTLOCK_FO_GAIN, 0x2f), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x7f), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_FASTLOCK_COUNT_LOW, 0xff), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_FASTLOCK_COUNT_HIGH, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_PI_CONTROLS, 0x99), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SB2_THRESH1, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SB2_THRESH2, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SB2_GAIN1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SB2_GAIN2, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_AUX_DATA_TCOARSE_TFINE, 0xa0), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_VGA_CAL_CNTRL1, 0x54), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_VGA_CAL_CNTRL2, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_GM_CAL, 0x13), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL3, 0x4a), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL4, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_IDAC_TSETTLE_LOW, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_IDAC_TSETTLE_HIGH, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1, 0x47), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_SIGDET_CNTRL, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_SIGDET_DEGLITCH_CNTRL, 0x0e), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_00_LOW, 0x3f), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_00_HIGH, 0xbf), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_00_HIGH2, 0xff), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_00_HIGH3, 0xdf), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_00_HIGH4, 0xed), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_01_LOW, 0xdc), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_01_HIGH, 0x5c), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_01_HIGH2, 0x9c), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_01_HIGH3, 0x1d), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_01_HIGH4, 0x09), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_DFE_EN_TIMER, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_DCC_CTRL1, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_VTH_CODE, 0x10), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_SIGDET_CAL_CTRL1, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V7_RX_SIGDET_CAL_TRIM, 0x08), +}; + +static const struct qmp_phy_init_tbl x1e80100_usb3_uniphy_pcs_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V7_PCS_LOCK_DETECT_CONFIG1, 0xc4), + QMP_PHY_INIT_CFG(QPHY_V7_PCS_LOCK_DETECT_CONFIG2, 0x89), + QMP_PHY_INIT_CFG(QPHY_V7_PCS_LOCK_DETECT_CONFIG3, 0x20), + QMP_PHY_INIT_CFG(QPHY_V7_PCS_LOCK_DETECT_CONFIG6, 0x13), + QMP_PHY_INIT_CFG(QPHY_V7_PCS_REFGEN_REQ_CONFIG1, 0x21), + QMP_PHY_INIT_CFG(QPHY_V7_PCS_RX_SIGDET_LVL, 0xaa), + QMP_PHY_INIT_CFG(QPHY_V7_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7), + QMP_PHY_INIT_CFG(QPHY_V7_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03), + QMP_PHY_INIT_CFG(QPHY_V7_PCS_CDR_RESET_TIME, 0x0a), + QMP_PHY_INIT_CFG(QPHY_V7_PCS_ALIGN_DETECT_CONFIG1, 0x88), + QMP_PHY_INIT_CFG(QPHY_V7_PCS_ALIGN_DETECT_CONFIG2, 0x13), + QMP_PHY_INIT_CFG(QPHY_V7_PCS_PCS_TX_RX_CONFIG, 0x0c), + QMP_PHY_INIT_CFG(QPHY_V7_PCS_EQ_CONFIG1, 0x4b), + QMP_PHY_INIT_CFG(QPHY_V7_PCS_EQ_CONFIG5, 0x10), +}; + +static const struct qmp_phy_init_tbl x1e80100_usb3_uniphy_pcs_usb_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V7_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL, 0xf8), + QMP_PHY_INIT_CFG(QPHY_V7_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07), + QMP_PHY_INIT_CFG(QPHY_V7_PCS_USB3_RCVR_DTCT_DLY_U3_L, 0x40), + QMP_PHY_INIT_CFG(QPHY_V7_PCS_USB3_RCVR_DTCT_DLY_U3_H, 0x00), +}; + struct qmp_usb_offsets { u16 serdes; u16 pcs; @@ -1317,6 +1597,22 @@ static const struct qmp_usb_offsets qmp_usb_offsets_v5 = { .rx = 0x1000, }; +static const struct qmp_usb_offsets qmp_usb_offsets_v6 = { + .serdes = 0, + .pcs = 0x0200, + .pcs_usb = 0x1200, + .tx = 0x0e00, + .rx = 0x1000, +}; + +static const struct qmp_usb_offsets qmp_usb_offsets_v7 = { + .serdes = 0, + .pcs = 0x0200, + .pcs_usb = 0x1200, + .tx = 0x0e00, + .rx = 0x1000, +}; + static const struct qmp_phy_cfg ipq8074_usb3phy_cfg = { .lanes = 1, @@ -1541,6 +1837,28 @@ static const struct qmp_phy_cfg sdx65_usb3_uniphy_cfg = { .has_pwrdn_delay = true, }; +static const struct qmp_phy_cfg sdx75_usb3_uniphy_cfg = { + .lanes = 1, + .offsets = &qmp_usb_offsets_v6, + + .serdes_tbl = sdx75_usb3_uniphy_serdes_tbl, + .serdes_tbl_num = ARRAY_SIZE(sdx75_usb3_uniphy_serdes_tbl), + .tx_tbl = sdx75_usb3_uniphy_tx_tbl, + .tx_tbl_num = ARRAY_SIZE(sdx75_usb3_uniphy_tx_tbl), + .rx_tbl = sdx75_usb3_uniphy_rx_tbl, + .rx_tbl_num = ARRAY_SIZE(sdx75_usb3_uniphy_rx_tbl), + .pcs_tbl = sdx75_usb3_uniphy_pcs_tbl, + .pcs_tbl_num = ARRAY_SIZE(sdx75_usb3_uniphy_pcs_tbl), + .pcs_usb_tbl = sdx75_usb3_uniphy_pcs_usb_tbl, + .pcs_usb_tbl_num = ARRAY_SIZE(sdx75_usb3_uniphy_pcs_usb_tbl), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), + .regs = qmp_v6_usb3phy_regs_layout, + .pcs_usb_offset = 0x1000, + + .has_pwrdn_delay = true, +}; + static const struct qmp_phy_cfg sm8350_usb3_uniphy_cfg = { .lanes = 1, @@ -1582,6 +1900,26 @@ static const struct qmp_phy_cfg qcm2290_usb3phy_cfg = { .regs = qmp_v3_usb3phy_regs_layout_qcm2290, }; +static const struct qmp_phy_cfg x1e80100_usb3_uniphy_cfg = { + .lanes = 1, + + .offsets = &qmp_usb_offsets_v7, + + .serdes_tbl = x1e80100_usb3_uniphy_serdes_tbl, + .serdes_tbl_num = ARRAY_SIZE(x1e80100_usb3_uniphy_serdes_tbl), + .tx_tbl = x1e80100_usb3_uniphy_tx_tbl, + .tx_tbl_num = ARRAY_SIZE(x1e80100_usb3_uniphy_tx_tbl), + .rx_tbl = x1e80100_usb3_uniphy_rx_tbl, + .rx_tbl_num = ARRAY_SIZE(x1e80100_usb3_uniphy_rx_tbl), + .pcs_tbl = x1e80100_usb3_uniphy_pcs_tbl, + .pcs_tbl_num = ARRAY_SIZE(x1e80100_usb3_uniphy_pcs_tbl), + .pcs_usb_tbl = x1e80100_usb3_uniphy_pcs_usb_tbl, + .pcs_usb_tbl_num = ARRAY_SIZE(x1e80100_usb3_uniphy_pcs_usb_tbl), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), + .regs = qmp_v7_usb3phy_regs_layout, +}; + static void qmp_usb_configure_lane(void __iomem *base, const struct qmp_phy_init_tbl tbl[], int num, @@ -2257,6 +2595,9 @@ static const struct of_device_id qmp_usb_of_match_table[] = { .compatible = "qcom,sdx65-qmp-usb3-uni-phy", .data = &sdx65_usb3_uniphy_cfg, }, { + .compatible = "qcom,sdx75-qmp-usb3-uni-phy", + .data = &sdx75_usb3_uniphy_cfg, + }, { .compatible = "qcom,sm6115-qmp-usb3-phy", .data = &qcm2290_usb3phy_cfg, }, { @@ -2268,6 +2609,9 @@ static const struct of_device_id qmp_usb_of_match_table[] = { }, { .compatible = "qcom,sm8350-qmp-usb3-uni-phy", .data = &sm8350_usb3_uniphy_cfg, + }, { + .compatible = "qcom,x1e80100-qmp-usb3-uni-phy", + .data = &x1e80100_usb3_uniphy_cfg, }, { }, }; diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.h b/drivers/phy/qualcomm/phy-qcom-qmp.h index 71f063f4a56e..6923496cbfee 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp.h @@ -24,8 +24,12 @@ #include "phy-qcom-qmp-qserdes-com-v6.h" #include "phy-qcom-qmp-qserdes-txrx-v6.h" #include "phy-qcom-qmp-qserdes-txrx-v6_20.h" +#include "phy-qcom-qmp-qserdes-txrx-v6_n4.h" #include "phy-qcom-qmp-qserdes-ln-shrd-v6.h" +#include "phy-qcom-qmp-qserdes-com-v7.h" +#include "phy-qcom-qmp-qserdes-txrx-v7.h" + #include "phy-qcom-qmp-qserdes-pll.h" #include "phy-qcom-qmp-pcs-v2.h" @@ -44,6 +48,8 @@ #include "phy-qcom-qmp-pcs-v6_20.h" +#include "phy-qcom-qmp-pcs-v7.h" + /* Only for QMP V3 & V4 PHY - DP COM registers */ #define QPHY_V3_DP_COM_PHY_MODE_CTRL 0x00 #define QPHY_V3_DP_COM_SW_RESET 0x04 diff --git a/drivers/phy/renesas/Kconfig b/drivers/phy/renesas/Kconfig index 36505fc5f386..e342eef0640b 100644 --- a/drivers/phy/renesas/Kconfig +++ b/drivers/phy/renesas/Kconfig @@ -13,7 +13,7 @@ config PHY_R8A779F0_ETHERNET_SERDES config PHY_RCAR_GEN2 tristate "Renesas R-Car generation 2 USB PHY driver" depends on ARCH_RENESAS - depends on GENERIC_PHY + select GENERIC_PHY help Support for USB PHY found on Renesas R-Car generation 2 SoCs. diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c index a24d2af154df..4f71373ae6e1 100644 --- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c +++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c @@ -123,9 +123,12 @@ struct rockchip_chg_det_reg { * @disrise_en: host disconnect rise edge detection enable. * @disrise_st: host disconnect rise edge detection state. * @disrise_clr: host disconnect rise edge detection clear. - * @id_det_en: id detection enable register. - * @id_det_st: id detection state register. - * @id_det_clr: id detection clear register. + * @idfall_det_en: id detection enable register, falling edge + * @idfall_det_st: id detection state register, falling edge + * @idfall_det_clr: id detection clear register, falling edge + * @idrise_det_en: id detection enable register, rising edge + * @idrise_det_st: id detection state register, rising edge + * @idrise_det_clr: id detection clear register, rising edge * @ls_det_en: linestate detection enable register. * @ls_det_st: linestate detection state register. * @ls_det_clr: linestate detection clear register. @@ -146,9 +149,12 @@ struct rockchip_usb2phy_port_cfg { struct usb2phy_reg disrise_en; struct usb2phy_reg disrise_st; struct usb2phy_reg disrise_clr; - struct usb2phy_reg id_det_en; - struct usb2phy_reg id_det_st; - struct usb2phy_reg id_det_clr; + struct usb2phy_reg idfall_det_en; + struct usb2phy_reg idfall_det_st; + struct usb2phy_reg idfall_det_clr; + struct usb2phy_reg idrise_det_en; + struct usb2phy_reg idrise_det_st; + struct usb2phy_reg idrise_det_clr; struct usb2phy_reg ls_det_en; struct usb2phy_reg ls_det_st; struct usb2phy_reg ls_det_clr; @@ -488,15 +494,27 @@ static int rockchip_usb2phy_init(struct phy *phy) if (ret) goto out; - /* clear id status and enable id detect irq */ + /* clear id status and enable id detect irqs */ ret = property_enable(rphy->grf, - &rport->port_cfg->id_det_clr, + &rport->port_cfg->idfall_det_clr, true); if (ret) goto out; ret = property_enable(rphy->grf, - &rport->port_cfg->id_det_en, + &rport->port_cfg->idrise_det_clr, + true); + if (ret) + goto out; + + ret = property_enable(rphy->grf, + &rport->port_cfg->idfall_det_en, + true); + if (ret) + goto out; + + ret = property_enable(rphy->grf, + &rport->port_cfg->idrise_det_en, true); if (ret) goto out; @@ -1030,11 +1048,16 @@ static irqreturn_t rockchip_usb2phy_id_irq(int irq, void *data) struct rockchip_usb2phy *rphy = dev_get_drvdata(rport->phy->dev.parent); bool id; - if (!property_enabled(rphy->grf, &rport->port_cfg->id_det_st)) + if (!property_enabled(rphy->grf, &rport->port_cfg->idfall_det_st) && + !property_enabled(rphy->grf, &rport->port_cfg->idrise_det_st)) return IRQ_NONE; /* clear id detect irq pending status */ - property_enable(rphy->grf, &rport->port_cfg->id_det_clr, true); + if (property_enabled(rphy->grf, &rport->port_cfg->idfall_det_st)) + property_enable(rphy->grf, &rport->port_cfg->idfall_det_clr, true); + + if (property_enabled(rphy->grf, &rport->port_cfg->idrise_det_st)) + property_enable(rphy->grf, &rport->port_cfg->idrise_det_clr, true); id = property_enabled(rphy->grf, &rport->port_cfg->utmi_id); extcon_set_state_sync(rphy->edev, EXTCON_USB_HOST, !id); @@ -1464,6 +1487,14 @@ put_child: return ret; } +static int rk3128_usb2phy_tuning(struct rockchip_usb2phy *rphy) +{ + /* Turn off differential receiver in suspend mode */ + return regmap_write_bits(rphy->grf, 0x298, + BIT(2) << BIT_WRITEABLE_SHIFT | BIT(2), + BIT(2) << BIT_WRITEABLE_SHIFT | 0); +} + static int rk3588_usb2phy_tuning(struct rockchip_usb2phy *rphy) { int ret; @@ -1513,6 +1544,54 @@ static int rk3588_usb2phy_tuning(struct rockchip_usb2phy *rphy) return ret; } +static const struct rockchip_usb2phy_cfg rk3128_phy_cfgs[] = { + { + .reg = 0x17c, + .num_ports = 2, + .phy_tuning = rk3128_usb2phy_tuning, + .clkout_ctl = { 0x0190, 15, 15, 1, 0 }, + .port_cfgs = { + [USB2PHY_PORT_OTG] = { + .phy_sus = { 0x017c, 8, 0, 0, 0x1d1 }, + .bvalid_det_en = { 0x017c, 14, 14, 0, 1 }, + .bvalid_det_st = { 0x017c, 15, 15, 0, 1 }, + .bvalid_det_clr = { 0x017c, 15, 15, 0, 1 }, + .idfall_det_en = { 0x01a0, 2, 2, 0, 1 }, + .idfall_det_st = { 0x01a0, 3, 3, 0, 1 }, + .idfall_det_clr = { 0x01a0, 3, 3, 0, 1 }, + .idrise_det_en = { 0x01a0, 0, 0, 0, 1 }, + .idrise_det_st = { 0x01a0, 1, 1, 0, 1 }, + .idrise_det_clr = { 0x01a0, 1, 1, 0, 1 }, + .ls_det_en = { 0x017c, 12, 12, 0, 1 }, + .ls_det_st = { 0x017c, 13, 13, 0, 1 }, + .ls_det_clr = { 0x017c, 13, 13, 0, 1 }, + .utmi_bvalid = { 0x014c, 5, 5, 0, 1 }, + .utmi_id = { 0x014c, 8, 8, 0, 1 }, + .utmi_ls = { 0x014c, 7, 6, 0, 1 }, + }, + [USB2PHY_PORT_HOST] = { + .phy_sus = { 0x0194, 8, 0, 0, 0x1d1 }, + .ls_det_en = { 0x0194, 14, 14, 0, 1 }, + .ls_det_st = { 0x0194, 15, 15, 0, 1 }, + .ls_det_clr = { 0x0194, 15, 15, 0, 1 } + } + }, + .chg_det = { + .opmode = { 0x017c, 3, 0, 5, 1 }, + .cp_det = { 0x02c0, 6, 6, 0, 1 }, + .dcp_det = { 0x02c0, 5, 5, 0, 1 }, + .dp_det = { 0x02c0, 7, 7, 0, 1 }, + .idm_sink_en = { 0x0184, 8, 8, 0, 1 }, + .idp_sink_en = { 0x0184, 7, 7, 0, 1 }, + .idp_src_en = { 0x0184, 9, 9, 0, 1 }, + .rdm_pdwn_en = { 0x0184, 10, 10, 0, 1 }, + .vdm_src_en = { 0x0184, 12, 12, 0, 1 }, + .vdp_src_en = { 0x0184, 11, 11, 0, 1 }, + }, + }, + { /* sentinel */ } +}; + static const struct rockchip_usb2phy_cfg rk3228_phy_cfgs[] = { { .reg = 0x760, @@ -1524,9 +1603,12 @@ static const struct rockchip_usb2phy_cfg rk3228_phy_cfgs[] = { .bvalid_det_en = { 0x0680, 3, 3, 0, 1 }, .bvalid_det_st = { 0x0690, 3, 3, 0, 1 }, .bvalid_det_clr = { 0x06a0, 3, 3, 0, 1 }, - .id_det_en = { 0x0680, 6, 5, 0, 3 }, - .id_det_st = { 0x0690, 6, 5, 0, 3 }, - .id_det_clr = { 0x06a0, 6, 5, 0, 3 }, + .idfall_det_en = { 0x0680, 6, 6, 0, 1 }, + .idfall_det_st = { 0x0690, 6, 6, 0, 1 }, + .idfall_det_clr = { 0x06a0, 6, 6, 0, 1 }, + .idrise_det_en = { 0x0680, 5, 5, 0, 1 }, + .idrise_det_st = { 0x0690, 5, 5, 0, 1 }, + .idrise_det_clr = { 0x06a0, 5, 5, 0, 1 }, .ls_det_en = { 0x0680, 2, 2, 0, 1 }, .ls_det_st = { 0x0690, 2, 2, 0, 1 }, .ls_det_clr = { 0x06a0, 2, 2, 0, 1 }, @@ -1587,9 +1669,12 @@ static const struct rockchip_usb2phy_cfg rk3308_phy_cfgs[] = { .bvalid_det_en = { 0x3020, 3, 2, 0, 3 }, .bvalid_det_st = { 0x3024, 3, 2, 0, 3 }, .bvalid_det_clr = { 0x3028, 3, 2, 0, 3 }, - .id_det_en = { 0x3020, 5, 4, 0, 3 }, - .id_det_st = { 0x3024, 5, 4, 0, 3 }, - .id_det_clr = { 0x3028, 5, 4, 0, 3 }, + .idfall_det_en = { 0x3020, 5, 5, 0, 1 }, + .idfall_det_st = { 0x3024, 5, 5, 0, 1 }, + .idfall_det_clr = { 0x3028, 5, 5, 0, 1 }, + .idrise_det_en = { 0x3020, 4, 4, 0, 1 }, + .idrise_det_st = { 0x3024, 4, 4, 0, 1 }, + .idrise_det_clr = { 0x3028, 4, 4, 0, 1 }, .ls_det_en = { 0x3020, 0, 0, 0, 1 }, .ls_det_st = { 0x3024, 0, 0, 0, 1 }, .ls_det_clr = { 0x3028, 0, 0, 0, 1 }, @@ -1634,9 +1719,12 @@ static const struct rockchip_usb2phy_cfg rk3328_phy_cfgs[] = { .bvalid_det_en = { 0x0110, 3, 2, 0, 3 }, .bvalid_det_st = { 0x0114, 3, 2, 0, 3 }, .bvalid_det_clr = { 0x0118, 3, 2, 0, 3 }, - .id_det_en = { 0x0110, 5, 4, 0, 3 }, - .id_det_st = { 0x0114, 5, 4, 0, 3 }, - .id_det_clr = { 0x0118, 5, 4, 0, 3 }, + .idfall_det_en = { 0x0110, 5, 5, 0, 1 }, + .idfall_det_st = { 0x0114, 5, 5, 0, 1 }, + .idfall_det_clr = { 0x0118, 5, 5, 0, 1 }, + .idrise_det_en = { 0x0110, 4, 4, 0, 1 }, + .idrise_det_st = { 0x0114, 4, 4, 0, 1 }, + .idrise_det_clr = { 0x0118, 4, 4, 0, 1 }, .ls_det_en = { 0x0110, 0, 0, 0, 1 }, .ls_det_st = { 0x0114, 0, 0, 0, 1 }, .ls_det_clr = { 0x0118, 0, 0, 0, 1 }, @@ -1700,9 +1788,12 @@ static const struct rockchip_usb2phy_cfg rk3399_phy_cfgs[] = { .bvalid_det_en = { 0xe3c0, 3, 3, 0, 1 }, .bvalid_det_st = { 0xe3e0, 3, 3, 0, 1 }, .bvalid_det_clr = { 0xe3d0, 3, 3, 0, 1 }, - .id_det_en = { 0xe3c0, 5, 4, 0, 3 }, - .id_det_st = { 0xe3e0, 5, 4, 0, 3 }, - .id_det_clr = { 0xe3d0, 5, 4, 0, 3 }, + .idfall_det_en = { 0xe3c0, 5, 5, 0, 1 }, + .idfall_det_st = { 0xe3e0, 5, 5, 0, 1 }, + .idfall_det_clr = { 0xe3d0, 5, 5, 0, 1 }, + .idrise_det_en = { 0xe3c0, 4, 4, 0, 1 }, + .idrise_det_st = { 0xe3e0, 4, 4, 0, 1 }, + .idrise_det_clr = { 0xe3d0, 4, 4, 0, 1 }, .utmi_avalid = { 0xe2ac, 7, 7, 0, 1 }, .utmi_bvalid = { 0xe2ac, 12, 12, 0, 1 }, .utmi_id = { 0xe2ac, 8, 8, 0, 1 }, @@ -1739,9 +1830,12 @@ static const struct rockchip_usb2phy_cfg rk3399_phy_cfgs[] = { .bvalid_det_en = { 0xe3c0, 8, 8, 0, 1 }, .bvalid_det_st = { 0xe3e0, 8, 8, 0, 1 }, .bvalid_det_clr = { 0xe3d0, 8, 8, 0, 1 }, - .id_det_en = { 0xe3c0, 10, 9, 0, 3 }, - .id_det_st = { 0xe3e0, 10, 9, 0, 3 }, - .id_det_clr = { 0xe3d0, 10, 9, 0, 3 }, + .idfall_det_en = { 0xe3c0, 10, 10, 0, 1 }, + .idfall_det_st = { 0xe3e0, 10, 10, 0, 1 }, + .idfall_det_clr = { 0xe3d0, 10, 10, 0, 1 }, + .idrise_det_en = { 0xe3c0, 9, 9, 0, 1 }, + .idrise_det_st = { 0xe3e0, 9, 9, 0, 1 }, + .idrise_det_clr = { 0xe3d0, 9, 9, 0, 1 }, .utmi_avalid = { 0xe2ac, 10, 10, 0, 1 }, .utmi_bvalid = { 0xe2ac, 16, 16, 0, 1 }, .utmi_id = { 0xe2ac, 11, 11, 0, 1 }, @@ -1770,9 +1864,12 @@ static const struct rockchip_usb2phy_cfg rk3568_phy_cfgs[] = { .bvalid_det_en = { 0x0080, 3, 2, 0, 3 }, .bvalid_det_st = { 0x0084, 3, 2, 0, 3 }, .bvalid_det_clr = { 0x0088, 3, 2, 0, 3 }, - .id_det_en = { 0x0080, 5, 4, 0, 3 }, - .id_det_st = { 0x0084, 5, 4, 0, 3 }, - .id_det_clr = { 0x0088, 5, 4, 0, 3 }, + .idfall_det_en = { 0x0080, 5, 5, 0, 1 }, + .idfall_det_st = { 0x0084, 5, 5, 0, 1 }, + .idfall_det_clr = { 0x0088, 5, 5, 0, 1 }, + .idrise_det_en = { 0x0080, 4, 4, 0, 1 }, + .idrise_det_st = { 0x0084, 4, 4, 0, 1 }, + .idrise_det_clr = { 0x0088, 4, 4, 0, 1 }, .utmi_avalid = { 0x00c0, 10, 10, 0, 1 }, .utmi_bvalid = { 0x00c0, 9, 9, 0, 1 }, .utmi_id = { 0x00c0, 6, 6, 0, 1 }, @@ -1990,6 +2087,7 @@ static const struct rockchip_usb2phy_cfg rv1108_phy_cfgs[] = { static const struct of_device_id rockchip_usb2phy_dt_match[] = { { .compatible = "rockchip,px30-usb2phy", .data = &rk3328_phy_cfgs }, + { .compatible = "rockchip,rk3128-usb2phy", .data = &rk3128_phy_cfgs }, { .compatible = "rockchip,rk3228-usb2phy", .data = &rk3228_phy_cfgs }, { .compatible = "rockchip,rk3308-usb2phy", .data = &rk3308_phy_cfgs }, { .compatible = "rockchip,rk3328-usb2phy", .data = &rk3328_phy_cfgs }, diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c index bc847d3879f7..0f4818adb440 100644 --- a/drivers/phy/ti/phy-gmii-sel.c +++ b/drivers/phy/ti/phy-gmii-sel.c @@ -248,7 +248,7 @@ static const struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw9g_soc_j784s4 = { .use_of_data = true, .regfields = phy_gmii_sel_fields_am654, - .extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | + .extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_SGMII) | BIT(PHY_INTERFACE_MODE_USXGMII), .num_ports = 8, .num_qsgmii_main_ports = 2, diff --git a/drivers/phy/ti/phy-j721e-wiz.c b/drivers/phy/ti/phy-j721e-wiz.c index fc3cd98c60ff..00d7e6a6de03 100644 --- a/drivers/phy/ti/phy-j721e-wiz.c +++ b/drivers/phy/ti/phy-j721e-wiz.c @@ -1240,6 +1240,7 @@ static int wiz_phy_fullrt_div(struct wiz *wiz, int lane) case J721E_WIZ_10G: case J7200_WIZ_10G: case J721S2_WIZ_10G: + case J784S4_WIZ_10G: if (wiz->lane_phy_type[lane] == PHY_TYPE_SGMII) return regmap_field_write(wiz->p0_fullrt_div[lane], 0x2); break; diff --git a/drivers/power/reset/as3722-poweroff.c b/drivers/power/reset/as3722-poweroff.c index 829e0dba2fda..ab3350ce2d62 100644 --- a/drivers/power/reset/as3722-poweroff.c +++ b/drivers/power/reset/as3722-poweroff.c @@ -61,13 +61,11 @@ static int as3722_poweroff_probe(struct platform_device *pdev) return 0; } -static int as3722_poweroff_remove(struct platform_device *pdev) +static void as3722_poweroff_remove(struct platform_device *pdev) { if (pm_power_off == as3722_pm_power_off) pm_power_off = NULL; as3722_pm_poweroff = NULL; - - return 0; } static struct platform_driver as3722_poweroff_driver = { @@ -75,7 +73,7 @@ static struct platform_driver as3722_poweroff_driver = { .name = "as3722-power-off", }, .probe = as3722_poweroff_probe, - .remove = as3722_poweroff_remove, + .remove_new = as3722_poweroff_remove, }; module_platform_driver(as3722_poweroff_driver); diff --git a/drivers/power/reset/at91-poweroff.c b/drivers/power/reset/at91-poweroff.c index dd5399785b69..93eece027865 100644 --- a/drivers/power/reset/at91-poweroff.c +++ b/drivers/power/reset/at91-poweroff.c @@ -57,7 +57,7 @@ static struct shdwc { void __iomem *mpddrc_base; } at91_shdwc; -static void __init at91_wakeup_status(struct platform_device *pdev) +static void at91_wakeup_status(struct platform_device *pdev) { const char *reason; u32 reg = readl(at91_shdwc.shdwc_base + AT91_SHDW_SR); @@ -149,7 +149,7 @@ static void at91_poweroff_dt_set_wakeup_mode(struct platform_device *pdev) writel(wakeup_mode | mode, at91_shdwc.shdwc_base + AT91_SHDW_MR); } -static int __init at91_poweroff_probe(struct platform_device *pdev) +static int at91_poweroff_probe(struct platform_device *pdev) { struct device_node *np; u32 ddr_type; @@ -202,7 +202,7 @@ clk_disable: return ret; } -static int __exit at91_poweroff_remove(struct platform_device *pdev) +static void at91_poweroff_remove(struct platform_device *pdev) { if (pm_power_off == at91_poweroff) pm_power_off = NULL; @@ -211,8 +211,6 @@ static int __exit at91_poweroff_remove(struct platform_device *pdev) iounmap(at91_shdwc.mpddrc_base); clk_disable_unprepare(at91_shdwc.sclk); - - return 0; } static const struct of_device_id at91_poweroff_of_match[] = { @@ -224,13 +222,14 @@ static const struct of_device_id at91_poweroff_of_match[] = { MODULE_DEVICE_TABLE(of, at91_poweroff_of_match); static struct platform_driver at91_poweroff_driver = { - .remove = __exit_p(at91_poweroff_remove), + .probe = at91_poweroff_probe, + .remove_new = at91_poweroff_remove, .driver = { .name = "at91-poweroff", .of_match_table = at91_poweroff_of_match, }, }; -module_platform_driver_probe(at91_poweroff_driver, at91_poweroff_probe); +module_platform_driver(at91_poweroff_driver); MODULE_AUTHOR("Atmel Corporation"); MODULE_DESCRIPTION("Shutdown driver for Atmel SoCs"); diff --git a/drivers/power/reset/at91-reset.c b/drivers/power/reset/at91-reset.c index aa9b012d3d00..16512654295f 100644 --- a/drivers/power/reset/at91-reset.c +++ b/drivers/power/reset/at91-reset.c @@ -337,7 +337,7 @@ static int at91_rcdev_init(struct at91_reset *reset, return devm_reset_controller_register(&pdev->dev, &reset->rcdev); } -static int __init at91_reset_probe(struct platform_device *pdev) +static int at91_reset_probe(struct platform_device *pdev) { const struct of_device_id *match; struct at91_reset *reset; @@ -417,24 +417,23 @@ disable_clk: return ret; } -static int __exit at91_reset_remove(struct platform_device *pdev) +static void at91_reset_remove(struct platform_device *pdev) { struct at91_reset *reset = platform_get_drvdata(pdev); unregister_restart_handler(&reset->nb); clk_disable_unprepare(reset->sclk); - - return 0; } static struct platform_driver at91_reset_driver = { - .remove = __exit_p(at91_reset_remove), + .probe = at91_reset_probe, + .remove_new = at91_reset_remove, .driver = { .name = "at91-reset", .of_match_table = at91_reset_of_match, }, }; -module_platform_driver_probe(at91_reset_driver, at91_reset_probe); +module_platform_driver(at91_reset_driver); MODULE_AUTHOR("Atmel Corporation"); MODULE_DESCRIPTION("Reset driver for Atmel SoCs"); diff --git a/drivers/power/reset/at91-sama5d2_shdwc.c b/drivers/power/reset/at91-sama5d2_shdwc.c index e76b102b57b1..959ce0dbe91d 100644 --- a/drivers/power/reset/at91-sama5d2_shdwc.c +++ b/drivers/power/reset/at91-sama5d2_shdwc.c @@ -107,7 +107,7 @@ static const unsigned long long sdwc_dbc_period[] = { 0, 3, 32, 512, 4096, 32768, }; -static void __init at91_wakeup_status(struct platform_device *pdev) +static void at91_wakeup_status(struct platform_device *pdev) { struct shdwc *shdw = platform_get_drvdata(pdev); const struct reg_config *rcfg = shdw->rcfg; @@ -329,7 +329,7 @@ static const struct of_device_id at91_pmc_ids[] = { { /* Sentinel. */ } }; -static int __init at91_shdwc_probe(struct platform_device *pdev) +static int at91_shdwc_probe(struct platform_device *pdev) { const struct of_device_id *match; struct device_node *np; @@ -421,7 +421,7 @@ clk_disable: return ret; } -static int __exit at91_shdwc_remove(struct platform_device *pdev) +static void at91_shdwc_remove(struct platform_device *pdev) { struct shdwc *shdw = platform_get_drvdata(pdev); @@ -437,18 +437,17 @@ static int __exit at91_shdwc_remove(struct platform_device *pdev) iounmap(shdw->pmc_base); clk_disable_unprepare(shdw->sclk); - - return 0; } static struct platform_driver at91_shdwc_driver = { - .remove = __exit_p(at91_shdwc_remove), + .probe = at91_shdwc_probe, + .remove_new = at91_shdwc_remove, .driver = { .name = "at91-shdwc", .of_match_table = at91_shdwc_of_match, }, }; -module_platform_driver_probe(at91_shdwc_driver, at91_shdwc_probe); +module_platform_driver(at91_shdwc_driver); MODULE_AUTHOR("Nicolas Ferre <nicolas.ferre@atmel.com>"); MODULE_DESCRIPTION("Atmel shutdown controller driver"); diff --git a/drivers/power/reset/atc260x-poweroff.c b/drivers/power/reset/atc260x-poweroff.c index 98f20251a6d1..b4aa50e9685e 100644 --- a/drivers/power/reset/atc260x-poweroff.c +++ b/drivers/power/reset/atc260x-poweroff.c @@ -233,7 +233,7 @@ static int atc260x_pwrc_probe(struct platform_device *pdev) return ret; } -static int atc260x_pwrc_remove(struct platform_device *pdev) +static void atc260x_pwrc_remove(struct platform_device *pdev) { struct atc260x_pwrc *priv = platform_get_drvdata(pdev); @@ -243,13 +243,11 @@ static int atc260x_pwrc_remove(struct platform_device *pdev) } unregister_restart_handler(&priv->restart_nb); - - return 0; } static struct platform_driver atc260x_pwrc_driver = { .probe = atc260x_pwrc_probe, - .remove = atc260x_pwrc_remove, + .remove_new = atc260x_pwrc_remove, .driver = { .name = "atc260x-pwrc", }, diff --git a/drivers/power/reset/gpio-restart.c b/drivers/power/reset/gpio-restart.c index 3aa19765772d..d1e177176fa1 100644 --- a/drivers/power/reset/gpio-restart.c +++ b/drivers/power/reset/gpio-restart.c @@ -17,17 +17,14 @@ struct gpio_restart { struct gpio_desc *reset_gpio; - struct notifier_block restart_handler; u32 active_delay_ms; u32 inactive_delay_ms; u32 wait_delay_ms; }; -static int gpio_restart_notify(struct notifier_block *this, - unsigned long mode, void *cmd) +static int gpio_restart_notify(struct sys_off_data *data) { - struct gpio_restart *gpio_restart = - container_of(this, struct gpio_restart, restart_handler); + struct gpio_restart *gpio_restart = data->cb_data; /* drive it active, also inactive->active edge */ gpiod_direction_output(gpio_restart->reset_gpio, 1); @@ -52,6 +49,7 @@ static int gpio_restart_probe(struct platform_device *pdev) { struct gpio_restart *gpio_restart; bool open_source = false; + int priority = 129; u32 property; int ret; @@ -71,8 +69,6 @@ static int gpio_restart_probe(struct platform_device *pdev) return ret; } - gpio_restart->restart_handler.notifier_call = gpio_restart_notify; - gpio_restart->restart_handler.priority = 129; gpio_restart->active_delay_ms = 100; gpio_restart->inactive_delay_ms = 100; gpio_restart->wait_delay_ms = 3000; @@ -83,7 +79,7 @@ static int gpio_restart_probe(struct platform_device *pdev) dev_err(&pdev->dev, "Invalid priority property: %u\n", property); else - gpio_restart->restart_handler.priority = property; + priority = property; } of_property_read_u32(pdev->dev.of_node, "active-delay", @@ -93,9 +89,11 @@ static int gpio_restart_probe(struct platform_device *pdev) of_property_read_u32(pdev->dev.of_node, "wait-delay", &gpio_restart->wait_delay_ms); - platform_set_drvdata(pdev, gpio_restart); - - ret = register_restart_handler(&gpio_restart->restart_handler); + ret = devm_register_sys_off_handler(&pdev->dev, + SYS_OFF_MODE_RESTART, + priority, + gpio_restart_notify, + gpio_restart); if (ret) { dev_err(&pdev->dev, "%s: cannot register restart handler, %d\n", __func__, ret); @@ -105,19 +103,6 @@ static int gpio_restart_probe(struct platform_device *pdev) return 0; } -static void gpio_restart_remove(struct platform_device *pdev) -{ - struct gpio_restart *gpio_restart = platform_get_drvdata(pdev); - int ret; - - ret = unregister_restart_handler(&gpio_restart->restart_handler); - if (ret) { - dev_err(&pdev->dev, - "%s: cannot unregister restart handler, %d\n", - __func__, ret); - } -} - static const struct of_device_id of_gpio_restart_match[] = { { .compatible = "gpio-restart", }, {}, @@ -125,7 +110,6 @@ static const struct of_device_id of_gpio_restart_match[] = { static struct platform_driver gpio_restart_driver = { .probe = gpio_restart_probe, - .remove_new = gpio_restart_remove, .driver = { .name = "restart-gpio", .of_match_table = of_gpio_restart_match, diff --git a/drivers/power/reset/ltc2952-poweroff.c b/drivers/power/reset/ltc2952-poweroff.c index eea05921a054..fa25fbd53934 100644 --- a/drivers/power/reset/ltc2952-poweroff.c +++ b/drivers/power/reset/ltc2952-poweroff.c @@ -286,7 +286,7 @@ static int ltc2952_poweroff_probe(struct platform_device *pdev) return 0; } -static int ltc2952_poweroff_remove(struct platform_device *pdev) +static void ltc2952_poweroff_remove(struct platform_device *pdev) { struct ltc2952_poweroff *data = platform_get_drvdata(pdev); @@ -295,7 +295,6 @@ static int ltc2952_poweroff_remove(struct platform_device *pdev) hrtimer_cancel(&data->timer_wde); atomic_notifier_chain_unregister(&panic_notifier_list, &data->panic_notifier); - return 0; } static const struct of_device_id of_ltc2952_poweroff_match[] = { @@ -306,7 +305,7 @@ MODULE_DEVICE_TABLE(of, of_ltc2952_poweroff_match); static struct platform_driver ltc2952_poweroff_driver = { .probe = ltc2952_poweroff_probe, - .remove = ltc2952_poweroff_remove, + .remove_new = ltc2952_poweroff_remove, .driver = { .name = "ltc2952-poweroff", .of_match_table = of_ltc2952_poweroff_match, diff --git a/drivers/power/reset/mt6323-poweroff.c b/drivers/power/reset/mt6323-poweroff.c index 108167f7738b..57a63c0ab7fb 100644 --- a/drivers/power/reset/mt6323-poweroff.c +++ b/drivers/power/reset/mt6323-poweroff.c @@ -70,12 +70,10 @@ static int mt6323_pwrc_probe(struct platform_device *pdev) return 0; } -static int mt6323_pwrc_remove(struct platform_device *pdev) +static void mt6323_pwrc_remove(struct platform_device *pdev) { if (pm_power_off == &mt6323_do_pwroff) pm_power_off = NULL; - - return 0; } static const struct of_device_id mt6323_pwrc_dt_match[] = { @@ -86,7 +84,7 @@ MODULE_DEVICE_TABLE(of, mt6323_pwrc_dt_match); static struct platform_driver mt6323_pwrc_driver = { .probe = mt6323_pwrc_probe, - .remove = mt6323_pwrc_remove, + .remove_new = mt6323_pwrc_remove, .driver = { .name = "mt6323-pwrc", .of_match_table = mt6323_pwrc_dt_match, diff --git a/drivers/power/reset/pwr-mlxbf.c b/drivers/power/reset/pwr-mlxbf.c index de35d24bb7ef..1775b318d0ef 100644 --- a/drivers/power/reset/pwr-mlxbf.c +++ b/drivers/power/reset/pwr-mlxbf.c @@ -17,11 +17,17 @@ #include <linux/types.h> struct pwr_mlxbf { - struct work_struct send_work; + struct work_struct reboot_work; + struct work_struct shutdown_work; const char *hid; }; -static void pwr_mlxbf_send_work(struct work_struct *work) +static void pwr_mlxbf_reboot_work(struct work_struct *work) +{ + acpi_bus_generate_netlink_event("button/reboot.*", "Reboot Button", 0x80, 1); +} + +static void pwr_mlxbf_shutdown_work(struct work_struct *work) { acpi_bus_generate_netlink_event("button/power.*", "Power Button", 0x80, 1); } @@ -33,10 +39,10 @@ static irqreturn_t pwr_mlxbf_irq(int irq, void *ptr) struct pwr_mlxbf *priv = ptr; if (!strncmp(priv->hid, rst_pwr_hid, 8)) - emergency_restart(); + schedule_work(&priv->reboot_work); if (!strncmp(priv->hid, low_pwr_hid, 8)) - schedule_work(&priv->send_work); + schedule_work(&priv->shutdown_work); return IRQ_HANDLED; } @@ -64,7 +70,11 @@ static int pwr_mlxbf_probe(struct platform_device *pdev) if (irq < 0) return dev_err_probe(dev, irq, "Error getting %s irq.\n", priv->hid); - err = devm_work_autocancel(dev, &priv->send_work, pwr_mlxbf_send_work); + err = devm_work_autocancel(dev, &priv->shutdown_work, pwr_mlxbf_shutdown_work); + if (err) + return err; + + err = devm_work_autocancel(dev, &priv->reboot_work, pwr_mlxbf_reboot_work); if (err) return err; diff --git a/drivers/power/reset/qnap-poweroff.c b/drivers/power/reset/qnap-poweroff.c index 0ddf7f25f7b8..e0f2ff6b147c 100644 --- a/drivers/power/reset/qnap-poweroff.c +++ b/drivers/power/reset/qnap-poweroff.c @@ -111,15 +111,14 @@ static int qnap_power_off_probe(struct platform_device *pdev) return 0; } -static int qnap_power_off_remove(struct platform_device *pdev) +static void qnap_power_off_remove(struct platform_device *pdev) { pm_power_off = NULL; - return 0; } static struct platform_driver qnap_power_off_driver = { .probe = qnap_power_off_probe, - .remove = qnap_power_off_remove, + .remove_new = qnap_power_off_remove, .driver = { .name = "qnap_power_off", .of_match_table = of_match_ptr(qnap_power_off_of_match_table), diff --git a/drivers/power/reset/regulator-poweroff.c b/drivers/power/reset/regulator-poweroff.c index 7f87fbb8b051..15160809c423 100644 --- a/drivers/power/reset/regulator-poweroff.c +++ b/drivers/power/reset/regulator-poweroff.c @@ -52,12 +52,10 @@ static int regulator_poweroff_probe(struct platform_device *pdev) return 0; } -static int regulator_poweroff_remove(__maybe_unused struct platform_device *pdev) +static void regulator_poweroff_remove(struct platform_device *pdev) { if (pm_power_off == ®ulator_poweroff_do_poweroff) pm_power_off = NULL; - - return 0; } static const struct of_device_id of_regulator_poweroff_match[] = { @@ -68,7 +66,7 @@ MODULE_DEVICE_TABLE(of, of_regulator_poweroff_match); static struct platform_driver regulator_poweroff_driver = { .probe = regulator_poweroff_probe, - .remove = regulator_poweroff_remove, + .remove_new = regulator_poweroff_remove, .driver = { .name = "poweroff-regulator", .of_match_table = of_regulator_poweroff_match, diff --git a/drivers/power/reset/restart-poweroff.c b/drivers/power/reset/restart-poweroff.c index 28f1822db162..f4d6004793d3 100644 --- a/drivers/power/reset/restart-poweroff.c +++ b/drivers/power/reset/restart-poweroff.c @@ -33,12 +33,10 @@ static int restart_poweroff_probe(struct platform_device *pdev) return 0; } -static int restart_poweroff_remove(struct platform_device *pdev) +static void restart_poweroff_remove(struct platform_device *pdev) { if (pm_power_off == &restart_poweroff_do_poweroff) pm_power_off = NULL; - - return 0; } static const struct of_device_id of_restart_poweroff_match[] = { @@ -49,7 +47,7 @@ MODULE_DEVICE_TABLE(of, of_restart_poweroff_match); static struct platform_driver restart_poweroff_driver = { .probe = restart_poweroff_probe, - .remove = restart_poweroff_remove, + .remove_new = restart_poweroff_remove, .driver = { .name = "poweroff-restart", .of_match_table = of_restart_poweroff_match, diff --git a/drivers/power/reset/rmobile-reset.c b/drivers/power/reset/rmobile-reset.c index bd3b396558e0..5df9b41c68c7 100644 --- a/drivers/power/reset/rmobile-reset.c +++ b/drivers/power/reset/rmobile-reset.c @@ -59,11 +59,10 @@ fail_unmap: return error; } -static int rmobile_reset_remove(struct platform_device *pdev) +static void rmobile_reset_remove(struct platform_device *pdev) { unregister_restart_handler(&rmobile_reset_nb); iounmap(sysc_base2); - return 0; } static const struct of_device_id rmobile_reset_of_match[] = { @@ -74,7 +73,7 @@ MODULE_DEVICE_TABLE(of, rmobile_reset_of_match); static struct platform_driver rmobile_reset_driver = { .probe = rmobile_reset_probe, - .remove = rmobile_reset_remove, + .remove_new = rmobile_reset_remove, .driver = { .name = "rmobile_reset", .of_match_table = rmobile_reset_of_match, diff --git a/drivers/power/reset/syscon-poweroff.c b/drivers/power/reset/syscon-poweroff.c index c3aab7f59345..1b2ce7734260 100644 --- a/drivers/power/reset/syscon-poweroff.c +++ b/drivers/power/reset/syscon-poweroff.c @@ -76,12 +76,10 @@ static int syscon_poweroff_probe(struct platform_device *pdev) return 0; } -static int syscon_poweroff_remove(struct platform_device *pdev) +static void syscon_poweroff_remove(struct platform_device *pdev) { if (pm_power_off == syscon_poweroff) pm_power_off = NULL; - - return 0; } static const struct of_device_id syscon_poweroff_of_match[] = { @@ -91,7 +89,7 @@ static const struct of_device_id syscon_poweroff_of_match[] = { static struct platform_driver syscon_poweroff_driver = { .probe = syscon_poweroff_probe, - .remove = syscon_poweroff_remove, + .remove_new = syscon_poweroff_remove, .driver = { .name = "syscon-poweroff", .of_match_table = syscon_poweroff_of_match, diff --git a/drivers/power/reset/tps65086-restart.c b/drivers/power/reset/tps65086-restart.c index 5ec819eac7da..ee8e9f4b837e 100644 --- a/drivers/power/reset/tps65086-restart.c +++ b/drivers/power/reset/tps65086-restart.c @@ -62,19 +62,21 @@ static int tps65086_restart_probe(struct platform_device *pdev) return 0; } -static int tps65086_restart_remove(struct platform_device *pdev) +static void tps65086_restart_remove(struct platform_device *pdev) { struct tps65086_restart *tps65086_restart = platform_get_drvdata(pdev); int ret; ret = unregister_restart_handler(&tps65086_restart->handler); if (ret) { + /* + * tps65086_restart_probe() registered the restart handler. So + * unregistering should work fine. Checking the error code + * shouldn't be needed, still doing it for completeness. + */ dev_err(&pdev->dev, "%s: cannot unregister restart handler: %d\n", __func__, ret); - return -ENODEV; } - - return 0; } static const struct platform_device_id tps65086_restart_id_table[] = { @@ -88,7 +90,7 @@ static struct platform_driver tps65086_restart_driver = { .name = "tps65086-restart", }, .probe = tps65086_restart_probe, - .remove = tps65086_restart_remove, + .remove_new = tps65086_restart_remove, .id_table = tps65086_restart_id_table, }; module_platform_driver(tps65086_restart_driver); diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c index 1db290ee2591..2b393eb5c282 100644 --- a/drivers/power/supply/bq24190_charger.c +++ b/drivers/power/supply/bq24190_charger.c @@ -36,10 +36,16 @@ #define BQ24190_REG_POC_WDT_RESET_SHIFT 6 #define BQ24190_REG_POC_CHG_CONFIG_MASK (BIT(5) | BIT(4)) #define BQ24190_REG_POC_CHG_CONFIG_SHIFT 4 -#define BQ24190_REG_POC_CHG_CONFIG_DISABLE 0x0 -#define BQ24190_REG_POC_CHG_CONFIG_CHARGE 0x1 -#define BQ24190_REG_POC_CHG_CONFIG_OTG 0x2 -#define BQ24190_REG_POC_CHG_CONFIG_OTG_ALT 0x3 +#define BQ24190_REG_POC_CHG_CONFIG_DISABLE 0x0 +#define BQ24190_REG_POC_CHG_CONFIG_CHARGE 0x1 +#define BQ24190_REG_POC_CHG_CONFIG_OTG 0x2 +#define BQ24190_REG_POC_CHG_CONFIG_OTG_ALT 0x3 +#define BQ24296_REG_POC_OTG_CONFIG_MASK BIT(5) +#define BQ24296_REG_POC_OTG_CONFIG_SHIFT 5 +#define BQ24296_REG_POC_CHG_CONFIG_MASK BIT(4) +#define BQ24296_REG_POC_CHG_CONFIG_SHIFT 4 +#define BQ24296_REG_POC_OTG_CONFIG_DISABLE 0x0 +#define BQ24296_REG_POC_OTG_CONFIG_OTG 0x1 #define BQ24190_REG_POC_SYS_MIN_MASK (BIT(3) | BIT(2) | BIT(1)) #define BQ24190_REG_POC_SYS_MIN_SHIFT 1 #define BQ24190_REG_POC_SYS_MIN_MIN 3000 @@ -134,59 +140,24 @@ #define BQ24190_REG_F_BAT_FAULT_SHIFT 3 #define BQ24190_REG_F_NTC_FAULT_MASK (BIT(2) | BIT(1) | BIT(0)) #define BQ24190_REG_F_NTC_FAULT_SHIFT 0 +#define BQ24296_REG_F_NTC_FAULT_MASK (BIT(1) | BIT(0)) +#define BQ24296_REG_F_NTC_FAULT_SHIFT 0 #define BQ24190_REG_VPRS 0x0A /* Vendor/Part/Revision Status */ #define BQ24190_REG_VPRS_PN_MASK (BIT(5) | BIT(4) | BIT(3)) #define BQ24190_REG_VPRS_PN_SHIFT 3 -#define BQ24190_REG_VPRS_PN_24190 0x4 -#define BQ24190_REG_VPRS_PN_24192 0x5 /* Also 24193, 24196 */ -#define BQ24190_REG_VPRS_PN_24192I 0x3 +#define BQ24190_REG_VPRS_PN_24190 0x4 +#define BQ24190_REG_VPRS_PN_24192 0x5 /* Also 24193, 24196 */ +#define BQ24190_REG_VPRS_PN_24192I 0x3 +#define BQ24296_REG_VPRS_PN_MASK (BIT(7) | BIT(6) | BIT(5)) +#define BQ24296_REG_VPRS_PN_SHIFT 5 +#define BQ24296_REG_VPRS_PN_24296 0x1 #define BQ24190_REG_VPRS_TS_PROFILE_MASK BIT(2) #define BQ24190_REG_VPRS_TS_PROFILE_SHIFT 2 #define BQ24190_REG_VPRS_DEV_REG_MASK (BIT(1) | BIT(0)) #define BQ24190_REG_VPRS_DEV_REG_SHIFT 0 /* - * The FAULT register is latched by the bq24190 (except for NTC_FAULT) - * so the first read after a fault returns the latched value and subsequent - * reads return the current value. In order to return the fault status - * to the user, have the interrupt handler save the reg's value and retrieve - * it in the appropriate health/status routine. - */ -struct bq24190_dev_info { - struct i2c_client *client; - struct device *dev; - struct extcon_dev *edev; - struct power_supply *charger; - struct power_supply *battery; - struct delayed_work input_current_limit_work; - char model_name[I2C_NAME_SIZE]; - bool initialized; - bool irq_event; - bool otg_vbus_enabled; - int charge_type; - u16 sys_min; - u16 iprechg; - u16 iterm; - u32 ichg; - u32 ichg_max; - u32 vreg; - u32 vreg_max; - struct mutex f_reg_lock; - u8 f_reg; - u8 ss_reg; - u8 watchdog; -}; - -static int bq24190_charger_set_charge_type(struct bq24190_dev_info *bdi, - const union power_supply_propval *val); - -static const unsigned int bq24190_usb_extcon_cable[] = { - EXTCON_USB, - EXTCON_NONE, -}; - -/* * The tables below provide a 2-way mapping for the value that goes in * the register field and the real-world value that it represents. * The index of the array is the value that goes in the register; the @@ -211,6 +182,9 @@ static const int bq24190_ccc_ichg_values[] = { 4096000, 4160000, 4224000, 4288000, 4352000, 4416000, 4480000, 4544000 }; +/* ICHG higher than 3008mA is not supported in BQ24296 */ +#define BQ24296_CCC_ICHG_VALUES_LEN 40 + /* REG04[7:2] (VREG) in uV */ static const int bq24190_cvc_vreg_values[] = { 3504000, 3520000, 3536000, 3552000, 3568000, 3584000, 3600000, 3616000, @@ -228,6 +202,68 @@ static const int bq24190_ictrc_treg_values[] = { 600, 800, 1000, 1200 }; +enum bq24190_chip { + BQ24190, + BQ24192, + BQ24192i, + BQ24196, + BQ24296, +}; + +/* + * The FAULT register is latched by the bq24190 (except for NTC_FAULT) + * so the first read after a fault returns the latched value and subsequent + * reads return the current value. In order to return the fault status + * to the user, have the interrupt handler save the reg's value and retrieve + * it in the appropriate health/status routine. + */ +struct bq24190_dev_info { + struct i2c_client *client; + struct device *dev; + struct extcon_dev *edev; + struct power_supply *charger; + struct power_supply *battery; + struct delayed_work input_current_limit_work; + char model_name[I2C_NAME_SIZE]; + bool initialized; + bool irq_event; + bool otg_vbus_enabled; + int charge_type; + u16 sys_min; + u16 iprechg; + u16 iterm; + u32 ichg; + u32 ichg_max; + u32 vreg; + u32 vreg_max; + struct mutex f_reg_lock; + u8 f_reg; + u8 ss_reg; + u8 watchdog; + const struct bq24190_chip_info *info; +}; + +struct bq24190_chip_info { + int ichg_array_size; +#ifdef CONFIG_REGULATOR + const struct regulator_desc *vbus_desc; +#endif + int (*check_chip)(struct bq24190_dev_info *bdi); + int (*set_chg_config)(struct bq24190_dev_info *bdi, const u8 chg_config); + int (*set_otg_vbus)(struct bq24190_dev_info *bdi, bool enable); + u8 ntc_fault_mask; + int (*get_ntc_status)(const u8 value); +}; + +static int bq24190_charger_set_charge_type(struct bq24190_dev_info *bdi, + const union power_supply_propval *val); + +static const unsigned int bq24190_usb_extcon_cable[] = { + EXTCON_USB, + EXTCON_NONE, +}; + + /* * Return the index in 'tbl' of greatest value that is less than or equal to * 'val'. The index range returned is 0 to 'tbl_size' - 1. Assumes that @@ -529,6 +565,43 @@ static int bq24190_set_otg_vbus(struct bq24190_dev_info *bdi, bool enable) return ret; } +static int bq24296_set_otg_vbus(struct bq24190_dev_info *bdi, bool enable) +{ + int ret; + + ret = pm_runtime_resume_and_get(bdi->dev); + if (ret < 0) { + dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", ret); + return ret; + } + + bdi->otg_vbus_enabled = enable; + if (enable) { + ret = bq24190_write_mask(bdi, BQ24190_REG_POC, + BQ24296_REG_POC_CHG_CONFIG_MASK, + BQ24296_REG_POC_CHG_CONFIG_SHIFT, + BQ24190_REG_POC_CHG_CONFIG_DISABLE); + + if (ret < 0) + goto out; + + ret = bq24190_write_mask(bdi, BQ24190_REG_POC, + BQ24296_REG_POC_OTG_CONFIG_MASK, + BQ24296_REG_POC_CHG_CONFIG_SHIFT, + BQ24296_REG_POC_OTG_CONFIG_OTG); + } else + ret = bq24190_write_mask(bdi, BQ24190_REG_POC, + BQ24296_REG_POC_OTG_CONFIG_MASK, + BQ24296_REG_POC_CHG_CONFIG_SHIFT, + BQ24296_REG_POC_OTG_CONFIG_DISABLE); + +out: + pm_runtime_mark_last_busy(bdi->dev); + pm_runtime_put_autosuspend(bdi->dev); + + return ret; +} + #ifdef CONFIG_REGULATOR static int bq24190_vbus_enable(struct regulator_dev *dev) { @@ -567,6 +640,43 @@ static int bq24190_vbus_is_enabled(struct regulator_dev *dev) return bdi->otg_vbus_enabled; } +static int bq24296_vbus_enable(struct regulator_dev *dev) +{ + return bq24296_set_otg_vbus(rdev_get_drvdata(dev), true); +} + +static int bq24296_vbus_disable(struct regulator_dev *dev) +{ + return bq24296_set_otg_vbus(rdev_get_drvdata(dev), false); +} + +static int bq24296_vbus_is_enabled(struct regulator_dev *dev) +{ + struct bq24190_dev_info *bdi = rdev_get_drvdata(dev); + int ret; + u8 val; + + ret = pm_runtime_resume_and_get(bdi->dev); + if (ret < 0) { + dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", ret); + return ret; + } + + ret = bq24190_read_mask(bdi, BQ24190_REG_POC, + BQ24296_REG_POC_OTG_CONFIG_MASK, + BQ24296_REG_POC_OTG_CONFIG_SHIFT, &val); + + pm_runtime_mark_last_busy(bdi->dev); + pm_runtime_put_autosuspend(bdi->dev); + + if (ret) + return ret; + + bdi->otg_vbus_enabled = (val == BQ24296_REG_POC_OTG_CONFIG_OTG); + + return bdi->otg_vbus_enabled; +} + static const struct regulator_ops bq24190_vbus_ops = { .enable = bq24190_vbus_enable, .disable = bq24190_vbus_disable, @@ -583,6 +693,22 @@ static const struct regulator_desc bq24190_vbus_desc = { .n_voltages = 1, }; +static const struct regulator_ops bq24296_vbus_ops = { + .enable = bq24296_vbus_enable, + .disable = bq24296_vbus_disable, + .is_enabled = bq24296_vbus_is_enabled, +}; + +static const struct regulator_desc bq24296_vbus_desc = { + .name = "usb_otg_vbus", + .of_match = "usb-otg-vbus", + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .ops = &bq24296_vbus_ops, + .fixed_uV = 5000000, + .n_voltages = 1, +}; + static const struct regulator_init_data bq24190_vbus_init_data = { .constraints = { .valid_ops_mask = REGULATOR_CHANGE_STATUS, @@ -602,7 +728,7 @@ static int bq24190_register_vbus_regulator(struct bq24190_dev_info *bdi) else cfg.init_data = &bq24190_vbus_init_data; cfg.driver_data = bdi; - reg = devm_regulator_register(bdi->dev, &bq24190_vbus_desc, &cfg); + reg = devm_regulator_register(bdi->dev, bdi->info->vbus_desc, &cfg); if (IS_ERR(reg)) { ret = PTR_ERR(reg); dev_err(bdi->dev, "Can't register regulator: %d\n", ret); @@ -678,7 +804,7 @@ static int bq24190_set_config(struct bq24190_dev_info *bdi) BQ24190_REG_CCC_ICHG_MASK, BQ24190_REG_CCC_ICHG_SHIFT, bq24190_ccc_ichg_values, - ARRAY_SIZE(bq24190_ccc_ichg_values), + bdi->info->ichg_array_size, bdi->ichg); if (ret < 0) return ret; @@ -777,6 +903,24 @@ static int bq24190_charger_get_charge_type(struct bq24190_dev_info *bdi, return 0; } +static int bq24190_battery_set_chg_config(struct bq24190_dev_info *bdi, + const u8 chg_config) +{ + return bq24190_write_mask(bdi, BQ24190_REG_POC, + BQ24190_REG_POC_CHG_CONFIG_MASK, + BQ24190_REG_POC_CHG_CONFIG_SHIFT, + chg_config); +} + +static int bq24296_battery_set_chg_config(struct bq24190_dev_info *bdi, + const u8 chg_config) +{ + return bq24190_write_mask(bdi, BQ24190_REG_POC, + BQ24296_REG_POC_CHG_CONFIG_MASK, + BQ24296_REG_POC_CHG_CONFIG_SHIFT, + chg_config); +} + static int bq24190_charger_set_charge_type(struct bq24190_dev_info *bdi, const union power_supply_propval *val) { @@ -835,9 +979,50 @@ static int bq24190_charger_set_charge_type(struct bq24190_dev_info *bdi, return ret; } - return bq24190_write_mask(bdi, BQ24190_REG_POC, - BQ24190_REG_POC_CHG_CONFIG_MASK, - BQ24190_REG_POC_CHG_CONFIG_SHIFT, chg_config); + return bdi->info->set_chg_config(bdi, chg_config); +} + +static int bq24190_charger_get_ntc_status(u8 value) +{ + int health; + + switch (value >> BQ24190_REG_F_NTC_FAULT_SHIFT & 0x7) { + case 0x1: /* TS1 Cold */ + case 0x3: /* TS2 Cold */ + case 0x5: /* Both Cold */ + health = POWER_SUPPLY_HEALTH_COLD; + break; + case 0x2: /* TS1 Hot */ + case 0x4: /* TS2 Hot */ + case 0x6: /* Both Hot */ + health = POWER_SUPPLY_HEALTH_OVERHEAT; + break; + default: + health = POWER_SUPPLY_HEALTH_UNKNOWN; + } + + return health; +} + +static int bq24296_charger_get_ntc_status(u8 value) +{ + int health; + + switch (value >> BQ24296_REG_F_NTC_FAULT_SHIFT & 0x3) { + case 0x0: /* Normal */ + health = POWER_SUPPLY_HEALTH_GOOD; + break; + case 0x1: /* Hot */ + health = POWER_SUPPLY_HEALTH_OVERHEAT; + break; + case 0x2: /* Cold */ + health = POWER_SUPPLY_HEALTH_COLD; + break; + default: + health = POWER_SUPPLY_HEALTH_UNKNOWN; + } + + return health; } static int bq24190_charger_get_health(struct bq24190_dev_info *bdi, @@ -850,21 +1035,8 @@ static int bq24190_charger_get_health(struct bq24190_dev_info *bdi, v = bdi->f_reg; mutex_unlock(&bdi->f_reg_lock); - if (v & BQ24190_REG_F_NTC_FAULT_MASK) { - switch (v >> BQ24190_REG_F_NTC_FAULT_SHIFT & 0x7) { - case 0x1: /* TS1 Cold */ - case 0x3: /* TS2 Cold */ - case 0x5: /* Both Cold */ - health = POWER_SUPPLY_HEALTH_COLD; - break; - case 0x2: /* TS1 Hot */ - case 0x4: /* TS2 Hot */ - case 0x6: /* Both Hot */ - health = POWER_SUPPLY_HEALTH_OVERHEAT; - break; - default: - health = POWER_SUPPLY_HEALTH_UNKNOWN; - } + if (v & bdi->info->ntc_fault_mask) { + health = bdi->info->get_ntc_status(v); } else if (v & BQ24190_REG_F_BAT_FAULT_MASK) { health = POWER_SUPPLY_HEALTH_OVERVOLTAGE; } else if (v & BQ24190_REG_F_CHRG_FAULT_MASK) { @@ -1015,7 +1187,7 @@ static int bq24190_charger_get_current(struct bq24190_dev_info *bdi, ret = bq24190_get_field_val(bdi, BQ24190_REG_CCC, BQ24190_REG_CCC_ICHG_MASK, BQ24190_REG_CCC_ICHG_SHIFT, bq24190_ccc_ichg_values, - ARRAY_SIZE(bq24190_ccc_ichg_values), &curr); + bdi->info->ichg_array_size, &curr); if (ret < 0) return ret; @@ -1055,7 +1227,7 @@ static int bq24190_charger_set_current(struct bq24190_dev_info *bdi, ret = bq24190_set_field_val(bdi, BQ24190_REG_CCC, BQ24190_REG_CCC_ICHG_MASK, BQ24190_REG_CCC_ICHG_SHIFT, bq24190_ccc_ichg_values, - ARRAY_SIZE(bq24190_ccc_ichg_values), curr); + bdi->info->ichg_array_size, curr); if (ret < 0) return ret; @@ -1395,26 +1567,9 @@ static int bq24190_battery_get_health(struct bq24190_dev_info *bdi, if (v & BQ24190_REG_F_BAT_FAULT_MASK) { health = POWER_SUPPLY_HEALTH_OVERVOLTAGE; } else { - v &= BQ24190_REG_F_NTC_FAULT_MASK; - v >>= BQ24190_REG_F_NTC_FAULT_SHIFT; + v &= bdi->info->ntc_fault_mask; - switch (v) { - case 0x0: /* Normal */ - health = POWER_SUPPLY_HEALTH_GOOD; - break; - case 0x1: /* TS1 Cold */ - case 0x3: /* TS2 Cold */ - case 0x5: /* Both Cold */ - health = POWER_SUPPLY_HEALTH_COLD; - break; - case 0x2: /* TS1 Hot */ - case 0x4: /* TS2 Hot */ - case 0x6: /* Both Hot */ - health = POWER_SUPPLY_HEALTH_OVERHEAT; - break; - default: - health = POWER_SUPPLY_HEALTH_UNKNOWN; - } + health = v ? bdi->info->get_ntc_status(v) : POWER_SUPPLY_HEALTH_GOOD; } val->intval = health; @@ -1601,12 +1756,13 @@ static int bq24190_configure_usb_otg(struct bq24190_dev_info *bdi, u8 ss_reg) static void bq24190_check_status(struct bq24190_dev_info *bdi) { const u8 battery_mask_ss = BQ24190_REG_SS_CHRG_STAT_MASK; - const u8 battery_mask_f = BQ24190_REG_F_BAT_FAULT_MASK - | BQ24190_REG_F_NTC_FAULT_MASK; + u8 battery_mask_f = BQ24190_REG_F_BAT_FAULT_MASK; bool alert_charger = false, alert_battery = false; u8 ss_reg = 0, f_reg = 0; int i, ret; + battery_mask_f |= bdi->info->ntc_fault_mask; + ret = bq24190_read(bdi, BQ24190_REG_SS, &ss_reg); if (ret < 0) { dev_err(bdi->dev, "Can't read SS reg: %d\n", ret); @@ -1633,7 +1789,7 @@ static void bq24190_check_status(struct bq24190_dev_info *bdi) !!(f_reg & BQ24190_REG_F_BOOST_FAULT_MASK), !!(f_reg & BQ24190_REG_F_CHRG_FAULT_MASK), !!(f_reg & BQ24190_REG_F_BAT_FAULT_MASK), - !!(f_reg & BQ24190_REG_F_NTC_FAULT_MASK)); + !!(f_reg & bdi->info->ntc_fault_mask)); mutex_lock(&bdi->f_reg_lock); if ((bdi->f_reg & battery_mask_f) != (f_reg & battery_mask_f)) @@ -1696,12 +1852,11 @@ static irqreturn_t bq24190_irq_handler_thread(int irq, void *data) return IRQ_HANDLED; } -static int bq24190_hw_init(struct bq24190_dev_info *bdi) +static int bq24190_check_chip(struct bq24190_dev_info *bdi) { u8 v; int ret; - /* First check that the device really is what its supposed to be */ ret = bq24190_read_mask(bdi, BQ24190_REG_VPRS, BQ24190_REG_VPRS_PN_MASK, BQ24190_REG_VPRS_PN_SHIFT, @@ -1719,6 +1874,40 @@ static int bq24190_hw_init(struct bq24190_dev_info *bdi) return -ENODEV; } + return 0; +} + +static int bq24296_check_chip(struct bq24190_dev_info *bdi) +{ + u8 v; + int ret; + + ret = bq24190_read_mask(bdi, BQ24190_REG_VPRS, + BQ24296_REG_VPRS_PN_MASK, + BQ24296_REG_VPRS_PN_SHIFT, + &v); + if (ret < 0) + return ret; + + switch (v) { + case BQ24296_REG_VPRS_PN_24296: + break; + default: + dev_err(bdi->dev, "Error unknown model: 0x%02x\n", v); + return -ENODEV; + } + + return 0; +} + +static int bq24190_hw_init(struct bq24190_dev_info *bdi) +{ + int ret; + + ret = bdi->info->check_chip(bdi); + if (ret < 0) + return ret; + ret = bq24190_register_reset(bdi); if (ret < 0) return ret; @@ -1736,7 +1925,8 @@ static int bq24190_get_config(struct bq24190_dev_info *bdi) struct power_supply_battery_info *info; int v, idx; - idx = ARRAY_SIZE(bq24190_ccc_ichg_values) - 1; + idx = bdi->info->ichg_array_size - 1; + bdi->ichg_max = bq24190_ccc_ichg_values[idx]; idx = ARRAY_SIZE(bq24190_cvc_vreg_values) - 1; @@ -1781,6 +1971,64 @@ static int bq24190_get_config(struct bq24190_dev_info *bdi) return 0; } +static const struct bq24190_chip_info bq24190_chip_info_tbl[] = { + [BQ24190] = { + .ichg_array_size = ARRAY_SIZE(bq24190_ccc_ichg_values), +#ifdef CONFIG_REGULATOR + .vbus_desc = &bq24190_vbus_desc, +#endif + .check_chip = bq24190_check_chip, + .set_chg_config = bq24190_battery_set_chg_config, + .ntc_fault_mask = BQ24190_REG_F_NTC_FAULT_MASK, + .get_ntc_status = bq24190_charger_get_ntc_status, + .set_otg_vbus = bq24190_set_otg_vbus, + }, + [BQ24192] = { + .ichg_array_size = ARRAY_SIZE(bq24190_ccc_ichg_values), +#ifdef CONFIG_REGULATOR + .vbus_desc = &bq24190_vbus_desc, +#endif + .check_chip = bq24190_check_chip, + .set_chg_config = bq24190_battery_set_chg_config, + .ntc_fault_mask = BQ24190_REG_F_NTC_FAULT_MASK, + .get_ntc_status = bq24190_charger_get_ntc_status, + .set_otg_vbus = bq24190_set_otg_vbus, + }, + [BQ24192i] = { + .ichg_array_size = ARRAY_SIZE(bq24190_ccc_ichg_values), +#ifdef CONFIG_REGULATOR + .vbus_desc = &bq24190_vbus_desc, +#endif + .check_chip = bq24190_check_chip, + .set_chg_config = bq24190_battery_set_chg_config, + .ntc_fault_mask = BQ24190_REG_F_NTC_FAULT_MASK, + .get_ntc_status = bq24190_charger_get_ntc_status, + .set_otg_vbus = bq24190_set_otg_vbus, + }, + [BQ24196] = { + .ichg_array_size = ARRAY_SIZE(bq24190_ccc_ichg_values), +#ifdef CONFIG_REGULATOR + .vbus_desc = &bq24190_vbus_desc, +#endif + .check_chip = bq24190_check_chip, + .set_chg_config = bq24190_battery_set_chg_config, + .ntc_fault_mask = BQ24190_REG_F_NTC_FAULT_MASK, + .get_ntc_status = bq24190_charger_get_ntc_status, + .set_otg_vbus = bq24190_set_otg_vbus, + }, + [BQ24296] = { + .ichg_array_size = BQ24296_CCC_ICHG_VALUES_LEN, +#ifdef CONFIG_REGULATOR + .vbus_desc = &bq24296_vbus_desc, +#endif + .check_chip = bq24296_check_chip, + .set_chg_config = bq24296_battery_set_chg_config, + .ntc_fault_mask = BQ24296_REG_F_NTC_FAULT_MASK, + .get_ntc_status = bq24296_charger_get_ntc_status, + .set_otg_vbus = bq24296_set_otg_vbus, + }, +}; + static int bq24190_probe(struct i2c_client *client) { const struct i2c_device_id *id = i2c_client_get_device_id(client); @@ -1804,6 +2052,7 @@ static int bq24190_probe(struct i2c_client *client) bdi->client = client; bdi->dev = dev; strscpy(bdi->model_name, id->name, sizeof(bdi->model_name)); + bdi->info = i2c_get_match_data(client); mutex_init(&bdi->f_reg_lock); bdi->charge_type = POWER_SUPPLY_CHARGE_TYPE_FAST; bdi->f_reg = 0; @@ -1940,7 +2189,7 @@ static void bq24190_shutdown(struct i2c_client *client) struct bq24190_dev_info *bdi = i2c_get_clientdata(client); /* Turn off 5V boost regulator on shutdown */ - bq24190_set_otg_vbus(bdi, false); + bdi->info->set_otg_vbus(bdi, false); } static __maybe_unused int bq24190_runtime_suspend(struct device *dev) @@ -2029,19 +2278,21 @@ static const struct dev_pm_ops bq24190_pm_ops = { }; static const struct i2c_device_id bq24190_i2c_ids[] = { - { "bq24190" }, - { "bq24192" }, - { "bq24192i" }, - { "bq24196" }, + { "bq24190", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24190] }, + { "bq24192", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24192] }, + { "bq24192i", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24192i] }, + { "bq24196", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24196] }, + { "bq24296", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24296] }, { }, }; MODULE_DEVICE_TABLE(i2c, bq24190_i2c_ids); static const struct of_device_id bq24190_of_match[] = { - { .compatible = "ti,bq24190", }, - { .compatible = "ti,bq24192", }, - { .compatible = "ti,bq24192i", }, - { .compatible = "ti,bq24196", }, + { .compatible = "ti,bq24190", .data = &bq24190_chip_info_tbl[BQ24190] }, + { .compatible = "ti,bq24192", .data = &bq24190_chip_info_tbl[BQ24192] }, + { .compatible = "ti,bq24192i", .data = &bq24190_chip_info_tbl[BQ24192i] }, + { .compatible = "ti,bq24196", .data = &bq24190_chip_info_tbl[BQ24196] }, + { .compatible = "ti,bq24296", .data = &bq24190_chip_info_tbl[BQ24296] }, { }, }; MODULE_DEVICE_TABLE(of, bq24190_of_match); diff --git a/drivers/power/supply/bq256xx_charger.c b/drivers/power/supply/bq256xx_charger.c index 789a31bd70c3..1a935bc88510 100644 --- a/drivers/power/supply/bq256xx_charger.c +++ b/drivers/power/supply/bq256xx_charger.c @@ -1574,13 +1574,16 @@ static int bq256xx_hw_init(struct bq256xx_device *bq) wd_reg_val = i; break; } - if (bq->watchdog_timer > bq256xx_watchdog_time[i] && + if (i + 1 < BQ256XX_NUM_WD_VAL && + bq->watchdog_timer > bq256xx_watchdog_time[i] && bq->watchdog_timer < bq256xx_watchdog_time[i + 1]) wd_reg_val = i; } ret = regmap_update_bits(bq->regmap, BQ256XX_CHARGER_CONTROL_1, BQ256XX_WATCHDOG_MASK, wd_reg_val << BQ256XX_WDT_BIT_SHIFT); + if (ret) + return ret; ret = power_supply_get_battery_info(bq->charger, &bat_info); if (ret == -ENOMEM) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 4296600e8912..1c4a9d137744 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -2162,6 +2162,28 @@ void bq27xxx_battery_teardown(struct bq27xxx_device_info *di) } EXPORT_SYMBOL_GPL(bq27xxx_battery_teardown); +#ifdef CONFIG_PM_SLEEP +static int bq27xxx_battery_suspend(struct device *dev) +{ + struct bq27xxx_device_info *di = dev_get_drvdata(dev); + + cancel_delayed_work(&di->work); + return 0; +} + +static int bq27xxx_battery_resume(struct device *dev) +{ + struct bq27xxx_device_info *di = dev_get_drvdata(dev); + + schedule_delayed_work(&di->work, 0); + return 0; +} +#endif /* CONFIG_PM_SLEEP */ + +SIMPLE_DEV_PM_OPS(bq27xxx_battery_battery_pm_ops, + bq27xxx_battery_suspend, bq27xxx_battery_resume); +EXPORT_SYMBOL_GPL(bq27xxx_battery_battery_pm_ops); + MODULE_AUTHOR("Rodolfo Giometti <giometti@linux.it>"); MODULE_DESCRIPTION("BQ27xxx battery monitor driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c index 9b5475590518..3a1798b0c1a7 100644 --- a/drivers/power/supply/bq27xxx_battery_i2c.c +++ b/drivers/power/supply/bq27xxx_battery_i2c.c @@ -295,6 +295,7 @@ static struct i2c_driver bq27xxx_battery_i2c_driver = { .driver = { .name = "bq27xxx-battery", .of_match_table = of_match_ptr(bq27xxx_battery_i2c_of_match_table), + .pm = &bq27xxx_battery_battery_pm_ops, }, .probe = bq27xxx_battery_i2c_probe, .remove = bq27xxx_battery_i2c_remove, diff --git a/drivers/power/supply/cw2015_battery.c b/drivers/power/supply/cw2015_battery.c index bb29e9ebd24a..99f3ccdc30a6 100644 --- a/drivers/power/supply/cw2015_battery.c +++ b/drivers/power/supply/cw2015_battery.c @@ -491,7 +491,7 @@ static int cw_battery_get_property(struct power_supply *psy, case POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW: if (cw_battery_valid_time_to_empty(cw_bat)) - val->intval = cw_bat->time_to_empty; + val->intval = cw_bat->time_to_empty * 60; else val->intval = 0; break; diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index 73265001dd4b..ecef35ac3b7e 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -861,44 +861,44 @@ const size_t power_supply_battery_info_properties_size = ARRAY_SIZE(power_supply EXPORT_SYMBOL_GPL(power_supply_battery_info_properties_size); bool power_supply_battery_info_has_prop(struct power_supply_battery_info *info, - enum power_supply_property psp) + enum power_supply_property psp) { if (!info) return false; switch (psp) { - case POWER_SUPPLY_PROP_TECHNOLOGY: - return info->technology != POWER_SUPPLY_TECHNOLOGY_UNKNOWN; - case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN: - return info->energy_full_design_uwh >= 0; - case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN: - return info->charge_full_design_uah >= 0; - case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN: - return info->voltage_min_design_uv >= 0; - case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN: - return info->voltage_max_design_uv >= 0; - case POWER_SUPPLY_PROP_PRECHARGE_CURRENT: - return info->precharge_current_ua >= 0; - case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT: - return info->charge_term_current_ua >= 0; - case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX: - return info->constant_charge_current_max_ua >= 0; - case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX: - return info->constant_charge_voltage_max_uv >= 0; - case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN: - return info->temp_ambient_alert_min > INT_MIN; - case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX: - return info->temp_ambient_alert_max < INT_MAX; - case POWER_SUPPLY_PROP_TEMP_ALERT_MIN: - return info->temp_alert_min > INT_MIN; - case POWER_SUPPLY_PROP_TEMP_ALERT_MAX: - return info->temp_alert_max < INT_MAX; - case POWER_SUPPLY_PROP_TEMP_MIN: - return info->temp_min > INT_MIN; - case POWER_SUPPLY_PROP_TEMP_MAX: - return info->temp_max < INT_MAX; - default: - return false; + case POWER_SUPPLY_PROP_TECHNOLOGY: + return info->technology != POWER_SUPPLY_TECHNOLOGY_UNKNOWN; + case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN: + return info->energy_full_design_uwh >= 0; + case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN: + return info->charge_full_design_uah >= 0; + case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN: + return info->voltage_min_design_uv >= 0; + case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN: + return info->voltage_max_design_uv >= 0; + case POWER_SUPPLY_PROP_PRECHARGE_CURRENT: + return info->precharge_current_ua >= 0; + case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT: + return info->charge_term_current_ua >= 0; + case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX: + return info->constant_charge_current_max_ua >= 0; + case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX: + return info->constant_charge_voltage_max_uv >= 0; + case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN: + return info->temp_ambient_alert_min > INT_MIN; + case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX: + return info->temp_ambient_alert_max < INT_MAX; + case POWER_SUPPLY_PROP_TEMP_ALERT_MIN: + return info->temp_alert_min > INT_MIN; + case POWER_SUPPLY_PROP_TEMP_ALERT_MAX: + return info->temp_alert_max < INT_MAX; + case POWER_SUPPLY_PROP_TEMP_MIN: + return info->temp_min > INT_MIN; + case POWER_SUPPLY_PROP_TEMP_MAX: + return info->temp_max < INT_MAX; + default: + return false; } } EXPORT_SYMBOL_GPL(power_supply_battery_info_has_prop); @@ -914,53 +914,53 @@ int power_supply_battery_info_get_prop(struct power_supply_battery_info *info, return -EINVAL; switch (psp) { - case POWER_SUPPLY_PROP_TECHNOLOGY: - val->intval = info->technology; - return 0; - case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN: - val->intval = info->energy_full_design_uwh; - return 0; - case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN: - val->intval = info->charge_full_design_uah; - return 0; - case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN: - val->intval = info->voltage_min_design_uv; - return 0; - case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN: - val->intval = info->voltage_max_design_uv; - return 0; - case POWER_SUPPLY_PROP_PRECHARGE_CURRENT: - val->intval = info->precharge_current_ua; - return 0; - case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT: - val->intval = info->charge_term_current_ua; - return 0; - case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX: - val->intval = info->constant_charge_current_max_ua; - return 0; - case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX: - val->intval = info->constant_charge_voltage_max_uv; - return 0; - case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN: - val->intval = info->temp_ambient_alert_min; - return 0; - case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX: - val->intval = info->temp_ambient_alert_max; - return 0; - case POWER_SUPPLY_PROP_TEMP_ALERT_MIN: - val->intval = info->temp_alert_min; - return 0; - case POWER_SUPPLY_PROP_TEMP_ALERT_MAX: - val->intval = info->temp_alert_max; - return 0; - case POWER_SUPPLY_PROP_TEMP_MIN: - val->intval = info->temp_min; - return 0; - case POWER_SUPPLY_PROP_TEMP_MAX: - val->intval = info->temp_max; - return 0; - default: - return -EINVAL; + case POWER_SUPPLY_PROP_TECHNOLOGY: + val->intval = info->technology; + return 0; + case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN: + val->intval = info->energy_full_design_uwh; + return 0; + case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN: + val->intval = info->charge_full_design_uah; + return 0; + case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN: + val->intval = info->voltage_min_design_uv; + return 0; + case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN: + val->intval = info->voltage_max_design_uv; + return 0; + case POWER_SUPPLY_PROP_PRECHARGE_CURRENT: + val->intval = info->precharge_current_ua; + return 0; + case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT: + val->intval = info->charge_term_current_ua; + return 0; + case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX: + val->intval = info->constant_charge_current_max_ua; + return 0; + case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX: + val->intval = info->constant_charge_voltage_max_uv; + return 0; + case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN: + val->intval = info->temp_ambient_alert_min; + return 0; + case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX: + val->intval = info->temp_ambient_alert_max; + return 0; + case POWER_SUPPLY_PROP_TEMP_ALERT_MIN: + val->intval = info->temp_alert_min; + return 0; + case POWER_SUPPLY_PROP_TEMP_ALERT_MAX: + val->intval = info->temp_alert_max; + return 0; + case POWER_SUPPLY_PROP_TEMP_MIN: + val->intval = info->temp_min; + return 0; + case POWER_SUPPLY_PROP_TEMP_MAX: + val->intval = info->temp_max; + return 0; + default: + return -EINVAL; } } EXPORT_SYMBOL_GPL(power_supply_battery_info_get_prop); @@ -1255,6 +1255,7 @@ EXPORT_SYMBOL_GPL(power_supply_powers); static void power_supply_dev_release(struct device *dev) { struct power_supply *psy = to_power_supply(dev); + dev_dbg(dev, "%s\n", __func__); kfree(psy); } @@ -1636,6 +1637,6 @@ subsys_initcall(power_supply_class_init); module_exit(power_supply_class_exit); MODULE_DESCRIPTION("Universal power supply monitor class"); -MODULE_AUTHOR("Ian Molton <spyro@f2s.com>, " - "Szabolcs Gyurko, " - "Anton Vorontsov <cbou@mail.ru>"); +MODULE_AUTHOR("Ian Molton <spyro@f2s.com>"); +MODULE_AUTHOR("Szabolcs Gyurko"); +MODULE_AUTHOR("Anton Vorontsov <cbou@mail.ru>"); diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c index ec163d1bcd18..a12e2a66d516 100644 --- a/drivers/power/supply/qcom_battmgr.c +++ b/drivers/power/supply/qcom_battmgr.c @@ -282,6 +282,7 @@ struct qcom_battmgr_wireless { struct qcom_battmgr { struct device *dev; + struct auxiliary_device *adev; struct pmic_glink_client *client; enum qcom_battmgr_variant variant; @@ -1293,11 +1294,69 @@ static void qcom_battmgr_enable_worker(struct work_struct *work) dev_err(battmgr->dev, "failed to request power notifications\n"); } +static char *qcom_battmgr_battery[] = { "battery" }; + +static void qcom_battmgr_register_psy(struct qcom_battmgr *battmgr) +{ + struct power_supply_config psy_cfg_supply = {}; + struct auxiliary_device *adev = battmgr->adev; + struct power_supply_config psy_cfg = {}; + struct device *dev = &adev->dev; + + psy_cfg.drv_data = battmgr; + psy_cfg.of_node = adev->dev.of_node; + + psy_cfg_supply.drv_data = battmgr; + psy_cfg_supply.of_node = adev->dev.of_node; + psy_cfg_supply.supplied_to = qcom_battmgr_battery; + psy_cfg_supply.num_supplicants = 1; + + if (battmgr->variant == QCOM_BATTMGR_SC8280XP) { + battmgr->bat_psy = devm_power_supply_register(dev, &sc8280xp_bat_psy_desc, &psy_cfg); + if (IS_ERR(battmgr->bat_psy)) + dev_err(dev, "failed to register battery power supply (%ld)\n", + PTR_ERR(battmgr->bat_psy)); + + battmgr->ac_psy = devm_power_supply_register(dev, &sc8280xp_ac_psy_desc, &psy_cfg_supply); + if (IS_ERR(battmgr->ac_psy)) + dev_err(dev, "failed to register AC power supply (%ld)\n", + PTR_ERR(battmgr->ac_psy)); + + battmgr->usb_psy = devm_power_supply_register(dev, &sc8280xp_usb_psy_desc, &psy_cfg_supply); + if (IS_ERR(battmgr->usb_psy)) + dev_err(dev, "failed to register USB power supply (%ld)\n", + PTR_ERR(battmgr->usb_psy)); + + battmgr->wls_psy = devm_power_supply_register(dev, &sc8280xp_wls_psy_desc, &psy_cfg_supply); + if (IS_ERR(battmgr->wls_psy)) + dev_err(dev, "failed to register wireless charing power supply (%ld)\n", + PTR_ERR(battmgr->wls_psy)); + } else { + battmgr->bat_psy = devm_power_supply_register(dev, &sm8350_bat_psy_desc, &psy_cfg); + if (IS_ERR(battmgr->bat_psy)) + dev_err(dev, "failed to register battery power supply (%ld)\n", + PTR_ERR(battmgr->bat_psy)); + + battmgr->usb_psy = devm_power_supply_register(dev, &sm8350_usb_psy_desc, &psy_cfg_supply); + if (IS_ERR(battmgr->usb_psy)) + dev_err(dev, "failed to register USB power supply (%ld)\n", + PTR_ERR(battmgr->usb_psy)); + + battmgr->wls_psy = devm_power_supply_register(dev, &sm8350_wls_psy_desc, &psy_cfg_supply); + if (IS_ERR(battmgr->wls_psy)) + dev_err(dev, "failed to register wireless charing power supply (%ld)\n", + PTR_ERR(battmgr->wls_psy)); + } +} + static void qcom_battmgr_pdr_notify(void *priv, int state) { struct qcom_battmgr *battmgr = priv; if (state == SERVREG_SERVICE_STATE_UP) { + if (!battmgr->bat_psy) + qcom_battmgr_register_psy(battmgr); + battmgr->service_up = true; schedule_work(&battmgr->enable_work); } else { @@ -1312,13 +1371,9 @@ static const struct of_device_id qcom_battmgr_of_variants[] = { {} }; -static char *qcom_battmgr_battery[] = { "battery" }; - static int qcom_battmgr_probe(struct auxiliary_device *adev, const struct auxiliary_device_id *id) { - struct power_supply_config psy_cfg_supply = {}; - struct power_supply_config psy_cfg = {}; const struct of_device_id *match; struct qcom_battmgr *battmgr; struct device *dev = &adev->dev; @@ -1328,14 +1383,7 @@ static int qcom_battmgr_probe(struct auxiliary_device *adev, return -ENOMEM; battmgr->dev = dev; - - psy_cfg.drv_data = battmgr; - psy_cfg.of_node = adev->dev.of_node; - - psy_cfg_supply.drv_data = battmgr; - psy_cfg_supply.of_node = adev->dev.of_node; - psy_cfg_supply.supplied_to = qcom_battmgr_battery; - psy_cfg_supply.num_supplicants = 1; + battmgr->adev = adev; INIT_WORK(&battmgr->enable_work, qcom_battmgr_enable_worker); mutex_init(&battmgr->lock); @@ -1347,43 +1395,6 @@ static int qcom_battmgr_probe(struct auxiliary_device *adev, else battmgr->variant = QCOM_BATTMGR_SM8350; - if (battmgr->variant == QCOM_BATTMGR_SC8280XP) { - battmgr->bat_psy = devm_power_supply_register(dev, &sc8280xp_bat_psy_desc, &psy_cfg); - if (IS_ERR(battmgr->bat_psy)) - return dev_err_probe(dev, PTR_ERR(battmgr->bat_psy), - "failed to register battery power supply\n"); - - battmgr->ac_psy = devm_power_supply_register(dev, &sc8280xp_ac_psy_desc, &psy_cfg_supply); - if (IS_ERR(battmgr->ac_psy)) - return dev_err_probe(dev, PTR_ERR(battmgr->ac_psy), - "failed to register AC power supply\n"); - - battmgr->usb_psy = devm_power_supply_register(dev, &sc8280xp_usb_psy_desc, &psy_cfg_supply); - if (IS_ERR(battmgr->usb_psy)) - return dev_err_probe(dev, PTR_ERR(battmgr->usb_psy), - "failed to register USB power supply\n"); - - battmgr->wls_psy = devm_power_supply_register(dev, &sc8280xp_wls_psy_desc, &psy_cfg_supply); - if (IS_ERR(battmgr->wls_psy)) - return dev_err_probe(dev, PTR_ERR(battmgr->wls_psy), - "failed to register wireless charing power supply\n"); - } else { - battmgr->bat_psy = devm_power_supply_register(dev, &sm8350_bat_psy_desc, &psy_cfg); - if (IS_ERR(battmgr->bat_psy)) - return dev_err_probe(dev, PTR_ERR(battmgr->bat_psy), - "failed to register battery power supply\n"); - - battmgr->usb_psy = devm_power_supply_register(dev, &sm8350_usb_psy_desc, &psy_cfg_supply); - if (IS_ERR(battmgr->usb_psy)) - return dev_err_probe(dev, PTR_ERR(battmgr->usb_psy), - "failed to register USB power supply\n"); - - battmgr->wls_psy = devm_power_supply_register(dev, &sm8350_wls_psy_desc, &psy_cfg_supply); - if (IS_ERR(battmgr->wls_psy)) - return dev_err_probe(dev, PTR_ERR(battmgr->wls_psy), - "failed to register wireless charing power supply\n"); - } - battmgr->client = devm_pmic_glink_register_client(dev, PMIC_GLINK_OWNER_BATTMGR, qcom_battmgr_callback, diff --git a/drivers/power/supply/qcom_pmi8998_charger.c b/drivers/power/supply/qcom_pmi8998_charger.c index 8acf63ee6897..9bb777406013 100644 --- a/drivers/power/supply/qcom_pmi8998_charger.c +++ b/drivers/power/supply/qcom_pmi8998_charger.c @@ -972,10 +972,14 @@ static int smb2_probe(struct platform_device *pdev) supply_config.of_node = pdev->dev.of_node; desc = devm_kzalloc(chip->dev, sizeof(smb2_psy_desc), GFP_KERNEL); + if (!desc) + return -ENOMEM; memcpy(desc, &smb2_psy_desc, sizeof(smb2_psy_desc)); desc->name = devm_kasprintf(chip->dev, GFP_KERNEL, "%s-charger", (const char *)device_get_match_data(chip->dev)); + if (!desc->name) + return -ENOMEM; chip->chg_psy = devm_power_supply_register(chip->dev, desc, &supply_config); diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index 9a4c720c88aa..f2728ee787d7 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -152,7 +152,7 @@ of_pwm_single_xlate(struct pwm_chip *chip, const struct of_phandle_args *args) pwm->args.period = args->args[0]; pwm->args.polarity = PWM_POLARITY_NORMAL; - if (args->args_count == 2 && args->args[2] & PWM_POLARITY_INVERTED) + if (args->args_count == 2 && args->args[1] & PWM_POLARITY_INVERTED) pwm->args.polarity = PWM_POLARITY_INVERSED; return pwm; diff --git a/drivers/pwm/pwm-bcm2835.c b/drivers/pwm/pwm-bcm2835.c index 307c0bd5f885..283cf27f25ba 100644 --- a/drivers/pwm/pwm-bcm2835.c +++ b/drivers/pwm/pwm-bcm2835.c @@ -160,10 +160,8 @@ static int bcm2835_pwm_probe(struct platform_device *pdev) ret = devm_add_action_or_reset(&pdev->dev, devm_clk_rate_exclusive_put, pc->clk); - if (ret) { - clk_rate_exclusive_put(pc->clk); + if (ret) return ret; - } pc->rate = clk_get_rate(pc->clk); if (!pc->rate) diff --git a/drivers/pwm/pwm-jz4740.c b/drivers/pwm/pwm-jz4740.c index 80dcff237a15..3933418e551b 100644 --- a/drivers/pwm/pwm-jz4740.c +++ b/drivers/pwm/pwm-jz4740.c @@ -61,9 +61,10 @@ static int jz4740_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm) snprintf(name, sizeof(name), "timer%u", pwm->hwpwm); clk = clk_get(chip->dev, name); - if (IS_ERR(clk)) - return dev_err_probe(chip->dev, PTR_ERR(clk), - "Failed to get clock\n"); + if (IS_ERR(clk)) { + dev_err(chip->dev, "error %pe: Failed to get clock\n", clk); + return PTR_ERR(clk); + } err = clk_prepare_enable(clk); if (err < 0) { diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 3814e0845e77..e37a4341f442 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -373,6 +373,19 @@ config RTC_DRV_MAX8997 This driver can also be built as a module. If so, the module will be called rtc-max8997. +config RTC_DRV_MAX31335 + tristate "Analog Devices MAX31335" + depends on I2C + depends on COMMON_CLK + depends on HWMON || HWMON=n + select REGMAP_I2C + help + If you say yes here you get support for the Analog Devices + MAX31335. + + This driver can also be built as a module. If so, the module + will be called rtc-max31335. + config RTC_DRV_MAX77686 tristate "Maxim MAX77686" depends on MFD_MAX77686 || MFD_MAX77620 || MFD_MAX77714 || COMPILE_TEST @@ -578,6 +591,18 @@ config RTC_DRV_TPS6586X along with alarm. This driver supports the RTC driver for the TPS6586X RTC module. +config RTC_DRV_TPS6594 + tristate "TI TPS6594 RTC driver" + depends on MFD_TPS6594 + default MFD_TPS6594 + help + TI Power Management IC TPS6594 supports RTC functionality + along with alarm. This driver supports the RTC driver for + the TPS6594 RTC module. + + This driver can also be built as a module. If so, the module + will be called rtc-tps6594. + config RTC_DRV_TPS65910 tristate "TI TPS65910 RTC driver" depends on MFD_TPS65910 @@ -1705,6 +1730,7 @@ config RTC_DRV_LPC24XX tristate "NXP RTC for LPC178x/18xx/408x/43xx" depends on ARCH_LPC18XX || COMPILE_TEST depends on OF && HAS_IOMEM + depends on COMMON_CLK help This enables support for the NXP RTC found which can be found on NXP LPC178x/18xx/408x/43xx devices. @@ -1930,6 +1956,17 @@ config RTC_DRV_TI_K3 This driver can also be built as a module, if so, the module will be called "rtc-ti-k3". +config RTC_DRV_MA35D1 + tristate "Nuvoton MA35D1 RTC" + depends on ARCH_MA35 || COMPILE_TEST + select REGMAP_MMIO + help + If you say yes here you get support for the Nuvoton MA35D1 + On-Chip Real Time Clock. + + This driver can also be built as a module, if so, the module + will be called "rtc-ma35d1". + comment "HID Sensor RTC drivers" config RTC_DRV_HID_SENSOR_TIME diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index 7b03c3abfd78..6efff381c484 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -88,6 +88,8 @@ obj-$(CONFIG_RTC_DRV_M41T94) += rtc-m41t94.o obj-$(CONFIG_RTC_DRV_M48T35) += rtc-m48t35.o obj-$(CONFIG_RTC_DRV_M48T59) += rtc-m48t59.o obj-$(CONFIG_RTC_DRV_M48T86) += rtc-m48t86.o +obj-$(CONFIG_RTC_DRV_MA35D1) += rtc-ma35d1.o +obj-$(CONFIG_RTC_DRV_MAX31335) += rtc-max31335.o obj-$(CONFIG_RTC_DRV_MAX6900) += rtc-max6900.o obj-$(CONFIG_RTC_DRV_MAX6902) += rtc-max6902.o obj-$(CONFIG_RTC_DRV_MAX6916) += rtc-max6916.o @@ -176,6 +178,7 @@ obj-$(CONFIG_RTC_DRV_TEGRA) += rtc-tegra.o obj-$(CONFIG_RTC_DRV_TEST) += rtc-test.o obj-$(CONFIG_RTC_DRV_TI_K3) += rtc-ti-k3.o obj-$(CONFIG_RTC_DRV_TPS6586X) += rtc-tps6586x.o +obj-$(CONFIG_RTC_DRV_TPS6594) += rtc-tps6594.o obj-$(CONFIG_RTC_DRV_TPS65910) += rtc-tps65910.o obj-$(CONFIG_RTC_DRV_TWL4030) += rtc-twl.o obj-$(CONFIG_RTC_DRV_VT8500) += rtc-vt8500.o diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index edfd942f8c54..921ee1827974 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -256,7 +256,7 @@ static int rtc_device_get_id(struct device *dev) of_id = of_alias_get_id(dev->parent->of_node, "rtc"); if (of_id >= 0) { - id = ida_simple_get(&rtc_ida, of_id, of_id + 1, GFP_KERNEL); + id = ida_alloc_range(&rtc_ida, of_id, of_id, GFP_KERNEL); if (id < 0) dev_warn(dev, "/aliases ID %d not available\n", of_id); } diff --git a/drivers/rtc/rtc-ac100.c b/drivers/rtc/rtc-ac100.c index eaf2c9ab9661..fa642bba3cee 100644 --- a/drivers/rtc/rtc-ac100.c +++ b/drivers/rtc/rtc-ac100.c @@ -99,7 +99,7 @@ struct ac100_rtc_dev { struct clk_hw_onecell_data *clk_data; }; -/** +/* * Clock controls for 3 clock output pins */ @@ -378,7 +378,7 @@ static void ac100_rtc_unregister_clks(struct ac100_rtc_dev *chip) clk_unregister_fixed_rate(chip->rtc_32k_clk->clk); } -/** +/* * RTC related bits */ static int ac100_rtc_get_time(struct device *dev, struct rtc_time *rtc_tm) diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 228fb2d11c70..7d99cd2c37a0 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -231,7 +231,7 @@ static int cmos_read_time(struct device *dev, struct rtc_time *t) if (!pm_trace_rtc_valid()) return -EIO; - ret = mc146818_get_time(t); + ret = mc146818_get_time(t, 1000); if (ret < 0) { dev_err_ratelimited(dev, "unable to read current time\n"); return ret; @@ -292,7 +292,7 @@ static int cmos_read_alarm(struct device *dev, struct rtc_wkalrm *t) /* This not only a rtc_op, but also called directly */ if (!is_valid_irq(cmos->irq)) - return -EIO; + return -ETIMEDOUT; /* Basic alarms only support hour, minute, and seconds fields. * Some also support day and month, for alarms up to a year in @@ -307,7 +307,7 @@ static int cmos_read_alarm(struct device *dev, struct rtc_wkalrm *t) * * Use the mc146818_avoid_UIP() function to avoid this. */ - if (!mc146818_avoid_UIP(cmos_read_alarm_callback, &p)) + if (!mc146818_avoid_UIP(cmos_read_alarm_callback, 10, &p)) return -EIO; if (!(p.rtc_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { @@ -556,8 +556,8 @@ static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t) * * Use mc146818_avoid_UIP() to avoid this. */ - if (!mc146818_avoid_UIP(cmos_set_alarm_callback, &p)) - return -EIO; + if (!mc146818_avoid_UIP(cmos_set_alarm_callback, 10, &p)) + return -ETIMEDOUT; cmos->alarm_expires = rtc_tm_to_time64(&t->time); @@ -818,18 +818,24 @@ static void rtc_wake_off(struct device *dev) } #ifdef CONFIG_X86 -/* Enable use_acpi_alarm mode for Intel platforms no earlier than 2015 */ static void use_acpi_alarm_quirks(void) { - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_INTEL: + if (dmi_get_bios_year() < 2015) + return; + break; + case X86_VENDOR_AMD: + case X86_VENDOR_HYGON: + if (dmi_get_bios_year() < 2021) + return; + break; + default: return; - + } if (!is_hpet_enabled()) return; - if (dmi_get_bios_year() < 2015) - return; - use_acpi_alarm = true; } #else diff --git a/drivers/rtc/rtc-da9063.c b/drivers/rtc/rtc-da9063.c index 2f5d60622564..859397541f29 100644 --- a/drivers/rtc/rtc-da9063.c +++ b/drivers/rtc/rtc-da9063.c @@ -377,7 +377,6 @@ static int da9063_rtc_probe(struct platform_device *pdev) { struct da9063_compatible_rtc *rtc; const struct da9063_compatible_rtc_regmap *config; - const struct of_device_id *match; int irq_alarm; u8 data[RTC_DATA_LEN]; int ret; @@ -385,14 +384,11 @@ static int da9063_rtc_probe(struct platform_device *pdev) if (!pdev->dev.of_node) return -ENXIO; - match = of_match_node(da9063_compatible_reg_id_table, - pdev->dev.of_node); - rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL); if (!rtc) return -ENOMEM; - rtc->config = match->data; + rtc->config = device_get_match_data(&pdev->dev); if (of_device_is_compatible(pdev->dev.of_node, "dlg,da9063-rtc")) { struct da9063 *chip = dev_get_drvdata(pdev->dev.parent); @@ -411,57 +407,49 @@ static int da9063_rtc_probe(struct platform_device *pdev) config->rtc_enable_reg, config->rtc_enable_mask, config->rtc_enable_mask); - if (ret < 0) { - dev_err(&pdev->dev, "Failed to enable RTC\n"); - return ret; - } + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, "Failed to enable RTC\n"); ret = regmap_update_bits(rtc->regmap, config->rtc_enable_32k_crystal_reg, config->rtc_crystal_mask, config->rtc_crystal_mask); - if (ret < 0) { - dev_err(&pdev->dev, "Failed to run 32kHz oscillator\n"); - return ret; - } + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, + "Failed to run 32kHz oscillator\n"); ret = regmap_update_bits(rtc->regmap, config->rtc_alarm_secs_reg, config->rtc_alarm_status_mask, 0); - if (ret < 0) { - dev_err(&pdev->dev, "Failed to access RTC alarm register\n"); - return ret; - } + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, + "Failed to access RTC alarm register\n"); ret = regmap_update_bits(rtc->regmap, config->rtc_alarm_secs_reg, DA9063_ALARM_STATUS_ALARM, DA9063_ALARM_STATUS_ALARM); - if (ret < 0) { - dev_err(&pdev->dev, "Failed to access RTC alarm register\n"); - return ret; - } + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, + "Failed to access RTC alarm register\n"); ret = regmap_update_bits(rtc->regmap, config->rtc_alarm_year_reg, config->rtc_tick_on_mask, 0); - if (ret < 0) { - dev_err(&pdev->dev, "Failed to disable TICKs\n"); - return ret; - } + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, + "Failed to disable TICKs\n"); data[RTC_SEC] = 0; ret = regmap_bulk_read(rtc->regmap, config->rtc_alarm_secs_reg, &data[config->rtc_data_start], config->rtc_alarm_len); - if (ret < 0) { - dev_err(&pdev->dev, "Failed to read initial alarm data: %d\n", - ret); - return ret; - } + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, + "Failed to read initial alarm data\n"); platform_set_drvdata(pdev, rtc); @@ -485,25 +473,29 @@ static int da9063_rtc_probe(struct platform_device *pdev) clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->rtc_dev->features); } - irq_alarm = platform_get_irq_byname(pdev, "ALARM"); - if (irq_alarm < 0) + irq_alarm = platform_get_irq_byname_optional(pdev, "ALARM"); + if (irq_alarm >= 0) { + ret = devm_request_threaded_irq(&pdev->dev, irq_alarm, NULL, + da9063_alarm_event, + IRQF_TRIGGER_LOW | IRQF_ONESHOT, + "ALARM", rtc); + if (ret) + dev_err(&pdev->dev, + "Failed to request ALARM IRQ %d: %d\n", + irq_alarm, ret); + + ret = dev_pm_set_wake_irq(&pdev->dev, irq_alarm); + if (ret) + dev_warn(&pdev->dev, + "Failed to set IRQ %d as a wake IRQ: %d\n", + irq_alarm, ret); + + device_init_wakeup(&pdev->dev, true); + } else if (irq_alarm != -ENXIO) { return irq_alarm; - - ret = devm_request_threaded_irq(&pdev->dev, irq_alarm, NULL, - da9063_alarm_event, - IRQF_TRIGGER_LOW | IRQF_ONESHOT, - "ALARM", rtc); - if (ret) - dev_err(&pdev->dev, "Failed to request ALARM IRQ %d: %d\n", - irq_alarm, ret); - - ret = dev_pm_set_wake_irq(&pdev->dev, irq_alarm); - if (ret) - dev_warn(&pdev->dev, - "Failed to set IRQ %d as a wake IRQ: %d\n", - irq_alarm, ret); - - device_init_wakeup(&pdev->dev, true); + } else { + clear_bit(RTC_FEATURE_ALARM, rtc->rtc_dev->features); + } return devm_rtc_register_device(rtc->rtc_dev); } diff --git a/drivers/rtc/rtc-ds3232.c b/drivers/rtc/rtc-ds3232.c index 89d7b085f721..1485a6ae51e6 100644 --- a/drivers/rtc/rtc-ds3232.c +++ b/drivers/rtc/rtc-ds3232.c @@ -536,6 +536,8 @@ static int ds3232_probe(struct device *dev, struct regmap *regmap, int irq, return 0; } +#if IS_ENABLED(CONFIG_I2C) + #ifdef CONFIG_PM_SLEEP static int ds3232_suspend(struct device *dev) { @@ -564,8 +566,6 @@ static const struct dev_pm_ops ds3232_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(ds3232_suspend, ds3232_resume) }; -#if IS_ENABLED(CONFIG_I2C) - static int ds3232_i2c_probe(struct i2c_client *client) { struct regmap *regmap; diff --git a/drivers/rtc/rtc-ma35d1.c b/drivers/rtc/rtc-ma35d1.c new file mode 100644 index 000000000000..cfcfc28060f6 --- /dev/null +++ b/drivers/rtc/rtc-ma35d1.c @@ -0,0 +1,304 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * RTC driver for Nuvoton MA35D1 + * + * Copyright (C) 2023 Nuvoton Technology Corp. + */ + +#include <linux/bcd.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/rtc.h> + +/* MA35D1 RTC Control Registers */ +#define MA35_REG_RTC_INIT 0x00 +#define MA35_REG_RTC_SINFASTS 0x04 +#define MA35_REG_RTC_FREQADJ 0x08 +#define MA35_REG_RTC_TIME 0x0c +#define MA35_REG_RTC_CAL 0x10 +#define MA35_REG_RTC_CLKFMT 0x14 +#define MA35_REG_RTC_WEEKDAY 0x18 +#define MA35_REG_RTC_TALM 0x1c +#define MA35_REG_RTC_CALM 0x20 +#define MA35_REG_RTC_LEAPYEAR 0x24 +#define MA35_REG_RTC_INTEN 0x28 +#define MA35_REG_RTC_INTSTS 0x2c + +/* register MA35_REG_RTC_INIT */ +#define RTC_INIT_ACTIVE BIT(0) +#define RTC_INIT_MAGIC_CODE 0xa5eb1357 + +/* register MA35_REG_RTC_CLKFMT */ +#define RTC_CLKFMT_24HEN BIT(0) +#define RTC_CLKFMT_DCOMPEN BIT(16) + +/* register MA35_REG_RTC_INTEN */ +#define RTC_INTEN_ALMIEN BIT(0) +#define RTC_INTEN_UIEN BIT(1) +#define RTC_INTEN_CLKFIEN BIT(24) +#define RTC_INTEN_CLKSTIEN BIT(25) + +/* register MA35_REG_RTC_INTSTS */ +#define RTC_INTSTS_ALMIF BIT(0) +#define RTC_INTSTS_UIF BIT(1) +#define RTC_INTSTS_CLKFIF BIT(24) +#define RTC_INTSTS_CLKSTIF BIT(25) + +#define RTC_INIT_TIMEOUT 250 + +struct ma35_rtc { + int irq_num; + void __iomem *rtc_reg; + struct rtc_device *rtcdev; +}; + +static u32 rtc_reg_read(struct ma35_rtc *p, u32 offset) +{ + return __raw_readl(p->rtc_reg + offset); +} + +static inline void rtc_reg_write(struct ma35_rtc *p, u32 offset, u32 value) +{ + __raw_writel(value, p->rtc_reg + offset); +} + +static irqreturn_t ma35d1_rtc_interrupt(int irq, void *data) +{ + struct ma35_rtc *rtc = (struct ma35_rtc *)data; + unsigned long events = 0, rtc_irq; + + rtc_irq = rtc_reg_read(rtc, MA35_REG_RTC_INTSTS); + + if (rtc_irq & RTC_INTSTS_ALMIF) { + rtc_reg_write(rtc, MA35_REG_RTC_INTSTS, RTC_INTSTS_ALMIF); + events |= RTC_AF | RTC_IRQF; + } + + rtc_update_irq(rtc->rtcdev, 1, events); + + return IRQ_HANDLED; +} + +static int ma35d1_rtc_init(struct ma35_rtc *rtc, u32 ms_timeout) +{ + const unsigned long timeout = jiffies + msecs_to_jiffies(ms_timeout); + + do { + if (rtc_reg_read(rtc, MA35_REG_RTC_INIT) & RTC_INIT_ACTIVE) + return 0; + + rtc_reg_write(rtc, MA35_REG_RTC_INIT, RTC_INIT_MAGIC_CODE); + + mdelay(1); + + } while (time_before(jiffies, timeout)); + + return -ETIMEDOUT; +} + +static int ma35d1_alarm_irq_enable(struct device *dev, u32 enabled) +{ + struct ma35_rtc *rtc = dev_get_drvdata(dev); + u32 reg_ien; + + reg_ien = rtc_reg_read(rtc, MA35_REG_RTC_INTEN); + + if (enabled) + rtc_reg_write(rtc, MA35_REG_RTC_INTEN, reg_ien | RTC_INTEN_ALMIEN); + else + rtc_reg_write(rtc, MA35_REG_RTC_INTEN, reg_ien & ~RTC_INTEN_ALMIEN); + + return 0; +} + +static int ma35d1_rtc_read_time(struct device *dev, struct rtc_time *tm) +{ + struct ma35_rtc *rtc = dev_get_drvdata(dev); + u32 time, cal, wday; + + do { + time = rtc_reg_read(rtc, MA35_REG_RTC_TIME); + cal = rtc_reg_read(rtc, MA35_REG_RTC_CAL); + wday = rtc_reg_read(rtc, MA35_REG_RTC_WEEKDAY); + } while (time != rtc_reg_read(rtc, MA35_REG_RTC_TIME) || + cal != rtc_reg_read(rtc, MA35_REG_RTC_CAL)); + + tm->tm_mday = bcd2bin(cal >> 0); + tm->tm_wday = wday; + tm->tm_mon = bcd2bin(cal >> 8); + tm->tm_mon = tm->tm_mon - 1; + tm->tm_year = bcd2bin(cal >> 16) + 100; + + tm->tm_sec = bcd2bin(time >> 0); + tm->tm_min = bcd2bin(time >> 8); + tm->tm_hour = bcd2bin(time >> 16); + + return rtc_valid_tm(tm); +} + +static int ma35d1_rtc_set_time(struct device *dev, struct rtc_time *tm) +{ + struct ma35_rtc *rtc = dev_get_drvdata(dev); + u32 val; + + val = bin2bcd(tm->tm_mday) << 0 | bin2bcd(tm->tm_mon + 1) << 8 | + bin2bcd(tm->tm_year - 100) << 16; + rtc_reg_write(rtc, MA35_REG_RTC_CAL, val); + + val = bin2bcd(tm->tm_sec) << 0 | bin2bcd(tm->tm_min) << 8 | + bin2bcd(tm->tm_hour) << 16; + rtc_reg_write(rtc, MA35_REG_RTC_TIME, val); + + val = tm->tm_wday; + rtc_reg_write(rtc, MA35_REG_RTC_WEEKDAY, val); + + return 0; +} + +static int ma35d1_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) +{ + struct ma35_rtc *rtc = dev_get_drvdata(dev); + u32 talm, calm; + + talm = rtc_reg_read(rtc, MA35_REG_RTC_TALM); + calm = rtc_reg_read(rtc, MA35_REG_RTC_CALM); + + alrm->time.tm_mday = bcd2bin(calm >> 0); + alrm->time.tm_mon = bcd2bin(calm >> 8); + alrm->time.tm_mon = alrm->time.tm_mon - 1; + + alrm->time.tm_year = bcd2bin(calm >> 16) + 100; + + alrm->time.tm_sec = bcd2bin(talm >> 0); + alrm->time.tm_min = bcd2bin(talm >> 8); + alrm->time.tm_hour = bcd2bin(talm >> 16); + + return rtc_valid_tm(&alrm->time); +} + +static int ma35d1_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) +{ + struct ma35_rtc *rtc = dev_get_drvdata(dev); + unsigned long val; + + val = bin2bcd(alrm->time.tm_mday) << 0 | bin2bcd(alrm->time.tm_mon + 1) << 8 | + bin2bcd(alrm->time.tm_year - 100) << 16; + rtc_reg_write(rtc, MA35_REG_RTC_CALM, val); + + val = bin2bcd(alrm->time.tm_sec) << 0 | bin2bcd(alrm->time.tm_min) << 8 | + bin2bcd(alrm->time.tm_hour) << 16; + rtc_reg_write(rtc, MA35_REG_RTC_TALM, val); + + ma35d1_alarm_irq_enable(dev, alrm->enabled); + + return 0; +} + +static const struct rtc_class_ops ma35d1_rtc_ops = { + .read_time = ma35d1_rtc_read_time, + .set_time = ma35d1_rtc_set_time, + .read_alarm = ma35d1_rtc_read_alarm, + .set_alarm = ma35d1_rtc_set_alarm, + .alarm_irq_enable = ma35d1_alarm_irq_enable, +}; + +static int ma35d1_rtc_probe(struct platform_device *pdev) +{ + struct ma35_rtc *rtc; + struct clk *clk; + int ret; + + rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL); + if (!rtc) + return -ENOMEM; + + rtc->rtc_reg = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(rtc->rtc_reg)) + return PTR_ERR(rtc->rtc_reg); + + clk = of_clk_get(pdev->dev.of_node, 0); + if (IS_ERR(clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(clk), "failed to find rtc clock\n"); + + ret = clk_prepare_enable(clk); + if (ret) + return ret; + + if (!(rtc_reg_read(rtc, MA35_REG_RTC_INIT) & RTC_INIT_ACTIVE)) { + ret = ma35d1_rtc_init(rtc, RTC_INIT_TIMEOUT); + if (ret) + return dev_err_probe(&pdev->dev, ret, "rtc init failed\n"); + } + + rtc->irq_num = platform_get_irq(pdev, 0); + + ret = devm_request_irq(&pdev->dev, rtc->irq_num, ma35d1_rtc_interrupt, + IRQF_NO_SUSPEND, "ma35d1rtc", rtc); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to request rtc irq\n"); + + platform_set_drvdata(pdev, rtc); + + device_init_wakeup(&pdev->dev, true); + + rtc->rtcdev = devm_rtc_allocate_device(&pdev->dev); + if (IS_ERR(rtc->rtcdev)) + return PTR_ERR(rtc->rtcdev); + + rtc->rtcdev->ops = &ma35d1_rtc_ops; + rtc->rtcdev->range_min = RTC_TIMESTAMP_BEGIN_2000; + rtc->rtcdev->range_max = RTC_TIMESTAMP_END_2099; + + ret = devm_rtc_register_device(rtc->rtcdev); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to register rtc device\n"); + + return 0; +} + +static int ma35d1_rtc_suspend(struct platform_device *pdev, pm_message_t state) +{ + struct ma35_rtc *rtc = platform_get_drvdata(pdev); + + if (device_may_wakeup(&pdev->dev)) + enable_irq_wake(rtc->irq_num); + + return 0; +} + +static int ma35d1_rtc_resume(struct platform_device *pdev) +{ + struct ma35_rtc *rtc = platform_get_drvdata(pdev); + + if (device_may_wakeup(&pdev->dev)) + disable_irq_wake(rtc->irq_num); + + return 0; +} + +static const struct of_device_id ma35d1_rtc_of_match[] = { + { .compatible = "nuvoton,ma35d1-rtc", }, + {}, +}; +MODULE_DEVICE_TABLE(of, ma35d1_rtc_of_match); + +static struct platform_driver ma35d1_rtc_driver = { + .suspend = ma35d1_rtc_suspend, + .resume = ma35d1_rtc_resume, + .probe = ma35d1_rtc_probe, + .driver = { + .name = "rtc-ma35d1", + .of_match_table = ma35d1_rtc_of_match, + }, +}; + +module_platform_driver(ma35d1_rtc_driver); + +MODULE_AUTHOR("Ming-Jen Chen <mjchen@nuvoton.com>"); +MODULE_DESCRIPTION("MA35D1 RTC driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/rtc/rtc-max31335.c b/drivers/rtc/rtc-max31335.c new file mode 100644 index 000000000000..402fda8fd548 --- /dev/null +++ b/drivers/rtc/rtc-max31335.c @@ -0,0 +1,697 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * RTC driver for the MAX31335 + * + * Copyright (C) 2023 Analog Devices + * + * Antoniu Miclaus <antoniu.miclaus@analog.com> + * + */ + +#include <asm-generic/unaligned.h> +#include <linux/bcd.h> +#include <linux/bitfield.h> +#include <linux/bitops.h> +#include <linux/clk.h> +#include <linux/clk-provider.h> +#include <linux/hwmon.h> +#include <linux/i2c.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/regmap.h> +#include <linux/rtc.h> +#include <linux/util_macros.h> + +/* MAX31335 Register Map */ +#define MAX31335_STATUS1 0x00 +#define MAX31335_INT_EN1 0x01 +#define MAX31335_STATUS2 0x02 +#define MAX31335_INT_EN2 0x03 +#define MAX31335_RTC_RESET 0x04 +#define MAX31335_RTC_CONFIG 0x05 +#define MAX31335_RTC_CONFIG2 0x06 +#define MAX31335_TIMESTAMP_CONFIG 0x07 +#define MAX31335_TIMER_CONFIG 0x08 +#define MAX31335_SECONDS_1_128 0x09 +#define MAX31335_SECONDS 0x0A +#define MAX31335_MINUTES 0x0B +#define MAX31335_HOURS 0x0C +#define MAX31335_DAY 0x0D +#define MAX31335_DATE 0x0E +#define MAX31335_MONTH 0x0F +#define MAX31335_YEAR 0x0F +#define MAX31335_ALM1_SEC 0x11 +#define MAX31335_ALM1_MIN 0x12 +#define MAX31335_ALM1_HRS 0x13 +#define MAX31335_ALM1_DAY_DATE 0x14 +#define MAX31335_ALM1_MON 0x15 +#define MAX31335_ALM1_YEAR 0x16 +#define MAX31335_ALM2_MIN 0x17 +#define MAX31335_ALM2_HRS 0x18 +#define MAX31335_ALM2_DAY_DATE 0x19 +#define MAX31335_TIMER_COUNT 0x1A +#define MAX31335_TIMER_INIT 0x1B +#define MAX31335_PWR_MGMT 0x1C +#define MAX31335_TRICKLE_REG 0x1D +#define MAX31335_AGING_OFFSET 0x1E +#define MAX31335_TS_CONFIG 0x30 +#define MAX31335_TEMP_ALARM_HIGH_MSB 0x31 +#define MAX31335_TEMP_ALARM_HIGH_LSB 0x32 +#define MAX31335_TEMP_ALARM_LOW_MSB 0x33 +#define MAX31335_TEMP_ALARM_LOW_LSB 0x34 +#define MAX31335_TEMP_DATA_MSB 0x35 +#define MAX31335_TEMP_DATA_LSB 0x36 +#define MAX31335_TS0_SEC_1_128 0x40 +#define MAX31335_TS0_SEC 0x41 +#define MAX31335_TS0_MIN 0x42 +#define MAX31335_TS0_HOUR 0x43 +#define MAX31335_TS0_DATE 0x44 +#define MAX31335_TS0_MONTH 0x45 +#define MAX31335_TS0_YEAR 0x46 +#define MAX31335_TS0_FLAGS 0x47 +#define MAX31335_TS1_SEC_1_128 0x48 +#define MAX31335_TS1_SEC 0x49 +#define MAX31335_TS1_MIN 0x4A +#define MAX31335_TS1_HOUR 0x4B +#define MAX31335_TS1_DATE 0x4C +#define MAX31335_TS1_MONTH 0x4D +#define MAX31335_TS1_YEAR 0x4E +#define MAX31335_TS1_FLAGS 0x4F +#define MAX31335_TS2_SEC_1_128 0x50 +#define MAX31335_TS2_SEC 0x51 +#define MAX31335_TS2_MIN 0x52 +#define MAX31335_TS2_HOUR 0x53 +#define MAX31335_TS2_DATE 0x54 +#define MAX31335_TS2_MONTH 0x55 +#define MAX31335_TS2_YEAR 0x56 +#define MAX31335_TS2_FLAGS 0x57 +#define MAX31335_TS3_SEC_1_128 0x58 +#define MAX31335_TS3_SEC 0x59 +#define MAX31335_TS3_MIN 0x5A +#define MAX31335_TS3_HOUR 0x5B +#define MAX31335_TS3_DATE 0x5C +#define MAX31335_TS3_MONTH 0x5D +#define MAX31335_TS3_YEAR 0x5E +#define MAX31335_TS3_FLAGS 0x5F + +/* MAX31335_STATUS1 Bit Definitions */ +#define MAX31335_STATUS1_PSDECT BIT(7) +#define MAX31335_STATUS1_OSF BIT(6) +#define MAX31335_STATUS1_PFAIL BIT(5) +#define MAX31335_STATUS1_VBATLOW BIT(4) +#define MAX31335_STATUS1_DIF BIT(3) +#define MAX31335_STATUS1_TIF BIT(2) +#define MAX31335_STATUS1_A2F BIT(1) +#define MAX31335_STATUS1_A1F BIT(0) + +/* MAX31335_INT_EN1 Bit Definitions */ +#define MAX31335_INT_EN1_DOSF BIT(6) +#define MAX31335_INT_EN1_PFAILE BIT(5) +#define MAX31335_INT_EN1_VBATLOWE BIT(4) +#define MAX31335_INT_EN1_DIE BIT(3) +#define MAX31335_INT_EN1_TIE BIT(2) +#define MAX31335_INT_EN1_A2IE BIT(1) +#define MAX31335_INT_EN1_A1IE BIT(0) + +/* MAX31335_STATUS2 Bit Definitions */ +#define MAX31335_STATUS2_TEMP_RDY BIT(2) +#define MAX31335_STATUS2_OTF BIT(1) +#define MAX31335_STATUS2_UTF BIT(0) + +/* MAX31335_INT_EN2 Bit Definitions */ +#define MAX31335_INT_EN2_TEMP_RDY_EN BIT(2) +#define MAX31335_INT_EN2_OTIE BIT(1) +#define MAX31335_INT_EN2_UTIE BIT(0) + +/* MAX31335_RTC_RESET Bit Definitions */ +#define MAX31335_RTC_RESET_SWRST BIT(0) + +/* MAX31335_RTC_CONFIG1 Bit Definitions */ +#define MAX31335_RTC_CONFIG1_EN_IO BIT(6) +#define MAX31335_RTC_CONFIG1_A1AC GENMASK(5, 4) +#define MAX31335_RTC_CONFIG1_DIP BIT(3) +#define MAX31335_RTC_CONFIG1_I2C_TIMEOUT BIT(1) +#define MAX31335_RTC_CONFIG1_EN_OSC BIT(0) + +/* MAX31335_RTC_CONFIG2 Bit Definitions */ +#define MAX31335_RTC_CONFIG2_ENCLKO BIT(2) +#define MAX31335_RTC_CONFIG2_CLKO_HZ GENMASK(1, 0) + +/* MAX31335_TIMESTAMP_CONFIG Bit Definitions */ +#define MAX31335_TIMESTAMP_CONFIG_TSVLOW BIT(5) +#define MAX31335_TIMESTAMP_CONFIG_TSPWM BIT(4) +#define MAX31335_TIMESTAMP_CONFIG_TSDIN BIT(3) +#define MAX31335_TIMESTAMP_CONFIG_TSOW BIT(2) +#define MAX31335_TIMESTAMP_CONFIG_TSR BIT(1) +#define MAX31335_TIMESTAMP_CONFIG_TSE BIT(0) + +/* MAX31335_TIMER_CONFIG Bit Definitions */ +#define MAX31335_TIMER_CONFIG_TE BIT(4) +#define MAX31335_TIMER_CONFIG_TPAUSE BIT(3) +#define MAX31335_TIMER_CONFIG_TRPT BIT(2) +#define MAX31335_TIMER_CONFIG_TFS GENMASK(1, 0) + +/* MAX31335_HOURS Bit Definitions */ +#define MAX31335_HOURS_F_24_12 BIT(6) +#define MAX31335_HOURS_HR_20_AM_PM BIT(5) + +/* MAX31335_MONTH Bit Definitions */ +#define MAX31335_MONTH_CENTURY BIT(7) + +/* MAX31335_PWR_MGMT Bit Definitions */ +#define MAX31335_PWR_MGMT_PFVT BIT(0) + +/* MAX31335_TRICKLE_REG Bit Definitions */ +#define MAX31335_TRICKLE_REG_TRICKLE GENMASK(3, 1) +#define MAX31335_TRICKLE_REG_EN_TRICKLE BIT(0) + +/* MAX31335_TS_CONFIG Bit Definitions */ +#define MAX31335_TS_CONFIG_AUTO BIT(4) +#define MAX31335_TS_CONFIG_CONVERT_T BIT(3) +#define MAX31335_TS_CONFIG_TSINT GENMASK(2, 0) + +/* MAX31335_TS_FLAGS Bit Definitions */ +#define MAX31335_TS_FLAGS_VLOWF BIT(3) +#define MAX31335_TS_FLAGS_VBATF BIT(2) +#define MAX31335_TS_FLAGS_VCCF BIT(1) +#define MAX31335_TS_FLAGS_DINF BIT(0) + +/* MAX31335 Miscellaneous Definitions */ +#define MAX31335_TRICKLE_SCHOTTKY_DIODE 1 +#define MAX31335_TRICKLE_STANDARD_DIODE 4 +#define MAX31335_RAM_SIZE 32 +#define MAX31335_TIME_SIZE 0x07 + +#define clk_hw_to_max31335(_hw) container_of(_hw, struct max31335_data, clkout) + +struct max31335_data { + struct regmap *regmap; + struct rtc_device *rtc; + struct clk_hw clkout; +}; + +static const int max31335_clkout_freq[] = { 1, 64, 1024, 32768 }; + +static const u16 max31335_trickle_resistors[] = {3000, 6000, 11000}; + +static bool max31335_volatile_reg(struct device *dev, unsigned int reg) +{ + /* time keeping registers */ + if (reg >= MAX31335_SECONDS && + reg < MAX31335_SECONDS + MAX31335_TIME_SIZE) + return true; + + /* interrupt status register */ + if (reg == MAX31335_INT_EN1_A1IE) + return true; + + /* temperature registers */ + if (reg == MAX31335_TEMP_DATA_MSB || reg == MAX31335_TEMP_DATA_LSB) + return true; + + return false; +} + +static const struct regmap_config regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = 0x5F, + .volatile_reg = max31335_volatile_reg, +}; + +static int max31335_read_time(struct device *dev, struct rtc_time *tm) +{ + struct max31335_data *max31335 = dev_get_drvdata(dev); + u8 date[7]; + int ret; + + ret = regmap_bulk_read(max31335->regmap, MAX31335_SECONDS, date, + sizeof(date)); + if (ret) + return ret; + + tm->tm_sec = bcd2bin(date[0] & 0x7f); + tm->tm_min = bcd2bin(date[1] & 0x7f); + tm->tm_hour = bcd2bin(date[2] & 0x3f); + tm->tm_wday = bcd2bin(date[3] & 0x7) - 1; + tm->tm_mday = bcd2bin(date[4] & 0x3f); + tm->tm_mon = bcd2bin(date[5] & 0x1f) - 1; + tm->tm_year = bcd2bin(date[6]) + 100; + + if (FIELD_GET(MAX31335_MONTH_CENTURY, date[5])) + tm->tm_year += 100; + + return 0; +} + +static int max31335_set_time(struct device *dev, struct rtc_time *tm) +{ + struct max31335_data *max31335 = dev_get_drvdata(dev); + u8 date[7]; + + date[0] = bin2bcd(tm->tm_sec); + date[1] = bin2bcd(tm->tm_min); + date[2] = bin2bcd(tm->tm_hour); + date[3] = bin2bcd(tm->tm_wday + 1); + date[4] = bin2bcd(tm->tm_mday); + date[5] = bin2bcd(tm->tm_mon + 1); + date[6] = bin2bcd(tm->tm_year % 100); + + if (tm->tm_year >= 200) + date[5] |= FIELD_PREP(MAX31335_MONTH_CENTURY, 1); + + return regmap_bulk_write(max31335->regmap, MAX31335_SECONDS, date, + sizeof(date)); +} + +static int max31335_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) +{ + struct max31335_data *max31335 = dev_get_drvdata(dev); + int ret, ctrl, status; + struct rtc_time time; + u8 regs[6]; + + ret = regmap_bulk_read(max31335->regmap, MAX31335_ALM1_SEC, regs, + sizeof(regs)); + if (ret) + return ret; + + alrm->time.tm_sec = bcd2bin(regs[0] & 0x7f); + alrm->time.tm_min = bcd2bin(regs[1] & 0x7f); + alrm->time.tm_hour = bcd2bin(regs[2] & 0x3f); + alrm->time.tm_mday = bcd2bin(regs[3] & 0x3f); + alrm->time.tm_mon = bcd2bin(regs[4] & 0x1f) - 1; + alrm->time.tm_year = bcd2bin(regs[5]) + 100; + + ret = max31335_read_time(dev, &time); + if (ret) + return ret; + + if (time.tm_year >= 200) + alrm->time.tm_year += 100; + + ret = regmap_read(max31335->regmap, MAX31335_INT_EN1, &ctrl); + if (ret) + return ret; + + ret = regmap_read(max31335->regmap, MAX31335_STATUS1, &status); + if (ret) + return ret; + + alrm->enabled = FIELD_GET(MAX31335_INT_EN1_A1IE, ctrl); + alrm->pending = FIELD_GET(MAX31335_STATUS1_A1F, status); + + return 0; +} + +static int max31335_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) +{ + struct max31335_data *max31335 = dev_get_drvdata(dev); + unsigned int reg; + u8 regs[6]; + int ret; + + regs[0] = bin2bcd(alrm->time.tm_sec); + regs[1] = bin2bcd(alrm->time.tm_min); + regs[2] = bin2bcd(alrm->time.tm_hour); + regs[3] = bin2bcd(alrm->time.tm_mday); + regs[4] = bin2bcd(alrm->time.tm_mon + 1); + regs[5] = bin2bcd(alrm->time.tm_year % 100); + + ret = regmap_bulk_write(max31335->regmap, MAX31335_ALM1_SEC, + regs, sizeof(regs)); + if (ret) + return ret; + + reg = FIELD_PREP(MAX31335_INT_EN1_A1IE, alrm->enabled); + ret = regmap_update_bits(max31335->regmap, MAX31335_INT_EN1, + MAX31335_INT_EN1_A1IE, reg); + if (ret) + return ret; + + ret = regmap_update_bits(max31335->regmap, MAX31335_STATUS1, + MAX31335_STATUS1_A1F, 0); + + return 0; +} + +static int max31335_alarm_irq_enable(struct device *dev, unsigned int enabled) +{ + struct max31335_data *max31335 = dev_get_drvdata(dev); + + return regmap_update_bits(max31335->regmap, MAX31335_INT_EN1, + MAX31335_INT_EN1_A1IE, enabled); +} + +static irqreturn_t max31335_handle_irq(int irq, void *dev_id) +{ + struct max31335_data *max31335 = dev_id; + bool status; + int ret; + + ret = regmap_update_bits_check(max31335->regmap, MAX31335_STATUS1, + MAX31335_STATUS1_A1F, 0, &status); + if (ret) + return IRQ_HANDLED; + + if (status) + rtc_update_irq(max31335->rtc, 1, RTC_AF | RTC_IRQF); + + return IRQ_HANDLED; +} + +static const struct rtc_class_ops max31335_rtc_ops = { + .read_time = max31335_read_time, + .set_time = max31335_set_time, + .read_alarm = max31335_read_alarm, + .set_alarm = max31335_set_alarm, + .alarm_irq_enable = max31335_alarm_irq_enable, +}; + +static int max31335_trickle_charger_setup(struct device *dev, + struct max31335_data *max31335) +{ + u32 ohms, chargeable; + int i, trickle_cfg; + const char *diode; + + if (device_property_read_u32(dev, "aux-voltage-chargeable", + &chargeable)) + return 0; + + if (device_property_read_u32(dev, "trickle-resistor-ohms", &ohms)) + return 0; + + if (device_property_read_string(dev, "adi,tc-diode", &diode)) + return 0; + + if (!strcmp(diode, "schottky")) + trickle_cfg = MAX31335_TRICKLE_SCHOTTKY_DIODE; + else if (!strcmp(diode, "standard+schottky")) + trickle_cfg = MAX31335_TRICKLE_STANDARD_DIODE; + else + return dev_err_probe(dev, -EINVAL, + "Invalid tc-diode value: %s\n", diode); + + for (i = 0; i < ARRAY_SIZE(max31335_trickle_resistors); i++) + if (ohms == max31335_trickle_resistors[i]) + break; + + if (i >= ARRAY_SIZE(max31335_trickle_resistors)) + return 0; + + i = i + trickle_cfg; + + return regmap_write(max31335->regmap, MAX31335_TRICKLE_REG, + FIELD_PREP(MAX31335_TRICKLE_REG_TRICKLE, i) | + FIELD_PREP(MAX31335_TRICKLE_REG_EN_TRICKLE, + chargeable)); +} + +static unsigned long max31335_clkout_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct max31335_data *max31335 = clk_hw_to_max31335(hw); + unsigned int freq_mask; + unsigned int reg; + int ret; + + ret = regmap_read(max31335->regmap, MAX31335_RTC_CONFIG2, ®); + if (ret) + return 0; + + freq_mask = __roundup_pow_of_two(ARRAY_SIZE(max31335_clkout_freq)) - 1; + + return max31335_clkout_freq[reg & freq_mask]; +} + +static long max31335_clkout_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate) +{ + int index; + + index = find_closest(rate, max31335_clkout_freq, + ARRAY_SIZE(max31335_clkout_freq)); + + return max31335_clkout_freq[index]; +} + +static int max31335_clkout_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct max31335_data *max31335 = clk_hw_to_max31335(hw); + unsigned int freq_mask; + int index; + + index = find_closest(rate, max31335_clkout_freq, + ARRAY_SIZE(max31335_clkout_freq)); + freq_mask = __roundup_pow_of_two(ARRAY_SIZE(max31335_clkout_freq)) - 1; + + return regmap_update_bits(max31335->regmap, MAX31335_RTC_CONFIG2, + freq_mask, index); +} + +static int max31335_clkout_enable(struct clk_hw *hw) +{ + struct max31335_data *max31335 = clk_hw_to_max31335(hw); + + return regmap_set_bits(max31335->regmap, MAX31335_RTC_CONFIG2, + MAX31335_RTC_CONFIG2_ENCLKO); +} + +static void max31335_clkout_disable(struct clk_hw *hw) +{ + struct max31335_data *max31335 = clk_hw_to_max31335(hw); + + regmap_clear_bits(max31335->regmap, MAX31335_RTC_CONFIG2, + MAX31335_RTC_CONFIG2_ENCLKO); +} + +static int max31335_clkout_is_enabled(struct clk_hw *hw) +{ + struct max31335_data *max31335 = clk_hw_to_max31335(hw); + unsigned int reg; + int ret; + + ret = regmap_read(max31335->regmap, MAX31335_RTC_CONFIG2, ®); + if (ret) + return ret; + + return !!(reg & MAX31335_RTC_CONFIG2_ENCLKO); +} + +static const struct clk_ops max31335_clkout_ops = { + .recalc_rate = max31335_clkout_recalc_rate, + .round_rate = max31335_clkout_round_rate, + .set_rate = max31335_clkout_set_rate, + .enable = max31335_clkout_enable, + .disable = max31335_clkout_disable, + .is_enabled = max31335_clkout_is_enabled, +}; + +static struct clk_init_data max31335_clk_init = { + .name = "max31335-clkout", + .ops = &max31335_clkout_ops, +}; + +static int max31335_nvmem_reg_read(void *priv, unsigned int offset, + void *val, size_t bytes) +{ + struct max31335_data *max31335 = priv; + unsigned int reg = MAX31335_TS0_SEC_1_128 + offset; + + return regmap_bulk_read(max31335->regmap, reg, val, bytes); +} + +static int max31335_nvmem_reg_write(void *priv, unsigned int offset, + void *val, size_t bytes) +{ + struct max31335_data *max31335 = priv; + unsigned int reg = MAX31335_TS0_SEC_1_128 + offset; + + return regmap_bulk_write(max31335->regmap, reg, val, bytes); +} + +static struct nvmem_config max31335_nvmem_cfg = { + .reg_read = max31335_nvmem_reg_read, + .reg_write = max31335_nvmem_reg_write, + .word_size = 8, + .size = MAX31335_RAM_SIZE, +}; + +#if IS_REACHABLE(HWMON) +static int max31335_read_temp(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long *val) +{ + struct max31335_data *max31335 = dev_get_drvdata(dev); + u8 reg[2]; + s16 temp; + int ret; + + if (type != hwmon_temp || attr != hwmon_temp_input) + return -EOPNOTSUPP; + + ret = regmap_bulk_read(max31335->regmap, MAX31335_TEMP_DATA_MSB, + reg, 2); + if (ret) + return ret; + + temp = get_unaligned_be16(reg); + + *val = (temp / 64) * 250; + + return 0; +} + +static umode_t max31335_is_visible(const void *data, + enum hwmon_sensor_types type, + u32 attr, int channel) +{ + if (type == hwmon_temp && attr == hwmon_temp_input) + return 0444; + + return 0; +} + +static const struct hwmon_channel_info *max31335_info[] = { + HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT), + NULL +}; + +static const struct hwmon_ops max31335_hwmon_ops = { + .is_visible = max31335_is_visible, + .read = max31335_read_temp, +}; + +static const struct hwmon_chip_info max31335_chip_info = { + .ops = &max31335_hwmon_ops, + .info = max31335_info, +}; +#endif + +static int max31335_clkout_register(struct device *dev) +{ + struct max31335_data *max31335 = dev_get_drvdata(dev); + int ret; + + if (!device_property_present(dev, "#clock-cells")) + return regmap_clear_bits(max31335->regmap, MAX31335_RTC_CONFIG2, + MAX31335_RTC_CONFIG2_ENCLKO); + + max31335->clkout.init = &max31335_clk_init; + + ret = devm_clk_hw_register(dev, &max31335->clkout); + if (ret) + return dev_err_probe(dev, ret, "cannot register clock\n"); + + ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, + &max31335->clkout); + if (ret) + return dev_err_probe(dev, ret, "cannot add hw provider\n"); + + max31335->clkout.clk = devm_clk_get_enabled(dev, NULL); + if (IS_ERR(max31335->clkout.clk)) + return dev_err_probe(dev, PTR_ERR(max31335->clkout.clk), + "cannot enable clkout\n"); + + return 0; +} + +static int max31335_probe(struct i2c_client *client) +{ + struct max31335_data *max31335; +#if IS_REACHABLE(HWMON) + struct device *hwmon; +#endif + int ret; + + max31335 = devm_kzalloc(&client->dev, sizeof(*max31335), GFP_KERNEL); + if (!max31335) + return -ENOMEM; + + max31335->regmap = devm_regmap_init_i2c(client, ®map_config); + if (IS_ERR(max31335->regmap)) + return PTR_ERR(max31335->regmap); + + i2c_set_clientdata(client, max31335); + + max31335->rtc = devm_rtc_allocate_device(&client->dev); + if (IS_ERR(max31335->rtc)) + return PTR_ERR(max31335->rtc); + + max31335->rtc->ops = &max31335_rtc_ops; + max31335->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; + max31335->rtc->range_max = RTC_TIMESTAMP_END_2199; + max31335->rtc->alarm_offset_max = 24 * 60 * 60; + + ret = max31335_clkout_register(&client->dev); + if (ret) + return ret; + + if (client->irq > 0) { + ret = devm_request_threaded_irq(&client->dev, client->irq, + NULL, max31335_handle_irq, + IRQF_ONESHOT, + "max31335", max31335); + if (ret) { + dev_warn(&client->dev, + "unable to request IRQ, alarm max31335 disabled\n"); + client->irq = 0; + } + } + + if (!client->irq) + clear_bit(RTC_FEATURE_ALARM, max31335->rtc->features); + + max31335_nvmem_cfg.priv = max31335; + ret = devm_rtc_nvmem_register(max31335->rtc, &max31335_nvmem_cfg); + if (ret) + return dev_err_probe(&client->dev, ret, + "cannot register rtc nvmem\n"); + +#if IS_REACHABLE(HWMON) + hwmon = devm_hwmon_device_register_with_info(&client->dev, client->name, + max31335, + &max31335_chip_info, + NULL); + if (IS_ERR(hwmon)) + return dev_err_probe(&client->dev, PTR_ERR(hwmon), + "cannot register hwmon device\n"); +#endif + + ret = max31335_trickle_charger_setup(&client->dev, max31335); + if (ret) + return ret; + + return devm_rtc_register_device(max31335->rtc); +} + +static const struct i2c_device_id max31335_id[] = { + { "max31335", 0 }, + { } +}; + +MODULE_DEVICE_TABLE(i2c, max31335_id); + +static const struct of_device_id max31335_of_match[] = { + { .compatible = "adi,max31335" }, + { } +}; + +MODULE_DEVICE_TABLE(of, max31335_of_match); + +static struct i2c_driver max31335_driver = { + .driver = { + .name = "rtc-max31335", + .of_match_table = max31335_of_match, + }, + .probe = max31335_probe, + .id_table = max31335_id, +}; +module_i2c_driver(max31335_driver); + +MODULE_AUTHOR("Antoniu Miclaus <antoniu.miclaus@analog.com>"); +MODULE_DESCRIPTION("MAX31335 RTC driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/rtc/rtc-mc146818-lib.c b/drivers/rtc/rtc-mc146818-lib.c index f1c09f1db044..651bf3c279c7 100644 --- a/drivers/rtc/rtc-mc146818-lib.c +++ b/drivers/rtc/rtc-mc146818-lib.c @@ -8,26 +8,31 @@ #include <linux/acpi.h> #endif +#define UIP_RECHECK_DELAY 100 /* usec */ +#define UIP_RECHECK_DELAY_MS (USEC_PER_MSEC / UIP_RECHECK_DELAY) +#define UIP_RECHECK_LOOPS_MS(x) (x / UIP_RECHECK_DELAY_MS) + /* * Execute a function while the UIP (Update-in-progress) bit of the RTC is - * unset. + * unset. The timeout is configurable by the caller in ms. * * Warning: callback may be executed more then once. */ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param), + int timeout, void *param) { int i; unsigned long flags; unsigned char seconds; - for (i = 0; i < 100; i++) { + for (i = 0; UIP_RECHECK_LOOPS_MS(i) < timeout; i++) { spin_lock_irqsave(&rtc_lock, flags); /* * Check whether there is an update in progress during which the * readout is unspecified. The maximum update time is ~2ms. Poll - * every 100 usec for completion. + * for completion. * * Store the second value before checking UIP so a long lasting * NMI which happens to hit after the UIP check cannot make @@ -37,7 +42,7 @@ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param), if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) { spin_unlock_irqrestore(&rtc_lock, flags); - udelay(100); + udelay(UIP_RECHECK_DELAY); continue; } @@ -56,7 +61,7 @@ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param), */ if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) { spin_unlock_irqrestore(&rtc_lock, flags); - udelay(100); + udelay(UIP_RECHECK_DELAY); continue; } @@ -72,6 +77,10 @@ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param), } spin_unlock_irqrestore(&rtc_lock, flags); + if (UIP_RECHECK_LOOPS_MS(i) >= 100) + pr_warn("Reading current time from RTC took around %li ms\n", + UIP_RECHECK_LOOPS_MS(i)); + return true; } return false; @@ -84,7 +93,7 @@ EXPORT_SYMBOL_GPL(mc146818_avoid_UIP); */ bool mc146818_does_rtc_work(void) { - return mc146818_avoid_UIP(NULL, NULL); + return mc146818_avoid_UIP(NULL, 1000, NULL); } EXPORT_SYMBOL_GPL(mc146818_does_rtc_work); @@ -130,15 +139,27 @@ static void mc146818_get_time_callback(unsigned char seconds, void *param_in) p->ctrl = CMOS_READ(RTC_CONTROL); } -int mc146818_get_time(struct rtc_time *time) +/** + * mc146818_get_time - Get the current time from the RTC + * @time: pointer to struct rtc_time to store the current time + * @timeout: timeout value in ms + * + * This function reads the current time from the RTC and stores it in the + * provided struct rtc_time. The timeout parameter specifies the maximum + * time to wait for the RTC to become ready. + * + * Return: 0 on success, -ETIMEDOUT if the RTC did not become ready within + * the specified timeout, or another error code if an error occurred. + */ +int mc146818_get_time(struct rtc_time *time, int timeout) { struct mc146818_get_time_callback_param p = { .time = time }; - if (!mc146818_avoid_UIP(mc146818_get_time_callback, &p)) { + if (!mc146818_avoid_UIP(mc146818_get_time_callback, timeout, &p)) { memset(time, 0, sizeof(*time)); - return -EIO; + return -ETIMEDOUT; } if (!(p.ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) diff --git a/drivers/rtc/rtc-nct3018y.c b/drivers/rtc/rtc-nct3018y.c index ed4e606be8e5..f488a189a465 100644 --- a/drivers/rtc/rtc-nct3018y.c +++ b/drivers/rtc/rtc-nct3018y.c @@ -23,6 +23,7 @@ #define NCT3018Y_REG_CTRL 0x0A /* timer control */ #define NCT3018Y_REG_ST 0x0B /* status */ #define NCT3018Y_REG_CLKO 0x0C /* clock out */ +#define NCT3018Y_REG_PART 0x21 /* part info */ #define NCT3018Y_BIT_AF BIT(7) #define NCT3018Y_BIT_ST BIT(7) @@ -37,10 +38,12 @@ #define NCT3018Y_REG_BAT_MASK 0x07 #define NCT3018Y_REG_CLKO_F_MASK 0x03 /* frequenc mask */ #define NCT3018Y_REG_CLKO_CKE 0x80 /* clock out enabled */ +#define NCT3018Y_REG_PART_NCT3018Y 0x02 struct nct3018y { struct rtc_device *rtc; struct i2c_client *client; + int part_num; #ifdef CONFIG_COMMON_CLK struct clk_hw clkout_hw; #endif @@ -177,8 +180,27 @@ static int nct3018y_rtc_read_time(struct device *dev, struct rtc_time *tm) static int nct3018y_rtc_set_time(struct device *dev, struct rtc_time *tm) { struct i2c_client *client = to_i2c_client(dev); + struct nct3018y *nct3018y = dev_get_drvdata(dev); unsigned char buf[4] = {0}; - int err; + int err, flags; + int restore_flags = 0; + + flags = i2c_smbus_read_byte_data(client, NCT3018Y_REG_CTRL); + if (flags < 0) { + dev_dbg(&client->dev, "Failed to read NCT3018Y_REG_CTRL.\n"); + return flags; + } + + /* Check and set TWO bit */ + if (nct3018y->part_num == NCT3018Y_REG_PART_NCT3018Y && !(flags & NCT3018Y_BIT_TWO)) { + restore_flags = 1; + flags |= NCT3018Y_BIT_TWO; + err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_CTRL, flags); + if (err < 0) { + dev_dbg(&client->dev, "Unable to write NCT3018Y_REG_CTRL.\n"); + return err; + } + } buf[0] = bin2bcd(tm->tm_sec); err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_SC, buf[0]); @@ -212,6 +234,18 @@ static int nct3018y_rtc_set_time(struct device *dev, struct rtc_time *tm) return -EIO; } + /* Restore TWO bit */ + if (restore_flags) { + if (nct3018y->part_num == NCT3018Y_REG_PART_NCT3018Y) + flags &= ~NCT3018Y_BIT_TWO; + + err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_CTRL, flags); + if (err < 0) { + dev_dbg(&client->dev, "Unable to write NCT3018Y_REG_CTRL.\n"); + return err; + } + } + return err; } @@ -479,11 +513,17 @@ static int nct3018y_probe(struct i2c_client *client) dev_dbg(&client->dev, "%s: NCT3018Y_BIT_TWO is set\n", __func__); } - flags = NCT3018Y_BIT_TWO; - err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_CTRL, flags); - if (err < 0) { - dev_dbg(&client->dev, "Unable to write NCT3018Y_REG_CTRL\n"); - return err; + nct3018y->part_num = i2c_smbus_read_byte_data(client, NCT3018Y_REG_PART); + if (nct3018y->part_num < 0) { + dev_dbg(&client->dev, "Failed to read NCT3018Y_REG_PART.\n"); + return nct3018y->part_num; + } else if (nct3018y->part_num == NCT3018Y_REG_PART_NCT3018Y) { + flags = NCT3018Y_BIT_HF; + err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_CTRL, flags); + if (err < 0) { + dev_dbg(&client->dev, "Unable to write NCT3018Y_REG_CTRL.\n"); + return err; + } } flags = 0; diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c index 1a3ec1bb5b81..1327251e527c 100644 --- a/drivers/rtc/rtc-rv8803.c +++ b/drivers/rtc/rtc-rv8803.c @@ -17,6 +17,7 @@ #include <linux/module.h> #include <linux/of.h> #include <linux/rtc.h> +#include <linux/pm_wakeirq.h> #define RV8803_I2C_TRY_COUNT 4 @@ -607,6 +608,28 @@ static int rv8803_regs_configure(struct rv8803_data *rv8803) return 0; } +static int rv8803_resume(struct device *dev) +{ + struct rv8803_data *rv8803 = dev_get_drvdata(dev); + + if (rv8803->client->irq > 0 && device_may_wakeup(dev)) + disable_irq_wake(rv8803->client->irq); + + return 0; +} + +static int rv8803_suspend(struct device *dev) +{ + struct rv8803_data *rv8803 = dev_get_drvdata(dev); + + if (rv8803->client->irq > 0 && device_may_wakeup(dev)) + enable_irq_wake(rv8803->client->irq); + + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(rv8803_pm_ops, rv8803_suspend, rv8803_resume); + static const struct i2c_device_id rv8803_id[] = { { "rv8803", rv_8803 }, { "rv8804", rx_8804 }, @@ -683,10 +706,18 @@ static int rv8803_probe(struct i2c_client *client) if (err) { dev_warn(&client->dev, "unable to request IRQ, alarms disabled\n"); client->irq = 0; + } else { + device_init_wakeup(&client->dev, true); + err = dev_pm_set_wake_irq(&client->dev, client->irq); + if (err) + dev_err(&client->dev, "failed to set wake IRQ\n"); } + } else { + if (device_property_read_bool(&client->dev, "wakeup-source")) + device_init_wakeup(&client->dev, true); + else + clear_bit(RTC_FEATURE_ALARM, rv8803->rtc->features); } - if (!client->irq) - clear_bit(RTC_FEATURE_ALARM, rv8803->rtc->features); if (of_property_read_bool(client->dev.of_node, "epson,vdet-disable")) rv8803->backup |= RX8900_FLAG_VDETOFF; @@ -737,6 +768,7 @@ static struct i2c_driver rv8803_driver = { .driver = { .name = "rtc-rv8803", .of_match_table = of_match_ptr(rv8803_of_match), + .pm = &rv8803_pm_ops, }, .probe = rv8803_probe, .id_table = rv8803_id, diff --git a/drivers/rtc/rtc-tps6594.c b/drivers/rtc/rtc-tps6594.c new file mode 100644 index 000000000000..838ae8562a35 --- /dev/null +++ b/drivers/rtc/rtc-tps6594.c @@ -0,0 +1,454 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * RTC driver for tps6594 PMIC + * + * Copyright (C) 2023 BayLibre Incorporated - https://www.baylibre.com/ + */ + +#include <linux/bcd.h> +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/limits.h> +#include <linux/math64.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/mod_devicetable.h> +#include <linux/property.h> +#include <linux/rtc.h> +#include <linux/types.h> +#include <linux/units.h> + +#include <linux/mfd/tps6594.h> + +// Total number of RTC registers needed to set time +#define NUM_TIME_REGS (TPS6594_REG_RTC_WEEKS - TPS6594_REG_RTC_SECONDS + 1) + +// Total number of RTC alarm registers +#define NUM_TIME_ALARM_REGS (NUM_TIME_REGS - 1) + +/* + * Min and max values supported by 'offset' interface (swapped sign). + * After conversion, the values do not exceed the range [-32767, 33767] + * which COMP_REG must conform to. + */ +#define MIN_OFFSET (-277774) +#define MAX_OFFSET (277774) + +// Number of ticks per hour +#define TICKS_PER_HOUR (32768 * 3600) + +// Multiplier for ppb conversions +#define PPB_MULT NANO + +static int tps6594_rtc_alarm_irq_enable(struct device *dev, + unsigned int enabled) +{ + struct tps6594 *tps = dev_get_drvdata(dev->parent); + u8 val; + + val = enabled ? TPS6594_BIT_IT_ALARM : 0; + + return regmap_update_bits(tps->regmap, TPS6594_REG_RTC_INTERRUPTS, + TPS6594_BIT_IT_ALARM, val); +} + +/* Pulse GET_TIME field of RTC_CTRL_1 to store a timestamp in shadow registers. */ +static int tps6594_rtc_shadow_timestamp(struct device *dev, struct tps6594 *tps) +{ + int ret; + + /* + * Set GET_TIME to 0. Next time we set GET_TIME to 1 we will be sure to store + * an up-to-date timestamp. + */ + ret = regmap_clear_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1, + TPS6594_BIT_GET_TIME); + if (ret < 0) + return ret; + + /* + * Copy content of RTC registers to shadow registers or latches to read + * a coherent timestamp. + */ + return regmap_set_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1, + TPS6594_BIT_GET_TIME); +} + +static int tps6594_rtc_read_time(struct device *dev, struct rtc_time *tm) +{ + unsigned char rtc_data[NUM_TIME_REGS]; + struct tps6594 *tps = dev_get_drvdata(dev->parent); + int ret; + + // Check if RTC is running. + ret = regmap_test_bits(tps->regmap, TPS6594_REG_RTC_STATUS, + TPS6594_BIT_RUN); + if (ret < 0) + return ret; + if (ret == 0) + return -EINVAL; + + ret = tps6594_rtc_shadow_timestamp(dev, tps); + if (ret < 0) + return ret; + + // Read shadowed RTC registers. + ret = regmap_bulk_read(tps->regmap, TPS6594_REG_RTC_SECONDS, rtc_data, + NUM_TIME_REGS); + if (ret < 0) + return ret; + + tm->tm_sec = bcd2bin(rtc_data[0]); + tm->tm_min = bcd2bin(rtc_data[1]); + tm->tm_hour = bcd2bin(rtc_data[2]); + tm->tm_mday = bcd2bin(rtc_data[3]); + tm->tm_mon = bcd2bin(rtc_data[4]) - 1; + tm->tm_year = bcd2bin(rtc_data[5]) + 100; + tm->tm_wday = bcd2bin(rtc_data[6]); + + return 0; +} + +static int tps6594_rtc_set_time(struct device *dev, struct rtc_time *tm) +{ + unsigned char rtc_data[NUM_TIME_REGS]; + struct tps6594 *tps = dev_get_drvdata(dev->parent); + int ret; + + rtc_data[0] = bin2bcd(tm->tm_sec); + rtc_data[1] = bin2bcd(tm->tm_min); + rtc_data[2] = bin2bcd(tm->tm_hour); + rtc_data[3] = bin2bcd(tm->tm_mday); + rtc_data[4] = bin2bcd(tm->tm_mon + 1); + rtc_data[5] = bin2bcd(tm->tm_year - 100); + rtc_data[6] = bin2bcd(tm->tm_wday); + + // Stop RTC while updating the RTC time registers. + ret = regmap_clear_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1, + TPS6594_BIT_STOP_RTC); + if (ret < 0) + return ret; + + // Update all the time registers in one shot. + ret = regmap_bulk_write(tps->regmap, TPS6594_REG_RTC_SECONDS, rtc_data, + NUM_TIME_REGS); + if (ret < 0) + return ret; + + // Start back RTC. + return regmap_set_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1, + TPS6594_BIT_STOP_RTC); +} + +static int tps6594_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alm) +{ + unsigned char alarm_data[NUM_TIME_ALARM_REGS]; + u32 int_val; + struct tps6594 *tps = dev_get_drvdata(dev->parent); + int ret; + + ret = regmap_bulk_read(tps->regmap, TPS6594_REG_ALARM_SECONDS, + alarm_data, NUM_TIME_ALARM_REGS); + if (ret < 0) + return ret; + + alm->time.tm_sec = bcd2bin(alarm_data[0]); + alm->time.tm_min = bcd2bin(alarm_data[1]); + alm->time.tm_hour = bcd2bin(alarm_data[2]); + alm->time.tm_mday = bcd2bin(alarm_data[3]); + alm->time.tm_mon = bcd2bin(alarm_data[4]) - 1; + alm->time.tm_year = bcd2bin(alarm_data[5]) + 100; + + ret = regmap_read(tps->regmap, TPS6594_REG_RTC_INTERRUPTS, &int_val); + if (ret < 0) + return ret; + + alm->enabled = int_val & TPS6594_BIT_IT_ALARM; + + return 0; +} + +static int tps6594_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm) +{ + unsigned char alarm_data[NUM_TIME_ALARM_REGS]; + struct tps6594 *tps = dev_get_drvdata(dev->parent); + int ret; + + // Disable alarm irq before changing the alarm timestamp. + ret = tps6594_rtc_alarm_irq_enable(dev, 0); + if (ret) + return ret; + + alarm_data[0] = bin2bcd(alm->time.tm_sec); + alarm_data[1] = bin2bcd(alm->time.tm_min); + alarm_data[2] = bin2bcd(alm->time.tm_hour); + alarm_data[3] = bin2bcd(alm->time.tm_mday); + alarm_data[4] = bin2bcd(alm->time.tm_mon + 1); + alarm_data[5] = bin2bcd(alm->time.tm_year - 100); + + // Update all the alarm registers in one shot. + ret = regmap_bulk_write(tps->regmap, TPS6594_REG_ALARM_SECONDS, + alarm_data, NUM_TIME_ALARM_REGS); + if (ret < 0) + return ret; + + if (alm->enabled) + ret = tps6594_rtc_alarm_irq_enable(dev, 1); + + return ret; +} + +static int tps6594_rtc_set_calibration(struct device *dev, int calibration) +{ + struct tps6594 *tps = dev_get_drvdata(dev->parent); + __le16 value; + int ret; + + /* + * TPS6594 uses two's complement 16 bit value for compensation of RTC + * crystal inaccuracies. One time every hour when seconds counter + * increments from 0 to 1 compensation value will be added to internal + * RTC counter value. + * + * Valid range for compensation value: [-32767 .. 32767]. + */ + if (calibration < S16_MIN + 1 || calibration > S16_MAX) + return -ERANGE; + + value = cpu_to_le16(calibration); + + // Update all the compensation registers in one shot. + ret = regmap_bulk_write(tps->regmap, TPS6594_REG_RTC_COMP_LSB, &value, + sizeof(value)); + if (ret < 0) + return ret; + + // Enable automatic compensation. + return regmap_set_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1, + TPS6594_BIT_AUTO_COMP); +} + +static int tps6594_rtc_get_calibration(struct device *dev, int *calibration) +{ + struct tps6594 *tps = dev_get_drvdata(dev->parent); + unsigned int ctrl; + __le16 value; + int ret; + + ret = regmap_read(tps->regmap, TPS6594_REG_RTC_CTRL_1, &ctrl); + if (ret < 0) + return ret; + + // If automatic compensation is not enabled report back zero. + if (!(ctrl & TPS6594_BIT_AUTO_COMP)) { + *calibration = 0; + return 0; + } + + ret = regmap_bulk_read(tps->regmap, TPS6594_REG_RTC_COMP_LSB, &value, + sizeof(value)); + if (ret < 0) + return ret; + + *calibration = le16_to_cpu(value); + + return 0; +} + +static int tps6594_rtc_read_offset(struct device *dev, long *offset) +{ + int calibration; + s64 tmp; + int ret; + + ret = tps6594_rtc_get_calibration(dev, &calibration); + if (ret < 0) + return ret; + + // Convert from RTC calibration register format to ppb format. + tmp = calibration * PPB_MULT; + + if (tmp < 0) + tmp -= TICKS_PER_HOUR / 2LL; + else + tmp += TICKS_PER_HOUR / 2LL; + tmp = div_s64(tmp, TICKS_PER_HOUR); + + /* + * SAFETY: + * Computatiion is the reverse operation of the one done in + * `tps6594_rtc_set_offset`. The safety remarks applie here too. + */ + + /* + * Offset value operates in negative way, so swap sign. + * See 8.3.10.5, (32768 - COMP_REG). + */ + *offset = (long)-tmp; + + return 0; +} + +static int tps6594_rtc_set_offset(struct device *dev, long offset) +{ + int calibration; + s64 tmp; + + // Make sure offset value is within supported range. + if (offset < MIN_OFFSET || offset > MAX_OFFSET) + return -ERANGE; + + // Convert from ppb format to RTC calibration register format. + + tmp = offset * TICKS_PER_HOUR; + if (tmp < 0) + tmp -= PPB_MULT / 2LL; + else + tmp += PPB_MULT / 2LL; + tmp = div_s64(tmp, PPB_MULT); + + /* + * SAFETY: + * - tmp = offset * TICK_PER_HOUR : + * `offset` can't be more than 277774, so `tmp` can't exceed 277774000000000 + * which is lower than the maximum value in an `s64` (2^63-1). No overflow here. + * + * - tmp += TICK_PER_HOUR / 2LL : + * tmp will have a maximum value of 277774117964800 which is still inferior to 2^63-1. + */ + + // Offset value operates in negative way, so swap sign. + calibration = (int)-tmp; + + return tps6594_rtc_set_calibration(dev, calibration); +} + +static irqreturn_t tps6594_rtc_interrupt(int irq, void *rtc) +{ + struct device *dev = rtc; + struct tps6594 *tps = dev_get_drvdata(dev->parent); + struct rtc_device *rtc_dev = dev_get_drvdata(dev); + int ret; + u32 rtc_reg; + + ret = regmap_read(tps->regmap, TPS6594_REG_RTC_STATUS, &rtc_reg); + if (ret) + return IRQ_NONE; + + rtc_update_irq(rtc_dev, 1, RTC_IRQF | RTC_AF); + + return IRQ_HANDLED; +} + +static const struct rtc_class_ops tps6594_rtc_ops = { + .read_time = tps6594_rtc_read_time, + .set_time = tps6594_rtc_set_time, + .read_alarm = tps6594_rtc_read_alarm, + .set_alarm = tps6594_rtc_set_alarm, + .alarm_irq_enable = tps6594_rtc_alarm_irq_enable, + .read_offset = tps6594_rtc_read_offset, + .set_offset = tps6594_rtc_set_offset, +}; + +static int tps6594_rtc_probe(struct platform_device *pdev) +{ + struct tps6594 *tps = dev_get_drvdata(pdev->dev.parent); + struct device *dev = &pdev->dev; + struct rtc_device *rtc; + int irq; + int ret; + + rtc = devm_kzalloc(dev, sizeof(*rtc), GFP_KERNEL); + if (!rtc) + return -ENOMEM; + + rtc = devm_rtc_allocate_device(dev); + if (IS_ERR(rtc)) + return PTR_ERR(rtc); + + // Enable crystal oscillator. + ret = regmap_set_bits(tps->regmap, TPS6594_REG_RTC_CTRL_2, + TPS6594_BIT_XTAL_EN); + if (ret < 0) + return ret; + + ret = regmap_test_bits(tps->regmap, TPS6594_REG_RTC_STATUS, + TPS6594_BIT_RUN); + if (ret < 0) + return ret; + // RTC not running. + if (ret == 0) { + ret = regmap_set_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1, + TPS6594_BIT_STOP_RTC); + if (ret < 0) + return ret; + + /* + * On some boards, a 40 ms delay is needed before BIT_RUN is set. + * 80 ms should provide sufficient margin. + */ + mdelay(80); + + /* + * RTC should be running now. Check if this is the case. + * If not it might be a missing oscillator. + */ + ret = regmap_test_bits(tps->regmap, TPS6594_REG_RTC_STATUS, + TPS6594_BIT_RUN); + if (ret < 0) + return ret; + if (ret == 0) + return -ENODEV; + + // Stop RTC until first call to `tps6594_rtc_set_time`. + ret = regmap_clear_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1, + TPS6594_BIT_STOP_RTC); + if (ret < 0) + return ret; + } + + platform_set_drvdata(pdev, rtc); + + irq = platform_get_irq_byname(pdev, TPS6594_IRQ_NAME_ALARM); + if (irq < 0) + return dev_err_probe(dev, irq, "Failed to get irq\n"); + + ret = devm_request_threaded_irq(dev, irq, NULL, tps6594_rtc_interrupt, + IRQF_ONESHOT, TPS6594_IRQ_NAME_ALARM, + dev); + if (ret < 0) + return dev_err_probe(dev, ret, + "Failed to request_threaded_irq\n"); + + ret = device_init_wakeup(dev, true); + if (ret < 0) + return dev_err_probe(dev, ret, + "Failed to init rtc as wakeup source\n"); + + rtc->ops = &tps6594_rtc_ops; + rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; + rtc->range_max = RTC_TIMESTAMP_END_2099; + + return devm_rtc_register_device(rtc); +} + +static const struct platform_device_id tps6594_rtc_id_table[] = { + { "tps6594-rtc", }, + {} +}; +MODULE_DEVICE_TABLE(platform, tps6594_rtc_id_table); + +static struct platform_driver tps6594_rtc_driver = { + .probe = tps6594_rtc_probe, + .driver = { + .name = "tps6594-rtc", + }, + .id_table = tps6594_rtc_id_table, +}; + +module_platform_driver(tps6594_rtc_driver); +MODULE_AUTHOR("Esteban Blanc <eblanc@baylibre.com>"); +MODULE_DESCRIPTION("TPS6594 RTC driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index acb710d3d7bc..983b3b16196c 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -32,7 +32,8 @@ #define AP_RESET_INTERVAL 20 /* Reset sleep interval (20ms) */ -static int vfio_ap_mdev_reset_queues(struct ap_queue_table *qtable); +static int vfio_ap_mdev_reset_queues(struct ap_matrix_mdev *matrix_mdev); +static int vfio_ap_mdev_reset_qlist(struct list_head *qlist); static struct vfio_ap_queue *vfio_ap_find_queue(int apqn); static const struct vfio_device_ops vfio_ap_matrix_dev_ops; static void vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q); @@ -665,17 +666,23 @@ static bool vfio_ap_mdev_filter_cdoms(struct ap_matrix_mdev *matrix_mdev) * device driver. * * @matrix_mdev: the matrix mdev whose matrix is to be filtered. + * @apm_filtered: a 256-bit bitmap for storing the APIDs filtered from the + * guest's AP configuration that are still in the host's AP + * configuration. * * Note: If an APQN referencing a queue device that is not bound to the vfio_ap * driver, its APID will be filtered from the guest's APCB. The matrix * structure precludes filtering an individual APQN, so its APID will be - * filtered. + * filtered. Consequently, all queues associated with the adapter that + * are in the host's AP configuration must be reset. If queues are + * subsequently made available again to the guest, they should re-appear + * in a reset state * * Return: a boolean value indicating whether the KVM guest's APCB was changed * by the filtering or not. */ -static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm, - struct ap_matrix_mdev *matrix_mdev) +static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev, + unsigned long *apm_filtered) { unsigned long apid, apqi, apqn; DECLARE_BITMAP(prev_shadow_apm, AP_DEVICES); @@ -685,6 +692,7 @@ static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm, bitmap_copy(prev_shadow_apm, matrix_mdev->shadow_apcb.apm, AP_DEVICES); bitmap_copy(prev_shadow_aqm, matrix_mdev->shadow_apcb.aqm, AP_DOMAINS); vfio_ap_matrix_init(&matrix_dev->info, &matrix_mdev->shadow_apcb); + bitmap_clear(apm_filtered, 0, AP_DEVICES); /* * Copy the adapters, domains and control domains to the shadow_apcb @@ -696,8 +704,9 @@ static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm, bitmap_and(matrix_mdev->shadow_apcb.aqm, matrix_mdev->matrix.aqm, (unsigned long *)matrix_dev->info.aqm, AP_DOMAINS); - for_each_set_bit_inv(apid, apm, AP_DEVICES) { - for_each_set_bit_inv(apqi, aqm, AP_DOMAINS) { + for_each_set_bit_inv(apid, matrix_mdev->shadow_apcb.apm, AP_DEVICES) { + for_each_set_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm, + AP_DOMAINS) { /* * If the APQN is not bound to the vfio_ap device * driver, then we can't assign it to the guest's @@ -709,8 +718,16 @@ static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm, apqn = AP_MKQID(apid, apqi); q = vfio_ap_mdev_get_queue(matrix_mdev, apqn); if (!q || q->reset_status.response_code) { - clear_bit_inv(apid, - matrix_mdev->shadow_apcb.apm); + clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm); + + /* + * If the adapter was previously plugged into + * the guest, let's let the caller know that + * the APID was filtered. + */ + if (test_bit_inv(apid, prev_shadow_apm)) + set_bit_inv(apid, apm_filtered); + break; } } @@ -812,7 +829,7 @@ static void vfio_ap_mdev_remove(struct mdev_device *mdev) mutex_lock(&matrix_dev->guests_lock); mutex_lock(&matrix_dev->mdevs_lock); - vfio_ap_mdev_reset_queues(&matrix_mdev->qtable); + vfio_ap_mdev_reset_queues(matrix_mdev); vfio_ap_mdev_unlink_fr_queues(matrix_mdev); list_del(&matrix_mdev->node); mutex_unlock(&matrix_dev->mdevs_lock); @@ -922,6 +939,47 @@ static void vfio_ap_mdev_link_adapter(struct ap_matrix_mdev *matrix_mdev, AP_MKQID(apid, apqi)); } +static void collect_queues_to_reset(struct ap_matrix_mdev *matrix_mdev, + unsigned long apid, + struct list_head *qlist) +{ + struct vfio_ap_queue *q; + unsigned long apqi; + + for_each_set_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm, AP_DOMAINS) { + q = vfio_ap_mdev_get_queue(matrix_mdev, AP_MKQID(apid, apqi)); + if (q) + list_add_tail(&q->reset_qnode, qlist); + } +} + +static void reset_queues_for_apid(struct ap_matrix_mdev *matrix_mdev, + unsigned long apid) +{ + struct list_head qlist; + + INIT_LIST_HEAD(&qlist); + collect_queues_to_reset(matrix_mdev, apid, &qlist); + vfio_ap_mdev_reset_qlist(&qlist); +} + +static int reset_queues_for_apids(struct ap_matrix_mdev *matrix_mdev, + unsigned long *apm_reset) +{ + struct list_head qlist; + unsigned long apid; + + if (bitmap_empty(apm_reset, AP_DEVICES)) + return 0; + + INIT_LIST_HEAD(&qlist); + + for_each_set_bit_inv(apid, apm_reset, AP_DEVICES) + collect_queues_to_reset(matrix_mdev, apid, &qlist); + + return vfio_ap_mdev_reset_qlist(&qlist); +} + /** * assign_adapter_store - parses the APID from @buf and sets the * corresponding bit in the mediated matrix device's APM @@ -962,7 +1020,7 @@ static ssize_t assign_adapter_store(struct device *dev, { int ret; unsigned long apid; - DECLARE_BITMAP(apm_delta, AP_DEVICES); + DECLARE_BITMAP(apm_filtered, AP_DEVICES); struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev); mutex_lock(&ap_perms_mutex); @@ -991,12 +1049,11 @@ static ssize_t assign_adapter_store(struct device *dev, } vfio_ap_mdev_link_adapter(matrix_mdev, apid); - memset(apm_delta, 0, sizeof(apm_delta)); - set_bit_inv(apid, apm_delta); - if (vfio_ap_mdev_filter_matrix(apm_delta, - matrix_mdev->matrix.aqm, matrix_mdev)) + if (vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered)) { vfio_ap_mdev_update_guest_apcb(matrix_mdev); + reset_queues_for_apids(matrix_mdev, apm_filtered); + } ret = count; done: @@ -1027,11 +1084,12 @@ static struct vfio_ap_queue * adapter was assigned. * @matrix_mdev: the matrix mediated device to which the adapter was assigned. * @apid: the APID of the unassigned adapter. - * @qtable: table for storing queues associated with unassigned adapter. + * @qlist: list for storing queues associated with unassigned adapter that + * need to be reset. */ static void vfio_ap_mdev_unlink_adapter(struct ap_matrix_mdev *matrix_mdev, unsigned long apid, - struct ap_queue_table *qtable) + struct list_head *qlist) { unsigned long apqi; struct vfio_ap_queue *q; @@ -1039,11 +1097,10 @@ static void vfio_ap_mdev_unlink_adapter(struct ap_matrix_mdev *matrix_mdev, for_each_set_bit_inv(apqi, matrix_mdev->matrix.aqm, AP_DOMAINS) { q = vfio_ap_unlink_apqn_fr_mdev(matrix_mdev, apid, apqi); - if (q && qtable) { + if (q && qlist) { if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) && test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) - hash_add(qtable->queues, &q->mdev_qnode, - q->apqn); + list_add_tail(&q->reset_qnode, qlist); } } } @@ -1051,26 +1108,23 @@ static void vfio_ap_mdev_unlink_adapter(struct ap_matrix_mdev *matrix_mdev, static void vfio_ap_mdev_hot_unplug_adapter(struct ap_matrix_mdev *matrix_mdev, unsigned long apid) { - int loop_cursor; - struct vfio_ap_queue *q; - struct ap_queue_table *qtable = kzalloc(sizeof(*qtable), GFP_KERNEL); + struct vfio_ap_queue *q, *tmpq; + struct list_head qlist; - hash_init(qtable->queues); - vfio_ap_mdev_unlink_adapter(matrix_mdev, apid, qtable); + INIT_LIST_HEAD(&qlist); + vfio_ap_mdev_unlink_adapter(matrix_mdev, apid, &qlist); if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm)) { clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm); vfio_ap_mdev_update_guest_apcb(matrix_mdev); } - vfio_ap_mdev_reset_queues(qtable); + vfio_ap_mdev_reset_qlist(&qlist); - hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) { + list_for_each_entry_safe(q, tmpq, &qlist, reset_qnode) { vfio_ap_unlink_mdev_fr_queue(q); - hash_del(&q->mdev_qnode); + list_del(&q->reset_qnode); } - - kfree(qtable); } /** @@ -1171,7 +1225,7 @@ static ssize_t assign_domain_store(struct device *dev, { int ret; unsigned long apqi; - DECLARE_BITMAP(aqm_delta, AP_DOMAINS); + DECLARE_BITMAP(apm_filtered, AP_DEVICES); struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev); mutex_lock(&ap_perms_mutex); @@ -1200,12 +1254,11 @@ static ssize_t assign_domain_store(struct device *dev, } vfio_ap_mdev_link_domain(matrix_mdev, apqi); - memset(aqm_delta, 0, sizeof(aqm_delta)); - set_bit_inv(apqi, aqm_delta); - if (vfio_ap_mdev_filter_matrix(matrix_mdev->matrix.apm, aqm_delta, - matrix_mdev)) + if (vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered)) { vfio_ap_mdev_update_guest_apcb(matrix_mdev); + reset_queues_for_apids(matrix_mdev, apm_filtered); + } ret = count; done: @@ -1218,7 +1271,7 @@ static DEVICE_ATTR_WO(assign_domain); static void vfio_ap_mdev_unlink_domain(struct ap_matrix_mdev *matrix_mdev, unsigned long apqi, - struct ap_queue_table *qtable) + struct list_head *qlist) { unsigned long apid; struct vfio_ap_queue *q; @@ -1226,11 +1279,10 @@ static void vfio_ap_mdev_unlink_domain(struct ap_matrix_mdev *matrix_mdev, for_each_set_bit_inv(apid, matrix_mdev->matrix.apm, AP_DEVICES) { q = vfio_ap_unlink_apqn_fr_mdev(matrix_mdev, apid, apqi); - if (q && qtable) { + if (q && qlist) { if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) && test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) - hash_add(qtable->queues, &q->mdev_qnode, - q->apqn); + list_add_tail(&q->reset_qnode, qlist); } } } @@ -1238,26 +1290,23 @@ static void vfio_ap_mdev_unlink_domain(struct ap_matrix_mdev *matrix_mdev, static void vfio_ap_mdev_hot_unplug_domain(struct ap_matrix_mdev *matrix_mdev, unsigned long apqi) { - int loop_cursor; - struct vfio_ap_queue *q; - struct ap_queue_table *qtable = kzalloc(sizeof(*qtable), GFP_KERNEL); + struct vfio_ap_queue *q, *tmpq; + struct list_head qlist; - hash_init(qtable->queues); - vfio_ap_mdev_unlink_domain(matrix_mdev, apqi, qtable); + INIT_LIST_HEAD(&qlist); + vfio_ap_mdev_unlink_domain(matrix_mdev, apqi, &qlist); if (test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) { clear_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm); vfio_ap_mdev_update_guest_apcb(matrix_mdev); } - vfio_ap_mdev_reset_queues(qtable); + vfio_ap_mdev_reset_qlist(&qlist); - hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) { + list_for_each_entry_safe(q, tmpq, &qlist, reset_qnode) { vfio_ap_unlink_mdev_fr_queue(q); - hash_del(&q->mdev_qnode); + list_del(&q->reset_qnode); } - - kfree(qtable); } /** @@ -1612,7 +1661,7 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev) get_update_locks_for_kvm(kvm); kvm_arch_crypto_clear_masks(kvm); - vfio_ap_mdev_reset_queues(&matrix_mdev->qtable); + vfio_ap_mdev_reset_queues(matrix_mdev); kvm_put_kvm(kvm); matrix_mdev->kvm = NULL; @@ -1748,15 +1797,33 @@ static void vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q) } } -static int vfio_ap_mdev_reset_queues(struct ap_queue_table *qtable) +static int vfio_ap_mdev_reset_queues(struct ap_matrix_mdev *matrix_mdev) { int ret = 0, loop_cursor; struct vfio_ap_queue *q; - hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) + hash_for_each(matrix_mdev->qtable.queues, loop_cursor, q, mdev_qnode) vfio_ap_mdev_reset_queue(q); - hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) { + hash_for_each(matrix_mdev->qtable.queues, loop_cursor, q, mdev_qnode) { + flush_work(&q->reset_work); + + if (q->reset_status.response_code) + ret = -EIO; + } + + return ret; +} + +static int vfio_ap_mdev_reset_qlist(struct list_head *qlist) +{ + int ret = 0; + struct vfio_ap_queue *q; + + list_for_each_entry(q, qlist, reset_qnode) + vfio_ap_mdev_reset_queue(q); + + list_for_each_entry(q, qlist, reset_qnode) { flush_work(&q->reset_work); if (q->reset_status.response_code) @@ -1942,7 +2009,7 @@ static ssize_t vfio_ap_mdev_ioctl(struct vfio_device *vdev, ret = vfio_ap_mdev_get_device_info(arg); break; case VFIO_DEVICE_RESET: - ret = vfio_ap_mdev_reset_queues(&matrix_mdev->qtable); + ret = vfio_ap_mdev_reset_queues(matrix_mdev); break; case VFIO_DEVICE_GET_IRQ_INFO: ret = vfio_ap_get_irq_info(arg); @@ -2088,6 +2155,7 @@ int vfio_ap_mdev_probe_queue(struct ap_device *apdev) { int ret; struct vfio_ap_queue *q; + DECLARE_BITMAP(apm_filtered, AP_DEVICES); struct ap_matrix_mdev *matrix_mdev; ret = sysfs_create_group(&apdev->device.kobj, &vfio_queue_attr_group); @@ -2109,15 +2177,28 @@ int vfio_ap_mdev_probe_queue(struct ap_device *apdev) if (matrix_mdev) { vfio_ap_mdev_link_queue(matrix_mdev, q); - if (vfio_ap_mdev_filter_matrix(matrix_mdev->matrix.apm, - matrix_mdev->matrix.aqm, - matrix_mdev)) + /* + * If we're in the process of handling the adding of adapters or + * domains to the host's AP configuration, then let the + * vfio_ap device driver's on_scan_complete callback filter the + * matrix and update the guest's AP configuration after all of + * the new queue devices are probed. + */ + if (!bitmap_empty(matrix_mdev->apm_add, AP_DEVICES) || + !bitmap_empty(matrix_mdev->aqm_add, AP_DOMAINS)) + goto done; + + if (vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered)) { vfio_ap_mdev_update_guest_apcb(matrix_mdev); + reset_queues_for_apids(matrix_mdev, apm_filtered); + } } + +done: dev_set_drvdata(&apdev->device, q); release_update_locks_for_mdev(matrix_mdev); - return 0; + return ret; err_remove_group: sysfs_remove_group(&apdev->device.kobj, &vfio_queue_attr_group); @@ -2134,26 +2215,40 @@ void vfio_ap_mdev_remove_queue(struct ap_device *apdev) q = dev_get_drvdata(&apdev->device); get_update_locks_for_queue(q); matrix_mdev = q->matrix_mdev; + apid = AP_QID_CARD(q->apqn); + apqi = AP_QID_QUEUE(q->apqn); if (matrix_mdev) { - vfio_ap_unlink_queue_fr_mdev(q); - - apid = AP_QID_CARD(q->apqn); - apqi = AP_QID_QUEUE(q->apqn); - - /* - * If the queue is assigned to the guest's APCB, then remove - * the adapter's APID from the APCB and hot it into the guest. - */ + /* If the queue is assigned to the guest's AP configuration */ if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) && test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) { + /* + * Since the queues are defined via a matrix of adapters + * and domains, it is not possible to hot unplug a + * single queue; so, let's unplug the adapter. + */ clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm); vfio_ap_mdev_update_guest_apcb(matrix_mdev); + reset_queues_for_apid(matrix_mdev, apid); + goto done; } } - vfio_ap_mdev_reset_queue(q); - flush_work(&q->reset_work); + /* + * If the queue is not in the host's AP configuration, then resetting + * it will fail with response code 01, (APQN not valid); so, let's make + * sure it is in the host's config. + */ + if (test_bit_inv(apid, (unsigned long *)matrix_dev->info.apm) && + test_bit_inv(apqi, (unsigned long *)matrix_dev->info.aqm)) { + vfio_ap_mdev_reset_queue(q); + flush_work(&q->reset_work); + } + +done: + if (matrix_mdev) + vfio_ap_unlink_queue_fr_mdev(q); + dev_set_drvdata(&apdev->device, NULL); kfree(q); release_update_locks_for_mdev(matrix_mdev); @@ -2461,39 +2556,30 @@ void vfio_ap_on_cfg_changed(struct ap_config_info *cur_cfg_info, static void vfio_ap_mdev_hot_plug_cfg(struct ap_matrix_mdev *matrix_mdev) { - bool do_hotplug = false; - int filter_domains = 0; - int filter_adapters = 0; - DECLARE_BITMAP(apm, AP_DEVICES); - DECLARE_BITMAP(aqm, AP_DOMAINS); + DECLARE_BITMAP(apm_filtered, AP_DEVICES); + bool filter_domains, filter_adapters, filter_cdoms, do_hotplug = false; mutex_lock(&matrix_mdev->kvm->lock); mutex_lock(&matrix_dev->mdevs_lock); - filter_adapters = bitmap_and(apm, matrix_mdev->matrix.apm, - matrix_mdev->apm_add, AP_DEVICES); - filter_domains = bitmap_and(aqm, matrix_mdev->matrix.aqm, - matrix_mdev->aqm_add, AP_DOMAINS); - - if (filter_adapters && filter_domains) - do_hotplug |= vfio_ap_mdev_filter_matrix(apm, aqm, matrix_mdev); - else if (filter_adapters) - do_hotplug |= - vfio_ap_mdev_filter_matrix(apm, - matrix_mdev->shadow_apcb.aqm, - matrix_mdev); - else - do_hotplug |= - vfio_ap_mdev_filter_matrix(matrix_mdev->shadow_apcb.apm, - aqm, matrix_mdev); + filter_adapters = bitmap_intersects(matrix_mdev->matrix.apm, + matrix_mdev->apm_add, AP_DEVICES); + filter_domains = bitmap_intersects(matrix_mdev->matrix.aqm, + matrix_mdev->aqm_add, AP_DOMAINS); + filter_cdoms = bitmap_intersects(matrix_mdev->matrix.adm, + matrix_mdev->adm_add, AP_DOMAINS); - if (bitmap_intersects(matrix_mdev->matrix.adm, matrix_mdev->adm_add, - AP_DOMAINS)) + if (filter_adapters || filter_domains) + do_hotplug = vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered); + + if (filter_cdoms) do_hotplug |= vfio_ap_mdev_filter_cdoms(matrix_mdev); if (do_hotplug) vfio_ap_mdev_update_guest_apcb(matrix_mdev); + reset_queues_for_apids(matrix_mdev, apm_filtered); + mutex_unlock(&matrix_dev->mdevs_lock); mutex_unlock(&matrix_mdev->kvm->lock); } diff --git a/drivers/s390/crypto/vfio_ap_private.h b/drivers/s390/crypto/vfio_ap_private.h index 88aff8b81f2f..98d37aa27044 100644 --- a/drivers/s390/crypto/vfio_ap_private.h +++ b/drivers/s390/crypto/vfio_ap_private.h @@ -133,6 +133,8 @@ struct ap_matrix_mdev { * @apqn: the APQN of the AP queue device * @saved_isc: the guest ISC registered with the GIB interface * @mdev_qnode: allows the vfio_ap_queue struct to be added to a hashtable + * @reset_qnode: allows the vfio_ap_queue struct to be added to a list of queues + * that need to be reset * @reset_status: the status from the last reset of the queue * @reset_work: work to wait for queue reset to complete */ @@ -143,6 +145,7 @@ struct vfio_ap_queue { #define VFIO_AP_ISC_INVALID 0xff unsigned char saved_isc; struct hlist_node mdev_qnode; + struct list_head reset_qnode; struct ap_queue_status reset_status; struct work_struct reset_work; }; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 03348f605c2e..dd674378f2f3 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -2889,7 +2889,7 @@ static void qla2x00_iocb_work_fn(struct work_struct *work) static void qla_trace_init(void) { - qla_trc_array = trace_array_get_by_name("qla2xxx"); + qla_trc_array = trace_array_get_by_name("qla2xxx", NULL); if (!qla_trc_array) { ql_log(ql_log_fatal, NULL, 0x0001, "Unable to create qla2xxx trace instance, instance logging will be disabled.\n"); diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 9d1bdcdc1331..4cf20be668a6 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -37,6 +37,11 @@ #define VIRTIO_SCSI_EVENT_LEN 8 #define VIRTIO_SCSI_VQ_BASE 2 +static unsigned int virtscsi_poll_queues; +module_param(virtscsi_poll_queues, uint, 0644); +MODULE_PARM_DESC(virtscsi_poll_queues, + "The number of dedicated virtqueues for polling I/O"); + /* Command queue element */ struct virtio_scsi_cmd { struct scsi_cmnd *sc; @@ -76,6 +81,7 @@ struct virtio_scsi { struct virtio_scsi_event_node event_list[VIRTIO_SCSI_EVENT_LEN]; u32 num_queues; + int io_queues[HCTX_MAX_TYPES]; struct hlist_node node; @@ -722,9 +728,49 @@ static int virtscsi_abort(struct scsi_cmnd *sc) static void virtscsi_map_queues(struct Scsi_Host *shost) { struct virtio_scsi *vscsi = shost_priv(shost); - struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; + int i, qoff; + + for (i = 0, qoff = 0; i < shost->nr_maps; i++) { + struct blk_mq_queue_map *map = &shost->tag_set.map[i]; + + map->nr_queues = vscsi->io_queues[i]; + map->queue_offset = qoff; + qoff += map->nr_queues; + + if (map->nr_queues == 0) + continue; + + /* + * Regular queues have interrupts and hence CPU affinity is + * defined by the core virtio code, but polling queues have + * no interrupts so we let the block layer assign CPU affinity. + */ + if (i == HCTX_TYPE_POLL) + blk_mq_map_queues(map); + else + blk_mq_virtio_map_queues(map, vscsi->vdev, 2); + } +} + +static int virtscsi_mq_poll(struct Scsi_Host *shost, unsigned int queue_num) +{ + struct virtio_scsi *vscsi = shost_priv(shost); + struct virtio_scsi_vq *virtscsi_vq = &vscsi->req_vqs[queue_num]; + unsigned long flags; + unsigned int len; + int found = 0; + void *buf; + + spin_lock_irqsave(&virtscsi_vq->vq_lock, flags); + + while ((buf = virtqueue_get_buf(virtscsi_vq->vq, &len)) != NULL) { + virtscsi_complete_cmd(vscsi, buf); + found++; + } + + spin_unlock_irqrestore(&virtscsi_vq->vq_lock, flags); - blk_mq_virtio_map_queues(qmap, vscsi->vdev, 2); + return found; } static void virtscsi_commit_rqs(struct Scsi_Host *shost, u16 hwq) @@ -751,6 +797,7 @@ static const struct scsi_host_template virtscsi_host_template = { .this_id = -1, .cmd_size = sizeof(struct virtio_scsi_cmd), .queuecommand = virtscsi_queuecommand, + .mq_poll = virtscsi_mq_poll, .commit_rqs = virtscsi_commit_rqs, .change_queue_depth = virtscsi_change_queue_depth, .eh_abort_handler = virtscsi_abort, @@ -795,13 +842,14 @@ static int virtscsi_init(struct virtio_device *vdev, { int err; u32 i; - u32 num_vqs; + u32 num_vqs, num_poll_vqs, num_req_vqs; vq_callback_t **callbacks; const char **names; struct virtqueue **vqs; struct irq_affinity desc = { .pre_vectors = 2 }; - num_vqs = vscsi->num_queues + VIRTIO_SCSI_VQ_BASE; + num_req_vqs = vscsi->num_queues; + num_vqs = num_req_vqs + VIRTIO_SCSI_VQ_BASE; vqs = kmalloc_array(num_vqs, sizeof(struct virtqueue *), GFP_KERNEL); callbacks = kmalloc_array(num_vqs, sizeof(vq_callback_t *), GFP_KERNEL); @@ -812,15 +860,31 @@ static int virtscsi_init(struct virtio_device *vdev, goto out; } + num_poll_vqs = min_t(unsigned int, virtscsi_poll_queues, + num_req_vqs - 1); + vscsi->io_queues[HCTX_TYPE_DEFAULT] = num_req_vqs - num_poll_vqs; + vscsi->io_queues[HCTX_TYPE_READ] = 0; + vscsi->io_queues[HCTX_TYPE_POLL] = num_poll_vqs; + + dev_info(&vdev->dev, "%d/%d/%d default/read/poll queues\n", + vscsi->io_queues[HCTX_TYPE_DEFAULT], + vscsi->io_queues[HCTX_TYPE_READ], + vscsi->io_queues[HCTX_TYPE_POLL]); + callbacks[0] = virtscsi_ctrl_done; callbacks[1] = virtscsi_event_done; names[0] = "control"; names[1] = "event"; - for (i = VIRTIO_SCSI_VQ_BASE; i < num_vqs; i++) { + for (i = VIRTIO_SCSI_VQ_BASE; i < num_vqs - num_poll_vqs; i++) { callbacks[i] = virtscsi_req_done; names[i] = "request"; } + for (; i < num_vqs; i++) { + callbacks[i] = NULL; + names[i] = "request_poll"; + } + /* Discover virtqueues and write information to configuration. */ err = virtio_find_vqs(vdev, num_vqs, vqs, callbacks, names, &desc); if (err) @@ -874,6 +938,7 @@ static int virtscsi_probe(struct virtio_device *vdev) sg_elems = virtscsi_config_get(vdev, seg_max) ?: 1; shost->sg_tablesize = sg_elems; + shost->nr_maps = 1; vscsi = shost_priv(shost); vscsi->vdev = vdev; vscsi->num_queues = num_queues; @@ -883,6 +948,9 @@ static int virtscsi_probe(struct virtio_device *vdev) if (err) goto virtscsi_init_failed; + if (vscsi->io_queues[HCTX_TYPE_POLL]) + shost->nr_maps = HCTX_TYPE_POLL + 1; + shost->can_queue = virtqueue_get_vring_size(vscsi->req_vqs[0].vq); cmd_per_lun = virtscsi_config_get(vdev, cmd_per_lun) ?: 1; diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c index 3a99f6dcdfaf..f54bb4dd2d10 100644 --- a/drivers/soundwire/amd_manager.c +++ b/drivers/soundwire/amd_manager.c @@ -927,6 +927,14 @@ static int amd_sdw_manager_probe(struct platform_device *pdev) amd_manager->bus.clk_stop_timeout = 200; amd_manager->bus.link_id = amd_manager->instance; + /* + * Due to BIOS compatibility, the two links are exposed within + * the scope of a single controller. If this changes, the + * controller_id will have to be updated with drv_data + * information. + */ + amd_manager->bus.controller_id = 0; + switch (amd_manager->instance) { case ACP_SDW0: amd_manager->num_dout_ports = AMD_SDW0_MAX_TX_PORTS; @@ -942,13 +950,13 @@ static int amd_sdw_manager_probe(struct platform_device *pdev) amd_manager->reg_mask = &sdw_manager_reg_mask_array[amd_manager->instance]; params = &amd_manager->bus.params; - params->max_dr_freq = AMD_SDW_DEFAULT_CLK_FREQ * 2; - params->curr_dr_freq = AMD_SDW_DEFAULT_CLK_FREQ * 2; + params->col = AMD_SDW_DEFAULT_COLUMNS; params->row = AMD_SDW_DEFAULT_ROWS; prop = &amd_manager->bus.prop; prop->clk_freq = &amd_sdw_freq_tbl[0]; prop->mclk_freq = AMD_SDW_BUS_BASE_FREQ; + prop->max_clk_freq = AMD_SDW_DEFAULT_CLK_FREQ; ret = sdw_bus_master_add(&amd_manager->bus, dev, dev->fwnode); if (ret) { diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index 41b0d9adf68e..f3fec15c3112 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -22,6 +22,10 @@ static int sdw_get_id(struct sdw_bus *bus) return rc; bus->id = rc; + + if (bus->controller_id == -1) + bus->controller_id = rc; + return 0; } diff --git a/drivers/soundwire/debugfs.c b/drivers/soundwire/debugfs.c index d1553cb77187..67abd7e52f09 100644 --- a/drivers/soundwire/debugfs.c +++ b/drivers/soundwire/debugfs.c @@ -20,7 +20,7 @@ void sdw_bus_debugfs_init(struct sdw_bus *bus) return; /* create the debugfs master-N */ - snprintf(name, sizeof(name), "master-%d-%d", bus->id, bus->link_id); + snprintf(name, sizeof(name), "master-%d-%d", bus->controller_id, bus->link_id); bus->debugfs = debugfs_create_dir(name, sdw_debugfs_root); } diff --git a/drivers/soundwire/generic_bandwidth_allocation.c b/drivers/soundwire/generic_bandwidth_allocation.c index 31162f2b5638..c70a63d009ae 100644 --- a/drivers/soundwire/generic_bandwidth_allocation.c +++ b/drivers/soundwire/generic_bandwidth_allocation.c @@ -333,7 +333,7 @@ static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq) */ static int sdw_compute_bus_params(struct sdw_bus *bus) { - unsigned int max_dr_freq, curr_dr_freq = 0; + unsigned int curr_dr_freq = 0; struct sdw_master_prop *mstr_prop = &bus->prop; int i, clk_values, ret; bool is_gear = false; @@ -351,14 +351,12 @@ static int sdw_compute_bus_params(struct sdw_bus *bus) clk_buf = NULL; } - max_dr_freq = mstr_prop->max_clk_freq * SDW_DOUBLE_RATE_FACTOR; - for (i = 0; i < clk_values; i++) { if (!clk_buf) - curr_dr_freq = max_dr_freq; + curr_dr_freq = bus->params.max_dr_freq; else curr_dr_freq = (is_gear) ? - (max_dr_freq >> clk_buf[i]) : + (bus->params.max_dr_freq >> clk_buf[i]) : clk_buf[i] * SDW_DOUBLE_RATE_FACTOR; if (curr_dr_freq <= bus->params.bandwidth) diff --git a/drivers/soundwire/intel_auxdevice.c b/drivers/soundwire/intel_auxdevice.c index 7f15e3549e53..93698532deac 100644 --- a/drivers/soundwire/intel_auxdevice.c +++ b/drivers/soundwire/intel_auxdevice.c @@ -234,6 +234,9 @@ static int intel_link_probe(struct auxiliary_device *auxdev, cdns->instance = sdw->instance; cdns->msg_count = 0; + /* single controller for all SoundWire links */ + bus->controller_id = 0; + bus->link_id = auxdev->id; bus->clk_stop_timeout = 1; diff --git a/drivers/soundwire/master.c b/drivers/soundwire/master.c index 9b05c9e25ebe..51abedbbaa66 100644 --- a/drivers/soundwire/master.c +++ b/drivers/soundwire/master.c @@ -145,7 +145,7 @@ int sdw_master_device_add(struct sdw_bus *bus, struct device *parent, md->dev.fwnode = fwnode; md->dev.dma_mask = parent->dma_mask; - dev_set_name(&md->dev, "sdw-master-%d", bus->id); + dev_set_name(&md->dev, "sdw-master-%d-%d", bus->controller_id, bus->link_id); ret = device_register(&md->dev); if (ret) { diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c index 8076d40407d4..3c4d6debab1f 100644 --- a/drivers/soundwire/qcom.c +++ b/drivers/soundwire/qcom.c @@ -1157,9 +1157,20 @@ static int qcom_swrm_stream_alloc_ports(struct qcom_swrm_ctrl *ctrl, struct sdw_port_runtime *p_rt; struct sdw_slave *slave; unsigned long *port_mask; - int i, maxport, pn, nports = 0, ret = 0; + int maxport, pn, nports = 0, ret = 0; unsigned int m_port; + if (direction == SNDRV_PCM_STREAM_CAPTURE) + sconfig.direction = SDW_DATA_DIR_TX; + else + sconfig.direction = SDW_DATA_DIR_RX; + + /* hw parameters wil be ignored as we only support PDM */ + sconfig.ch_count = 1; + sconfig.frame_rate = params_rate(params); + sconfig.type = stream->type; + sconfig.bps = 1; + mutex_lock(&ctrl->port_lock); list_for_each_entry(m_rt, &stream->master_list, stream_node) { if (m_rt->direction == SDW_DATA_DIR_RX) { @@ -1183,7 +1194,7 @@ static int qcom_swrm_stream_alloc_ports(struct qcom_swrm_ctrl *ctrl, if (pn > maxport) { dev_err(ctrl->dev, "All ports busy\n"); ret = -EBUSY; - goto err; + goto out; } set_bit(pn, port_mask); pconfig[nports].num = pn; @@ -1193,24 +1204,9 @@ static int qcom_swrm_stream_alloc_ports(struct qcom_swrm_ctrl *ctrl, } } - if (direction == SNDRV_PCM_STREAM_CAPTURE) - sconfig.direction = SDW_DATA_DIR_TX; - else - sconfig.direction = SDW_DATA_DIR_RX; - - /* hw parameters wil be ignored as we only support PDM */ - sconfig.ch_count = 1; - sconfig.frame_rate = params_rate(params); - sconfig.type = stream->type; - sconfig.bps = 1; sdw_stream_add_master(&ctrl->bus, &sconfig, pconfig, nports, stream); -err: - if (ret) { - for (i = 0; i < nports; i++) - clear_bit(pconfig[i].num, port_mask); - } - +out: mutex_unlock(&ctrl->port_lock); return ret; @@ -1593,6 +1589,13 @@ static int qcom_swrm_probe(struct platform_device *pdev) } } + ctrl->bus.controller_id = -1; + + if (ctrl->version > SWRM_VERSION_1_3_0) { + ctrl->reg_read(ctrl, SWRM_COMP_MASTER_ID, &val); + ctrl->bus.controller_id = val; + } + ret = sdw_bus_master_add(&ctrl->bus, dev, dev->fwnode); if (ret) { dev_err(dev, "Failed to register Soundwire controller (%d)\n", diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c index c1c1a2ac293a..060c2982e26b 100644 --- a/drivers/soundwire/slave.c +++ b/drivers/soundwire/slave.c @@ -39,14 +39,14 @@ int sdw_slave_add(struct sdw_bus *bus, slave->dev.fwnode = fwnode; if (id->unique_id == SDW_IGNORED_UNIQUE_ID) { - /* name shall be sdw:link:mfg:part:class */ - dev_set_name(&slave->dev, "sdw:%01x:%04x:%04x:%02x", - bus->link_id, id->mfg_id, id->part_id, + /* name shall be sdw:ctrl:link:mfg:part:class */ + dev_set_name(&slave->dev, "sdw:%01x:%01x:%04x:%04x:%02x", + bus->controller_id, bus->link_id, id->mfg_id, id->part_id, id->class_id); } else { - /* name shall be sdw:link:mfg:part:class:unique */ - dev_set_name(&slave->dev, "sdw:%01x:%04x:%04x:%02x:%01x", - bus->link_id, id->mfg_id, id->part_id, + /* name shall be sdw:ctrl:link:mfg:part:class:unique */ + dev_set_name(&slave->dev, "sdw:%01x:%01x:%04x:%04x:%02x:%01x", + bus->controller_id, bus->link_id, id->mfg_id, id->part_id, id->class_id, id->unique_id); } diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index f048b3d55b2e..f9c0adc0738d 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -898,7 +898,7 @@ static struct sdw_port_runtime *sdw_port_alloc(struct list_head *port_list) } static int sdw_port_config(struct sdw_port_runtime *p_rt, - struct sdw_port_config *port_config, + const struct sdw_port_config *port_config, int port_index) { p_rt->ch_mask = port_config[port_index].ch_mask; @@ -971,7 +971,7 @@ static int sdw_slave_port_is_valid_range(struct device *dev, int num) static int sdw_slave_port_config(struct sdw_slave *slave, struct sdw_slave_runtime *s_rt, - struct sdw_port_config *port_config) + const struct sdw_port_config *port_config) { struct sdw_port_runtime *p_rt; int ret; @@ -1027,7 +1027,7 @@ static int sdw_master_port_alloc(struct sdw_master_runtime *m_rt, } static int sdw_master_port_config(struct sdw_master_runtime *m_rt, - struct sdw_port_config *port_config) + const struct sdw_port_config *port_config) { struct sdw_port_runtime *p_rt; int ret; @@ -1862,7 +1862,7 @@ EXPORT_SYMBOL(sdw_release_stream); */ int sdw_stream_add_master(struct sdw_bus *bus, struct sdw_stream_config *stream_config, - struct sdw_port_config *port_config, + const struct sdw_port_config *port_config, unsigned int num_ports, struct sdw_stream_runtime *stream) { @@ -1982,7 +1982,7 @@ EXPORT_SYMBOL(sdw_stream_remove_master); */ int sdw_stream_add_slave(struct sdw_slave *slave, struct sdw_stream_config *stream_config, - struct sdw_port_config *port_config, + const struct sdw_port_config *port_config, unsigned int num_ports, struct sdw_stream_runtime *stream) { diff --git a/drivers/spi/spi-coldfire-qspi.c b/drivers/spi/spi-coldfire-qspi.c index f0b630fe16c3..b341b6908df0 100644 --- a/drivers/spi/spi-coldfire-qspi.c +++ b/drivers/spi/spi-coldfire-qspi.c @@ -441,7 +441,6 @@ static void mcfqspi_remove(struct platform_device *pdev) mcfqspi_wr_qmr(mcfqspi, MCFQSPI_QMR_MSTR); mcfqspi_cs_teardown(mcfqspi); - clk_disable_unprepare(mcfqspi->clk); } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/staging/greybus/i2c.c b/drivers/staging/greybus/i2c.c index de2f6516da09..22325ab9d652 100644 --- a/drivers/staging/greybus/i2c.c +++ b/drivers/staging/greybus/i2c.c @@ -264,7 +264,7 @@ static int gb_i2c_probe(struct gbphy_device *gbphy_dev, /* Looks good; up our i2c adapter */ adapter = &gb_i2c_dev->adapter; adapter->owner = THIS_MODULE; - adapter->class = I2C_CLASS_HWMON | I2C_CLASS_SPD; + adapter->class = I2C_CLASS_HWMON; adapter->algo = &gb_i2c_algorithm; adapter->dev.parent = &gbphy_dev->dev; diff --git a/drivers/thermal/loongson2_thermal.c b/drivers/thermal/loongson2_thermal.c index 99ca0c7bc41c..0f475fe46bc9 100644 --- a/drivers/thermal/loongson2_thermal.c +++ b/drivers/thermal/loongson2_thermal.c @@ -8,9 +8,10 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/minmax.h> +#include <linux/mod_devicetable.h> #include <linux/module.h> -#include <linux/of_device.h> #include <linux/platform_device.h> +#include <linux/property.h> #include <linux/thermal.h> #include <linux/units.h> #include "thermal_hwmon.h" diff --git a/drivers/vdpa/alibaba/eni_vdpa.c b/drivers/vdpa/alibaba/eni_vdpa.c index 5a09a09cca70..cce3d1837104 100644 --- a/drivers/vdpa/alibaba/eni_vdpa.c +++ b/drivers/vdpa/alibaba/eni_vdpa.c @@ -497,7 +497,7 @@ static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (!eni_vdpa->vring) { ret = -ENOMEM; ENI_ERR(pdev, "failed to allocate virtqueues\n"); - goto err; + goto err_remove_vp_legacy; } for (i = 0; i < eni_vdpa->queues; i++) { @@ -509,11 +509,13 @@ static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = vdpa_register_device(&eni_vdpa->vdpa, eni_vdpa->queues); if (ret) { ENI_ERR(pdev, "failed to register to vdpa bus\n"); - goto err; + goto err_remove_vp_legacy; } return 0; +err_remove_vp_legacy: + vp_legacy_remove(&eni_vdpa->ldev); err: put_device(&eni_vdpa->vdpa.dev); return ret; diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h index 84547d998bcf..50aac8fe57ef 100644 --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h @@ -35,6 +35,9 @@ struct mlx5_vdpa_mr { struct vhost_iotlb *iotlb; bool user_mr; + + refcount_t refcount; + struct list_head mr_list; }; struct mlx5_vdpa_resources { @@ -93,6 +96,7 @@ struct mlx5_vdpa_dev { u32 generation; struct mlx5_vdpa_mr *mr[MLX5_VDPA_NUM_AS]; + struct list_head mr_list_head; /* serialize mr access */ struct mutex mr_mtx; struct mlx5_control_vq cvq; @@ -118,8 +122,10 @@ int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, u32 mkey); struct mlx5_vdpa_mr *mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb); void mlx5_vdpa_destroy_mr_resources(struct mlx5_vdpa_dev *mvdev); -void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev, - struct mlx5_vdpa_mr *mr); +void mlx5_vdpa_get_mr(struct mlx5_vdpa_dev *mvdev, + struct mlx5_vdpa_mr *mr); +void mlx5_vdpa_put_mr(struct mlx5_vdpa_dev *mvdev, + struct mlx5_vdpa_mr *mr); void mlx5_vdpa_update_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr, unsigned int asid); diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index 2197c46e563a..4758914ccf86 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -498,32 +498,54 @@ static void destroy_user_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr static void _mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr) { + if (WARN_ON(!mr)) + return; + if (mr->user_mr) destroy_user_mr(mvdev, mr); else destroy_dma_mr(mvdev, mr); vhost_iotlb_free(mr->iotlb); + + list_del(&mr->mr_list); + + kfree(mr); } -void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev, - struct mlx5_vdpa_mr *mr) +static void _mlx5_vdpa_put_mr(struct mlx5_vdpa_dev *mvdev, + struct mlx5_vdpa_mr *mr) { if (!mr) return; + if (refcount_dec_and_test(&mr->refcount)) + _mlx5_vdpa_destroy_mr(mvdev, mr); +} + +void mlx5_vdpa_put_mr(struct mlx5_vdpa_dev *mvdev, + struct mlx5_vdpa_mr *mr) +{ mutex_lock(&mvdev->mr_mtx); + _mlx5_vdpa_put_mr(mvdev, mr); + mutex_unlock(&mvdev->mr_mtx); +} - _mlx5_vdpa_destroy_mr(mvdev, mr); +static void _mlx5_vdpa_get_mr(struct mlx5_vdpa_dev *mvdev, + struct mlx5_vdpa_mr *mr) +{ + if (!mr) + return; - for (int i = 0; i < MLX5_VDPA_NUM_AS; i++) { - if (mvdev->mr[i] == mr) - mvdev->mr[i] = NULL; - } + refcount_inc(&mr->refcount); +} +void mlx5_vdpa_get_mr(struct mlx5_vdpa_dev *mvdev, + struct mlx5_vdpa_mr *mr) +{ + mutex_lock(&mvdev->mr_mtx); + _mlx5_vdpa_get_mr(mvdev, mr); mutex_unlock(&mvdev->mr_mtx); - - kfree(mr); } void mlx5_vdpa_update_mr(struct mlx5_vdpa_dev *mvdev, @@ -534,10 +556,23 @@ void mlx5_vdpa_update_mr(struct mlx5_vdpa_dev *mvdev, mutex_lock(&mvdev->mr_mtx); + _mlx5_vdpa_put_mr(mvdev, old_mr); mvdev->mr[asid] = new_mr; - if (old_mr) { - _mlx5_vdpa_destroy_mr(mvdev, old_mr); - kfree(old_mr); + + mutex_unlock(&mvdev->mr_mtx); +} + +static void mlx5_vdpa_show_mr_leaks(struct mlx5_vdpa_dev *mvdev) +{ + struct mlx5_vdpa_mr *mr; + + mutex_lock(&mvdev->mr_mtx); + + list_for_each_entry(mr, &mvdev->mr_list_head, mr_list) { + + mlx5_vdpa_warn(mvdev, "mkey still alive after resource delete: " + "mr: %p, mkey: 0x%x, refcount: %u\n", + mr, mr->mkey, refcount_read(&mr->refcount)); } mutex_unlock(&mvdev->mr_mtx); @@ -547,9 +582,11 @@ void mlx5_vdpa_update_mr(struct mlx5_vdpa_dev *mvdev, void mlx5_vdpa_destroy_mr_resources(struct mlx5_vdpa_dev *mvdev) { for (int i = 0; i < MLX5_VDPA_NUM_AS; i++) - mlx5_vdpa_destroy_mr(mvdev, mvdev->mr[i]); + mlx5_vdpa_update_mr(mvdev, NULL, i); prune_iotlb(mvdev->cvq.iotlb); + + mlx5_vdpa_show_mr_leaks(mvdev); } static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, @@ -576,6 +613,8 @@ static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, if (err) goto err_iotlb; + list_add_tail(&mr->mr_list, &mvdev->mr_list_head); + return 0; err_iotlb: @@ -607,6 +646,8 @@ struct mlx5_vdpa_mr *mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, if (err) goto out_err; + refcount_set(&mr->refcount, 1); + return mr; out_err: @@ -651,7 +692,7 @@ int mlx5_vdpa_reset_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid) if (asid >= MLX5_VDPA_NUM_AS) return -EINVAL; - mlx5_vdpa_destroy_mr(mvdev, mvdev->mr[asid]); + mlx5_vdpa_update_mr(mvdev, NULL, asid); if (asid == 0 && MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) { if (mlx5_vdpa_create_dma_mr(mvdev)) diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 26ba7da6b410..778821bab7d9 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -120,6 +120,12 @@ struct mlx5_vdpa_virtqueue { u16 avail_idx; u16 used_idx; int fw_state; + + u64 modified_fields; + + struct mlx5_vdpa_mr *vq_mr; + struct mlx5_vdpa_mr *desc_mr; + struct msi_map map; /* keep last in the struct */ @@ -943,6 +949,14 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque kfree(in); mvq->virtq_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); + mlx5_vdpa_get_mr(mvdev, vq_mr); + mvq->vq_mr = vq_mr; + + if (vq_desc_mr && MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, desc_group_mkey_supported)) { + mlx5_vdpa_get_mr(mvdev, vq_desc_mr); + mvq->desc_mr = vq_desc_mr; + } + return 0; err_cmd: @@ -969,6 +983,12 @@ static void destroy_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtq } mvq->fw_state = MLX5_VIRTIO_NET_Q_OBJECT_NONE; umems_destroy(ndev, mvq); + + mlx5_vdpa_put_mr(&ndev->mvdev, mvq->vq_mr); + mvq->vq_mr = NULL; + + mlx5_vdpa_put_mr(&ndev->mvdev, mvq->desc_mr); + mvq->desc_mr = NULL; } static u32 get_rqpn(struct mlx5_vdpa_virtqueue *mvq, bool fw) @@ -1167,7 +1187,12 @@ err_cmd: return err; } -static bool is_valid_state_change(int oldstate, int newstate) +static bool is_resumable(struct mlx5_vdpa_net *ndev) +{ + return ndev->mvdev.vdev.config->resume; +} + +static bool is_valid_state_change(int oldstate, int newstate, bool resumable) { switch (oldstate) { case MLX5_VIRTIO_NET_Q_OBJECT_STATE_INIT: @@ -1175,25 +1200,43 @@ static bool is_valid_state_change(int oldstate, int newstate) case MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY: return newstate == MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND; case MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND: + return resumable ? newstate == MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY : false; case MLX5_VIRTIO_NET_Q_OBJECT_STATE_ERR: default: return false; } } -static int modify_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, int state) +static bool modifiable_virtqueue_fields(struct mlx5_vdpa_virtqueue *mvq) +{ + /* Only state is always modifiable */ + if (mvq->modified_fields & ~MLX5_VIRTQ_MODIFY_MASK_STATE) + return mvq->fw_state == MLX5_VIRTIO_NET_Q_OBJECT_STATE_INIT || + mvq->fw_state == MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND; + + return true; +} + +static int modify_virtqueue(struct mlx5_vdpa_net *ndev, + struct mlx5_vdpa_virtqueue *mvq, + int state) { int inlen = MLX5_ST_SZ_BYTES(modify_virtio_net_q_in); u32 out[MLX5_ST_SZ_DW(modify_virtio_net_q_out)] = {}; + struct mlx5_vdpa_dev *mvdev = &ndev->mvdev; + struct mlx5_vdpa_mr *desc_mr = NULL; + struct mlx5_vdpa_mr *vq_mr = NULL; + bool state_change = false; void *obj_context; void *cmd_hdr; + void *vq_ctx; void *in; int err; if (mvq->fw_state == MLX5_VIRTIO_NET_Q_OBJECT_NONE) return 0; - if (!is_valid_state_change(mvq->fw_state, state)) + if (!modifiable_virtqueue_fields(mvq)) return -EINVAL; in = kzalloc(inlen, GFP_KERNEL); @@ -1208,17 +1251,83 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, uid, ndev->mvdev.res.uid); obj_context = MLX5_ADDR_OF(modify_virtio_net_q_in, in, obj_context); - MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select, - MLX5_VIRTQ_MODIFY_MASK_STATE); - MLX5_SET(virtio_net_q_object, obj_context, state, state); + vq_ctx = MLX5_ADDR_OF(virtio_net_q_object, obj_context, virtio_q_context); + + if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_STATE) { + if (!is_valid_state_change(mvq->fw_state, state, is_resumable(ndev))) { + err = -EINVAL; + goto done; + } + + MLX5_SET(virtio_net_q_object, obj_context, state, state); + state_change = true; + } + + if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS) { + MLX5_SET64(virtio_q, vq_ctx, desc_addr, mvq->desc_addr); + MLX5_SET64(virtio_q, vq_ctx, used_addr, mvq->device_addr); + MLX5_SET64(virtio_q, vq_ctx, available_addr, mvq->driver_addr); + } + + if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX) + MLX5_SET(virtio_net_q_object, obj_context, hw_available_index, mvq->avail_idx); + + if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX) + MLX5_SET(virtio_net_q_object, obj_context, hw_used_index, mvq->used_idx); + + if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY) { + vq_mr = mvdev->mr[mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP]]; + + if (vq_mr) + MLX5_SET(virtio_q, vq_ctx, virtio_q_mkey, vq_mr->mkey); + else + mvq->modified_fields &= ~MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY; + } + + if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY) { + desc_mr = mvdev->mr[mvdev->group2asid[MLX5_VDPA_DATAVQ_DESC_GROUP]]; + + if (desc_mr && MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, desc_group_mkey_supported)) + MLX5_SET(virtio_q, vq_ctx, desc_group_mkey, desc_mr->mkey); + else + mvq->modified_fields &= ~MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY; + } + + MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select, mvq->modified_fields); err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out)); - kfree(in); - if (!err) + if (err) + goto done; + + if (state_change) mvq->fw_state = state; + if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY) { + mlx5_vdpa_put_mr(mvdev, mvq->vq_mr); + mlx5_vdpa_get_mr(mvdev, vq_mr); + mvq->vq_mr = vq_mr; + } + + if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY) { + mlx5_vdpa_put_mr(mvdev, mvq->desc_mr); + mlx5_vdpa_get_mr(mvdev, desc_mr); + mvq->desc_mr = desc_mr; + } + + mvq->modified_fields = 0; + +done: + kfree(in); return err; } +static int modify_virtqueue_state(struct mlx5_vdpa_net *ndev, + struct mlx5_vdpa_virtqueue *mvq, + unsigned int state) +{ + mvq->modified_fields |= MLX5_VIRTQ_MODIFY_MASK_STATE; + return modify_virtqueue(ndev, mvq, state); +} + static int counter_set_alloc(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq) { u32 in[MLX5_ST_SZ_DW(create_virtio_q_counters_in)] = {}; @@ -1347,7 +1456,7 @@ static int setup_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq) goto err_vq; if (mvq->ready) { - err = modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY); + err = modify_virtqueue_state(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY); if (err) { mlx5_vdpa_warn(&ndev->mvdev, "failed to modify to ready vq idx %d(%d)\n", idx, err); @@ -1382,7 +1491,7 @@ static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *m if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY) return; - if (modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND)) + if (modify_virtqueue_state(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND)) mlx5_vdpa_warn(&ndev->mvdev, "modify to suspend failed\n"); if (query_virtqueue(ndev, mvq, &attr)) { @@ -1401,12 +1510,31 @@ static void suspend_vqs(struct mlx5_vdpa_net *ndev) suspend_vq(ndev, &ndev->vqs[i]); } +static void resume_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq) +{ + if (!mvq->initialized || !is_resumable(ndev)) + return; + + if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND) + return; + + if (modify_virtqueue_state(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY)) + mlx5_vdpa_warn(&ndev->mvdev, "modify to resume failed for vq %u\n", mvq->index); +} + +static void resume_vqs(struct mlx5_vdpa_net *ndev) +{ + for (int i = 0; i < ndev->mvdev.max_vqs; i++) + resume_vq(ndev, &ndev->vqs[i]); +} + static void teardown_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq) { if (!mvq->initialized) return; suspend_vq(ndev, mvq); + mvq->modified_fields = 0; destroy_virtqueue(ndev, mvq); dealloc_vector(ndev, mvq); counter_set_dealloc(ndev, mvq); @@ -2138,6 +2266,7 @@ static int mlx5_vdpa_set_vq_address(struct vdpa_device *vdev, u16 idx, u64 desc_ mvq->desc_addr = desc_area; mvq->device_addr = device_area; mvq->driver_addr = driver_area; + mvq->modified_fields |= MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS; return 0; } @@ -2207,7 +2336,7 @@ static void mlx5_vdpa_set_vq_ready(struct vdpa_device *vdev, u16 idx, bool ready if (!ready) { suspend_vq(ndev, mvq); } else { - err = modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY); + err = modify_virtqueue_state(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY); if (err) { mlx5_vdpa_warn(mvdev, "modify VQ %d to ready failed (%d)\n", idx, err); ready = false; @@ -2255,6 +2384,8 @@ static int mlx5_vdpa_set_vq_state(struct vdpa_device *vdev, u16 idx, mvq->used_idx = state->split.avail_index; mvq->avail_idx = state->split.avail_index; + mvq->modified_fields |= MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX | + MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX; return 0; } @@ -2703,24 +2834,35 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, unsigned int asid) { struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + bool teardown = !is_resumable(ndev); int err; suspend_vqs(ndev); - err = save_channels_info(ndev); - if (err) - return err; + if (teardown) { + err = save_channels_info(ndev); + if (err) + return err; - teardown_driver(ndev); + teardown_driver(ndev); + } mlx5_vdpa_update_mr(mvdev, new_mr, asid); + for (int i = 0; i < ndev->cur_num_vqs; i++) + ndev->vqs[i].modified_fields |= MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY | + MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY; + if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK) || mvdev->suspended) return 0; - restore_channels_info(ndev); - err = setup_driver(mvdev); - if (err) - return err; + if (teardown) { + restore_channels_info(ndev); + err = setup_driver(mvdev); + if (err) + return err; + } + + resume_vqs(ndev); return 0; } @@ -2804,8 +2946,10 @@ static void clear_vqs_ready(struct mlx5_vdpa_net *ndev) { int i; - for (i = 0; i < ndev->mvdev.max_vqs; i++) + for (i = 0; i < ndev->mvdev.max_vqs; i++) { ndev->vqs[i].ready = false; + ndev->vqs[i].modified_fields = 0; + } ndev->mvdev.cvq.ready = false; } @@ -2982,7 +3126,7 @@ static int set_map_data(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb, return mlx5_vdpa_update_cvq_iotlb(mvdev, iotlb, asid); out_err: - mlx5_vdpa_destroy_mr(mvdev, new_mr); + mlx5_vdpa_put_mr(mvdev, new_mr); return err; } @@ -3229,6 +3373,23 @@ static int mlx5_vdpa_suspend(struct vdpa_device *vdev) return 0; } +static int mlx5_vdpa_resume(struct vdpa_device *vdev) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev; + + ndev = to_mlx5_vdpa_ndev(mvdev); + + mlx5_vdpa_info(mvdev, "resuming device\n"); + + down_write(&ndev->reslock); + mvdev->suspended = false; + resume_vqs(ndev); + register_link_notifier(ndev); + up_write(&ndev->reslock); + return 0; +} + static int mlx5_set_group_asid(struct vdpa_device *vdev, u32 group, unsigned int asid) { @@ -3285,6 +3446,7 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = { .get_vq_dma_dev = mlx5_get_vq_dma_dev, .free = mlx5_vdpa_free, .suspend = mlx5_vdpa_suspend, + .resume = mlx5_vdpa_resume, /* Op disabled if not supported. */ }; static int query_mtu(struct mlx5_core_dev *mdev, u16 *mtu) @@ -3560,6 +3722,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, if (err) goto err_mpfs; + INIT_LIST_HEAD(&mvdev->mr_list_head); + if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) { err = mlx5_vdpa_create_dma_mr(mvdev); if (err) @@ -3656,6 +3820,9 @@ static int mlx5v_probe(struct auxiliary_device *adev, if (!MLX5_CAP_DEV_VDPA_EMULATION(mdev, desc_group_mkey_supported)) mgtdev->vdpa_ops.get_vq_desc_group = NULL; + if (!MLX5_CAP_DEV_VDPA_EMULATION(mdev, freeze_to_rdy_supported)) + mgtdev->vdpa_ops.resume = NULL; + err = vdpa_mgmtdev_register(&mgtdev->mgtdev); if (err) goto reg_err; diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index a7612e0783b3..d0695680b282 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -131,7 +131,7 @@ static void vdpa_release_dev(struct device *d) if (ops->free) ops->free(vdev); - ida_simple_remove(&vdpa_index_ida, vdev->index); + ida_free(&vdpa_index_ida, vdev->index); kfree(vdev->driver_override); kfree(vdev); } @@ -205,7 +205,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, return vdev; err_name: - ida_simple_remove(&vdpa_index_ida, vdev->index); + ida_free(&vdpa_index_ida, vdev->index); err_ida: kfree(vdev); err: diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig index 6bda6dbb4878..ceae52fd7586 100644 --- a/drivers/vfio/Kconfig +++ b/drivers/vfio/Kconfig @@ -80,6 +80,16 @@ config VFIO_VIRQFD select EVENTFD default n +config VFIO_DEBUGFS + bool "Export VFIO internals in DebugFS" + depends on DEBUG_FS + help + Allows exposure of VFIO device internals. This option enables + the use of debugfs by VFIO drivers as required. The device can + cause the VFIO code create a top-level debug/vfio directory + during initialization, and then populate a subdirectory with + entries as required. + source "drivers/vfio/pci/Kconfig" source "drivers/vfio/platform/Kconfig" source "drivers/vfio/mdev/Kconfig" diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile index 68c05705200f..b2fc9fb499d8 100644 --- a/drivers/vfio/Makefile +++ b/drivers/vfio/Makefile @@ -7,6 +7,7 @@ vfio-$(CONFIG_VFIO_GROUP) += group.o vfio-$(CONFIG_IOMMUFD) += iommufd.o vfio-$(CONFIG_VFIO_CONTAINER) += container.o vfio-$(CONFIG_VFIO_VIRQFD) += virqfd.o +vfio-$(CONFIG_VFIO_DEBUGFS) += debugfs.o obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o diff --git a/drivers/vfio/debugfs.c b/drivers/vfio/debugfs.c new file mode 100644 index 000000000000..298bd866f157 --- /dev/null +++ b/drivers/vfio/debugfs.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2023, HiSilicon Ltd. + */ + +#include <linux/device.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> +#include <linux/vfio.h> +#include "vfio.h" + +static struct dentry *vfio_debugfs_root; + +static int vfio_device_state_read(struct seq_file *seq, void *data) +{ + struct device *vf_dev = seq->private; + struct vfio_device *vdev = container_of(vf_dev, + struct vfio_device, device); + enum vfio_device_mig_state state; + int ret; + + BUILD_BUG_ON(VFIO_DEVICE_STATE_NR != + VFIO_DEVICE_STATE_PRE_COPY_P2P + 1); + + ret = vdev->mig_ops->migration_get_state(vdev, &state); + if (ret) + return -EINVAL; + + switch (state) { + case VFIO_DEVICE_STATE_ERROR: + seq_puts(seq, "ERROR\n"); + break; + case VFIO_DEVICE_STATE_STOP: + seq_puts(seq, "STOP\n"); + break; + case VFIO_DEVICE_STATE_RUNNING: + seq_puts(seq, "RUNNING\n"); + break; + case VFIO_DEVICE_STATE_STOP_COPY: + seq_puts(seq, "STOP_COPY\n"); + break; + case VFIO_DEVICE_STATE_RESUMING: + seq_puts(seq, "RESUMING\n"); + break; + case VFIO_DEVICE_STATE_RUNNING_P2P: + seq_puts(seq, "RUNNING_P2P\n"); + break; + case VFIO_DEVICE_STATE_PRE_COPY: + seq_puts(seq, "PRE_COPY\n"); + break; + case VFIO_DEVICE_STATE_PRE_COPY_P2P: + seq_puts(seq, "PRE_COPY_P2P\n"); + break; + default: + seq_puts(seq, "Invalid\n"); + } + + return 0; +} + +void vfio_device_debugfs_init(struct vfio_device *vdev) +{ + struct device *dev = &vdev->device; + + vdev->debug_root = debugfs_create_dir(dev_name(vdev->dev), + vfio_debugfs_root); + + if (vdev->mig_ops) { + struct dentry *vfio_dev_migration = NULL; + + vfio_dev_migration = debugfs_create_dir("migration", + vdev->debug_root); + debugfs_create_devm_seqfile(dev, "state", vfio_dev_migration, + vfio_device_state_read); + } +} + +void vfio_device_debugfs_exit(struct vfio_device *vdev) +{ + debugfs_remove_recursive(vdev->debug_root); +} + +void vfio_debugfs_create_root(void) +{ + vfio_debugfs_root = debugfs_create_dir("vfio", NULL); +} + +void vfio_debugfs_remove_root(void) +{ + debugfs_remove_recursive(vfio_debugfs_root); + vfio_debugfs_root = NULL; +} diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig index 8125e5f37832..18c397df566d 100644 --- a/drivers/vfio/pci/Kconfig +++ b/drivers/vfio/pci/Kconfig @@ -65,4 +65,6 @@ source "drivers/vfio/pci/hisilicon/Kconfig" source "drivers/vfio/pci/pds/Kconfig" +source "drivers/vfio/pci/virtio/Kconfig" + endmenu diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index 45167be462d8..046139a4eca5 100644 --- a/drivers/vfio/pci/Makefile +++ b/drivers/vfio/pci/Makefile @@ -13,3 +13,5 @@ obj-$(CONFIG_MLX5_VFIO_PCI) += mlx5/ obj-$(CONFIG_HISI_ACC_VFIO_PCI) += hisilicon/ obj-$(CONFIG_PDS_VFIO_PCI) += pds/ + +obj-$(CONFIG_VIRTIO_VFIO_PCI) += virtio/ diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c index b2f9778c8366..4d27465c8f1a 100644 --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c @@ -694,6 +694,7 @@ static ssize_t hisi_acc_vf_resume_write(struct file *filp, const char __user *bu size_t len, loff_t *pos) { struct hisi_acc_vf_migration_file *migf = filp->private_data; + u8 *vf_data = (u8 *)&migf->vf_data; loff_t requested_length; ssize_t done = 0; int ret; @@ -715,7 +716,7 @@ static ssize_t hisi_acc_vf_resume_write(struct file *filp, const char __user *bu goto out_unlock; } - ret = copy_from_user(&migf->vf_data, buf, len); + ret = copy_from_user(vf_data + *pos, buf, len); if (ret) { done = -EFAULT; goto out_unlock; @@ -835,7 +836,9 @@ static ssize_t hisi_acc_vf_save_read(struct file *filp, char __user *buf, size_t len = min_t(size_t, migf->total_length - *pos, len); if (len) { - ret = copy_to_user(buf, &migf->vf_data, len); + u8 *vf_data = (u8 *)&migf->vf_data; + + ret = copy_to_user(buf, vf_data + *pos, len); if (ret) { done = -EFAULT; goto out_unlock; diff --git a/drivers/vfio/pci/pds/dirty.c b/drivers/vfio/pci/pds/dirty.c index c937aa6f3954..8ddf4346fcd5 100644 --- a/drivers/vfio/pci/pds/dirty.c +++ b/drivers/vfio/pci/pds/dirty.c @@ -70,7 +70,7 @@ out_free_region_info: kfree(region_info); } -static int pds_vfio_dirty_alloc_bitmaps(struct pds_vfio_dirty *dirty, +static int pds_vfio_dirty_alloc_bitmaps(struct pds_vfio_region *region, unsigned long bytes) { unsigned long *host_seq_bmp, *host_ack_bmp; @@ -85,47 +85,63 @@ static int pds_vfio_dirty_alloc_bitmaps(struct pds_vfio_dirty *dirty, return -ENOMEM; } - dirty->host_seq.bmp = host_seq_bmp; - dirty->host_ack.bmp = host_ack_bmp; + region->host_seq = host_seq_bmp; + region->host_ack = host_ack_bmp; + region->bmp_bytes = bytes; return 0; } static void pds_vfio_dirty_free_bitmaps(struct pds_vfio_dirty *dirty) { - vfree(dirty->host_seq.bmp); - vfree(dirty->host_ack.bmp); - dirty->host_seq.bmp = NULL; - dirty->host_ack.bmp = NULL; + if (!dirty->regions) + return; + + for (int i = 0; i < dirty->num_regions; i++) { + struct pds_vfio_region *region = &dirty->regions[i]; + + vfree(region->host_seq); + vfree(region->host_ack); + region->host_seq = NULL; + region->host_ack = NULL; + region->bmp_bytes = 0; + } } static void __pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio, - struct pds_vfio_bmp_info *bmp_info) + struct pds_vfio_region *region) { struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev; struct device *pdsc_dev = &pci_physfn(pdev)->dev; - dma_unmap_single(pdsc_dev, bmp_info->sgl_addr, - bmp_info->num_sge * sizeof(struct pds_lm_sg_elem), + dma_unmap_single(pdsc_dev, region->sgl_addr, + region->num_sge * sizeof(struct pds_lm_sg_elem), DMA_BIDIRECTIONAL); - kfree(bmp_info->sgl); + kfree(region->sgl); - bmp_info->num_sge = 0; - bmp_info->sgl = NULL; - bmp_info->sgl_addr = 0; + region->num_sge = 0; + region->sgl = NULL; + region->sgl_addr = 0; } static void pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio) { - if (pds_vfio->dirty.host_seq.sgl) - __pds_vfio_dirty_free_sgl(pds_vfio, &pds_vfio->dirty.host_seq); - if (pds_vfio->dirty.host_ack.sgl) - __pds_vfio_dirty_free_sgl(pds_vfio, &pds_vfio->dirty.host_ack); + struct pds_vfio_dirty *dirty = &pds_vfio->dirty; + + if (!dirty->regions) + return; + + for (int i = 0; i < dirty->num_regions; i++) { + struct pds_vfio_region *region = &dirty->regions[i]; + + if (region->sgl) + __pds_vfio_dirty_free_sgl(pds_vfio, region); + } } -static int __pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio, - struct pds_vfio_bmp_info *bmp_info, - u32 page_count) +static int pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio, + struct pds_vfio_region *region, + u32 page_count) { struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev; struct device *pdsc_dev = &pci_physfn(pdev)->dev; @@ -147,32 +163,81 @@ static int __pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio, return -EIO; } - bmp_info->sgl = sgl; - bmp_info->num_sge = max_sge; - bmp_info->sgl_addr = sgl_addr; + region->sgl = sgl; + region->num_sge = max_sge; + region->sgl_addr = sgl_addr; return 0; } -static int pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio, - u32 page_count) +static void pds_vfio_dirty_free_regions(struct pds_vfio_dirty *dirty) { + vfree(dirty->regions); + dirty->regions = NULL; + dirty->num_regions = 0; +} + +static int pds_vfio_dirty_alloc_regions(struct pds_vfio_pci_device *pds_vfio, + struct pds_lm_dirty_region_info *region_info, + u64 region_page_size, u8 num_regions) +{ + struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev; struct pds_vfio_dirty *dirty = &pds_vfio->dirty; + u32 dev_bmp_offset_byte = 0; int err; - err = __pds_vfio_dirty_alloc_sgl(pds_vfio, &dirty->host_seq, - page_count); - if (err) - return err; + dirty->regions = vcalloc(num_regions, sizeof(struct pds_vfio_region)); + if (!dirty->regions) + return -ENOMEM; + dirty->num_regions = num_regions; + + for (int i = 0; i < num_regions; i++) { + struct pds_lm_dirty_region_info *ri = ®ion_info[i]; + struct pds_vfio_region *region = &dirty->regions[i]; + u64 region_size, region_start; + u32 page_count; + + /* page_count might be adjusted by the device */ + page_count = le32_to_cpu(ri->page_count); + region_start = le64_to_cpu(ri->dma_base); + region_size = page_count * region_page_size; + + err = pds_vfio_dirty_alloc_bitmaps(region, + page_count / BITS_PER_BYTE); + if (err) { + dev_err(&pdev->dev, "Failed to alloc dirty bitmaps: %pe\n", + ERR_PTR(err)); + goto out_free_regions; + } - err = __pds_vfio_dirty_alloc_sgl(pds_vfio, &dirty->host_ack, - page_count); - if (err) { - __pds_vfio_dirty_free_sgl(pds_vfio, &dirty->host_seq); - return err; + err = pds_vfio_dirty_alloc_sgl(pds_vfio, region, page_count); + if (err) { + dev_err(&pdev->dev, "Failed to alloc dirty sg lists: %pe\n", + ERR_PTR(err)); + goto out_free_regions; + } + + region->size = region_size; + region->start = region_start; + region->page_size = region_page_size; + region->dev_bmp_offset_start_byte = dev_bmp_offset_byte; + + dev_bmp_offset_byte += page_count / BITS_PER_BYTE; + if (dev_bmp_offset_byte % BITS_PER_BYTE) { + dev_err(&pdev->dev, "Device bitmap offset is mis-aligned\n"); + err = -EINVAL; + goto out_free_regions; + } } return 0; + +out_free_regions: + pds_vfio_dirty_free_bitmaps(dirty); + pds_vfio_dirty_free_sgl(pds_vfio); + pds_vfio_dirty_free_regions(dirty); + + return err; } static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio, @@ -181,16 +246,14 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio, { struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev; struct device *pdsc_dev = &pci_physfn(pdev)->dev; - struct pds_vfio_dirty *dirty = &pds_vfio->dirty; - u64 region_start, region_size, region_page_size; struct pds_lm_dirty_region_info *region_info; struct interval_tree_node *node = NULL; + u64 region_page_size = *page_size; u8 max_regions = 0, num_regions; dma_addr_t regions_dma = 0; u32 num_ranges = nnodes; - u32 page_count; - u16 len; int err; + u16 len; dev_dbg(&pdev->dev, "vf%u: Start dirty page tracking\n", pds_vfio->vf_id); @@ -217,39 +280,38 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio, return -EOPNOTSUPP; } - /* - * Only support 1 region for now. If there are any large gaps in the - * VM's address regions, then this would be a waste of memory as we are - * generating 2 bitmaps (ack/seq) from the min address to the max - * address of the VM's address regions. In the future, if we support - * more than one region in the device/driver we can split the bitmaps - * on the largest address region gaps. We can do this split up to the - * max_regions times returned from the dirty_status command. - */ - max_regions = 1; if (num_ranges > max_regions) { vfio_combine_iova_ranges(ranges, nnodes, max_regions); num_ranges = max_regions; } + region_info = kcalloc(num_ranges, sizeof(*region_info), GFP_KERNEL); + if (!region_info) + return -ENOMEM; + len = num_ranges * sizeof(*region_info); + node = interval_tree_iter_first(ranges, 0, ULONG_MAX); if (!node) return -EINVAL; + for (int i = 0; i < num_ranges; i++) { + struct pds_lm_dirty_region_info *ri = ®ion_info[i]; + u64 region_size = node->last - node->start + 1; + u64 region_start = node->start; + u32 page_count; - region_size = node->last - node->start + 1; - region_start = node->start; - region_page_size = *page_size; + page_count = DIV_ROUND_UP(region_size, region_page_size); - len = sizeof(*region_info); - region_info = kzalloc(len, GFP_KERNEL); - if (!region_info) - return -ENOMEM; + ri->dma_base = cpu_to_le64(region_start); + ri->page_count = cpu_to_le32(page_count); + ri->page_size_log2 = ilog2(region_page_size); - page_count = DIV_ROUND_UP(region_size, region_page_size); + dev_dbg(&pdev->dev, + "region_info[%d]: region_start 0x%llx region_end 0x%lx region_size 0x%llx page_count %u page_size %llu\n", + i, region_start, node->last, region_size, page_count, + region_page_size); - region_info->dma_base = cpu_to_le64(region_start); - region_info->page_count = cpu_to_le32(page_count); - region_info->page_size_log2 = ilog2(region_page_size); + node = interval_tree_iter_next(node, 0, ULONG_MAX); + } regions_dma = dma_map_single(pdsc_dev, (void *)region_info, len, DMA_BIDIRECTIONAL); @@ -258,39 +320,20 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio, goto out_free_region_info; } - err = pds_vfio_dirty_enable_cmd(pds_vfio, regions_dma, max_regions); + err = pds_vfio_dirty_enable_cmd(pds_vfio, regions_dma, num_ranges); dma_unmap_single(pdsc_dev, regions_dma, len, DMA_BIDIRECTIONAL); if (err) goto out_free_region_info; - /* - * page_count might be adjusted by the device, - * update it before freeing region_info DMA - */ - page_count = le32_to_cpu(region_info->page_count); - - dev_dbg(&pdev->dev, - "region_info: regions_dma 0x%llx dma_base 0x%llx page_count %u page_size_log2 %u\n", - regions_dma, region_start, page_count, - (u8)ilog2(region_page_size)); - - err = pds_vfio_dirty_alloc_bitmaps(dirty, page_count / BITS_PER_BYTE); - if (err) { - dev_err(&pdev->dev, "Failed to alloc dirty bitmaps: %pe\n", - ERR_PTR(err)); - goto out_free_region_info; - } - - err = pds_vfio_dirty_alloc_sgl(pds_vfio, page_count); + err = pds_vfio_dirty_alloc_regions(pds_vfio, region_info, + region_page_size, num_ranges); if (err) { - dev_err(&pdev->dev, "Failed to alloc dirty sg lists: %pe\n", - ERR_PTR(err)); - goto out_free_bitmaps; + dev_err(&pdev->dev, + "Failed to allocate %d regions for tracking dirty regions: %pe\n", + num_regions, ERR_PTR(err)); + goto out_dirty_disable; } - dirty->region_start = region_start; - dirty->region_size = region_size; - dirty->region_page_size = region_page_size; pds_vfio_dirty_set_enabled(pds_vfio); pds_vfio_print_guest_region_info(pds_vfio, max_regions); @@ -299,8 +342,8 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio, return 0; -out_free_bitmaps: - pds_vfio_dirty_free_bitmaps(dirty); +out_dirty_disable: + pds_vfio_dirty_disable_cmd(pds_vfio); out_free_region_info: kfree(region_info); return err; @@ -314,6 +357,7 @@ void pds_vfio_dirty_disable(struct pds_vfio_pci_device *pds_vfio, bool send_cmd) pds_vfio_dirty_disable_cmd(pds_vfio); pds_vfio_dirty_free_sgl(pds_vfio); pds_vfio_dirty_free_bitmaps(&pds_vfio->dirty); + pds_vfio_dirty_free_regions(&pds_vfio->dirty); } if (send_cmd) @@ -321,8 +365,9 @@ void pds_vfio_dirty_disable(struct pds_vfio_pci_device *pds_vfio, bool send_cmd) } static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio, - struct pds_vfio_bmp_info *bmp_info, - u32 offset, u32 bmp_bytes, bool read_seq) + struct pds_vfio_region *region, + unsigned long *seq_ack_bmp, u32 offset, + u32 bmp_bytes, bool read_seq) { const char *bmp_type_str = read_seq ? "read_seq" : "write_ack"; u8 dma_dir = read_seq ? DMA_FROM_DEVICE : DMA_TO_DEVICE; @@ -339,7 +384,7 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio, int err; int i; - bmp = (void *)((u64)bmp_info->bmp + offset); + bmp = (void *)((u64)seq_ack_bmp + offset); page_offset = offset_in_page(bmp); bmp -= page_offset; @@ -375,7 +420,7 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio, goto out_free_sg_table; for_each_sgtable_dma_sg(&sg_table, sg, i) { - struct pds_lm_sg_elem *sg_elem = &bmp_info->sgl[i]; + struct pds_lm_sg_elem *sg_elem = ®ion->sgl[i]; sg_elem->addr = cpu_to_le64(sg_dma_address(sg)); sg_elem->len = cpu_to_le32(sg_dma_len(sg)); @@ -383,15 +428,16 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio, num_sge = sg_table.nents; size = num_sge * sizeof(struct pds_lm_sg_elem); - dma_sync_single_for_device(pdsc_dev, bmp_info->sgl_addr, size, dma_dir); - err = pds_vfio_dirty_seq_ack_cmd(pds_vfio, bmp_info->sgl_addr, num_sge, + offset += region->dev_bmp_offset_start_byte; + dma_sync_single_for_device(pdsc_dev, region->sgl_addr, size, dma_dir); + err = pds_vfio_dirty_seq_ack_cmd(pds_vfio, region->sgl_addr, num_sge, offset, bmp_bytes, read_seq); if (err) dev_err(&pdev->dev, "Dirty bitmap %s failed offset %u bmp_bytes %u num_sge %u DMA 0x%llx: %pe\n", bmp_type_str, offset, bmp_bytes, - num_sge, bmp_info->sgl_addr, ERR_PTR(err)); - dma_sync_single_for_cpu(pdsc_dev, bmp_info->sgl_addr, size, dma_dir); + num_sge, region->sgl_addr, ERR_PTR(err)); + dma_sync_single_for_cpu(pdsc_dev, region->sgl_addr, size, dma_dir); dma_unmap_sgtable(pdsc_dev, &sg_table, dma_dir, 0); out_free_sg_table: @@ -403,32 +449,36 @@ out_free_pages: } static int pds_vfio_dirty_write_ack(struct pds_vfio_pci_device *pds_vfio, + struct pds_vfio_region *region, u32 offset, u32 len) { - return pds_vfio_dirty_seq_ack(pds_vfio, &pds_vfio->dirty.host_ack, + + return pds_vfio_dirty_seq_ack(pds_vfio, region, region->host_ack, offset, len, WRITE_ACK); } static int pds_vfio_dirty_read_seq(struct pds_vfio_pci_device *pds_vfio, + struct pds_vfio_region *region, u32 offset, u32 len) { - return pds_vfio_dirty_seq_ack(pds_vfio, &pds_vfio->dirty.host_seq, + return pds_vfio_dirty_seq_ack(pds_vfio, region, region->host_seq, offset, len, READ_SEQ); } static int pds_vfio_dirty_process_bitmaps(struct pds_vfio_pci_device *pds_vfio, + struct pds_vfio_region *region, struct iova_bitmap *dirty_bitmap, u32 bmp_offset, u32 len_bytes) { - u64 page_size = pds_vfio->dirty.region_page_size; - u64 region_start = pds_vfio->dirty.region_start; + u64 page_size = region->page_size; + u64 region_start = region->start; u32 bmp_offset_bit; __le64 *seq, *ack; int dword_count; dword_count = len_bytes / sizeof(u64); - seq = (__le64 *)((u64)pds_vfio->dirty.host_seq.bmp + bmp_offset); - ack = (__le64 *)((u64)pds_vfio->dirty.host_ack.bmp + bmp_offset); + seq = (__le64 *)((u64)region->host_seq + bmp_offset); + ack = (__le64 *)((u64)region->host_ack + bmp_offset); bmp_offset_bit = bmp_offset * 8; for (int i = 0; i < dword_count; i++) { @@ -451,12 +501,28 @@ static int pds_vfio_dirty_process_bitmaps(struct pds_vfio_pci_device *pds_vfio, return 0; } +static struct pds_vfio_region * +pds_vfio_get_region(struct pds_vfio_pci_device *pds_vfio, unsigned long iova) +{ + struct pds_vfio_dirty *dirty = &pds_vfio->dirty; + + for (int i = 0; i < dirty->num_regions; i++) { + struct pds_vfio_region *region = &dirty->regions[i]; + + if (iova >= region->start && + iova < (region->start + region->size)) + return region; + } + + return NULL; +} + static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio, struct iova_bitmap *dirty_bitmap, unsigned long iova, unsigned long length) { struct device *dev = &pds_vfio->vfio_coredev.pdev->dev; - struct pds_vfio_dirty *dirty = &pds_vfio->dirty; + struct pds_vfio_region *region; u64 bmp_offset, bmp_bytes; u64 bitmap_size, pages; int err; @@ -469,26 +535,31 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio, return -EINVAL; } - pages = DIV_ROUND_UP(length, pds_vfio->dirty.region_page_size); + region = pds_vfio_get_region(pds_vfio, iova); + if (!region) { + dev_err(dev, "vf%u: Failed to find region that contains iova 0x%lx length 0x%lx\n", + pds_vfio->vf_id, iova, length); + return -EINVAL; + } + + pages = DIV_ROUND_UP(length, region->page_size); bitmap_size = round_up(pages, sizeof(u64) * BITS_PER_BYTE) / BITS_PER_BYTE; dev_dbg(dev, "vf%u: iova 0x%lx length %lu page_size %llu pages %llu bitmap_size %llu\n", - pds_vfio->vf_id, iova, length, pds_vfio->dirty.region_page_size, + pds_vfio->vf_id, iova, length, region->page_size, pages, bitmap_size); - if (!length || ((dirty->region_start + iova + length) > - (dirty->region_start + dirty->region_size))) { + if (!length || ((iova - region->start + length) > region->size)) { dev_err(dev, "Invalid iova 0x%lx and/or length 0x%lx to sync\n", iova, length); return -EINVAL; } /* bitmap is modified in 64 bit chunks */ - bmp_bytes = ALIGN(DIV_ROUND_UP(length / dirty->region_page_size, - sizeof(u64)), - sizeof(u64)); + bmp_bytes = ALIGN(DIV_ROUND_UP(length / region->page_size, + sizeof(u64)), sizeof(u64)); if (bmp_bytes != bitmap_size) { dev_err(dev, "Calculated bitmap bytes %llu not equal to bitmap size %llu\n", @@ -496,22 +567,30 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio, return -EINVAL; } - bmp_offset = DIV_ROUND_UP(iova / dirty->region_page_size, sizeof(u64)); + if (bmp_bytes > region->bmp_bytes) { + dev_err(dev, + "Calculated bitmap bytes %llu larger than region's cached bmp_bytes %llu\n", + bmp_bytes, region->bmp_bytes); + return -EINVAL; + } + + bmp_offset = DIV_ROUND_UP((iova - region->start) / + region->page_size, sizeof(u64)); dev_dbg(dev, "Syncing dirty bitmap, iova 0x%lx length 0x%lx, bmp_offset %llu bmp_bytes %llu\n", iova, length, bmp_offset, bmp_bytes); - err = pds_vfio_dirty_read_seq(pds_vfio, bmp_offset, bmp_bytes); + err = pds_vfio_dirty_read_seq(pds_vfio, region, bmp_offset, bmp_bytes); if (err) return err; - err = pds_vfio_dirty_process_bitmaps(pds_vfio, dirty_bitmap, bmp_offset, - bmp_bytes); + err = pds_vfio_dirty_process_bitmaps(pds_vfio, region, dirty_bitmap, + bmp_offset, bmp_bytes); if (err) return err; - err = pds_vfio_dirty_write_ack(pds_vfio, bmp_offset, bmp_bytes); + err = pds_vfio_dirty_write_ack(pds_vfio, region, bmp_offset, bmp_bytes); if (err) return err; diff --git a/drivers/vfio/pci/pds/dirty.h b/drivers/vfio/pci/pds/dirty.h index f78da25d75ca..c8e23018b801 100644 --- a/drivers/vfio/pci/pds/dirty.h +++ b/drivers/vfio/pci/pds/dirty.h @@ -4,20 +4,22 @@ #ifndef _DIRTY_H_ #define _DIRTY_H_ -struct pds_vfio_bmp_info { - unsigned long *bmp; - u32 bmp_bytes; +struct pds_vfio_region { + unsigned long *host_seq; + unsigned long *host_ack; + u64 bmp_bytes; + u64 size; + u64 start; + u64 page_size; struct pds_lm_sg_elem *sgl; dma_addr_t sgl_addr; + u32 dev_bmp_offset_start_byte; u16 num_sge; }; struct pds_vfio_dirty { - struct pds_vfio_bmp_info host_seq; - struct pds_vfio_bmp_info host_ack; - u64 region_size; - u64 region_start; - u64 region_page_size; + struct pds_vfio_region *regions; + u8 num_regions; bool is_enabled; }; diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c index e27de61ac9fe..07fea08ea8a2 100644 --- a/drivers/vfio/pci/vfio_pci_rdwr.c +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -38,7 +38,7 @@ #define vfio_iowrite8 iowrite8 #define VFIO_IOWRITE(size) \ -static int vfio_pci_iowrite##size(struct vfio_pci_core_device *vdev, \ +int vfio_pci_core_iowrite##size(struct vfio_pci_core_device *vdev, \ bool test_mem, u##size val, void __iomem *io) \ { \ if (test_mem) { \ @@ -55,7 +55,8 @@ static int vfio_pci_iowrite##size(struct vfio_pci_core_device *vdev, \ up_read(&vdev->memory_lock); \ \ return 0; \ -} +} \ +EXPORT_SYMBOL_GPL(vfio_pci_core_iowrite##size); VFIO_IOWRITE(8) VFIO_IOWRITE(16) @@ -65,7 +66,7 @@ VFIO_IOWRITE(64) #endif #define VFIO_IOREAD(size) \ -static int vfio_pci_ioread##size(struct vfio_pci_core_device *vdev, \ +int vfio_pci_core_ioread##size(struct vfio_pci_core_device *vdev, \ bool test_mem, u##size *val, void __iomem *io) \ { \ if (test_mem) { \ @@ -82,7 +83,8 @@ static int vfio_pci_ioread##size(struct vfio_pci_core_device *vdev, \ up_read(&vdev->memory_lock); \ \ return 0; \ -} +} \ +EXPORT_SYMBOL_GPL(vfio_pci_core_ioread##size); VFIO_IOREAD(8) VFIO_IOREAD(16) @@ -119,13 +121,13 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, if (copy_from_user(&val, buf, 4)) return -EFAULT; - ret = vfio_pci_iowrite32(vdev, test_mem, - val, io + off); + ret = vfio_pci_core_iowrite32(vdev, test_mem, + val, io + off); if (ret) return ret; } else { - ret = vfio_pci_ioread32(vdev, test_mem, - &val, io + off); + ret = vfio_pci_core_ioread32(vdev, test_mem, + &val, io + off); if (ret) return ret; @@ -141,13 +143,13 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, if (copy_from_user(&val, buf, 2)) return -EFAULT; - ret = vfio_pci_iowrite16(vdev, test_mem, - val, io + off); + ret = vfio_pci_core_iowrite16(vdev, test_mem, + val, io + off); if (ret) return ret; } else { - ret = vfio_pci_ioread16(vdev, test_mem, - &val, io + off); + ret = vfio_pci_core_ioread16(vdev, test_mem, + &val, io + off); if (ret) return ret; @@ -163,13 +165,13 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, if (copy_from_user(&val, buf, 1)) return -EFAULT; - ret = vfio_pci_iowrite8(vdev, test_mem, - val, io + off); + ret = vfio_pci_core_iowrite8(vdev, test_mem, + val, io + off); if (ret) return ret; } else { - ret = vfio_pci_ioread8(vdev, test_mem, - &val, io + off); + ret = vfio_pci_core_ioread8(vdev, test_mem, + &val, io + off); if (ret) return ret; @@ -200,7 +202,7 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, return done; } -static int vfio_pci_setup_barmap(struct vfio_pci_core_device *vdev, int bar) +int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar) { struct pci_dev *pdev = vdev->pdev; int ret; @@ -223,6 +225,7 @@ static int vfio_pci_setup_barmap(struct vfio_pci_core_device *vdev, int bar) return 0; } +EXPORT_SYMBOL_GPL(vfio_pci_core_setup_barmap); ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, size_t count, loff_t *ppos, bool iswrite) @@ -262,7 +265,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, } x_end = end; } else { - int ret = vfio_pci_setup_barmap(vdev, bar); + int ret = vfio_pci_core_setup_barmap(vdev, bar); if (ret) { done = ret; goto out; @@ -363,21 +366,21 @@ static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd, { switch (ioeventfd->count) { case 1: - vfio_pci_iowrite8(ioeventfd->vdev, test_mem, - ioeventfd->data, ioeventfd->addr); + vfio_pci_core_iowrite8(ioeventfd->vdev, test_mem, + ioeventfd->data, ioeventfd->addr); break; case 2: - vfio_pci_iowrite16(ioeventfd->vdev, test_mem, - ioeventfd->data, ioeventfd->addr); + vfio_pci_core_iowrite16(ioeventfd->vdev, test_mem, + ioeventfd->data, ioeventfd->addr); break; case 4: - vfio_pci_iowrite32(ioeventfd->vdev, test_mem, - ioeventfd->data, ioeventfd->addr); + vfio_pci_core_iowrite32(ioeventfd->vdev, test_mem, + ioeventfd->data, ioeventfd->addr); break; #ifdef iowrite64 case 8: - vfio_pci_iowrite64(ioeventfd->vdev, test_mem, - ioeventfd->data, ioeventfd->addr); + vfio_pci_core_iowrite64(ioeventfd->vdev, test_mem, + ioeventfd->data, ioeventfd->addr); break; #endif } @@ -438,7 +441,7 @@ int vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset, return -EINVAL; #endif - ret = vfio_pci_setup_barmap(vdev, bar); + ret = vfio_pci_core_setup_barmap(vdev, bar); if (ret) return ret; diff --git a/drivers/vfio/pci/virtio/Kconfig b/drivers/vfio/pci/virtio/Kconfig new file mode 100644 index 000000000000..bd80eca4a196 --- /dev/null +++ b/drivers/vfio/pci/virtio/Kconfig @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0-only +config VIRTIO_VFIO_PCI + tristate "VFIO support for VIRTIO NET PCI devices" + depends on VIRTIO_PCI && VIRTIO_PCI_ADMIN_LEGACY + select VFIO_PCI_CORE + help + This provides support for exposing VIRTIO NET VF devices which support + legacy IO access, using the VFIO framework that can work with a legacy + virtio driver in the guest. + Based on PCIe spec, VFs do not support I/O Space. + As of that this driver emulates I/O BAR in software to let a VF be + seen as a transitional device by its users and let it work with + a legacy driver. + + If you don't know what to do here, say N. diff --git a/drivers/vfio/pci/virtio/Makefile b/drivers/vfio/pci/virtio/Makefile new file mode 100644 index 000000000000..7171105baf33 --- /dev/null +++ b/drivers/vfio/pci/virtio/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_VIRTIO_VFIO_PCI) += virtio-vfio-pci.o +virtio-vfio-pci-y := main.o diff --git a/drivers/vfio/pci/virtio/main.c b/drivers/vfio/pci/virtio/main.c new file mode 100644 index 000000000000..d5af683837d3 --- /dev/null +++ b/drivers/vfio/pci/virtio/main.c @@ -0,0 +1,576 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved + */ + +#include <linux/device.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/pci.h> +#include <linux/pm_runtime.h> +#include <linux/types.h> +#include <linux/uaccess.h> +#include <linux/vfio.h> +#include <linux/vfio_pci_core.h> +#include <linux/virtio_pci.h> +#include <linux/virtio_net.h> +#include <linux/virtio_pci_admin.h> + +struct virtiovf_pci_core_device { + struct vfio_pci_core_device core_device; + u8 *bar0_virtual_buf; + /* synchronize access to the virtual buf */ + struct mutex bar_mutex; + void __iomem *notify_addr; + u64 notify_offset; + __le32 pci_base_addr_0; + __le16 pci_cmd; + u8 bar0_virtual_buf_size; + u8 notify_bar; +}; + +static int +virtiovf_issue_legacy_rw_cmd(struct virtiovf_pci_core_device *virtvdev, + loff_t pos, char __user *buf, + size_t count, bool read) +{ + bool msix_enabled = + (virtvdev->core_device.irq_type == VFIO_PCI_MSIX_IRQ_INDEX); + struct pci_dev *pdev = virtvdev->core_device.pdev; + u8 *bar0_buf = virtvdev->bar0_virtual_buf; + bool common; + u8 offset; + int ret; + + common = pos < VIRTIO_PCI_CONFIG_OFF(msix_enabled); + /* offset within the relevant configuration area */ + offset = common ? pos : pos - VIRTIO_PCI_CONFIG_OFF(msix_enabled); + mutex_lock(&virtvdev->bar_mutex); + if (read) { + if (common) + ret = virtio_pci_admin_legacy_common_io_read(pdev, offset, + count, bar0_buf + pos); + else + ret = virtio_pci_admin_legacy_device_io_read(pdev, offset, + count, bar0_buf + pos); + if (ret) + goto out; + if (copy_to_user(buf, bar0_buf + pos, count)) + ret = -EFAULT; + } else { + if (copy_from_user(bar0_buf + pos, buf, count)) { + ret = -EFAULT; + goto out; + } + + if (common) + ret = virtio_pci_admin_legacy_common_io_write(pdev, offset, + count, bar0_buf + pos); + else + ret = virtio_pci_admin_legacy_device_io_write(pdev, offset, + count, bar0_buf + pos); + } +out: + mutex_unlock(&virtvdev->bar_mutex); + return ret; +} + +static int +virtiovf_pci_bar0_rw(struct virtiovf_pci_core_device *virtvdev, + loff_t pos, char __user *buf, + size_t count, bool read) +{ + struct vfio_pci_core_device *core_device = &virtvdev->core_device; + struct pci_dev *pdev = core_device->pdev; + u16 queue_notify; + int ret; + + if (!(le16_to_cpu(virtvdev->pci_cmd) & PCI_COMMAND_IO)) + return -EIO; + + if (pos + count > virtvdev->bar0_virtual_buf_size) + return -EINVAL; + + ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret) { + pci_info_ratelimited(pdev, "runtime resume failed %d\n", ret); + return -EIO; + } + + switch (pos) { + case VIRTIO_PCI_QUEUE_NOTIFY: + if (count != sizeof(queue_notify)) { + ret = -EINVAL; + goto end; + } + if (read) { + ret = vfio_pci_core_ioread16(core_device, true, &queue_notify, + virtvdev->notify_addr); + if (ret) + goto end; + if (copy_to_user(buf, &queue_notify, + sizeof(queue_notify))) { + ret = -EFAULT; + goto end; + } + } else { + if (copy_from_user(&queue_notify, buf, count)) { + ret = -EFAULT; + goto end; + } + ret = vfio_pci_core_iowrite16(core_device, true, queue_notify, + virtvdev->notify_addr); + } + break; + default: + ret = virtiovf_issue_legacy_rw_cmd(virtvdev, pos, buf, count, + read); + } + +end: + pm_runtime_put(&pdev->dev); + return ret ? ret : count; +} + +static bool range_intersect_range(loff_t range1_start, size_t count1, + loff_t range2_start, size_t count2, + loff_t *start_offset, + size_t *intersect_count, + size_t *register_offset) +{ + if (range1_start <= range2_start && + range1_start + count1 > range2_start) { + *start_offset = range2_start - range1_start; + *intersect_count = min_t(size_t, count2, + range1_start + count1 - range2_start); + *register_offset = 0; + return true; + } + + if (range1_start > range2_start && + range1_start < range2_start + count2) { + *start_offset = 0; + *intersect_count = min_t(size_t, count1, + range2_start + count2 - range1_start); + *register_offset = range1_start - range2_start; + return true; + } + + return false; +} + +static ssize_t virtiovf_pci_read_config(struct vfio_device *core_vdev, + char __user *buf, size_t count, + loff_t *ppos) +{ + struct virtiovf_pci_core_device *virtvdev = container_of( + core_vdev, struct virtiovf_pci_core_device, core_device.vdev); + loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK; + size_t register_offset; + loff_t copy_offset; + size_t copy_count; + __le32 val32; + __le16 val16; + u8 val8; + int ret; + + ret = vfio_pci_core_read(core_vdev, buf, count, ppos); + if (ret < 0) + return ret; + + if (range_intersect_range(pos, count, PCI_DEVICE_ID, sizeof(val16), + ©_offset, ©_count, ®ister_offset)) { + val16 = cpu_to_le16(VIRTIO_TRANS_ID_NET); + if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset, copy_count)) + return -EFAULT; + } + + if ((le16_to_cpu(virtvdev->pci_cmd) & PCI_COMMAND_IO) && + range_intersect_range(pos, count, PCI_COMMAND, sizeof(val16), + ©_offset, ©_count, ®ister_offset)) { + if (copy_from_user((void *)&val16 + register_offset, buf + copy_offset, + copy_count)) + return -EFAULT; + val16 |= cpu_to_le16(PCI_COMMAND_IO); + if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset, + copy_count)) + return -EFAULT; + } + + if (range_intersect_range(pos, count, PCI_REVISION_ID, sizeof(val8), + ©_offset, ©_count, ®ister_offset)) { + /* Transional needs to have revision 0 */ + val8 = 0; + if (copy_to_user(buf + copy_offset, &val8, copy_count)) + return -EFAULT; + } + + if (range_intersect_range(pos, count, PCI_BASE_ADDRESS_0, sizeof(val32), + ©_offset, ©_count, ®ister_offset)) { + u32 bar_mask = ~(virtvdev->bar0_virtual_buf_size - 1); + u32 pci_base_addr_0 = le32_to_cpu(virtvdev->pci_base_addr_0); + + val32 = cpu_to_le32((pci_base_addr_0 & bar_mask) | PCI_BASE_ADDRESS_SPACE_IO); + if (copy_to_user(buf + copy_offset, (void *)&val32 + register_offset, copy_count)) + return -EFAULT; + } + + if (range_intersect_range(pos, count, PCI_SUBSYSTEM_ID, sizeof(val16), + ©_offset, ©_count, ®ister_offset)) { + /* + * Transitional devices use the PCI subsystem device id as + * virtio device id, same as legacy driver always did. + */ + val16 = cpu_to_le16(VIRTIO_ID_NET); + if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset, + copy_count)) + return -EFAULT; + } + + if (range_intersect_range(pos, count, PCI_SUBSYSTEM_VENDOR_ID, sizeof(val16), + ©_offset, ©_count, ®ister_offset)) { + val16 = cpu_to_le16(PCI_VENDOR_ID_REDHAT_QUMRANET); + if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset, + copy_count)) + return -EFAULT; + } + + return count; +} + +static ssize_t +virtiovf_pci_core_read(struct vfio_device *core_vdev, char __user *buf, + size_t count, loff_t *ppos) +{ + struct virtiovf_pci_core_device *virtvdev = container_of( + core_vdev, struct virtiovf_pci_core_device, core_device.vdev); + unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos); + loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK; + + if (!count) + return 0; + + if (index == VFIO_PCI_CONFIG_REGION_INDEX) + return virtiovf_pci_read_config(core_vdev, buf, count, ppos); + + if (index == VFIO_PCI_BAR0_REGION_INDEX) + return virtiovf_pci_bar0_rw(virtvdev, pos, buf, count, true); + + return vfio_pci_core_read(core_vdev, buf, count, ppos); +} + +static ssize_t virtiovf_pci_write_config(struct vfio_device *core_vdev, + const char __user *buf, size_t count, + loff_t *ppos) +{ + struct virtiovf_pci_core_device *virtvdev = container_of( + core_vdev, struct virtiovf_pci_core_device, core_device.vdev); + loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK; + size_t register_offset; + loff_t copy_offset; + size_t copy_count; + + if (range_intersect_range(pos, count, PCI_COMMAND, sizeof(virtvdev->pci_cmd), + ©_offset, ©_count, + ®ister_offset)) { + if (copy_from_user((void *)&virtvdev->pci_cmd + register_offset, + buf + copy_offset, + copy_count)) + return -EFAULT; + } + + if (range_intersect_range(pos, count, PCI_BASE_ADDRESS_0, + sizeof(virtvdev->pci_base_addr_0), + ©_offset, ©_count, + ®ister_offset)) { + if (copy_from_user((void *)&virtvdev->pci_base_addr_0 + register_offset, + buf + copy_offset, + copy_count)) + return -EFAULT; + } + + return vfio_pci_core_write(core_vdev, buf, count, ppos); +} + +static ssize_t +virtiovf_pci_core_write(struct vfio_device *core_vdev, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct virtiovf_pci_core_device *virtvdev = container_of( + core_vdev, struct virtiovf_pci_core_device, core_device.vdev); + unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos); + loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK; + + if (!count) + return 0; + + if (index == VFIO_PCI_CONFIG_REGION_INDEX) + return virtiovf_pci_write_config(core_vdev, buf, count, ppos); + + if (index == VFIO_PCI_BAR0_REGION_INDEX) + return virtiovf_pci_bar0_rw(virtvdev, pos, (char __user *)buf, count, false); + + return vfio_pci_core_write(core_vdev, buf, count, ppos); +} + +static int +virtiovf_pci_ioctl_get_region_info(struct vfio_device *core_vdev, + unsigned int cmd, unsigned long arg) +{ + struct virtiovf_pci_core_device *virtvdev = container_of( + core_vdev, struct virtiovf_pci_core_device, core_device.vdev); + unsigned long minsz = offsetofend(struct vfio_region_info, offset); + void __user *uarg = (void __user *)arg; + struct vfio_region_info info = {}; + + if (copy_from_user(&info, uarg, minsz)) + return -EFAULT; + + if (info.argsz < minsz) + return -EINVAL; + + switch (info.index) { + case VFIO_PCI_BAR0_REGION_INDEX: + info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index); + info.size = virtvdev->bar0_virtual_buf_size; + info.flags = VFIO_REGION_INFO_FLAG_READ | + VFIO_REGION_INFO_FLAG_WRITE; + return copy_to_user(uarg, &info, minsz) ? -EFAULT : 0; + default: + return vfio_pci_core_ioctl(core_vdev, cmd, arg); + } +} + +static long +virtiovf_vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd, + unsigned long arg) +{ + switch (cmd) { + case VFIO_DEVICE_GET_REGION_INFO: + return virtiovf_pci_ioctl_get_region_info(core_vdev, cmd, arg); + default: + return vfio_pci_core_ioctl(core_vdev, cmd, arg); + } +} + +static int +virtiovf_set_notify_addr(struct virtiovf_pci_core_device *virtvdev) +{ + struct vfio_pci_core_device *core_device = &virtvdev->core_device; + int ret; + + /* + * Setup the BAR where the 'notify' exists to be used by vfio as well + * This will let us mmap it only once and use it when needed. + */ + ret = vfio_pci_core_setup_barmap(core_device, + virtvdev->notify_bar); + if (ret) + return ret; + + virtvdev->notify_addr = core_device->barmap[virtvdev->notify_bar] + + virtvdev->notify_offset; + return 0; +} + +static int virtiovf_pci_open_device(struct vfio_device *core_vdev) +{ + struct virtiovf_pci_core_device *virtvdev = container_of( + core_vdev, struct virtiovf_pci_core_device, core_device.vdev); + struct vfio_pci_core_device *vdev = &virtvdev->core_device; + int ret; + + ret = vfio_pci_core_enable(vdev); + if (ret) + return ret; + + if (virtvdev->bar0_virtual_buf) { + /* + * Upon close_device() the vfio_pci_core_disable() is called + * and will close all the previous mmaps, so it seems that the + * valid life cycle for the 'notify' addr is per open/close. + */ + ret = virtiovf_set_notify_addr(virtvdev); + if (ret) { + vfio_pci_core_disable(vdev); + return ret; + } + } + + vfio_pci_core_finish_enable(vdev); + return 0; +} + +static int virtiovf_get_device_config_size(unsigned short device) +{ + /* Network card */ + return offsetofend(struct virtio_net_config, status); +} + +static int virtiovf_read_notify_info(struct virtiovf_pci_core_device *virtvdev) +{ + u64 offset; + int ret; + u8 bar; + + ret = virtio_pci_admin_legacy_io_notify_info(virtvdev->core_device.pdev, + VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_MEM, + &bar, &offset); + if (ret) + return ret; + + virtvdev->notify_bar = bar; + virtvdev->notify_offset = offset; + return 0; +} + +static int virtiovf_pci_init_device(struct vfio_device *core_vdev) +{ + struct virtiovf_pci_core_device *virtvdev = container_of( + core_vdev, struct virtiovf_pci_core_device, core_device.vdev); + struct pci_dev *pdev; + int ret; + + ret = vfio_pci_core_init_dev(core_vdev); + if (ret) + return ret; + + pdev = virtvdev->core_device.pdev; + ret = virtiovf_read_notify_info(virtvdev); + if (ret) + return ret; + + virtvdev->bar0_virtual_buf_size = VIRTIO_PCI_CONFIG_OFF(true) + + virtiovf_get_device_config_size(pdev->device); + BUILD_BUG_ON(!is_power_of_2(virtvdev->bar0_virtual_buf_size)); + virtvdev->bar0_virtual_buf = kzalloc(virtvdev->bar0_virtual_buf_size, + GFP_KERNEL); + if (!virtvdev->bar0_virtual_buf) + return -ENOMEM; + mutex_init(&virtvdev->bar_mutex); + return 0; +} + +static void virtiovf_pci_core_release_dev(struct vfio_device *core_vdev) +{ + struct virtiovf_pci_core_device *virtvdev = container_of( + core_vdev, struct virtiovf_pci_core_device, core_device.vdev); + + kfree(virtvdev->bar0_virtual_buf); + vfio_pci_core_release_dev(core_vdev); +} + +static const struct vfio_device_ops virtiovf_vfio_pci_tran_ops = { + .name = "virtio-vfio-pci-trans", + .init = virtiovf_pci_init_device, + .release = virtiovf_pci_core_release_dev, + .open_device = virtiovf_pci_open_device, + .close_device = vfio_pci_core_close_device, + .ioctl = virtiovf_vfio_pci_core_ioctl, + .device_feature = vfio_pci_core_ioctl_feature, + .read = virtiovf_pci_core_read, + .write = virtiovf_pci_core_write, + .mmap = vfio_pci_core_mmap, + .request = vfio_pci_core_request, + .match = vfio_pci_core_match, + .bind_iommufd = vfio_iommufd_physical_bind, + .unbind_iommufd = vfio_iommufd_physical_unbind, + .attach_ioas = vfio_iommufd_physical_attach_ioas, + .detach_ioas = vfio_iommufd_physical_detach_ioas, +}; + +static const struct vfio_device_ops virtiovf_vfio_pci_ops = { + .name = "virtio-vfio-pci", + .init = vfio_pci_core_init_dev, + .release = vfio_pci_core_release_dev, + .open_device = virtiovf_pci_open_device, + .close_device = vfio_pci_core_close_device, + .ioctl = vfio_pci_core_ioctl, + .device_feature = vfio_pci_core_ioctl_feature, + .read = vfio_pci_core_read, + .write = vfio_pci_core_write, + .mmap = vfio_pci_core_mmap, + .request = vfio_pci_core_request, + .match = vfio_pci_core_match, + .bind_iommufd = vfio_iommufd_physical_bind, + .unbind_iommufd = vfio_iommufd_physical_unbind, + .attach_ioas = vfio_iommufd_physical_attach_ioas, + .detach_ioas = vfio_iommufd_physical_detach_ioas, +}; + +static bool virtiovf_bar0_exists(struct pci_dev *pdev) +{ + struct resource *res = pdev->resource; + + return res->flags; +} + +static int virtiovf_pci_probe(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + const struct vfio_device_ops *ops = &virtiovf_vfio_pci_ops; + struct virtiovf_pci_core_device *virtvdev; + int ret; + + if (pdev->is_virtfn && virtio_pci_admin_has_legacy_io(pdev) && + !virtiovf_bar0_exists(pdev)) + ops = &virtiovf_vfio_pci_tran_ops; + + virtvdev = vfio_alloc_device(virtiovf_pci_core_device, core_device.vdev, + &pdev->dev, ops); + if (IS_ERR(virtvdev)) + return PTR_ERR(virtvdev); + + dev_set_drvdata(&pdev->dev, &virtvdev->core_device); + ret = vfio_pci_core_register_device(&virtvdev->core_device); + if (ret) + goto out; + return 0; +out: + vfio_put_device(&virtvdev->core_device.vdev); + return ret; +} + +static void virtiovf_pci_remove(struct pci_dev *pdev) +{ + struct virtiovf_pci_core_device *virtvdev = dev_get_drvdata(&pdev->dev); + + vfio_pci_core_unregister_device(&virtvdev->core_device); + vfio_put_device(&virtvdev->core_device.vdev); +} + +static const struct pci_device_id virtiovf_pci_table[] = { + /* Only virtio-net is supported/tested so far */ + { PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_REDHAT_QUMRANET, 0x1041) }, + {} +}; + +MODULE_DEVICE_TABLE(pci, virtiovf_pci_table); + +static void virtiovf_pci_aer_reset_done(struct pci_dev *pdev) +{ + struct virtiovf_pci_core_device *virtvdev = dev_get_drvdata(&pdev->dev); + + virtvdev->pci_cmd = 0; +} + +static const struct pci_error_handlers virtiovf_err_handlers = { + .reset_done = virtiovf_pci_aer_reset_done, + .error_detected = vfio_pci_core_aer_err_detected, +}; + +static struct pci_driver virtiovf_pci_driver = { + .name = KBUILD_MODNAME, + .id_table = virtiovf_pci_table, + .probe = virtiovf_pci_probe, + .remove = virtiovf_pci_remove, + .err_handler = &virtiovf_err_handlers, + .driver_managed_dma = true, +}; + +module_pci_driver(virtiovf_pci_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Yishai Hadas <yishaih@nvidia.com>"); +MODULE_DESCRIPTION( + "VIRTIO VFIO PCI - User Level meta-driver for VIRTIO NET devices"); diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h index 307e3f29b527..bde84ad344e5 100644 --- a/drivers/vfio/vfio.h +++ b/drivers/vfio/vfio.h @@ -448,4 +448,18 @@ static inline void vfio_device_put_kvm(struct vfio_device *device) } #endif +#ifdef CONFIG_VFIO_DEBUGFS +void vfio_debugfs_create_root(void); +void vfio_debugfs_remove_root(void); + +void vfio_device_debugfs_init(struct vfio_device *vdev); +void vfio_device_debugfs_exit(struct vfio_device *vdev); +#else +static inline void vfio_debugfs_create_root(void) { } +static inline void vfio_debugfs_remove_root(void) { } + +static inline void vfio_device_debugfs_init(struct vfio_device *vdev) { } +static inline void vfio_device_debugfs_exit(struct vfio_device *vdev) { } +#endif /* CONFIG_VFIO_DEBUGFS */ + #endif diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index eacd6ec04de5..b2854d7939ce 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1436,7 +1436,7 @@ static int vfio_iommu_map(struct vfio_iommu *iommu, dma_addr_t iova, list_for_each_entry(d, &iommu->domain_list, next) { ret = iommu_map(d->domain, iova, (phys_addr_t)pfn << PAGE_SHIFT, npage << PAGE_SHIFT, prot | IOMMU_CACHE, - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (ret) goto unwind; @@ -1750,7 +1750,8 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, } ret = iommu_map(domain->domain, iova, phys, size, - dma->prot | IOMMU_CACHE, GFP_KERNEL); + dma->prot | IOMMU_CACHE, + GFP_KERNEL_ACCOUNT); if (ret) { if (!dma->iommu_mapped) { vfio_unpin_pages_remote(dma, iova, @@ -1845,7 +1846,8 @@ static void vfio_test_domain_fgsp(struct vfio_domain *domain, struct list_head * continue; ret = iommu_map(domain->domain, start, page_to_phys(pages), PAGE_SIZE * 2, - IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE, GFP_KERNEL); + IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE, + GFP_KERNEL_ACCOUNT); if (!ret) { size_t unmapped = iommu_unmap(domain->domain, start, PAGE_SIZE); diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index 8d4995ada74a..1cc93aac99a2 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -311,6 +311,7 @@ static int __vfio_register_dev(struct vfio_device *device, refcount_set(&device->refcount, 1); vfio_device_group_register(device); + vfio_device_debugfs_init(device); return 0; err_out: @@ -378,6 +379,7 @@ void vfio_unregister_group_dev(struct vfio_device *device) } } + vfio_device_debugfs_exit(device); /* Balances vfio_device_set_group in register path */ vfio_device_remove_group(device); } @@ -1676,6 +1678,7 @@ static int __init vfio_init(void) if (ret) goto err_alloc_dev_chrdev; + vfio_debugfs_create_root(); pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n"); return 0; @@ -1691,6 +1694,7 @@ err_virqfd: static void __exit vfio_cleanup(void) { + vfio_debugfs_remove_root(); ida_destroy(&vfio.device_ida); vfio_cdev_cleanup(); class_destroy(vfio.device_class); diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 173beda74b38..bc4a51e4638b 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -59,6 +59,7 @@ struct vhost_vdpa { int in_batch; struct vdpa_iova_range range; u32 batch_asid; + bool suspended; }; static DEFINE_IDA(vhost_vdpa_ida); @@ -232,6 +233,8 @@ static int _compat_vdpa_reset(struct vhost_vdpa *v) struct vdpa_device *vdpa = v->vdpa; u32 flags = 0; + v->suspended = false; + if (v->vdev.vqs) { flags |= !vhost_backend_has_feature(v->vdev.vqs[0], VHOST_BACKEND_F_IOTLB_PERSIST) ? @@ -590,11 +593,16 @@ static long vhost_vdpa_suspend(struct vhost_vdpa *v) { struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; + int ret; if (!ops->suspend) return -EOPNOTSUPP; - return ops->suspend(vdpa); + ret = ops->suspend(vdpa); + if (!ret) + v->suspended = true; + + return ret; } /* After a successful return of this ioctl the device resumes processing @@ -605,11 +613,16 @@ static long vhost_vdpa_resume(struct vhost_vdpa *v) { struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; + int ret; if (!ops->resume) return -EOPNOTSUPP; - return ops->resume(vdpa); + ret = ops->resume(vdpa); + if (!ret) + v->suspended = false; + + return ret; } static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, @@ -690,6 +703,9 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, switch (cmd) { case VHOST_SET_VRING_ADDR: + if ((ops->get_status(vdpa) & VIRTIO_CONFIG_S_DRIVER_OK) && !v->suspended) + return -EINVAL; + if (ops->set_vq_address(vdpa, idx, (u64)(uintptr_t)vq->desc, (u64)(uintptr_t)vq->avail, @@ -698,6 +714,9 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, break; case VHOST_SET_VRING_BASE: + if ((ops->get_status(vdpa) & VIRTIO_CONFIG_S_DRIVER_OK) && !v->suspended) + return -EINVAL; + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) { vq_state.packed.last_avail_idx = vq->last_avail_idx & 0x7fff; vq_state.packed.last_avail_counter = !!(vq->last_avail_idx & 0x8000); @@ -968,7 +987,8 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb, r = ops->set_map(vdpa, asid, iotlb); } else { r = iommu_map(v->domain, iova, pa, size, - perm_to_iommu_flags(perm), GFP_KERNEL); + perm_to_iommu_flags(perm), + GFP_KERNEL_ACCOUNT); } if (r) { vhost_iotlb_del_range(iotlb, iova, iova + size - 1); diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig index 94d092091b5e..ea2d0d69bd8c 100644 --- a/drivers/video/backlight/Kconfig +++ b/drivers/video/backlight/Kconfig @@ -395,6 +395,17 @@ config BACKLIGHT_LP8788 help This supports TI LP8788 backlight driver. +config BACKLIGHT_MP3309C + tristate "Backlight Driver for MPS MP3309C" + depends on I2C && PWM + select REGMAP_I2C + help + This supports MPS MP3309C backlight WLED driver in both PWM and + analog/I2C dimming modes. + + To compile this driver as a module, choose M here: the module will + be called mp3309c. + config BACKLIGHT_PANDORA tristate "Backlight driver for Pandora console" depends on TWL4030_CORE diff --git a/drivers/video/backlight/Makefile b/drivers/video/backlight/Makefile index 67d3ff39be3c..06966cb20459 100644 --- a/drivers/video/backlight/Makefile +++ b/drivers/video/backlight/Makefile @@ -43,6 +43,7 @@ obj-$(CONFIG_BACKLIGHT_LP855X) += lp855x_bl.o obj-$(CONFIG_BACKLIGHT_LP8788) += lp8788_bl.o obj-$(CONFIG_BACKLIGHT_LV5207LP) += lv5207lp.o obj-$(CONFIG_BACKLIGHT_MAX8925) += max8925_bl.o +obj-$(CONFIG_BACKLIGHT_MP3309C) += mp3309c.o obj-$(CONFIG_BACKLIGHT_MT6370) += mt6370-backlight.o obj-$(CONFIG_BACKLIGHT_OMAP1) += omap1_bl.o obj-$(CONFIG_BACKLIGHT_PANDORA) += pandora_bl.o diff --git a/drivers/video/backlight/hx8357.c b/drivers/video/backlight/hx8357.c index f76d2469d490..d7298376cf74 100644 --- a/drivers/video/backlight/hx8357.c +++ b/drivers/video/backlight/hx8357.c @@ -6,11 +6,11 @@ */ #include <linux/delay.h> +#include <linux/gpio/consumer.h> #include <linux/lcd.h> #include <linux/module.h> #include <linux/of.h> #include <linux/of_device.h> -#include <linux/of_gpio.h> #include <linux/spi/spi.h> #define HX8357_NUM_IM_PINS 3 @@ -83,11 +83,10 @@ #define HX8369_SET_GAMMA_CURVE_RELATED 0xe0 struct hx8357_data { - unsigned im_pins[HX8357_NUM_IM_PINS]; - unsigned reset; + struct gpio_descs *im_pins; + struct gpio_desc *reset; struct spi_device *spi; int state; - bool use_im_pins; }; static u8 hx8357_seq_power[] = { @@ -321,11 +320,11 @@ static void hx8357_lcd_reset(struct lcd_device *lcdev) struct hx8357_data *lcd = lcd_get_data(lcdev); /* Reset the screen */ - gpio_set_value(lcd->reset, 1); + gpiod_set_value(lcd->reset, 0); usleep_range(10000, 12000); - gpio_set_value(lcd->reset, 0); + gpiod_set_value(lcd->reset, 1); usleep_range(10000, 12000); - gpio_set_value(lcd->reset, 1); + gpiod_set_value(lcd->reset, 0); /* The controller needs 120ms to recover from reset */ msleep(120); @@ -340,10 +339,10 @@ static int hx8357_lcd_init(struct lcd_device *lcdev) * Set the interface selection pins to SPI mode, with three * wires */ - if (lcd->use_im_pins) { - gpio_set_value_cansleep(lcd->im_pins[0], 1); - gpio_set_value_cansleep(lcd->im_pins[1], 0); - gpio_set_value_cansleep(lcd->im_pins[2], 1); + if (lcd->im_pins) { + gpiod_set_value_cansleep(lcd->im_pins->desc[0], 1); + gpiod_set_value_cansleep(lcd->im_pins->desc[1], 0); + gpiod_set_value_cansleep(lcd->im_pins->desc[2], 1); } ret = hx8357_spi_write_array(lcdev, hx8357_seq_power, @@ -580,6 +579,7 @@ MODULE_DEVICE_TABLE(of, hx8357_dt_ids); static int hx8357_probe(struct spi_device *spi) { + struct device *dev = &spi->dev; struct lcd_device *lcdev; struct hx8357_data *lcd; const struct of_device_id *match; @@ -601,49 +601,19 @@ static int hx8357_probe(struct spi_device *spi) if (!match || !match->data) return -EINVAL; - lcd->reset = of_get_named_gpio(spi->dev.of_node, "gpios-reset", 0); - if (!gpio_is_valid(lcd->reset)) { - dev_err(&spi->dev, "Missing dt property: gpios-reset\n"); - return -EINVAL; - } + lcd->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(lcd->reset)) + return dev_err_probe(dev, PTR_ERR(lcd->reset), "failed to request reset GPIO\n"); + gpiod_set_consumer_name(lcd->reset, "hx8357-reset"); - ret = devm_gpio_request_one(&spi->dev, lcd->reset, - GPIOF_OUT_INIT_HIGH, - "hx8357-reset"); - if (ret) { - dev_err(&spi->dev, - "failed to request gpio %d: %d\n", - lcd->reset, ret); - return -EINVAL; - } + lcd->im_pins = devm_gpiod_get_array_optional(dev, "im", GPIOD_OUT_LOW); + if (IS_ERR(lcd->im_pins)) + return dev_err_probe(dev, PTR_ERR(lcd->im_pins), "failed to request im GPIOs\n"); + if (lcd->im_pins->ndescs < HX8357_NUM_IM_PINS) + return dev_err_probe(dev, -EINVAL, "not enough im GPIOs\n"); - if (of_property_present(spi->dev.of_node, "im-gpios")) { - lcd->use_im_pins = 1; - - for (i = 0; i < HX8357_NUM_IM_PINS; i++) { - lcd->im_pins[i] = of_get_named_gpio(spi->dev.of_node, - "im-gpios", i); - if (lcd->im_pins[i] == -EPROBE_DEFER) { - dev_info(&spi->dev, "GPIO requested is not here yet, deferring the probe\n"); - return -EPROBE_DEFER; - } - if (!gpio_is_valid(lcd->im_pins[i])) { - dev_err(&spi->dev, "Missing dt property: im-gpios\n"); - return -EINVAL; - } - - ret = devm_gpio_request_one(&spi->dev, lcd->im_pins[i], - GPIOF_OUT_INIT_LOW, - "im_pins"); - if (ret) { - dev_err(&spi->dev, "failed to request gpio %d: %d\n", - lcd->im_pins[i], ret); - return -EINVAL; - } - } - } else { - lcd->use_im_pins = 0; - } + for (i = 0; i < HX8357_NUM_IM_PINS; i++) + gpiod_set_consumer_name(lcd->im_pins->desc[i], "im_pins"); lcdev = devm_lcd_device_register(&spi->dev, "mxsfb", &spi->dev, lcd, &hx8357_ops); diff --git a/drivers/video/backlight/ili922x.c b/drivers/video/backlight/ili922x.c index e7b6bd827986..c8e0e655dc86 100644 --- a/drivers/video/backlight/ili922x.c +++ b/drivers/video/backlight/ili922x.c @@ -81,7 +81,7 @@ #define START_RW_WRITE 0 #define START_RW_READ 1 -/** +/* * START_BYTE(id, rs, rw) * * Set the start byte according to the required operation. @@ -100,7 +100,7 @@ #define START_BYTE(id, rs, rw) \ (0x70 | (((id) & 0x01) << 2) | (((rs) & 0x01) << 1) | ((rw) & 0x01)) -/** +/* * CHECK_FREQ_REG(spi_device s, spi_transfer x) - Check the frequency * for the SPI transfer. According to the datasheet, the controller * accept higher frequency for the GRAM transfer, but it requires @@ -269,6 +269,10 @@ static int ili922x_write(struct spi_device *spi, u8 reg, u16 value) spi_message_add_tail(&xfer_regindex, &msg); ret = spi_sync(spi, &msg); + if (ret < 0) { + dev_err(&spi->dev, "Error sending SPI message 0x%x", ret); + return ret; + } spi_message_init(&msg); tbuf[0] = set_tx_byte(START_BYTE(ili922x_id, START_RS_REG, diff --git a/drivers/video/backlight/mp3309c.c b/drivers/video/backlight/mp3309c.c new file mode 100644 index 000000000000..34d71259fac1 --- /dev/null +++ b/drivers/video/backlight/mp3309c.c @@ -0,0 +1,444 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Driver for MPS MP3309C White LED driver with I2C interface + * + * This driver support both analog (by I2C commands) and PWM dimming control + * modes. + * + * Copyright (C) 2023 ASEM Srl + * Author: Flavio Suligoi <f.suligoi@asem.it> + * + * Based on pwm_bl.c + */ + +#include <linux/backlight.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/i2c.h> +#include <linux/pwm.h> +#include <linux/regmap.h> + +#define REG_I2C_0 0x00 +#define REG_I2C_1 0x01 + +#define REG_I2C_0_EN 0x80 +#define REG_I2C_0_D0 0x40 +#define REG_I2C_0_D1 0x20 +#define REG_I2C_0_D2 0x10 +#define REG_I2C_0_D3 0x08 +#define REG_I2C_0_D4 0x04 +#define REG_I2C_0_RSRV1 0x02 +#define REG_I2C_0_RSRV2 0x01 + +#define REG_I2C_1_RSRV1 0x80 +#define REG_I2C_1_DIMS 0x40 +#define REG_I2C_1_SYNC 0x20 +#define REG_I2C_1_OVP0 0x10 +#define REG_I2C_1_OVP1 0x08 +#define REG_I2C_1_VOS 0x04 +#define REG_I2C_1_LEDO 0x02 +#define REG_I2C_1_OTP 0x01 + +#define ANALOG_I2C_NUM_LEVELS 32 /* 0..31 */ +#define ANALOG_I2C_REG_MASK 0x7c + +#define MP3309C_PWM_DEFAULT_NUM_LEVELS 256 /* 0..255 */ + +enum mp3309c_status_value { + FIRST_POWER_ON, + BACKLIGHT_OFF, + BACKLIGHT_ON, +}; + +enum mp3309c_dimming_mode_value { + DIMMING_PWM, + DIMMING_ANALOG_I2C, +}; + +struct mp3309c_platform_data { + unsigned int max_brightness; + unsigned int default_brightness; + unsigned int *levels; + u8 dimming_mode; + u8 over_voltage_protection; + bool sync_mode; + u8 status; +}; + +struct mp3309c_chip { + struct device *dev; + struct mp3309c_platform_data *pdata; + struct backlight_device *bl; + struct gpio_desc *enable_gpio; + struct regmap *regmap; + struct pwm_device *pwmd; +}; + +static const struct regmap_config mp3309c_regmap = { + .name = "mp3309c_regmap", + .reg_bits = 8, + .reg_stride = 1, + .val_bits = 8, + .max_register = REG_I2C_1, +}; + +static int mp3309c_enable_device(struct mp3309c_chip *chip) +{ + u8 reg_val; + int ret; + + /* I2C register #0 - Device enable */ + ret = regmap_update_bits(chip->regmap, REG_I2C_0, REG_I2C_0_EN, + REG_I2C_0_EN); + if (ret) + return ret; + + /* + * I2C register #1 - Set working mode: + * - set one of the two dimming mode: + * - PWM dimming using an external PWM dimming signal + * - analog dimming using I2C commands + * - enable/disable synchronous mode + * - set overvoltage protection (OVP) + */ + reg_val = 0x00; + if (chip->pdata->dimming_mode == DIMMING_PWM) + reg_val |= REG_I2C_1_DIMS; + if (chip->pdata->sync_mode) + reg_val |= REG_I2C_1_SYNC; + reg_val |= chip->pdata->over_voltage_protection; + ret = regmap_write(chip->regmap, REG_I2C_1, reg_val); + if (ret) + return ret; + + return 0; +} + +static int mp3309c_bl_update_status(struct backlight_device *bl) +{ + struct mp3309c_chip *chip = bl_get_data(bl); + int brightness = backlight_get_brightness(bl); + struct pwm_state pwmstate; + unsigned int analog_val, bits_val; + int i, ret; + + if (chip->pdata->dimming_mode == DIMMING_PWM) { + /* + * PWM control mode + */ + pwm_get_state(chip->pwmd, &pwmstate); + pwm_set_relative_duty_cycle(&pwmstate, + chip->pdata->levels[brightness], + chip->pdata->levels[chip->pdata->max_brightness]); + pwmstate.enabled = true; + ret = pwm_apply_state(chip->pwmd, &pwmstate); + if (ret) + return ret; + + switch (chip->pdata->status) { + case FIRST_POWER_ON: + case BACKLIGHT_OFF: + /* + * After 20ms of low pwm signal level, the chip turns + * off automatically. In this case, before enabling the + * chip again, we must wait about 10ms for pwm signal to + * stabilize. + */ + if (brightness > 0) { + msleep(10); + mp3309c_enable_device(chip); + chip->pdata->status = BACKLIGHT_ON; + } else { + chip->pdata->status = BACKLIGHT_OFF; + } + break; + case BACKLIGHT_ON: + if (brightness == 0) + chip->pdata->status = BACKLIGHT_OFF; + break; + } + } else { + /* + * Analog (by I2C command) control mode + * + * The first time, before setting brightness, we must enable the + * device + */ + if (chip->pdata->status == FIRST_POWER_ON) + mp3309c_enable_device(chip); + + /* + * Dimming mode I2C command (fixed dimming range 0..31) + * + * The 5 bits of the dimming analog value D4..D0 is allocated + * in the I2C register #0, in the following way: + * + * +--+--+--+--+--+--+--+--+ + * |EN|D0|D1|D2|D3|D4|XX|XX| + * +--+--+--+--+--+--+--+--+ + */ + analog_val = brightness; + bits_val = 0; + for (i = 0; i <= 5; i++) + bits_val += ((analog_val >> i) & 0x01) << (6 - i); + ret = regmap_update_bits(chip->regmap, REG_I2C_0, + ANALOG_I2C_REG_MASK, bits_val); + if (ret) + return ret; + + if (brightness > 0) + chip->pdata->status = BACKLIGHT_ON; + else + chip->pdata->status = BACKLIGHT_OFF; + } + + return 0; +} + +static const struct backlight_ops mp3309c_bl_ops = { + .update_status = mp3309c_bl_update_status, +}; + +static int pm3309c_parse_dt_node(struct mp3309c_chip *chip, + struct mp3309c_platform_data *pdata) +{ + struct device_node *node = chip->dev->of_node; + struct property *prop_pwms; + struct property *prop_levels = NULL; + int length = 0; + int ret, i; + unsigned int num_levels, tmp_value; + + if (!node) { + dev_err(chip->dev, "failed to get DT node\n"); + return -ENODEV; + } + + /* + * Dimming mode: the MP3309C provides two dimming control mode: + * + * - PWM mode + * - Analog by I2C control mode (default) + * + * I2C control mode is assumed as default but, if the pwms property is + * found in the backlight node, the mode switches to PWM mode. + */ + pdata->dimming_mode = DIMMING_ANALOG_I2C; + prop_pwms = of_find_property(node, "pwms", &length); + if (prop_pwms) { + chip->pwmd = devm_pwm_get(chip->dev, NULL); + if (IS_ERR(chip->pwmd)) + return dev_err_probe(chip->dev, PTR_ERR(chip->pwmd), + "error getting pwm data\n"); + pdata->dimming_mode = DIMMING_PWM; + pwm_apply_args(chip->pwmd); + } + + /* + * In I2C control mode the dimming levels (0..31) are fixed by the + * hardware, while in PWM control mode they can be chosen by the user, + * to allow nonlinear mappings. + */ + if (pdata->dimming_mode == DIMMING_ANALOG_I2C) { + /* + * Analog (by I2C commands) control mode: fixed 0..31 brightness + * levels + */ + num_levels = ANALOG_I2C_NUM_LEVELS; + + /* Enable GPIO used in I2C dimming mode only */ + chip->enable_gpio = devm_gpiod_get(chip->dev, "enable", + GPIOD_OUT_HIGH); + if (IS_ERR(chip->enable_gpio)) + return dev_err_probe(chip->dev, + PTR_ERR(chip->enable_gpio), + "error getting enable gpio\n"); + } else { + /* + * PWM control mode: check for brightness level in DT + */ + prop_levels = of_find_property(node, "brightness-levels", + &length); + if (prop_levels) { + /* Read brightness levels from DT */ + num_levels = length / sizeof(u32); + if (num_levels < 2) + return -EINVAL; + } else { + /* Use default brightness levels */ + num_levels = MP3309C_PWM_DEFAULT_NUM_LEVELS; + } + } + + /* Fill brightness levels array */ + pdata->levels = devm_kcalloc(chip->dev, num_levels, + sizeof(*pdata->levels), GFP_KERNEL); + if (!pdata->levels) + return -ENOMEM; + if (prop_levels) { + ret = of_property_read_u32_array(node, "brightness-levels", + pdata->levels, + num_levels); + if (ret < 0) + return ret; + } else { + for (i = 0; i < num_levels; i++) + pdata->levels[i] = i; + } + + pdata->max_brightness = num_levels - 1; + + ret = of_property_read_u32(node, "default-brightness", + &pdata->default_brightness); + if (ret) + pdata->default_brightness = pdata->max_brightness; + if (pdata->default_brightness > pdata->max_brightness) { + dev_err(chip->dev, + "default brightness exceeds max brightness\n"); + pdata->default_brightness = pdata->max_brightness; + } + + /* + * Over-voltage protection (OVP) + * + * This (optional) property values are: + * + * - 13.5V + * - 24V + * - 35.5V (hardware default setting) + * + * If missing, the default value for OVP is 35.5V + */ + pdata->over_voltage_protection = REG_I2C_1_OVP1; + if (!of_property_read_u32(node, "mps,overvoltage-protection-microvolt", + &tmp_value)) { + switch (tmp_value) { + case 13500000: + pdata->over_voltage_protection = 0x00; + break; + case 24000000: + pdata->over_voltage_protection = REG_I2C_1_OVP0; + break; + case 35500000: + pdata->over_voltage_protection = REG_I2C_1_OVP1; + break; + default: + return -EINVAL; + } + } + + /* Synchronous (default) and non-synchronous mode */ + pdata->sync_mode = true; + if (of_property_read_bool(node, "mps,no-sync-mode")) + pdata->sync_mode = false; + + return 0; +} + +static int mp3309c_probe(struct i2c_client *client) +{ + struct mp3309c_platform_data *pdata = dev_get_platdata(&client->dev); + struct mp3309c_chip *chip; + struct backlight_properties props; + struct pwm_state pwmstate; + int ret; + + if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { + dev_err(&client->dev, "failed to check i2c functionality\n"); + return -EOPNOTSUPP; + } + + chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL); + if (!chip) + return -ENOMEM; + + chip->dev = &client->dev; + + chip->regmap = devm_regmap_init_i2c(client, &mp3309c_regmap); + if (IS_ERR(chip->regmap)) + return dev_err_probe(&client->dev, PTR_ERR(chip->regmap), + "failed to allocate register map\n"); + + i2c_set_clientdata(client, chip); + + if (!pdata) { + pdata = devm_kzalloc(chip->dev, sizeof(*pdata), GFP_KERNEL); + if (!pdata) + return -ENOMEM; + + ret = pm3309c_parse_dt_node(chip, pdata); + if (ret) + return ret; + } + chip->pdata = pdata; + + /* Backlight properties */ + props.brightness = pdata->default_brightness; + props.max_brightness = pdata->max_brightness; + props.scale = BACKLIGHT_SCALE_LINEAR; + props.type = BACKLIGHT_RAW; + props.power = FB_BLANK_UNBLANK; + props.fb_blank = FB_BLANK_UNBLANK; + chip->bl = devm_backlight_device_register(chip->dev, "mp3309c", + chip->dev, chip, + &mp3309c_bl_ops, &props); + if (IS_ERR(chip->bl)) + return dev_err_probe(chip->dev, PTR_ERR(chip->bl), + "error registering backlight device\n"); + + /* In PWM dimming mode, enable pwm device */ + if (chip->pdata->dimming_mode == DIMMING_PWM) { + pwm_init_state(chip->pwmd, &pwmstate); + pwm_set_relative_duty_cycle(&pwmstate, + chip->pdata->default_brightness, + chip->pdata->max_brightness); + pwmstate.enabled = true; + ret = pwm_apply_state(chip->pwmd, &pwmstate); + if (ret) + return dev_err_probe(chip->dev, ret, + "error setting pwm device\n"); + } + + chip->pdata->status = FIRST_POWER_ON; + backlight_update_status(chip->bl); + + return 0; +} + +static void mp3309c_remove(struct i2c_client *client) +{ + struct mp3309c_chip *chip = i2c_get_clientdata(client); + struct backlight_device *bl = chip->bl; + + bl->props.power = FB_BLANK_POWERDOWN; + bl->props.brightness = 0; + backlight_update_status(chip->bl); +} + +static const struct of_device_id mp3309c_match_table[] = { + { .compatible = "mps,mp3309c", }, + { }, +}; +MODULE_DEVICE_TABLE(of, mp3309c_match_table); + +static const struct i2c_device_id mp3309c_id[] = { + { "mp3309c", 0 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, mp3309c_id); + +static struct i2c_driver mp3309c_i2c_driver = { + .driver = { + .name = KBUILD_MODNAME, + .of_match_table = mp3309c_match_table, + }, + .probe = mp3309c_probe, + .remove = mp3309c_remove, + .id_table = mp3309c_id, +}; + +module_i2c_driver(mp3309c_i2c_driver); + +MODULE_DESCRIPTION("Backlight Driver for MPS MP3309C"); +MODULE_AUTHOR("Flavio Suligoi <f.suligoi@asem.it>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c index 35c716e9043c..ffcebf6aa76a 100644 --- a/drivers/video/backlight/pwm_bl.c +++ b/drivers/video/backlight/pwm_bl.c @@ -461,10 +461,9 @@ static int pwm_backlight_probe(struct platform_device *pdev) if (!data) { ret = pwm_backlight_parse_dt(&pdev->dev, &defdata); - if (ret < 0) { - dev_err(&pdev->dev, "failed to find platform data\n"); - return ret; - } + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, + "failed to find platform data\n"); data = &defdata; } @@ -493,24 +492,27 @@ static int pwm_backlight_probe(struct platform_device *pdev) pb->enable_gpio = devm_gpiod_get_optional(&pdev->dev, "enable", GPIOD_ASIS); if (IS_ERR(pb->enable_gpio)) { - ret = PTR_ERR(pb->enable_gpio); + ret = dev_err_probe(&pdev->dev, PTR_ERR(pb->enable_gpio), + "failed to acquire enable GPIO\n"); goto err_alloc; } pb->power_supply = devm_regulator_get_optional(&pdev->dev, "power"); if (IS_ERR(pb->power_supply)) { ret = PTR_ERR(pb->power_supply); - if (ret == -ENODEV) + if (ret == -ENODEV) { pb->power_supply = NULL; - else + } else { + dev_err_probe(&pdev->dev, ret, + "failed to acquire power regulator\n"); goto err_alloc; + } } pb->pwm = devm_pwm_get(&pdev->dev, NULL); if (IS_ERR(pb->pwm)) { - ret = PTR_ERR(pb->pwm); - if (ret != -EPROBE_DEFER) - dev_err(&pdev->dev, "unable to request PWM\n"); + ret = dev_err_probe(&pdev->dev, PTR_ERR(pb->pwm), + "unable to request PWM\n"); goto err_alloc; } @@ -530,8 +532,8 @@ static int pwm_backlight_probe(struct platform_device *pdev) ret = pwm_apply_might_sleep(pb->pwm, &state); if (ret) { - dev_err(&pdev->dev, "failed to apply initial PWM state: %d\n", - ret); + dev_err_probe(&pdev->dev, ret, + "failed to apply initial PWM state"); goto err_alloc; } @@ -568,8 +570,8 @@ static int pwm_backlight_probe(struct platform_device *pdev) ret = pwm_backlight_brightness_default(&pdev->dev, data, state.period); if (ret < 0) { - dev_err(&pdev->dev, - "failed to setup default brightness table\n"); + dev_err_probe(&pdev->dev, ret, + "failed to setup default brightness table\n"); goto err_alloc; } @@ -597,8 +599,8 @@ static int pwm_backlight_probe(struct platform_device *pdev) bl = backlight_device_register(dev_name(&pdev->dev), &pdev->dev, pb, &pwm_backlight_ops, &props); if (IS_ERR(bl)) { - dev_err(&pdev->dev, "failed to register backlight\n"); - ret = PTR_ERR(bl); + ret = dev_err_probe(&pdev->dev, PTR_ERR(bl), + "failed to register backlight\n"); goto err_alloc; } diff --git a/drivers/video/fbdev/core/fb_ddc.c b/drivers/video/fbdev/core/fb_ddc.c index 8bf5f2f54be7..e25143219862 100644 --- a/drivers/video/fbdev/core/fb_ddc.c +++ b/drivers/video/fbdev/core/fb_ddc.c @@ -116,7 +116,6 @@ unsigned char *fb_ddc_read(struct i2c_adapter *adapter) algo_data->setsda(algo_data->data, 1); algo_data->setscl(algo_data->data, 1); - adapter->class |= I2C_CLASS_DDC; return edid; } diff --git a/drivers/video/fbdev/cyber2000fb.c b/drivers/video/fbdev/cyber2000fb.c index abb87d3576db..986760b90465 100644 --- a/drivers/video/fbdev/cyber2000fb.c +++ b/drivers/video/fbdev/cyber2000fb.c @@ -1227,7 +1227,6 @@ static int cyber2000fb_setup_ddc_bus(struct cfb_info *cfb) strscpy(cfb->ddc_adapter.name, cfb->fb.fix.id, sizeof(cfb->ddc_adapter.name)); cfb->ddc_adapter.owner = THIS_MODULE; - cfb->ddc_adapter.class = I2C_CLASS_DDC; cfb->ddc_adapter.algo_data = &cfb->ddc_algo; cfb->ddc_adapter.dev.parent = cfb->fb.device; cfb->ddc_algo.setsda = cyber2000fb_ddc_setsda; diff --git a/drivers/video/fbdev/i740fb.c b/drivers/video/fbdev/i740fb.c index 1897e65ab703..9b74dae71472 100644 --- a/drivers/video/fbdev/i740fb.c +++ b/drivers/video/fbdev/i740fb.c @@ -163,7 +163,6 @@ static int i740fb_setup_ddc_bus(struct fb_info *info) strscpy(par->ddc_adapter.name, info->fix.id, sizeof(par->ddc_adapter.name)); par->ddc_adapter.owner = THIS_MODULE; - par->ddc_adapter.class = I2C_CLASS_DDC; par->ddc_adapter.algo_data = &par->ddc_algo; par->ddc_adapter.dev.parent = info->device; par->ddc_algo.setsda = i740fb_ddc_setsda; diff --git a/drivers/video/fbdev/matrox/i2c-matroxfb.c b/drivers/video/fbdev/matrox/i2c-matroxfb.c index e2e4705e3fe0..bb048e14b2cf 100644 --- a/drivers/video/fbdev/matrox/i2c-matroxfb.c +++ b/drivers/video/fbdev/matrox/i2c-matroxfb.c @@ -100,8 +100,7 @@ static const struct i2c_algo_bit_data matrox_i2c_algo_template = }; static int i2c_bus_reg(struct i2c_bit_adapter* b, struct matrox_fb_info* minfo, - unsigned int data, unsigned int clock, const char *name, - int class) + unsigned int data, unsigned int clock, const char *name) { int err; @@ -112,7 +111,6 @@ static int i2c_bus_reg(struct i2c_bit_adapter* b, struct matrox_fb_info* minfo, snprintf(b->adapter.name, sizeof(b->adapter.name), name, minfo->fbcon.node); i2c_set_adapdata(&b->adapter, b); - b->adapter.class = class; b->adapter.algo_data = &b->bac; b->adapter.dev.parent = &minfo->pcidev->dev; b->bac = matrox_i2c_algo_template; @@ -160,27 +158,24 @@ static void* i2c_matroxfb_probe(struct matrox_fb_info* minfo) { case MGA_2164: err = i2c_bus_reg(&m2info->ddc1, minfo, DDC1B_DATA, DDC1B_CLK, - "DDC:fb%u #0", I2C_CLASS_DDC); + "DDC:fb%u #0"); break; default: err = i2c_bus_reg(&m2info->ddc1, minfo, DDC1_DATA, DDC1_CLK, - "DDC:fb%u #0", I2C_CLASS_DDC); + "DDC:fb%u #0"); break; } if (err) goto fail_ddc1; if (minfo->devflags.dualhead) { - err = i2c_bus_reg(&m2info->ddc2, minfo, - DDC2_DATA, DDC2_CLK, - "DDC:fb%u #1", I2C_CLASS_DDC); + err = i2c_bus_reg(&m2info->ddc2, minfo, DDC2_DATA, DDC2_CLK, "DDC:fb%u #1"); if (err == -ENODEV) { printk(KERN_INFO "i2c-matroxfb: VGA->TV plug detected, DDC unavailable.\n"); } else if (err) printk(KERN_INFO "i2c-matroxfb: Could not register secondary output i2c bus. Continuing anyway.\n"); /* Register maven bus even on G450/G550 */ - err = i2c_bus_reg(&m2info->maven, minfo, - MAT_DATA, MAT_CLK, "MAVEN:fb%u", 0); + err = i2c_bus_reg(&m2info->maven, minfo, MAT_DATA, MAT_CLK, "MAVEN:fb%u"); if (err) printk(KERN_INFO "i2c-matroxfb: Could not register Maven i2c bus. Continuing anyway.\n"); else { diff --git a/drivers/video/fbdev/s3fb.c b/drivers/video/fbdev/s3fb.c index 589b349cb63e..07722a5ea8ef 100644 --- a/drivers/video/fbdev/s3fb.c +++ b/drivers/video/fbdev/s3fb.c @@ -252,7 +252,6 @@ static int s3fb_setup_ddc_bus(struct fb_info *info) strscpy(par->ddc_adapter.name, info->fix.id, sizeof(par->ddc_adapter.name)); par->ddc_adapter.owner = THIS_MODULE; - par->ddc_adapter.class = I2C_CLASS_DDC; par->ddc_adapter.algo_data = &par->ddc_algo; par->ddc_adapter.dev.parent = info->device; par->ddc_algo.setsda = s3fb_ddc_setsda; diff --git a/drivers/video/fbdev/tdfxfb.c b/drivers/video/fbdev/tdfxfb.c index 22aa953138b0..51ebe78359ec 100644 --- a/drivers/video/fbdev/tdfxfb.c +++ b/drivers/video/fbdev/tdfxfb.c @@ -1267,7 +1267,6 @@ static int tdfxfb_setup_ddc_bus(struct tdfxfb_i2c_chan *chan, const char *name, strscpy(chan->adapter.name, name, sizeof(chan->adapter.name)); chan->adapter.owner = THIS_MODULE; - chan->adapter.class = I2C_CLASS_DDC; chan->adapter.algo_data = &chan->algo; chan->adapter.dev.parent = dev; chan->algo.setsda = tdfxfb_ddc_setsda; diff --git a/drivers/video/fbdev/tridentfb.c b/drivers/video/fbdev/tridentfb.c index 816d40b6f689..516cf2a18757 100644 --- a/drivers/video/fbdev/tridentfb.c +++ b/drivers/video/fbdev/tridentfb.c @@ -274,7 +274,6 @@ static int tridentfb_setup_ddc_bus(struct fb_info *info) strscpy(par->ddc_adapter.name, info->fix.id, sizeof(par->ddc_adapter.name)); par->ddc_adapter.owner = THIS_MODULE; - par->ddc_adapter.class = I2C_CLASS_DDC; par->ddc_adapter.algo_data = &par->ddc_algo; par->ddc_adapter.dev.parent = info->device; if (is_oldclock(par->chip_id)) { /* not sure if this check is OK */ diff --git a/drivers/video/fbdev/via/via_i2c.c b/drivers/video/fbdev/via/via_i2c.c index c35e530e0ec9..582502810575 100644 --- a/drivers/video/fbdev/via/via_i2c.c +++ b/drivers/video/fbdev/via/via_i2c.c @@ -201,7 +201,6 @@ static int create_i2c_bus(struct i2c_adapter *adapter, sprintf(adapter->name, "viafb i2c io_port idx 0x%02x", adap_cfg->ioport_index); adapter->owner = THIS_MODULE; - adapter->class = I2C_CLASS_DDC; adapter->algo_data = algo; if (pdev) adapter->dev.parent = &pdev->dev; diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 0a53a61231c2..c17193544268 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -60,6 +60,11 @@ config VIRTIO_PCI If unsure, say M. +config VIRTIO_PCI_ADMIN_LEGACY + bool + depends on VIRTIO_PCI && (X86 || COMPILE_TEST) + default y + config VIRTIO_PCI_LEGACY bool "Support for legacy virtio draft 0.9.X and older devices" default y diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile index 8e98d24917cc..73ace62af440 100644 --- a/drivers/virtio/Makefile +++ b/drivers/virtio/Makefile @@ -7,6 +7,7 @@ obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o +virtio_pci-$(CONFIG_VIRTIO_PCI_ADMIN_LEGACY) += virtio_pci_admin_legacy_io.o obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o obj-$(CONFIG_VIRTIO_VDPA) += virtio_vdpa.o diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 3893dc29eb26..f4080692b351 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -302,9 +302,15 @@ static int virtio_dev_probe(struct device *_d) if (err) goto err; + if (dev->config->create_avq) { + err = dev->config->create_avq(dev); + if (err) + goto err; + } + err = drv->probe(dev); if (err) - goto err; + goto err_probe; /* If probe didn't do it, mark device DRIVER_OK ourselves. */ if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK)) @@ -316,6 +322,10 @@ static int virtio_dev_probe(struct device *_d) virtio_config_enable(dev); return 0; + +err_probe: + if (dev->config->destroy_avq) + dev->config->destroy_avq(dev); err: virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED); return err; @@ -331,6 +341,9 @@ static void virtio_dev_remove(struct device *_d) drv->remove(dev); + if (dev->config->destroy_avq) + dev->config->destroy_avq(dev); + /* Driver should have reset device. */ WARN_ON_ONCE(dev->config->get_status(dev)); @@ -489,13 +502,20 @@ EXPORT_SYMBOL_GPL(unregister_virtio_device); int virtio_device_freeze(struct virtio_device *dev) { struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); + int ret; virtio_config_disable(dev); dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED; - if (drv && drv->freeze) - return drv->freeze(dev); + if (drv && drv->freeze) { + ret = drv->freeze(dev); + if (ret) + return ret; + } + + if (dev->config->destroy_avq) + dev->config->destroy_avq(dev); return 0; } @@ -532,10 +552,16 @@ int virtio_device_restore(struct virtio_device *dev) if (ret) goto err; + if (dev->config->create_avq) { + ret = dev->config->create_avq(dev); + if (ret) + goto err; + } + if (drv->restore) { ret = drv->restore(dev); if (ret) - goto err; + goto err_restore; } /* If restore didn't do it, mark device DRIVER_OK ourselves. */ @@ -546,6 +572,9 @@ int virtio_device_restore(struct virtio_device *dev) return 0; +err_restore: + if (dev->config->destroy_avq) + dev->config->destroy_avq(dev); err: virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED); return ret; diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 59cdc0292dce..1f5b3dd31fcf 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -119,6 +119,11 @@ struct virtio_balloon { /* Free page reporting device */ struct virtqueue *reporting_vq; struct page_reporting_dev_info pr_dev_info; + + /* State for keeping the wakeup_source active while adjusting the balloon */ + spinlock_t adjustment_lock; + bool adjustment_signal_pending; + bool adjustment_in_progress; }; static const struct virtio_device_id id_table[] = { @@ -437,6 +442,31 @@ static void virtio_balloon_queue_free_page_work(struct virtio_balloon *vb) queue_work(vb->balloon_wq, &vb->report_free_page_work); } +static void start_update_balloon_size(struct virtio_balloon *vb) +{ + unsigned long flags; + + spin_lock_irqsave(&vb->adjustment_lock, flags); + vb->adjustment_signal_pending = true; + if (!vb->adjustment_in_progress) { + vb->adjustment_in_progress = true; + pm_stay_awake(vb->vdev->dev.parent); + } + spin_unlock_irqrestore(&vb->adjustment_lock, flags); + + queue_work(system_freezable_wq, &vb->update_balloon_size_work); +} + +static void end_update_balloon_size(struct virtio_balloon *vb) +{ + spin_lock_irq(&vb->adjustment_lock); + if (!vb->adjustment_signal_pending && vb->adjustment_in_progress) { + vb->adjustment_in_progress = false; + pm_relax(vb->vdev->dev.parent); + } + spin_unlock_irq(&vb->adjustment_lock); +} + static void virtballoon_changed(struct virtio_device *vdev) { struct virtio_balloon *vb = vdev->priv; @@ -444,8 +474,7 @@ static void virtballoon_changed(struct virtio_device *vdev) spin_lock_irqsave(&vb->stop_update_lock, flags); if (!vb->stop_update) { - queue_work(system_freezable_wq, - &vb->update_balloon_size_work); + start_update_balloon_size(vb); virtio_balloon_queue_free_page_work(vb); } spin_unlock_irqrestore(&vb->stop_update_lock, flags); @@ -476,19 +505,25 @@ static void update_balloon_size_func(struct work_struct *work) vb = container_of(work, struct virtio_balloon, update_balloon_size_work); - diff = towards_target(vb); - if (!diff) - return; + spin_lock_irq(&vb->adjustment_lock); + vb->adjustment_signal_pending = false; + spin_unlock_irq(&vb->adjustment_lock); - if (diff > 0) - diff -= fill_balloon(vb, diff); - else - diff += leak_balloon(vb, -diff); - update_balloon_size(vb); + diff = towards_target(vb); + + if (diff) { + if (diff > 0) + diff -= fill_balloon(vb, diff); + else + diff += leak_balloon(vb, -diff); + update_balloon_size(vb); + } if (diff) queue_work(system_freezable_wq, work); + else + end_update_balloon_size(vb); } static int init_vqs(struct virtio_balloon *vb) @@ -992,6 +1027,8 @@ static int virtballoon_probe(struct virtio_device *vdev) goto out_unregister_oom; } + spin_lock_init(&vb->adjustment_lock); + virtio_device_ready(vdev); if (towards_target(vb)) diff --git a/drivers/virtio/virtio_pci_admin_legacy_io.c b/drivers/virtio/virtio_pci_admin_legacy_io.c new file mode 100644 index 000000000000..819cfbbc67c3 --- /dev/null +++ b/drivers/virtio/virtio_pci_admin_legacy_io.c @@ -0,0 +1,244 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved + */ + +#include <linux/virtio_pci_admin.h> +#include "virtio_pci_common.h" + +/* + * virtio_pci_admin_has_legacy_io - Checks whether the legacy IO + * commands are supported + * @dev: VF pci_dev + * + * Returns true on success. + */ +bool virtio_pci_admin_has_legacy_io(struct pci_dev *pdev) +{ + struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev); + struct virtio_pci_device *vp_dev; + + if (!virtio_dev) + return false; + + if (!virtio_has_feature(virtio_dev, VIRTIO_F_ADMIN_VQ)) + return false; + + vp_dev = to_vp_device(virtio_dev); + + if ((vp_dev->admin_vq.supported_cmds & VIRTIO_LEGACY_ADMIN_CMD_BITMAP) == + VIRTIO_LEGACY_ADMIN_CMD_BITMAP) + return true; + return false; +} +EXPORT_SYMBOL_GPL(virtio_pci_admin_has_legacy_io); + +static int virtio_pci_admin_legacy_io_write(struct pci_dev *pdev, u16 opcode, + u8 offset, u8 size, u8 *buf) +{ + struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev); + struct virtio_admin_cmd_legacy_wr_data *data; + struct virtio_admin_cmd cmd = {}; + struct scatterlist data_sg; + int vf_id; + int ret; + + if (!virtio_dev) + return -ENODEV; + + vf_id = pci_iov_vf_id(pdev); + if (vf_id < 0) + return vf_id; + + data = kzalloc(sizeof(*data) + size, GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->offset = offset; + memcpy(data->registers, buf, size); + sg_init_one(&data_sg, data, sizeof(*data) + size); + cmd.opcode = cpu_to_le16(opcode); + cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV); + cmd.group_member_id = cpu_to_le64(vf_id + 1); + cmd.data_sg = &data_sg; + ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd); + + kfree(data); + return ret; +} + +/* + * virtio_pci_admin_legacy_io_write_common - Write legacy common configuration + * of a member device + * @dev: VF pci_dev + * @offset: starting byte offset within the common configuration area to write to + * @size: size of the data to write + * @buf: buffer which holds the data + * + * Note: caller must serialize access for the given device. + * Returns 0 on success, or negative on failure. + */ +int virtio_pci_admin_legacy_common_io_write(struct pci_dev *pdev, u8 offset, + u8 size, u8 *buf) +{ + return virtio_pci_admin_legacy_io_write(pdev, + VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE, + offset, size, buf); +} +EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_common_io_write); + +/* + * virtio_pci_admin_legacy_io_write_device - Write legacy device configuration + * of a member device + * @dev: VF pci_dev + * @offset: starting byte offset within the device configuration area to write to + * @size: size of the data to write + * @buf: buffer which holds the data + * + * Note: caller must serialize access for the given device. + * Returns 0 on success, or negative on failure. + */ +int virtio_pci_admin_legacy_device_io_write(struct pci_dev *pdev, u8 offset, + u8 size, u8 *buf) +{ + return virtio_pci_admin_legacy_io_write(pdev, + VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE, + offset, size, buf); +} +EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_device_io_write); + +static int virtio_pci_admin_legacy_io_read(struct pci_dev *pdev, u16 opcode, + u8 offset, u8 size, u8 *buf) +{ + struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev); + struct virtio_admin_cmd_legacy_rd_data *data; + struct scatterlist data_sg, result_sg; + struct virtio_admin_cmd cmd = {}; + int vf_id; + int ret; + + if (!virtio_dev) + return -ENODEV; + + vf_id = pci_iov_vf_id(pdev); + if (vf_id < 0) + return vf_id; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->offset = offset; + sg_init_one(&data_sg, data, sizeof(*data)); + sg_init_one(&result_sg, buf, size); + cmd.opcode = cpu_to_le16(opcode); + cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV); + cmd.group_member_id = cpu_to_le64(vf_id + 1); + cmd.data_sg = &data_sg; + cmd.result_sg = &result_sg; + ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd); + + kfree(data); + return ret; +} + +/* + * virtio_pci_admin_legacy_device_io_read - Read legacy device configuration of + * a member device + * @dev: VF pci_dev + * @offset: starting byte offset within the device configuration area to read from + * @size: size of the data to be read + * @buf: buffer to hold the returned data + * + * Note: caller must serialize access for the given device. + * Returns 0 on success, or negative on failure. + */ +int virtio_pci_admin_legacy_device_io_read(struct pci_dev *pdev, u8 offset, + u8 size, u8 *buf) +{ + return virtio_pci_admin_legacy_io_read(pdev, + VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ, + offset, size, buf); +} +EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_device_io_read); + +/* + * virtio_pci_admin_legacy_common_io_read - Read legacy common configuration of + * a member device + * @dev: VF pci_dev + * @offset: starting byte offset within the common configuration area to read from + * @size: size of the data to be read + * @buf: buffer to hold the returned data + * + * Note: caller must serialize access for the given device. + * Returns 0 on success, or negative on failure. + */ +int virtio_pci_admin_legacy_common_io_read(struct pci_dev *pdev, u8 offset, + u8 size, u8 *buf) +{ + return virtio_pci_admin_legacy_io_read(pdev, + VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ, + offset, size, buf); +} +EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_common_io_read); + +/* + * virtio_pci_admin_legacy_io_notify_info - Read the queue notification + * information for legacy interface + * @dev: VF pci_dev + * @req_bar_flags: requested bar flags + * @bar: on output the BAR number of the owner or member device + * @bar_offset: on output the offset within bar + * + * Returns 0 on success, or negative on failure. + */ +int virtio_pci_admin_legacy_io_notify_info(struct pci_dev *pdev, + u8 req_bar_flags, u8 *bar, + u64 *bar_offset) +{ + struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev); + struct virtio_admin_cmd_notify_info_result *result; + struct virtio_admin_cmd cmd = {}; + struct scatterlist result_sg; + int vf_id; + int ret; + + if (!virtio_dev) + return -ENODEV; + + vf_id = pci_iov_vf_id(pdev); + if (vf_id < 0) + return vf_id; + + result = kzalloc(sizeof(*result), GFP_KERNEL); + if (!result) + return -ENOMEM; + + sg_init_one(&result_sg, result, sizeof(*result)); + cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO); + cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV); + cmd.group_member_id = cpu_to_le64(vf_id + 1); + cmd.result_sg = &result_sg; + ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd); + if (!ret) { + struct virtio_admin_cmd_notify_info_data *entry; + int i; + + ret = -ENOENT; + for (i = 0; i < VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO; i++) { + entry = &result->entries[i]; + if (entry->flags == VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_END) + break; + if (entry->flags != req_bar_flags) + continue; + *bar = entry->bar; + *bar_offset = le64_to_cpu(entry->offset); + ret = 0; + break; + } + } + + kfree(result); + return ret; +} +EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_io_notify_info); diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 7a5593997e0e..b655fccaf773 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -236,6 +236,9 @@ void vp_del_vqs(struct virtio_device *vdev) int i; list_for_each_entry_safe(vq, n, &vdev->vqs, list) { + if (vp_dev->is_avq(vdev, vq->index)) + continue; + if (vp_dev->per_vq_vectors) { int v = vp_dev->vqs[vq->index]->msix_vector; @@ -492,8 +495,40 @@ static int virtio_pci_restore(struct device *dev) return virtio_device_restore(&vp_dev->vdev); } +static bool vp_supports_pm_no_reset(struct device *dev) +{ + struct pci_dev *pci_dev = to_pci_dev(dev); + u16 pmcsr; + + if (!pci_dev->pm_cap) + return false; + + pci_read_config_word(pci_dev, pci_dev->pm_cap + PCI_PM_CTRL, &pmcsr); + if (PCI_POSSIBLE_ERROR(pmcsr)) { + dev_err(dev, "Unable to query pmcsr"); + return false; + } + + return pmcsr & PCI_PM_CTRL_NO_SOFT_RESET; +} + +static int virtio_pci_suspend(struct device *dev) +{ + return vp_supports_pm_no_reset(dev) ? 0 : virtio_pci_freeze(dev); +} + +static int virtio_pci_resume(struct device *dev) +{ + return vp_supports_pm_no_reset(dev) ? 0 : virtio_pci_restore(dev); +} + static const struct dev_pm_ops virtio_pci_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(virtio_pci_freeze, virtio_pci_restore) + .suspend = virtio_pci_suspend, + .resume = virtio_pci_resume, + .freeze = virtio_pci_freeze, + .thaw = virtio_pci_restore, + .poweroff = virtio_pci_freeze, + .restore = virtio_pci_restore, }; #endif @@ -642,6 +677,17 @@ static struct pci_driver virtio_pci_driver = { .sriov_configure = virtio_pci_sriov_configure, }; +struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev) +{ + struct virtio_pci_device *pf_vp_dev; + + pf_vp_dev = pci_iov_get_pf_drvdata(pdev, &virtio_pci_driver); + if (IS_ERR(pf_vp_dev)) + return NULL; + + return &pf_vp_dev->vdev; +} + module_pci_driver(virtio_pci_driver); MODULE_AUTHOR("Anthony Liguori <aliguori@us.ibm.com>"); diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index 4b773bd7c58c..7fef52bee455 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -29,6 +29,7 @@ #include <linux/virtio_pci_modern.h> #include <linux/highmem.h> #include <linux/spinlock.h> +#include <linux/mutex.h> struct virtio_pci_vq_info { /* the actual virtqueue */ @@ -41,6 +42,17 @@ struct virtio_pci_vq_info { unsigned int msix_vector; }; +struct virtio_pci_admin_vq { + /* Virtqueue info associated with this admin queue. */ + struct virtio_pci_vq_info info; + /* serializing admin commands execution and virtqueue deletion */ + struct mutex cmd_lock; + u64 supported_cmds; + /* Name of the admin queue: avq.$vq_index. */ + char name[10]; + u16 vq_index; +}; + /* Our device structure */ struct virtio_pci_device { struct virtio_device vdev; @@ -58,9 +70,13 @@ struct virtio_pci_device { spinlock_t lock; struct list_head virtqueues; - /* array of all queues for house-keeping */ + /* Array of all virtqueues reported in the + * PCI common config num_queues field + */ struct virtio_pci_vq_info **vqs; + struct virtio_pci_admin_vq admin_vq; + /* MSI-X support */ int msix_enabled; int intx_enabled; @@ -86,6 +102,7 @@ struct virtio_pci_device { void (*del_vq)(struct virtio_pci_vq_info *info); u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector); + bool (*is_avq)(struct virtio_device *vdev, unsigned int index); }; /* Constants for MSI-X */ @@ -139,4 +156,27 @@ static inline void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev) int virtio_pci_modern_probe(struct virtio_pci_device *); void virtio_pci_modern_remove(struct virtio_pci_device *); +struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev); + +#define VIRTIO_LEGACY_ADMIN_CMD_BITMAP \ + (BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE) | \ + BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ) | \ + BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE) | \ + BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ) | \ + BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO)) + +/* Unlike modern drivers which support hardware virtio devices, legacy drivers + * assume software-based devices: e.g. they don't use proper memory barriers + * on ARM, use big endian on PPC, etc. X86 drivers are mostly ok though, more + * or less by chance. For now, only support legacy IO on X86. + */ +#ifdef CONFIG_VIRTIO_PCI_ADMIN_LEGACY +#define VIRTIO_ADMIN_CMD_BITMAP VIRTIO_LEGACY_ADMIN_CMD_BITMAP +#else +#define VIRTIO_ADMIN_CMD_BITMAP 0 +#endif + +int vp_modern_admin_cmd_exec(struct virtio_device *vdev, + struct virtio_admin_cmd *cmd); + #endif diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index ee6a386d250b..f62b530aa3b5 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -19,6 +19,8 @@ #define VIRTIO_RING_NO_LEGACY #include "virtio_pci_common.h" +#define VIRTIO_AVQ_SGS_MAX 4 + static u64 vp_get_features(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); @@ -26,6 +28,187 @@ static u64 vp_get_features(struct virtio_device *vdev) return vp_modern_get_features(&vp_dev->mdev); } +static bool vp_is_avq(struct virtio_device *vdev, unsigned int index) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + + if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) + return false; + + return index == vp_dev->admin_vq.vq_index; +} + +static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq, + u16 opcode, + struct scatterlist **sgs, + unsigned int out_num, + unsigned int in_num, + void *data) +{ + struct virtqueue *vq; + int ret, len; + + vq = admin_vq->info.vq; + if (!vq) + return -EIO; + + if (opcode != VIRTIO_ADMIN_CMD_LIST_QUERY && + opcode != VIRTIO_ADMIN_CMD_LIST_USE && + !((1ULL << opcode) & admin_vq->supported_cmds)) + return -EOPNOTSUPP; + + ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, data, GFP_KERNEL); + if (ret < 0) + return -EIO; + + if (unlikely(!virtqueue_kick(vq))) + return -EIO; + + while (!virtqueue_get_buf(vq, &len) && + !virtqueue_is_broken(vq)) + cpu_relax(); + + if (virtqueue_is_broken(vq)) + return -EIO; + + return 0; +} + +int vp_modern_admin_cmd_exec(struct virtio_device *vdev, + struct virtio_admin_cmd *cmd) +{ + struct scatterlist *sgs[VIRTIO_AVQ_SGS_MAX], hdr, stat; + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_admin_cmd_status *va_status; + unsigned int out_num = 0, in_num = 0; + struct virtio_admin_cmd_hdr *va_hdr; + u16 status; + int ret; + + if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) + return -EOPNOTSUPP; + + va_status = kzalloc(sizeof(*va_status), GFP_KERNEL); + if (!va_status) + return -ENOMEM; + + va_hdr = kzalloc(sizeof(*va_hdr), GFP_KERNEL); + if (!va_hdr) { + ret = -ENOMEM; + goto err_alloc; + } + + va_hdr->opcode = cmd->opcode; + va_hdr->group_type = cmd->group_type; + va_hdr->group_member_id = cmd->group_member_id; + + /* Add header */ + sg_init_one(&hdr, va_hdr, sizeof(*va_hdr)); + sgs[out_num] = &hdr; + out_num++; + + if (cmd->data_sg) { + sgs[out_num] = cmd->data_sg; + out_num++; + } + + /* Add return status */ + sg_init_one(&stat, va_status, sizeof(*va_status)); + sgs[out_num + in_num] = &stat; + in_num++; + + if (cmd->result_sg) { + sgs[out_num + in_num] = cmd->result_sg; + in_num++; + } + + mutex_lock(&vp_dev->admin_vq.cmd_lock); + ret = virtqueue_exec_admin_cmd(&vp_dev->admin_vq, + le16_to_cpu(cmd->opcode), + sgs, out_num, in_num, sgs); + mutex_unlock(&vp_dev->admin_vq.cmd_lock); + + if (ret) { + dev_err(&vdev->dev, + "Failed to execute command on admin vq: %d\n.", ret); + goto err_cmd_exec; + } + + status = le16_to_cpu(va_status->status); + if (status != VIRTIO_ADMIN_STATUS_OK) { + dev_err(&vdev->dev, + "admin command error: status(%#x) qualifier(%#x)\n", + status, le16_to_cpu(va_status->status_qualifier)); + ret = -status; + } + +err_cmd_exec: + kfree(va_hdr); +err_alloc: + kfree(va_status); + return ret; +} + +static void virtio_pci_admin_cmd_list_init(struct virtio_device *virtio_dev) +{ + struct virtio_pci_device *vp_dev = to_vp_device(virtio_dev); + struct virtio_admin_cmd cmd = {}; + struct scatterlist result_sg; + struct scatterlist data_sg; + __le64 *data; + int ret; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return; + + sg_init_one(&result_sg, data, sizeof(*data)); + cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_LIST_QUERY); + cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV); + cmd.result_sg = &result_sg; + + ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd); + if (ret) + goto end; + + *data &= cpu_to_le64(VIRTIO_ADMIN_CMD_BITMAP); + sg_init_one(&data_sg, data, sizeof(*data)); + cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_LIST_USE); + cmd.data_sg = &data_sg; + cmd.result_sg = NULL; + + ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd); + if (ret) + goto end; + + vp_dev->admin_vq.supported_cmds = le64_to_cpu(*data); +end: + kfree(data); +} + +static void vp_modern_avq_activate(struct virtio_device *vdev) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq; + + if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) + return; + + __virtqueue_unbreak(admin_vq->info.vq); + virtio_pci_admin_cmd_list_init(vdev); +} + +static void vp_modern_avq_deactivate(struct virtio_device *vdev) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq; + + if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) + return; + + __virtqueue_break(admin_vq->info.vq); +} + static void vp_transport_features(struct virtio_device *vdev, u64 features) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); @@ -37,6 +220,9 @@ static void vp_transport_features(struct virtio_device *vdev, u64 features) if (features & BIT_ULL(VIRTIO_F_RING_RESET)) __virtio_set_bit(vdev, VIRTIO_F_RING_RESET); + + if (features & BIT_ULL(VIRTIO_F_ADMIN_VQ)) + __virtio_set_bit(vdev, VIRTIO_F_ADMIN_VQ); } static int __vp_check_common_size_one_feature(struct virtio_device *vdev, u32 fbit, @@ -69,6 +255,9 @@ static int vp_check_common_size(struct virtio_device *vdev) if (vp_check_common_size_one_feature(vdev, VIRTIO_F_RING_RESET, queue_reset)) return -EINVAL; + if (vp_check_common_size_one_feature(vdev, VIRTIO_F_ADMIN_VQ, admin_queue_num)) + return -EINVAL; + return 0; } @@ -195,6 +384,8 @@ static void vp_set_status(struct virtio_device *vdev, u8 status) /* We should never be setting status to 0. */ BUG_ON(status == 0); vp_modern_set_status(&vp_dev->mdev, status); + if (status & VIRTIO_CONFIG_S_DRIVER_OK) + vp_modern_avq_activate(vdev); } static void vp_reset(struct virtio_device *vdev) @@ -211,6 +402,9 @@ static void vp_reset(struct virtio_device *vdev) */ while (vp_modern_get_status(mdev)) msleep(1); + + vp_modern_avq_deactivate(vdev); + /* Flush pending VQ/configuration callbacks. */ vp_synchronize_vectors(vdev); } @@ -345,6 +539,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, struct virtio_pci_modern_device *mdev = &vp_dev->mdev; bool (*notify)(struct virtqueue *vq); struct virtqueue *vq; + bool is_avq; u16 num; int err; @@ -353,11 +548,13 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, else notify = vp_notify; - if (index >= vp_modern_get_num_queues(mdev)) + is_avq = vp_is_avq(&vp_dev->vdev, index); + if (index >= vp_modern_get_num_queues(mdev) && !is_avq) return ERR_PTR(-EINVAL); + num = is_avq ? + VIRTIO_AVQ_SGS_MAX : vp_modern_get_queue_size(mdev, index); /* Check if queue is either not available or already active. */ - num = vp_modern_get_queue_size(mdev, index); if (!num || vp_modern_get_queue_enable(mdev, index)) return ERR_PTR(-ENOENT); @@ -383,6 +580,12 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, goto err; } + if (is_avq) { + mutex_lock(&vp_dev->admin_vq.cmd_lock); + vp_dev->admin_vq.info.vq = vq; + mutex_unlock(&vp_dev->admin_vq.cmd_lock); + } + return vq; err: @@ -418,6 +621,12 @@ static void del_vq(struct virtio_pci_vq_info *info) struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); struct virtio_pci_modern_device *mdev = &vp_dev->mdev; + if (vp_is_avq(&vp_dev->vdev, vq->index)) { + mutex_lock(&vp_dev->admin_vq.cmd_lock); + vp_dev->admin_vq.info.vq = NULL; + mutex_unlock(&vp_dev->admin_vq.cmd_lock); + } + if (vp_dev->msix_enabled) vp_modern_queue_vector(mdev, vq->index, VIRTIO_MSI_NO_VECTOR); @@ -527,6 +736,45 @@ static bool vp_get_shm_region(struct virtio_device *vdev, return true; } +static int vp_modern_create_avq(struct virtio_device *vdev) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_admin_vq *avq; + struct virtqueue *vq; + u16 admin_q_num; + + if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) + return 0; + + admin_q_num = vp_modern_avq_num(&vp_dev->mdev); + if (!admin_q_num) + return -EINVAL; + + avq = &vp_dev->admin_vq; + avq->vq_index = vp_modern_avq_index(&vp_dev->mdev); + sprintf(avq->name, "avq.%u", avq->vq_index); + vq = vp_dev->setup_vq(vp_dev, &vp_dev->admin_vq.info, avq->vq_index, NULL, + avq->name, NULL, VIRTIO_MSI_NO_VECTOR); + if (IS_ERR(vq)) { + dev_err(&vdev->dev, "failed to setup admin virtqueue, err=%ld", + PTR_ERR(vq)); + return PTR_ERR(vq); + } + + vp_modern_set_queue_enable(&vp_dev->mdev, avq->info.vq->index, true); + return 0; +} + +static void vp_modern_destroy_avq(struct virtio_device *vdev) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + + if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) + return; + + vp_dev->del_vq(&vp_dev->admin_vq.info); +} + static const struct virtio_config_ops virtio_pci_config_nodev_ops = { .get = NULL, .set = NULL, @@ -545,6 +793,8 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = { .get_shm_region = vp_get_shm_region, .disable_vq_and_reset = vp_modern_disable_vq_and_reset, .enable_vq_after_reset = vp_modern_enable_vq_after_reset, + .create_avq = vp_modern_create_avq, + .destroy_avq = vp_modern_destroy_avq, }; static const struct virtio_config_ops virtio_pci_config_ops = { @@ -565,6 +815,8 @@ static const struct virtio_config_ops virtio_pci_config_ops = { .get_shm_region = vp_get_shm_region, .disable_vq_and_reset = vp_modern_disable_vq_and_reset, .enable_vq_after_reset = vp_modern_enable_vq_after_reset, + .create_avq = vp_modern_create_avq, + .destroy_avq = vp_modern_destroy_avq, }; /* the PCI probing function */ @@ -588,9 +840,11 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) vp_dev->config_vector = vp_config_vector; vp_dev->setup_vq = setup_vq; vp_dev->del_vq = del_vq; + vp_dev->is_avq = vp_is_avq; vp_dev->isr = mdev->isr; vp_dev->vdev.id = mdev->id; + mutex_init(&vp_dev->admin_vq.cmd_lock); return 0; } @@ -598,5 +852,6 @@ void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev) { struct virtio_pci_modern_device *mdev = &vp_dev->mdev; + mutex_destroy(&vp_dev->admin_vq.cmd_lock); vp_modern_remove(mdev); } diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c index 7de8b1ebabac..0d3dbfaf4b23 100644 --- a/drivers/virtio/virtio_pci_modern_dev.c +++ b/drivers/virtio/virtio_pci_modern_dev.c @@ -207,6 +207,10 @@ static inline void check_offsets(void) offsetof(struct virtio_pci_modern_common_cfg, queue_notify_data)); BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_RESET != offsetof(struct virtio_pci_modern_common_cfg, queue_reset)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_ADM_Q_IDX != + offsetof(struct virtio_pci_modern_common_cfg, admin_queue_index)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_ADM_Q_NUM != + offsetof(struct virtio_pci_modern_common_cfg, admin_queue_num)); } /* @@ -296,7 +300,7 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev) mdev->common = vp_modern_map_capability(mdev, common, sizeof(struct virtio_pci_common_cfg), 4, 0, offsetofend(struct virtio_pci_modern_common_cfg, - queue_reset), + admin_queue_num), &mdev->common_len, NULL); if (!mdev->common) goto err_map_common; @@ -719,6 +723,24 @@ void __iomem *vp_modern_map_vq_notify(struct virtio_pci_modern_device *mdev, } EXPORT_SYMBOL_GPL(vp_modern_map_vq_notify); +u16 vp_modern_avq_num(struct virtio_pci_modern_device *mdev) +{ + struct virtio_pci_modern_common_cfg __iomem *cfg; + + cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common; + return vp_ioread16(&cfg->admin_queue_num); +} +EXPORT_SYMBOL_GPL(vp_modern_avq_num); + +u16 vp_modern_avq_index(struct virtio_pci_modern_device *mdev) +{ + struct virtio_pci_modern_common_cfg __iomem *cfg; + + cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common; + return vp_ioread16(&cfg->admin_queue_index); +} +EXPORT_SYMBOL_GPL(vp_modern_avq_index); + MODULE_VERSION("0.1"); MODULE_DESCRIPTION("Modern Virtio PCI Device"); MODULE_AUTHOR("Jason Wang <jasowang@redhat.com>"); diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index 731e3d14b67d..0e8418066a48 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -42,6 +42,7 @@ struct inode *v9fs_alloc_inode(struct super_block *sb); void v9fs_free_inode(struct inode *inode); struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t rdev); +void v9fs_set_netfs_context(struct inode *inode); int v9fs_init_inode(struct v9fs_session_info *v9ses, struct inode *inode, umode_t mode, dev_t rdev); void v9fs_evict_inode(struct inode *inode); diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 8a635999a7d6..047855033d32 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -19,12 +19,45 @@ #include <linux/netfs.h> #include <net/9p/9p.h> #include <net/9p/client.h> +#include <trace/events/netfs.h> #include "v9fs.h" #include "v9fs_vfs.h" #include "cache.h" #include "fid.h" +static void v9fs_upload_to_server(struct netfs_io_subrequest *subreq) +{ + struct p9_fid *fid = subreq->rreq->netfs_priv; + int err, len; + + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); + len = p9_client_write(fid, subreq->start, &subreq->io_iter, &err); + netfs_write_subrequest_terminated(subreq, len ?: err, false); +} + +static void v9fs_upload_to_server_worker(struct work_struct *work) +{ + struct netfs_io_subrequest *subreq = + container_of(work, struct netfs_io_subrequest, work); + + v9fs_upload_to_server(subreq); +} + +/* + * Set up write requests for a writeback slice. We need to add a write request + * for each write we want to make. + */ +static void v9fs_create_write_requests(struct netfs_io_request *wreq, loff_t start, size_t len) +{ + struct netfs_io_subrequest *subreq; + + subreq = netfs_create_write_request(wreq, NETFS_UPLOAD_TO_SERVER, + start, len, v9fs_upload_to_server_worker); + if (subreq) + netfs_queue_write_request(subreq); +} + /** * v9fs_issue_read - Issue a read from 9P * @subreq: The read to make @@ -33,14 +66,10 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; struct p9_fid *fid = rreq->netfs_priv; - struct iov_iter to; - loff_t pos = subreq->start + subreq->transferred; - size_t len = subreq->len - subreq->transferred; int total, err; - iov_iter_xarray(&to, ITER_DEST, &rreq->mapping->i_pages, pos, len); - - total = p9_client_read(fid, pos, &to, &err); + total = p9_client_read(fid, subreq->start + subreq->transferred, + &subreq->io_iter, &err); /* if we just extended the file size, any portion not in * cache won't be on server and is zeroes */ @@ -50,25 +79,42 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq) } /** - * v9fs_init_request - Initialise a read request + * v9fs_init_request - Initialise a request * @rreq: The read request * @file: The file being read from */ static int v9fs_init_request(struct netfs_io_request *rreq, struct file *file) { - struct p9_fid *fid = file->private_data; - - BUG_ON(!fid); + struct p9_fid *fid; + bool writing = (rreq->origin == NETFS_READ_FOR_WRITE || + rreq->origin == NETFS_WRITEBACK || + rreq->origin == NETFS_WRITETHROUGH || + rreq->origin == NETFS_LAUNDER_WRITE || + rreq->origin == NETFS_UNBUFFERED_WRITE || + rreq->origin == NETFS_DIO_WRITE); + + if (file) { + fid = file->private_data; + if (!fid) + goto no_fid; + p9_fid_get(fid); + } else { + fid = v9fs_fid_find_inode(rreq->inode, writing, INVALID_UID, true); + if (!fid) + goto no_fid; + } /* we might need to read from a fid that was opened write-only * for read-modify-write of page cache, use the writeback fid * for that */ - WARN_ON(rreq->origin == NETFS_READ_FOR_WRITE && - !(fid->mode & P9_ORDWR)); - - p9_fid_get(fid); + WARN_ON(rreq->origin == NETFS_READ_FOR_WRITE && !(fid->mode & P9_ORDWR)); rreq->netfs_priv = fid; return 0; + +no_fid: + WARN_ONCE(1, "folio expected an open fid inode->i_ino=%lx\n", + rreq->inode->i_ino); + return -EINVAL; } /** @@ -82,281 +128,20 @@ static void v9fs_free_request(struct netfs_io_request *rreq) p9_fid_put(fid); } -/** - * v9fs_begin_cache_operation - Begin a cache operation for a read - * @rreq: The read request - */ -static int v9fs_begin_cache_operation(struct netfs_io_request *rreq) -{ -#ifdef CONFIG_9P_FSCACHE - struct fscache_cookie *cookie = v9fs_inode_cookie(V9FS_I(rreq->inode)); - - return fscache_begin_read_operation(&rreq->cache_resources, cookie); -#else - return -ENOBUFS; -#endif -} - const struct netfs_request_ops v9fs_req_ops = { .init_request = v9fs_init_request, .free_request = v9fs_free_request, - .begin_cache_operation = v9fs_begin_cache_operation, .issue_read = v9fs_issue_read, + .create_write_requests = v9fs_create_write_requests, }; -/** - * v9fs_release_folio - release the private state associated with a folio - * @folio: The folio to be released - * @gfp: The caller's allocation restrictions - * - * Returns true if the page can be released, false otherwise. - */ - -static bool v9fs_release_folio(struct folio *folio, gfp_t gfp) -{ - if (folio_test_private(folio)) - return false; -#ifdef CONFIG_9P_FSCACHE - if (folio_test_fscache(folio)) { - if (current_is_kswapd() || !(gfp & __GFP_FS)) - return false; - folio_wait_fscache(folio); - } - fscache_note_page_release(v9fs_inode_cookie(V9FS_I(folio_inode(folio)))); -#endif - return true; -} - -static void v9fs_invalidate_folio(struct folio *folio, size_t offset, - size_t length) -{ - folio_wait_fscache(folio); -} - -#ifdef CONFIG_9P_FSCACHE -static void v9fs_write_to_cache_done(void *priv, ssize_t transferred_or_error, - bool was_async) -{ - struct v9fs_inode *v9inode = priv; - __le32 version; - - if (IS_ERR_VALUE(transferred_or_error) && - transferred_or_error != -ENOBUFS) { - version = cpu_to_le32(v9inode->qid.version); - fscache_invalidate(v9fs_inode_cookie(v9inode), &version, - i_size_read(&v9inode->netfs.inode), 0); - } -} -#endif - -static int v9fs_vfs_write_folio_locked(struct folio *folio) -{ - struct inode *inode = folio_inode(folio); - loff_t start = folio_pos(folio); - loff_t i_size = i_size_read(inode); - struct iov_iter from; - size_t len = folio_size(folio); - struct p9_fid *writeback_fid; - int err; - struct v9fs_inode __maybe_unused *v9inode = V9FS_I(inode); - struct fscache_cookie __maybe_unused *cookie = v9fs_inode_cookie(v9inode); - - if (start >= i_size) - return 0; /* Simultaneous truncation occurred */ - - len = min_t(loff_t, i_size - start, len); - - iov_iter_xarray(&from, ITER_SOURCE, &folio_mapping(folio)->i_pages, start, len); - - writeback_fid = v9fs_fid_find_inode(inode, true, INVALID_UID, true); - if (!writeback_fid) { - WARN_ONCE(1, "folio expected an open fid inode->i_private=%p\n", - inode->i_private); - return -EINVAL; - } - - folio_wait_fscache(folio); - folio_start_writeback(folio); - - p9_client_write(writeback_fid, start, &from, &err); - -#ifdef CONFIG_9P_FSCACHE - if (err == 0 && - fscache_cookie_enabled(cookie) && - test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags)) { - folio_start_fscache(folio); - fscache_write_to_cache(v9fs_inode_cookie(v9inode), - folio_mapping(folio), start, len, i_size, - v9fs_write_to_cache_done, v9inode, - true); - } -#endif - - folio_end_writeback(folio); - p9_fid_put(writeback_fid); - - return err; -} - -static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc) -{ - struct folio *folio = page_folio(page); - int retval; - - p9_debug(P9_DEBUG_VFS, "folio %p\n", folio); - - retval = v9fs_vfs_write_folio_locked(folio); - if (retval < 0) { - if (retval == -EAGAIN) { - folio_redirty_for_writepage(wbc, folio); - retval = 0; - } else { - mapping_set_error(folio_mapping(folio), retval); - } - } else - retval = 0; - - folio_unlock(folio); - return retval; -} - -static int v9fs_launder_folio(struct folio *folio) -{ - int retval; - - if (folio_clear_dirty_for_io(folio)) { - retval = v9fs_vfs_write_folio_locked(folio); - if (retval) - return retval; - } - folio_wait_fscache(folio); - return 0; -} - -/** - * v9fs_direct_IO - 9P address space operation for direct I/O - * @iocb: target I/O control block - * @iter: The data/buffer to use - * - * The presence of v9fs_direct_IO() in the address space ops vector - * allowes open() O_DIRECT flags which would have failed otherwise. - * - * In the non-cached mode, we shunt off direct read and write requests before - * the VFS gets them, so this method should never be called. - * - * Direct IO is not 'yet' supported in the cached mode. Hence when - * this routine is called through generic_file_aio_read(), the read/write fails - * with an error. - * - */ -static ssize_t -v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) -{ - struct file *file = iocb->ki_filp; - loff_t pos = iocb->ki_pos; - ssize_t n; - int err = 0; - - if (iov_iter_rw(iter) == WRITE) { - n = p9_client_write(file->private_data, pos, iter, &err); - if (n) { - struct inode *inode = file_inode(file); - loff_t i_size = i_size_read(inode); - - if (pos + n > i_size) - inode_add_bytes(inode, pos + n - i_size); - } - } else { - n = p9_client_read(file->private_data, pos, iter, &err); - } - return n ? n : err; -} - -static int v9fs_write_begin(struct file *filp, struct address_space *mapping, - loff_t pos, unsigned int len, - struct page **subpagep, void **fsdata) -{ - int retval; - struct folio *folio; - struct v9fs_inode *v9inode = V9FS_I(mapping->host); - - p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping); - - /* Prefetch area to be written into the cache if we're caching this - * file. We need to do this before we get a lock on the page in case - * there's more than one writer competing for the same cache block. - */ - retval = netfs_write_begin(&v9inode->netfs, filp, mapping, pos, len, &folio, fsdata); - if (retval < 0) - return retval; - - *subpagep = &folio->page; - return retval; -} - -static int v9fs_write_end(struct file *filp, struct address_space *mapping, - loff_t pos, unsigned int len, unsigned int copied, - struct page *subpage, void *fsdata) -{ - loff_t last_pos = pos + copied; - struct folio *folio = page_folio(subpage); - struct inode *inode = mapping->host; - - p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping); - - if (!folio_test_uptodate(folio)) { - if (unlikely(copied < len)) { - copied = 0; - goto out; - } - - folio_mark_uptodate(folio); - } - - /* - * No need to use i_size_read() here, the i_size - * cannot change under us because we hold the i_mutex. - */ - if (last_pos > inode->i_size) { - inode_add_bytes(inode, last_pos - inode->i_size); - i_size_write(inode, last_pos); -#ifdef CONFIG_9P_FSCACHE - fscache_update_cookie(v9fs_inode_cookie(V9FS_I(inode)), NULL, - &last_pos); -#endif - } - folio_mark_dirty(folio); -out: - folio_unlock(folio); - folio_put(folio); - - return copied; -} - -#ifdef CONFIG_9P_FSCACHE -/* - * Mark a page as having been made dirty and thus needing writeback. We also - * need to pin the cache object to write back to. - */ -static bool v9fs_dirty_folio(struct address_space *mapping, struct folio *folio) -{ - struct v9fs_inode *v9inode = V9FS_I(mapping->host); - - return fscache_dirty_folio(mapping, folio, v9fs_inode_cookie(v9inode)); -} -#else -#define v9fs_dirty_folio filemap_dirty_folio -#endif - const struct address_space_operations v9fs_addr_operations = { - .read_folio = netfs_read_folio, - .readahead = netfs_readahead, - .dirty_folio = v9fs_dirty_folio, - .writepage = v9fs_vfs_writepage, - .write_begin = v9fs_write_begin, - .write_end = v9fs_write_end, - .release_folio = v9fs_release_folio, - .invalidate_folio = v9fs_invalidate_folio, - .launder_folio = v9fs_launder_folio, - .direct_IO = v9fs_direct_IO, + .read_folio = netfs_read_folio, + .readahead = netfs_readahead, + .dirty_folio = netfs_dirty_folio, + .release_folio = netfs_release_folio, + .invalidate_folio = netfs_invalidate_folio, + .launder_folio = netfs_launder_folio, + .direct_IO = noop_direct_IO, + .writepages = netfs_writepages, }; diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 11cd8d23f6f2..bae330c2f0cf 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -353,25 +353,15 @@ static ssize_t v9fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct p9_fid *fid = iocb->ki_filp->private_data; - int ret, err = 0; p9_debug(P9_DEBUG_VFS, "fid %d count %zu offset %lld\n", fid->fid, iov_iter_count(to), iocb->ki_pos); - if (!(fid->mode & P9L_DIRECT)) { - p9_debug(P9_DEBUG_VFS, "(cached)\n"); - return generic_file_read_iter(iocb, to); - } - - if (iocb->ki_filp->f_flags & O_NONBLOCK) - ret = p9_client_read_once(fid, iocb->ki_pos, to, &err); - else - ret = p9_client_read(fid, iocb->ki_pos, to, &err); - if (!ret) - return err; + if (fid->mode & P9L_DIRECT) + return netfs_unbuffered_read_iter(iocb, to); - iocb->ki_pos += ret; - return ret; + p9_debug(P9_DEBUG_VFS, "(cached)\n"); + return netfs_file_read_iter(iocb, to); } /* @@ -407,46 +397,14 @@ v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct p9_fid *fid = file->private_data; - ssize_t retval; - loff_t origin; - int err = 0; p9_debug(P9_DEBUG_VFS, "fid %d\n", fid->fid); - if (!(fid->mode & (P9L_DIRECT | P9L_NOWRITECACHE))) { - p9_debug(P9_DEBUG_CACHE, "(cached)\n"); - return generic_file_write_iter(iocb, from); - } + if (fid->mode & (P9L_DIRECT | P9L_NOWRITECACHE)) + return netfs_unbuffered_write_iter(iocb, from); - retval = generic_write_checks(iocb, from); - if (retval <= 0) - return retval; - - origin = iocb->ki_pos; - retval = p9_client_write(file->private_data, iocb->ki_pos, from, &err); - if (retval > 0) { - struct inode *inode = file_inode(file); - loff_t i_size; - unsigned long pg_start, pg_end; - - pg_start = origin >> PAGE_SHIFT; - pg_end = (origin + retval - 1) >> PAGE_SHIFT; - if (inode->i_mapping && inode->i_mapping->nrpages) - invalidate_inode_pages2_range(inode->i_mapping, - pg_start, pg_end); - iocb->ki_pos += retval; - i_size = i_size_read(inode); - if (iocb->ki_pos > i_size) { - inode_add_bytes(inode, iocb->ki_pos - i_size); - /* - * Need to serialize against i_size_write() in - * v9fs_stat2inode() - */ - v9fs_i_size_write(inode, iocb->ki_pos); - } - return retval; - } - return err; + p9_debug(P9_DEBUG_CACHE, "(cached)\n"); + return netfs_file_write_iter(iocb, from); } static int v9fs_file_fsync(struct file *filp, loff_t start, loff_t end, @@ -519,36 +477,7 @@ v9fs_file_mmap(struct file *filp, struct vm_area_struct *vma) static vm_fault_t v9fs_vm_page_mkwrite(struct vm_fault *vmf) { - struct folio *folio = page_folio(vmf->page); - struct file *filp = vmf->vma->vm_file; - struct inode *inode = file_inode(filp); - - - p9_debug(P9_DEBUG_VFS, "folio %p fid %lx\n", - folio, (unsigned long)filp->private_data); - - /* Wait for the page to be written to the cache before we allow it to - * be modified. We then assume the entire page will need writing back. - */ -#ifdef CONFIG_9P_FSCACHE - if (folio_test_fscache(folio) && - folio_wait_fscache_killable(folio) < 0) - return VM_FAULT_NOPAGE; -#endif - - /* Update file times before taking page lock */ - file_update_time(filp); - - if (folio_lock_killable(folio) < 0) - return VM_FAULT_RETRY; - if (folio_mapping(folio) != inode->i_mapping) - goto out_unlock; - folio_wait_stable(folio); - - return VM_FAULT_LOCKED; -out_unlock: - folio_unlock(folio); - return VM_FAULT_NOPAGE; + return netfs_page_mkwrite(vmf, NULL); } static void v9fs_mmap_vm_close(struct vm_area_struct *vma) diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index b845ee18a80b..32572982f72e 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -246,10 +246,10 @@ void v9fs_free_inode(struct inode *inode) /* * Set parameters for the netfs library */ -static void v9fs_set_netfs_context(struct inode *inode) +void v9fs_set_netfs_context(struct inode *inode) { struct v9fs_inode *v9inode = V9FS_I(inode); - netfs_inode_init(&v9inode->netfs, &v9fs_req_ops); + netfs_inode_init(&v9inode->netfs, &v9fs_req_ops, true); } int v9fs_init_inode(struct v9fs_session_info *v9ses, @@ -326,8 +326,6 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses, err = -EINVAL; goto error; } - - v9fs_set_netfs_context(inode); error: return err; @@ -359,6 +357,7 @@ struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t rdev) iput(inode); return ERR_PTR(err); } + v9fs_set_netfs_context(inode); return inode; } @@ -374,11 +373,8 @@ void v9fs_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); -#ifdef CONFIG_9P_FSCACHE version = cpu_to_le32(v9inode->qid.version); - fscache_clear_inode_writeback(v9fs_inode_cookie(v9inode), inode, - &version); -#endif + netfs_clear_inode_writeback(inode, &version); clear_inode(inode); filemap_fdatawrite(&inode->i_data); @@ -464,6 +460,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb, goto error; v9fs_stat2inode(st, inode, sb, 0); + v9fs_set_netfs_context(inode); v9fs_cache_inode_get_cookie(inode); unlock_new_inode(inode); return inode; @@ -1113,7 +1110,7 @@ static int v9fs_vfs_setattr(struct mnt_idmap *idmap, if ((iattr->ia_valid & ATTR_SIZE) && iattr->ia_size != i_size_read(inode)) { truncate_setsize(inode, iattr->ia_size); - truncate_pagecache(inode, iattr->ia_size); + netfs_resize_file(netfs_inode(inode), iattr->ia_size, true); #ifdef CONFIG_9P_FSCACHE if (v9ses->cache & CACHE_FSCACHE) { @@ -1181,6 +1178,7 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; + v9inode->netfs.remote_i_size = stat->length; if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE)) v9fs_i_size_write(inode, stat->length); /* not real number of blocks, but 512 byte ones ... */ diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index c7319af2f471..3505227e1704 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -128,6 +128,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb, goto error; v9fs_stat2inode_dotl(st, inode, 0); + v9fs_set_netfs_context(inode); v9fs_cache_inode_get_cookie(inode); retval = v9fs_get_acl(inode, fid); if (retval) @@ -598,7 +599,7 @@ int v9fs_vfs_setattr_dotl(struct mnt_idmap *idmap, if ((iattr->ia_valid & ATTR_SIZE) && iattr->ia_size != i_size_read(inode)) { truncate_setsize(inode, iattr->ia_size); - truncate_pagecache(inode, iattr->ia_size); + netfs_resize_file(netfs_inode(inode), iattr->ia_size, true); #ifdef CONFIG_9P_FSCACHE if (v9ses->cache & CACHE_FSCACHE) @@ -655,6 +656,7 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; + v9inode->netfs.remote_i_size = stat->st_size; if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE)) v9fs_i_size_write(inode, stat->st_size); inode->i_blocks = stat->st_blocks; @@ -683,8 +685,10 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, inode->i_mode = mode; } if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE) && - stat->st_result_mask & P9_STATS_SIZE) + stat->st_result_mask & P9_STATS_SIZE) { + v9inode->netfs.remote_i_size = stat->st_size; v9fs_i_size_write(inode, stat->st_size); + } if (stat->st_result_mask & P9_STATS_BLOCKS) inode->i_blocks = stat->st_blocks; } diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 73db55c050bf..941f7d0e0bfa 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -289,31 +289,21 @@ static int v9fs_drop_inode(struct inode *inode) static int v9fs_write_inode(struct inode *inode, struct writeback_control *wbc) { - struct v9fs_inode *v9inode; - /* * send an fsync request to server irrespective of * wbc->sync_mode. */ p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode); - - v9inode = V9FS_I(inode); - fscache_unpin_writeback(wbc, v9fs_inode_cookie(v9inode)); - - return 0; + return netfs_unpin_writeback(inode, wbc); } static int v9fs_write_inode_dotl(struct inode *inode, struct writeback_control *wbc) { - struct v9fs_inode *v9inode; - v9inode = V9FS_I(inode); p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode); - fscache_unpin_writeback(wbc, v9fs_inode_cookie(v9inode)); - - return 0; + return netfs_unpin_writeback(inode, wbc); } static const struct super_operations v9fs_super_ops = { diff --git a/fs/Kconfig b/fs/Kconfig index a3159831ba98..89fdbefd1075 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -144,7 +144,6 @@ source "fs/overlayfs/Kconfig" menu "Caches" source "fs/netfs/Kconfig" -source "fs/fscache/Kconfig" source "fs/cachefiles/Kconfig" endmenu diff --git a/fs/Makefile b/fs/Makefile index a6962c588962..c09016257f05 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -61,7 +61,6 @@ obj-$(CONFIG_DLM) += dlm/ # Do not add any filesystems before this line obj-$(CONFIG_NETFS_SUPPORT) += netfs/ -obj-$(CONFIG_FSCACHE) += fscache/ obj-$(CONFIG_REISERFS_FS) += reiserfs/ obj-$(CONFIG_EXT4_FS) += ext4/ # We place ext4 before ext2 so that clean ext3 root fs's do NOT mount using the diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index 2cd40ba601f1..d3bc4a2d7085 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -76,7 +76,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) /* there shouldn't be an existing inode */ BUG_ON(!(inode->i_state & I_NEW)); - netfs_inode_init(&vnode->netfs, NULL); + netfs_inode_init(&vnode->netfs, NULL, false); inode->i_size = 0; inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; if (root) { diff --git a/fs/afs/file.c b/fs/afs/file.c index 30914e0d9cb2..3d33b221d9ca 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -20,9 +20,6 @@ static int afs_file_mmap(struct file *file, struct vm_area_struct *vma); static int afs_symlink_read_folio(struct file *file, struct folio *folio); -static void afs_invalidate_folio(struct folio *folio, size_t offset, - size_t length); -static bool afs_release_folio(struct folio *folio, gfp_t gfp_flags); static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); static ssize_t afs_file_splice_read(struct file *in, loff_t *ppos, @@ -37,7 +34,7 @@ const struct file_operations afs_file_operations = { .release = afs_release, .llseek = generic_file_llseek, .read_iter = afs_file_read_iter, - .write_iter = afs_file_write, + .write_iter = netfs_file_write_iter, .mmap = afs_file_mmap, .splice_read = afs_file_splice_read, .splice_write = iter_file_splice_write, @@ -53,22 +50,21 @@ const struct inode_operations afs_file_inode_operations = { }; const struct address_space_operations afs_file_aops = { + .direct_IO = noop_direct_IO, .read_folio = netfs_read_folio, .readahead = netfs_readahead, - .dirty_folio = afs_dirty_folio, - .launder_folio = afs_launder_folio, - .release_folio = afs_release_folio, - .invalidate_folio = afs_invalidate_folio, - .write_begin = afs_write_begin, - .write_end = afs_write_end, - .writepages = afs_writepages, + .dirty_folio = netfs_dirty_folio, + .launder_folio = netfs_launder_folio, + .release_folio = netfs_release_folio, + .invalidate_folio = netfs_invalidate_folio, .migrate_folio = filemap_migrate_folio, + .writepages = afs_writepages, }; const struct address_space_operations afs_symlink_aops = { .read_folio = afs_symlink_read_folio, - .release_folio = afs_release_folio, - .invalidate_folio = afs_invalidate_folio, + .release_folio = netfs_release_folio, + .invalidate_folio = netfs_invalidate_folio, .migrate_folio = filemap_migrate_folio, }; @@ -323,11 +319,7 @@ static void afs_issue_read(struct netfs_io_subrequest *subreq) fsreq->len = subreq->len - subreq->transferred; fsreq->key = key_get(subreq->rreq->netfs_priv); fsreq->vnode = vnode; - fsreq->iter = &fsreq->def_iter; - - iov_iter_xarray(&fsreq->def_iter, ITER_DEST, - &fsreq->vnode->netfs.inode.i_mapping->i_pages, - fsreq->pos, fsreq->len); + fsreq->iter = &subreq->io_iter; afs_fetch_data(fsreq->vnode, fsreq); afs_put_read(fsreq); @@ -359,22 +351,13 @@ static int afs_symlink_read_folio(struct file *file, struct folio *folio) static int afs_init_request(struct netfs_io_request *rreq, struct file *file) { - rreq->netfs_priv = key_get(afs_file_key(file)); + if (file) + rreq->netfs_priv = key_get(afs_file_key(file)); + rreq->rsize = 256 * 1024; + rreq->wsize = 256 * 1024; return 0; } -static int afs_begin_cache_operation(struct netfs_io_request *rreq) -{ -#ifdef CONFIG_AFS_FSCACHE - struct afs_vnode *vnode = AFS_FS_I(rreq->inode); - - return fscache_begin_read_operation(&rreq->cache_resources, - afs_vnode_cache(vnode)); -#else - return -ENOBUFS; -#endif -} - static int afs_check_write_begin(struct file *file, loff_t pos, unsigned len, struct folio **foliop, void **_fsdata) { @@ -388,128 +371,37 @@ static void afs_free_request(struct netfs_io_request *rreq) key_put(rreq->netfs_priv); } -const struct netfs_request_ops afs_req_ops = { - .init_request = afs_init_request, - .free_request = afs_free_request, - .begin_cache_operation = afs_begin_cache_operation, - .check_write_begin = afs_check_write_begin, - .issue_read = afs_issue_read, -}; - -int afs_write_inode(struct inode *inode, struct writeback_control *wbc) +static void afs_update_i_size(struct inode *inode, loff_t new_i_size) { - fscache_unpin_writeback(wbc, afs_vnode_cache(AFS_FS_I(inode))); - return 0; -} - -/* - * Adjust the dirty region of the page on truncation or full invalidation, - * getting rid of the markers altogether if the region is entirely invalidated. - */ -static void afs_invalidate_dirty(struct folio *folio, size_t offset, - size_t length) -{ - struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio)); - unsigned long priv; - unsigned int f, t, end = offset + length; - - priv = (unsigned long)folio_get_private(folio); - - /* we clean up only if the entire page is being invalidated */ - if (offset == 0 && length == folio_size(folio)) - goto full_invalidate; - - /* If the page was dirtied by page_mkwrite(), the PTE stays writable - * and we don't get another notification to tell us to expand it - * again. - */ - if (afs_is_folio_dirty_mmapped(priv)) - return; - - /* We may need to shorten the dirty region */ - f = afs_folio_dirty_from(folio, priv); - t = afs_folio_dirty_to(folio, priv); - - if (t <= offset || f >= end) - return; /* Doesn't overlap */ - - if (f < offset && t > end) - return; /* Splits the dirty region - just absorb it */ - - if (f >= offset && t <= end) - goto undirty; + struct afs_vnode *vnode = AFS_FS_I(inode); + loff_t i_size; - if (f < offset) - t = offset; - else - f = end; - if (f == t) - goto undirty; - - priv = afs_folio_dirty(folio, f, t); - folio_change_private(folio, (void *)priv); - trace_afs_folio_dirty(vnode, tracepoint_string("trunc"), folio); - return; - -undirty: - trace_afs_folio_dirty(vnode, tracepoint_string("undirty"), folio); - folio_clear_dirty_for_io(folio); -full_invalidate: - trace_afs_folio_dirty(vnode, tracepoint_string("inval"), folio); - folio_detach_private(folio); + write_seqlock(&vnode->cb_lock); + i_size = i_size_read(&vnode->netfs.inode); + if (new_i_size > i_size) { + i_size_write(&vnode->netfs.inode, new_i_size); + inode_set_bytes(&vnode->netfs.inode, new_i_size); + } + write_sequnlock(&vnode->cb_lock); + fscache_update_cookie(afs_vnode_cache(vnode), NULL, &new_i_size); } -/* - * invalidate part or all of a page - * - release a page and clean up its private data if offset is 0 (indicating - * the entire page) - */ -static void afs_invalidate_folio(struct folio *folio, size_t offset, - size_t length) +static void afs_netfs_invalidate_cache(struct netfs_io_request *wreq) { - _enter("{%lu},%zu,%zu", folio->index, offset, length); - - BUG_ON(!folio_test_locked(folio)); + struct afs_vnode *vnode = AFS_FS_I(wreq->inode); - if (folio_get_private(folio)) - afs_invalidate_dirty(folio, offset, length); - - folio_wait_fscache(folio); - _leave(""); + afs_invalidate_cache(vnode, 0); } -/* - * release a page and clean up its private state if it's not busy - * - return true if the page can now be released, false if not - */ -static bool afs_release_folio(struct folio *folio, gfp_t gfp) -{ - struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio)); - - _enter("{{%llx:%llu}[%lu],%lx},%x", - vnode->fid.vid, vnode->fid.vnode, folio_index(folio), folio->flags, - gfp); - - /* deny if folio is being written to the cache and the caller hasn't - * elected to wait */ -#ifdef CONFIG_AFS_FSCACHE - if (folio_test_fscache(folio)) { - if (current_is_kswapd() || !(gfp & __GFP_FS)) - return false; - folio_wait_fscache(folio); - } - fscache_note_page_release(afs_vnode_cache(vnode)); -#endif - - if (folio_test_private(folio)) { - trace_afs_folio_dirty(vnode, tracepoint_string("rel"), folio); - folio_detach_private(folio); - } - - /* Indicate that the folio can be released */ - _leave(" = T"); - return true; -} +const struct netfs_request_ops afs_req_ops = { + .init_request = afs_init_request, + .free_request = afs_free_request, + .check_write_begin = afs_check_write_begin, + .issue_read = afs_issue_read, + .update_i_size = afs_update_i_size, + .invalidate_cache = afs_netfs_invalidate_cache, + .create_write_requests = afs_create_write_requests, +}; static void afs_add_open_mmap(struct afs_vnode *vnode) { @@ -576,28 +468,39 @@ static vm_fault_t afs_vm_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pg static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { - struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp)); + struct inode *inode = file_inode(iocb->ki_filp); + struct afs_vnode *vnode = AFS_FS_I(inode); struct afs_file *af = iocb->ki_filp->private_data; - int ret; + ssize_t ret; - ret = afs_validate(vnode, af->key); + if (iocb->ki_flags & IOCB_DIRECT) + return netfs_unbuffered_read_iter(iocb, iter); + + ret = netfs_start_io_read(inode); if (ret < 0) return ret; - - return generic_file_read_iter(iocb, iter); + ret = afs_validate(vnode, af->key); + if (ret == 0) + ret = filemap_read(iocb, iter, 0); + netfs_end_io_read(inode); + return ret; } static ssize_t afs_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { - struct afs_vnode *vnode = AFS_FS_I(file_inode(in)); + struct inode *inode = file_inode(in); + struct afs_vnode *vnode = AFS_FS_I(inode); struct afs_file *af = in->private_data; - int ret; + ssize_t ret; - ret = afs_validate(vnode, af->key); + ret = netfs_start_io_read(inode); if (ret < 0) return ret; - - return filemap_splice_read(in, ppos, pipe, len, flags); + ret = afs_validate(vnode, af->key); + if (ret == 0) + ret = filemap_splice_read(in, ppos, pipe, len, flags); + netfs_end_io_read(inode); + return ret; } diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 4f04f6f33f46..94fc049aff58 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -58,7 +58,7 @@ static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *paren */ static void afs_set_netfs_context(struct afs_vnode *vnode) { - netfs_inode_init(&vnode->netfs, &afs_req_ops); + netfs_inode_init(&vnode->netfs, &afs_req_ops, true); } /* @@ -166,6 +166,7 @@ static void afs_apply_status(struct afs_operation *op, struct inode *inode = &vnode->netfs.inode; struct timespec64 t; umode_t mode; + bool unexpected_jump = false; bool data_changed = false; bool change_size = vp->set_size; @@ -230,6 +231,7 @@ static void afs_apply_status(struct afs_operation *op, } change_size = true; data_changed = true; + unexpected_jump = true; } else if (vnode->status.type == AFS_FTYPE_DIR) { /* Expected directory change is handled elsewhere so * that we can locally edit the directory and save on a @@ -249,8 +251,10 @@ static void afs_apply_status(struct afs_operation *op, * what's on the server. */ vnode->netfs.remote_i_size = status->size; - if (change_size) { + if (change_size || status->size > i_size_read(inode)) { afs_set_i_size(vnode, status->size); + if (unexpected_jump) + vnode->netfs.zero_point = status->size; inode_set_ctime_to_ts(inode, t); inode_set_atime_to_ts(inode, t); } @@ -647,7 +651,7 @@ void afs_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); afs_set_cache_aux(vnode, &aux); - fscache_clear_inode_writeback(afs_vnode_cache(vnode), inode, &aux); + netfs_clear_inode_writeback(inode, &aux); clear_inode(inode); while (!list_empty(&vnode->wb_keys)) { @@ -689,17 +693,17 @@ static void afs_setattr_success(struct afs_operation *op) static void afs_setattr_edit_file(struct afs_operation *op) { struct afs_vnode_param *vp = &op->file[0]; - struct inode *inode = &vp->vnode->netfs.inode; + struct afs_vnode *vnode = vp->vnode; if (op->setattr.attr->ia_valid & ATTR_SIZE) { loff_t size = op->setattr.attr->ia_size; loff_t i_size = op->setattr.old_i_size; - if (size < i_size) - truncate_pagecache(inode, size); - if (size != i_size) - fscache_resize_cookie(afs_vnode_cache(vp->vnode), - vp->scb.status.size); + if (size != i_size) { + truncate_setsize(&vnode->netfs.inode, size); + netfs_resize_file(&vnode->netfs, size, true); + fscache_resize_cookie(afs_vnode_cache(vnode), size); + } } } @@ -767,11 +771,11 @@ int afs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, */ if (!(attr->ia_valid & (supported & ~ATTR_SIZE & ~ATTR_MTIME)) && attr->ia_size < i_size && - attr->ia_size > vnode->status.size) { - truncate_pagecache(inode, attr->ia_size); + attr->ia_size > vnode->netfs.remote_i_size) { + truncate_setsize(inode, attr->ia_size); + netfs_resize_file(&vnode->netfs, size, false); fscache_resize_cookie(afs_vnode_cache(vnode), attr->ia_size); - i_size_write(inode, attr->ia_size); ret = 0; goto out_unlock; } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 55aa0679d8ce..9c03fcf7ffaa 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -985,62 +985,6 @@ static inline void afs_invalidate_cache(struct afs_vnode *vnode, unsigned int fl i_size_read(&vnode->netfs.inode), flags); } -/* - * We use folio->private to hold the amount of the folio that we've written to, - * splitting the field into two parts. However, we need to represent a range - * 0...FOLIO_SIZE, so we reduce the resolution if the size of the folio - * exceeds what we can encode. - */ -#ifdef CONFIG_64BIT -#define __AFS_FOLIO_PRIV_MASK 0x7fffffffUL -#define __AFS_FOLIO_PRIV_SHIFT 32 -#define __AFS_FOLIO_PRIV_MMAPPED 0x80000000UL -#else -#define __AFS_FOLIO_PRIV_MASK 0x7fffUL -#define __AFS_FOLIO_PRIV_SHIFT 16 -#define __AFS_FOLIO_PRIV_MMAPPED 0x8000UL -#endif - -static inline unsigned int afs_folio_dirty_resolution(struct folio *folio) -{ - int shift = folio_shift(folio) - (__AFS_FOLIO_PRIV_SHIFT - 1); - return (shift > 0) ? shift : 0; -} - -static inline size_t afs_folio_dirty_from(struct folio *folio, unsigned long priv) -{ - unsigned long x = priv & __AFS_FOLIO_PRIV_MASK; - - /* The lower bound is inclusive */ - return x << afs_folio_dirty_resolution(folio); -} - -static inline size_t afs_folio_dirty_to(struct folio *folio, unsigned long priv) -{ - unsigned long x = (priv >> __AFS_FOLIO_PRIV_SHIFT) & __AFS_FOLIO_PRIV_MASK; - - /* The upper bound is immediately beyond the region */ - return (x + 1) << afs_folio_dirty_resolution(folio); -} - -static inline unsigned long afs_folio_dirty(struct folio *folio, size_t from, size_t to) -{ - unsigned int res = afs_folio_dirty_resolution(folio); - from >>= res; - to = (to - 1) >> res; - return (to << __AFS_FOLIO_PRIV_SHIFT) | from; -} - -static inline unsigned long afs_folio_dirty_mmapped(unsigned long priv) -{ - return priv | __AFS_FOLIO_PRIV_MMAPPED; -} - -static inline bool afs_is_folio_dirty_mmapped(unsigned long priv) -{ - return priv & __AFS_FOLIO_PRIV_MMAPPED; -} - #include <trace/events/afs.h> /*****************************************************************************/ @@ -1167,7 +1111,6 @@ extern int afs_release(struct inode *, struct file *); extern int afs_fetch_data(struct afs_vnode *, struct afs_read *); extern struct afs_read *afs_alloc_read(gfp_t); extern void afs_put_read(struct afs_read *); -extern int afs_write_inode(struct inode *, struct writeback_control *); static inline struct afs_read *afs_get_read(struct afs_read *req) { @@ -1658,24 +1601,11 @@ extern int afs_check_volume_status(struct afs_volume *, struct afs_operation *); /* * write.c */ -#ifdef CONFIG_AFS_FSCACHE -bool afs_dirty_folio(struct address_space *, struct folio *); -#else -#define afs_dirty_folio filemap_dirty_folio -#endif -extern int afs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, - struct page **pagep, void **fsdata); -extern int afs_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); -extern int afs_writepage(struct page *, struct writeback_control *); extern int afs_writepages(struct address_space *, struct writeback_control *); -extern ssize_t afs_file_write(struct kiocb *, struct iov_iter *); extern int afs_fsync(struct file *, loff_t, loff_t, int); extern vm_fault_t afs_page_mkwrite(struct vm_fault *vmf); extern void afs_prune_wb_keys(struct afs_vnode *); -int afs_launder_folio(struct folio *); +void afs_create_write_requests(struct netfs_io_request *wreq, loff_t start, size_t len); /* * xattr.c diff --git a/fs/afs/super.c b/fs/afs/super.c index ae2d66a52add..f3ba1c3e72f5 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -55,7 +55,7 @@ int afs_net_id; static const struct super_operations afs_super_ops = { .statfs = afs_statfs, .alloc_inode = afs_alloc_inode, - .write_inode = afs_write_inode, + .write_inode = netfs_unpin_writeback, .drop_inode = afs_drop_inode, .destroy_inode = afs_destroy_inode, .free_inode = afs_free_inode, diff --git a/fs/afs/write.c b/fs/afs/write.c index 61d34ad2ca7d..74402d95a884 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -12,309 +12,17 @@ #include <linux/writeback.h> #include <linux/pagevec.h> #include <linux/netfs.h> +#include <trace/events/netfs.h> #include "internal.h" -static int afs_writepages_region(struct address_space *mapping, - struct writeback_control *wbc, - loff_t start, loff_t end, loff_t *_next, - bool max_one_loop); - -static void afs_write_to_cache(struct afs_vnode *vnode, loff_t start, size_t len, - loff_t i_size, bool caching); - -#ifdef CONFIG_AFS_FSCACHE -/* - * Mark a page as having been made dirty and thus needing writeback. We also - * need to pin the cache object to write back to. - */ -bool afs_dirty_folio(struct address_space *mapping, struct folio *folio) -{ - return fscache_dirty_folio(mapping, folio, - afs_vnode_cache(AFS_FS_I(mapping->host))); -} -static void afs_folio_start_fscache(bool caching, struct folio *folio) -{ - if (caching) - folio_start_fscache(folio); -} -#else -static void afs_folio_start_fscache(bool caching, struct folio *folio) -{ -} -#endif - -/* - * Flush out a conflicting write. This may extend the write to the surrounding - * pages if also dirty and contiguous to the conflicting region.. - */ -static int afs_flush_conflicting_write(struct address_space *mapping, - struct folio *folio) -{ - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL, - .nr_to_write = LONG_MAX, - .range_start = folio_pos(folio), - .range_end = LLONG_MAX, - }; - loff_t next; - - return afs_writepages_region(mapping, &wbc, folio_pos(folio), LLONG_MAX, - &next, true); -} - -/* - * prepare to perform part of a write to a page - */ -int afs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, - struct page **_page, void **fsdata) -{ - struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); - struct folio *folio; - unsigned long priv; - unsigned f, from; - unsigned t, to; - pgoff_t index; - int ret; - - _enter("{%llx:%llu},%llx,%x", - vnode->fid.vid, vnode->fid.vnode, pos, len); - - /* Prefetch area to be written into the cache if we're caching this - * file. We need to do this before we get a lock on the page in case - * there's more than one writer competing for the same cache block. - */ - ret = netfs_write_begin(&vnode->netfs, file, mapping, pos, len, &folio, fsdata); - if (ret < 0) - return ret; - - index = folio_index(folio); - from = pos - index * PAGE_SIZE; - to = from + len; - -try_again: - /* See if this page is already partially written in a way that we can - * merge the new write with. - */ - if (folio_test_private(folio)) { - priv = (unsigned long)folio_get_private(folio); - f = afs_folio_dirty_from(folio, priv); - t = afs_folio_dirty_to(folio, priv); - ASSERTCMP(f, <=, t); - - if (folio_test_writeback(folio)) { - trace_afs_folio_dirty(vnode, tracepoint_string("alrdy"), folio); - folio_unlock(folio); - goto wait_for_writeback; - } - /* If the file is being filled locally, allow inter-write - * spaces to be merged into writes. If it's not, only write - * back what the user gives us. - */ - if (!test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags) && - (to < f || from > t)) - goto flush_conflicting_write; - } - - *_page = folio_file_page(folio, pos / PAGE_SIZE); - _leave(" = 0"); - return 0; - - /* The previous write and this write aren't adjacent or overlapping, so - * flush the page out. - */ -flush_conflicting_write: - trace_afs_folio_dirty(vnode, tracepoint_string("confl"), folio); - folio_unlock(folio); - - ret = afs_flush_conflicting_write(mapping, folio); - if (ret < 0) - goto error; - -wait_for_writeback: - ret = folio_wait_writeback_killable(folio); - if (ret < 0) - goto error; - - ret = folio_lock_killable(folio); - if (ret < 0) - goto error; - goto try_again; - -error: - folio_put(folio); - _leave(" = %d", ret); - return ret; -} - -/* - * finalise part of a write to a page - */ -int afs_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *subpage, void *fsdata) -{ - struct folio *folio = page_folio(subpage); - struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); - unsigned long priv; - unsigned int f, from = offset_in_folio(folio, pos); - unsigned int t, to = from + copied; - loff_t i_size, write_end_pos; - - _enter("{%llx:%llu},{%lx}", - vnode->fid.vid, vnode->fid.vnode, folio_index(folio)); - - if (!folio_test_uptodate(folio)) { - if (copied < len) { - copied = 0; - goto out; - } - - folio_mark_uptodate(folio); - } - - if (copied == 0) - goto out; - - write_end_pos = pos + copied; - - i_size = i_size_read(&vnode->netfs.inode); - if (write_end_pos > i_size) { - write_seqlock(&vnode->cb_lock); - i_size = i_size_read(&vnode->netfs.inode); - if (write_end_pos > i_size) - afs_set_i_size(vnode, write_end_pos); - write_sequnlock(&vnode->cb_lock); - fscache_update_cookie(afs_vnode_cache(vnode), NULL, &write_end_pos); - } - - if (folio_test_private(folio)) { - priv = (unsigned long)folio_get_private(folio); - f = afs_folio_dirty_from(folio, priv); - t = afs_folio_dirty_to(folio, priv); - if (from < f) - f = from; - if (to > t) - t = to; - priv = afs_folio_dirty(folio, f, t); - folio_change_private(folio, (void *)priv); - trace_afs_folio_dirty(vnode, tracepoint_string("dirty+"), folio); - } else { - priv = afs_folio_dirty(folio, from, to); - folio_attach_private(folio, (void *)priv); - trace_afs_folio_dirty(vnode, tracepoint_string("dirty"), folio); - } - - if (folio_mark_dirty(folio)) - _debug("dirtied %lx", folio_index(folio)); - -out: - folio_unlock(folio); - folio_put(folio); - return copied; -} - -/* - * kill all the pages in the given range - */ -static void afs_kill_pages(struct address_space *mapping, - loff_t start, loff_t len) -{ - struct afs_vnode *vnode = AFS_FS_I(mapping->host); - struct folio *folio; - pgoff_t index = start / PAGE_SIZE; - pgoff_t last = (start + len - 1) / PAGE_SIZE, next; - - _enter("{%llx:%llu},%llx @%llx", - vnode->fid.vid, vnode->fid.vnode, len, start); - - do { - _debug("kill %lx (to %lx)", index, last); - - folio = filemap_get_folio(mapping, index); - if (IS_ERR(folio)) { - next = index + 1; - continue; - } - - next = folio_next_index(folio); - - folio_clear_uptodate(folio); - folio_end_writeback(folio); - folio_lock(folio); - generic_error_remove_folio(mapping, folio); - folio_unlock(folio); - folio_put(folio); - - } while (index = next, index <= last); - - _leave(""); -} - -/* - * Redirty all the pages in a given range. - */ -static void afs_redirty_pages(struct writeback_control *wbc, - struct address_space *mapping, - loff_t start, loff_t len) -{ - struct afs_vnode *vnode = AFS_FS_I(mapping->host); - struct folio *folio; - pgoff_t index = start / PAGE_SIZE; - pgoff_t last = (start + len - 1) / PAGE_SIZE, next; - - _enter("{%llx:%llu},%llx @%llx", - vnode->fid.vid, vnode->fid.vnode, len, start); - - do { - _debug("redirty %llx @%llx", len, start); - - folio = filemap_get_folio(mapping, index); - if (IS_ERR(folio)) { - next = index + 1; - continue; - } - - next = index + folio_nr_pages(folio); - folio_redirty_for_writepage(wbc, folio); - folio_end_writeback(folio); - folio_put(folio); - } while (index = next, index <= last); - - _leave(""); -} - /* * completion of write to server */ static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsigned int len) { - struct address_space *mapping = vnode->netfs.inode.i_mapping; - struct folio *folio; - pgoff_t end; - - XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE); - _enter("{%llx:%llu},{%x @%llx}", vnode->fid.vid, vnode->fid.vnode, len, start); - rcu_read_lock(); - - end = (start + len - 1) / PAGE_SIZE; - xas_for_each(&xas, folio, end) { - if (!folio_test_writeback(folio)) { - kdebug("bad %x @%llx page %lx %lx", - len, start, folio_index(folio), end); - ASSERT(folio_test_writeback(folio)); - } - - trace_afs_folio_dirty(vnode, tracepoint_string("clear"), folio); - folio_detach_private(folio); - folio_end_writeback(folio); - } - - rcu_read_unlock(); - afs_prune_wb_keys(vnode); _leave(""); } @@ -451,363 +159,53 @@ try_next_key: return afs_put_operation(op); } -/* - * Extend the region to be written back to include subsequent contiguously - * dirty pages if possible, but don't sleep while doing so. - * - * If this page holds new content, then we can include filler zeros in the - * writeback. - */ -static void afs_extend_writeback(struct address_space *mapping, - struct afs_vnode *vnode, - long *_count, - loff_t start, - loff_t max_len, - bool new_content, - bool caching, - unsigned int *_len) +static void afs_upload_to_server(struct netfs_io_subrequest *subreq) { - struct folio_batch fbatch; - struct folio *folio; - unsigned long priv; - unsigned int psize, filler = 0; - unsigned int f, t; - loff_t len = *_len; - pgoff_t index = (start + len) / PAGE_SIZE; - bool stop = true; - unsigned int i; - - XA_STATE(xas, &mapping->i_pages, index); - folio_batch_init(&fbatch); - - do { - /* Firstly, we gather up a batch of contiguous dirty pages - * under the RCU read lock - but we can't clear the dirty flags - * there if any of those pages are mapped. - */ - rcu_read_lock(); - - xas_for_each(&xas, folio, ULONG_MAX) { - stop = true; - if (xas_retry(&xas, folio)) - continue; - if (xa_is_value(folio)) - break; - if (folio_index(folio) != index) - break; - - if (!folio_try_get_rcu(folio)) { - xas_reset(&xas); - continue; - } - - /* Has the page moved or been split? */ - if (unlikely(folio != xas_reload(&xas))) { - folio_put(folio); - break; - } - - if (!folio_trylock(folio)) { - folio_put(folio); - break; - } - if (!folio_test_dirty(folio) || - folio_test_writeback(folio) || - folio_test_fscache(folio)) { - folio_unlock(folio); - folio_put(folio); - break; - } - - psize = folio_size(folio); - priv = (unsigned long)folio_get_private(folio); - f = afs_folio_dirty_from(folio, priv); - t = afs_folio_dirty_to(folio, priv); - if (f != 0 && !new_content) { - folio_unlock(folio); - folio_put(folio); - break; - } - - len += filler + t; - filler = psize - t; - if (len >= max_len || *_count <= 0) - stop = true; - else if (t == psize || new_content) - stop = false; - - index += folio_nr_pages(folio); - if (!folio_batch_add(&fbatch, folio)) - break; - if (stop) - break; - } - - if (!stop) - xas_pause(&xas); - rcu_read_unlock(); - - /* Now, if we obtained any folios, we can shift them to being - * writable and mark them for caching. - */ - if (!folio_batch_count(&fbatch)) - break; - - for (i = 0; i < folio_batch_count(&fbatch); i++) { - folio = fbatch.folios[i]; - trace_afs_folio_dirty(vnode, tracepoint_string("store+"), folio); - - if (!folio_clear_dirty_for_io(folio)) - BUG(); - folio_start_writeback(folio); - afs_folio_start_fscache(caching, folio); - - *_count -= folio_nr_pages(folio); - folio_unlock(folio); - } + struct afs_vnode *vnode = AFS_FS_I(subreq->rreq->inode); + ssize_t ret; - folio_batch_release(&fbatch); - cond_resched(); - } while (!stop); + _enter("%x[%x],%zx", + subreq->rreq->debug_id, subreq->debug_index, subreq->io_iter.count); - *_len = len; + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); + ret = afs_store_data(vnode, &subreq->io_iter, subreq->start, + subreq->rreq->origin == NETFS_LAUNDER_WRITE); + netfs_write_subrequest_terminated(subreq, ret < 0 ? ret : subreq->len, + false); } -/* - * Synchronously write back the locked page and any subsequent non-locked dirty - * pages. - */ -static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping, - struct writeback_control *wbc, - struct folio *folio, - loff_t start, loff_t end) +static void afs_upload_to_server_worker(struct work_struct *work) { - struct afs_vnode *vnode = AFS_FS_I(mapping->host); - struct iov_iter iter; - unsigned long priv; - unsigned int offset, to, len, max_len; - loff_t i_size = i_size_read(&vnode->netfs.inode); - bool new_content = test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags); - bool caching = fscache_cookie_enabled(afs_vnode_cache(vnode)); - long count = wbc->nr_to_write; - int ret; - - _enter(",%lx,%llx-%llx", folio_index(folio), start, end); - - folio_start_writeback(folio); - afs_folio_start_fscache(caching, folio); - - count -= folio_nr_pages(folio); - - /* Find all consecutive lockable dirty pages that have contiguous - * written regions, stopping when we find a page that is not - * immediately lockable, is not dirty or is missing, or we reach the - * end of the range. - */ - priv = (unsigned long)folio_get_private(folio); - offset = afs_folio_dirty_from(folio, priv); - to = afs_folio_dirty_to(folio, priv); - trace_afs_folio_dirty(vnode, tracepoint_string("store"), folio); - - len = to - offset; - start += offset; - if (start < i_size) { - /* Trim the write to the EOF; the extra data is ignored. Also - * put an upper limit on the size of a single storedata op. - */ - max_len = 65536 * 4096; - max_len = min_t(unsigned long long, max_len, end - start + 1); - max_len = min_t(unsigned long long, max_len, i_size - start); - - if (len < max_len && - (to == folio_size(folio) || new_content)) - afs_extend_writeback(mapping, vnode, &count, - start, max_len, new_content, - caching, &len); - len = min_t(loff_t, len, max_len); - } - - /* We now have a contiguous set of dirty pages, each with writeback - * set; the first page is still locked at this point, but all the rest - * have been unlocked. - */ - folio_unlock(folio); - - if (start < i_size) { - _debug("write back %x @%llx [%llx]", len, start, i_size); - - /* Speculatively write to the cache. We have to fix this up - * later if the store fails. - */ - afs_write_to_cache(vnode, start, len, i_size, caching); - - iov_iter_xarray(&iter, ITER_SOURCE, &mapping->i_pages, start, len); - ret = afs_store_data(vnode, &iter, start, false); - } else { - _debug("write discard %x @%llx [%llx]", len, start, i_size); - - /* The dirty region was entirely beyond the EOF. */ - fscache_clear_page_bits(mapping, start, len, caching); - afs_pages_written_back(vnode, start, len); - ret = 0; - } - - switch (ret) { - case 0: - wbc->nr_to_write = count; - ret = len; - break; + struct netfs_io_subrequest *subreq = + container_of(work, struct netfs_io_subrequest, work); - default: - pr_notice("kAFS: Unexpected error from FS.StoreData %d\n", ret); - fallthrough; - case -EACCES: - case -EPERM: - case -ENOKEY: - case -EKEYEXPIRED: - case -EKEYREJECTED: - case -EKEYREVOKED: - case -ENETRESET: - afs_redirty_pages(wbc, mapping, start, len); - mapping_set_error(mapping, ret); - break; - - case -EDQUOT: - case -ENOSPC: - afs_redirty_pages(wbc, mapping, start, len); - mapping_set_error(mapping, -ENOSPC); - break; - - case -EROFS: - case -EIO: - case -EREMOTEIO: - case -EFBIG: - case -ENOENT: - case -ENOMEDIUM: - case -ENXIO: - trace_afs_file_error(vnode, ret, afs_file_error_writeback_fail); - afs_kill_pages(mapping, start, len); - mapping_set_error(mapping, ret); - break; - } - - _leave(" = %d", ret); - return ret; + afs_upload_to_server(subreq); } /* - * write a region of pages back to the server + * Set up write requests for a writeback slice. We need to add a write request + * for each write we want to make. */ -static int afs_writepages_region(struct address_space *mapping, - struct writeback_control *wbc, - loff_t start, loff_t end, loff_t *_next, - bool max_one_loop) +void afs_create_write_requests(struct netfs_io_request *wreq, loff_t start, size_t len) { - struct folio *folio; - struct folio_batch fbatch; - ssize_t ret; - unsigned int i; - int n, skips = 0; - - _enter("%llx,%llx,", start, end); - folio_batch_init(&fbatch); - - do { - pgoff_t index = start / PAGE_SIZE; - - n = filemap_get_folios_tag(mapping, &index, end / PAGE_SIZE, - PAGECACHE_TAG_DIRTY, &fbatch); - - if (!n) - break; - for (i = 0; i < n; i++) { - folio = fbatch.folios[i]; - start = folio_pos(folio); /* May regress with THPs */ - - _debug("wback %lx", folio_index(folio)); - - /* At this point we hold neither the i_pages lock nor the - * page lock: the page may be truncated or invalidated - * (changing page->mapping to NULL), or even swizzled - * back from swapper_space to tmpfs file mapping - */ -try_again: - if (wbc->sync_mode != WB_SYNC_NONE) { - ret = folio_lock_killable(folio); - if (ret < 0) { - folio_batch_release(&fbatch); - return ret; - } - } else { - if (!folio_trylock(folio)) - continue; - } - - if (folio->mapping != mapping || - !folio_test_dirty(folio)) { - start += folio_size(folio); - folio_unlock(folio); - continue; - } - - if (folio_test_writeback(folio) || - folio_test_fscache(folio)) { - folio_unlock(folio); - if (wbc->sync_mode != WB_SYNC_NONE) { - folio_wait_writeback(folio); -#ifdef CONFIG_AFS_FSCACHE - folio_wait_fscache(folio); -#endif - goto try_again; - } - - start += folio_size(folio); - if (wbc->sync_mode == WB_SYNC_NONE) { - if (skips >= 5 || need_resched()) { - *_next = start; - folio_batch_release(&fbatch); - _leave(" = 0 [%llx]", *_next); - return 0; - } - skips++; - } - continue; - } - - if (!folio_clear_dirty_for_io(folio)) - BUG(); - ret = afs_write_back_from_locked_folio(mapping, wbc, - folio, start, end); - if (ret < 0) { - _leave(" = %zd", ret); - folio_batch_release(&fbatch); - return ret; - } - - start += ret; - } + struct netfs_io_subrequest *subreq; - folio_batch_release(&fbatch); - cond_resched(); - } while (wbc->nr_to_write > 0); + _enter("%x,%llx-%llx", wreq->debug_id, start, start + len); - *_next = start; - _leave(" = 0 [%llx]", *_next); - return 0; + subreq = netfs_create_write_request(wreq, NETFS_UPLOAD_TO_SERVER, + start, len, afs_upload_to_server_worker); + if (subreq) + netfs_queue_write_request(subreq); } /* * write some of the pending data back to the server */ -int afs_writepages(struct address_space *mapping, - struct writeback_control *wbc) +int afs_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct afs_vnode *vnode = AFS_FS_I(mapping->host); - loff_t start, next; int ret; - _enter(""); - /* We have to be careful as we can end up racing with setattr() * truncating the pagecache since the caller doesn't take a lock here * to prevent it. @@ -817,69 +215,12 @@ int afs_writepages(struct address_space *mapping, else if (!down_read_trylock(&vnode->validate_lock)) return 0; - if (wbc->range_cyclic) { - start = mapping->writeback_index * PAGE_SIZE; - ret = afs_writepages_region(mapping, wbc, start, LLONG_MAX, - &next, false); - if (ret == 0) { - mapping->writeback_index = next / PAGE_SIZE; - if (start > 0 && wbc->nr_to_write > 0) { - ret = afs_writepages_region(mapping, wbc, 0, - start, &next, false); - if (ret == 0) - mapping->writeback_index = - next / PAGE_SIZE; - } - } - } else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) { - ret = afs_writepages_region(mapping, wbc, 0, LLONG_MAX, - &next, false); - if (wbc->nr_to_write > 0 && ret == 0) - mapping->writeback_index = next / PAGE_SIZE; - } else { - ret = afs_writepages_region(mapping, wbc, - wbc->range_start, wbc->range_end, - &next, false); - } - + ret = netfs_writepages(mapping, wbc); up_read(&vnode->validate_lock); - _leave(" = %d", ret); return ret; } /* - * write to an AFS file - */ -ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from) -{ - struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp)); - struct afs_file *af = iocb->ki_filp->private_data; - ssize_t result; - size_t count = iov_iter_count(from); - - _enter("{%llx:%llu},{%zu},", - vnode->fid.vid, vnode->fid.vnode, count); - - if (IS_SWAPFILE(&vnode->netfs.inode)) { - printk(KERN_INFO - "AFS: Attempt to write to active swap file!\n"); - return -EBUSY; - } - - if (!count) - return 0; - - result = afs_validate(vnode, af->key); - if (result < 0) - return result; - - result = generic_file_write_iter(iocb, from); - - _leave(" = %zd", result); - return result; -} - -/* * flush any dirty pages for this process, and check for write errors. * - the return status from this call provides a reliable indication of * whether any write errors occurred for this process. @@ -907,59 +248,11 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync) */ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) { - struct folio *folio = page_folio(vmf->page); struct file *file = vmf->vma->vm_file; - struct inode *inode = file_inode(file); - struct afs_vnode *vnode = AFS_FS_I(inode); - struct afs_file *af = file->private_data; - unsigned long priv; - vm_fault_t ret = VM_FAULT_RETRY; - - _enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, folio_index(folio)); - - afs_validate(vnode, af->key); - sb_start_pagefault(inode->i_sb); - - /* Wait for the page to be written to the cache before we allow it to - * be modified. We then assume the entire page will need writing back. - */ -#ifdef CONFIG_AFS_FSCACHE - if (folio_test_fscache(folio) && - folio_wait_fscache_killable(folio) < 0) - goto out; -#endif - - if (folio_wait_writeback_killable(folio)) - goto out; - - if (folio_lock_killable(folio) < 0) - goto out; - - /* We mustn't change folio->private until writeback is complete as that - * details the portion of the page we need to write back and we might - * need to redirty the page if there's a problem. - */ - if (folio_wait_writeback_killable(folio) < 0) { - folio_unlock(folio); - goto out; - } - - priv = afs_folio_dirty(folio, 0, folio_size(folio)); - priv = afs_folio_dirty_mmapped(priv); - if (folio_test_private(folio)) { - folio_change_private(folio, (void *)priv); - trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite+"), folio); - } else { - folio_attach_private(folio, (void *)priv); - trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite"), folio); - } - file_update_time(file); - - ret = VM_FAULT_LOCKED; -out: - sb_end_pagefault(inode->i_sb); - return ret; + if (afs_validate(AFS_FS_I(file_inode(file)), afs_file_key(file)) < 0) + return VM_FAULT_SIGBUS; + return netfs_page_mkwrite(vmf, NULL); } /* @@ -989,64 +282,3 @@ void afs_prune_wb_keys(struct afs_vnode *vnode) afs_put_wb_key(wbk); } } - -/* - * Clean up a page during invalidation. - */ -int afs_launder_folio(struct folio *folio) -{ - struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio)); - struct iov_iter iter; - struct bio_vec bv; - unsigned long priv; - unsigned int f, t; - int ret = 0; - - _enter("{%lx}", folio->index); - - priv = (unsigned long)folio_get_private(folio); - if (folio_clear_dirty_for_io(folio)) { - f = 0; - t = folio_size(folio); - if (folio_test_private(folio)) { - f = afs_folio_dirty_from(folio, priv); - t = afs_folio_dirty_to(folio, priv); - } - - bvec_set_folio(&bv, folio, t - f, f); - iov_iter_bvec(&iter, ITER_SOURCE, &bv, 1, bv.bv_len); - - trace_afs_folio_dirty(vnode, tracepoint_string("launder"), folio); - ret = afs_store_data(vnode, &iter, folio_pos(folio) + f, true); - } - - trace_afs_folio_dirty(vnode, tracepoint_string("laundered"), folio); - folio_detach_private(folio); - folio_wait_fscache(folio); - return ret; -} - -/* - * Deal with the completion of writing the data to the cache. - */ -static void afs_write_to_cache_done(void *priv, ssize_t transferred_or_error, - bool was_async) -{ - struct afs_vnode *vnode = priv; - - if (IS_ERR_VALUE(transferred_or_error) && - transferred_or_error != -ENOBUFS) - afs_invalidate_cache(vnode, 0); -} - -/* - * Save the write to the cache also. - */ -static void afs_write_to_cache(struct afs_vnode *vnode, - loff_t start, size_t len, loff_t i_size, - bool caching) -{ - fscache_write_to_cache(afs_vnode_cache(vnode), - vnode->netfs.inode.i_mapping, start, len, i_size, - afs_write_to_cache_done, vnode, caching); -} diff --git a/fs/cachefiles/Kconfig b/fs/cachefiles/Kconfig index 8df715640a48..c5a070550ee3 100644 --- a/fs/cachefiles/Kconfig +++ b/fs/cachefiles/Kconfig @@ -2,7 +2,7 @@ config CACHEFILES tristate "Filesystem caching on files" - depends on FSCACHE && BLOCK + depends on NETFS_SUPPORT && FSCACHE && BLOCK help This permits use of a mounted filesystem as a cache for other filesystems - primarily networking filesystems - thus allowing fast diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 4a87c9d714a9..d33169f0018b 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -246,7 +246,7 @@ extern bool cachefiles_begin_operation(struct netfs_cache_resources *cres, enum fscache_want_state want_state); extern int __cachefiles_prepare_write(struct cachefiles_object *object, struct file *file, - loff_t *_start, size_t *_len, + loff_t *_start, size_t *_len, size_t upper_len, bool no_space_allocated_yet); extern int __cachefiles_write(struct cachefiles_object *object, struct file *file, diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index 5857241c5918..1d685357e67f 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -517,18 +517,26 @@ cachefiles_prepare_ondemand_read(struct netfs_cache_resources *cres, */ int __cachefiles_prepare_write(struct cachefiles_object *object, struct file *file, - loff_t *_start, size_t *_len, + loff_t *_start, size_t *_len, size_t upper_len, bool no_space_allocated_yet) { struct cachefiles_cache *cache = object->volume->cache; loff_t start = *_start, pos; - size_t len = *_len, down; + size_t len = *_len; int ret; /* Round to DIO size */ - down = start - round_down(start, PAGE_SIZE); - *_start = start - down; - *_len = round_up(down + len, PAGE_SIZE); + start = round_down(*_start, PAGE_SIZE); + if (start != *_start || *_len > upper_len) { + /* Probably asked to cache a streaming write written into the + * pagecache when the cookie was temporarily out of service to + * culling. + */ + fscache_count_dio_misfit(); + return -ENOBUFS; + } + + *_len = round_up(len, PAGE_SIZE); /* We need to work out whether there's sufficient disk space to perform * the write - but we can skip that check if we have space already @@ -539,7 +547,7 @@ int __cachefiles_prepare_write(struct cachefiles_object *object, pos = cachefiles_inject_read_error(); if (pos == 0) - pos = vfs_llseek(file, *_start, SEEK_DATA); + pos = vfs_llseek(file, start, SEEK_DATA); if (pos < 0 && pos >= (loff_t)-MAX_ERRNO) { if (pos == -ENXIO) goto check_space; /* Unallocated tail */ @@ -547,7 +555,7 @@ int __cachefiles_prepare_write(struct cachefiles_object *object, cachefiles_trace_seek_error); return pos; } - if ((u64)pos >= (u64)*_start + *_len) + if ((u64)pos >= (u64)start + *_len) goto check_space; /* Unallocated region */ /* We have a block that's at least partially filled - if we're low on @@ -560,13 +568,13 @@ int __cachefiles_prepare_write(struct cachefiles_object *object, pos = cachefiles_inject_read_error(); if (pos == 0) - pos = vfs_llseek(file, *_start, SEEK_HOLE); + pos = vfs_llseek(file, start, SEEK_HOLE); if (pos < 0 && pos >= (loff_t)-MAX_ERRNO) { trace_cachefiles_io_error(object, file_inode(file), pos, cachefiles_trace_seek_error); return pos; } - if ((u64)pos >= (u64)*_start + *_len) + if ((u64)pos >= (u64)start + *_len) return 0; /* Fully allocated */ /* Partially allocated, but insufficient space: cull. */ @@ -574,7 +582,7 @@ int __cachefiles_prepare_write(struct cachefiles_object *object, ret = cachefiles_inject_remove_error(); if (ret == 0) ret = vfs_fallocate(file, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, - *_start, *_len); + start, *_len); if (ret < 0) { trace_cachefiles_io_error(object, file_inode(file), ret, cachefiles_trace_fallocate_error); @@ -591,8 +599,8 @@ check_space: } static int cachefiles_prepare_write(struct netfs_cache_resources *cres, - loff_t *_start, size_t *_len, loff_t i_size, - bool no_space_allocated_yet) + loff_t *_start, size_t *_len, size_t upper_len, + loff_t i_size, bool no_space_allocated_yet) { struct cachefiles_object *object = cachefiles_cres_object(cres); struct cachefiles_cache *cache = object->volume->cache; @@ -608,7 +616,7 @@ static int cachefiles_prepare_write(struct netfs_cache_resources *cres, cachefiles_begin_secure(cache, &saved_cred); ret = __cachefiles_prepare_write(object, cachefiles_cres_file(cres), - _start, _len, + _start, _len, upper_len, no_space_allocated_yet); cachefiles_end_secure(cache, saved_cred); return ret; diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index b8fbbb1961bb..5fd74ec60bef 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -50,7 +50,7 @@ static ssize_t cachefiles_ondemand_fd_write_iter(struct kiocb *kiocb, return -ENOBUFS; cachefiles_begin_secure(cache, &saved_cred); - ret = __cachefiles_prepare_write(object, file, &pos, &len, true); + ret = __cachefiles_prepare_write(object, file, &pos, &len, len, true); cachefiles_end_secure(cache, saved_cred); if (ret < 0) return ret; diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig index 94df854147d3..7249d70e1a43 100644 --- a/fs/ceph/Kconfig +++ b/fs/ceph/Kconfig @@ -7,6 +7,7 @@ config CEPH_FS select CRYPTO_AES select CRYPTO select NETFS_SUPPORT + select FS_ENCRYPTION_ALGS if FS_ENCRYPTION default n help Choose Y or M here to include support for mounting the diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 13af429ab030..1340d77124ae 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -159,27 +159,7 @@ static void ceph_invalidate_folio(struct folio *folio, size_t offset, ceph_put_snap_context(snapc); } - folio_wait_fscache(folio); -} - -static bool ceph_release_folio(struct folio *folio, gfp_t gfp) -{ - struct inode *inode = folio->mapping->host; - struct ceph_client *cl = ceph_inode_to_client(inode); - - doutc(cl, "%llx.%llx idx %lu (%sdirty)\n", ceph_vinop(inode), - folio->index, folio_test_dirty(folio) ? "" : "not "); - - if (folio_test_private(folio)) - return false; - - if (folio_test_fscache(folio)) { - if (current_is_kswapd() || !(gfp & __GFP_FS)) - return false; - folio_wait_fscache(folio); - } - ceph_fscache_note_page_release(inode); - return true; + netfs_invalidate_folio(folio, offset, length); } static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq) @@ -357,6 +337,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) u64 len = subreq->len; bool sparse = IS_ENCRYPTED(inode) || ceph_test_mount_opt(fsc, SPARSEREAD); u64 off = subreq->start; + int extent_cnt; if (ceph_inode_is_shutdown(inode)) { err = -EIO; @@ -370,8 +351,8 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, off, &len, 0, 1, sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ, - CEPH_OSD_FLAG_READ | fsc->client->osdc.client->options->read_from_replica, - NULL, ci->i_truncate_seq, ci->i_truncate_size, false); + CEPH_OSD_FLAG_READ, NULL, ci->i_truncate_seq, + ci->i_truncate_size, false); if (IS_ERR(req)) { err = PTR_ERR(req); req = NULL; @@ -379,7 +360,8 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) } if (sparse) { - err = ceph_alloc_sparse_ext_map(&req->r_ops[0]); + extent_cnt = __ceph_sparse_read_ext_count(inode, len); + err = ceph_alloc_sparse_ext_map(&req->r_ops[0], extent_cnt); if (err) goto out; } @@ -509,7 +491,6 @@ static void ceph_netfs_free_request(struct netfs_io_request *rreq) const struct netfs_request_ops ceph_netfs_ops = { .init_request = ceph_init_request, .free_request = ceph_netfs_free_request, - .begin_cache_operation = ceph_begin_cache_operation, .issue_read = ceph_netfs_issue_read, .expand_readahead = ceph_netfs_expand_readahead, .clamp_length = ceph_netfs_clamp_length, @@ -1586,7 +1567,7 @@ const struct address_space_operations ceph_aops = { .write_end = ceph_write_end, .dirty_folio = ceph_dirty_folio, .invalidate_folio = ceph_invalidate_folio, - .release_folio = ceph_release_folio, + .release_folio = netfs_release_folio, .direct_IO = noop_direct_IO, }; diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h index dc502daac49a..20efac020394 100644 --- a/fs/ceph/cache.h +++ b/fs/ceph/cache.h @@ -43,38 +43,19 @@ static inline void ceph_fscache_resize(struct inode *inode, loff_t to) } } -static inline void ceph_fscache_unpin_writeback(struct inode *inode, +static inline int ceph_fscache_unpin_writeback(struct inode *inode, struct writeback_control *wbc) { - fscache_unpin_writeback(wbc, ceph_fscache_cookie(ceph_inode(inode))); + return netfs_unpin_writeback(inode, wbc); } -static inline int ceph_fscache_dirty_folio(struct address_space *mapping, - struct folio *folio) -{ - struct ceph_inode_info *ci = ceph_inode(mapping->host); - - return fscache_dirty_folio(mapping, folio, ceph_fscache_cookie(ci)); -} - -static inline int ceph_begin_cache_operation(struct netfs_io_request *rreq) -{ - struct fscache_cookie *cookie = ceph_fscache_cookie(ceph_inode(rreq->inode)); - - return fscache_begin_read_operation(&rreq->cache_resources, cookie); -} +#define ceph_fscache_dirty_folio netfs_dirty_folio static inline bool ceph_is_cache_enabled(struct inode *inode) { return fscache_cookie_enabled(ceph_fscache_cookie(ceph_inode(inode))); } -static inline void ceph_fscache_note_page_release(struct inode *inode) -{ - struct ceph_inode_info *ci = ceph_inode(inode); - - fscache_note_page_release(ceph_fscache_cookie(ci)); -} #else /* CONFIG_CEPH_FSCACHE */ static inline int ceph_fscache_register_fs(struct ceph_fs_client* fsc, struct fs_context *fc) @@ -119,30 +100,18 @@ static inline void ceph_fscache_resize(struct inode *inode, loff_t to) { } -static inline void ceph_fscache_unpin_writeback(struct inode *inode, - struct writeback_control *wbc) +static inline int ceph_fscache_unpin_writeback(struct inode *inode, + struct writeback_control *wbc) { + return 0; } -static inline int ceph_fscache_dirty_folio(struct address_space *mapping, - struct folio *folio) -{ - return filemap_dirty_folio(mapping, folio); -} +#define ceph_fscache_dirty_folio filemap_dirty_folio static inline bool ceph_is_cache_enabled(struct inode *inode) { return false; } - -static inline int ceph_begin_cache_operation(struct netfs_io_request *rreq) -{ - return -ENOBUFS; -} - -static inline void ceph_fscache_note_page_release(struct inode *inode) -{ -} #endif /* CONFIG_CEPH_FSCACHE */ #endif diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 2c0b8dc3dd0d..9c02f328c966 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -4887,13 +4887,15 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry, struct inode *dir, int mds, int drop, int unless) { - struct dentry *parent = NULL; struct ceph_mds_request_release *rel = *p; struct ceph_dentry_info *di = ceph_dentry(dentry); struct ceph_client *cl; int force = 0; int ret; + /* This shouldn't happen */ + BUG_ON(!dir); + /* * force an record for the directory caps if we have a dentry lease. * this is racy (can't take i_ceph_lock and d_lock together), but it @@ -4903,14 +4905,9 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry, spin_lock(&dentry->d_lock); if (di->lease_session && di->lease_session->s_mds == mds) force = 1; - if (!dir) { - parent = dget(dentry->d_parent); - dir = d_inode(parent); - } spin_unlock(&dentry->d_lock); ret = ceph_encode_inode_release(p, dir, mds, drop, unless, force); - dput(parent); cl = ceph_inode_to_client(dir); spin_lock(&dentry->d_lock); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 678596684596..0e9f56eaba1e 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1593,10 +1593,12 @@ struct ceph_lease_walk_control { unsigned long dir_lease_ttl; }; +static int __dir_lease_check(const struct dentry *, struct ceph_lease_walk_control *); +static int __dentry_lease_check(const struct dentry *); + static unsigned long __dentry_leases_walk(struct ceph_mds_client *mdsc, - struct ceph_lease_walk_control *lwc, - int (*check)(struct dentry*, void*)) + struct ceph_lease_walk_control *lwc) { struct ceph_dentry_info *di, *tmp; struct dentry *dentry, *last = NULL; @@ -1624,7 +1626,10 @@ __dentry_leases_walk(struct ceph_mds_client *mdsc, goto next; } - ret = check(dentry, lwc); + if (lwc->dir_lease) + ret = __dir_lease_check(dentry, lwc); + else + ret = __dentry_lease_check(dentry); if (ret & TOUCH) { /* move it into tail of dir lease list */ __dentry_dir_lease_touch(mdsc, di); @@ -1681,7 +1686,7 @@ next: return freed; } -static int __dentry_lease_check(struct dentry *dentry, void *arg) +static int __dentry_lease_check(const struct dentry *dentry) { struct ceph_dentry_info *di = ceph_dentry(dentry); int ret; @@ -1696,9 +1701,9 @@ static int __dentry_lease_check(struct dentry *dentry, void *arg) return DELETE; } -static int __dir_lease_check(struct dentry *dentry, void *arg) +static int __dir_lease_check(const struct dentry *dentry, + struct ceph_lease_walk_control *lwc) { - struct ceph_lease_walk_control *lwc = arg; struct ceph_dentry_info *di = ceph_dentry(dentry); int ret = __dir_lease_try_check(dentry); @@ -1737,7 +1742,7 @@ int ceph_trim_dentries(struct ceph_mds_client *mdsc) lwc.dir_lease = false; lwc.nr_to_scan = CEPH_CAPS_PER_RELEASE * 2; - freed = __dentry_leases_walk(mdsc, &lwc, __dentry_lease_check); + freed = __dentry_leases_walk(mdsc, &lwc); if (!lwc.nr_to_scan) /* more invalid leases */ return -EAGAIN; @@ -1747,7 +1752,7 @@ int ceph_trim_dentries(struct ceph_mds_client *mdsc) lwc.dir_lease = true; lwc.expire_dir_lease = freed < count; lwc.dir_lease_ttl = mdsc->fsc->mount_options->caps_wanted_delay_max * HZ; - freed +=__dentry_leases_walk(mdsc, &lwc, __dir_lease_check); + freed +=__dentry_leases_walk(mdsc, &lwc); if (!lwc.nr_to_scan) /* more to check */ return -EAGAIN; diff --git a/fs/ceph/export.c b/fs/ceph/export.c index 726af69d4d62..a79f163ae4ed 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -286,8 +286,6 @@ static struct dentry *__snapfh_to_dentry(struct super_block *sb, doutc(cl, "%llx.%llx parent %llx hash %x err=%d", vino.ino, vino.snap, sfh->parent_ino, sfh->hash, err); } - if (IS_ERR(inode)) - return ERR_CAST(inode); /* see comments in ceph_get_parent() */ return unlinked ? d_obtain_root(inode) : d_obtain_alias(inode); } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index d380d9dad0e0..abe8028d95bf 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1029,6 +1029,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, struct ceph_osd_req_op *op; u64 read_off = off; u64 read_len = len; + int extent_cnt; /* determine new offset/length if encrypted */ ceph_fscrypt_adjust_off_and_len(inode, &read_off, &read_len); @@ -1068,7 +1069,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, op = &req->r_ops[0]; if (sparse) { - ret = ceph_alloc_sparse_ext_map(op); + extent_cnt = __ceph_sparse_read_ext_count(inode, read_len); + ret = ceph_alloc_sparse_ext_map(op, extent_cnt); if (ret) { ceph_osdc_put_request(req); break; @@ -1465,6 +1467,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, ssize_t len; struct ceph_osd_req_op *op; int readop = sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ; + int extent_cnt; if (write) size = min_t(u64, size, fsc->mount_options->wsize); @@ -1528,7 +1531,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len); op = &req->r_ops[0]; if (sparse) { - ret = ceph_alloc_sparse_ext_map(op); + extent_cnt = __ceph_sparse_read_ext_count(inode, size); + ret = ceph_alloc_sparse_ext_map(op, extent_cnt); if (ret) { ceph_osdc_put_request(req); break; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 0679240f06db..0c25d326afc4 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -574,7 +574,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb) doutc(fsc->client, "%p\n", &ci->netfs.inode); /* Set parameters for the netfs library */ - netfs_inode_init(&ci->netfs, &ceph_netfs_ops); + netfs_inode_init(&ci->netfs, &ceph_netfs_ops, false); spin_lock_init(&ci->i_ceph_lock); @@ -694,7 +694,7 @@ void ceph_evict_inode(struct inode *inode) percpu_counter_dec(&mdsc->metric.total_inodes); truncate_inode_pages_final(&inode->i_data); - if (inode->i_state & I_PINNING_FSCACHE_WB) + if (inode->i_state & I_PINNING_NETFS_WB) ceph_fscache_unuse_cookie(inode, true); clear_inode(inode); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 02ebfabfc8ee..548d1de379f3 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1534,7 +1534,8 @@ static int encode_metric_spec(void **p, void *end) * session message, specialization for CEPH_SESSION_REQUEST_OPEN * to include additional client metadata fields. */ -static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u64 seq) +static struct ceph_msg * +create_session_full_msg(struct ceph_mds_client *mdsc, int op, u64 seq) { struct ceph_msg *msg; struct ceph_mds_session_head *h; @@ -1578,6 +1579,9 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 size = METRIC_BYTES(count); extra_bytes += 2 + 4 + 4 + size; + /* flags, mds auth caps and oldest_client_tid */ + extra_bytes += 4 + 4 + 8; + /* Allocate the message */ msg = ceph_msg_new(CEPH_MSG_CLIENT_SESSION, sizeof(*h) + extra_bytes, GFP_NOFS, false); @@ -1589,16 +1593,16 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 end = p + msg->front.iov_len; h = p; - h->op = cpu_to_le32(CEPH_SESSION_REQUEST_OPEN); + h->op = cpu_to_le32(op); h->seq = cpu_to_le64(seq); /* * Serialize client metadata into waiting buffer space, using * the format that userspace expects for map<string, string> * - * ClientSession messages with metadata are v4 + * ClientSession messages with metadata are v7 */ - msg->hdr.version = cpu_to_le16(4); + msg->hdr.version = cpu_to_le16(7); msg->hdr.compat_version = cpu_to_le16(1); /* The write pointer, following the session_head structure */ @@ -1634,6 +1638,15 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 return ERR_PTR(ret); } + /* version == 5, flags */ + ceph_encode_32(&p, 0); + + /* version == 6, mds auth caps */ + ceph_encode_32(&p, 0); + + /* version == 7, oldest_client_tid */ + ceph_encode_64(&p, mdsc->oldest_tid); + msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); @@ -1663,7 +1676,8 @@ static int __open_session(struct ceph_mds_client *mdsc, session->s_renew_requested = jiffies; /* send connect message */ - msg = create_session_open_msg(mdsc, session->s_seq); + msg = create_session_full_msg(mdsc, CEPH_SESSION_REQUEST_OPEN, + session->s_seq); if (IS_ERR(msg)) return PTR_ERR(msg); ceph_con_send(&session->s_con, msg); @@ -2028,10 +2042,10 @@ static int send_renew_caps(struct ceph_mds_client *mdsc, doutc(cl, "to mds%d (%s)\n", session->s_mds, ceph_mds_state_name(state)); - msg = ceph_create_session_msg(CEPH_SESSION_REQUEST_RENEWCAPS, + msg = create_session_full_msg(mdsc, CEPH_SESSION_REQUEST_RENEWCAPS, ++session->s_renew_seq); - if (!msg) - return -ENOMEM; + if (IS_ERR(msg)) + return PTR_ERR(msg); ceph_con_send(&session->s_con, msg); return 0; } @@ -4128,12 +4142,12 @@ static void handle_session(struct ceph_mds_session *session, pr_info_client(cl, "mds%d reconnect success\n", session->s_mds); + session->s_features = features; if (session->s_state == CEPH_MDS_SESSION_OPEN) { pr_notice_client(cl, "mds%d is already opened\n", session->s_mds); } else { session->s_state = CEPH_MDS_SESSION_OPEN; - session->s_features = features; renewed_caps(mdsc, session, 0); if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &session->s_features)) @@ -5870,7 +5884,8 @@ static void mds_peer_reset(struct ceph_connection *con) pr_warn_client(mdsc->fsc->client, "mds%d closed our session\n", s->s_mds); - if (READ_ONCE(mdsc->fsc->mount_state) != CEPH_MOUNT_FENCE_IO) + if (READ_ONCE(mdsc->fsc->mount_state) != CEPH_MOUNT_FENCE_IO && + ceph_mdsmap_get_state(mdsc->mdsmap, s->s_mds) >= CEPH_MDS_STATE_RECONNECT) send_mds_reconnect(mdsc, s); } diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index 9d36c3532de1..06ee397e0c3a 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -197,10 +197,10 @@ void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc) } /* - * This function walks through the snaprealm for an inode and returns the - * ceph_snap_realm for the first snaprealm that has quotas set (max_files, + * This function walks through the snaprealm for an inode and set the + * realmp with the first snaprealm that has quotas set (max_files, * max_bytes, or any, depending on the 'which_quota' argument). If the root is - * reached, return the root ceph_snap_realm instead. + * reached, set the realmp with the root ceph_snap_realm instead. * * Note that the caller is responsible for calling ceph_put_snap_realm() on the * returned realm. @@ -211,10 +211,9 @@ void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc) * this function will return -EAGAIN; otherwise, the snaprealms walk-through * will be restarted. */ -static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc, - struct inode *inode, - enum quota_get_realm which_quota, - bool retry) +static int get_quota_realm(struct ceph_mds_client *mdsc, struct inode *inode, + enum quota_get_realm which_quota, + struct ceph_snap_realm **realmp, bool retry) { struct ceph_client *cl = mdsc->fsc->client; struct ceph_inode_info *ci = NULL; @@ -222,8 +221,10 @@ static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc, struct inode *in; bool has_quota; + if (realmp) + *realmp = NULL; if (ceph_snap(inode) != CEPH_NOSNAP) - return NULL; + return 0; restart: realm = ceph_inode(inode)->i_snap_realm; @@ -250,7 +251,7 @@ restart: break; ceph_put_snap_realm(mdsc, realm); if (!retry) - return ERR_PTR(-EAGAIN); + return -EAGAIN; goto restart; } @@ -259,8 +260,11 @@ restart: iput(in); next = realm->parent; - if (has_quota || !next) - return realm; + if (has_quota || !next) { + if (realmp) + *realmp = realm; + return 0; + } ceph_get_snap_realm(mdsc, next); ceph_put_snap_realm(mdsc, realm); @@ -269,7 +273,7 @@ restart: if (realm) ceph_put_snap_realm(mdsc, realm); - return NULL; + return 0; } bool ceph_quota_is_same_realm(struct inode *old, struct inode *new) @@ -277,6 +281,7 @@ bool ceph_quota_is_same_realm(struct inode *old, struct inode *new) struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(old->i_sb); struct ceph_snap_realm *old_realm, *new_realm; bool is_same; + int ret; restart: /* @@ -286,9 +291,9 @@ restart: * dropped and we can then restart the whole operation. */ down_read(&mdsc->snap_rwsem); - old_realm = get_quota_realm(mdsc, old, QUOTA_GET_ANY, true); - new_realm = get_quota_realm(mdsc, new, QUOTA_GET_ANY, false); - if (PTR_ERR(new_realm) == -EAGAIN) { + get_quota_realm(mdsc, old, QUOTA_GET_ANY, &old_realm, true); + ret = get_quota_realm(mdsc, new, QUOTA_GET_ANY, &new_realm, false); + if (ret == -EAGAIN) { up_read(&mdsc->snap_rwsem); if (old_realm) ceph_put_snap_realm(mdsc, old_realm); @@ -492,8 +497,8 @@ bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf) bool is_updated = false; down_read(&mdsc->snap_rwsem); - realm = get_quota_realm(mdsc, d_inode(fsc->sb->s_root), - QUOTA_GET_MAX_BYTES, true); + get_quota_realm(mdsc, d_inode(fsc->sb->s_root), QUOTA_GET_MAX_BYTES, + &realm, true); up_read(&mdsc->snap_rwsem); if (!realm) return false; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index fe0f64a0acb2..b06e2bc86221 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -3,6 +3,7 @@ #define _FS_CEPH_SUPER_H #include <linux/ceph/ceph_debug.h> +#include <linux/ceph/osd_client.h> #include <asm/unaligned.h> #include <linux/backing-dev.h> @@ -1407,6 +1408,19 @@ static inline void __ceph_update_quota(struct ceph_inode_info *ci, ceph_adjust_quota_realms_count(&ci->netfs.inode, has_quota); } +static inline int __ceph_sparse_read_ext_count(struct inode *inode, u64 len) +{ + int cnt = 0; + + if (IS_ENCRYPTED(inode)) { + cnt = len >> CEPH_FSCRYPT_BLOCK_SHIFT; + if (cnt > CEPH_SPARSE_EXT_ARRAY_INITIAL) + cnt = 0; + } + + return cnt; +} + extern void ceph_handle_quota(struct ceph_mds_client *mdsc, struct ceph_mds_session *session, struct ceph_msg *msg); diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig index 1d318f85232d..fffd3919343e 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -114,8 +114,11 @@ config EROFS_FS_ZIP_DEFLATE config EROFS_FS_ONDEMAND bool "EROFS fscache-based on-demand read support" - depends on CACHEFILES_ONDEMAND && (EROFS_FS=m && FSCACHE || EROFS_FS=y && FSCACHE=y) - default n + depends on EROFS_FS + select NETFS_SUPPORT + select FSCACHE + select CACHEFILES + select CACHEFILES_ONDEMAND help This permits EROFS to use fscache-backed data blobs with on-demand read support. diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 1d65b9f60a39..072ef6a66823 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -408,7 +408,7 @@ int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb) int size, ret = 0; if (!erofs_sb_has_compr_cfgs(sbi)) { - sbi->available_compr_algs = Z_EROFS_COMPRESSION_LZ4; + sbi->available_compr_algs = 1 << Z_EROFS_COMPRESSION_LZ4; return z_erofs_load_lz4_config(sb, dsb, NULL, 0); } diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 87ff35bff8d5..bc12030393b2 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -165,10 +165,10 @@ static int erofs_fscache_read_folios_async(struct fscache_cookie *cookie, static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio) { int ret; - struct erofs_fscache *ctx = folio_mapping(folio)->host->i_private; + struct erofs_fscache *ctx = folio->mapping->host->i_private; struct erofs_fscache_request *req; - req = erofs_fscache_req_alloc(folio_mapping(folio), + req = erofs_fscache_req_alloc(folio->mapping, folio_pos(folio), folio_size(folio)); if (IS_ERR(req)) { folio_unlock(folio); @@ -276,7 +276,7 @@ static int erofs_fscache_read_folio(struct file *file, struct folio *folio) struct erofs_fscache_request *req; int ret; - req = erofs_fscache_req_alloc(folio_mapping(folio), + req = erofs_fscache_req_alloc(folio->mapping, folio_pos(folio), folio_size(folio)); if (IS_ERR(req)) { folio_unlock(folio); diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 9753875e41cb..e313c936351d 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -454,7 +454,7 @@ static int z_erofs_do_map_blocks(struct inode *inode, .map = map, }; int err = 0; - unsigned int lclusterbits, endoff; + unsigned int lclusterbits, endoff, afmt; unsigned long initial_lcn; unsigned long long ofs, end; @@ -543,17 +543,20 @@ static int z_erofs_do_map_blocks(struct inode *inode, err = -EFSCORRUPTED; goto unmap_out; } - if (vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER) - map->m_algorithmformat = - Z_EROFS_COMPRESSION_INTERLACED; - else - map->m_algorithmformat = - Z_EROFS_COMPRESSION_SHIFTED; - } else if (m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) { - map->m_algorithmformat = vi->z_algorithmtype[1]; + afmt = vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER ? + Z_EROFS_COMPRESSION_INTERLACED : + Z_EROFS_COMPRESSION_SHIFTED; } else { - map->m_algorithmformat = vi->z_algorithmtype[0]; + afmt = m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2 ? + vi->z_algorithmtype[1] : vi->z_algorithmtype[0]; + if (!(EROFS_I_SB(inode)->available_compr_algs & (1 << afmt))) { + erofs_err(inode->i_sb, "inconsistent algorithmtype %u for nid %llu", + afmt, vi->nid); + err = -EFSCORRUPTED; + goto unmap_out; + } } + map->m_algorithmformat = afmt; if ((flags & EROFS_GET_BLOCKS_FIEMAP) || ((flags & EROFS_GET_BLOCKS_READMORE) && diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 1767493dffda..3d84fcc471c6 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1675,11 +1675,11 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) inode->i_state |= I_DIRTY_PAGES; - else if (unlikely(inode->i_state & I_PINNING_FSCACHE_WB)) { + else if (unlikely(inode->i_state & I_PINNING_NETFS_WB)) { if (!(inode->i_state & I_DIRTY_PAGES)) { - inode->i_state &= ~I_PINNING_FSCACHE_WB; - wbc->unpinned_fscache_wb = true; - dirty |= I_PINNING_FSCACHE_WB; /* Cause write_inode */ + inode->i_state &= ~I_PINNING_NETFS_WB; + wbc->unpinned_netfs_wb = true; + dirty |= I_PINNING_NETFS_WB; /* Cause write_inode */ } } @@ -1691,7 +1691,7 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) if (ret == 0) ret = err; } - wbc->unpinned_fscache_wb = false; + wbc->unpinned_netfs_wb = false; trace_writeback_single_inode(inode, wbc, nr_to_write); return ret; } diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig deleted file mode 100644 index b313a978ae0a..000000000000 --- a/fs/fscache/Kconfig +++ /dev/null @@ -1,40 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only - -config FSCACHE - tristate "General filesystem local caching manager" - select NETFS_SUPPORT - help - This option enables a generic filesystem caching manager that can be - used by various network and other filesystems to cache data locally. - Different sorts of caches can be plugged in, depending on the - resources available. - - See Documentation/filesystems/caching/fscache.rst for more information. - -config FSCACHE_STATS - bool "Gather statistical information on local caching" - depends on FSCACHE && PROC_FS - select NETFS_STATS - help - This option causes statistical information to be gathered on local - caching and exported through file: - - /proc/fs/fscache/stats - - The gathering of statistics adds a certain amount of overhead to - execution as there are a quite a few stats gathered, and on a - multi-CPU system these may be on cachelines that keep bouncing - between CPUs. On the other hand, the stats are very useful for - debugging purposes. Saying 'Y' here is recommended. - - See Documentation/filesystems/caching/fscache.rst for more information. - -config FSCACHE_DEBUG - bool "Debug FS-Cache" - depends on FSCACHE - help - This permits debugging to be dynamically enabled in the local caching - management module. If this is set, the debugging output may be - enabled by setting bits in /sys/modules/fscache/parameter/debug. - - See Documentation/filesystems/caching/fscache.rst for more information. diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile deleted file mode 100644 index afb090ea16c4..000000000000 --- a/fs/fscache/Makefile +++ /dev/null @@ -1,16 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# Makefile for general filesystem caching code -# - -fscache-y := \ - cache.o \ - cookie.o \ - io.o \ - main.o \ - volume.o - -fscache-$(CONFIG_PROC_FS) += proc.o -fscache-$(CONFIG_FSCACHE_STATS) += stats.o - -obj-$(CONFIG_FSCACHE) := fscache.o diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h deleted file mode 100644 index 1336f517e9b1..000000000000 --- a/fs/fscache/internal.h +++ /dev/null @@ -1,277 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* Internal definitions for FS-Cache - * - * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#ifdef pr_fmt -#undef pr_fmt -#endif - -#define pr_fmt(fmt) "FS-Cache: " fmt - -#include <linux/slab.h> -#include <linux/fscache-cache.h> -#include <trace/events/fscache.h> -#include <linux/sched.h> -#include <linux/seq_file.h> - -/* - * cache.c - */ -#ifdef CONFIG_PROC_FS -extern const struct seq_operations fscache_caches_seq_ops; -#endif -bool fscache_begin_cache_access(struct fscache_cache *cache, enum fscache_access_trace why); -void fscache_end_cache_access(struct fscache_cache *cache, enum fscache_access_trace why); -struct fscache_cache *fscache_lookup_cache(const char *name, bool is_cache); -void fscache_put_cache(struct fscache_cache *cache, enum fscache_cache_trace where); - -static inline enum fscache_cache_state fscache_cache_state(const struct fscache_cache *cache) -{ - return smp_load_acquire(&cache->state); -} - -static inline bool fscache_cache_is_live(const struct fscache_cache *cache) -{ - return fscache_cache_state(cache) == FSCACHE_CACHE_IS_ACTIVE; -} - -static inline void fscache_set_cache_state(struct fscache_cache *cache, - enum fscache_cache_state new_state) -{ - smp_store_release(&cache->state, new_state); - -} - -static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache, - enum fscache_cache_state old_state, - enum fscache_cache_state new_state) -{ - return try_cmpxchg_release(&cache->state, &old_state, new_state); -} - -/* - * cookie.c - */ -extern struct kmem_cache *fscache_cookie_jar; -#ifdef CONFIG_PROC_FS -extern const struct seq_operations fscache_cookies_seq_ops; -#endif -extern struct timer_list fscache_cookie_lru_timer; - -extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix); -extern bool fscache_begin_cookie_access(struct fscache_cookie *cookie, - enum fscache_access_trace why); - -static inline void fscache_see_cookie(struct fscache_cookie *cookie, - enum fscache_cookie_trace where) -{ - trace_fscache_cookie(cookie->debug_id, refcount_read(&cookie->ref), - where); -} - -/* - * main.c - */ -extern unsigned fscache_debug; - -extern unsigned int fscache_hash(unsigned int salt, const void *data, size_t len); - -/* - * proc.c - */ -#ifdef CONFIG_PROC_FS -extern int __init fscache_proc_init(void); -extern void fscache_proc_cleanup(void); -#else -#define fscache_proc_init() (0) -#define fscache_proc_cleanup() do {} while (0) -#endif - -/* - * stats.c - */ -#ifdef CONFIG_FSCACHE_STATS -extern atomic_t fscache_n_volumes; -extern atomic_t fscache_n_volumes_collision; -extern atomic_t fscache_n_volumes_nomem; -extern atomic_t fscache_n_cookies; -extern atomic_t fscache_n_cookies_lru; -extern atomic_t fscache_n_cookies_lru_expired; -extern atomic_t fscache_n_cookies_lru_removed; -extern atomic_t fscache_n_cookies_lru_dropped; - -extern atomic_t fscache_n_acquires; -extern atomic_t fscache_n_acquires_ok; -extern atomic_t fscache_n_acquires_oom; - -extern atomic_t fscache_n_invalidates; - -extern atomic_t fscache_n_relinquishes; -extern atomic_t fscache_n_relinquishes_retire; -extern atomic_t fscache_n_relinquishes_dropped; - -extern atomic_t fscache_n_resizes; -extern atomic_t fscache_n_resizes_null; - -static inline void fscache_stat(atomic_t *stat) -{ - atomic_inc(stat); -} - -static inline void fscache_stat_d(atomic_t *stat) -{ - atomic_dec(stat); -} - -#define __fscache_stat(stat) (stat) - -int fscache_stats_show(struct seq_file *m, void *v); -#else - -#define __fscache_stat(stat) (NULL) -#define fscache_stat(stat) do {} while (0) -#define fscache_stat_d(stat) do {} while (0) -#endif - -/* - * volume.c - */ -#ifdef CONFIG_PROC_FS -extern const struct seq_operations fscache_volumes_seq_ops; -#endif - -struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, - enum fscache_volume_trace where); -void fscache_put_volume(struct fscache_volume *volume, - enum fscache_volume_trace where); -bool fscache_begin_volume_access(struct fscache_volume *volume, - struct fscache_cookie *cookie, - enum fscache_access_trace why); -void fscache_create_volume(struct fscache_volume *volume, bool wait); - - -/*****************************************************************************/ -/* - * debug tracing - */ -#define dbgprintk(FMT, ...) \ - printk("[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__) - -#define kenter(FMT, ...) dbgprintk("==> %s("FMT")", __func__, ##__VA_ARGS__) -#define kleave(FMT, ...) dbgprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__) -#define kdebug(FMT, ...) dbgprintk(FMT, ##__VA_ARGS__) - -#define kjournal(FMT, ...) no_printk(FMT, ##__VA_ARGS__) - -#ifdef __KDEBUG -#define _enter(FMT, ...) kenter(FMT, ##__VA_ARGS__) -#define _leave(FMT, ...) kleave(FMT, ##__VA_ARGS__) -#define _debug(FMT, ...) kdebug(FMT, ##__VA_ARGS__) - -#elif defined(CONFIG_FSCACHE_DEBUG) -#define _enter(FMT, ...) \ -do { \ - if (__do_kdebug(ENTER)) \ - kenter(FMT, ##__VA_ARGS__); \ -} while (0) - -#define _leave(FMT, ...) \ -do { \ - if (__do_kdebug(LEAVE)) \ - kleave(FMT, ##__VA_ARGS__); \ -} while (0) - -#define _debug(FMT, ...) \ -do { \ - if (__do_kdebug(DEBUG)) \ - kdebug(FMT, ##__VA_ARGS__); \ -} while (0) - -#else -#define _enter(FMT, ...) no_printk("==> %s("FMT")", __func__, ##__VA_ARGS__) -#define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__) -#define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__) -#endif - -/* - * determine whether a particular optional debugging point should be logged - * - we need to go through three steps to persuade cpp to correctly join the - * shorthand in FSCACHE_DEBUG_LEVEL with its prefix - */ -#define ____do_kdebug(LEVEL, POINT) \ - unlikely((fscache_debug & \ - (FSCACHE_POINT_##POINT << (FSCACHE_DEBUG_ ## LEVEL * 3)))) -#define ___do_kdebug(LEVEL, POINT) \ - ____do_kdebug(LEVEL, POINT) -#define __do_kdebug(POINT) \ - ___do_kdebug(FSCACHE_DEBUG_LEVEL, POINT) - -#define FSCACHE_DEBUG_CACHE 0 -#define FSCACHE_DEBUG_COOKIE 1 -#define FSCACHE_DEBUG_OBJECT 2 -#define FSCACHE_DEBUG_OPERATION 3 - -#define FSCACHE_POINT_ENTER 1 -#define FSCACHE_POINT_LEAVE 2 -#define FSCACHE_POINT_DEBUG 4 - -#ifndef FSCACHE_DEBUG_LEVEL -#define FSCACHE_DEBUG_LEVEL CACHE -#endif - -/* - * assertions - */ -#if 1 /* defined(__KDEBUGALL) */ - -#define ASSERT(X) \ -do { \ - if (unlikely(!(X))) { \ - pr_err("\n"); \ - pr_err("Assertion failed\n"); \ - BUG(); \ - } \ -} while (0) - -#define ASSERTCMP(X, OP, Y) \ -do { \ - if (unlikely(!((X) OP (Y)))) { \ - pr_err("\n"); \ - pr_err("Assertion failed\n"); \ - pr_err("%lx " #OP " %lx is false\n", \ - (unsigned long)(X), (unsigned long)(Y)); \ - BUG(); \ - } \ -} while (0) - -#define ASSERTIF(C, X) \ -do { \ - if (unlikely((C) && !(X))) { \ - pr_err("\n"); \ - pr_err("Assertion failed\n"); \ - BUG(); \ - } \ -} while (0) - -#define ASSERTIFCMP(C, X, OP, Y) \ -do { \ - if (unlikely((C) && !((X) OP (Y)))) { \ - pr_err("\n"); \ - pr_err("Assertion failed\n"); \ - pr_err("%lx " #OP " %lx is false\n", \ - (unsigned long)(X), (unsigned long)(Y)); \ - BUG(); \ - } \ -} while (0) - -#else - -#define ASSERT(X) do {} while (0) -#define ASSERTCMP(X, OP, Y) do {} while (0) -#define ASSERTIF(C, X) do {} while (0) -#define ASSERTIFCMP(C, X, OP, Y) do {} while (0) - -#endif /* assert or not */ diff --git a/fs/netfs/Kconfig b/fs/netfs/Kconfig index b4db21022cb4..bec805e0c44c 100644 --- a/fs/netfs/Kconfig +++ b/fs/netfs/Kconfig @@ -21,3 +21,42 @@ config NETFS_STATS multi-CPU system these may be on cachelines that keep bouncing between CPUs. On the other hand, the stats are very useful for debugging purposes. Saying 'Y' here is recommended. + +config FSCACHE + bool "General filesystem local caching manager" + depends on NETFS_SUPPORT + help + This option enables a generic filesystem caching manager that can be + used by various network and other filesystems to cache data locally. + Different sorts of caches can be plugged in, depending on the + resources available. + + See Documentation/filesystems/caching/fscache.rst for more information. + +config FSCACHE_STATS + bool "Gather statistical information on local caching" + depends on FSCACHE && PROC_FS + select NETFS_STATS + help + This option causes statistical information to be gathered on local + caching and exported through file: + + /proc/fs/fscache/stats + + The gathering of statistics adds a certain amount of overhead to + execution as there are a quite a few stats gathered, and on a + multi-CPU system these may be on cachelines that keep bouncing + between CPUs. On the other hand, the stats are very useful for + debugging purposes. Saying 'Y' here is recommended. + + See Documentation/filesystems/caching/fscache.rst for more information. + +config FSCACHE_DEBUG + bool "Debug FS-Cache" + depends on FSCACHE + help + This permits debugging to be dynamically enabled in the local caching + management module. If this is set, the debugging output may be + enabled by setting bits in /sys/modules/fscache/parameter/debug. + + See Documentation/filesystems/caching/fscache.rst for more information. diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile index 386d6fb92793..d4d1d799819e 100644 --- a/fs/netfs/Makefile +++ b/fs/netfs/Makefile @@ -2,11 +2,29 @@ netfs-y := \ buffered_read.o \ + buffered_write.o \ + direct_read.o \ + direct_write.o \ io.o \ iterator.o \ + locking.o \ main.o \ - objects.o + misc.o \ + objects.o \ + output.o netfs-$(CONFIG_NETFS_STATS) += stats.o -obj-$(CONFIG_NETFS_SUPPORT) := netfs.o +netfs-$(CONFIG_FSCACHE) += \ + fscache_cache.o \ + fscache_cookie.o \ + fscache_io.o \ + fscache_main.o \ + fscache_volume.o + +ifeq ($(CONFIG_PROC_FS),y) +netfs-$(CONFIG_FSCACHE) += fscache_proc.o +endif +netfs-$(CONFIG_FSCACHE_STATS) += fscache_stats.o + +obj-$(CONFIG_NETFS_SUPPORT) += netfs.o diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 2cd3ccf4c439..a59e7b2edaac 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -16,6 +16,7 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) { struct netfs_io_subrequest *subreq; + struct netfs_folio *finfo; struct folio *folio; pgoff_t start_page = rreq->start / PAGE_SIZE; pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; @@ -63,6 +64,7 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) break; } if (!folio_started && test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { + trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); folio_start_fscache(folio); folio_started = true; } @@ -86,6 +88,15 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) if (!pg_failed) { flush_dcache_folio(folio); + finfo = netfs_folio_info(folio); + if (finfo) { + trace_netfs_folio(folio, netfs_folio_trace_filled_gaps); + if (finfo->netfs_group) + folio_change_private(folio, finfo->netfs_group); + else + folio_detach_private(folio); + kfree(finfo); + } folio_mark_uptodate(folio); } @@ -147,6 +158,15 @@ static void netfs_rreq_expand(struct netfs_io_request *rreq, } } +/* + * Begin an operation, and fetch the stored zero point value from the cookie if + * available. + */ +static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_inode *ctx) +{ + return fscache_begin_read_operation(&rreq->cache_resources, netfs_i_cookie(ctx)); +} + /** * netfs_readahead - Helper to manage a read request * @ractl: The description of the readahead request @@ -180,11 +200,9 @@ void netfs_readahead(struct readahead_control *ractl) if (IS_ERR(rreq)) return; - if (ctx->ops->begin_cache_operation) { - ret = ctx->ops->begin_cache_operation(rreq); - if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) - goto cleanup_free; - } + ret = netfs_begin_cache_read(rreq, ctx); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto cleanup_free; netfs_stat(&netfs_n_rh_readahead); trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), @@ -192,6 +210,10 @@ void netfs_readahead(struct readahead_control *ractl) netfs_rreq_expand(rreq, ractl); + /* Set up the output buffer */ + iov_iter_xarray(&rreq->iter, ITER_DEST, &ractl->mapping->i_pages, + rreq->start, rreq->len); + /* Drop the refs on the folios here rather than in the cache or * filesystem. The locks will be dropped in netfs_rreq_unlock(). */ @@ -199,6 +221,7 @@ void netfs_readahead(struct readahead_control *ractl) ; netfs_begin_read(rreq, false); + netfs_put_request(rreq, false, netfs_rreq_trace_put_return); return; cleanup_free: @@ -226,6 +249,7 @@ int netfs_read_folio(struct file *file, struct folio *folio) struct address_space *mapping = folio_file_mapping(folio); struct netfs_io_request *rreq; struct netfs_inode *ctx = netfs_inode(mapping->host); + struct folio *sink = NULL; int ret; _enter("%lx", folio_index(folio)); @@ -238,15 +262,64 @@ int netfs_read_folio(struct file *file, struct folio *folio) goto alloc_error; } - if (ctx->ops->begin_cache_operation) { - ret = ctx->ops->begin_cache_operation(rreq); - if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) - goto discard; - } + ret = netfs_begin_cache_read(rreq, ctx); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto discard; netfs_stat(&netfs_n_rh_readpage); trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage); - return netfs_begin_read(rreq, true); + + /* Set up the output buffer */ + if (folio_test_dirty(folio)) { + /* Handle someone trying to read from an unflushed streaming + * write. We fiddle the buffer so that a gap at the beginning + * and/or a gap at the end get copied to, but the middle is + * discarded. + */ + struct netfs_folio *finfo = netfs_folio_info(folio); + struct bio_vec *bvec; + unsigned int from = finfo->dirty_offset; + unsigned int to = from + finfo->dirty_len; + unsigned int off = 0, i = 0; + size_t flen = folio_size(folio); + size_t nr_bvec = flen / PAGE_SIZE + 2; + size_t part; + + ret = -ENOMEM; + bvec = kmalloc_array(nr_bvec, sizeof(*bvec), GFP_KERNEL); + if (!bvec) + goto discard; + + sink = folio_alloc(GFP_KERNEL, 0); + if (!sink) + goto discard; + + trace_netfs_folio(folio, netfs_folio_trace_read_gaps); + + rreq->direct_bv = bvec; + rreq->direct_bv_count = nr_bvec; + if (from > 0) { + bvec_set_folio(&bvec[i++], folio, from, 0); + off = from; + } + while (off < to) { + part = min_t(size_t, to - off, PAGE_SIZE); + bvec_set_folio(&bvec[i++], sink, part, 0); + off += part; + } + if (to < flen) + bvec_set_folio(&bvec[i++], folio, flen - to, to); + iov_iter_bvec(&rreq->iter, ITER_DEST, bvec, i, rreq->len); + } else { + iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages, + rreq->start, rreq->len); + } + + ret = netfs_begin_read(rreq, true); + if (sink) + folio_put(sink); + netfs_put_request(rreq, false, netfs_rreq_trace_put_return); + return ret < 0 ? ret : 0; discard: netfs_put_request(rreq, false, netfs_rreq_trace_put_discard); @@ -390,11 +463,9 @@ retry: rreq->no_unlock_folio = folio_index(folio); __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); - if (ctx->ops->begin_cache_operation) { - ret = ctx->ops->begin_cache_operation(rreq); - if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) - goto error_put; - } + ret = netfs_begin_cache_read(rreq, ctx); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto error_put; netfs_stat(&netfs_n_rh_write_begin); trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin); @@ -405,6 +476,10 @@ retry: ractl._nr_pages = folio_nr_pages(folio); netfs_rreq_expand(rreq, &ractl); + /* Set up the output buffer */ + iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages, + rreq->start, rreq->len); + /* We hold the folio locks, so we can drop the references */ folio_get(folio); while (readahead_folio(&ractl)) @@ -413,6 +488,7 @@ retry: ret = netfs_begin_read(rreq, true); if (ret < 0) goto error; + netfs_put_request(rreq, false, netfs_rreq_trace_put_return); have_folio: ret = folio_wait_fscache_killable(folio); @@ -434,3 +510,124 @@ error: return ret; } EXPORT_SYMBOL(netfs_write_begin); + +/* + * Preload the data into a page we're proposing to write into. + */ +int netfs_prefetch_for_write(struct file *file, struct folio *folio, + size_t offset, size_t len) +{ + struct netfs_io_request *rreq; + struct address_space *mapping = folio_file_mapping(folio); + struct netfs_inode *ctx = netfs_inode(mapping->host); + unsigned long long start = folio_pos(folio); + size_t flen = folio_size(folio); + int ret; + + _enter("%zx @%llx", flen, start); + + ret = -ENOMEM; + + rreq = netfs_alloc_request(mapping, file, start, flen, + NETFS_READ_FOR_WRITE); + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); + goto error; + } + + rreq->no_unlock_folio = folio_index(folio); + __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); + ret = netfs_begin_cache_read(rreq, ctx); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto error_put; + + netfs_stat(&netfs_n_rh_write_begin); + trace_netfs_read(rreq, start, flen, netfs_read_trace_prefetch_for_write); + + /* Set up the output buffer */ + iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages, + rreq->start, rreq->len); + + ret = netfs_begin_read(rreq, true); + netfs_put_request(rreq, false, netfs_rreq_trace_put_return); + return ret; + +error_put: + netfs_put_request(rreq, false, netfs_rreq_trace_put_discard); +error: + _leave(" = %d", ret); + return ret; +} + +/** + * netfs_buffered_read_iter - Filesystem buffered I/O read routine + * @iocb: kernel I/O control block + * @iter: destination for the data read + * + * This is the ->read_iter() routine for all filesystems that can use the page + * cache directly. + * + * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall be + * returned when no data can be read without waiting for I/O requests to + * complete; it doesn't prevent readahead. + * + * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O requests + * shall be made for the read or for readahead. When no data can be read, + * -EAGAIN shall be returned. When readahead would be triggered, a partial, + * possibly empty read shall be returned. + * + * Return: + * * number of bytes copied, even for partial reads + * * negative error code (or 0 if IOCB_NOIO) if nothing was read + */ +ssize_t netfs_buffered_read_iter(struct kiocb *iocb, struct iov_iter *iter) +{ + struct inode *inode = file_inode(iocb->ki_filp); + struct netfs_inode *ictx = netfs_inode(inode); + ssize_t ret; + + if (WARN_ON_ONCE((iocb->ki_flags & IOCB_DIRECT) || + test_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags))) + return -EINVAL; + + ret = netfs_start_io_read(inode); + if (ret == 0) { + ret = filemap_read(iocb, iter, 0); + netfs_end_io_read(inode); + } + return ret; +} +EXPORT_SYMBOL(netfs_buffered_read_iter); + +/** + * netfs_file_read_iter - Generic filesystem read routine + * @iocb: kernel I/O control block + * @iter: destination for the data read + * + * This is the ->read_iter() routine for all filesystems that can use the page + * cache directly. + * + * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall be + * returned when no data can be read without waiting for I/O requests to + * complete; it doesn't prevent readahead. + * + * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O requests + * shall be made for the read or for readahead. When no data can be read, + * -EAGAIN shall be returned. When readahead would be triggered, a partial, + * possibly empty read shall be returned. + * + * Return: + * * number of bytes copied, even for partial reads + * * negative error code (or 0 if IOCB_NOIO) if nothing was read + */ +ssize_t netfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) +{ + struct netfs_inode *ictx = netfs_inode(iocb->ki_filp->f_mapping->host); + + if ((iocb->ki_flags & IOCB_DIRECT) || + test_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags)) + return netfs_unbuffered_read_iter(iocb, iter); + + return netfs_buffered_read_iter(iocb, iter); +} +EXPORT_SYMBOL(netfs_file_read_iter); diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c new file mode 100644 index 000000000000..93dc76f34e39 --- /dev/null +++ b/fs/netfs/buffered_write.c @@ -0,0 +1,1253 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Network filesystem high-level write support. + * + * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/export.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/slab.h> +#include <linux/pagevec.h> +#include "internal.h" + +/* + * Determined write method. Adjust netfs_folio_traces if this is changed. + */ +enum netfs_how_to_modify { + NETFS_FOLIO_IS_UPTODATE, /* Folio is uptodate already */ + NETFS_JUST_PREFETCH, /* We have to read the folio anyway */ + NETFS_WHOLE_FOLIO_MODIFY, /* We're going to overwrite the whole folio */ + NETFS_MODIFY_AND_CLEAR, /* We can assume there is no data to be downloaded. */ + NETFS_STREAMING_WRITE, /* Store incomplete data in non-uptodate page. */ + NETFS_STREAMING_WRITE_CONT, /* Continue streaming write. */ + NETFS_FLUSH_CONTENT, /* Flush incompatible content. */ +}; + +static void netfs_cleanup_buffered_write(struct netfs_io_request *wreq); + +static void netfs_set_group(struct folio *folio, struct netfs_group *netfs_group) +{ + if (netfs_group && !folio_get_private(folio)) + folio_attach_private(folio, netfs_get_group(netfs_group)); +} + +#if IS_ENABLED(CONFIG_FSCACHE) +static void netfs_folio_start_fscache(bool caching, struct folio *folio) +{ + if (caching) + folio_start_fscache(folio); +} +#else +static void netfs_folio_start_fscache(bool caching, struct folio *folio) +{ +} +#endif + +/* + * Decide how we should modify a folio. We might be attempting to do + * write-streaming, in which case we don't want to a local RMW cycle if we can + * avoid it. If we're doing local caching or content crypto, we award that + * priority over avoiding RMW. If the file is open readably, then we also + * assume that we may want to read what we wrote. + */ +static enum netfs_how_to_modify netfs_how_to_modify(struct netfs_inode *ctx, + struct file *file, + struct folio *folio, + void *netfs_group, + size_t flen, + size_t offset, + size_t len, + bool maybe_trouble) +{ + struct netfs_folio *finfo = netfs_folio_info(folio); + loff_t pos = folio_file_pos(folio); + + _enter(""); + + if (netfs_folio_group(folio) != netfs_group) + return NETFS_FLUSH_CONTENT; + + if (folio_test_uptodate(folio)) + return NETFS_FOLIO_IS_UPTODATE; + + if (pos >= ctx->zero_point) + return NETFS_MODIFY_AND_CLEAR; + + if (!maybe_trouble && offset == 0 && len >= flen) + return NETFS_WHOLE_FOLIO_MODIFY; + + if (file->f_mode & FMODE_READ) + goto no_write_streaming; + if (test_bit(NETFS_ICTX_NO_WRITE_STREAMING, &ctx->flags)) + goto no_write_streaming; + + if (netfs_is_cache_enabled(ctx)) { + /* We don't want to get a streaming write on a file that loses + * caching service temporarily because the backing store got + * culled. + */ + if (!test_bit(NETFS_ICTX_NO_WRITE_STREAMING, &ctx->flags)) + set_bit(NETFS_ICTX_NO_WRITE_STREAMING, &ctx->flags); + goto no_write_streaming; + } + + if (!finfo) + return NETFS_STREAMING_WRITE; + + /* We can continue a streaming write only if it continues on from the + * previous. If it overlaps, we must flush lest we suffer a partial + * copy and disjoint dirty regions. + */ + if (offset == finfo->dirty_offset + finfo->dirty_len) + return NETFS_STREAMING_WRITE_CONT; + return NETFS_FLUSH_CONTENT; + +no_write_streaming: + if (finfo) { + netfs_stat(&netfs_n_wh_wstream_conflict); + return NETFS_FLUSH_CONTENT; + } + return NETFS_JUST_PREFETCH; +} + +/* + * Grab a folio for writing and lock it. Attempt to allocate as large a folio + * as possible to hold as much of the remaining length as possible in one go. + */ +static struct folio *netfs_grab_folio_for_write(struct address_space *mapping, + loff_t pos, size_t part) +{ + pgoff_t index = pos / PAGE_SIZE; + fgf_t fgp_flags = FGP_WRITEBEGIN; + + if (mapping_large_folio_support(mapping)) + fgp_flags |= fgf_set_order(pos % PAGE_SIZE + part); + + return __filemap_get_folio(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); +} + +/** + * netfs_perform_write - Copy data into the pagecache. + * @iocb: The operation parameters + * @iter: The source buffer + * @netfs_group: Grouping for dirty pages (eg. ceph snaps). + * + * Copy data into pagecache pages attached to the inode specified by @iocb. + * The caller must hold appropriate inode locks. + * + * Dirty pages are tagged with a netfs_folio struct if they're not up to date + * to indicate the range modified. Dirty pages may also be tagged with a + * netfs-specific grouping such that data from an old group gets flushed before + * a new one is started. + */ +ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, + struct netfs_group *netfs_group) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); + struct address_space *mapping = inode->i_mapping; + struct netfs_inode *ctx = netfs_inode(inode); + struct writeback_control wbc = { + .sync_mode = WB_SYNC_NONE, + .for_sync = true, + .nr_to_write = LONG_MAX, + .range_start = iocb->ki_pos, + .range_end = iocb->ki_pos + iter->count, + }; + struct netfs_io_request *wreq = NULL; + struct netfs_folio *finfo; + struct folio *folio; + enum netfs_how_to_modify howto; + enum netfs_folio_trace trace; + unsigned int bdp_flags = (iocb->ki_flags & IOCB_SYNC) ? 0: BDP_ASYNC; + ssize_t written = 0, ret; + loff_t i_size, pos = iocb->ki_pos, from, to; + size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER; + bool maybe_trouble = false; + + if (unlikely(test_bit(NETFS_ICTX_WRITETHROUGH, &ctx->flags) || + iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC)) + ) { + if (pos < i_size_read(inode)) { + ret = filemap_write_and_wait_range(mapping, pos, pos + iter->count); + if (ret < 0) { + goto out; + } + } + + wbc_attach_fdatawrite_inode(&wbc, mapping->host); + + wreq = netfs_begin_writethrough(iocb, iter->count); + if (IS_ERR(wreq)) { + wbc_detach_inode(&wbc); + ret = PTR_ERR(wreq); + wreq = NULL; + goto out; + } + if (!is_sync_kiocb(iocb)) + wreq->iocb = iocb; + wreq->cleanup = netfs_cleanup_buffered_write; + } + + do { + size_t flen; + size_t offset; /* Offset into pagecache folio */ + size_t part; /* Bytes to write to folio */ + size_t copied; /* Bytes copied from user */ + + ret = balance_dirty_pages_ratelimited_flags(mapping, bdp_flags); + if (unlikely(ret < 0)) + break; + + offset = pos & (max_chunk - 1); + part = min(max_chunk - offset, iov_iter_count(iter)); + + /* Bring in the user pages that we will copy from _first_ lest + * we hit a nasty deadlock on copying from the same page as + * we're writing to, without it being marked uptodate. + * + * Not only is this an optimisation, but it is also required to + * check that the address is actually valid, when atomic + * usercopies are used below. + * + * We rely on the page being held onto long enough by the LRU + * that we can grab it below if this causes it to be read. + */ + ret = -EFAULT; + if (unlikely(fault_in_iov_iter_readable(iter, part) == part)) + break; + + ret = -ENOMEM; + folio = netfs_grab_folio_for_write(mapping, pos, part); + if (!folio) + break; + + flen = folio_size(folio); + offset = pos & (flen - 1); + part = min_t(size_t, flen - offset, part); + + if (signal_pending(current)) { + ret = written ? -EINTR : -ERESTARTSYS; + goto error_folio_unlock; + } + + /* See if we need to prefetch the area we're going to modify. + * We need to do this before we get a lock on the folio in case + * there's more than one writer competing for the same cache + * block. + */ + howto = netfs_how_to_modify(ctx, file, folio, netfs_group, + flen, offset, part, maybe_trouble); + _debug("howto %u", howto); + switch (howto) { + case NETFS_JUST_PREFETCH: + ret = netfs_prefetch_for_write(file, folio, offset, part); + if (ret < 0) { + _debug("prefetch = %zd", ret); + goto error_folio_unlock; + } + break; + case NETFS_FOLIO_IS_UPTODATE: + case NETFS_WHOLE_FOLIO_MODIFY: + case NETFS_STREAMING_WRITE_CONT: + break; + case NETFS_MODIFY_AND_CLEAR: + zero_user_segment(&folio->page, 0, offset); + break; + case NETFS_STREAMING_WRITE: + ret = -EIO; + if (WARN_ON(folio_get_private(folio))) + goto error_folio_unlock; + break; + case NETFS_FLUSH_CONTENT: + trace_netfs_folio(folio, netfs_flush_content); + from = folio_pos(folio); + to = from + folio_size(folio) - 1; + folio_unlock(folio); + folio_put(folio); + ret = filemap_write_and_wait_range(mapping, from, to); + if (ret < 0) + goto error_folio_unlock; + continue; + } + + if (mapping_writably_mapped(mapping)) + flush_dcache_folio(folio); + + copied = copy_folio_from_iter_atomic(folio, offset, part, iter); + + flush_dcache_folio(folio); + + /* Deal with a (partially) failed copy */ + if (copied == 0) { + ret = -EFAULT; + goto error_folio_unlock; + } + + trace = (enum netfs_folio_trace)howto; + switch (howto) { + case NETFS_FOLIO_IS_UPTODATE: + case NETFS_JUST_PREFETCH: + netfs_set_group(folio, netfs_group); + break; + case NETFS_MODIFY_AND_CLEAR: + zero_user_segment(&folio->page, offset + copied, flen); + netfs_set_group(folio, netfs_group); + folio_mark_uptodate(folio); + break; + case NETFS_WHOLE_FOLIO_MODIFY: + if (unlikely(copied < part)) { + maybe_trouble = true; + iov_iter_revert(iter, copied); + copied = 0; + goto retry; + } + netfs_set_group(folio, netfs_group); + folio_mark_uptodate(folio); + break; + case NETFS_STREAMING_WRITE: + if (offset == 0 && copied == flen) { + netfs_set_group(folio, netfs_group); + folio_mark_uptodate(folio); + trace = netfs_streaming_filled_page; + break; + } + finfo = kzalloc(sizeof(*finfo), GFP_KERNEL); + if (!finfo) { + iov_iter_revert(iter, copied); + ret = -ENOMEM; + goto error_folio_unlock; + } + finfo->netfs_group = netfs_get_group(netfs_group); + finfo->dirty_offset = offset; + finfo->dirty_len = copied; + folio_attach_private(folio, (void *)((unsigned long)finfo | + NETFS_FOLIO_INFO)); + break; + case NETFS_STREAMING_WRITE_CONT: + finfo = netfs_folio_info(folio); + finfo->dirty_len += copied; + if (finfo->dirty_offset == 0 && finfo->dirty_len == flen) { + if (finfo->netfs_group) + folio_change_private(folio, finfo->netfs_group); + else + folio_detach_private(folio); + folio_mark_uptodate(folio); + kfree(finfo); + trace = netfs_streaming_cont_filled_page; + } + break; + default: + WARN(true, "Unexpected modify type %u ix=%lx\n", + howto, folio_index(folio)); + ret = -EIO; + goto error_folio_unlock; + } + + trace_netfs_folio(folio, trace); + + /* Update the inode size if we moved the EOF marker */ + i_size = i_size_read(inode); + pos += copied; + if (pos > i_size) { + if (ctx->ops->update_i_size) { + ctx->ops->update_i_size(inode, pos); + } else { + i_size_write(inode, pos); +#if IS_ENABLED(CONFIG_FSCACHE) + fscache_update_cookie(ctx->cache, NULL, &pos); +#endif + } + } + written += copied; + + if (likely(!wreq)) { + folio_mark_dirty(folio); + } else { + if (folio_test_dirty(folio)) + /* Sigh. mmap. */ + folio_clear_dirty_for_io(folio); + /* We make multiple writes to the folio... */ + if (!folio_test_writeback(folio)) { + folio_wait_fscache(folio); + folio_start_writeback(folio); + folio_start_fscache(folio); + if (wreq->iter.count == 0) + trace_netfs_folio(folio, netfs_folio_trace_wthru); + else + trace_netfs_folio(folio, netfs_folio_trace_wthru_plus); + } + netfs_advance_writethrough(wreq, copied, + offset + copied == flen); + } + retry: + folio_unlock(folio); + folio_put(folio); + folio = NULL; + + cond_resched(); + } while (iov_iter_count(iter)); + +out: + if (unlikely(wreq)) { + ret = netfs_end_writethrough(wreq, iocb); + wbc_detach_inode(&wbc); + if (ret == -EIOCBQUEUED) + return ret; + } + + iocb->ki_pos += written; + _leave(" = %zd [%zd]", written, ret); + return written ? written : ret; + +error_folio_unlock: + folio_unlock(folio); + folio_put(folio); + goto out; +} +EXPORT_SYMBOL(netfs_perform_write); + +/** + * netfs_buffered_write_iter_locked - write data to a file + * @iocb: IO state structure (file, offset, etc.) + * @from: iov_iter with data to write + * @netfs_group: Grouping for dirty pages (eg. ceph snaps). + * + * This function does all the work needed for actually writing data to a + * file. It does all basic checks, removes SUID from the file, updates + * modification times and calls proper subroutines depending on whether we + * do direct IO or a standard buffered write. + * + * The caller must hold appropriate locks around this function and have called + * generic_write_checks() already. The caller is also responsible for doing + * any necessary syncing afterwards. + * + * This function does *not* take care of syncing data in case of O_SYNC write. + * A caller has to handle it. This is mainly due to the fact that we want to + * avoid syncing under i_rwsem. + * + * Return: + * * number of bytes written, even for truncated writes + * * negative error code if no data has been written at all + */ +ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *from, + struct netfs_group *netfs_group) +{ + struct file *file = iocb->ki_filp; + ssize_t ret; + + trace_netfs_write_iter(iocb, from); + + ret = file_remove_privs(file); + if (ret) + return ret; + + ret = file_update_time(file); + if (ret) + return ret; + + return netfs_perform_write(iocb, from, netfs_group); +} +EXPORT_SYMBOL(netfs_buffered_write_iter_locked); + +/** + * netfs_file_write_iter - write data to a file + * @iocb: IO state structure + * @from: iov_iter with data to write + * + * Perform a write to a file, writing into the pagecache if possible and doing + * an unbuffered write instead if not. + * + * Return: + * * Negative error code if no data has been written at all of + * vfs_fsync_range() failed for a synchronous write + * * Number of bytes written, even for truncated writes + */ +ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + struct netfs_inode *ictx = netfs_inode(inode); + ssize_t ret; + + _enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode)); + + if ((iocb->ki_flags & IOCB_DIRECT) || + test_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags)) + return netfs_unbuffered_write_iter(iocb, from); + + ret = netfs_start_io_write(inode); + if (ret < 0) + return ret; + + ret = generic_write_checks(iocb, from); + if (ret > 0) + ret = netfs_buffered_write_iter_locked(iocb, from, NULL); + netfs_end_io_write(inode); + if (ret > 0) + ret = generic_write_sync(iocb, ret); + return ret; +} +EXPORT_SYMBOL(netfs_file_write_iter); + +/* + * Notification that a previously read-only page is about to become writable. + * Note that the caller indicates a single page of a multipage folio. + */ +vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group) +{ + struct folio *folio = page_folio(vmf->page); + struct file *file = vmf->vma->vm_file; + struct inode *inode = file_inode(file); + vm_fault_t ret = VM_FAULT_RETRY; + int err; + + _enter("%lx", folio->index); + + sb_start_pagefault(inode->i_sb); + + if (folio_wait_writeback_killable(folio)) + goto out; + + if (folio_lock_killable(folio) < 0) + goto out; + + /* Can we see a streaming write here? */ + if (WARN_ON(!folio_test_uptodate(folio))) { + ret = VM_FAULT_SIGBUS | VM_FAULT_LOCKED; + goto out; + } + + if (netfs_folio_group(folio) != netfs_group) { + folio_unlock(folio); + err = filemap_fdatawait_range(inode->i_mapping, + folio_pos(folio), + folio_pos(folio) + folio_size(folio)); + switch (err) { + case 0: + ret = VM_FAULT_RETRY; + goto out; + case -ENOMEM: + ret = VM_FAULT_OOM; + goto out; + default: + ret = VM_FAULT_SIGBUS; + goto out; + } + } + + if (folio_test_dirty(folio)) + trace_netfs_folio(folio, netfs_folio_trace_mkwrite_plus); + else + trace_netfs_folio(folio, netfs_folio_trace_mkwrite); + netfs_set_group(folio, netfs_group); + file_update_time(file); + ret = VM_FAULT_LOCKED; +out: + sb_end_pagefault(inode->i_sb); + return ret; +} +EXPORT_SYMBOL(netfs_page_mkwrite); + +/* + * Kill all the pages in the given range + */ +static void netfs_kill_pages(struct address_space *mapping, + loff_t start, loff_t len) +{ + struct folio *folio; + pgoff_t index = start / PAGE_SIZE; + pgoff_t last = (start + len - 1) / PAGE_SIZE, next; + + _enter("%llx-%llx", start, start + len - 1); + + do { + _debug("kill %lx (to %lx)", index, last); + + folio = filemap_get_folio(mapping, index); + if (IS_ERR(folio)) { + next = index + 1; + continue; + } + + next = folio_next_index(folio); + + trace_netfs_folio(folio, netfs_folio_trace_kill); + folio_clear_uptodate(folio); + if (folio_test_fscache(folio)) + folio_end_fscache(folio); + folio_end_writeback(folio); + folio_lock(folio); + generic_error_remove_folio(mapping, folio); + folio_unlock(folio); + folio_put(folio); + + } while (index = next, index <= last); + + _leave(""); +} + +/* + * Redirty all the pages in a given range. + */ +static void netfs_redirty_pages(struct address_space *mapping, + loff_t start, loff_t len) +{ + struct folio *folio; + pgoff_t index = start / PAGE_SIZE; + pgoff_t last = (start + len - 1) / PAGE_SIZE, next; + + _enter("%llx-%llx", start, start + len - 1); + + do { + _debug("redirty %llx @%llx", len, start); + + folio = filemap_get_folio(mapping, index); + if (IS_ERR(folio)) { + next = index + 1; + continue; + } + + next = folio_next_index(folio); + trace_netfs_folio(folio, netfs_folio_trace_redirty); + filemap_dirty_folio(mapping, folio); + if (folio_test_fscache(folio)) + folio_end_fscache(folio); + folio_end_writeback(folio); + folio_put(folio); + } while (index = next, index <= last); + + balance_dirty_pages_ratelimited(mapping); + + _leave(""); +} + +/* + * Completion of write to server + */ +static void netfs_pages_written_back(struct netfs_io_request *wreq) +{ + struct address_space *mapping = wreq->mapping; + struct netfs_folio *finfo; + struct netfs_group *group = NULL; + struct folio *folio; + pgoff_t last; + int gcount = 0; + + XA_STATE(xas, &mapping->i_pages, wreq->start / PAGE_SIZE); + + _enter("%llx-%llx", wreq->start, wreq->start + wreq->len); + + rcu_read_lock(); + + last = (wreq->start + wreq->len - 1) / PAGE_SIZE; + xas_for_each(&xas, folio, last) { + WARN(!folio_test_writeback(folio), + "bad %zx @%llx page %lx %lx\n", + wreq->len, wreq->start, folio_index(folio), last); + + if ((finfo = netfs_folio_info(folio))) { + /* Streaming writes cannot be redirtied whilst under + * writeback, so discard the streaming record. + */ + folio_detach_private(folio); + group = finfo->netfs_group; + gcount++; + trace_netfs_folio(folio, netfs_folio_trace_clear_s); + kfree(finfo); + } else if ((group = netfs_folio_group(folio))) { + /* Need to detach the group pointer if the page didn't + * get redirtied. If it has been redirtied, then it + * must be within the same group. + */ + if (folio_test_dirty(folio)) { + trace_netfs_folio(folio, netfs_folio_trace_redirtied); + goto end_wb; + } + if (folio_trylock(folio)) { + if (!folio_test_dirty(folio)) { + folio_detach_private(folio); + gcount++; + trace_netfs_folio(folio, netfs_folio_trace_clear_g); + } else { + trace_netfs_folio(folio, netfs_folio_trace_redirtied); + } + folio_unlock(folio); + goto end_wb; + } + + xas_pause(&xas); + rcu_read_unlock(); + folio_lock(folio); + if (!folio_test_dirty(folio)) { + folio_detach_private(folio); + gcount++; + trace_netfs_folio(folio, netfs_folio_trace_clear_g); + } else { + trace_netfs_folio(folio, netfs_folio_trace_redirtied); + } + folio_unlock(folio); + rcu_read_lock(); + } else { + trace_netfs_folio(folio, netfs_folio_trace_clear); + } + end_wb: + if (folio_test_fscache(folio)) + folio_end_fscache(folio); + xas_advance(&xas, folio_next_index(folio) - 1); + folio_end_writeback(folio); + } + + rcu_read_unlock(); + netfs_put_group_many(group, gcount); + _leave(""); +} + +/* + * Deal with the disposition of the folios that are under writeback to close + * out the operation. + */ +static void netfs_cleanup_buffered_write(struct netfs_io_request *wreq) +{ + struct address_space *mapping = wreq->mapping; + + _enter(""); + + switch (wreq->error) { + case 0: + netfs_pages_written_back(wreq); + break; + + default: + pr_notice("R=%08x Unexpected error %d\n", wreq->debug_id, wreq->error); + fallthrough; + case -EACCES: + case -EPERM: + case -ENOKEY: + case -EKEYEXPIRED: + case -EKEYREJECTED: + case -EKEYREVOKED: + case -ENETRESET: + case -EDQUOT: + case -ENOSPC: + netfs_redirty_pages(mapping, wreq->start, wreq->len); + break; + + case -EROFS: + case -EIO: + case -EREMOTEIO: + case -EFBIG: + case -ENOENT: + case -ENOMEDIUM: + case -ENXIO: + netfs_kill_pages(mapping, wreq->start, wreq->len); + break; + } + + if (wreq->error) + mapping_set_error(mapping, wreq->error); + if (wreq->netfs_ops->done) + wreq->netfs_ops->done(wreq); +} + +/* + * Extend the region to be written back to include subsequent contiguously + * dirty pages if possible, but don't sleep while doing so. + * + * If this page holds new content, then we can include filler zeros in the + * writeback. + */ +static void netfs_extend_writeback(struct address_space *mapping, + struct netfs_group *group, + struct xa_state *xas, + long *_count, + loff_t start, + loff_t max_len, + bool caching, + size_t *_len, + size_t *_top) +{ + struct netfs_folio *finfo; + struct folio_batch fbatch; + struct folio *folio; + unsigned int i; + pgoff_t index = (start + *_len) / PAGE_SIZE; + size_t len; + void *priv; + bool stop = true; + + folio_batch_init(&fbatch); + + do { + /* Firstly, we gather up a batch of contiguous dirty pages + * under the RCU read lock - but we can't clear the dirty flags + * there if any of those pages are mapped. + */ + rcu_read_lock(); + + xas_for_each(xas, folio, ULONG_MAX) { + stop = true; + if (xas_retry(xas, folio)) + continue; + if (xa_is_value(folio)) + break; + if (folio_index(folio) != index) { + xas_reset(xas); + break; + } + + if (!folio_try_get_rcu(folio)) { + xas_reset(xas); + continue; + } + + /* Has the folio moved or been split? */ + if (unlikely(folio != xas_reload(xas))) { + folio_put(folio); + xas_reset(xas); + break; + } + + if (!folio_trylock(folio)) { + folio_put(folio); + xas_reset(xas); + break; + } + if (!folio_test_dirty(folio) || + folio_test_writeback(folio) || + folio_test_fscache(folio)) { + folio_unlock(folio); + folio_put(folio); + xas_reset(xas); + break; + } + + stop = false; + len = folio_size(folio); + priv = folio_get_private(folio); + if ((const struct netfs_group *)priv != group) { + stop = true; + finfo = netfs_folio_info(folio); + if (finfo->netfs_group != group || + finfo->dirty_offset > 0) { + folio_unlock(folio); + folio_put(folio); + xas_reset(xas); + break; + } + len = finfo->dirty_len; + } + + *_top += folio_size(folio); + index += folio_nr_pages(folio); + *_count -= folio_nr_pages(folio); + *_len += len; + if (*_len >= max_len || *_count <= 0) + stop = true; + + if (!folio_batch_add(&fbatch, folio)) + break; + if (stop) + break; + } + + xas_pause(xas); + rcu_read_unlock(); + + /* Now, if we obtained any folios, we can shift them to being + * writable and mark them for caching. + */ + if (!folio_batch_count(&fbatch)) + break; + + for (i = 0; i < folio_batch_count(&fbatch); i++) { + folio = fbatch.folios[i]; + trace_netfs_folio(folio, netfs_folio_trace_store_plus); + + if (!folio_clear_dirty_for_io(folio)) + BUG(); + folio_start_writeback(folio); + netfs_folio_start_fscache(caching, folio); + folio_unlock(folio); + } + + folio_batch_release(&fbatch); + cond_resched(); + } while (!stop); +} + +/* + * Synchronously write back the locked page and any subsequent non-locked dirty + * pages. + */ +static ssize_t netfs_write_back_from_locked_folio(struct address_space *mapping, + struct writeback_control *wbc, + struct netfs_group *group, + struct xa_state *xas, + struct folio *folio, + unsigned long long start, + unsigned long long end) +{ + struct netfs_io_request *wreq; + struct netfs_folio *finfo; + struct netfs_inode *ctx = netfs_inode(mapping->host); + unsigned long long i_size = i_size_read(&ctx->inode); + size_t len, max_len; + bool caching = netfs_is_cache_enabled(ctx); + long count = wbc->nr_to_write; + int ret; + + _enter(",%lx,%llx-%llx,%u", folio_index(folio), start, end, caching); + + wreq = netfs_alloc_request(mapping, NULL, start, folio_size(folio), + NETFS_WRITEBACK); + if (IS_ERR(wreq)) { + folio_unlock(folio); + return PTR_ERR(wreq); + } + + if (!folio_clear_dirty_for_io(folio)) + BUG(); + folio_start_writeback(folio); + netfs_folio_start_fscache(caching, folio); + + count -= folio_nr_pages(folio); + + /* Find all consecutive lockable dirty pages that have contiguous + * written regions, stopping when we find a page that is not + * immediately lockable, is not dirty or is missing, or we reach the + * end of the range. + */ + trace_netfs_folio(folio, netfs_folio_trace_store); + + len = wreq->len; + finfo = netfs_folio_info(folio); + if (finfo) { + start += finfo->dirty_offset; + if (finfo->dirty_offset + finfo->dirty_len != len) { + len = finfo->dirty_len; + goto cant_expand; + } + len = finfo->dirty_len; + } + + if (start < i_size) { + /* Trim the write to the EOF; the extra data is ignored. Also + * put an upper limit on the size of a single storedata op. + */ + max_len = 65536 * 4096; + max_len = min_t(unsigned long long, max_len, end - start + 1); + max_len = min_t(unsigned long long, max_len, i_size - start); + + if (len < max_len) + netfs_extend_writeback(mapping, group, xas, &count, start, + max_len, caching, &len, &wreq->upper_len); + } + +cant_expand: + len = min_t(unsigned long long, len, i_size - start); + + /* We now have a contiguous set of dirty pages, each with writeback + * set; the first page is still locked at this point, but all the rest + * have been unlocked. + */ + folio_unlock(folio); + wreq->start = start; + wreq->len = len; + + if (start < i_size) { + _debug("write back %zx @%llx [%llx]", len, start, i_size); + + /* Speculatively write to the cache. We have to fix this up + * later if the store fails. + */ + wreq->cleanup = netfs_cleanup_buffered_write; + + iov_iter_xarray(&wreq->iter, ITER_SOURCE, &mapping->i_pages, start, + wreq->upper_len); + __set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags); + ret = netfs_begin_write(wreq, true, netfs_write_trace_writeback); + if (ret == 0 || ret == -EIOCBQUEUED) + wbc->nr_to_write -= len / PAGE_SIZE; + } else { + _debug("write discard %zx @%llx [%llx]", len, start, i_size); + + /* The dirty region was entirely beyond the EOF. */ + fscache_clear_page_bits(mapping, start, len, caching); + netfs_pages_written_back(wreq); + ret = 0; + } + + netfs_put_request(wreq, false, netfs_rreq_trace_put_return); + _leave(" = 1"); + return 1; +} + +/* + * Write a region of pages back to the server + */ +static ssize_t netfs_writepages_begin(struct address_space *mapping, + struct writeback_control *wbc, + struct netfs_group *group, + struct xa_state *xas, + unsigned long long *_start, + unsigned long long end) +{ + const struct netfs_folio *finfo; + struct folio *folio; + unsigned long long start = *_start; + ssize_t ret; + void *priv; + int skips = 0; + + _enter("%llx,%llx,", start, end); + +search_again: + /* Find the first dirty page in the group. */ + rcu_read_lock(); + + for (;;) { + folio = xas_find_marked(xas, end / PAGE_SIZE, PAGECACHE_TAG_DIRTY); + if (xas_retry(xas, folio) || xa_is_value(folio)) + continue; + if (!folio) + break; + + if (!folio_try_get_rcu(folio)) { + xas_reset(xas); + continue; + } + + if (unlikely(folio != xas_reload(xas))) { + folio_put(folio); + xas_reset(xas); + continue; + } + + /* Skip any dirty folio that's not in the group of interest. */ + priv = folio_get_private(folio); + if ((const struct netfs_group *)priv != group) { + finfo = netfs_folio_info(folio); + if (finfo->netfs_group != group) { + folio_put(folio); + continue; + } + } + + xas_pause(xas); + break; + } + rcu_read_unlock(); + if (!folio) + return 0; + + start = folio_pos(folio); /* May regress with THPs */ + + _debug("wback %lx", folio_index(folio)); + + /* At this point we hold neither the i_pages lock nor the page lock: + * the page may be truncated or invalidated (changing page->mapping to + * NULL), or even swizzled back from swapper_space to tmpfs file + * mapping + */ +lock_again: + if (wbc->sync_mode != WB_SYNC_NONE) { + ret = folio_lock_killable(folio); + if (ret < 0) + return ret; + } else { + if (!folio_trylock(folio)) + goto search_again; + } + + if (folio->mapping != mapping || + !folio_test_dirty(folio)) { + start += folio_size(folio); + folio_unlock(folio); + goto search_again; + } + + if (folio_test_writeback(folio) || + folio_test_fscache(folio)) { + folio_unlock(folio); + if (wbc->sync_mode != WB_SYNC_NONE) { + folio_wait_writeback(folio); +#ifdef CONFIG_FSCACHE + folio_wait_fscache(folio); +#endif + goto lock_again; + } + + start += folio_size(folio); + if (wbc->sync_mode == WB_SYNC_NONE) { + if (skips >= 5 || need_resched()) { + ret = 0; + goto out; + } + skips++; + } + goto search_again; + } + + ret = netfs_write_back_from_locked_folio(mapping, wbc, group, xas, + folio, start, end); +out: + if (ret > 0) + *_start = start + ret; + _leave(" = %zd [%llx]", ret, *_start); + return ret; +} + +/* + * Write a region of pages back to the server + */ +static int netfs_writepages_region(struct address_space *mapping, + struct writeback_control *wbc, + struct netfs_group *group, + unsigned long long *_start, + unsigned long long end) +{ + ssize_t ret; + + XA_STATE(xas, &mapping->i_pages, *_start / PAGE_SIZE); + + do { + ret = netfs_writepages_begin(mapping, wbc, group, &xas, + _start, end); + if (ret > 0 && wbc->nr_to_write > 0) + cond_resched(); + } while (ret > 0 && wbc->nr_to_write > 0); + + return ret > 0 ? 0 : ret; +} + +/* + * write some of the pending data back to the server + */ +int netfs_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct netfs_group *group = NULL; + loff_t start, end; + int ret; + + _enter(""); + + /* We have to be careful as we can end up racing with setattr() + * truncating the pagecache since the caller doesn't take a lock here + * to prevent it. + */ + + if (wbc->range_cyclic && mapping->writeback_index) { + start = mapping->writeback_index * PAGE_SIZE; + ret = netfs_writepages_region(mapping, wbc, group, + &start, LLONG_MAX); + if (ret < 0) + goto out; + + if (wbc->nr_to_write <= 0) { + mapping->writeback_index = start / PAGE_SIZE; + goto out; + } + + start = 0; + end = mapping->writeback_index * PAGE_SIZE; + mapping->writeback_index = 0; + ret = netfs_writepages_region(mapping, wbc, group, &start, end); + if (ret == 0) + mapping->writeback_index = start / PAGE_SIZE; + } else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) { + start = 0; + ret = netfs_writepages_region(mapping, wbc, group, + &start, LLONG_MAX); + if (wbc->nr_to_write > 0 && ret == 0) + mapping->writeback_index = start / PAGE_SIZE; + } else { + start = wbc->range_start; + ret = netfs_writepages_region(mapping, wbc, group, + &start, wbc->range_end); + } + +out: + _leave(" = %d", ret); + return ret; +} +EXPORT_SYMBOL(netfs_writepages); + +/* + * Deal with the disposition of a laundered folio. + */ +static void netfs_cleanup_launder_folio(struct netfs_io_request *wreq) +{ + if (wreq->error) { + pr_notice("R=%08x Laundering error %d\n", wreq->debug_id, wreq->error); + mapping_set_error(wreq->mapping, wreq->error); + } +} + +/** + * netfs_launder_folio - Clean up a dirty folio that's being invalidated + * @folio: The folio to clean + * + * This is called to write back a folio that's being invalidated when an inode + * is getting torn down. Ideally, writepages would be used instead. + */ +int netfs_launder_folio(struct folio *folio) +{ + struct netfs_io_request *wreq; + struct address_space *mapping = folio->mapping; + struct netfs_folio *finfo = netfs_folio_info(folio); + struct netfs_group *group = netfs_folio_group(folio); + struct bio_vec bvec; + unsigned long long i_size = i_size_read(mapping->host); + unsigned long long start = folio_pos(folio); + size_t offset = 0, len; + int ret = 0; + + if (finfo) { + offset = finfo->dirty_offset; + start += offset; + len = finfo->dirty_len; + } else { + len = folio_size(folio); + } + len = min_t(unsigned long long, len, i_size - start); + + wreq = netfs_alloc_request(mapping, NULL, start, len, NETFS_LAUNDER_WRITE); + if (IS_ERR(wreq)) { + ret = PTR_ERR(wreq); + goto out; + } + + if (!folio_clear_dirty_for_io(folio)) + goto out_put; + + trace_netfs_folio(folio, netfs_folio_trace_launder); + + _debug("launder %llx-%llx", start, start + len - 1); + + /* Speculatively write to the cache. We have to fix this up later if + * the store fails. + */ + wreq->cleanup = netfs_cleanup_launder_folio; + + bvec_set_folio(&bvec, folio, len, offset); + iov_iter_bvec(&wreq->iter, ITER_SOURCE, &bvec, 1, len); + __set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags); + ret = netfs_begin_write(wreq, true, netfs_write_trace_launder); + +out_put: + folio_detach_private(folio); + netfs_put_group(group); + kfree(finfo); + netfs_put_request(wreq, false, netfs_rreq_trace_put_return); +out: + folio_wait_fscache(folio); + _leave(" = %d", ret); + return ret; +} +EXPORT_SYMBOL(netfs_launder_folio); diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c new file mode 100644 index 000000000000..ad4370b3935d --- /dev/null +++ b/fs/netfs/direct_read.c @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Direct I/O support. + * + * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/export.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/slab.h> +#include <linux/uio.h> +#include <linux/sched/mm.h> +#include <linux/task_io_accounting_ops.h> +#include <linux/netfs.h> +#include "internal.h" + +/** + * netfs_unbuffered_read_iter_locked - Perform an unbuffered or direct I/O read + * @iocb: The I/O control descriptor describing the read + * @iter: The output buffer (also specifies read length) + * + * Perform an unbuffered I/O or direct I/O from the file in @iocb to the + * output buffer. No use is made of the pagecache. + * + * The caller must hold any appropriate locks. + */ +static ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *iter) +{ + struct netfs_io_request *rreq; + ssize_t ret; + size_t orig_count = iov_iter_count(iter); + bool async = !is_sync_kiocb(iocb); + + _enter(""); + + if (!orig_count) + return 0; /* Don't update atime */ + + ret = kiocb_write_and_wait(iocb, orig_count); + if (ret < 0) + return ret; + file_accessed(iocb->ki_filp); + + rreq = netfs_alloc_request(iocb->ki_filp->f_mapping, iocb->ki_filp, + iocb->ki_pos, orig_count, + NETFS_DIO_READ); + if (IS_ERR(rreq)) + return PTR_ERR(rreq); + + netfs_stat(&netfs_n_rh_dio_read); + trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_dio_read); + + /* If this is an async op, we have to keep track of the destination + * buffer for ourselves as the caller's iterator will be trashed when + * we return. + * + * In such a case, extract an iterator to represent as much of the the + * output buffer as we can manage. Note that the extraction might not + * be able to allocate a sufficiently large bvec array and may shorten + * the request. + */ + if (user_backed_iter(iter)) { + ret = netfs_extract_user_iter(iter, rreq->len, &rreq->iter, 0); + if (ret < 0) + goto out; + rreq->direct_bv = (struct bio_vec *)rreq->iter.bvec; + rreq->direct_bv_count = ret; + rreq->direct_bv_unpin = iov_iter_extract_will_pin(iter); + rreq->len = iov_iter_count(&rreq->iter); + } else { + rreq->iter = *iter; + rreq->len = orig_count; + rreq->direct_bv_unpin = false; + iov_iter_advance(iter, orig_count); + } + + // TODO: Set up bounce buffer if needed + + if (async) + rreq->iocb = iocb; + + ret = netfs_begin_read(rreq, is_sync_kiocb(iocb)); + if (ret < 0) + goto out; /* May be -EIOCBQUEUED */ + if (!async) { + // TODO: Copy from bounce buffer + iocb->ki_pos += rreq->transferred; + ret = rreq->transferred; + } + +out: + netfs_put_request(rreq, false, netfs_rreq_trace_put_return); + if (ret > 0) + orig_count -= ret; + if (ret != -EIOCBQUEUED) + iov_iter_revert(iter, orig_count - iov_iter_count(iter)); + return ret; +} + +/** + * netfs_unbuffered_read_iter - Perform an unbuffered or direct I/O read + * @iocb: The I/O control descriptor describing the read + * @iter: The output buffer (also specifies read length) + * + * Perform an unbuffered I/O or direct I/O from the file in @iocb to the + * output buffer. No use is made of the pagecache. + */ +ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter) +{ + struct inode *inode = file_inode(iocb->ki_filp); + ssize_t ret; + + if (!iter->count) + return 0; /* Don't update atime */ + + ret = netfs_start_io_direct(inode); + if (ret == 0) { + ret = netfs_unbuffered_read_iter_locked(iocb, iter); + netfs_end_io_direct(inode); + } + return ret; +} +EXPORT_SYMBOL(netfs_unbuffered_read_iter); diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c new file mode 100644 index 000000000000..60a40d293c87 --- /dev/null +++ b/fs/netfs/direct_write.c @@ -0,0 +1,171 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Unbuffered and direct write support. + * + * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/export.h> +#include <linux/uio.h> +#include "internal.h" + +static void netfs_cleanup_dio_write(struct netfs_io_request *wreq) +{ + struct inode *inode = wreq->inode; + unsigned long long end = wreq->start + wreq->len; + + if (!wreq->error && + i_size_read(inode) < end) { + if (wreq->netfs_ops->update_i_size) + wreq->netfs_ops->update_i_size(inode, end); + else + i_size_write(inode, end); + } +} + +/* + * Perform an unbuffered write where we may have to do an RMW operation on an + * encrypted file. This can also be used for direct I/O writes. + */ +static ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter, + struct netfs_group *netfs_group) +{ + struct netfs_io_request *wreq; + unsigned long long start = iocb->ki_pos; + unsigned long long end = start + iov_iter_count(iter); + ssize_t ret, n; + bool async = !is_sync_kiocb(iocb); + + _enter(""); + + /* We're going to need a bounce buffer if what we transmit is going to + * be different in some way to the source buffer, e.g. because it gets + * encrypted/compressed or because it needs expanding to a block size. + */ + // TODO + + _debug("uw %llx-%llx", start, end); + + wreq = netfs_alloc_request(iocb->ki_filp->f_mapping, iocb->ki_filp, + start, end - start, + iocb->ki_flags & IOCB_DIRECT ? + NETFS_DIO_WRITE : NETFS_UNBUFFERED_WRITE); + if (IS_ERR(wreq)) + return PTR_ERR(wreq); + + { + /* If this is an async op and we're not using a bounce buffer, + * we have to save the source buffer as the iterator is only + * good until we return. In such a case, extract an iterator + * to represent as much of the the output buffer as we can + * manage. Note that the extraction might not be able to + * allocate a sufficiently large bvec array and may shorten the + * request. + */ + if (async || user_backed_iter(iter)) { + n = netfs_extract_user_iter(iter, wreq->len, &wreq->iter, 0); + if (n < 0) { + ret = n; + goto out; + } + wreq->direct_bv = (struct bio_vec *)wreq->iter.bvec; + wreq->direct_bv_count = n; + wreq->direct_bv_unpin = iov_iter_extract_will_pin(iter); + wreq->len = iov_iter_count(&wreq->iter); + } else { + wreq->iter = *iter; + } + + wreq->io_iter = wreq->iter; + } + + /* Copy the data into the bounce buffer and encrypt it. */ + // TODO + + /* Dispatch the write. */ + __set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags); + if (async) + wreq->iocb = iocb; + wreq->cleanup = netfs_cleanup_dio_write; + ret = netfs_begin_write(wreq, is_sync_kiocb(iocb), + iocb->ki_flags & IOCB_DIRECT ? + netfs_write_trace_dio_write : + netfs_write_trace_unbuffered_write); + if (ret < 0) { + _debug("begin = %zd", ret); + goto out; + } + + if (!async) { + trace_netfs_rreq(wreq, netfs_rreq_trace_wait_ip); + wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS, + TASK_UNINTERRUPTIBLE); + + ret = wreq->error; + _debug("waited = %zd", ret); + if (ret == 0) { + ret = wreq->transferred; + iocb->ki_pos += ret; + } + } else { + ret = -EIOCBQUEUED; + } + +out: + netfs_put_request(wreq, false, netfs_rreq_trace_put_return); + return ret; +} + +/** + * netfs_unbuffered_write_iter - Unbuffered write to a file + * @iocb: IO state structure + * @from: iov_iter with data to write + * + * Do an unbuffered write to a file, writing the data directly to the server + * and not lodging the data in the pagecache. + * + * Return: + * * Negative error code if no data has been written at all of + * vfs_fsync_range() failed for a synchronous write + * * Number of bytes written, even for truncated writes + */ +ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + struct netfs_inode *ictx = netfs_inode(inode); + unsigned long long end; + ssize_t ret; + + _enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode)); + + trace_netfs_write_iter(iocb, from); + netfs_stat(&netfs_n_rh_dio_write); + + ret = netfs_start_io_direct(inode); + if (ret < 0) + return ret; + ret = generic_write_checks(iocb, from); + if (ret < 0) + goto out; + ret = file_remove_privs(file); + if (ret < 0) + goto out; + ret = file_update_time(file); + if (ret < 0) + goto out; + ret = kiocb_invalidate_pages(iocb, iov_iter_count(from)); + if (ret < 0) + goto out; + end = iocb->ki_pos + iov_iter_count(from); + if (end > ictx->zero_point) + ictx->zero_point = end; + + fscache_invalidate(netfs_i_cookie(ictx), NULL, i_size_read(inode), + FSCACHE_INVAL_DIO_WRITE); + ret = netfs_unbuffered_write_iter_locked(iocb, from, NULL); +out: + netfs_end_io_direct(inode); + return ret; +} +EXPORT_SYMBOL(netfs_unbuffered_write_iter); diff --git a/fs/fscache/cache.c b/fs/netfs/fscache_cache.c index d645f8b302a2..d645f8b302a2 100644 --- a/fs/fscache/cache.c +++ b/fs/netfs/fscache_cache.c diff --git a/fs/fscache/cookie.c b/fs/netfs/fscache_cookie.c index bce2492186d0..bce2492186d0 100644 --- a/fs/fscache/cookie.c +++ b/fs/netfs/fscache_cookie.c diff --git a/fs/netfs/fscache_internal.h b/fs/netfs/fscache_internal.h new file mode 100644 index 000000000000..a09b948fcef2 --- /dev/null +++ b/fs/netfs/fscache_internal.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Internal definitions for FS-Cache + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include "internal.h" + +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) "FS-Cache: " fmt diff --git a/fs/fscache/io.c b/fs/netfs/fscache_io.c index 0d2b8dec8f82..ad572f7ee897 100644 --- a/fs/fscache/io.c +++ b/fs/netfs/fscache_io.c @@ -158,46 +158,6 @@ int __fscache_begin_write_operation(struct netfs_cache_resources *cres, } EXPORT_SYMBOL(__fscache_begin_write_operation); -/** - * fscache_dirty_folio - Mark folio dirty and pin a cache object for writeback - * @mapping: The mapping the folio belongs to. - * @folio: The folio being dirtied. - * @cookie: The cookie referring to the cache object - * - * Set the dirty flag on a folio and pin an in-use cache object in memory - * so that writeback can later write to it. This is intended - * to be called from the filesystem's ->dirty_folio() method. - * - * Return: true if the dirty flag was set on the folio, false otherwise. - */ -bool fscache_dirty_folio(struct address_space *mapping, struct folio *folio, - struct fscache_cookie *cookie) -{ - struct inode *inode = mapping->host; - bool need_use = false; - - _enter(""); - - if (!filemap_dirty_folio(mapping, folio)) - return false; - if (!fscache_cookie_valid(cookie)) - return true; - - if (!(inode->i_state & I_PINNING_FSCACHE_WB)) { - spin_lock(&inode->i_lock); - if (!(inode->i_state & I_PINNING_FSCACHE_WB)) { - inode->i_state |= I_PINNING_FSCACHE_WB; - need_use = true; - } - spin_unlock(&inode->i_lock); - - if (need_use) - fscache_use_cookie(cookie, true); - } - return true; -} -EXPORT_SYMBOL(fscache_dirty_folio); - struct fscache_write_request { struct netfs_cache_resources cache_resources; struct address_space *mapping; @@ -277,7 +237,7 @@ void __fscache_write_to_cache(struct fscache_cookie *cookie, fscache_access_io_write) < 0) goto abandon_free; - ret = cres->ops->prepare_write(cres, &start, &len, i_size, false); + ret = cres->ops->prepare_write(cres, &start, &len, len, i_size, false); if (ret < 0) goto abandon_end; diff --git a/fs/fscache/main.c b/fs/netfs/fscache_main.c index dad85fd84f6f..42e98bb523e3 100644 --- a/fs/fscache/main.c +++ b/fs/netfs/fscache_main.c @@ -8,18 +8,9 @@ #define FSCACHE_DEBUG_LEVEL CACHE #include <linux/module.h> #include <linux/init.h> -#define CREATE_TRACE_POINTS #include "internal.h" - -MODULE_DESCRIPTION("FS Cache Manager"); -MODULE_AUTHOR("Red Hat, Inc."); -MODULE_LICENSE("GPL"); - -unsigned fscache_debug; -module_param_named(debug, fscache_debug, uint, - S_IWUSR | S_IRUGO); -MODULE_PARM_DESC(fscache_debug, - "FS-Cache debugging mask"); +#define CREATE_TRACE_POINTS +#include <trace/events/fscache.h> EXPORT_TRACEPOINT_SYMBOL(fscache_access_cache); EXPORT_TRACEPOINT_SYMBOL(fscache_access_volume); @@ -71,7 +62,7 @@ unsigned int fscache_hash(unsigned int salt, const void *data, size_t len) /* * initialise the fs caching module */ -static int __init fscache_init(void) +int __init fscache_init(void) { int ret = -ENOMEM; @@ -92,7 +83,7 @@ static int __init fscache_init(void) goto error_cookie_jar; } - pr_notice("Loaded\n"); + pr_notice("FS-Cache loaded\n"); return 0; error_cookie_jar: @@ -103,19 +94,15 @@ error_wq: return ret; } -fs_initcall(fscache_init); - /* * clean up on module removal */ -static void __exit fscache_exit(void) +void __exit fscache_exit(void) { _enter(""); kmem_cache_destroy(fscache_cookie_jar); fscache_proc_cleanup(); destroy_workqueue(fscache_wq); - pr_notice("Unloaded\n"); + pr_notice("FS-Cache unloaded\n"); } - -module_exit(fscache_exit); diff --git a/fs/fscache/proc.c b/fs/netfs/fscache_proc.c index dc3b0e9c8cce..874d951bc390 100644 --- a/fs/fscache/proc.c +++ b/fs/netfs/fscache_proc.c @@ -12,41 +12,34 @@ #include "internal.h" /* - * initialise the /proc/fs/fscache/ directory + * Add files to /proc/fs/netfs/. */ int __init fscache_proc_init(void) { - if (!proc_mkdir("fs/fscache", NULL)) - goto error_dir; + if (!proc_symlink("fs/fscache", NULL, "netfs")) + goto error_sym; - if (!proc_create_seq("fs/fscache/caches", S_IFREG | 0444, NULL, + if (!proc_create_seq("fs/netfs/caches", S_IFREG | 0444, NULL, &fscache_caches_seq_ops)) goto error; - if (!proc_create_seq("fs/fscache/volumes", S_IFREG | 0444, NULL, + if (!proc_create_seq("fs/netfs/volumes", S_IFREG | 0444, NULL, &fscache_volumes_seq_ops)) goto error; - if (!proc_create_seq("fs/fscache/cookies", S_IFREG | 0444, NULL, + if (!proc_create_seq("fs/netfs/cookies", S_IFREG | 0444, NULL, &fscache_cookies_seq_ops)) goto error; - -#ifdef CONFIG_FSCACHE_STATS - if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL, - fscache_stats_show)) - goto error; -#endif - return 0; error: remove_proc_entry("fs/fscache", NULL); -error_dir: +error_sym: return -ENOMEM; } /* - * clean up the /proc/fs/fscache/ directory + * Clean up the /proc/fs/fscache symlink. */ void fscache_proc_cleanup(void) { diff --git a/fs/fscache/stats.c b/fs/netfs/fscache_stats.c index fc94e5e79f1c..add21abdf713 100644 --- a/fs/fscache/stats.c +++ b/fs/netfs/fscache_stats.c @@ -48,13 +48,15 @@ atomic_t fscache_n_no_create_space; EXPORT_SYMBOL(fscache_n_no_create_space); atomic_t fscache_n_culled; EXPORT_SYMBOL(fscache_n_culled); +atomic_t fscache_n_dio_misfit; +EXPORT_SYMBOL(fscache_n_dio_misfit); /* * display the general statistics */ -int fscache_stats_show(struct seq_file *m, void *v) +int fscache_stats_show(struct seq_file *m) { - seq_puts(m, "FS-Cache statistics\n"); + seq_puts(m, "-- FS-Cache statistics --\n"); seq_printf(m, "Cookies: n=%d v=%d vcol=%u voom=%u\n", atomic_read(&fscache_n_cookies), atomic_read(&fscache_n_volumes), @@ -93,10 +95,9 @@ int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_no_create_space), atomic_read(&fscache_n_culled)); - seq_printf(m, "IO : rd=%u wr=%u\n", + seq_printf(m, "IO : rd=%u wr=%u mis=%u\n", atomic_read(&fscache_n_read), - atomic_read(&fscache_n_write)); - - netfs_stats_show(m); + atomic_read(&fscache_n_write), + atomic_read(&fscache_n_dio_misfit)); return 0; } diff --git a/fs/fscache/volume.c b/fs/netfs/fscache_volume.c index cdf991bdd9de..cdf991bdd9de 100644 --- a/fs/fscache/volume.c +++ b/fs/netfs/fscache_volume.c diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index 43fac1b14e40..ec7045d24400 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -5,9 +5,13 @@ * Written by David Howells (dhowells@redhat.com) */ +#include <linux/slab.h> +#include <linux/seq_file.h> #include <linux/netfs.h> #include <linux/fscache.h> +#include <linux/fscache-cache.h> #include <trace/events/netfs.h> +#include <trace/events/fscache.h> #ifdef pr_fmt #undef pr_fmt @@ -19,6 +23,8 @@ * buffered_read.c */ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq); +int netfs_prefetch_for_write(struct file *file, struct folio *folio, + size_t offset, size_t len); /* * io.c @@ -29,6 +35,41 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync); * main.c */ extern unsigned int netfs_debug; +extern struct list_head netfs_io_requests; +extern spinlock_t netfs_proc_lock; + +#ifdef CONFIG_PROC_FS +static inline void netfs_proc_add_rreq(struct netfs_io_request *rreq) +{ + spin_lock(&netfs_proc_lock); + list_add_tail_rcu(&rreq->proc_link, &netfs_io_requests); + spin_unlock(&netfs_proc_lock); +} +static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq) +{ + if (!list_empty(&rreq->proc_link)) { + spin_lock(&netfs_proc_lock); + list_del_rcu(&rreq->proc_link); + spin_unlock(&netfs_proc_lock); + } +} +#else +static inline void netfs_proc_add_rreq(struct netfs_io_request *rreq) {} +static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq) {} +#endif + +/* + * misc.c + */ +#define NETFS_FLAG_PUT_MARK BIT(0) +#define NETFS_FLAG_PAGECACHE_MARK BIT(1) +int netfs_xa_store_and_mark(struct xarray *xa, unsigned long index, + struct folio *folio, unsigned int flags, + gfp_t gfp_mask); +int netfs_add_folios_to_buffer(struct xarray *buffer, + struct address_space *mapping, + pgoff_t index, pgoff_t to, gfp_t gfp_mask); +void netfs_clear_buffer(struct xarray *buffer); /* * objects.c @@ -50,9 +91,20 @@ static inline void netfs_see_request(struct netfs_io_request *rreq, } /* + * output.c + */ +int netfs_begin_write(struct netfs_io_request *wreq, bool may_wait, + enum netfs_write_trace what); +struct netfs_io_request *netfs_begin_writethrough(struct kiocb *iocb, size_t len); +int netfs_advance_writethrough(struct netfs_io_request *wreq, size_t copied, bool to_page_end); +int netfs_end_writethrough(struct netfs_io_request *wreq, struct kiocb *iocb); + +/* * stats.c */ #ifdef CONFIG_NETFS_STATS +extern atomic_t netfs_n_rh_dio_read; +extern atomic_t netfs_n_rh_dio_write; extern atomic_t netfs_n_rh_readahead; extern atomic_t netfs_n_rh_readpage; extern atomic_t netfs_n_rh_rreq; @@ -71,7 +123,15 @@ extern atomic_t netfs_n_rh_write_begin; extern atomic_t netfs_n_rh_write_done; extern atomic_t netfs_n_rh_write_failed; extern atomic_t netfs_n_rh_write_zskip; +extern atomic_t netfs_n_wh_wstream_conflict; +extern atomic_t netfs_n_wh_upload; +extern atomic_t netfs_n_wh_upload_done; +extern atomic_t netfs_n_wh_upload_failed; +extern atomic_t netfs_n_wh_write; +extern atomic_t netfs_n_wh_write_done; +extern atomic_t netfs_n_wh_write_failed; +int netfs_stats_show(struct seq_file *m, void *v); static inline void netfs_stat(atomic_t *stat) { @@ -103,6 +163,176 @@ static inline bool netfs_is_cache_enabled(struct netfs_inode *ctx) #endif } +/* + * Get a ref on a netfs group attached to a dirty page (e.g. a ceph snap). + */ +static inline struct netfs_group *netfs_get_group(struct netfs_group *netfs_group) +{ + if (netfs_group) + refcount_inc(&netfs_group->ref); + return netfs_group; +} + +/* + * Dispose of a netfs group attached to a dirty page (e.g. a ceph snap). + */ +static inline void netfs_put_group(struct netfs_group *netfs_group) +{ + if (netfs_group && refcount_dec_and_test(&netfs_group->ref)) + netfs_group->free(netfs_group); +} + +/* + * Dispose of a netfs group attached to a dirty page (e.g. a ceph snap). + */ +static inline void netfs_put_group_many(struct netfs_group *netfs_group, int nr) +{ + if (netfs_group && refcount_sub_and_test(nr, &netfs_group->ref)) + netfs_group->free(netfs_group); +} + +/* + * fscache-cache.c + */ +#ifdef CONFIG_PROC_FS +extern const struct seq_operations fscache_caches_seq_ops; +#endif +bool fscache_begin_cache_access(struct fscache_cache *cache, enum fscache_access_trace why); +void fscache_end_cache_access(struct fscache_cache *cache, enum fscache_access_trace why); +struct fscache_cache *fscache_lookup_cache(const char *name, bool is_cache); +void fscache_put_cache(struct fscache_cache *cache, enum fscache_cache_trace where); + +static inline enum fscache_cache_state fscache_cache_state(const struct fscache_cache *cache) +{ + return smp_load_acquire(&cache->state); +} + +static inline bool fscache_cache_is_live(const struct fscache_cache *cache) +{ + return fscache_cache_state(cache) == FSCACHE_CACHE_IS_ACTIVE; +} + +static inline void fscache_set_cache_state(struct fscache_cache *cache, + enum fscache_cache_state new_state) +{ + smp_store_release(&cache->state, new_state); + +} + +static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache, + enum fscache_cache_state old_state, + enum fscache_cache_state new_state) +{ + return try_cmpxchg_release(&cache->state, &old_state, new_state); +} + +/* + * fscache-cookie.c + */ +extern struct kmem_cache *fscache_cookie_jar; +#ifdef CONFIG_PROC_FS +extern const struct seq_operations fscache_cookies_seq_ops; +#endif +extern struct timer_list fscache_cookie_lru_timer; + +extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix); +extern bool fscache_begin_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why); + +static inline void fscache_see_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where) +{ + trace_fscache_cookie(cookie->debug_id, refcount_read(&cookie->ref), + where); +} + +/* + * fscache-main.c + */ +extern unsigned int fscache_hash(unsigned int salt, const void *data, size_t len); +#ifdef CONFIG_FSCACHE +int __init fscache_init(void); +void __exit fscache_exit(void); +#else +static inline int fscache_init(void) { return 0; } +static inline void fscache_exit(void) {} +#endif + +/* + * fscache-proc.c + */ +#ifdef CONFIG_PROC_FS +extern int __init fscache_proc_init(void); +extern void fscache_proc_cleanup(void); +#else +#define fscache_proc_init() (0) +#define fscache_proc_cleanup() do {} while (0) +#endif + +/* + * fscache-stats.c + */ +#ifdef CONFIG_FSCACHE_STATS +extern atomic_t fscache_n_volumes; +extern atomic_t fscache_n_volumes_collision; +extern atomic_t fscache_n_volumes_nomem; +extern atomic_t fscache_n_cookies; +extern atomic_t fscache_n_cookies_lru; +extern atomic_t fscache_n_cookies_lru_expired; +extern atomic_t fscache_n_cookies_lru_removed; +extern atomic_t fscache_n_cookies_lru_dropped; + +extern atomic_t fscache_n_acquires; +extern atomic_t fscache_n_acquires_ok; +extern atomic_t fscache_n_acquires_oom; + +extern atomic_t fscache_n_invalidates; + +extern atomic_t fscache_n_relinquishes; +extern atomic_t fscache_n_relinquishes_retire; +extern atomic_t fscache_n_relinquishes_dropped; + +extern atomic_t fscache_n_resizes; +extern atomic_t fscache_n_resizes_null; + +static inline void fscache_stat(atomic_t *stat) +{ + atomic_inc(stat); +} + +static inline void fscache_stat_d(atomic_t *stat) +{ + atomic_dec(stat); +} + +#define __fscache_stat(stat) (stat) + +int fscache_stats_show(struct seq_file *m); +#else + +#define __fscache_stat(stat) (NULL) +#define fscache_stat(stat) do {} while (0) +#define fscache_stat_d(stat) do {} while (0) + +static inline int fscache_stats_show(struct seq_file *m) { return 0; } +#endif + +/* + * fscache-volume.c + */ +#ifdef CONFIG_PROC_FS +extern const struct seq_operations fscache_volumes_seq_ops; +#endif + +struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, + enum fscache_volume_trace where); +void fscache_put_volume(struct fscache_volume *volume, + enum fscache_volume_trace where); +bool fscache_begin_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why); +void fscache_create_volume(struct fscache_volume *volume, bool wait); + /*****************************************************************************/ /* * debug tracing @@ -143,3 +373,57 @@ do { \ #define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__) #define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__) #endif + +/* + * assertions + */ +#if 1 /* defined(__KDEBUGALL) */ + +#define ASSERT(X) \ +do { \ + if (unlikely(!(X))) { \ + pr_err("\n"); \ + pr_err("Assertion failed\n"); \ + BUG(); \ + } \ +} while (0) + +#define ASSERTCMP(X, OP, Y) \ +do { \ + if (unlikely(!((X) OP (Y)))) { \ + pr_err("\n"); \ + pr_err("Assertion failed\n"); \ + pr_err("%lx " #OP " %lx is false\n", \ + (unsigned long)(X), (unsigned long)(Y)); \ + BUG(); \ + } \ +} while (0) + +#define ASSERTIF(C, X) \ +do { \ + if (unlikely((C) && !(X))) { \ + pr_err("\n"); \ + pr_err("Assertion failed\n"); \ + BUG(); \ + } \ +} while (0) + +#define ASSERTIFCMP(C, X, OP, Y) \ +do { \ + if (unlikely((C) && !((X) OP (Y)))) { \ + pr_err("\n"); \ + pr_err("Assertion failed\n"); \ + pr_err("%lx " #OP " %lx is false\n", \ + (unsigned long)(X), (unsigned long)(Y)); \ + BUG(); \ + } \ +} while (0) + +#else + +#define ASSERT(X) do {} while (0) +#define ASSERTCMP(X, OP, Y) do {} while (0) +#define ASSERTIF(C, X) do {} while (0) +#define ASSERTIFCMP(C, X, OP, Y) do {} while (0) + +#endif /* assert or not */ diff --git a/fs/netfs/io.c b/fs/netfs/io.c index 7f753380e047..4309edf33862 100644 --- a/fs/netfs/io.c +++ b/fs/netfs/io.c @@ -21,12 +21,7 @@ */ static void netfs_clear_unread(struct netfs_io_subrequest *subreq) { - struct iov_iter iter; - - iov_iter_xarray(&iter, ITER_DEST, &subreq->rreq->mapping->i_pages, - subreq->start + subreq->transferred, - subreq->len - subreq->transferred); - iov_iter_zero(iov_iter_count(&iter), &iter); + iov_iter_zero(iov_iter_count(&subreq->io_iter), &subreq->io_iter); } static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, @@ -46,14 +41,9 @@ static void netfs_read_from_cache(struct netfs_io_request *rreq, enum netfs_read_from_hole read_hole) { struct netfs_cache_resources *cres = &rreq->cache_resources; - struct iov_iter iter; netfs_stat(&netfs_n_rh_read); - iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages, - subreq->start + subreq->transferred, - subreq->len - subreq->transferred); - - cres->ops->read(cres, subreq->start, &iter, read_hole, + cres->ops->read(cres, subreq->start, &subreq->io_iter, read_hole, netfs_cache_read_terminated, subreq); } @@ -88,6 +78,13 @@ static void netfs_read_from_server(struct netfs_io_request *rreq, struct netfs_io_subrequest *subreq) { netfs_stat(&netfs_n_rh_download); + + if (rreq->origin != NETFS_DIO_READ && + iov_iter_count(&subreq->io_iter) != subreq->len - subreq->transferred) + pr_warn("R=%08x[%u] ITER PRE-MISMATCH %zx != %zx-%zx %lx\n", + rreq->debug_id, subreq->debug_index, + iov_iter_count(&subreq->io_iter), subreq->len, + subreq->transferred, subreq->flags); rreq->netfs_ops->issue_read(subreq); } @@ -129,7 +126,8 @@ static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq, */ if (have_unlocked && folio_index(folio) <= unlocked) continue; - unlocked = folio_index(folio); + unlocked = folio_next_index(folio) - 1; + trace_netfs_folio(folio, netfs_folio_trace_end_copy); folio_end_fscache(folio); have_unlocked = true; } @@ -201,7 +199,7 @@ static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq) } ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len, - rreq->i_size, true); + subreq->len, rreq->i_size, true); if (ret < 0) { trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write); trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip); @@ -260,6 +258,30 @@ static void netfs_rreq_short_read(struct netfs_io_request *rreq, } /* + * Reset the subrequest iterator prior to resubmission. + */ +static void netfs_reset_subreq_iter(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + size_t remaining = subreq->len - subreq->transferred; + size_t count = iov_iter_count(&subreq->io_iter); + + if (count == remaining) + return; + + _debug("R=%08x[%u] ITER RESUB-MISMATCH %zx != %zx-%zx-%llx %x\n", + rreq->debug_id, subreq->debug_index, + iov_iter_count(&subreq->io_iter), subreq->transferred, + subreq->len, rreq->i_size, + subreq->io_iter.iter_type); + + if (count < remaining) + iov_iter_revert(&subreq->io_iter, remaining - count); + else + iov_iter_advance(&subreq->io_iter, count - remaining); +} + +/* * Resubmit any short or failed operations. Returns true if we got the rreq * ref back. */ @@ -287,6 +309,7 @@ static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq) trace_netfs_sreq(subreq, netfs_sreq_trace_download_instead); netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); atomic_inc(&rreq->nr_outstanding); + netfs_reset_subreq_iter(rreq, subreq); netfs_read_from_server(rreq, subreq); } else if (test_bit(NETFS_SREQ_SHORT_IO, &subreq->flags)) { netfs_rreq_short_read(rreq, subreq); @@ -321,6 +344,43 @@ static void netfs_rreq_is_still_valid(struct netfs_io_request *rreq) } /* + * Determine how much we can admit to having read from a DIO read. + */ +static void netfs_rreq_assess_dio(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + unsigned int i; + size_t transferred = 0; + + for (i = 0; i < rreq->direct_bv_count; i++) + flush_dcache_page(rreq->direct_bv[i].bv_page); + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + if (subreq->error || subreq->transferred == 0) + break; + transferred += subreq->transferred; + if (subreq->transferred < subreq->len) + break; + } + + for (i = 0; i < rreq->direct_bv_count; i++) + flush_dcache_page(rreq->direct_bv[i].bv_page); + + rreq->transferred = transferred; + task_io_account_read(transferred); + + if (rreq->iocb) { + rreq->iocb->ki_pos += transferred; + if (rreq->iocb->ki_complete) + rreq->iocb->ki_complete( + rreq->iocb, rreq->error ? rreq->error : transferred); + } + if (rreq->netfs_ops->done) + rreq->netfs_ops->done(rreq); + inode_dio_end(rreq->inode); +} + +/* * Assess the state of a read request and decide what to do next. * * Note that we could be in an ordinary kernel thread, on a workqueue or in @@ -340,8 +400,12 @@ again: return; } - netfs_rreq_unlock_folios(rreq); + if (rreq->origin != NETFS_DIO_READ) + netfs_rreq_unlock_folios(rreq); + else + netfs_rreq_assess_dio(rreq); + trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip); clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); @@ -399,9 +463,9 @@ void netfs_subreq_terminated(struct netfs_io_subrequest *subreq, struct netfs_io_request *rreq = subreq->rreq; int u; - _enter("[%u]{%llx,%lx},%zd", - subreq->debug_index, subreq->start, subreq->flags, - transferred_or_error); + _enter("R=%x[%x]{%llx,%lx},%zd", + rreq->debug_id, subreq->debug_index, + subreq->start, subreq->flags, transferred_or_error); switch (subreq->source) { case NETFS_READ_FROM_CACHE: @@ -501,15 +565,20 @@ static enum netfs_io_source netfs_cache_prepare_read(struct netfs_io_subrequest */ static enum netfs_io_source netfs_rreq_prepare_read(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq) + struct netfs_io_subrequest *subreq, + struct iov_iter *io_iter) { - enum netfs_io_source source; + enum netfs_io_source source = NETFS_DOWNLOAD_FROM_SERVER; + struct netfs_inode *ictx = netfs_inode(rreq->inode); + size_t lsize; _enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size); - source = netfs_cache_prepare_read(subreq, rreq->i_size); - if (source == NETFS_INVALID_READ) - goto out; + if (rreq->origin != NETFS_DIO_READ) { + source = netfs_cache_prepare_read(subreq, rreq->i_size); + if (source == NETFS_INVALID_READ) + goto out; + } if (source == NETFS_DOWNLOAD_FROM_SERVER) { /* Call out to the netfs to let it shrink the request to fit @@ -518,19 +587,52 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq, * to make serial calls, it can indicate a short read and then * we will call it again. */ + if (rreq->origin != NETFS_DIO_READ) { + if (subreq->start >= ictx->zero_point) { + source = NETFS_FILL_WITH_ZEROES; + goto set; + } + if (subreq->len > ictx->zero_point - subreq->start) + subreq->len = ictx->zero_point - subreq->start; + } if (subreq->len > rreq->i_size - subreq->start) subreq->len = rreq->i_size - subreq->start; + if (rreq->rsize && subreq->len > rreq->rsize) + subreq->len = rreq->rsize; if (rreq->netfs_ops->clamp_length && !rreq->netfs_ops->clamp_length(subreq)) { source = NETFS_INVALID_READ; goto out; } + + if (subreq->max_nr_segs) { + lsize = netfs_limit_iter(io_iter, 0, subreq->len, + subreq->max_nr_segs); + if (subreq->len > lsize) { + subreq->len = lsize; + trace_netfs_sreq(subreq, netfs_sreq_trace_limited); + } + } } - if (WARN_ON(subreq->len == 0)) +set: + if (subreq->len > rreq->len) + pr_warn("R=%08x[%u] SREQ>RREQ %zx > %zx\n", + rreq->debug_id, subreq->debug_index, + subreq->len, rreq->len); + + if (WARN_ON(subreq->len == 0)) { source = NETFS_INVALID_READ; + goto out; + } + subreq->source = source; + trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); + + subreq->io_iter = *io_iter; + iov_iter_truncate(&subreq->io_iter, subreq->len); + iov_iter_advance(io_iter, subreq->len); out: subreq->source = source; trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); @@ -541,6 +643,7 @@ out: * Slice off a piece of a read request and submit an I/O request for it. */ static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq, + struct iov_iter *io_iter, unsigned int *_debug_index) { struct netfs_io_subrequest *subreq; @@ -552,7 +655,7 @@ static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq, subreq->debug_index = (*_debug_index)++; subreq->start = rreq->start + rreq->submitted; - subreq->len = rreq->len - rreq->submitted; + subreq->len = io_iter->count; _debug("slice %llx,%zx,%zx", subreq->start, subreq->len, rreq->submitted); list_add_tail(&subreq->rreq_link, &rreq->subrequests); @@ -565,7 +668,7 @@ static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq, * (the starts must coincide), in which case, we go around the loop * again and ask it to download the next piece. */ - source = netfs_rreq_prepare_read(rreq, subreq); + source = netfs_rreq_prepare_read(rreq, subreq, io_iter); if (source == NETFS_INVALID_READ) goto subreq_failed; @@ -603,6 +706,7 @@ subreq_failed: */ int netfs_begin_read(struct netfs_io_request *rreq, bool sync) { + struct iov_iter io_iter; unsigned int debug_index = 0; int ret; @@ -611,50 +715,71 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync) if (rreq->len == 0) { pr_err("Zero-sized read [R=%x]\n", rreq->debug_id); - netfs_put_request(rreq, false, netfs_rreq_trace_put_zero_len); return -EIO; } - INIT_WORK(&rreq->work, netfs_rreq_work); + if (rreq->origin == NETFS_DIO_READ) + inode_dio_begin(rreq->inode); - if (sync) - netfs_get_request(rreq, netfs_rreq_trace_get_hold); + // TODO: Use bounce buffer if requested + rreq->io_iter = rreq->iter; + + INIT_WORK(&rreq->work, netfs_rreq_work); /* Chop the read into slices according to what the cache and the netfs * want and submit each one. */ + netfs_get_request(rreq, netfs_rreq_trace_get_for_outstanding); atomic_set(&rreq->nr_outstanding, 1); + io_iter = rreq->io_iter; do { - if (!netfs_rreq_submit_slice(rreq, &debug_index)) + _debug("submit %llx + %zx >= %llx", + rreq->start, rreq->submitted, rreq->i_size); + if (rreq->origin == NETFS_DIO_READ && + rreq->start + rreq->submitted >= rreq->i_size) + break; + if (!netfs_rreq_submit_slice(rreq, &io_iter, &debug_index)) + break; + if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) && + test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags)) break; } while (rreq->submitted < rreq->len); + if (!rreq->submitted) { + netfs_put_request(rreq, false, netfs_rreq_trace_put_no_submit); + ret = 0; + goto out; + } + if (sync) { - /* Keep nr_outstanding incremented so that the ref always belongs to - * us, and the service code isn't punted off to a random thread pool to - * process. + /* Keep nr_outstanding incremented so that the ref always + * belongs to us, and the service code isn't punted off to a + * random thread pool to process. Note that this might start + * further work, such as writing to the cache. */ - for (;;) { - wait_var_event(&rreq->nr_outstanding, - atomic_read(&rreq->nr_outstanding) == 1); + wait_var_event(&rreq->nr_outstanding, + atomic_read(&rreq->nr_outstanding) == 1); + if (atomic_dec_and_test(&rreq->nr_outstanding)) netfs_rreq_assess(rreq, false); - if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) - break; - cond_resched(); - } + + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip); + wait_on_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS, + TASK_UNINTERRUPTIBLE); ret = rreq->error; - if (ret == 0 && rreq->submitted < rreq->len) { + if (ret == 0 && rreq->submitted < rreq->len && + rreq->origin != NETFS_DIO_READ) { trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); ret = -EIO; } - netfs_put_request(rreq, false, netfs_rreq_trace_put_hold); } else { /* If we decrement nr_outstanding to 0, the ref belongs to us. */ if (atomic_dec_and_test(&rreq->nr_outstanding)) netfs_rreq_assess(rreq, false); - ret = 0; + ret = -EIOCBQUEUED; } + +out: return ret; } diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c index 2ff07ba655a0..b781bbbf1d8d 100644 --- a/fs/netfs/iterator.c +++ b/fs/netfs/iterator.c @@ -101,3 +101,100 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, return npages; } EXPORT_SYMBOL_GPL(netfs_extract_user_iter); + +/* + * Select the span of a bvec iterator we're going to use. Limit it by both maximum + * size and maximum number of segments. Returns the size of the span in bytes. + */ +static size_t netfs_limit_bvec(const struct iov_iter *iter, size_t start_offset, + size_t max_size, size_t max_segs) +{ + const struct bio_vec *bvecs = iter->bvec; + unsigned int nbv = iter->nr_segs, ix = 0, nsegs = 0; + size_t len, span = 0, n = iter->count; + size_t skip = iter->iov_offset + start_offset; + + if (WARN_ON(!iov_iter_is_bvec(iter)) || + WARN_ON(start_offset > n) || + n == 0) + return 0; + + while (n && ix < nbv && skip) { + len = bvecs[ix].bv_len; + if (skip < len) + break; + skip -= len; + n -= len; + ix++; + } + + while (n && ix < nbv) { + len = min3(n, bvecs[ix].bv_len - skip, max_size); + span += len; + nsegs++; + ix++; + if (span >= max_size || nsegs >= max_segs) + break; + skip = 0; + n -= len; + } + + return min(span, max_size); +} + +/* + * Select the span of an xarray iterator we're going to use. Limit it by both + * maximum size and maximum number of segments. It is assumed that segments + * can be larger than a page in size, provided they're physically contiguous. + * Returns the size of the span in bytes. + */ +static size_t netfs_limit_xarray(const struct iov_iter *iter, size_t start_offset, + size_t max_size, size_t max_segs) +{ + struct folio *folio; + unsigned int nsegs = 0; + loff_t pos = iter->xarray_start + iter->iov_offset; + pgoff_t index = pos / PAGE_SIZE; + size_t span = 0, n = iter->count; + + XA_STATE(xas, iter->xarray, index); + + if (WARN_ON(!iov_iter_is_xarray(iter)) || + WARN_ON(start_offset > n) || + n == 0) + return 0; + max_size = min(max_size, n - start_offset); + + rcu_read_lock(); + xas_for_each(&xas, folio, ULONG_MAX) { + size_t offset, flen, len; + if (xas_retry(&xas, folio)) + continue; + if (WARN_ON(xa_is_value(folio))) + break; + if (WARN_ON(folio_test_hugetlb(folio))) + break; + + flen = folio_size(folio); + offset = offset_in_folio(folio, pos); + len = min(max_size, flen - offset); + span += len; + nsegs++; + if (span >= max_size || nsegs >= max_segs) + break; + } + + rcu_read_unlock(); + return min(span, max_size); +} + +size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset, + size_t max_size, size_t max_segs) +{ + if (iov_iter_is_bvec(iter)) + return netfs_limit_bvec(iter, start_offset, max_size, max_segs); + if (iov_iter_is_xarray(iter)) + return netfs_limit_xarray(iter, start_offset, max_size, max_segs); + BUG(); +} +EXPORT_SYMBOL(netfs_limit_iter); diff --git a/fs/netfs/locking.c b/fs/netfs/locking.c new file mode 100644 index 000000000000..75dc52a49b3a --- /dev/null +++ b/fs/netfs/locking.c @@ -0,0 +1,216 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * I/O and data path helper functionality. + * + * Borrowed from NFS Copyright (c) 2016 Trond Myklebust + */ + +#include <linux/kernel.h> +#include <linux/netfs.h> +#include "internal.h" + +/* + * inode_dio_wait_interruptible - wait for outstanding DIO requests to finish + * @inode: inode to wait for + * + * Waits for all pending direct I/O requests to finish so that we can + * proceed with a truncate or equivalent operation. + * + * Must be called under a lock that serializes taking new references + * to i_dio_count, usually by inode->i_mutex. + */ +static int inode_dio_wait_interruptible(struct inode *inode) +{ + if (!atomic_read(&inode->i_dio_count)) + return 0; + + wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP); + DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP); + + for (;;) { + prepare_to_wait(wq, &q.wq_entry, TASK_INTERRUPTIBLE); + if (!atomic_read(&inode->i_dio_count)) + break; + if (signal_pending(current)) + break; + schedule(); + } + finish_wait(wq, &q.wq_entry); + + return atomic_read(&inode->i_dio_count) ? -ERESTARTSYS : 0; +} + +/* Call with exclusively locked inode->i_rwsem */ +static int netfs_block_o_direct(struct netfs_inode *ictx) +{ + if (!test_bit(NETFS_ICTX_ODIRECT, &ictx->flags)) + return 0; + clear_bit(NETFS_ICTX_ODIRECT, &ictx->flags); + return inode_dio_wait_interruptible(&ictx->inode); +} + +/** + * netfs_start_io_read - declare the file is being used for buffered reads + * @inode: file inode + * + * Declare that a buffered read operation is about to start, and ensure + * that we block all direct I/O. + * On exit, the function ensures that the NETFS_ICTX_ODIRECT flag is unset, + * and holds a shared lock on inode->i_rwsem to ensure that the flag + * cannot be changed. + * In practice, this means that buffered read operations are allowed to + * execute in parallel, thanks to the shared lock, whereas direct I/O + * operations need to wait to grab an exclusive lock in order to set + * NETFS_ICTX_ODIRECT. + * Note that buffered writes and truncates both take a write lock on + * inode->i_rwsem, meaning that those are serialised w.r.t. the reads. + */ +int netfs_start_io_read(struct inode *inode) + __acquires(inode->i_rwsem) +{ + struct netfs_inode *ictx = netfs_inode(inode); + + /* Be an optimist! */ + if (down_read_interruptible(&inode->i_rwsem) < 0) + return -ERESTARTSYS; + if (test_bit(NETFS_ICTX_ODIRECT, &ictx->flags) == 0) + return 0; + up_read(&inode->i_rwsem); + + /* Slow path.... */ + if (down_write_killable(&inode->i_rwsem) < 0) + return -ERESTARTSYS; + if (netfs_block_o_direct(ictx) < 0) { + up_write(&inode->i_rwsem); + return -ERESTARTSYS; + } + downgrade_write(&inode->i_rwsem); + return 0; +} +EXPORT_SYMBOL(netfs_start_io_read); + +/** + * netfs_end_io_read - declare that the buffered read operation is done + * @inode: file inode + * + * Declare that a buffered read operation is done, and release the shared + * lock on inode->i_rwsem. + */ +void netfs_end_io_read(struct inode *inode) + __releases(inode->i_rwsem) +{ + up_read(&inode->i_rwsem); +} +EXPORT_SYMBOL(netfs_end_io_read); + +/** + * netfs_start_io_write - declare the file is being used for buffered writes + * @inode: file inode + * + * Declare that a buffered read operation is about to start, and ensure + * that we block all direct I/O. + */ +int netfs_start_io_write(struct inode *inode) + __acquires(inode->i_rwsem) +{ + struct netfs_inode *ictx = netfs_inode(inode); + + if (down_write_killable(&inode->i_rwsem) < 0) + return -ERESTARTSYS; + if (netfs_block_o_direct(ictx) < 0) { + up_write(&inode->i_rwsem); + return -ERESTARTSYS; + } + return 0; +} +EXPORT_SYMBOL(netfs_start_io_write); + +/** + * netfs_end_io_write - declare that the buffered write operation is done + * @inode: file inode + * + * Declare that a buffered write operation is done, and release the + * lock on inode->i_rwsem. + */ +void netfs_end_io_write(struct inode *inode) + __releases(inode->i_rwsem) +{ + up_write(&inode->i_rwsem); +} +EXPORT_SYMBOL(netfs_end_io_write); + +/* Call with exclusively locked inode->i_rwsem */ +static int netfs_block_buffered(struct inode *inode) +{ + struct netfs_inode *ictx = netfs_inode(inode); + int ret; + + if (!test_bit(NETFS_ICTX_ODIRECT, &ictx->flags)) { + set_bit(NETFS_ICTX_ODIRECT, &ictx->flags); + if (inode->i_mapping->nrpages != 0) { + unmap_mapping_range(inode->i_mapping, 0, 0, 0); + ret = filemap_fdatawait(inode->i_mapping); + if (ret < 0) { + clear_bit(NETFS_ICTX_ODIRECT, &ictx->flags); + return ret; + } + } + } + return 0; +} + +/** + * netfs_start_io_direct - declare the file is being used for direct i/o + * @inode: file inode + * + * Declare that a direct I/O operation is about to start, and ensure + * that we block all buffered I/O. + * On exit, the function ensures that the NETFS_ICTX_ODIRECT flag is set, + * and holds a shared lock on inode->i_rwsem to ensure that the flag + * cannot be changed. + * In practice, this means that direct I/O operations are allowed to + * execute in parallel, thanks to the shared lock, whereas buffered I/O + * operations need to wait to grab an exclusive lock in order to clear + * NETFS_ICTX_ODIRECT. + * Note that buffered writes and truncates both take a write lock on + * inode->i_rwsem, meaning that those are serialised w.r.t. O_DIRECT. + */ +int netfs_start_io_direct(struct inode *inode) + __acquires(inode->i_rwsem) +{ + struct netfs_inode *ictx = netfs_inode(inode); + int ret; + + /* Be an optimist! */ + if (down_read_interruptible(&inode->i_rwsem) < 0) + return -ERESTARTSYS; + if (test_bit(NETFS_ICTX_ODIRECT, &ictx->flags) != 0) + return 0; + up_read(&inode->i_rwsem); + + /* Slow path.... */ + if (down_write_killable(&inode->i_rwsem) < 0) + return -ERESTARTSYS; + ret = netfs_block_buffered(inode); + if (ret < 0) { + up_write(&inode->i_rwsem); + return ret; + } + downgrade_write(&inode->i_rwsem); + return 0; +} +EXPORT_SYMBOL(netfs_start_io_direct); + +/** + * netfs_end_io_direct - declare that the direct i/o operation is done + * @inode: file inode + * + * Declare that a direct I/O operation is done, and release the shared + * lock on inode->i_rwsem. + */ +void netfs_end_io_direct(struct inode *inode) + __releases(inode->i_rwsem) +{ + up_read(&inode->i_rwsem); +} +EXPORT_SYMBOL(netfs_end_io_direct); diff --git a/fs/netfs/main.c b/fs/netfs/main.c index 068568702957..5e77618a7940 100644 --- a/fs/netfs/main.c +++ b/fs/netfs/main.c @@ -7,6 +7,8 @@ #include <linux/module.h> #include <linux/export.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/netfs.h> @@ -15,6 +17,113 @@ MODULE_DESCRIPTION("Network fs support"); MODULE_AUTHOR("Red Hat, Inc."); MODULE_LICENSE("GPL"); +EXPORT_TRACEPOINT_SYMBOL(netfs_sreq); + unsigned netfs_debug; module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO); MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask"); + +#ifdef CONFIG_PROC_FS +LIST_HEAD(netfs_io_requests); +DEFINE_SPINLOCK(netfs_proc_lock); + +static const char *netfs_origins[nr__netfs_io_origin] = { + [NETFS_READAHEAD] = "RA", + [NETFS_READPAGE] = "RP", + [NETFS_READ_FOR_WRITE] = "RW", + [NETFS_WRITEBACK] = "WB", + [NETFS_WRITETHROUGH] = "WT", + [NETFS_LAUNDER_WRITE] = "LW", + [NETFS_UNBUFFERED_WRITE] = "UW", + [NETFS_DIO_READ] = "DR", + [NETFS_DIO_WRITE] = "DW", +}; + +/* + * Generate a list of I/O requests in /proc/fs/netfs/requests + */ +static int netfs_requests_seq_show(struct seq_file *m, void *v) +{ + struct netfs_io_request *rreq; + + if (v == &netfs_io_requests) { + seq_puts(m, + "REQUEST OR REF FL ERR OPS COVERAGE\n" + "======== == === == ==== === =========\n" + ); + return 0; + } + + rreq = list_entry(v, struct netfs_io_request, proc_link); + seq_printf(m, + "%08x %s %3d %2lx %4d %3d @%04llx %zx/%zx", + rreq->debug_id, + netfs_origins[rreq->origin], + refcount_read(&rreq->ref), + rreq->flags, + rreq->error, + atomic_read(&rreq->nr_outstanding), + rreq->start, rreq->submitted, rreq->len); + seq_putc(m, '\n'); + return 0; +} + +static void *netfs_requests_seq_start(struct seq_file *m, loff_t *_pos) + __acquires(rcu) +{ + rcu_read_lock(); + return seq_list_start_head(&netfs_io_requests, *_pos); +} + +static void *netfs_requests_seq_next(struct seq_file *m, void *v, loff_t *_pos) +{ + return seq_list_next(v, &netfs_io_requests, _pos); +} + +static void netfs_requests_seq_stop(struct seq_file *m, void *v) + __releases(rcu) +{ + rcu_read_unlock(); +} + +static const struct seq_operations netfs_requests_seq_ops = { + .start = netfs_requests_seq_start, + .next = netfs_requests_seq_next, + .stop = netfs_requests_seq_stop, + .show = netfs_requests_seq_show, +}; +#endif /* CONFIG_PROC_FS */ + +static int __init netfs_init(void) +{ + int ret = -ENOMEM; + + if (!proc_mkdir("fs/netfs", NULL)) + goto error; + if (!proc_create_seq("fs/netfs/requests", S_IFREG | 0444, NULL, + &netfs_requests_seq_ops)) + goto error_proc; +#ifdef CONFIG_FSCACHE_STATS + if (!proc_create_single("fs/netfs/stats", S_IFREG | 0444, NULL, + netfs_stats_show)) + goto error_proc; +#endif + + ret = fscache_init(); + if (ret < 0) + goto error_proc; + return 0; + +error_proc: + remove_proc_entry("fs/netfs", NULL); +error: + return ret; +} +fs_initcall(netfs_init); + +static void __exit netfs_exit(void) +{ + fscache_exit(); + remove_proc_entry("fs/netfs", NULL); +} +module_exit(netfs_exit); diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c new file mode 100644 index 000000000000..0e3af37fc924 --- /dev/null +++ b/fs/netfs/misc.c @@ -0,0 +1,260 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Miscellaneous routines. + * + * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/swap.h> +#include "internal.h" + +/* + * Attach a folio to the buffer and maybe set marks on it to say that we need + * to put the folio later and twiddle the pagecache flags. + */ +int netfs_xa_store_and_mark(struct xarray *xa, unsigned long index, + struct folio *folio, unsigned int flags, + gfp_t gfp_mask) +{ + XA_STATE_ORDER(xas, xa, index, folio_order(folio)); + +retry: + xas_lock(&xas); + for (;;) { + xas_store(&xas, folio); + if (!xas_error(&xas)) + break; + xas_unlock(&xas); + if (!xas_nomem(&xas, gfp_mask)) + return xas_error(&xas); + goto retry; + } + + if (flags & NETFS_FLAG_PUT_MARK) + xas_set_mark(&xas, NETFS_BUF_PUT_MARK); + if (flags & NETFS_FLAG_PAGECACHE_MARK) + xas_set_mark(&xas, NETFS_BUF_PAGECACHE_MARK); + xas_unlock(&xas); + return xas_error(&xas); +} + +/* + * Create the specified range of folios in the buffer attached to the read + * request. The folios are marked with NETFS_BUF_PUT_MARK so that we know that + * these need freeing later. + */ +int netfs_add_folios_to_buffer(struct xarray *buffer, + struct address_space *mapping, + pgoff_t index, pgoff_t to, gfp_t gfp_mask) +{ + struct folio *folio; + int ret; + + if (to + 1 == index) /* Page range is inclusive */ + return 0; + + do { + /* TODO: Figure out what order folio can be allocated here */ + folio = filemap_alloc_folio(readahead_gfp_mask(mapping), 0); + if (!folio) + return -ENOMEM; + folio->index = index; + ret = netfs_xa_store_and_mark(buffer, index, folio, + NETFS_FLAG_PUT_MARK, gfp_mask); + if (ret < 0) { + folio_put(folio); + return ret; + } + + index += folio_nr_pages(folio); + } while (index <= to && index != 0); + + return 0; +} + +/* + * Clear an xarray buffer, putting a ref on the folios that have + * NETFS_BUF_PUT_MARK set. + */ +void netfs_clear_buffer(struct xarray *buffer) +{ + struct folio *folio; + XA_STATE(xas, buffer, 0); + + rcu_read_lock(); + xas_for_each_marked(&xas, folio, ULONG_MAX, NETFS_BUF_PUT_MARK) { + folio_put(folio); + } + rcu_read_unlock(); + xa_destroy(buffer); +} + +/** + * netfs_dirty_folio - Mark folio dirty and pin a cache object for writeback + * @mapping: The mapping the folio belongs to. + * @folio: The folio being dirtied. + * + * Set the dirty flag on a folio and pin an in-use cache object in memory so + * that writeback can later write to it. This is intended to be called from + * the filesystem's ->dirty_folio() method. + * + * Return: true if the dirty flag was set on the folio, false otherwise. + */ +bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio) +{ + struct inode *inode = mapping->host; + struct netfs_inode *ictx = netfs_inode(inode); + struct fscache_cookie *cookie = netfs_i_cookie(ictx); + bool need_use = false; + + _enter(""); + + if (!filemap_dirty_folio(mapping, folio)) + return false; + if (!fscache_cookie_valid(cookie)) + return true; + + if (!(inode->i_state & I_PINNING_NETFS_WB)) { + spin_lock(&inode->i_lock); + if (!(inode->i_state & I_PINNING_NETFS_WB)) { + inode->i_state |= I_PINNING_NETFS_WB; + need_use = true; + } + spin_unlock(&inode->i_lock); + + if (need_use) + fscache_use_cookie(cookie, true); + } + return true; +} +EXPORT_SYMBOL(netfs_dirty_folio); + +/** + * netfs_unpin_writeback - Unpin writeback resources + * @inode: The inode on which the cookie resides + * @wbc: The writeback control + * + * Unpin the writeback resources pinned by netfs_dirty_folio(). This is + * intended to be called as/by the netfs's ->write_inode() method. + */ +int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc) +{ + struct fscache_cookie *cookie = netfs_i_cookie(netfs_inode(inode)); + + if (wbc->unpinned_netfs_wb) + fscache_unuse_cookie(cookie, NULL, NULL); + return 0; +} +EXPORT_SYMBOL(netfs_unpin_writeback); + +/** + * netfs_clear_inode_writeback - Clear writeback resources pinned by an inode + * @inode: The inode to clean up + * @aux: Auxiliary data to apply to the inode + * + * Clear any writeback resources held by an inode when the inode is evicted. + * This must be called before clear_inode() is called. + */ +void netfs_clear_inode_writeback(struct inode *inode, const void *aux) +{ + struct fscache_cookie *cookie = netfs_i_cookie(netfs_inode(inode)); + + if (inode->i_state & I_PINNING_NETFS_WB) { + loff_t i_size = i_size_read(inode); + fscache_unuse_cookie(cookie, aux, &i_size); + } +} +EXPORT_SYMBOL(netfs_clear_inode_writeback); + +/** + * netfs_invalidate_folio - Invalidate or partially invalidate a folio + * @folio: Folio proposed for release + * @offset: Offset of the invalidated region + * @length: Length of the invalidated region + * + * Invalidate part or all of a folio for a network filesystem. The folio will + * be removed afterwards if the invalidated region covers the entire folio. + */ +void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length) +{ + struct netfs_folio *finfo = NULL; + size_t flen = folio_size(folio); + + _enter("{%lx},%zx,%zx", folio_index(folio), offset, length); + + folio_wait_fscache(folio); + + if (!folio_test_private(folio)) + return; + + finfo = netfs_folio_info(folio); + + if (offset == 0 && length >= flen) + goto erase_completely; + + if (finfo) { + /* We have a partially uptodate page from a streaming write. */ + unsigned int fstart = finfo->dirty_offset; + unsigned int fend = fstart + finfo->dirty_len; + unsigned int end = offset + length; + + if (offset >= fend) + return; + if (end <= fstart) + return; + if (offset <= fstart && end >= fend) + goto erase_completely; + if (offset <= fstart && end > fstart) + goto reduce_len; + if (offset > fstart && end >= fend) + goto move_start; + /* A partial write was split. The caller has already zeroed + * it, so just absorb the hole. + */ + } + return; + +erase_completely: + netfs_put_group(netfs_folio_group(folio)); + folio_detach_private(folio); + folio_clear_uptodate(folio); + kfree(finfo); + return; +reduce_len: + finfo->dirty_len = offset + length - finfo->dirty_offset; + return; +move_start: + finfo->dirty_len -= offset - finfo->dirty_offset; + finfo->dirty_offset = offset; +} +EXPORT_SYMBOL(netfs_invalidate_folio); + +/** + * netfs_release_folio - Try to release a folio + * @folio: Folio proposed for release + * @gfp: Flags qualifying the release + * + * Request release of a folio and clean up its private state if it's not busy. + * Returns true if the folio can now be released, false if not + */ +bool netfs_release_folio(struct folio *folio, gfp_t gfp) +{ + struct netfs_inode *ctx = netfs_inode(folio_inode(folio)); + unsigned long long end; + + end = folio_pos(folio) + folio_size(folio); + if (end > ctx->zero_point) + ctx->zero_point = end; + + if (folio_test_private(folio)) + return false; + if (folio_test_fscache(folio)) { + if (current_is_kswapd() || !(gfp & __GFP_FS)) + return false; + folio_wait_fscache(folio); + } + + fscache_note_page_release(netfs_i_cookie(ctx)); + return true; +} +EXPORT_SYMBOL(netfs_release_folio); diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index e17cdf53f6a7..610ceb5bd86c 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -20,14 +20,20 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, struct inode *inode = file ? file_inode(file) : mapping->host; struct netfs_inode *ctx = netfs_inode(inode); struct netfs_io_request *rreq; + bool is_unbuffered = (origin == NETFS_UNBUFFERED_WRITE || + origin == NETFS_DIO_READ || + origin == NETFS_DIO_WRITE); + bool cached = !is_unbuffered && netfs_is_cache_enabled(ctx); int ret; - rreq = kzalloc(sizeof(struct netfs_io_request), GFP_KERNEL); + rreq = kzalloc(ctx->ops->io_request_size ?: sizeof(struct netfs_io_request), + GFP_KERNEL); if (!rreq) return ERR_PTR(-ENOMEM); rreq->start = start; rreq->len = len; + rreq->upper_len = len; rreq->origin = origin; rreq->netfs_ops = ctx->ops; rreq->mapping = mapping; @@ -35,8 +41,14 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, rreq->i_size = i_size_read(inode); rreq->debug_id = atomic_inc_return(&debug_ids); INIT_LIST_HEAD(&rreq->subrequests); + INIT_WORK(&rreq->work, NULL); refcount_set(&rreq->ref, 1); + __set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); + if (cached) + __set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags); + if (file && file->f_flags & O_NONBLOCK) + __set_bit(NETFS_RREQ_NONBLOCK, &rreq->flags); if (rreq->netfs_ops->init_request) { ret = rreq->netfs_ops->init_request(rreq, file); if (ret < 0) { @@ -45,6 +57,8 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, } } + trace_netfs_rreq_ref(rreq->debug_id, 1, netfs_rreq_trace_new); + netfs_proc_add_rreq(rreq); netfs_stat(&netfs_n_rh_rreq); return rreq; } @@ -74,33 +88,47 @@ static void netfs_free_request(struct work_struct *work) { struct netfs_io_request *rreq = container_of(work, struct netfs_io_request, work); + unsigned int i; trace_netfs_rreq(rreq, netfs_rreq_trace_free); + netfs_proc_del_rreq(rreq); netfs_clear_subrequests(rreq, false); if (rreq->netfs_ops->free_request) rreq->netfs_ops->free_request(rreq); if (rreq->cache_resources.ops) rreq->cache_resources.ops->end_operation(&rreq->cache_resources); - kfree(rreq); + if (rreq->direct_bv) { + for (i = 0; i < rreq->direct_bv_count; i++) { + if (rreq->direct_bv[i].bv_page) { + if (rreq->direct_bv_unpin) + unpin_user_page(rreq->direct_bv[i].bv_page); + } + } + kvfree(rreq->direct_bv); + } + kfree_rcu(rreq, rcu); netfs_stat_d(&netfs_n_rh_rreq); } void netfs_put_request(struct netfs_io_request *rreq, bool was_async, enum netfs_rreq_ref_trace what) { - unsigned int debug_id = rreq->debug_id; + unsigned int debug_id; bool dead; int r; - dead = __refcount_dec_and_test(&rreq->ref, &r); - trace_netfs_rreq_ref(debug_id, r - 1, what); - if (dead) { - if (was_async) { - rreq->work.func = netfs_free_request; - if (!queue_work(system_unbound_wq, &rreq->work)) - BUG(); - } else { - netfs_free_request(&rreq->work); + if (rreq) { + debug_id = rreq->debug_id; + dead = __refcount_dec_and_test(&rreq->ref, &r); + trace_netfs_rreq_ref(debug_id, r - 1, what); + if (dead) { + if (was_async) { + rreq->work.func = netfs_free_request; + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); + } else { + netfs_free_request(&rreq->work); + } } } } @@ -112,8 +140,11 @@ struct netfs_io_subrequest *netfs_alloc_subrequest(struct netfs_io_request *rreq { struct netfs_io_subrequest *subreq; - subreq = kzalloc(sizeof(struct netfs_io_subrequest), GFP_KERNEL); + subreq = kzalloc(rreq->netfs_ops->io_subrequest_size ?: + sizeof(struct netfs_io_subrequest), + GFP_KERNEL); if (subreq) { + INIT_WORK(&subreq->work, NULL); INIT_LIST_HEAD(&subreq->rreq_link); refcount_set(&subreq->ref, 2); subreq->rreq = rreq; @@ -140,6 +171,8 @@ static void netfs_free_subrequest(struct netfs_io_subrequest *subreq, struct netfs_io_request *rreq = subreq->rreq; trace_netfs_sreq(subreq, netfs_sreq_trace_free); + if (rreq->netfs_ops->free_subrequest) + rreq->netfs_ops->free_subrequest(subreq); kfree(subreq); netfs_stat_d(&netfs_n_rh_sreq); netfs_put_request(rreq, was_async, netfs_rreq_trace_put_subreq); diff --git a/fs/netfs/output.c b/fs/netfs/output.c new file mode 100644 index 000000000000..625eb68f3e5a --- /dev/null +++ b/fs/netfs/output.c @@ -0,0 +1,478 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Network filesystem high-level write support. + * + * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/slab.h> +#include <linux/writeback.h> +#include <linux/pagevec.h> +#include "internal.h" + +/** + * netfs_create_write_request - Create a write operation. + * @wreq: The write request this is storing from. + * @dest: The destination type + * @start: Start of the region this write will modify + * @len: Length of the modification + * @worker: The worker function to handle the write(s) + * + * Allocate a write operation, set it up and add it to the list on a write + * request. + */ +struct netfs_io_subrequest *netfs_create_write_request(struct netfs_io_request *wreq, + enum netfs_io_source dest, + loff_t start, size_t len, + work_func_t worker) +{ + struct netfs_io_subrequest *subreq; + + subreq = netfs_alloc_subrequest(wreq); + if (subreq) { + INIT_WORK(&subreq->work, worker); + subreq->source = dest; + subreq->start = start; + subreq->len = len; + subreq->debug_index = wreq->subreq_counter++; + + switch (subreq->source) { + case NETFS_UPLOAD_TO_SERVER: + netfs_stat(&netfs_n_wh_upload); + break; + case NETFS_WRITE_TO_CACHE: + netfs_stat(&netfs_n_wh_write); + break; + default: + BUG(); + } + + subreq->io_iter = wreq->io_iter; + iov_iter_advance(&subreq->io_iter, subreq->start - wreq->start); + iov_iter_truncate(&subreq->io_iter, subreq->len); + + trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index, + refcount_read(&subreq->ref), + netfs_sreq_trace_new); + atomic_inc(&wreq->nr_outstanding); + list_add_tail(&subreq->rreq_link, &wreq->subrequests); + trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); + } + + return subreq; +} +EXPORT_SYMBOL(netfs_create_write_request); + +/* + * Process a completed write request once all the component operations have + * been completed. + */ +static void netfs_write_terminated(struct netfs_io_request *wreq, bool was_async) +{ + struct netfs_io_subrequest *subreq; + struct netfs_inode *ctx = netfs_inode(wreq->inode); + size_t transferred = 0; + + _enter("R=%x[]", wreq->debug_id); + + trace_netfs_rreq(wreq, netfs_rreq_trace_write_done); + + list_for_each_entry(subreq, &wreq->subrequests, rreq_link) { + if (subreq->error || subreq->transferred == 0) + break; + transferred += subreq->transferred; + if (subreq->transferred < subreq->len) + break; + } + wreq->transferred = transferred; + + list_for_each_entry(subreq, &wreq->subrequests, rreq_link) { + if (!subreq->error) + continue; + switch (subreq->source) { + case NETFS_UPLOAD_TO_SERVER: + /* Depending on the type of failure, this may prevent + * writeback completion unless we're in disconnected + * mode. + */ + if (!wreq->error) + wreq->error = subreq->error; + break; + + case NETFS_WRITE_TO_CACHE: + /* Failure doesn't prevent writeback completion unless + * we're in disconnected mode. + */ + if (subreq->error != -ENOBUFS) + ctx->ops->invalidate_cache(wreq); + break; + + default: + WARN_ON_ONCE(1); + if (!wreq->error) + wreq->error = -EIO; + return; + } + } + + wreq->cleanup(wreq); + + if (wreq->origin == NETFS_DIO_WRITE && + wreq->mapping->nrpages) { + pgoff_t first = wreq->start >> PAGE_SHIFT; + pgoff_t last = (wreq->start + wreq->transferred - 1) >> PAGE_SHIFT; + invalidate_inode_pages2_range(wreq->mapping, first, last); + } + + if (wreq->origin == NETFS_DIO_WRITE) + inode_dio_end(wreq->inode); + + _debug("finished"); + trace_netfs_rreq(wreq, netfs_rreq_trace_wake_ip); + clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &wreq->flags); + wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS); + + if (wreq->iocb) { + wreq->iocb->ki_pos += transferred; + if (wreq->iocb->ki_complete) + wreq->iocb->ki_complete( + wreq->iocb, wreq->error ? wreq->error : transferred); + } + + netfs_clear_subrequests(wreq, was_async); + netfs_put_request(wreq, was_async, netfs_rreq_trace_put_complete); +} + +/* + * Deal with the completion of writing the data to the cache. + */ +void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error, + bool was_async) +{ + struct netfs_io_subrequest *subreq = _op; + struct netfs_io_request *wreq = subreq->rreq; + unsigned int u; + + _enter("%x[%x] %zd", wreq->debug_id, subreq->debug_index, transferred_or_error); + + switch (subreq->source) { + case NETFS_UPLOAD_TO_SERVER: + netfs_stat(&netfs_n_wh_upload_done); + break; + case NETFS_WRITE_TO_CACHE: + netfs_stat(&netfs_n_wh_write_done); + break; + case NETFS_INVALID_WRITE: + break; + default: + BUG(); + } + + if (IS_ERR_VALUE(transferred_or_error)) { + subreq->error = transferred_or_error; + trace_netfs_failure(wreq, subreq, transferred_or_error, + netfs_fail_write); + goto failed; + } + + if (WARN(transferred_or_error > subreq->len - subreq->transferred, + "Subreq excess write: R%x[%x] %zd > %zu - %zu", + wreq->debug_id, subreq->debug_index, + transferred_or_error, subreq->len, subreq->transferred)) + transferred_or_error = subreq->len - subreq->transferred; + + subreq->error = 0; + subreq->transferred += transferred_or_error; + + if (iov_iter_count(&subreq->io_iter) != subreq->len - subreq->transferred) + pr_warn("R=%08x[%u] ITER POST-MISMATCH %zx != %zx-%zx %x\n", + wreq->debug_id, subreq->debug_index, + iov_iter_count(&subreq->io_iter), subreq->len, + subreq->transferred, subreq->io_iter.iter_type); + + if (subreq->transferred < subreq->len) + goto incomplete; + + __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); +out: + trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); + + /* If we decrement nr_outstanding to 0, the ref belongs to us. */ + u = atomic_dec_return(&wreq->nr_outstanding); + if (u == 0) + netfs_write_terminated(wreq, was_async); + else if (u == 1) + wake_up_var(&wreq->nr_outstanding); + + netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); + return; + +incomplete: + if (transferred_or_error == 0) { + if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { + subreq->error = -ENODATA; + goto failed; + } + } else { + __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + } + + __set_bit(NETFS_SREQ_SHORT_IO, &subreq->flags); + set_bit(NETFS_RREQ_INCOMPLETE_IO, &wreq->flags); + goto out; + +failed: + switch (subreq->source) { + case NETFS_WRITE_TO_CACHE: + netfs_stat(&netfs_n_wh_write_failed); + set_bit(NETFS_RREQ_INCOMPLETE_IO, &wreq->flags); + break; + case NETFS_UPLOAD_TO_SERVER: + netfs_stat(&netfs_n_wh_upload_failed); + set_bit(NETFS_RREQ_FAILED, &wreq->flags); + wreq->error = subreq->error; + break; + default: + break; + } + goto out; +} +EXPORT_SYMBOL(netfs_write_subrequest_terminated); + +static void netfs_write_to_cache_op(struct netfs_io_subrequest *subreq) +{ + struct netfs_io_request *wreq = subreq->rreq; + struct netfs_cache_resources *cres = &wreq->cache_resources; + + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); + + cres->ops->write(cres, subreq->start, &subreq->io_iter, + netfs_write_subrequest_terminated, subreq); +} + +static void netfs_write_to_cache_op_worker(struct work_struct *work) +{ + struct netfs_io_subrequest *subreq = + container_of(work, struct netfs_io_subrequest, work); + + netfs_write_to_cache_op(subreq); +} + +/** + * netfs_queue_write_request - Queue a write request for attention + * @subreq: The write request to be queued + * + * Queue the specified write request for processing by a worker thread. We + * pass the caller's ref on the request to the worker thread. + */ +void netfs_queue_write_request(struct netfs_io_subrequest *subreq) +{ + if (!queue_work(system_unbound_wq, &subreq->work)) + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_wip); +} +EXPORT_SYMBOL(netfs_queue_write_request); + +/* + * Set up a op for writing to the cache. + */ +static void netfs_set_up_write_to_cache(struct netfs_io_request *wreq) +{ + struct netfs_cache_resources *cres = &wreq->cache_resources; + struct netfs_io_subrequest *subreq; + struct netfs_inode *ctx = netfs_inode(wreq->inode); + struct fscache_cookie *cookie = netfs_i_cookie(ctx); + loff_t start = wreq->start; + size_t len = wreq->len; + int ret; + + if (!fscache_cookie_enabled(cookie)) { + clear_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags); + return; + } + + _debug("write to cache"); + ret = fscache_begin_write_operation(cres, cookie); + if (ret < 0) + return; + + ret = cres->ops->prepare_write(cres, &start, &len, wreq->upper_len, + i_size_read(wreq->inode), true); + if (ret < 0) + return; + + subreq = netfs_create_write_request(wreq, NETFS_WRITE_TO_CACHE, start, len, + netfs_write_to_cache_op_worker); + if (!subreq) + return; + + netfs_write_to_cache_op(subreq); +} + +/* + * Begin the process of writing out a chunk of data. + * + * We are given a write request that holds a series of dirty regions and + * (partially) covers a sequence of folios, all of which are present. The + * pages must have been marked as writeback as appropriate. + * + * We need to perform the following steps: + * + * (1) If encrypting, create an output buffer and encrypt each block of the + * data into it, otherwise the output buffer will point to the original + * folios. + * + * (2) If the data is to be cached, set up a write op for the entire output + * buffer to the cache, if the cache wants to accept it. + * + * (3) If the data is to be uploaded (ie. not merely cached): + * + * (a) If the data is to be compressed, create a compression buffer and + * compress the data into it. + * + * (b) For each destination we want to upload to, set up write ops to write + * to that destination. We may need multiple writes if the data is not + * contiguous or the span exceeds wsize for a server. + */ +int netfs_begin_write(struct netfs_io_request *wreq, bool may_wait, + enum netfs_write_trace what) +{ + struct netfs_inode *ctx = netfs_inode(wreq->inode); + + _enter("R=%x %llx-%llx f=%lx", + wreq->debug_id, wreq->start, wreq->start + wreq->len - 1, + wreq->flags); + + trace_netfs_write(wreq, what); + if (wreq->len == 0 || wreq->iter.count == 0) { + pr_err("Zero-sized write [R=%x]\n", wreq->debug_id); + return -EIO; + } + + if (wreq->origin == NETFS_DIO_WRITE) + inode_dio_begin(wreq->inode); + + wreq->io_iter = wreq->iter; + + /* ->outstanding > 0 carries a ref */ + netfs_get_request(wreq, netfs_rreq_trace_get_for_outstanding); + atomic_set(&wreq->nr_outstanding, 1); + + /* Start the encryption/compression going. We can do that in the + * background whilst we generate a list of write ops that we want to + * perform. + */ + // TODO: Encrypt or compress the region as appropriate + + /* We need to write all of the region to the cache */ + if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags)) + netfs_set_up_write_to_cache(wreq); + + /* However, we don't necessarily write all of the region to the server. + * Caching of reads is being managed this way also. + */ + if (test_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags)) + ctx->ops->create_write_requests(wreq, wreq->start, wreq->len); + + if (atomic_dec_and_test(&wreq->nr_outstanding)) + netfs_write_terminated(wreq, false); + + if (!may_wait) + return -EIOCBQUEUED; + + wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS, + TASK_UNINTERRUPTIBLE); + return wreq->error; +} + +/* + * Begin a write operation for writing through the pagecache. + */ +struct netfs_io_request *netfs_begin_writethrough(struct kiocb *iocb, size_t len) +{ + struct netfs_io_request *wreq; + struct file *file = iocb->ki_filp; + + wreq = netfs_alloc_request(file->f_mapping, file, iocb->ki_pos, len, + NETFS_WRITETHROUGH); + if (IS_ERR(wreq)) + return wreq; + + trace_netfs_write(wreq, netfs_write_trace_writethrough); + + __set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags); + iov_iter_xarray(&wreq->iter, ITER_SOURCE, &wreq->mapping->i_pages, wreq->start, 0); + wreq->io_iter = wreq->iter; + + /* ->outstanding > 0 carries a ref */ + netfs_get_request(wreq, netfs_rreq_trace_get_for_outstanding); + atomic_set(&wreq->nr_outstanding, 1); + return wreq; +} + +static void netfs_submit_writethrough(struct netfs_io_request *wreq, bool final) +{ + struct netfs_inode *ictx = netfs_inode(wreq->inode); + unsigned long long start; + size_t len; + + if (!test_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags)) + return; + + start = wreq->start + wreq->submitted; + len = wreq->iter.count - wreq->submitted; + if (!final) { + len /= wreq->wsize; /* Round to number of maximum packets */ + len *= wreq->wsize; + } + + ictx->ops->create_write_requests(wreq, start, len); + wreq->submitted += len; +} + +/* + * Advance the state of the write operation used when writing through the + * pagecache. Data has been copied into the pagecache that we need to append + * to the request. If we've added more than wsize then we need to create a new + * subrequest. + */ +int netfs_advance_writethrough(struct netfs_io_request *wreq, size_t copied, bool to_page_end) +{ + _enter("ic=%zu sb=%zu ws=%u cp=%zu tp=%u", + wreq->iter.count, wreq->submitted, wreq->wsize, copied, to_page_end); + + wreq->iter.count += copied; + wreq->io_iter.count += copied; + if (to_page_end && wreq->io_iter.count - wreq->submitted >= wreq->wsize) + netfs_submit_writethrough(wreq, false); + + return wreq->error; +} + +/* + * End a write operation used when writing through the pagecache. + */ +int netfs_end_writethrough(struct netfs_io_request *wreq, struct kiocb *iocb) +{ + int ret = -EIOCBQUEUED; + + _enter("ic=%zu sb=%zu ws=%u", + wreq->iter.count, wreq->submitted, wreq->wsize); + + if (wreq->submitted < wreq->io_iter.count) + netfs_submit_writethrough(wreq, true); + + if (atomic_dec_and_test(&wreq->nr_outstanding)) + netfs_write_terminated(wreq, false); + + if (is_sync_kiocb(iocb)) { + wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS, + TASK_UNINTERRUPTIBLE); + ret = wreq->error; + } + + netfs_put_request(wreq, false, netfs_rreq_trace_put_return); + return ret; +} diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c index 5510a7a14a40..deeba9f9dcf5 100644 --- a/fs/netfs/stats.c +++ b/fs/netfs/stats.c @@ -9,6 +9,8 @@ #include <linux/seq_file.h> #include "internal.h" +atomic_t netfs_n_rh_dio_read; +atomic_t netfs_n_rh_dio_write; atomic_t netfs_n_rh_readahead; atomic_t netfs_n_rh_readpage; atomic_t netfs_n_rh_rreq; @@ -27,32 +29,48 @@ atomic_t netfs_n_rh_write_begin; atomic_t netfs_n_rh_write_done; atomic_t netfs_n_rh_write_failed; atomic_t netfs_n_rh_write_zskip; +atomic_t netfs_n_wh_wstream_conflict; +atomic_t netfs_n_wh_upload; +atomic_t netfs_n_wh_upload_done; +atomic_t netfs_n_wh_upload_failed; +atomic_t netfs_n_wh_write; +atomic_t netfs_n_wh_write_done; +atomic_t netfs_n_wh_write_failed; -void netfs_stats_show(struct seq_file *m) +int netfs_stats_show(struct seq_file *m, void *v) { - seq_printf(m, "RdHelp : RA=%u RP=%u WB=%u WBZ=%u rr=%u sr=%u\n", + seq_printf(m, "Netfs : DR=%u DW=%u RA=%u RP=%u WB=%u WBZ=%u\n", + atomic_read(&netfs_n_rh_dio_read), + atomic_read(&netfs_n_rh_dio_write), atomic_read(&netfs_n_rh_readahead), atomic_read(&netfs_n_rh_readpage), atomic_read(&netfs_n_rh_write_begin), - atomic_read(&netfs_n_rh_write_zskip), - atomic_read(&netfs_n_rh_rreq), - atomic_read(&netfs_n_rh_sreq)); - seq_printf(m, "RdHelp : ZR=%u sh=%u sk=%u\n", + atomic_read(&netfs_n_rh_write_zskip)); + seq_printf(m, "Netfs : ZR=%u sh=%u sk=%u\n", atomic_read(&netfs_n_rh_zero), atomic_read(&netfs_n_rh_short_read), atomic_read(&netfs_n_rh_write_zskip)); - seq_printf(m, "RdHelp : DL=%u ds=%u df=%u di=%u\n", + seq_printf(m, "Netfs : DL=%u ds=%u df=%u di=%u\n", atomic_read(&netfs_n_rh_download), atomic_read(&netfs_n_rh_download_done), atomic_read(&netfs_n_rh_download_failed), atomic_read(&netfs_n_rh_download_instead)); - seq_printf(m, "RdHelp : RD=%u rs=%u rf=%u\n", + seq_printf(m, "Netfs : RD=%u rs=%u rf=%u\n", atomic_read(&netfs_n_rh_read), atomic_read(&netfs_n_rh_read_done), atomic_read(&netfs_n_rh_read_failed)); - seq_printf(m, "RdHelp : WR=%u ws=%u wf=%u\n", - atomic_read(&netfs_n_rh_write), - atomic_read(&netfs_n_rh_write_done), - atomic_read(&netfs_n_rh_write_failed)); + seq_printf(m, "Netfs : UL=%u us=%u uf=%u\n", + atomic_read(&netfs_n_wh_upload), + atomic_read(&netfs_n_wh_upload_done), + atomic_read(&netfs_n_wh_upload_failed)); + seq_printf(m, "Netfs : WR=%u ws=%u wf=%u\n", + atomic_read(&netfs_n_wh_write), + atomic_read(&netfs_n_wh_write_done), + atomic_read(&netfs_n_wh_write_failed)); + seq_printf(m, "Netfs : rr=%u sr=%u wsc=%u\n", + atomic_read(&netfs_n_rh_rreq), + atomic_read(&netfs_n_rh_sreq), + atomic_read(&netfs_n_wh_wstream_conflict)); + return fscache_stats_show(m); } EXPORT_SYMBOL(netfs_stats_show); diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 01ac733a6320..f7e32d76e34d 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -169,8 +169,8 @@ config ROOT_NFS config NFS_FSCACHE bool "Provide NFS client caching support" - depends on NFS_FS=m && FSCACHE || NFS_FS=y && FSCACHE=y - select NETFS_SUPPORT + depends on NFS_FS=m && NETFS_SUPPORT || NFS_FS=y && NETFS_SUPPORT=y + select FSCACHE help Say Y here if you want NFS data to be cached locally on disc through the general filesystem cache manager diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index b05717fe0d4e..2d1bfee225c3 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -274,12 +274,6 @@ static void nfs_netfs_free_request(struct netfs_io_request *rreq) put_nfs_open_context(rreq->netfs_priv); } -static inline int nfs_netfs_begin_cache_operation(struct netfs_io_request *rreq) -{ - return fscache_begin_read_operation(&rreq->cache_resources, - netfs_i_cookie(netfs_inode(rreq->inode))); -} - static struct nfs_netfs_io_data *nfs_netfs_alloc(struct netfs_io_subrequest *sreq) { struct nfs_netfs_io_data *netfs; @@ -387,7 +381,6 @@ void nfs_netfs_read_completion(struct nfs_pgio_header *hdr) const struct netfs_request_ops nfs_netfs_ops = { .init_request = nfs_netfs_init_request, .free_request = nfs_netfs_free_request, - .begin_cache_operation = nfs_netfs_begin_cache_operation, .issue_read = nfs_netfs_issue_read, .clamp_length = nfs_netfs_clamp_length }; diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 5407ab8c8783..e3cb4923316b 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -80,7 +80,7 @@ static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs) } static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi) { - netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops); + netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops, false); } extern void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr); extern void nfs_netfs_read_completion(struct nfs_pgio_header *hdr); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 99b0ade833aa..aa8450c9b849 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -430,7 +430,7 @@ static void cifs_evict_inode(struct inode *inode) { truncate_inode_pages_final(&inode->i_data); - if (inode->i_state & I_PINNING_FSCACHE_WB) + if (inode->i_state & I_PINNING_NETFS_WB) cifs_fscache_unuse_inode_cookie(inode, true); cifs_fscache_release_inode_cookie(inode); clear_inode(inode); @@ -793,8 +793,7 @@ static int cifs_show_stats(struct seq_file *s, struct dentry *root) static int cifs_write_inode(struct inode *inode, struct writeback_control *wbc) { - fscache_unpin_writeback(wbc, cifs_inode_cookie(inode)); - return 0; + return netfs_unpin_writeback(inode, wbc); } static int cifs_drop_inode(struct inode *inode) @@ -1222,7 +1221,7 @@ static int cifs_precopy_set_eof(struct inode *src_inode, struct cifsInodeInfo *s if (rc < 0) goto set_failed; - netfs_resize_file(&src_cifsi->netfs, src_end); + netfs_resize_file(&src_cifsi->netfs, src_end, true); fscache_resize_cookie(cifs_inode_cookie(src_inode), src_end); return 0; @@ -1353,7 +1352,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, smb_file_src, smb_file_target, off, len, destoff); if (rc == 0 && new_size > i_size_read(target_inode)) { truncate_setsize(target_inode, new_size); - netfs_resize_file(&target_cifsi->netfs, new_size); + netfs_resize_file(&target_cifsi->netfs, new_size, true); fscache_resize_cookie(cifs_inode_cookie(target_inode), new_size); } diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 1b4262aff8fa..3a213432775b 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -5043,27 +5043,13 @@ static void cifs_swap_deactivate(struct file *file) /* do we need to unpin (or unlock) the file */ } -/* - * Mark a page as having been made dirty and thus needing writeback. We also - * need to pin the cache object to write back to. - */ -#ifdef CONFIG_CIFS_FSCACHE -static bool cifs_dirty_folio(struct address_space *mapping, struct folio *folio) -{ - return fscache_dirty_folio(mapping, folio, - cifs_inode_cookie(mapping->host)); -} -#else -#define cifs_dirty_folio filemap_dirty_folio -#endif - const struct address_space_operations cifs_addr_ops = { .read_folio = cifs_read_folio, .readahead = cifs_readahead, .writepages = cifs_writepages, .write_begin = cifs_write_begin, .write_end = cifs_write_end, - .dirty_folio = cifs_dirty_folio, + .dirty_folio = netfs_dirty_folio, .release_folio = cifs_release_folio, .direct_IO = cifs_direct_io, .invalidate_folio = cifs_invalidate_folio, @@ -5087,7 +5073,7 @@ const struct address_space_operations cifs_addr_ops_smallbuf = { .writepages = cifs_writepages, .write_begin = cifs_write_begin, .write_end = cifs_write_end, - .dirty_folio = cifs_dirty_folio, + .dirty_folio = netfs_dirty_folio, .release_folio = cifs_release_folio, .invalidate_folio = cifs_invalidate_folio, .launder_folio = cifs_launder_folio, diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c index e5cad149f5a2..c4a3cb736881 100644 --- a/fs/smb/client/fscache.c +++ b/fs/smb/client/fscache.c @@ -180,7 +180,7 @@ static int fscache_fallback_write_pages(struct inode *inode, loff_t start, size_ if (ret < 0) return ret; - ret = cres.ops->prepare_write(&cres, &start, &len, i_size_read(inode), + ret = cres.ops->prepare_write(&cres, &start, &len, len, i_size_read(inode), no_space_allocated_yet); if (ret == 0) ret = fscache_write(&cres, start, &iter, NULL, NULL); diff --git a/fs/smb/server/asn1.c b/fs/smb/server/asn1.c index 4a4b2b03ff33..b931a99ab9c8 100644 --- a/fs/smb/server/asn1.c +++ b/fs/smb/server/asn1.c @@ -214,10 +214,15 @@ static int ksmbd_neg_token_alloc(void *context, size_t hdrlen, { struct ksmbd_conn *conn = context; + if (!vlen) + return -EINVAL; + conn->mechToken = kmemdup_nul(value, vlen, GFP_KERNEL); if (!conn->mechToken) return -ENOMEM; + conn->mechTokenLen = (unsigned int)vlen; + return 0; } diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index d311c2ee10bd..09e1e7771592 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -416,13 +416,7 @@ static void stop_sessions(void) again: down_read(&conn_list_lock); list_for_each_entry(conn, &conn_list, conns_list) { - struct task_struct *task; - t = conn->transport; - task = t->handler; - if (task) - ksmbd_debug(CONN, "Stop session handler %s/%d\n", - task->comm, task_pid_nr(task)); ksmbd_conn_set_exiting(conn); if (t->ops->shutdown) { up_read(&conn_list_lock); diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 3c005246a32e..0e04cf8b1d89 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -88,6 +88,7 @@ struct ksmbd_conn { __u16 dialect; char *mechToken; + unsigned int mechTokenLen; struct ksmbd_conn_ops *conn_ops; @@ -134,7 +135,6 @@ struct ksmbd_transport_ops { struct ksmbd_transport { struct ksmbd_conn *conn; struct ksmbd_transport_ops *ops; - struct task_struct *handler; }; #define KSMBD_TCP_RECV_TIMEOUT (7 * HZ) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 001926d3b348..53dfaac425c6 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -1197,6 +1197,12 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, bool prev_op_has_lease; __le32 prev_op_state = 0; + /* Only v2 leases handle the directory */ + if (S_ISDIR(file_inode(fp->filp)->i_mode)) { + if (!lctx || lctx->version != 2) + return 0; + } + opinfo = alloc_opinfo(work, pid, tid); if (!opinfo) return -ENOMEM; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 3143819935dc..ba7a72a6a4f4 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1414,7 +1414,10 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn, char *name; unsigned int name_off, name_len, secbuf_len; - secbuf_len = le16_to_cpu(req->SecurityBufferLength); + if (conn->use_spnego && conn->mechToken) + secbuf_len = conn->mechTokenLen; + else + secbuf_len = le16_to_cpu(req->SecurityBufferLength); if (secbuf_len < sizeof(struct authenticate_message)) { ksmbd_debug(SMB, "blob len %d too small\n", secbuf_len); return NULL; @@ -1505,7 +1508,10 @@ static int ntlm_authenticate(struct ksmbd_work *work, struct authenticate_message *authblob; authblob = user_authblob(conn, req); - sz = le16_to_cpu(req->SecurityBufferLength); + if (conn->use_spnego && conn->mechToken) + sz = conn->mechTokenLen; + else + sz = le16_to_cpu(req->SecurityBufferLength); rc = ksmbd_decode_ntlmssp_auth_blob(authblob, sz, conn, sess); if (rc) { set_user_flag(sess->user, KSMBD_USER_FLAG_BAD_PASSWORD); @@ -1778,8 +1784,7 @@ int smb2_sess_setup(struct ksmbd_work *work) negblob_off = le16_to_cpu(req->SecurityBufferOffset); negblob_len = le16_to_cpu(req->SecurityBufferLength); - if (negblob_off < offsetof(struct smb2_sess_setup_req, Buffer) || - negblob_len < offsetof(struct negotiate_message, NegotiateFlags)) { + if (negblob_off < offsetof(struct smb2_sess_setup_req, Buffer)) { rc = -EINVAL; goto out_err; } @@ -1788,8 +1793,15 @@ int smb2_sess_setup(struct ksmbd_work *work) negblob_off); if (decode_negotiation_token(conn, negblob, negblob_len) == 0) { - if (conn->mechToken) + if (conn->mechToken) { negblob = (struct negotiate_message *)conn->mechToken; + negblob_len = conn->mechTokenLen; + } + } + + if (negblob_len < offsetof(struct negotiate_message, NegotiateFlags)) { + rc = -EINVAL; + goto out_err; } if (server_conf.auth_mechs & conn->auth_mechs) { diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index c5629a68c8b7..8faa25c6e129 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -2039,6 +2039,7 @@ static bool rdma_frwr_is_supported(struct ib_device_attr *attrs) static int smb_direct_handle_connect_request(struct rdma_cm_id *new_cm_id) { struct smb_direct_transport *t; + struct task_struct *handler; int ret; if (!rdma_frwr_is_supported(&new_cm_id->device->attrs)) { @@ -2056,11 +2057,11 @@ static int smb_direct_handle_connect_request(struct rdma_cm_id *new_cm_id) if (ret) goto out_err; - KSMBD_TRANS(t)->handler = kthread_run(ksmbd_conn_handler_loop, - KSMBD_TRANS(t)->conn, "ksmbd:r%u", - smb_direct_port); - if (IS_ERR(KSMBD_TRANS(t)->handler)) { - ret = PTR_ERR(KSMBD_TRANS(t)->handler); + handler = kthread_run(ksmbd_conn_handler_loop, + KSMBD_TRANS(t)->conn, "ksmbd:r%u", + smb_direct_port); + if (IS_ERR(handler)) { + ret = PTR_ERR(handler); pr_err("Can't start thread\n"); goto out_err; } diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index eff7a1d793f0..9d4222154dcc 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -185,6 +185,7 @@ static int ksmbd_tcp_new_connection(struct socket *client_sk) struct sockaddr *csin; int rc = 0; struct tcp_transport *t; + struct task_struct *handler; t = alloc_transport(client_sk); if (!t) { @@ -199,13 +200,13 @@ static int ksmbd_tcp_new_connection(struct socket *client_sk) goto out_error; } - KSMBD_TRANS(t)->handler = kthread_run(ksmbd_conn_handler_loop, - KSMBD_TRANS(t)->conn, - "ksmbd:%u", - ksmbd_tcp_get_port(csin)); - if (IS_ERR(KSMBD_TRANS(t)->handler)) { + handler = kthread_run(ksmbd_conn_handler_loop, + KSMBD_TRANS(t)->conn, + "ksmbd:%u", + ksmbd_tcp_get_port(csin)); + if (IS_ERR(handler)) { pr_err("cannot start conn thread\n"); - rc = PTR_ERR(KSMBD_TRANS(t)->handler); + rc = PTR_ERR(handler); free_transport(t); } return rc; diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index f0677ea0ec24..6795fda2af19 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -32,6 +32,10 @@ */ static DEFINE_MUTEX(eventfs_mutex); +/* Choose something "unique" ;-) */ +#define EVENTFS_FILE_INODE_INO 0x12c4e37 +#define EVENTFS_DIR_INODE_INO 0x134b2f5 + /* * The eventfs_inode (ei) itself is protected by SRCU. It is released from * its parent's list and will have is_freed set (under eventfs_mutex). @@ -45,6 +49,7 @@ enum { EVENTFS_SAVE_MODE = BIT(16), EVENTFS_SAVE_UID = BIT(17), EVENTFS_SAVE_GID = BIT(18), + EVENTFS_TOPLEVEL = BIT(19), }; #define EVENTFS_MODE_MASK (EVENTFS_SAVE_MODE - 1) @@ -52,9 +57,7 @@ enum { static struct dentry *eventfs_root_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); -static int dcache_dir_open_wrapper(struct inode *inode, struct file *file); -static int dcache_readdir_wrapper(struct file *file, struct dir_context *ctx); -static int eventfs_release(struct inode *inode, struct file *file); +static int eventfs_iterate(struct file *file, struct dir_context *ctx); static void update_attr(struct eventfs_attr *attr, struct iattr *iattr) { @@ -94,7 +97,7 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry, /* Preallocate the children mode array if necessary */ if (!(dentry->d_inode->i_mode & S_IFDIR)) { if (!ei->entry_attrs) { - ei->entry_attrs = kzalloc(sizeof(*ei->entry_attrs) * ei->nr_entries, + ei->entry_attrs = kcalloc(ei->nr_entries, sizeof(*ei->entry_attrs), GFP_NOFS); if (!ei->entry_attrs) { ret = -ENOMEM; @@ -117,10 +120,17 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry, * The events directory dentry is never freed, unless its * part of an instance that is deleted. It's attr is the * default for its child files and directories. - * Do not update it. It's not used for its own mode or ownership + * Do not update it. It's not used for its own mode or ownership. */ - if (!ei->is_events) + if (ei->is_events) { + /* But it still needs to know if it was modified */ + if (iattr->ia_valid & ATTR_UID) + ei->attr.mode |= EVENTFS_SAVE_UID; + if (iattr->ia_valid & ATTR_GID) + ei->attr.mode |= EVENTFS_SAVE_GID; + } else { update_attr(&ei->attr, iattr); + } } else { name = dentry->d_name.name; @@ -138,9 +148,66 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry, return ret; } +static void update_top_events_attr(struct eventfs_inode *ei, struct dentry *dentry) +{ + struct inode *inode; + + /* Only update if the "events" was on the top level */ + if (!ei || !(ei->attr.mode & EVENTFS_TOPLEVEL)) + return; + + /* Get the tracefs root inode. */ + inode = d_inode(dentry->d_sb->s_root); + ei->attr.uid = inode->i_uid; + ei->attr.gid = inode->i_gid; +} + +static void set_top_events_ownership(struct inode *inode) +{ + struct tracefs_inode *ti = get_tracefs(inode); + struct eventfs_inode *ei = ti->private; + struct dentry *dentry; + + /* The top events directory doesn't get automatically updated */ + if (!ei || !ei->is_events || !(ei->attr.mode & EVENTFS_TOPLEVEL)) + return; + + dentry = ei->dentry; + + update_top_events_attr(ei, dentry); + + if (!(ei->attr.mode & EVENTFS_SAVE_UID)) + inode->i_uid = ei->attr.uid; + + if (!(ei->attr.mode & EVENTFS_SAVE_GID)) + inode->i_gid = ei->attr.gid; +} + +static int eventfs_get_attr(struct mnt_idmap *idmap, + const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int flags) +{ + struct dentry *dentry = path->dentry; + struct inode *inode = d_backing_inode(dentry); + + set_top_events_ownership(inode); + + generic_fillattr(idmap, request_mask, inode, stat); + return 0; +} + +static int eventfs_permission(struct mnt_idmap *idmap, + struct inode *inode, int mask) +{ + set_top_events_ownership(inode); + return generic_permission(idmap, inode, mask); +} + static const struct inode_operations eventfs_root_dir_inode_operations = { .lookup = eventfs_root_lookup, .setattr = eventfs_set_attr, + .getattr = eventfs_get_attr, + .permission = eventfs_permission, }; static const struct inode_operations eventfs_file_inode_operations = { @@ -148,11 +215,9 @@ static const struct inode_operations eventfs_file_inode_operations = { }; static const struct file_operations eventfs_file_operations = { - .open = dcache_dir_open_wrapper, .read = generic_read_dir, - .iterate_shared = dcache_readdir_wrapper, + .iterate_shared = eventfs_iterate, .llseek = generic_file_llseek, - .release = eventfs_release, }; /* Return the evenfs_inode of the "events" directory */ @@ -178,6 +243,8 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry) } while (!ei->is_events); mutex_unlock(&eventfs_mutex); + update_top_events_attr(ei, dentry); + return ei; } @@ -289,6 +356,9 @@ static struct dentry *create_file(const char *name, umode_t mode, inode->i_fop = fop; inode->i_private = data; + /* All files will have the same inode number */ + inode->i_ino = EVENTFS_FILE_INODE_INO; + ti = get_tracefs(inode); ti->flags |= TRACEFS_EVENT_INODE; d_instantiate(dentry, inode); @@ -325,6 +395,9 @@ static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent inode->i_op = &eventfs_root_dir_inode_operations; inode->i_fop = &eventfs_file_operations; + /* All directories will have the same inode number */ + inode->i_ino = EVENTFS_DIR_INODE_INO; + ti = get_tracefs(inode); ti->flags |= TRACEFS_EVENT_INODE; @@ -390,16 +463,14 @@ void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry) * @mode: The mode of the file. * @data: The data to use to set the inode of the file with on open() * @fops: The fops of the file to be created. - * @lookup: If called by the lookup routine, in which case, dput() the created dentry. * * Create a dentry for a file of an eventfs_inode @ei and place it into the - * address located at @e_dentry. If the @e_dentry already has a dentry, then - * just do a dget() on it and return. Otherwise create the dentry and attach it. + * address located at @e_dentry. */ static struct dentry * create_file_dentry(struct eventfs_inode *ei, int idx, struct dentry *parent, const char *name, umode_t mode, void *data, - const struct file_operations *fops, bool lookup) + const struct file_operations *fops) { struct eventfs_attr *attr = NULL; struct dentry **e_dentry = &ei->d_children[idx]; @@ -414,9 +485,7 @@ create_file_dentry(struct eventfs_inode *ei, int idx, } /* If the e_dentry already has a dentry, use it */ if (*e_dentry) { - /* lookup does not need to up the ref count */ - if (!lookup) - dget(*e_dentry); + dget(*e_dentry); mutex_unlock(&eventfs_mutex); return *e_dentry; } @@ -441,13 +510,12 @@ create_file_dentry(struct eventfs_inode *ei, int idx, * way to being freed, don't return it. If e_dentry is NULL * it means it was already freed. */ - if (ei->is_freed) + if (ei->is_freed) { dentry = NULL; - else + } else { dentry = *e_dentry; - /* The lookup does not need to up the dentry refcount */ - if (dentry && !lookup) dget(dentry); + } mutex_unlock(&eventfs_mutex); return dentry; } @@ -465,9 +533,6 @@ create_file_dentry(struct eventfs_inode *ei, int idx, } mutex_unlock(&eventfs_mutex); - if (lookup) - dput(dentry); - return dentry; } @@ -500,13 +565,12 @@ static void eventfs_post_create_dir(struct eventfs_inode *ei) * @pei: The eventfs_inode parent of ei. * @ei: The eventfs_inode to create the directory for * @parent: The dentry of the parent of this directory - * @lookup: True if this is called by the lookup code * * This creates and attaches a directory dentry to the eventfs_inode @ei. */ static struct dentry * create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei, - struct dentry *parent, bool lookup) + struct dentry *parent) { struct dentry *dentry = NULL; @@ -518,11 +582,9 @@ create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei, return NULL; } if (ei->dentry) { - /* If the dentry already has a dentry, use it */ + /* If the eventfs_inode already has a dentry, use it */ dentry = ei->dentry; - /* lookup does not need to up the ref count */ - if (!lookup) - dget(dentry); + dget(dentry); mutex_unlock(&eventfs_mutex); return dentry; } @@ -542,7 +604,7 @@ create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei, * way to being freed. */ dentry = ei->dentry; - if (dentry && !lookup) + if (dentry) dget(dentry); mutex_unlock(&eventfs_mutex); return dentry; @@ -562,9 +624,6 @@ create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei, } mutex_unlock(&eventfs_mutex); - if (lookup) - dput(dentry); - return dentry; } @@ -589,8 +648,8 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, struct eventfs_inode *ei; struct dentry *ei_dentry = NULL; struct dentry *ret = NULL; + struct dentry *d; const char *name = dentry->d_name.name; - bool created = false; umode_t mode; void *data; int idx; @@ -626,13 +685,10 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, ret = simple_lookup(dir, dentry, flags); if (IS_ERR(ret)) goto out; - create_dir_dentry(ei, ei_child, ei_dentry, true); - created = true; - break; - } - - if (created) + d = create_dir_dentry(ei, ei_child, ei_dentry); + dput(d); goto out; + } for (i = 0; i < ei->nr_entries; i++) { entry = &ei->entries[i]; @@ -650,8 +706,8 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, ret = simple_lookup(dir, dentry, flags); if (IS_ERR(ret)) goto out; - create_file_dentry(ei, i, ei_dentry, name, mode, cdata, - fops, true); + d = create_file_dentry(ei, i, ei_dentry, name, mode, cdata, fops); + dput(d); break; } } @@ -660,172 +716,107 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, return ret; } -struct dentry_list { - void *cursor; - struct dentry **dentries; -}; - -/** - * eventfs_release - called to release eventfs file/dir - * @inode: inode to be released - * @file: file to be released (not used) - */ -static int eventfs_release(struct inode *inode, struct file *file) -{ - struct tracefs_inode *ti; - struct dentry_list *dlist = file->private_data; - void *cursor; - int i; - - ti = get_tracefs(inode); - if (!(ti->flags & TRACEFS_EVENT_INODE)) - return -EINVAL; - - if (WARN_ON_ONCE(!dlist)) - return -EINVAL; - - for (i = 0; dlist->dentries && dlist->dentries[i]; i++) { - dput(dlist->dentries[i]); - } - - cursor = dlist->cursor; - kfree(dlist->dentries); - kfree(dlist); - file->private_data = cursor; - return dcache_dir_close(inode, file); -} - -static int add_dentries(struct dentry ***dentries, struct dentry *d, int cnt) -{ - struct dentry **tmp; - - tmp = krealloc(*dentries, sizeof(d) * (cnt + 2), GFP_NOFS); - if (!tmp) - return -1; - tmp[cnt] = d; - tmp[cnt + 1] = NULL; - *dentries = tmp; - return 0; -} - -/** - * dcache_dir_open_wrapper - eventfs open wrapper - * @inode: not used - * @file: dir to be opened (to create it's children) - * - * Used to dynamic create file/dir with-in @file, all the - * file/dir will be created. If already created then references - * will be increased +/* + * Walk the children of a eventfs_inode to fill in getdents(). */ -static int dcache_dir_open_wrapper(struct inode *inode, struct file *file) +static int eventfs_iterate(struct file *file, struct dir_context *ctx) { const struct file_operations *fops; + struct inode *f_inode = file_inode(file); const struct eventfs_entry *entry; struct eventfs_inode *ei_child; struct tracefs_inode *ti; struct eventfs_inode *ei; - struct dentry_list *dlist; - struct dentry **dentries = NULL; - struct dentry *parent = file_dentry(file); - struct dentry *d; - struct inode *f_inode = file_inode(file); - const char *name = parent->d_name.name; + const char *name; umode_t mode; - void *data; - int cnt = 0; int idx; - int ret; - int i; - int r; + int ret = -EINVAL; + int ino; + int i, r, c; + + if (!dir_emit_dots(file, ctx)) + return 0; ti = get_tracefs(f_inode); if (!(ti->flags & TRACEFS_EVENT_INODE)) return -EINVAL; - if (WARN_ON_ONCE(file->private_data)) - return -EINVAL; + c = ctx->pos - 2; idx = srcu_read_lock(&eventfs_srcu); mutex_lock(&eventfs_mutex); ei = READ_ONCE(ti->private); + if (ei && ei->is_freed) + ei = NULL; mutex_unlock(&eventfs_mutex); - if (!ei) { - srcu_read_unlock(&eventfs_srcu, idx); - return -EINVAL; - } - - - data = ei->data; + if (!ei) + goto out; - dlist = kmalloc(sizeof(*dlist), GFP_KERNEL); - if (!dlist) { - srcu_read_unlock(&eventfs_srcu, idx); - return -ENOMEM; - } + /* + * Need to create the dentries and inodes to have a consistent + * inode number. + */ + ret = 0; - inode_lock(parent->d_inode); - list_for_each_entry_srcu(ei_child, &ei->children, list, - srcu_read_lock_held(&eventfs_srcu)) { - d = create_dir_dentry(ei, ei_child, parent, false); - if (d) { - ret = add_dentries(&dentries, d, cnt); - if (ret < 0) - break; - cnt++; - } - } + /* Start at 'c' to jump over already read entries */ + for (i = c; i < ei->nr_entries; i++, ctx->pos++) { + void *cdata = ei->data; - for (i = 0; i < ei->nr_entries; i++) { - void *cdata = data; entry = &ei->entries[i]; name = entry->name; + mutex_lock(&eventfs_mutex); - /* If ei->is_freed, then the event itself may be too */ - if (!ei->is_freed) - r = entry->callback(name, &mode, &cdata, &fops); - else - r = -1; + /* If ei->is_freed then just bail here, nothing more to do */ + if (ei->is_freed) { + mutex_unlock(&eventfs_mutex); + goto out; + } + r = entry->callback(name, &mode, &cdata, &fops); mutex_unlock(&eventfs_mutex); if (r <= 0) continue; - d = create_file_dentry(ei, i, parent, name, mode, cdata, fops, false); - if (d) { - ret = add_dentries(&dentries, d, cnt); - if (ret < 0) - break; - cnt++; + + ino = EVENTFS_FILE_INODE_INO; + + if (!dir_emit(ctx, name, strlen(name), ino, DT_REG)) + goto out; + } + + /* Subtract the skipped entries above */ + c -= min((unsigned int)c, (unsigned int)ei->nr_entries); + + list_for_each_entry_srcu(ei_child, &ei->children, list, + srcu_read_lock_held(&eventfs_srcu)) { + + if (c > 0) { + c--; + continue; } + + ctx->pos++; + + if (ei_child->is_freed) + continue; + + name = ei_child->name; + + ino = EVENTFS_DIR_INODE_INO; + + if (!dir_emit(ctx, name, strlen(name), ino, DT_DIR)) + goto out_dec; } - inode_unlock(parent->d_inode); + ret = 1; + out: srcu_read_unlock(&eventfs_srcu, idx); - ret = dcache_dir_open(inode, file); - /* - * dcache_dir_open() sets file->private_data to a dentry cursor. - * Need to save that but also save all the dentries that were - * opened by this function. - */ - dlist->cursor = file->private_data; - dlist->dentries = dentries; - file->private_data = dlist; return ret; -} - -/* - * This just sets the file->private_data back to the cursor and back. - */ -static int dcache_readdir_wrapper(struct file *file, struct dir_context *ctx) -{ - struct dentry_list *dlist = file->private_data; - int ret; - file->private_data = dlist->cursor; - ret = dcache_readdir(file, ctx); - dlist->cursor = file->private_data; - file->private_data = dlist; - return ret; + out_dec: + /* Incremented ctx->pos without adding something, reset it */ + ctx->pos--; + goto out; } /** @@ -883,7 +874,7 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode } if (size) { - ei->d_children = kzalloc(sizeof(*ei->d_children) * size, GFP_KERNEL); + ei->d_children = kcalloc(size, sizeof(*ei->d_children), GFP_KERNEL); if (!ei->d_children) { kfree_const(ei->name); kfree(ei); @@ -950,7 +941,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry goto fail; if (size) { - ei->d_children = kzalloc(sizeof(*ei->d_children) * size, GFP_KERNEL); + ei->d_children = kcalloc(size, sizeof(*ei->d_children), GFP_KERNEL); if (!ei->d_children) goto fail; } @@ -968,6 +959,14 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry uid = d_inode(dentry->d_parent)->i_uid; gid = d_inode(dentry->d_parent)->i_gid; + /* + * If the events directory is of the top instance, then parent + * is NULL. Set the attr.mode to reflect this and its permissions will + * default to the tracefs root dentry. + */ + if (!parent) + ei->attr.mode = EVENTFS_TOPLEVEL; + /* This is used as the default ownership of the files and directories */ ei->attr.uid = uid; ei->attr.gid = gid; diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index ad20e6af938d..e1b172c0e091 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -91,6 +91,7 @@ static int tracefs_syscall_mkdir(struct mnt_idmap *idmap, struct inode *inode, struct dentry *dentry, umode_t mode) { + struct tracefs_inode *ti; char *name; int ret; @@ -99,6 +100,15 @@ static int tracefs_syscall_mkdir(struct mnt_idmap *idmap, return -ENOMEM; /* + * This is a new directory that does not take the default of + * the rootfs. It becomes the default permissions for all the + * files and directories underneath it. + */ + ti = get_tracefs(inode); + ti->flags |= TRACEFS_INSTANCE_INODE; + ti->private = inode; + + /* * The mkdir call can call the generic functions that create * the files within the tracefs system. It is up to the individual * mkdir routine to handle races. @@ -141,10 +151,76 @@ static int tracefs_syscall_rmdir(struct inode *inode, struct dentry *dentry) return ret; } -static const struct inode_operations tracefs_dir_inode_operations = { +static void set_tracefs_inode_owner(struct inode *inode) +{ + struct tracefs_inode *ti = get_tracefs(inode); + struct inode *root_inode = ti->private; + + /* + * If this inode has never been referenced, then update + * the permissions to the superblock. + */ + if (!(ti->flags & TRACEFS_UID_PERM_SET)) + inode->i_uid = root_inode->i_uid; + + if (!(ti->flags & TRACEFS_GID_PERM_SET)) + inode->i_gid = root_inode->i_gid; +} + +static int tracefs_permission(struct mnt_idmap *idmap, + struct inode *inode, int mask) +{ + set_tracefs_inode_owner(inode); + return generic_permission(idmap, inode, mask); +} + +static int tracefs_getattr(struct mnt_idmap *idmap, + const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int flags) +{ + struct inode *inode = d_backing_inode(path->dentry); + + set_tracefs_inode_owner(inode); + generic_fillattr(idmap, request_mask, inode, stat); + return 0; +} + +static int tracefs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, + struct iattr *attr) +{ + unsigned int ia_valid = attr->ia_valid; + struct inode *inode = d_inode(dentry); + struct tracefs_inode *ti = get_tracefs(inode); + + if (ia_valid & ATTR_UID) + ti->flags |= TRACEFS_UID_PERM_SET; + + if (ia_valid & ATTR_GID) + ti->flags |= TRACEFS_GID_PERM_SET; + + return simple_setattr(idmap, dentry, attr); +} + +static const struct inode_operations tracefs_instance_dir_inode_operations = { .lookup = simple_lookup, .mkdir = tracefs_syscall_mkdir, .rmdir = tracefs_syscall_rmdir, + .permission = tracefs_permission, + .getattr = tracefs_getattr, + .setattr = tracefs_setattr, +}; + +static const struct inode_operations tracefs_dir_inode_operations = { + .lookup = simple_lookup, + .permission = tracefs_permission, + .getattr = tracefs_getattr, + .setattr = tracefs_setattr, +}; + +static const struct inode_operations tracefs_file_inode_operations = { + .permission = tracefs_permission, + .getattr = tracefs_getattr, + .setattr = tracefs_setattr, }; struct inode *tracefs_get_inode(struct super_block *sb) @@ -183,82 +259,6 @@ struct tracefs_fs_info { struct tracefs_mount_opts mount_opts; }; -static void change_gid(struct dentry *dentry, kgid_t gid) -{ - if (!dentry->d_inode) - return; - dentry->d_inode->i_gid = gid; -} - -/* - * Taken from d_walk, but without he need for handling renames. - * Nothing can be renamed while walking the list, as tracefs - * does not support renames. This is only called when mounting - * or remounting the file system, to set all the files to - * the given gid. - */ -static void set_gid(struct dentry *parent, kgid_t gid) -{ - struct dentry *this_parent, *dentry; - - this_parent = parent; - spin_lock(&this_parent->d_lock); - - change_gid(this_parent, gid); -repeat: - dentry = d_first_child(this_parent); -resume: - hlist_for_each_entry_from(dentry, d_sib) { - struct tracefs_inode *ti; - - /* Note, getdents() can add a cursor dentry with no inode */ - if (!dentry->d_inode) - continue; - - spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); - - change_gid(dentry, gid); - - /* If this is the events directory, update that too */ - ti = get_tracefs(dentry->d_inode); - if (ti && (ti->flags & TRACEFS_EVENT_INODE)) - eventfs_update_gid(dentry, gid); - - if (!hlist_empty(&dentry->d_children)) { - spin_unlock(&this_parent->d_lock); - spin_release(&dentry->d_lock.dep_map, _RET_IP_); - this_parent = dentry; - spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); - goto repeat; - } - spin_unlock(&dentry->d_lock); - } - /* - * All done at this level ... ascend and resume the search. - */ - rcu_read_lock(); -ascend: - if (this_parent != parent) { - dentry = this_parent; - this_parent = dentry->d_parent; - - spin_unlock(&dentry->d_lock); - spin_lock(&this_parent->d_lock); - - /* go into the first sibling still alive */ - hlist_for_each_entry_continue(dentry, d_sib) { - if (likely(!(dentry->d_flags & DCACHE_DENTRY_KILLED))) { - rcu_read_unlock(); - goto resume; - } - } - goto ascend; - } - rcu_read_unlock(); - spin_unlock(&this_parent->d_lock); - return; -} - static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) { substring_t args[MAX_OPT_ARGS]; @@ -331,10 +331,8 @@ static int tracefs_apply_options(struct super_block *sb, bool remount) if (!remount || opts->opts & BIT(Opt_uid)) inode->i_uid = opts->uid; - if (!remount || opts->opts & BIT(Opt_gid)) { - /* Set all the group ids to the mount option */ - set_gid(sb->s_root, opts->gid); - } + if (!remount || opts->opts & BIT(Opt_gid)) + inode->i_gid = opts->gid; return 0; } @@ -568,6 +566,26 @@ struct dentry *eventfs_end_creating(struct dentry *dentry) return dentry; } +/* Find the inode that this will use for default */ +static struct inode *instance_inode(struct dentry *parent, struct inode *inode) +{ + struct tracefs_inode *ti; + + /* If parent is NULL then use root inode */ + if (!parent) + return d_inode(inode->i_sb->s_root); + + /* Find the inode that is flagged as an instance or the root inode */ + while (!IS_ROOT(parent)) { + ti = get_tracefs(d_inode(parent)); + if (ti->flags & TRACEFS_INSTANCE_INODE) + break; + parent = parent->d_parent; + } + + return d_inode(parent); +} + /** * tracefs_create_file - create a file in the tracefs filesystem * @name: a pointer to a string containing the name of the file to create. @@ -598,6 +616,7 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops) { + struct tracefs_inode *ti; struct dentry *dentry; struct inode *inode; @@ -616,7 +635,11 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode, if (unlikely(!inode)) return tracefs_failed_creating(dentry); + ti = get_tracefs(inode); + ti->private = instance_inode(parent, inode); + inode->i_mode = mode; + inode->i_op = &tracefs_file_inode_operations; inode->i_fop = fops ? fops : &tracefs_file_operations; inode->i_private = data; inode->i_uid = d_inode(dentry->d_parent)->i_uid; @@ -629,6 +652,7 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode, static struct dentry *__create_dir(const char *name, struct dentry *parent, const struct inode_operations *ops) { + struct tracefs_inode *ti; struct dentry *dentry = tracefs_start_creating(name, parent); struct inode *inode; @@ -646,6 +670,9 @@ static struct dentry *__create_dir(const char *name, struct dentry *parent, inode->i_uid = d_inode(dentry->d_parent)->i_uid; inode->i_gid = d_inode(dentry->d_parent)->i_gid; + ti = get_tracefs(inode); + ti->private = instance_inode(parent, inode); + /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); d_instantiate(dentry, inode); @@ -676,7 +703,7 @@ struct dentry *tracefs_create_dir(const char *name, struct dentry *parent) if (security_locked_down(LOCKDOWN_TRACEFS)) return NULL; - return __create_dir(name, parent, &simple_dir_inode_operations); + return __create_dir(name, parent, &tracefs_dir_inode_operations); } /** @@ -707,7 +734,7 @@ __init struct dentry *tracefs_create_instance_dir(const char *name, if (WARN_ON(tracefs_ops.mkdir || tracefs_ops.rmdir)) return NULL; - dentry = __create_dir(name, parent, &tracefs_dir_inode_operations); + dentry = __create_dir(name, parent, &tracefs_instance_dir_inode_operations); if (!dentry) return NULL; diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index 42bdeb471a07..12b7d0150ae9 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -5,6 +5,9 @@ enum { TRACEFS_EVENT_INODE = BIT(1), TRACEFS_EVENT_TOP_INODE = BIT(2), + TRACEFS_GID_PERM_SET = BIT(3), + TRACEFS_UID_PERM_SET = BIT(4), + TRACEFS_INSTANCE_INODE = BIT(5), }; struct tracefs_inode { diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 98aaca933bdd..f362345467fa 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3277,7 +3277,7 @@ xfs_bmap_alloc_account( struct xfs_bmalloca *ap) { bool isrt = XFS_IS_REALTIME_INODE(ap->ip) && - (ap->flags & XFS_BMAPI_ATTRFORK); + !(ap->flags & XFS_BMAPI_ATTRFORK); uint fld; if (ap->flags & XFS_BMAPI_COWFORK) { diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 2b3ae51f950d..e4d24d3f9abb 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -719,6 +719,8 @@ struct acpi_pci_root { /* helper */ +struct iommu_ops; + bool acpi_dma_supported(const struct acpi_device *adev); enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev); int acpi_iommu_fwspec_init(struct device *dev, u32 id, diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h index 84ec53ccc450..7ee8a179d103 100644 --- a/include/asm-generic/cacheflush.h +++ b/include/asm-generic/cacheflush.h @@ -91,6 +91,12 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end) } #endif +#ifndef flush_cache_vmap_early +static inline void flush_cache_vmap_early(unsigned long start, unsigned long end) +{ +} +#endif + #ifndef flush_cache_vunmap static inline void flush_cache_vunmap(unsigned long start, unsigned long end) { diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 118a18b7ff84..b7165e52b3c6 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -15,6 +15,7 @@ #include <linux/mod_devicetable.h> #include <linux/property.h> #include <linux/uuid.h> +#include <linux/node.h> struct irq_domain; struct irq_domain_ops; @@ -431,6 +432,16 @@ int thermal_acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp); int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp); #endif +#ifdef CONFIG_ACPI_HMAT +int acpi_get_genport_coordinates(u32 uid, struct access_coordinate *coord); +#else +static inline int acpi_get_genport_coordinates(u32 uid, + struct access_coordinate *coord) +{ + return -EOPNOTSUPP; +} +#endif + #ifdef CONFIG_ACPI_NUMA int acpi_map_pxm_to_node(int pxm); int acpi_get_node(acpi_handle handle); diff --git a/include/linux/bio.h b/include/linux/bio.h index ec4db73e5f4e..875d792bffff 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -286,6 +286,11 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio, { struct bio_vec *bvec = bio_first_bvec_all(bio) + i; + if (unlikely(i >= bio->bi_vcnt)) { + fi->folio = NULL; + return; + } + fi->folio = page_folio(bvec->bv_page); fi->offset = bvec->bv_offset + PAGE_SIZE * (bvec->bv_page - &fi->folio->page); @@ -303,10 +308,8 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) fi->offset = 0; fi->length = min(folio_size(fi->folio), fi->_seg_count); fi->_next = folio_next(fi->folio); - } else if (fi->_i + 1 < bio->bi_vcnt) { - bio_first_folio(fi, bio, fi->_i + 1); } else { - fi->folio = NULL; + bio_first_folio(fi, bio, fi->_i + 1); } } diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index a676e116085f..7a8150a5f051 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -391,9 +391,6 @@ struct blk_mq_hw_ctx { */ struct blk_mq_tags *sched_tags; - /** @run: Number of dispatched requests. */ - unsigned long run; - /** @numa_node: NUMA node the storage adapter has been connected to. */ unsigned int numa_node; /** @queue_num: Index of this hardware queue. */ diff --git a/include/linux/btf.h b/include/linux/btf.h index 59d404e22814..cf5c6ff48981 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -512,7 +512,7 @@ s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id); int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, struct module *owner); struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id); -const struct btf_member * +const struct btf_type * btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, enum bpf_prog_type prog_type, int arg); diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index b8610e9d2471..fa018d5864e7 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -572,9 +572,12 @@ int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt); */ #define CEPH_SPARSE_EXT_ARRAY_INITIAL 16 -static inline int ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op) +static inline int ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt) { - return __ceph_alloc_sparse_ext_map(op, CEPH_SPARSE_EXT_ARRAY_INITIAL); + if (!cnt) + cnt = CEPH_SPARSE_EXT_ARRAY_INITIAL; + + return __ceph_alloc_sparse_ext_map(op, cnt); } extern void ceph_osdc_get_request(struct ceph_osd_request *req); diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h new file mode 100644 index 000000000000..91125eca4c8a --- /dev/null +++ b/include/linux/cxl-event.h @@ -0,0 +1,161 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2023 Intel Corporation. */ +#ifndef _LINUX_CXL_EVENT_H +#define _LINUX_CXL_EVENT_H + +/* + * Common Event Record Format + * CXL rev 3.0 section 8.2.9.2.1; Table 8-42 + */ +struct cxl_event_record_hdr { + u8 length; + u8 flags[3]; + __le16 handle; + __le16 related_handle; + __le64 timestamp; + u8 maint_op_class; + u8 reserved[15]; +} __packed; + +#define CXL_EVENT_RECORD_DATA_LENGTH 0x50 +struct cxl_event_generic { + struct cxl_event_record_hdr hdr; + u8 data[CXL_EVENT_RECORD_DATA_LENGTH]; +} __packed; + +/* + * General Media Event Record + * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 + */ +#define CXL_EVENT_GEN_MED_COMP_ID_SIZE 0x10 +struct cxl_event_gen_media { + struct cxl_event_record_hdr hdr; + __le64 phys_addr; + u8 descriptor; + u8 type; + u8 transaction_type; + u8 validity_flags[2]; + u8 channel; + u8 rank; + u8 device[3]; + u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE]; + u8 reserved[46]; +} __packed; + +/* + * DRAM Event Record - DER + * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44 + */ +#define CXL_EVENT_DER_CORRECTION_MASK_SIZE 0x20 +struct cxl_event_dram { + struct cxl_event_record_hdr hdr; + __le64 phys_addr; + u8 descriptor; + u8 type; + u8 transaction_type; + u8 validity_flags[2]; + u8 channel; + u8 rank; + u8 nibble_mask[3]; + u8 bank_group; + u8 bank; + u8 row[3]; + u8 column[2]; + u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE]; + u8 reserved[0x17]; +} __packed; + +/* + * Get Health Info Record + * CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100 + */ +struct cxl_get_health_info { + u8 health_status; + u8 media_status; + u8 add_status; + u8 life_used; + u8 device_temp[2]; + u8 dirty_shutdown_cnt[4]; + u8 cor_vol_err_cnt[4]; + u8 cor_per_err_cnt[4]; +} __packed; + +/* + * Memory Module Event Record + * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45 + */ +struct cxl_event_mem_module { + struct cxl_event_record_hdr hdr; + u8 event_type; + struct cxl_get_health_info info; + u8 reserved[0x3d]; +} __packed; + +union cxl_event { + struct cxl_event_generic generic; + struct cxl_event_gen_media gen_media; + struct cxl_event_dram dram; + struct cxl_event_mem_module mem_module; +} __packed; + +/* + * Common Event Record Format; in event logs + * CXL rev 3.0 section 8.2.9.2.1; Table 8-42 + */ +struct cxl_event_record_raw { + uuid_t id; + union cxl_event event; +} __packed; + +enum cxl_event_type { + CXL_CPER_EVENT_GENERIC, + CXL_CPER_EVENT_GEN_MEDIA, + CXL_CPER_EVENT_DRAM, + CXL_CPER_EVENT_MEM_MODULE, +}; + +#define CPER_CXL_DEVICE_ID_VALID BIT(0) +#define CPER_CXL_DEVICE_SN_VALID BIT(1) +#define CPER_CXL_COMP_EVENT_LOG_VALID BIT(2) +struct cxl_cper_event_rec { + struct { + u32 length; + u64 validation_bits; + struct cper_cxl_event_devid { + u16 vendor_id; + u16 device_id; + u8 func_num; + u8 device_num; + u8 bus_num; + u16 segment_num; + u16 slot_num; /* bits 2:0 reserved */ + u8 reserved; + } __packed device_id; + struct cper_cxl_event_sn { + u32 lower_dw; + u32 upper_dw; + } __packed dev_serial_num; + } __packed hdr; + + union cxl_event event; +} __packed; + +typedef void (*cxl_cper_callback)(enum cxl_event_type type, + struct cxl_cper_event_rec *rec); + +#ifdef CONFIG_ACPI_APEI_GHES +int cxl_cper_register_callback(cxl_cper_callback callback); +int cxl_cper_unregister_callback(cxl_cper_callback callback); +#else +static inline int cxl_cper_register_callback(cxl_cper_callback callback) +{ + return 0; +} + +static inline int cxl_cper_unregister_callback(cxl_cper_callback callback) +{ + return 0; +} +#endif + +#endif /* _LINUX_CXL_EVENT_H */ diff --git a/include/linux/device.h b/include/linux/device.h index 58af8307c7dd..97c4b046c09d 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -42,7 +42,6 @@ struct class; struct subsys_private; struct device_node; struct fwnode_handle; -struct iommu_ops; struct iommu_group; struct dev_pin_info; struct dev_iommu; diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 25127f750349..5ef4ec1c36c3 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -62,9 +62,6 @@ struct fwnode_handle; * this bus. * @pm: Power management operations of this bus, callback the specific * device driver's pm-ops. - * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU - * driver implementations to a bus and allow the driver to do - * bus-specific setup * @need_parent_lock: When probing or removing a device on this bus, the * device core should lock the device's parent. * @@ -104,8 +101,6 @@ struct bus_type { const struct dev_pm_ops *pm; - const struct iommu_ops *iommu_ops; - bool need_parent_lock; }; diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index e401f824a007..4abc60f04209 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -11,6 +11,7 @@ #include <linux/slab.h> struct cma; +struct iommu_ops; /* * Values for struct dma_map_ops.flags: @@ -426,10 +427,10 @@ bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg, #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent); + bool coherent); #else static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, - u64 size, const struct iommu_ops *iommu, bool coherent) + u64 size, bool coherent) { } #endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */ diff --git a/include/linux/export.h b/include/linux/export.h index 9911508a9604..0bbd02fd351d 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -7,15 +7,6 @@ #include <linux/stringify.h> /* - * Export symbols from the kernel to modules. Forked from module.h - * to reduce the amount of pointless cruft we feed to gcc when only - * exporting a simple symbol or two. - * - * Try not to add #includes here. It slows compilation and makes kernel - * hackers place grumpy comments in header files. - */ - -/* * This comment block is used by fixdep. Please do not remove. * * When CONFIG_MODVERSIONS is changed from n to y, all source files having @@ -23,15 +14,6 @@ * side effect of the *.o build rule. */ -#ifndef __ASSEMBLY__ -#ifdef MODULE -extern struct module __this_module; -#define THIS_MODULE (&__this_module) -#else -#define THIS_MODULE ((struct module *)0) -#endif -#endif /* __ASSEMBLY__ */ - #ifdef CONFIG_64BIT #define __EXPORT_SYMBOL_REF(sym) \ .balign 8 ASM_NL \ diff --git a/include/linux/fs.h b/include/linux/fs.h index e6ba0cc6f2ee..ed5966a70495 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2371,7 +2371,7 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_CREATING (1 << 15) #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) -#define I_PINNING_FSCACHE_WB (1 << 18) +#define I_PINNING_NETFS_WB (1 << 18) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index a174cedf4d90..bdf7f3eddf0a 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -189,17 +189,20 @@ extern atomic_t fscache_n_write; extern atomic_t fscache_n_no_write_space; extern atomic_t fscache_n_no_create_space; extern atomic_t fscache_n_culled; +extern atomic_t fscache_n_dio_misfit; #define fscache_count_read() atomic_inc(&fscache_n_read) #define fscache_count_write() atomic_inc(&fscache_n_write) #define fscache_count_no_write_space() atomic_inc(&fscache_n_no_write_space) #define fscache_count_no_create_space() atomic_inc(&fscache_n_no_create_space) #define fscache_count_culled() atomic_inc(&fscache_n_culled) +#define fscache_count_dio_misfit() atomic_inc(&fscache_n_dio_misfit) #else #define fscache_count_read() do {} while(0) #define fscache_count_write() do {} while(0) #define fscache_count_no_write_space() do {} while(0) #define fscache_count_no_create_space() do {} while(0) #define fscache_count_culled() do {} while(0) +#define fscache_count_dio_misfit() do {} while(0) #endif #endif /* _LINUX_FSCACHE_CACHE_H */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 8e312c8323a8..6e8562cbcc43 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -437,9 +437,6 @@ const struct netfs_cache_ops *fscache_operation_valid(const struct netfs_cache_r * indicates the cache resources to which the operation state should be * attached; @cookie indicates the cache object that will be accessed. * - * This is intended to be called from the ->begin_cache_operation() netfs lib - * operation as implemented by the network filesystem. - * * @cres->inval_counter is set from @cookie->inval_counter for comparison at * the end of the operation. This allows invalidation during the operation to * be detected by the caller. @@ -629,48 +626,6 @@ static inline void fscache_write_to_cache(struct fscache_cookie *cookie, } -#if __fscache_available -bool fscache_dirty_folio(struct address_space *mapping, struct folio *folio, - struct fscache_cookie *cookie); -#else -#define fscache_dirty_folio(MAPPING, FOLIO, COOKIE) \ - filemap_dirty_folio(MAPPING, FOLIO) -#endif - -/** - * fscache_unpin_writeback - Unpin writeback resources - * @wbc: The writeback control - * @cookie: The cookie referring to the cache object - * - * Unpin the writeback resources pinned by fscache_dirty_folio(). This is - * intended to be called by the netfs's ->write_inode() method. - */ -static inline void fscache_unpin_writeback(struct writeback_control *wbc, - struct fscache_cookie *cookie) -{ - if (wbc->unpinned_fscache_wb) - fscache_unuse_cookie(cookie, NULL, NULL); -} - -/** - * fscache_clear_inode_writeback - Clear writeback resources pinned by an inode - * @cookie: The cookie referring to the cache object - * @inode: The inode to clean up - * @aux: Auxiliary data to apply to the inode - * - * Clear any writeback resources held by an inode when the inode is evicted. - * This must be called before clear_inode() is called. - */ -static inline void fscache_clear_inode_writeback(struct fscache_cookie *cookie, - struct inode *inode, - const void *aux) -{ - if (inode->i_state & I_PINNING_FSCACHE_WB) { - loff_t i_size = i_size_read(inode); - fscache_unuse_cookie(cookie, aux, &i_size); - } -} - /** * fscache_note_page_release - Note that a netfs page got released * @cookie: The cookie corresponding to the file diff --git a/include/linux/fw_table.h b/include/linux/fw_table.h index ca49947f0a77..95421860397a 100644 --- a/include/linux/fw_table.h +++ b/include/linux/fw_table.h @@ -25,16 +25,35 @@ struct acpi_subtable_proc { int count; }; +union fw_table_header { + struct acpi_table_header acpi; + struct acpi_table_cdat cdat; +}; + union acpi_subtable_headers { struct acpi_subtable_header common; struct acpi_hmat_structure hmat; struct acpi_prmt_module_header prmt; struct acpi_cedt_header cedt; + struct acpi_cdat_header cdat; }; int acpi_parse_entries_array(char *id, unsigned long table_size, - struct acpi_table_header *table_header, + union fw_table_header *table_header, struct acpi_subtable_proc *proc, int proc_num, unsigned int max_entries); +int cdat_table_parse(enum acpi_cdat_type type, + acpi_tbl_entry_handler_arg handler_arg, void *arg, + struct acpi_table_cdat *table_header); + +/* CXL is the only non-ACPI consumer of the FIRMWARE_TABLE library */ +#if IS_ENABLED(CONFIG_ACPI) && !IS_ENABLED(CONFIG_CXL_BUS) +#define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_ACPI_LIB(x) +#define __init_or_fwtbl_lib __init_or_acpilib +#else +#define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_NS_GPL(x, CXL) +#define __init_or_fwtbl_lib +#endif + #endif diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index e846bd4e7559..9a5c6c76e653 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -635,7 +635,7 @@ struct gpio_device *gpio_device_get(struct gpio_device *gdev); void gpio_device_put(struct gpio_device *gdev); DEFINE_FREE(gpio_device_put, struct gpio_device *, - if (IS_ERR_OR_NULL(_T)) gpio_device_put(_T)); + if (!IS_ERR_OR_NULL(_T)) gpio_device_put(_T)) struct device *gpio_device_to_device(struct gpio_device *gdev); diff --git a/include/linux/gpio_keys.h b/include/linux/gpio_keys.h index 3f84aeb81e48..80fa930b04c6 100644 --- a/include/linux/gpio_keys.h +++ b/include/linux/gpio_keys.h @@ -21,6 +21,7 @@ struct device; * disable button via sysfs * @value: axis value for %EV_ABS * @irq: Irq number in case of interrupt keys + * @wakeirq: Optional dedicated wake-up interrupt */ struct gpio_keys_button { unsigned int code; @@ -34,6 +35,7 @@ struct gpio_keys_button { bool can_disable; int value; unsigned int irq; + unsigned int wakeirq; }; /** diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 0dae9db27538..652ecb7abeda 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -23,7 +23,7 @@ #include <linux/swab.h> /* for swab16 */ #include <uapi/linux/i2c.h> -extern struct bus_type i2c_bus_type; +extern const struct bus_type i2c_bus_type; extern struct device_type i2c_adapter_type; extern struct device_type i2c_client_type; @@ -746,6 +746,8 @@ struct i2c_adapter { struct irq_domain *host_notify_domain; struct regulator *bus_regulator; + + struct dentry *debugfs; }; #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev) @@ -850,7 +852,6 @@ static inline void i2c_mark_adapter_resumed(struct i2c_adapter *adap) /* i2c adapter classes (bitmask) */ #define I2C_CLASS_HWMON (1<<0) /* lm_sensors, ... */ -#define I2C_CLASS_DDC (1<<3) /* DDC bus on graphics adapters */ #define I2C_CLASS_SPD (1<<7) /* Memory modules */ /* Warn users that the adapter doesn't support classes anymore */ #define I2C_CLASS_DEPRECATED (1<<8) diff --git a/include/linux/init.h b/include/linux/init.h index 01b52c9c7526..3fa3f6241350 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -179,6 +179,13 @@ extern void (*late_time_init)(void); extern bool initcall_debug; +#ifdef MODULE +extern struct module __this_module; +#define THIS_MODULE (&__this_module) +#else +#define THIS_MODULE ((struct module *)0) +#endif + #endif #ifndef MODULE diff --git a/include/linux/input/as5011.h b/include/linux/input/as5011.h index 5fba52a56cd6..5705d5de3aea 100644 --- a/include/linux/input/as5011.h +++ b/include/linux/input/as5011.h @@ -7,7 +7,6 @@ */ struct as5011_platform_data { - unsigned int button_gpio; unsigned int axis_irq; /* irq number */ unsigned long axis_irqflags; char xp, xn; /* threshold for x axis */ diff --git a/include/linux/input/navpoint.h b/include/linux/input/navpoint.h index d464ffb4db52..5192ae3f5ec1 100644 --- a/include/linux/input/navpoint.h +++ b/include/linux/input/navpoint.h @@ -5,5 +5,4 @@ struct navpoint_platform_data { int port; /* PXA SSP port for pxa_ssp_request() */ - int gpio; /* GPIO for power on/off */ }; diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 25142a0e2fc2..86cf1f7ae389 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -100,6 +100,30 @@ struct io_pgtable_cfg { const struct iommu_flush_ops *tlb; struct device *iommu_dev; + /** + * @alloc: Custom page allocator. + * + * Optional hook used to allocate page tables. If this function is NULL, + * @free must be NULL too. + * + * Memory returned should be zeroed and suitable for dma_map_single() and + * virt_to_phys(). + * + * Not all formats support custom page allocators. Before considering + * passing a non-NULL value, make sure the chosen page format supports + * this feature. + */ + void *(*alloc)(void *cookie, size_t size, gfp_t gfp); + + /** + * @free: Custom page de-allocator. + * + * Optional hook used to free page tables allocated with the @alloc + * hook. Must be non-NULL if @alloc is not NULL, must be NULL + * otherwise. + */ + void (*free)(void *cookie, void *pages, size_t size); + /* Low-level data specific to the table format */ union { struct { @@ -242,15 +266,25 @@ io_pgtable_tlb_add_page(struct io_pgtable *iop, } /** + * enum io_pgtable_caps - IO page table backend capabilities. + */ +enum io_pgtable_caps { + /** @IO_PGTABLE_CAP_CUSTOM_ALLOCATOR: Backend accepts custom page table allocators. */ + IO_PGTABLE_CAP_CUSTOM_ALLOCATOR = BIT(0), +}; + +/** * struct io_pgtable_init_fns - Alloc/free a set of page tables for a * particular format. * * @alloc: Allocate a set of page tables described by cfg. * @free: Free the page tables associated with iop. + * @caps: Combination of @io_pgtable_caps flags encoding the backend capabilities. */ struct io_pgtable_init_fns { struct io_pgtable *(*alloc)(struct io_pgtable_cfg *cfg, void *cookie); void (*free)(struct io_pgtable *iop); + u32 caps; }; extern struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 6291aa7b079b..1ea2a820e1eb 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -106,7 +106,7 @@ struct iommu_domain { unsigned type; const struct iommu_domain_ops *ops; const struct iommu_dirty_ops *dirty_ops; - + const struct iommu_ops *owner; /* Whose domain_alloc we came from */ unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ struct iommu_domain_geometry geometry; struct iommu_dma_cookie *iova_cookie; @@ -121,6 +121,11 @@ struct iommu_domain { struct { /* IOMMU_DOMAIN_SVA */ struct mm_struct *mm; int users; + /* + * Next iommu_domain in mm->iommu_mm->sva-domains list + * protected by iommu_sva_lock. + */ + struct list_head next; }; }; }; @@ -285,6 +290,23 @@ struct iommu_user_data { }; /** + * struct iommu_user_data_array - iommu driver specific user space data array + * @type: The data type of all the entries in the user buffer array + * @uptr: Pointer to the user buffer array + * @entry_len: The fixed-width length of an entry in the array, in bytes + * @entry_num: The number of total entries in the array + * + * The user buffer includes an array of requests with format defined in + * include/uapi/linux/iommufd.h + */ +struct iommu_user_data_array { + unsigned int type; + void __user *uptr; + size_t entry_len; + u32 entry_num; +}; + +/** * __iommu_copy_struct_from_user - Copy iommu driver specific user space data * @dst_data: Pointer to an iommu driver specific user data that is defined in * include/uapi/linux/iommufd.h @@ -325,6 +347,57 @@ static inline int __iommu_copy_struct_from_user( offsetofend(typeof(*kdst), min_last)) /** + * __iommu_copy_struct_from_user_array - Copy iommu driver specific user space + * data from an iommu_user_data_array + * @dst_data: Pointer to an iommu driver specific user data that is defined in + * include/uapi/linux/iommufd.h + * @src_array: Pointer to a struct iommu_user_data_array for a user space array + * @data_type: The data type of the @dst_data. Must match with @src_array.type + * @index: Index to the location in the array to copy user data from + * @data_len: Length of current user data structure, i.e. sizeof(struct _dst) + * @min_len: Initial length of user data structure for backward compatibility. + * This should be offsetofend using the last member in the user data + * struct that was initially added to include/uapi/linux/iommufd.h + */ +static inline int __iommu_copy_struct_from_user_array( + void *dst_data, const struct iommu_user_data_array *src_array, + unsigned int data_type, unsigned int index, size_t data_len, + size_t min_len) +{ + struct iommu_user_data src_data; + + if (WARN_ON(!src_array || index >= src_array->entry_num)) + return -EINVAL; + if (!src_array->entry_num) + return -EINVAL; + src_data.uptr = src_array->uptr + src_array->entry_len * index; + src_data.len = src_array->entry_len; + src_data.type = src_array->type; + + return __iommu_copy_struct_from_user(dst_data, &src_data, data_type, + data_len, min_len); +} + +/** + * iommu_copy_struct_from_user_array - Copy iommu driver specific user space + * data from an iommu_user_data_array + * @kdst: Pointer to an iommu driver specific user data that is defined in + * include/uapi/linux/iommufd.h + * @user_array: Pointer to a struct iommu_user_data_array for a user space + * array + * @data_type: The data type of the @kdst. Must match with @user_array->type + * @index: Index to the location in the array to copy user data from + * @min_last: The last member of the data structure @kdst points in the + * initial version. + * Return 0 for success, otherwise -error. + */ +#define iommu_copy_struct_from_user_array(kdst, user_array, data_type, index, \ + min_last) \ + __iommu_copy_struct_from_user_array( \ + kdst, user_array, data_type, index, sizeof(*(kdst)), \ + offsetofend(typeof(*(kdst)), min_last)) + +/** * struct iommu_ops - iommu ops and capabilities * @capable: check capability * @hw_info: report iommu hardware information. The data buffer returned by this @@ -440,6 +513,13 @@ struct iommu_ops { * @iotlb_sync_map: Sync mappings created recently using @map to the hardware * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush * queue + * @cache_invalidate_user: Flush hardware cache for user space IO page table. + * The @domain must be IOMMU_DOMAIN_NESTED. The @array + * passes in the cache invalidation requests, in form + * of a driver data structure. The driver must update + * array->entry_num to report the number of handled + * invalidation requests. The driver data structure + * must be defined in include/uapi/linux/iommufd.h * @iova_to_phys: translate iova to physical address * @enforce_cache_coherency: Prevent any kind of DMA from bypassing IOMMU_CACHE, * including no-snoop TLPs on PCIe or other platform @@ -465,6 +545,8 @@ struct iommu_domain_ops { size_t size); void (*iotlb_sync)(struct iommu_domain *domain, struct iommu_iotlb_gather *iotlb_gather); + int (*cache_invalidate_user)(struct iommu_domain *domain, + struct iommu_user_data_array *array); phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); @@ -812,6 +894,11 @@ struct iommu_sva { struct iommu_domain *domain; }; +struct iommu_mm_data { + u32 pasid; + struct list_head sva_domains; +}; + int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, const struct iommu_ops *ops); void iommu_fwspec_free(struct device *dev); @@ -840,10 +927,7 @@ static inline void *dev_iommu_priv_get(struct device *dev) return NULL; } -static inline void dev_iommu_priv_set(struct device *dev, void *priv) -{ - dev->iommu->priv = priv; -} +void dev_iommu_priv_set(struct device *dev, void *priv); extern struct mutex iommu_probe_device_lock; int iommu_probe_device(struct device *dev); @@ -1337,15 +1421,33 @@ static inline bool tegra_dev_iommu_get_stream_id(struct device *dev, u32 *stream return false; } -#ifdef CONFIG_IOMMU_SVA +#ifdef CONFIG_IOMMU_MM_DATA static inline void mm_pasid_init(struct mm_struct *mm) { - mm->pasid = IOMMU_PASID_INVALID; + /* + * During dup_mm(), a new mm will be memcpy'd from an old one and that makes + * the new mm and the old one point to a same iommu_mm instance. When either + * one of the two mms gets released, the iommu_mm instance is freed, leaving + * the other mm running into a use-after-free/double-free problem. To avoid + * the problem, zeroing the iommu_mm pointer of a new mm is needed here. + */ + mm->iommu_mm = NULL; } + static inline bool mm_valid_pasid(struct mm_struct *mm) { - return mm->pasid != IOMMU_PASID_INVALID; + return READ_ONCE(mm->iommu_mm); +} + +static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm) +{ + struct iommu_mm_data *iommu_mm = READ_ONCE(mm->iommu_mm); + + if (!iommu_mm) + return IOMMU_PASID_INVALID; + return iommu_mm->pasid; } + void mm_pasid_drop(struct mm_struct *mm); struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm); @@ -1368,6 +1470,12 @@ static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle) } static inline void mm_pasid_init(struct mm_struct *mm) {} static inline bool mm_valid_pasid(struct mm_struct *mm) { return false; } + +static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm) +{ + return IOMMU_PASID_INVALID; +} + static inline void mm_pasid_drop(struct mm_struct *mm) {} #endif /* CONFIG_IOMMU_SVA */ diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index 7578d4f6a969..db1249cd9692 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -47,7 +47,30 @@ static inline int task_nice_ioclass(struct task_struct *task) } #ifdef CONFIG_BLOCK -int __get_task_ioprio(struct task_struct *p); +/* + * If the task has set an I/O priority, use that. Otherwise, return + * the default I/O priority. + * + * Expected to be called for current task or with task_lock() held to keep + * io_context stable. + */ +static inline int __get_task_ioprio(struct task_struct *p) +{ + struct io_context *ioc = p->io_context; + int prio; + + if (!ioc) + return IOPRIO_DEFAULT; + + if (p != current) + lockdep_assert_held(&p->alloc_lock); + + prio = ioc->ioprio; + if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE) + prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p), + task_nice_ioprio(p)); + return prio; +} #else static inline int __get_task_ioprio(struct task_struct *p) { diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h index b0da04fe087b..34dfcc77f505 100644 --- a/include/linux/mc146818rtc.h +++ b/include/linux/mc146818rtc.h @@ -126,10 +126,11 @@ struct cmos_rtc_board_info { #endif /* ARCH_RTC_LOCATION */ bool mc146818_does_rtc_work(void); -int mc146818_get_time(struct rtc_time *time); +int mc146818_get_time(struct rtc_time *time, int timeout); int mc146818_set_time(struct rtc_time *time); bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param), + int timeout, void *param); #endif /* _MC146818RTC_H */ diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 1e39d27bee41..69e781900082 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -33,7 +33,7 @@ struct memory_dev_type { struct kref kref; }; -struct node_hmem_attrs; +struct access_coordinate; #ifdef CONFIG_NUMA extern bool numa_demotion_enabled; @@ -45,9 +45,9 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype); int register_mt_adistance_algorithm(struct notifier_block *nb); int unregister_mt_adistance_algorithm(struct notifier_block *nb); int mt_calc_adistance(int node, int *adist); -int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf, +int mt_set_default_dram_perf(int nid, struct access_coordinate *perf, const char *source); -int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist); +int mt_perf_to_adistance(struct access_coordinate *perf, int *adist); #ifdef CONFIG_MIGRATION int next_demotion_node(int node); void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets); @@ -126,13 +126,13 @@ static inline int mt_calc_adistance(int node, int *adist) return NOTIFY_DONE; } -static inline int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf, +static inline int mt_set_default_dram_perf(int nid, struct access_coordinate *perf, const char *source) { return -EIO; } -static inline int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist) +static inline int mt_perf_to_adistance(struct access_coordinate *perf, int *adist) { return -EIO; } diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 7235f3eaed8b..bf5320b28b8b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1241,7 +1241,8 @@ struct mlx5_ifc_virtio_emulation_cap_bits { u8 reserved_at_c0[0x13]; u8 desc_group_mkey_supported[0x1]; - u8 reserved_at_d4[0xc]; + u8 freeze_to_rdy_supported[0x1]; + u8 reserved_at_d5[0xb]; u8 reserved_at_e0[0x20]; diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h index b86d51a855f6..40371c916cf9 100644 --- a/include/linux/mlx5/mlx5_ifc_vdpa.h +++ b/include/linux/mlx5/mlx5_ifc_vdpa.h @@ -145,6 +145,10 @@ enum { MLX5_VIRTQ_MODIFY_MASK_STATE = (u64)1 << 0, MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_PARAMS = (u64)1 << 3, MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_DUMP_ENABLE = (u64)1 << 4, + MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS = (u64)1 << 6, + MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX = (u64)1 << 7, + MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX = (u64)1 << 8, + MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY = (u64)1 << 11, MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY = (u64)1 << 14, }; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index b2d3a88a34d1..8b611e13153e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -730,6 +730,7 @@ struct mm_cid { #endif struct kioctx_table; +struct iommu_mm_data; struct mm_struct { struct { /* @@ -941,8 +942,8 @@ struct mm_struct { #endif struct work_struct async_put_work; -#ifdef CONFIG_IOMMU_SVA - u32 pasid; +#ifdef CONFIG_IOMMU_MM_DATA + struct iommu_mm_data *iommu_mm; #endif #ifdef CONFIG_KSM /* diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index f980edfdd278..743475ca7e9d 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -42,7 +42,7 @@ static inline int nf_bridge_get_physinif(const struct sk_buff *skb) if (!nf_bridge) return 0; - return nf_bridge->physindev ? nf_bridge->physindev->ifindex : 0; + return nf_bridge->physinif; } static inline int nf_bridge_get_physoutif(const struct sk_buff *skb) @@ -56,11 +56,11 @@ static inline int nf_bridge_get_physoutif(const struct sk_buff *skb) } static inline struct net_device * -nf_bridge_get_physindev(const struct sk_buff *skb) +nf_bridge_get_physindev(const struct sk_buff *skb, struct net *net) { const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); - return nf_bridge ? nf_bridge->physindev : NULL; + return nf_bridge ? dev_get_by_index_rcu(net, nf_bridge->physinif) : NULL; } static inline struct net_device * diff --git a/include/linux/netfs.h b/include/linux/netfs.h index b11a84f6c32b..100cbb261269 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -109,11 +109,18 @@ static inline int wait_on_page_fscache_killable(struct page *page) return folio_wait_private_2_killable(page_folio(page)); } +/* Marks used on xarray-based buffers */ +#define NETFS_BUF_PUT_MARK XA_MARK_0 /* - Page needs putting */ +#define NETFS_BUF_PAGECACHE_MARK XA_MARK_1 /* - Page needs wb/dirty flag wrangling */ + enum netfs_io_source { NETFS_FILL_WITH_ZEROES, NETFS_DOWNLOAD_FROM_SERVER, NETFS_READ_FROM_CACHE, NETFS_INVALID_READ, + NETFS_UPLOAD_TO_SERVER, + NETFS_WRITE_TO_CACHE, + NETFS_INVALID_WRITE, } __mode(byte); typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error, @@ -129,9 +136,57 @@ struct netfs_inode { struct fscache_cookie *cache; #endif loff_t remote_i_size; /* Size of the remote file */ + loff_t zero_point; /* Size after which we assume there's no data + * on the server */ + unsigned long flags; +#define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ +#define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ +#define NETFS_ICTX_WRITETHROUGH 2 /* Write-through caching */ +#define NETFS_ICTX_NO_WRITE_STREAMING 3 /* Don't engage in write-streaming */ +}; + +/* + * A netfs group - for instance a ceph snap. This is marked on dirty pages and + * pages marked with a group must be flushed before they can be written under + * the domain of another group. + */ +struct netfs_group { + refcount_t ref; + void (*free)(struct netfs_group *netfs_group); }; /* + * Information about a dirty page (attached only if necessary). + * folio->private + */ +struct netfs_folio { + struct netfs_group *netfs_group; /* Filesystem's grouping marker (or NULL). */ + unsigned int dirty_offset; /* Write-streaming dirty data offset */ + unsigned int dirty_len; /* Write-streaming dirty data length */ +}; +#define NETFS_FOLIO_INFO 0x1UL /* OR'd with folio->private. */ + +static inline struct netfs_folio *netfs_folio_info(struct folio *folio) +{ + void *priv = folio_get_private(folio); + + if ((unsigned long)priv & NETFS_FOLIO_INFO) + return (struct netfs_folio *)((unsigned long)priv & ~NETFS_FOLIO_INFO); + return NULL; +} + +static inline struct netfs_group *netfs_folio_group(struct folio *folio) +{ + struct netfs_folio *finfo; + void *priv = folio_get_private(folio); + + finfo = netfs_folio_info(folio); + if (finfo) + return finfo->netfs_group; + return priv; +} + +/* * Resources required to do operations on a cache. */ struct netfs_cache_resources { @@ -143,17 +198,24 @@ struct netfs_cache_resources { }; /* - * Descriptor for a single component subrequest. + * Descriptor for a single component subrequest. Each operation represents an + * individual read/write from/to a server, a cache, a journal, etc.. + * + * The buffer iterator is persistent for the life of the subrequest struct and + * the pages it points to can be relied on to exist for the duration. */ struct netfs_io_subrequest { struct netfs_io_request *rreq; /* Supervising I/O request */ + struct work_struct work; struct list_head rreq_link; /* Link in rreq->subrequests */ + struct iov_iter io_iter; /* Iterator for this subrequest */ loff_t start; /* Where to start the I/O */ size_t len; /* Size of the I/O */ size_t transferred; /* Amount of data transferred */ refcount_t ref; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ + unsigned int max_nr_segs; /* 0 or max number of segments in an iterator */ enum netfs_io_source source; /* Where to read from/write to */ unsigned long flags; #define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ @@ -168,6 +230,13 @@ enum netfs_io_origin { NETFS_READAHEAD, /* This read was triggered by readahead */ NETFS_READPAGE, /* This read is a synchronous read */ NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ + NETFS_WRITEBACK, /* This write was triggered by writepages */ + NETFS_WRITETHROUGH, /* This write was made by netfs_perform_write() */ + NETFS_LAUNDER_WRITE, /* This is triggered by ->launder_folio() */ + NETFS_UNBUFFERED_WRITE, /* This is an unbuffered write */ + NETFS_DIO_READ, /* This is a direct I/O read */ + NETFS_DIO_WRITE, /* This is a direct I/O write */ + nr__netfs_io_origin } __mode(byte); /* @@ -175,19 +244,34 @@ enum netfs_io_origin { * operations to a variety of data stores and then stitch the result together. */ struct netfs_io_request { - struct work_struct work; + union { + struct work_struct work; + struct rcu_head rcu; + }; struct inode *inode; /* The file being accessed */ struct address_space *mapping; /* The mapping being accessed */ + struct kiocb *iocb; /* AIO completion vector */ struct netfs_cache_resources cache_resources; + struct list_head proc_link; /* Link in netfs_iorequests */ struct list_head subrequests; /* Contributory I/O operations */ + struct iov_iter iter; /* Unencrypted-side iterator */ + struct iov_iter io_iter; /* I/O (Encrypted-side) iterator */ void *netfs_priv; /* Private data for the netfs */ + struct bio_vec *direct_bv; /* DIO buffer list (when handling iovec-iter) */ + unsigned int direct_bv_count; /* Number of elements in direct_bv[] */ unsigned int debug_id; + unsigned int rsize; /* Maximum read size (0 for none) */ + unsigned int wsize; /* Maximum write size (0 for none) */ + unsigned int subreq_counter; /* Next subreq->debug_index */ atomic_t nr_outstanding; /* Number of ops in progress */ atomic_t nr_copy_ops; /* Number of copy-to-cache ops in progress */ size_t submitted; /* Amount submitted for I/O so far */ size_t len; /* Length of the request */ + size_t upper_len; /* Length can be extended to here */ + size_t transferred; /* Amount to be indicated as transferred */ short error; /* 0 or error that occurred */ enum netfs_io_origin origin; /* Origin of the request */ + bool direct_bv_unpin; /* T if direct_bv[] must be unpinned */ loff_t i_size; /* Size of the file */ loff_t start; /* Start position */ pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ @@ -199,17 +283,25 @@ struct netfs_io_request { #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ +#define NETFS_RREQ_WRITE_TO_CACHE 7 /* Need to write to the cache */ +#define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ +#define NETFS_RREQ_NONBLOCK 9 /* Don't block if possible (O_NONBLOCK) */ +#define NETFS_RREQ_BLOCKED 10 /* We blocked */ const struct netfs_request_ops *netfs_ops; + void (*cleanup)(struct netfs_io_request *req); }; /* * Operations the network filesystem can/must provide to the helpers. */ struct netfs_request_ops { + unsigned int io_request_size; /* Alloc size for netfs_io_request struct */ + unsigned int io_subrequest_size; /* Alloc size for netfs_io_subrequest struct */ int (*init_request)(struct netfs_io_request *rreq, struct file *file); void (*free_request)(struct netfs_io_request *rreq); - int (*begin_cache_operation)(struct netfs_io_request *rreq); + void (*free_subrequest)(struct netfs_io_subrequest *rreq); + /* Read request handling */ void (*expand_readahead)(struct netfs_io_request *rreq); bool (*clamp_length)(struct netfs_io_subrequest *subreq); void (*issue_read)(struct netfs_io_subrequest *subreq); @@ -217,6 +309,14 @@ struct netfs_request_ops { int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, struct folio **foliop, void **_fsdata); void (*done)(struct netfs_io_request *rreq); + + /* Modification handling */ + void (*update_i_size)(struct inode *inode, loff_t i_size); + + /* Write request handling */ + void (*create_write_requests)(struct netfs_io_request *wreq, + loff_t start, size_t len); + void (*invalidate_cache)(struct netfs_io_request *wreq); }; /* @@ -229,8 +329,7 @@ enum netfs_read_from_hole { }; /* - * Table of operations for access to a cache. This is obtained by - * rreq->ops->begin_cache_operation(). + * Table of operations for access to a cache. */ struct netfs_cache_ops { /* End an operation */ @@ -265,8 +364,8 @@ struct netfs_cache_ops { * actually do. */ int (*prepare_write)(struct netfs_cache_resources *cres, - loff_t *_start, size_t *_len, loff_t i_size, - bool no_space_allocated_yet); + loff_t *_start, size_t *_len, size_t upper_len, + loff_t i_size, bool no_space_allocated_yet); /* Prepare an on-demand read operation, shortening it to a cached/uncached * boundary as appropriate. @@ -284,22 +383,62 @@ struct netfs_cache_ops { loff_t *_data_start, size_t *_data_len); }; +/* High-level read API. */ +ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); +ssize_t netfs_buffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); +ssize_t netfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); + +/* High-level write API */ +ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, + struct netfs_group *netfs_group); +ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *from, + struct netfs_group *netfs_group); +ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from); +ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from); + +/* Address operations API */ struct readahead_control; void netfs_readahead(struct readahead_control *); int netfs_read_folio(struct file *, struct folio *); int netfs_write_begin(struct netfs_inode *, struct file *, - struct address_space *, loff_t pos, unsigned int len, - struct folio **, void **fsdata); - + struct address_space *, loff_t pos, unsigned int len, + struct folio **, void **fsdata); +int netfs_writepages(struct address_space *mapping, + struct writeback_control *wbc); +bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio); +int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc); +void netfs_clear_inode_writeback(struct inode *inode, const void *aux); +void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length); +bool netfs_release_folio(struct folio *folio, gfp_t gfp); +int netfs_launder_folio(struct folio *folio); + +/* VMA operations API. */ +vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group); + +/* (Sub)request management API. */ void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool); void netfs_get_subrequest(struct netfs_io_subrequest *subreq, enum netfs_sreq_ref_trace what); void netfs_put_subrequest(struct netfs_io_subrequest *subreq, bool was_async, enum netfs_sreq_ref_trace what); -void netfs_stats_show(struct seq_file *); ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, struct iov_iter *new, iov_iter_extraction_t extraction_flags); +size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset, + size_t max_size, size_t max_segs); +struct netfs_io_subrequest *netfs_create_write_request( + struct netfs_io_request *wreq, enum netfs_io_source dest, + loff_t start, size_t len, work_func_t worker); +void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error, + bool was_async); +void netfs_queue_write_request(struct netfs_io_subrequest *subreq); + +int netfs_start_io_read(struct inode *inode); +void netfs_end_io_read(struct inode *inode); +int netfs_start_io_write(struct inode *inode); +void netfs_end_io_write(struct inode *inode); +int netfs_start_io_direct(struct inode *inode); +void netfs_end_io_direct(struct inode *inode); /** * netfs_inode - Get the netfs inode context from the inode @@ -317,30 +456,44 @@ static inline struct netfs_inode *netfs_inode(struct inode *inode) * netfs_inode_init - Initialise a netfslib inode context * @ctx: The netfs inode to initialise * @ops: The netfs's operations list + * @use_zero_point: True to use the zero_point read optimisation * * Initialise the netfs library context struct. This is expected to follow on * directly from the VFS inode struct. */ static inline void netfs_inode_init(struct netfs_inode *ctx, - const struct netfs_request_ops *ops) + const struct netfs_request_ops *ops, + bool use_zero_point) { ctx->ops = ops; ctx->remote_i_size = i_size_read(&ctx->inode); + ctx->zero_point = LLONG_MAX; + ctx->flags = 0; #if IS_ENABLED(CONFIG_FSCACHE) ctx->cache = NULL; #endif + /* ->releasepage() drives zero_point */ + if (use_zero_point) { + ctx->zero_point = ctx->remote_i_size; + mapping_set_release_always(ctx->inode.i_mapping); + } } /** * netfs_resize_file - Note that a file got resized * @ctx: The netfs inode being resized * @new_i_size: The new file size + * @changed_on_server: The change was applied to the server * * Inform the netfs lib that a file got resized so that it can adjust its state. */ -static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size) +static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size, + bool changed_on_server) { - ctx->remote_i_size = new_i_size; + if (changed_on_server) + ctx->remote_i_size = new_i_size; + if (new_i_size < ctx->zero_point) + ctx->zero_point = new_i_size; } /** diff --git a/include/linux/node.h b/include/linux/node.h index 427a5975cf40..25b66d705ee2 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -20,14 +20,14 @@ #include <linux/list.h> /** - * struct node_hmem_attrs - heterogeneous memory performance attributes + * struct access_coordinate - generic performance coordinates container * * @read_bandwidth: Read bandwidth in MB/s * @write_bandwidth: Write bandwidth in MB/s * @read_latency: Read latency in nanoseconds * @write_latency: Write latency in nanoseconds */ -struct node_hmem_attrs { +struct access_coordinate { unsigned int read_bandwidth; unsigned int write_bandwidth; unsigned int read_latency; @@ -65,7 +65,7 @@ struct node_cache_attrs { #ifdef CONFIG_HMEM_REPORTING void node_add_cache(unsigned int nid, struct node_cache_attrs *cache_attrs); -void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs, +void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord, unsigned access); #else static inline void node_add_cache(unsigned int nid, @@ -74,7 +74,7 @@ static inline void node_add_cache(unsigned int nid, } static inline void node_set_perf_attrs(unsigned int nid, - struct node_hmem_attrs *hmem_attrs, + struct access_coordinate *coord, unsigned access) { } diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 44325c068b6a..462c21e0e417 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -20,7 +20,6 @@ #define NVMF_TRSVCID_SIZE 32 #define NVMF_TRADDR_SIZE 256 #define NVMF_TSAS_SIZE 256 -#define NVMF_AUTH_HASH_LEN 64 #define NVME_DISC_SUBSYS_NAME "nqn.2014-08.org.nvmexpress.discovery" diff --git a/include/linux/of_device.h b/include/linux/of_device.h index a72661e47faa..9042bca5bb84 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -2,10 +2,7 @@ #ifndef _LINUX_OF_DEVICE_H #define _LINUX_OF_DEVICE_H -#include <linux/platform_device.h> -#include <linux/of_platform.h> /* temporary until merge */ - -#include <linux/of.h> +#include <linux/device/driver.h> struct device; struct of_device_id; diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h index 9a5e6b410dd2..e61cbbe12dac 100644 --- a/include/linux/of_iommu.h +++ b/include/linux/of_iommu.h @@ -8,20 +8,19 @@ struct iommu_ops; #ifdef CONFIG_OF_IOMMU -extern const struct iommu_ops *of_iommu_configure(struct device *dev, - struct device_node *master_np, - const u32 *id); +extern int of_iommu_configure(struct device *dev, struct device_node *master_np, + const u32 *id); extern void of_iommu_get_resv_regions(struct device *dev, struct list_head *list); #else -static inline const struct iommu_ops *of_iommu_configure(struct device *dev, - struct device_node *master_np, - const u32 *id) +static inline int of_iommu_configure(struct device *dev, + struct device_node *master_np, + const u32 *id) { - return NULL; + return -ENODEV; } static inline void of_iommu_get_resv_regions(struct device *dev, diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index fadfea575485..a2ff1ad48f7f 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -7,11 +7,11 @@ */ #include <linux/mod_devicetable.h> -#include <linux/of_device.h> -#include <linux/platform_device.h> struct device; +struct device_node; struct of_device_id; +struct platform_device; /** * struct of_dev_auxdata - lookup table entry for device names & platform_data diff --git a/include/linux/pci.h b/include/linux/pci.h index 99a66bc69a39..add9368e6314 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1171,6 +1171,7 @@ int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge); u8 pci_common_swizzle(struct pci_dev *dev, u8 *pinp); struct pci_dev *pci_dev_get(struct pci_dev *dev); void pci_dev_put(struct pci_dev *dev); +DEFINE_FREE(pci_dev_put, struct pci_dev *, if (_T) pci_dev_put(_T)) void pci_remove_bus(struct pci_bus *b); void pci_stop_and_remove_bus_device(struct pci_dev *dev); void pci_stop_and_remove_bus_device_locked(struct pci_dev *dev); @@ -1367,6 +1368,7 @@ int pcie_set_mps(struct pci_dev *dev, int mps); u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev, enum pci_bus_speed *speed, enum pcie_link_width *width); +int pcie_link_speed_mbps(struct pci_dev *pdev); void pcie_print_link_status(struct pci_dev *dev); int pcie_reset_flr(struct pci_dev *dev, bool probe); int pcie_flr(struct pci_dev *dev); @@ -1877,6 +1879,7 @@ void pci_cfg_access_unlock(struct pci_dev *dev); void pci_dev_lock(struct pci_dev *dev); int pci_dev_trylock(struct pci_dev *dev); void pci_dev_unlock(struct pci_dev *dev); +DEFINE_GUARD(pci_dev, struct pci_dev *, pci_dev_lock(_T), pci_dev_unlock(_T)) /* * PCI domain support. Sometimes called PCI segment (eg by ACPI), diff --git a/include/linux/platform_data/i2c-mux-reg.h b/include/linux/platform_data/i2c-mux-reg.h index 2543c2a1c9ae..e2e895768311 100644 --- a/include/linux/platform_data/i2c-mux-reg.h +++ b/include/linux/platform_data/i2c-mux-reg.h @@ -17,7 +17,6 @@ * @n_values: Number of multiplexer channels * @little_endian: Indicating if the register is in little endian * @write_only: Reading the register is not allowed by hardware - * @classes: Optional I2C auto-detection classes * @idle: Value to write to mux when idle * @idle_in_use: indicate if idle value is in use * @reg: Virtual address of the register to switch channel @@ -30,7 +29,6 @@ struct i2c_mux_reg_platform_data { int n_values; bool little_endian; bool write_only; - const unsigned int *classes; u32 idle; bool idle_in_use; void __iomem *reg; diff --git a/include/linux/platform_data/keypad-omap.h b/include/linux/platform_data/keypad-omap.h index 3e7c64c854f4..f3f1311cdf3a 100644 --- a/include/linux/platform_data/keypad-omap.h +++ b/include/linux/platform_data/keypad-omap.h @@ -19,9 +19,6 @@ struct omap_kp_platform_data { bool rep; unsigned long delay; bool dbounce; - /* specific to OMAP242x*/ - unsigned int *row_gpios; - unsigned int *col_gpios; }; /* Group (0..3) -- when multiple keys are pressed, only the diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index 7c8d65414a70..7d8025fb74b7 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -83,5 +83,6 @@ struct bq27xxx_device_info { void bq27xxx_battery_update(struct bq27xxx_device_info *di); int bq27xxx_battery_setup(struct bq27xxx_device_info *di); void bq27xxx_battery_teardown(struct bq27xxx_device_info *di); +extern const struct dev_pm_ops bq27xxx_battery_battery_pm_ops; #endif diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 782e14f62201..fa802db216f9 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -141,6 +141,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter); bool ring_buffer_iter_dropped(struct ring_buffer_iter *iter); unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu); +unsigned long ring_buffer_max_event_size(struct trace_buffer *buffer); void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu); void ring_buffer_reset_online_cpus(struct trace_buffer *buffer); @@ -191,15 +192,24 @@ bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer); size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu); size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu); -void *ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu); -void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data); -int ring_buffer_read_page(struct trace_buffer *buffer, void **data_page, +struct buffer_data_read_page; +struct buffer_data_read_page * +ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu); +void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, + struct buffer_data_read_page *page); +int ring_buffer_read_page(struct trace_buffer *buffer, + struct buffer_data_read_page *data_page, size_t len, int cpu, int full); +void *ring_buffer_read_page_data(struct buffer_data_read_page *page); struct trace_seq; int ring_buffer_print_entry_header(struct trace_seq *s); -int ring_buffer_print_page_header(struct trace_seq *s); +int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq *s); + +int ring_buffer_subbuf_order_get(struct trace_buffer *buffer); +int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order); +int ring_buffer_subbuf_size_get(struct trace_buffer *buffer); enum ring_buffer_flags { RB_FL_OVERWRITE = 1 << 0, diff --git a/include/linux/sched.h b/include/linux/sched.h index 9a66147915b2..cdb8ea53c365 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -957,7 +957,7 @@ struct task_struct { /* Recursion prevention for eventfd_signal() */ unsigned in_eventfd:1; #endif -#ifdef CONFIG_IOMMU_SVA +#ifdef CONFIG_ARCH_HAS_CPU_PASID unsigned pasid_activated:1; #endif #ifdef CONFIG_CPU_SUP_INTEL diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index 5fb1f12c33f9..c44f4b47b945 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -22,9 +22,8 @@ struct seq_buf { }; #define DECLARE_SEQ_BUF(NAME, SIZE) \ - char __ ## NAME ## _buffer[SIZE] = ""; \ struct seq_buf NAME = { \ - .buffer = &__ ## NAME ## _buffer, \ + .buffer = (char[SIZE]) { 0 }, \ .size = SIZE, \ } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a5ae952454c8..2dde34c29203 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -295,7 +295,7 @@ struct nf_bridge_info { u8 bridged_dnat:1; u8 sabotage_in_done:1; __u16 frag_max_size; - struct net_device *physindev; + int physinif; /* always valid & non-NULL from FORWARD on, for physdev match */ struct net_device *physoutdev; diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 4f3d14bb1538..66f814b63a43 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -886,7 +886,8 @@ struct sdw_master_ops { * struct sdw_bus - SoundWire bus * @dev: Shortcut to &bus->md->dev to avoid changing the entire code. * @md: Master device - * @link_id: Link id number, can be 0 to N, unique for each Master + * @controller_id: system-unique controller ID. If set to -1, the bus @id will be used. + * @link_id: Link id number, can be 0 to N, unique for each Controller * @id: bus system-wide unique id * @slaves: list of Slaves on this bus * @assigned: Bitmap for Slave device numbers. @@ -918,6 +919,7 @@ struct sdw_master_ops { struct sdw_bus { struct device *dev; struct sdw_master_device *md; + int controller_id; unsigned int link_id; int id; struct list_head slaves; @@ -1040,7 +1042,7 @@ int sdw_compute_params(struct sdw_bus *bus); int sdw_stream_add_master(struct sdw_bus *bus, struct sdw_stream_config *stream_config, - struct sdw_port_config *port_config, + const struct sdw_port_config *port_config, unsigned int num_ports, struct sdw_stream_runtime *stream); int sdw_stream_remove_master(struct sdw_bus *bus, @@ -1062,7 +1064,7 @@ void sdw_extract_slave_id(struct sdw_bus *bus, u64 addr, struct sdw_slave_id *id int sdw_stream_add_slave(struct sdw_slave *slave, struct sdw_stream_config *stream_config, - struct sdw_port_config *port_config, + const struct sdw_port_config *port_config, unsigned int num_ports, struct sdw_stream_runtime *stream); int sdw_stream_remove_slave(struct sdw_slave *slave, @@ -1084,7 +1086,7 @@ int sdw_update_no_pm(struct sdw_slave *slave, u32 addr, u8 mask, u8 val); static inline int sdw_stream_add_slave(struct sdw_slave *slave, struct sdw_stream_config *stream_config, - struct sdw_port_config *port_config, + const struct sdw_port_config *port_config, unsigned int num_ports, struct sdw_stream_runtime *stream) { diff --git a/include/linux/trace.h b/include/linux/trace.h index 2a70a447184c..fdcd76b7be83 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -51,7 +51,7 @@ int trace_array_printk(struct trace_array *tr, unsigned long ip, const char *fmt, ...); int trace_array_init_printk(struct trace_array *tr); void trace_array_put(struct trace_array *tr); -struct trace_array *trace_array_get_by_name(const char *name); +struct trace_array *trace_array_get_by_name(const char *name, const char *systems); int trace_array_destroy(struct trace_array *tr); /* For osnoise tracer */ @@ -84,7 +84,7 @@ static inline int trace_array_init_printk(struct trace_array *tr) static inline void trace_array_put(struct trace_array *tr) { } -static inline struct trace_array *trace_array_get_by_name(const char *name) +static inline struct trace_array *trace_array_get_by_name(const char *name, const char *systems) { return NULL; } diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h index 3691e0e76a1a..9ec229dfddaa 100644 --- a/include/linux/trace_seq.h +++ b/include/linux/trace_seq.h @@ -8,11 +8,14 @@ /* * Trace sequences are used to allow a function to call several other functions - * to create a string of data to use (up to a max of PAGE_SIZE). + * to create a string of data to use. */ +#define TRACE_SEQ_BUFFER_SIZE (PAGE_SIZE * 2 - \ + (sizeof(struct seq_buf) + sizeof(size_t) + sizeof(int))) + struct trace_seq { - char buffer[PAGE_SIZE]; + char buffer[TRACE_SEQ_BUFFER_SIZE]; struct seq_buf seq; size_t readpos; int full; @@ -21,7 +24,7 @@ struct trace_seq { static inline void trace_seq_init(struct trace_seq *s) { - seq_buf_init(&s->seq, s->buffer, PAGE_SIZE); + seq_buf_init(&s->seq, s->buffer, TRACE_SEQ_BUFFER_SIZE); s->full = 0; s->readpos = 0; } diff --git a/include/linux/vfio.h b/include/linux/vfio.h index a65b2513f8cd..89b265bc6ec3 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -69,6 +69,13 @@ struct vfio_device { u8 iommufd_attached:1; #endif u8 cdev_opened:1; +#ifdef CONFIG_DEBUG_FS + /* + * debug_root is a static property of the vfio_device + * which must be set prior to registering the vfio_device. + */ + struct dentry *debug_root; +#endif }; /** diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 562e8754869d..85e84b92751b 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -127,7 +127,27 @@ int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf); int vfio_pci_core_enable(struct vfio_pci_core_device *vdev); void vfio_pci_core_disable(struct vfio_pci_core_device *vdev); void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev); +int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar); pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, pci_channel_state_t state); +#define VFIO_IOWRITE_DECLATION(size) \ +int vfio_pci_core_iowrite##size(struct vfio_pci_core_device *vdev, \ + bool test_mem, u##size val, void __iomem *io); + +VFIO_IOWRITE_DECLATION(8) +VFIO_IOWRITE_DECLATION(16) +VFIO_IOWRITE_DECLATION(32) +#ifdef iowrite64 +VFIO_IOWRITE_DECLATION(64) +#endif + +#define VFIO_IOREAD_DECLATION(size) \ +int vfio_pci_core_ioread##size(struct vfio_pci_core_device *vdev, \ + bool test_mem, u##size *val, void __iomem *io); + +VFIO_IOREAD_DECLATION(8) +VFIO_IOREAD_DECLATION(16) +VFIO_IOREAD_DECLATION(32) + #endif /* VFIO_PCI_CORE_H */ diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 4cc614a38376..b0201747a263 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -103,6 +103,14 @@ int virtqueue_resize(struct virtqueue *vq, u32 num, int virtqueue_reset(struct virtqueue *vq, void (*recycle)(struct virtqueue *vq, void *buf)); +struct virtio_admin_cmd { + __le16 opcode; + __le16 group_type; + __le64 group_member_id; + struct scatterlist *data_sg; + struct scatterlist *result_sg; +}; + /** * struct virtio_device - representation of a device using virtio * @index: unique position on the virtio bus diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 2b3438de2c4d..da9b271b54db 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -93,6 +93,8 @@ typedef void vq_callback_t(struct virtqueue *); * Returns 0 on success or error status * If disable_vq_and_reset is set, then enable_vq_after_reset must also be * set. + * @create_avq: create admin virtqueue resource. + * @destroy_avq: destroy admin virtqueue resource. */ struct virtio_config_ops { void (*get)(struct virtio_device *vdev, unsigned offset, @@ -120,6 +122,8 @@ struct virtio_config_ops { struct virtio_shm_region *region, u8 id); int (*disable_vq_and_reset)(struct virtqueue *vq); int (*enable_vq_after_reset)(struct virtqueue *vq); + int (*create_avq)(struct virtio_device *vdev); + void (*destroy_avq)(struct virtio_device *vdev); }; /* If driver didn't advertise the feature, it will never appear. */ diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 27cc1d464321..4dfa9b69ca8d 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -3,6 +3,8 @@ #define _LINUX_VIRTIO_NET_H #include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/ipv6.h> #include <linux/udp.h> #include <uapi/linux/tcp.h> #include <uapi/linux/virtio_net.h> @@ -49,6 +51,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, const struct virtio_net_hdr *hdr, bool little_endian) { + unsigned int nh_min_len = sizeof(struct iphdr); unsigned int gso_type = 0; unsigned int thlen = 0; unsigned int p_off = 0; @@ -65,6 +68,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, gso_type = SKB_GSO_TCPV6; ip_proto = IPPROTO_TCP; thlen = sizeof(struct tcphdr); + nh_min_len = sizeof(struct ipv6hdr); break; case VIRTIO_NET_HDR_GSO_UDP: gso_type = SKB_GSO_UDP; @@ -100,7 +104,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; - p_off = skb_transport_offset(skb) + thlen; + nh_min_len = max_t(u32, nh_min_len, skb_transport_offset(skb)); + p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; } else { @@ -140,7 +145,7 @@ retry: skb_set_transport_header(skb, keys.control.thoff); } else if (gso_type) { - p_off = thlen; + p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; } diff --git a/include/linux/virtio_pci_admin.h b/include/linux/virtio_pci_admin.h new file mode 100644 index 000000000000..f4a100a0fe2e --- /dev/null +++ b/include/linux/virtio_pci_admin.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_VIRTIO_PCI_ADMIN_H +#define _LINUX_VIRTIO_PCI_ADMIN_H + +#include <linux/types.h> +#include <linux/pci.h> + +#ifdef CONFIG_VIRTIO_PCI_ADMIN_LEGACY +bool virtio_pci_admin_has_legacy_io(struct pci_dev *pdev); +int virtio_pci_admin_legacy_common_io_write(struct pci_dev *pdev, u8 offset, + u8 size, u8 *buf); +int virtio_pci_admin_legacy_common_io_read(struct pci_dev *pdev, u8 offset, + u8 size, u8 *buf); +int virtio_pci_admin_legacy_device_io_write(struct pci_dev *pdev, u8 offset, + u8 size, u8 *buf); +int virtio_pci_admin_legacy_device_io_read(struct pci_dev *pdev, u8 offset, + u8 size, u8 *buf); +int virtio_pci_admin_legacy_io_notify_info(struct pci_dev *pdev, + u8 req_bar_flags, u8 *bar, + u64 *bar_offset); +#endif + +#endif /* _LINUX_VIRTIO_PCI_ADMIN_H */ diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h index a09e13a577a9..c0b1b1ca1163 100644 --- a/include/linux/virtio_pci_modern.h +++ b/include/linux/virtio_pci_modern.h @@ -125,4 +125,6 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev); void vp_modern_remove(struct virtio_pci_modern_device *mdev); int vp_modern_get_queue_reset(struct virtio_pci_modern_device *mdev, u16 index); void vp_modern_set_queue_reset(struct virtio_pci_modern_device *mdev, u16 index); +u16 vp_modern_avq_num(struct virtio_pci_modern_device *mdev); +u16 vp_modern_avq_index(struct virtio_pci_modern_device *mdev); #endif diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 6d0a14f7019d..453736fd1d23 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -60,7 +60,7 @@ struct writeback_control { unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ - unsigned unpinned_fscache_wb:1; /* Cleared I_PINNING_FSCACHE_WB */ + unsigned unpinned_netfs_wb:1; /* Cleared I_PINNING_NETFS_WB */ /* * When writeback IOs are bounced through async layers, only the diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index d68b0a483431..8b8ed4e13d74 100644 --- a/include/net/netdev_queues.h +++ b/include/net/netdev_queues.h @@ -128,7 +128,7 @@ netdev_txq_completed_mb(struct netdev_queue *dev_queue, netdev_txq_completed_mb(txq, pkts, bytes); \ \ _res = -1; \ - if (pkts && likely(get_desc > start_thrs)) { \ + if (pkts && likely(get_desc >= start_thrs)) { \ _res = 1; \ if (unlikely(netif_tx_queue_stopped(txq)) && \ !(down_cond)) { \ diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h index 0a86ab8d47b9..b00d65417c31 100644 --- a/include/sound/tas2781.h +++ b/include/sound/tas2781.h @@ -1,13 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ // -// ALSA SoC Texas Instruments TAS2781 Audio Smart Amplifier +// ALSA SoC Texas Instruments TAS2563/TAS2781 Audio Smart Amplifier // // Copyright (C) 2022 - 2023 Texas Instruments Incorporated // https://www.ti.com // -// The TAS2781 driver implements a flexible and configurable +// The TAS2563/TAS2781 driver implements a flexible and configurable // algo coefficient setting for one, two, or even multiple -// TAS2781 chips. +// TAS2563/TAS2781 chips. // // Author: Shenghao Ding <shenghao-ding@ti.com> // Author: Kevin Lu <kevin-lu@ti.com> @@ -60,7 +60,8 @@ #define TASDEVICE_CMD_FIELD_W 0x4 enum audio_device { - TAS2781 = 0, + TAS2563, + TAS2781, }; enum device_catlog_id { diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index 5194b7e6dc8d..8d73171cb9f0 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -902,37 +902,6 @@ TRACE_EVENT(afs_dir_check_failed, __entry->vnode, __entry->off, __entry->i_size) ); -TRACE_EVENT(afs_folio_dirty, - TP_PROTO(struct afs_vnode *vnode, const char *where, struct folio *folio), - - TP_ARGS(vnode, where, folio), - - TP_STRUCT__entry( - __field(struct afs_vnode *, vnode) - __field(const char *, where) - __field(pgoff_t, index) - __field(unsigned long, from) - __field(unsigned long, to) - ), - - TP_fast_assign( - unsigned long priv = (unsigned long)folio_get_private(folio); - __entry->vnode = vnode; - __entry->where = where; - __entry->index = folio_index(folio); - __entry->from = afs_folio_dirty_from(folio, priv); - __entry->to = afs_folio_dirty_to(folio, priv); - __entry->to |= (afs_is_folio_dirty_mmapped(priv) ? - (1UL << (BITS_PER_LONG - 1)) : 0); - ), - - TP_printk("vn=%p %lx %s %lx-%lx%s", - __entry->vnode, __entry->index, __entry->where, - __entry->from, - __entry->to & ~(1UL << (BITS_PER_LONG - 1)), - __entry->to & (1UL << (BITS_PER_LONG - 1)) ? " M" : "") - ); - TRACE_EVENT(afs_call_state, TP_PROTO(struct afs_call *call, enum afs_call_state from, diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index beec534cbaab..447a8c21cf57 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -16,34 +16,57 @@ * Define enums for tracing information. */ #define netfs_read_traces \ + EM(netfs_read_trace_dio_read, "DIO-READ ") \ EM(netfs_read_trace_expanded, "EXPANDED ") \ EM(netfs_read_trace_readahead, "READAHEAD") \ EM(netfs_read_trace_readpage, "READPAGE ") \ + EM(netfs_read_trace_prefetch_for_write, "PREFETCHW") \ E_(netfs_read_trace_write_begin, "WRITEBEGN") +#define netfs_write_traces \ + EM(netfs_write_trace_dio_write, "DIO-WRITE") \ + EM(netfs_write_trace_launder, "LAUNDER ") \ + EM(netfs_write_trace_unbuffered_write, "UNB-WRITE") \ + EM(netfs_write_trace_writeback, "WRITEBACK") \ + E_(netfs_write_trace_writethrough, "WRITETHRU") + #define netfs_rreq_origins \ EM(NETFS_READAHEAD, "RA") \ EM(NETFS_READPAGE, "RP") \ - E_(NETFS_READ_FOR_WRITE, "RW") + EM(NETFS_READ_FOR_WRITE, "RW") \ + EM(NETFS_WRITEBACK, "WB") \ + EM(NETFS_WRITETHROUGH, "WT") \ + EM(NETFS_LAUNDER_WRITE, "LW") \ + EM(NETFS_UNBUFFERED_WRITE, "UW") \ + EM(NETFS_DIO_READ, "DR") \ + E_(NETFS_DIO_WRITE, "DW") #define netfs_rreq_traces \ EM(netfs_rreq_trace_assess, "ASSESS ") \ EM(netfs_rreq_trace_copy, "COPY ") \ EM(netfs_rreq_trace_done, "DONE ") \ EM(netfs_rreq_trace_free, "FREE ") \ + EM(netfs_rreq_trace_redirty, "REDIRTY") \ EM(netfs_rreq_trace_resubmit, "RESUBMT") \ EM(netfs_rreq_trace_unlock, "UNLOCK ") \ - E_(netfs_rreq_trace_unmark, "UNMARK ") + EM(netfs_rreq_trace_unmark, "UNMARK ") \ + EM(netfs_rreq_trace_wait_ip, "WAIT-IP") \ + EM(netfs_rreq_trace_wake_ip, "WAKE-IP") \ + E_(netfs_rreq_trace_write_done, "WR-DONE") #define netfs_sreq_sources \ EM(NETFS_FILL_WITH_ZEROES, "ZERO") \ EM(NETFS_DOWNLOAD_FROM_SERVER, "DOWN") \ EM(NETFS_READ_FROM_CACHE, "READ") \ - E_(NETFS_INVALID_READ, "INVL") \ + EM(NETFS_INVALID_READ, "INVL") \ + EM(NETFS_UPLOAD_TO_SERVER, "UPLD") \ + EM(NETFS_WRITE_TO_CACHE, "WRIT") \ + E_(NETFS_INVALID_WRITE, "INVL") #define netfs_sreq_traces \ EM(netfs_sreq_trace_download_instead, "RDOWN") \ EM(netfs_sreq_trace_free, "FREE ") \ + EM(netfs_sreq_trace_limited, "LIMIT") \ EM(netfs_sreq_trace_prepare, "PREP ") \ EM(netfs_sreq_trace_resubmit_short, "SHORT") \ EM(netfs_sreq_trace_submit, "SUBMT") \ @@ -55,19 +78,24 @@ #define netfs_failures \ EM(netfs_fail_check_write_begin, "check-write-begin") \ EM(netfs_fail_copy_to_cache, "copy-to-cache") \ + EM(netfs_fail_dio_read_short, "dio-read-short") \ + EM(netfs_fail_dio_read_zero, "dio-read-zero") \ EM(netfs_fail_read, "read") \ EM(netfs_fail_short_read, "short-read") \ - E_(netfs_fail_prepare_write, "prep-write") + EM(netfs_fail_prepare_write, "prep-write") \ + E_(netfs_fail_write, "write") #define netfs_rreq_ref_traces \ - EM(netfs_rreq_trace_get_hold, "GET HOLD ") \ + EM(netfs_rreq_trace_get_for_outstanding,"GET OUTSTND") \ EM(netfs_rreq_trace_get_subreq, "GET SUBREQ ") \ EM(netfs_rreq_trace_put_complete, "PUT COMPLT ") \ EM(netfs_rreq_trace_put_discard, "PUT DISCARD") \ EM(netfs_rreq_trace_put_failed, "PUT FAILED ") \ - EM(netfs_rreq_trace_put_hold, "PUT HOLD ") \ + EM(netfs_rreq_trace_put_no_submit, "PUT NO-SUBM") \ + EM(netfs_rreq_trace_put_return, "PUT RETURN ") \ EM(netfs_rreq_trace_put_subreq, "PUT SUBREQ ") \ - EM(netfs_rreq_trace_put_zero_len, "PUT ZEROLEN") \ + EM(netfs_rreq_trace_put_work, "PUT WORK ") \ + EM(netfs_rreq_trace_see_work, "SEE WORK ") \ E_(netfs_rreq_trace_new, "NEW ") #define netfs_sreq_ref_traces \ @@ -76,11 +104,44 @@ EM(netfs_sreq_trace_get_short_read, "GET SHORTRD") \ EM(netfs_sreq_trace_new, "NEW ") \ EM(netfs_sreq_trace_put_clear, "PUT CLEAR ") \ + EM(netfs_sreq_trace_put_discard, "PUT DISCARD") \ EM(netfs_sreq_trace_put_failed, "PUT FAILED ") \ EM(netfs_sreq_trace_put_merged, "PUT MERGED ") \ EM(netfs_sreq_trace_put_no_copy, "PUT NO COPY") \ + EM(netfs_sreq_trace_put_wip, "PUT WIP ") \ + EM(netfs_sreq_trace_put_work, "PUT WORK ") \ E_(netfs_sreq_trace_put_terminated, "PUT TERM ") +#define netfs_folio_traces \ + /* The first few correspond to enum netfs_how_to_modify */ \ + EM(netfs_folio_is_uptodate, "mod-uptodate") \ + EM(netfs_just_prefetch, "mod-prefetch") \ + EM(netfs_whole_folio_modify, "mod-whole-f") \ + EM(netfs_modify_and_clear, "mod-n-clear") \ + EM(netfs_streaming_write, "mod-streamw") \ + EM(netfs_streaming_write_cont, "mod-streamw+") \ + EM(netfs_flush_content, "flush") \ + EM(netfs_streaming_filled_page, "mod-streamw-f") \ + EM(netfs_streaming_cont_filled_page, "mod-streamw-f+") \ + /* The rest are for writeback */ \ + EM(netfs_folio_trace_clear, "clear") \ + EM(netfs_folio_trace_clear_s, "clear-s") \ + EM(netfs_folio_trace_clear_g, "clear-g") \ + EM(netfs_folio_trace_copy_to_cache, "copy") \ + EM(netfs_folio_trace_end_copy, "end-copy") \ + EM(netfs_folio_trace_filled_gaps, "filled-gaps") \ + EM(netfs_folio_trace_kill, "kill") \ + EM(netfs_folio_trace_launder, "launder") \ + EM(netfs_folio_trace_mkwrite, "mkwrite") \ + EM(netfs_folio_trace_mkwrite_plus, "mkwrite+") \ + EM(netfs_folio_trace_read_gaps, "read-gaps") \ + EM(netfs_folio_trace_redirty, "redirty") \ + EM(netfs_folio_trace_redirtied, "redirtied") \ + EM(netfs_folio_trace_store, "store") \ + EM(netfs_folio_trace_store_plus, "store+") \ + EM(netfs_folio_trace_wthru, "wthru") \ + E_(netfs_folio_trace_wthru_plus, "wthru+") + #ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY #define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY @@ -90,11 +151,13 @@ #define E_(a, b) a enum netfs_read_trace { netfs_read_traces } __mode(byte); +enum netfs_write_trace { netfs_write_traces } __mode(byte); enum netfs_rreq_trace { netfs_rreq_traces } __mode(byte); enum netfs_sreq_trace { netfs_sreq_traces } __mode(byte); enum netfs_failure { netfs_failures } __mode(byte); enum netfs_rreq_ref_trace { netfs_rreq_ref_traces } __mode(byte); enum netfs_sreq_ref_trace { netfs_sreq_ref_traces } __mode(byte); +enum netfs_folio_trace { netfs_folio_traces } __mode(byte); #endif @@ -107,6 +170,7 @@ enum netfs_sreq_ref_trace { netfs_sreq_ref_traces } __mode(byte); #define E_(a, b) TRACE_DEFINE_ENUM(a); netfs_read_traces; +netfs_write_traces; netfs_rreq_origins; netfs_rreq_traces; netfs_sreq_sources; @@ -114,6 +178,7 @@ netfs_sreq_traces; netfs_failures; netfs_rreq_ref_traces; netfs_sreq_ref_traces; +netfs_folio_traces; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -314,6 +379,82 @@ TRACE_EVENT(netfs_sreq_ref, __entry->ref) ); +TRACE_EVENT(netfs_folio, + TP_PROTO(struct folio *folio, enum netfs_folio_trace why), + + TP_ARGS(folio, why), + + TP_STRUCT__entry( + __field(ino_t, ino) + __field(pgoff_t, index) + __field(unsigned int, nr) + __field(enum netfs_folio_trace, why) + ), + + TP_fast_assign( + __entry->ino = folio->mapping->host->i_ino; + __entry->why = why; + __entry->index = folio_index(folio); + __entry->nr = folio_nr_pages(folio); + ), + + TP_printk("i=%05lx ix=%05lx-%05lx %s", + __entry->ino, __entry->index, __entry->index + __entry->nr - 1, + __print_symbolic(__entry->why, netfs_folio_traces)) + ); + +TRACE_EVENT(netfs_write_iter, + TP_PROTO(const struct kiocb *iocb, const struct iov_iter *from), + + TP_ARGS(iocb, from), + + TP_STRUCT__entry( + __field(unsigned long long, start ) + __field(size_t, len ) + __field(unsigned int, flags ) + ), + + TP_fast_assign( + __entry->start = iocb->ki_pos; + __entry->len = iov_iter_count(from); + __entry->flags = iocb->ki_flags; + ), + + TP_printk("WRITE-ITER s=%llx l=%zx f=%x", + __entry->start, __entry->len, __entry->flags) + ); + +TRACE_EVENT(netfs_write, + TP_PROTO(const struct netfs_io_request *wreq, + enum netfs_write_trace what), + + TP_ARGS(wreq, what), + + TP_STRUCT__entry( + __field(unsigned int, wreq ) + __field(unsigned int, cookie ) + __field(enum netfs_write_trace, what ) + __field(unsigned long long, start ) + __field(size_t, len ) + ), + + TP_fast_assign( + struct netfs_inode *__ctx = netfs_inode(wreq->inode); + struct fscache_cookie *__cookie = netfs_i_cookie(__ctx); + __entry->wreq = wreq->debug_id; + __entry->cookie = __cookie ? __cookie->debug_id : 0; + __entry->what = what; + __entry->start = wreq->start; + __entry->len = wreq->len; + ), + + TP_printk("R=%08x %s c=%08x by=%llx-%llx", + __entry->wreq, + __print_symbolic(__entry->what, netfs_write_traces), + __entry->cookie, + __entry->start, __entry->start + __entry->len - 1) + ); + #undef EM #undef E_ #endif /* _TRACE_NETFS_H */ diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 14bc6e742148..42066f4eb890 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -46,6 +46,7 @@ ___C(GET_SCAN_MEDIA_CAPS, "Get Scan Media Capabilities"), \ ___DEPRECATED(SCAN_MEDIA, "Scan Media"), \ ___DEPRECATED(GET_SCAN_MEDIA, "Get Scan Media Results"), \ + ___C(GET_TIMESTAMP, "Get Timestamp"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 0b2bc6252e2c..1dfeaa2e649e 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -49,6 +49,7 @@ enum { IOMMUFD_CMD_GET_HW_INFO, IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING, IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP, + IOMMUFD_CMD_HWPT_INVALIDATE, }; /** @@ -613,4 +614,82 @@ struct iommu_hwpt_get_dirty_bitmap { #define IOMMU_HWPT_GET_DIRTY_BITMAP _IO(IOMMUFD_TYPE, \ IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP) +/** + * enum iommu_hwpt_invalidate_data_type - IOMMU HWPT Cache Invalidation + * Data Type + * @IOMMU_HWPT_INVALIDATE_DATA_VTD_S1: Invalidation data for VTD_S1 + */ +enum iommu_hwpt_invalidate_data_type { + IOMMU_HWPT_INVALIDATE_DATA_VTD_S1, +}; + +/** + * enum iommu_hwpt_vtd_s1_invalidate_flags - Flags for Intel VT-d + * stage-1 cache invalidation + * @IOMMU_VTD_INV_FLAGS_LEAF: Indicates whether the invalidation applies + * to all-levels page structure cache or just + * the leaf PTE cache. + */ +enum iommu_hwpt_vtd_s1_invalidate_flags { + IOMMU_VTD_INV_FLAGS_LEAF = 1 << 0, +}; + +/** + * struct iommu_hwpt_vtd_s1_invalidate - Intel VT-d cache invalidation + * (IOMMU_HWPT_INVALIDATE_DATA_VTD_S1) + * @addr: The start address of the range to be invalidated. It needs to + * be 4KB aligned. + * @npages: Number of contiguous 4K pages to be invalidated. + * @flags: Combination of enum iommu_hwpt_vtd_s1_invalidate_flags + * @__reserved: Must be 0 + * + * The Intel VT-d specific invalidation data for user-managed stage-1 cache + * invalidation in nested translation. Userspace uses this structure to + * tell the impacted cache scope after modifying the stage-1 page table. + * + * Invalidating all the caches related to the page table by setting @addr + * to be 0 and @npages to be U64_MAX. + * + * The device TLB will be invalidated automatically if ATS is enabled. + */ +struct iommu_hwpt_vtd_s1_invalidate { + __aligned_u64 addr; + __aligned_u64 npages; + __u32 flags; + __u32 __reserved; +}; + +/** + * struct iommu_hwpt_invalidate - ioctl(IOMMU_HWPT_INVALIDATE) + * @size: sizeof(struct iommu_hwpt_invalidate) + * @hwpt_id: ID of a nested HWPT for cache invalidation + * @data_uptr: User pointer to an array of driver-specific cache invalidation + * data. + * @data_type: One of enum iommu_hwpt_invalidate_data_type, defining the data + * type of all the entries in the invalidation request array. It + * should be a type supported by the hwpt pointed by @hwpt_id. + * @entry_len: Length (in bytes) of a request entry in the request array + * @entry_num: Input the number of cache invalidation requests in the array. + * Output the number of requests successfully handled by kernel. + * @__reserved: Must be 0. + * + * Invalidate the iommu cache for user-managed page table. Modifications on a + * user-managed page table should be followed by this operation to sync cache. + * Each ioctl can support one or more cache invalidation requests in the array + * that has a total size of @entry_len * @entry_num. + * + * An empty invalidation request array by setting @entry_num==0 is allowed, and + * @entry_len and @data_uptr would be ignored in this case. This can be used to + * check if the given @data_type is supported or not by kernel. + */ +struct iommu_hwpt_invalidate { + __u32 size; + __u32 hwpt_id; + __aligned_u64 data_uptr; + __u32 data_type; + __u32 entry_len; + __u32 entry_num; + __u32 __reserved; +}; +#define IOMMU_HWPT_INVALIDATE _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_INVALIDATE) #endif diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 7f5fb010226d..2b68e6cdf190 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1219,6 +1219,7 @@ enum vfio_device_mig_state { VFIO_DEVICE_STATE_RUNNING_P2P = 5, VFIO_DEVICE_STATE_PRE_COPY = 6, VFIO_DEVICE_STATE_PRE_COPY_P2P = 7, + VFIO_DEVICE_STATE_NR, }; /** diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h index 8881aea60f6f..2445f365bce7 100644 --- a/include/uapi/linux/virtio_config.h +++ b/include/uapi/linux/virtio_config.h @@ -52,7 +52,7 @@ * rest are per-device feature bits. */ #define VIRTIO_TRANSPORT_F_START 28 -#define VIRTIO_TRANSPORT_F_END 41 +#define VIRTIO_TRANSPORT_F_END 42 #ifndef VIRTIO_CONFIG_NO_LEGACY /* Do we get callbacks when the ring is completely used, even if we've @@ -114,4 +114,10 @@ * This feature indicates that the driver can reset a queue individually. */ #define VIRTIO_F_RING_RESET 40 + +/* + * This feature indicates that the device support administration virtqueues. + */ +#define VIRTIO_F_ADMIN_VQ 41 + #endif /* _UAPI_LINUX_VIRTIO_CONFIG_H */ diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index 44f4dd2add18..ef3810dee7ef 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -175,6 +175,9 @@ struct virtio_pci_modern_common_cfg { __le16 queue_notify_data; /* read-write */ __le16 queue_reset; /* read-write */ + + __le16 admin_queue_index; /* read-only */ + __le16 admin_queue_num; /* read-only */ }; /* Fields in VIRTIO_PCI_CAP_PCI_CFG: */ @@ -215,7 +218,72 @@ struct virtio_pci_cfg_cap { #define VIRTIO_PCI_COMMON_Q_USEDHI 52 #define VIRTIO_PCI_COMMON_Q_NDATA 56 #define VIRTIO_PCI_COMMON_Q_RESET 58 +#define VIRTIO_PCI_COMMON_ADM_Q_IDX 60 +#define VIRTIO_PCI_COMMON_ADM_Q_NUM 62 #endif /* VIRTIO_PCI_NO_MODERN */ +/* Admin command status. */ +#define VIRTIO_ADMIN_STATUS_OK 0 + +/* Admin command opcode. */ +#define VIRTIO_ADMIN_CMD_LIST_QUERY 0x0 +#define VIRTIO_ADMIN_CMD_LIST_USE 0x1 + +/* Admin command group type. */ +#define VIRTIO_ADMIN_GROUP_TYPE_SRIOV 0x1 + +/* Transitional device admin command. */ +#define VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE 0x2 +#define VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ 0x3 +#define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE 0x4 +#define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ 0x5 +#define VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO 0x6 + +struct __packed virtio_admin_cmd_hdr { + __le16 opcode; + /* + * 1 - SR-IOV + * 2-65535 - reserved + */ + __le16 group_type; + /* Unused, reserved for future extensions. */ + __u8 reserved1[12]; + __le64 group_member_id; +}; + +struct __packed virtio_admin_cmd_status { + __le16 status; + __le16 status_qualifier; + /* Unused, reserved for future extensions. */ + __u8 reserved2[4]; +}; + +struct __packed virtio_admin_cmd_legacy_wr_data { + __u8 offset; /* Starting offset of the register(s) to write. */ + __u8 reserved[7]; + __u8 registers[]; +}; + +struct __packed virtio_admin_cmd_legacy_rd_data { + __u8 offset; /* Starting offset of the register(s) to read. */ +}; + +#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_END 0 +#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_DEV 0x1 +#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_MEM 0x2 + +#define VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO 4 + +struct __packed virtio_admin_cmd_notify_info_data { + __u8 flags; /* 0 = end of list, 1 = owner device, 2 = member device */ + __u8 bar; /* BAR of the member or the owner device */ + __u8 padding[6]; + __le64 offset; /* Offset within bar. */ +}; + +struct virtio_admin_cmd_notify_info_result { + struct virtio_admin_cmd_notify_info_data entries[VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO]; +}; + #endif diff --git a/include/uapi/linux/virtio_pmem.h b/include/uapi/linux/virtio_pmem.h index d676b3620383..ede4f3564977 100644 --- a/include/uapi/linux/virtio_pmem.h +++ b/include/uapi/linux/virtio_pmem.h @@ -14,6 +14,13 @@ #include <linux/virtio_ids.h> #include <linux/virtio_config.h> +/* Feature bits */ +/* guest physical address range will be indicated as shared memory region 0 */ +#define VIRTIO_PMEM_F_SHMEM_REGION 0 + +/* shmid of the shared memory region corresponding to the pmem */ +#define VIRTIO_PMEM_SHMEM_REGION_ID 0 + struct virtio_pmem_config { __le64 start; __le64 size; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 86761ec623f9..cd9a137ad6ce 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -137,6 +137,14 @@ struct io_defer_entry { #define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL) #define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK) +/* + * No waiters. It's larger than any valid value of the tw counter + * so that tests against ->cq_wait_nr would fail and skip wake_up(). + */ +#define IO_CQ_WAKE_INIT (-1U) +/* Forced wake up if there is a waiter regardless of ->cq_wait_nr */ +#define IO_CQ_WAKE_FORCE (IO_CQ_WAKE_INIT >> 1) + static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, struct task_struct *task, bool cancel_all); @@ -303,6 +311,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) goto err; ctx->flags = p->flags; + atomic_set(&ctx->cq_wait_nr, IO_CQ_WAKE_INIT); init_waitqueue_head(&ctx->sqo_sq_wait); INIT_LIST_HEAD(&ctx->sqd_list); INIT_LIST_HEAD(&ctx->cq_overflow_list); @@ -1304,16 +1313,23 @@ static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags) { struct io_ring_ctx *ctx = req->ctx; unsigned nr_wait, nr_tw, nr_tw_prev; - struct llist_node *first; + struct llist_node *head; + + /* See comment above IO_CQ_WAKE_INIT */ + BUILD_BUG_ON(IO_CQ_WAKE_FORCE <= IORING_MAX_CQ_ENTRIES); + /* + * We don't know how many reuqests is there in the link and whether + * they can even be queued lazily, fall back to non-lazy. + */ if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) flags &= ~IOU_F_TWQ_LAZY_WAKE; - first = READ_ONCE(ctx->work_llist.first); + head = READ_ONCE(ctx->work_llist.first); do { nr_tw_prev = 0; - if (first) { - struct io_kiocb *first_req = container_of(first, + if (head) { + struct io_kiocb *first_req = container_of(head, struct io_kiocb, io_task_work.node); /* @@ -1322,17 +1338,29 @@ static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags) */ nr_tw_prev = READ_ONCE(first_req->nr_tw); } + + /* + * Theoretically, it can overflow, but that's fine as one of + * previous adds should've tried to wake the task. + */ nr_tw = nr_tw_prev + 1; - /* Large enough to fail the nr_wait comparison below */ if (!(flags & IOU_F_TWQ_LAZY_WAKE)) - nr_tw = -1U; + nr_tw = IO_CQ_WAKE_FORCE; req->nr_tw = nr_tw; - req->io_task_work.node.next = first; - } while (!try_cmpxchg(&ctx->work_llist.first, &first, + req->io_task_work.node.next = head; + } while (!try_cmpxchg(&ctx->work_llist.first, &head, &req->io_task_work.node)); - if (!first) { + /* + * cmpxchg implies a full barrier, which pairs with the barrier + * in set_current_state() on the io_cqring_wait() side. It's used + * to ensure that either we see updated ->cq_wait_nr, or waiters + * going to sleep will observe the work added to the list, which + * is similar to the wait/wawke task state sync. + */ + + if (!head) { if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); if (ctx->has_evfd) @@ -1340,14 +1368,12 @@ static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags) } nr_wait = atomic_read(&ctx->cq_wait_nr); - /* no one is waiting */ - if (!nr_wait) + /* not enough or no one is waiting */ + if (nr_tw < nr_wait) return; - /* either not enough or the previous add has already woken it up */ - if (nr_wait > nr_tw || nr_tw_prev >= nr_wait) + /* the previous add has already woken it up */ + if (nr_tw_prev >= nr_wait) return; - /* pairs with set_current_state() in io_cqring_wait() */ - smp_mb__after_atomic(); wake_up_state(ctx->submitter_task, TASK_INTERRUPTIBLE); } @@ -2000,9 +2026,10 @@ inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, goto out; fd = array_index_nospec(fd, ctx->nr_user_files); slot = io_fixed_file_slot(&ctx->file_table, fd); - file = io_slot_file(slot); + if (!req->rsrc_node) + __io_req_set_rsrc_node(req, ctx); req->flags |= io_slot_flags(slot); - io_req_set_rsrc_node(req, ctx, 0); + file = io_slot_file(slot); out: io_ring_submit_unlock(ctx, issue_flags); return file; @@ -2613,7 +2640,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, ret = io_cqring_wait_schedule(ctx, &iowq); __set_current_state(TASK_RUNNING); - atomic_set(&ctx->cq_wait_nr, 0); + atomic_set(&ctx->cq_wait_nr, IO_CQ_WAKE_INIT); /* * Run task_work after scheduling and before io_should_wake(). diff --git a/io_uring/register.c b/io_uring/register.c index 708dd1d89add..5e62c1208996 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -14,6 +14,7 @@ #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/nospec.h> +#include <linux/compat.h> #include <linux/io_uring.h> #include <linux/io_uring_types.h> @@ -278,13 +279,14 @@ static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx, if (len > cpumask_size()) len = cpumask_size(); - if (in_compat_syscall()) { +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) ret = compat_get_bitmap(cpumask_bits(new_mask), (const compat_ulong_t __user *)arg, len * 8 /* CHAR_BIT */); - } else { + else +#endif ret = copy_from_user(new_mask, arg, len); - } if (ret) { free_cpumask_var(new_mask); diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index 7238b9cfe33b..c6f199bbee28 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -102,17 +102,21 @@ static inline void io_charge_rsrc_node(struct io_ring_ctx *ctx, node->refs++; } +static inline void __io_req_set_rsrc_node(struct io_kiocb *req, + struct io_ring_ctx *ctx) +{ + lockdep_assert_held(&ctx->uring_lock); + req->rsrc_node = ctx->rsrc_node; + io_charge_rsrc_node(ctx, ctx->rsrc_node); +} + static inline void io_req_set_rsrc_node(struct io_kiocb *req, struct io_ring_ctx *ctx, unsigned int issue_flags) { if (!req->rsrc_node) { io_ring_submit_lock(ctx, issue_flags); - - lockdep_assert_held(&ctx->uring_lock); - - req->rsrc_node = ctx->rsrc_node; - io_charge_rsrc_node(ctx, ctx->rsrc_node); + __io_req_set_rsrc_node(req, ctx); io_ring_submit_unlock(ctx, issue_flags); } } diff --git a/io_uring/rw.c b/io_uring/rw.c index 0c856726b15d..118cc9f1cf16 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -168,27 +168,6 @@ void io_readv_writev_cleanup(struct io_kiocb *req) kfree(io->free_iovec); } -static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) -{ - switch (ret) { - case -EIOCBQUEUED: - break; - case -ERESTARTSYS: - case -ERESTARTNOINTR: - case -ERESTARTNOHAND: - case -ERESTART_RESTARTBLOCK: - /* - * We can't just restart the syscall, since previously - * submitted sqes may already be in progress. Just fail this - * IO with EINTR. - */ - ret = -EINTR; - fallthrough; - default: - kiocb->ki_complete(kiocb, ret); - } -} - static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req) { struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); @@ -371,6 +350,33 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res) smp_store_release(&req->iopoll_completed, 1); } +static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) +{ + /* IO was queued async, completion will happen later */ + if (ret == -EIOCBQUEUED) + return; + + /* transform internal restart error codes */ + if (unlikely(ret < 0)) { + switch (ret) { + case -ERESTARTSYS: + case -ERESTARTNOINTR: + case -ERESTARTNOHAND: + case -ERESTART_RESTARTBLOCK: + /* + * We can't just restart the syscall, since previously + * submitted sqes may already be in progress. Just fail + * this IO with EINTR. + */ + ret = -EINTR; + break; + } + } + + INDIRECT_CALL_2(kiocb->ki_complete, io_complete_rw_iopoll, + io_complete_rw, kiocb, ret); +} + static int kiocb_done(struct io_kiocb *req, ssize_t ret, unsigned int issue_flags) { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 51e8b4bee0c8..596471189176 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5615,21 +5615,46 @@ static u8 bpf_ctx_convert_map[] = { #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE -const struct btf_member * -btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, - const struct btf_type *t, enum bpf_prog_type prog_type, - int arg) +static const struct btf_type *find_canonical_prog_ctx_type(enum bpf_prog_type prog_type) { const struct btf_type *conv_struct; - const struct btf_type *ctx_struct; const struct btf_member *ctx_type; - const char *tname, *ctx_tname; conv_struct = bpf_ctx_convert.t; - if (!conv_struct) { - bpf_log(log, "btf_vmlinux is malformed\n"); + if (!conv_struct) return NULL; - } + /* prog_type is valid bpf program type. No need for bounds check. */ + ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2; + /* ctx_type is a pointer to prog_ctx_type in vmlinux. + * Like 'struct __sk_buff' + */ + return btf_type_by_id(btf_vmlinux, ctx_type->type); +} + +static int find_kern_ctx_type_id(enum bpf_prog_type prog_type) +{ + const struct btf_type *conv_struct; + const struct btf_member *ctx_type; + + conv_struct = bpf_ctx_convert.t; + if (!conv_struct) + return -EFAULT; + /* prog_type is valid bpf program type. No need for bounds check. */ + ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2 + 1; + /* ctx_type is a pointer to prog_ctx_type in vmlinux. + * Like 'struct sk_buff' + */ + return ctx_type->type; +} + +const struct btf_type * +btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, enum bpf_prog_type prog_type, + int arg) +{ + const struct btf_type *ctx_type; + const char *tname, *ctx_tname; + t = btf_type_by_id(btf, t->type); while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); @@ -5646,17 +5671,15 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, bpf_log(log, "arg#%d struct doesn't have a name\n", arg); return NULL; } - /* prog_type is valid bpf program type. No need for bounds check. */ - ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2; - /* ctx_struct is a pointer to prog_ctx_type in vmlinux. - * Like 'struct __sk_buff' - */ - ctx_struct = btf_type_by_id(btf_vmlinux, ctx_type->type); - if (!ctx_struct) + + ctx_type = find_canonical_prog_ctx_type(prog_type); + if (!ctx_type) { + bpf_log(log, "btf_vmlinux is malformed\n"); /* should not happen */ return NULL; + } again: - ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_struct->name_off); + ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off); if (!ctx_tname) { /* should not happen */ bpf_log(log, "Please fix kernel include/linux/bpf_types.h\n"); @@ -5677,28 +5700,167 @@ again: /* bpf_user_pt_regs_t is a typedef, so resolve it to * underlying struct and check name again */ - if (!btf_type_is_modifier(ctx_struct)) + if (!btf_type_is_modifier(ctx_type)) return NULL; - while (btf_type_is_modifier(ctx_struct)) - ctx_struct = btf_type_by_id(btf_vmlinux, ctx_struct->type); + while (btf_type_is_modifier(ctx_type)) + ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type); goto again; } return ctx_type; } +/* forward declarations for arch-specific underlying types of + * bpf_user_pt_regs_t; this avoids the need for arch-specific #ifdef + * compilation guards below for BPF_PROG_TYPE_PERF_EVENT checks, but still + * works correctly with __builtin_types_compatible_p() on respective + * architectures + */ +struct user_regs_struct; +struct user_pt_regs; + +static int btf_validate_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, int arg, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type) +{ + const struct btf_type *ctx_type; + const char *tname, *ctx_tname; + + if (!btf_is_ptr(t)) { + bpf_log(log, "arg#%d type isn't a pointer\n", arg); + return -EINVAL; + } + t = btf_type_by_id(btf, t->type); + + /* KPROBE and PERF_EVENT programs allow bpf_user_pt_regs_t typedef */ + if (prog_type == BPF_PROG_TYPE_KPROBE || prog_type == BPF_PROG_TYPE_PERF_EVENT) { + while (btf_type_is_modifier(t) && !btf_type_is_typedef(t)) + t = btf_type_by_id(btf, t->type); + + if (btf_type_is_typedef(t)) { + tname = btf_name_by_offset(btf, t->name_off); + if (tname && strcmp(tname, "bpf_user_pt_regs_t") == 0) + return 0; + } + } + + /* all other program types don't use typedefs for context type */ + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); + + /* `void *ctx __arg_ctx` is always valid */ + if (btf_type_is_void(t)) + return 0; + + tname = btf_name_by_offset(btf, t->name_off); + if (str_is_empty(tname)) { + bpf_log(log, "arg#%d type doesn't have a name\n", arg); + return -EINVAL; + } + + /* special cases */ + switch (prog_type) { + case BPF_PROG_TYPE_KPROBE: + if (__btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0) + return 0; + break; + case BPF_PROG_TYPE_PERF_EVENT: + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct pt_regs) && + __btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0) + return 0; + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_pt_regs) && + __btf_type_is_struct(t) && strcmp(tname, "user_pt_regs") == 0) + return 0; + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_regs_struct) && + __btf_type_is_struct(t) && strcmp(tname, "user_regs_struct") == 0) + return 0; + break; + case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return 0; + break; + case BPF_PROG_TYPE_TRACING: + switch (attach_type) { + case BPF_TRACE_RAW_TP: + /* tp_btf program is TRACING, so need special case here */ + if (__btf_type_is_struct(t) && + strcmp(tname, "bpf_raw_tracepoint_args") == 0) + return 0; + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return 0; + break; + case BPF_TRACE_ITER: + /* allow struct bpf_iter__xxx types only */ + if (__btf_type_is_struct(t) && + strncmp(tname, "bpf_iter__", sizeof("bpf_iter__") - 1) == 0) + return 0; + break; + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + case BPF_MODIFY_RETURN: + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return 0; + break; + default: + break; + } + break; + case BPF_PROG_TYPE_LSM: + case BPF_PROG_TYPE_STRUCT_OPS: + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return 0; + break; + case BPF_PROG_TYPE_TRACEPOINT: + case BPF_PROG_TYPE_SYSCALL: + case BPF_PROG_TYPE_EXT: + return 0; /* anything goes */ + default: + break; + } + + ctx_type = find_canonical_prog_ctx_type(prog_type); + if (!ctx_type) { + /* should not happen */ + bpf_log(log, "btf_vmlinux is malformed\n"); + return -EINVAL; + } + + /* resolve typedefs and check that underlying structs are matching as well */ + while (btf_type_is_modifier(ctx_type)) + ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type); + + /* if program type doesn't have distinctly named struct type for + * context, then __arg_ctx argument can only be `void *`, which we + * already checked above + */ + if (!__btf_type_is_struct(ctx_type)) { + bpf_log(log, "arg#%d should be void pointer\n", arg); + return -EINVAL; + } + + ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off); + if (!__btf_type_is_struct(t) || strcmp(ctx_tname, tname) != 0) { + bpf_log(log, "arg#%d should be `struct %s *`\n", arg, ctx_tname); + return -EINVAL; + } + + return 0; +} + static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *t, enum bpf_prog_type prog_type, int arg) { - const struct btf_member *prog_ctx_type, *kern_ctx_type; - - prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type, arg); - if (!prog_ctx_type) + if (!btf_get_prog_ctx_type(log, btf, t, prog_type, arg)) return -ENOENT; - kern_ctx_type = prog_ctx_type + 1; - return kern_ctx_type->type; + return find_kern_ctx_type_id(prog_type); } int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type) @@ -6934,6 +7096,23 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) return -EINVAL; } + for (i = 0; i < nargs; i++) { + const char *tag; + + if (sub->args[i].arg_type != ARG_PTR_TO_CTX) + continue; + + /* check if arg has "arg:ctx" tag */ + t = btf_type_by_id(btf, args[i].type); + tag = btf_find_decl_tag_value(btf, fn_t, i, "arg:"); + if (IS_ERR_OR_NULL(tag) || strcmp(tag, "ctx") != 0) + continue; + + if (btf_validate_prog_ctx_type(log, btf, t, i, prog_type, + prog->expected_attach_type)) + return -EINVAL; + } + sub->arg_cnt = nargs; sub->args_cached = true; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index adbf330d364b..65f598694d55 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -12826,6 +12826,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } switch (base_type(ptr_reg->type)) { + case PTR_TO_FLOW_KEYS: + if (known) + break; + fallthrough; case CONST_PTR_TO_MAP: /* smin_val represents the known value */ if (known && smin_val == 0 && opcode == BPF_ADD) diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 6b213c8252d6..d05066cb40b2 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1348,8 +1348,6 @@ do_full_getstr: /* PROMPT can only be set if we have MEM_READ permission. */ snprintf(kdb_prompt_str, CMD_BUFLEN, kdbgetenv("PROMPT"), raw_smp_processor_id()); - if (defcmd_in_progress) - strncat(kdb_prompt_str, "[defcmd]", CMD_BUFLEN); /* * Fetch command from keyboard diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 1a5c86dd87d5..a6e3792b15f8 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -62,7 +62,8 @@ enum map_err_types { * @pfn: page frame of the start address * @offset: offset of mapping relative to pfn * @map_err_type: track whether dma_mapping_error() was checked - * @stacktrace: support backtraces when a violation is detected + * @stack_len: number of backtrace entries in @stack_entries + * @stack_entries: stack of backtrace history */ struct dma_debug_entry { struct list_head list; diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 97c298b210bc..b079a9a8e087 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -1136,6 +1136,9 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, int cpu, i; int index; + if (alloc_size > IO_TLB_SEGSIZE * IO_TLB_SIZE) + return -1; + cpu = raw_smp_processor_id(); for (i = 0; i < default_nareas; ++i) { index = swiotlb_search_area(dev, cpu, i, orig_addr, alloc_size, diff --git a/kernel/fork.c b/kernel/fork.c index c981fa6171c1..47ff3b35352e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1173,7 +1173,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->use_memdelay = 0; #endif -#ifdef CONFIG_IOMMU_SVA +#ifdef CONFIG_ARCH_HAS_CPU_PASID tsk->pasid_activated = 0; #endif diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 9286f88fcd32..13aaf5e85b81 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -27,6 +27,7 @@ #include <linux/cpu.h> #include <linux/oom.h> +#include <asm/local64.h> #include <asm/local.h> /* @@ -317,6 +318,11 @@ struct buffer_data_page { unsigned char data[] RB_ALIGN_DATA; /* data of buffer page */ }; +struct buffer_data_read_page { + unsigned order; /* order of the page */ + struct buffer_data_page *data; /* actual data, stored in this page */ +}; + /* * Note, the buffer_page list must be first. The buffer pages * are allocated in cache lines, which means that each buffer @@ -331,6 +337,7 @@ struct buffer_page { unsigned read; /* index for next read */ local_t entries; /* entries on this page */ unsigned long real_end; /* real end of data */ + unsigned order; /* order of the page */ struct buffer_data_page *page; /* Actual data page */ }; @@ -361,7 +368,7 @@ static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage) static void free_buffer_page(struct buffer_page *bpage) { - free_page((unsigned long)bpage->page); + free_pages((unsigned long)bpage->page, bpage->order); kfree(bpage); } @@ -373,41 +380,6 @@ static inline bool test_time_stamp(u64 delta) return !!(delta & TS_DELTA_TEST); } -#define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE) - -/* Max payload is BUF_PAGE_SIZE - header (8bytes) */ -#define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2)) - -int ring_buffer_print_page_header(struct trace_seq *s) -{ - struct buffer_data_page field; - - trace_seq_printf(s, "\tfield: u64 timestamp;\t" - "offset:0;\tsize:%u;\tsigned:%u;\n", - (unsigned int)sizeof(field.time_stamp), - (unsigned int)is_signed_type(u64)); - - trace_seq_printf(s, "\tfield: local_t commit;\t" - "offset:%u;\tsize:%u;\tsigned:%u;\n", - (unsigned int)offsetof(typeof(field), commit), - (unsigned int)sizeof(field.commit), - (unsigned int)is_signed_type(long)); - - trace_seq_printf(s, "\tfield: int overwrite;\t" - "offset:%u;\tsize:%u;\tsigned:%u;\n", - (unsigned int)offsetof(typeof(field), commit), - 1, - (unsigned int)is_signed_type(long)); - - trace_seq_printf(s, "\tfield: char data;\t" - "offset:%u;\tsize:%u;\tsigned:%u;\n", - (unsigned int)offsetof(typeof(field), data), - (unsigned int)BUF_PAGE_SIZE, - (unsigned int)is_signed_type(char)); - - return !trace_seq_has_overflowed(s); -} - struct rb_irq_work { struct irq_work work; wait_queue_head_t waiters; @@ -463,27 +435,9 @@ enum { RB_CTX_MAX }; -#if BITS_PER_LONG == 32 -#define RB_TIME_32 -#endif - -/* To test on 64 bit machines */ -//#define RB_TIME_32 - -#ifdef RB_TIME_32 - -struct rb_time_struct { - local_t cnt; - local_t top; - local_t bottom; - local_t msb; -}; -#else -#include <asm/local64.h> struct rb_time_struct { local64_t time; }; -#endif typedef struct rb_time_struct rb_time_t; #define MAX_NEST 5 @@ -557,6 +511,10 @@ struct trace_buffer { struct rb_irq_work irq_work; bool time_stamp_abs; + + unsigned int subbuf_size; + unsigned int subbuf_order; + unsigned int max_data_size; }; struct ring_buffer_iter { @@ -570,150 +528,48 @@ struct ring_buffer_iter { u64 read_stamp; u64 page_stamp; struct ring_buffer_event *event; + size_t event_size; int missed_events; }; -#ifdef RB_TIME_32 - -/* - * On 32 bit machines, local64_t is very expensive. As the ring - * buffer doesn't need all the features of a true 64 bit atomic, - * on 32 bit, it uses these functions (64 still uses local64_t). - * - * For the ring buffer, 64 bit required operations for the time is - * the following: - * - * - Reads may fail if it interrupted a modification of the time stamp. - * It will succeed if it did not interrupt another write even if - * the read itself is interrupted by a write. - * It returns whether it was successful or not. - * - * - Writes always succeed and will overwrite other writes and writes - * that were done by events interrupting the current write. - * - * - A write followed by a read of the same time stamp will always succeed, - * but may not contain the same value. - * - * - A cmpxchg will fail if it interrupted another write or cmpxchg. - * Other than that, it acts like a normal cmpxchg. - * - * The 60 bit time stamp is broken up by 30 bits in a top and bottom half - * (bottom being the least significant 30 bits of the 60 bit time stamp). - * - * The two most significant bits of each half holds a 2 bit counter (0-3). - * Each update will increment this counter by one. - * When reading the top and bottom, if the two counter bits match then the - * top and bottom together make a valid 60 bit number. - */ -#define RB_TIME_SHIFT 30 -#define RB_TIME_VAL_MASK ((1 << RB_TIME_SHIFT) - 1) -#define RB_TIME_MSB_SHIFT 60 - -static inline int rb_time_cnt(unsigned long val) +int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq *s) { - return (val >> RB_TIME_SHIFT) & 3; -} - -static inline u64 rb_time_val(unsigned long top, unsigned long bottom) -{ - u64 val; - - val = top & RB_TIME_VAL_MASK; - val <<= RB_TIME_SHIFT; - val |= bottom & RB_TIME_VAL_MASK; - - return val; -} - -static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt) -{ - unsigned long top, bottom, msb; - unsigned long c; - - /* - * If the read is interrupted by a write, then the cnt will - * be different. Loop until both top and bottom have been read - * without interruption. - */ - do { - c = local_read(&t->cnt); - top = local_read(&t->top); - bottom = local_read(&t->bottom); - msb = local_read(&t->msb); - } while (c != local_read(&t->cnt)); - - *cnt = rb_time_cnt(top); - - /* If top, msb or bottom counts don't match, this interrupted a write */ - if (*cnt != rb_time_cnt(msb) || *cnt != rb_time_cnt(bottom)) - return false; - - /* The shift to msb will lose its cnt bits */ - *ret = rb_time_val(top, bottom) | ((u64)msb << RB_TIME_MSB_SHIFT); - return true; -} - -static bool rb_time_read(rb_time_t *t, u64 *ret) -{ - unsigned long cnt; - - return __rb_time_read(t, ret, &cnt); -} - -static inline unsigned long rb_time_val_cnt(unsigned long val, unsigned long cnt) -{ - return (val & RB_TIME_VAL_MASK) | ((cnt & 3) << RB_TIME_SHIFT); -} - -static inline void rb_time_split(u64 val, unsigned long *top, unsigned long *bottom, - unsigned long *msb) -{ - *top = (unsigned long)((val >> RB_TIME_SHIFT) & RB_TIME_VAL_MASK); - *bottom = (unsigned long)(val & RB_TIME_VAL_MASK); - *msb = (unsigned long)(val >> RB_TIME_MSB_SHIFT); -} + struct buffer_data_page field; -static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long cnt) -{ - val = rb_time_val_cnt(val, cnt); - local_set(t, val); -} + trace_seq_printf(s, "\tfield: u64 timestamp;\t" + "offset:0;\tsize:%u;\tsigned:%u;\n", + (unsigned int)sizeof(field.time_stamp), + (unsigned int)is_signed_type(u64)); -static void rb_time_set(rb_time_t *t, u64 val) -{ - unsigned long cnt, top, bottom, msb; + trace_seq_printf(s, "\tfield: local_t commit;\t" + "offset:%u;\tsize:%u;\tsigned:%u;\n", + (unsigned int)offsetof(typeof(field), commit), + (unsigned int)sizeof(field.commit), + (unsigned int)is_signed_type(long)); - rb_time_split(val, &top, &bottom, &msb); + trace_seq_printf(s, "\tfield: int overwrite;\t" + "offset:%u;\tsize:%u;\tsigned:%u;\n", + (unsigned int)offsetof(typeof(field), commit), + 1, + (unsigned int)is_signed_type(long)); - /* Writes always succeed with a valid number even if it gets interrupted. */ - do { - cnt = local_inc_return(&t->cnt); - rb_time_val_set(&t->top, top, cnt); - rb_time_val_set(&t->bottom, bottom, cnt); - rb_time_val_set(&t->msb, val >> RB_TIME_MSB_SHIFT, cnt); - } while (cnt != local_read(&t->cnt)); -} + trace_seq_printf(s, "\tfield: char data;\t" + "offset:%u;\tsize:%u;\tsigned:%u;\n", + (unsigned int)offsetof(typeof(field), data), + (unsigned int)buffer->subbuf_size, + (unsigned int)is_signed_type(char)); -static inline bool -rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set) -{ - return local_try_cmpxchg(l, &expect, set); + return !trace_seq_has_overflowed(s); } -#else /* 64 bits */ - -/* local64_t always succeeds */ - -static inline bool rb_time_read(rb_time_t *t, u64 *ret) +static inline void rb_time_read(rb_time_t *t, u64 *ret) { *ret = local64_read(&t->time); - return true; } static void rb_time_set(rb_time_t *t, u64 val) { local64_set(&t->time, val); } -#endif /* * Enable this to make sure that the event passed to @@ -820,10 +676,7 @@ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer, WARN_ONCE(1, "nest (%d) greater than max", nest); fail: - /* Can only fail on 32 bit */ - if (!rb_time_read(&cpu_buffer->write_stamp, &ts)) - /* Screw it, just read the current time */ - ts = rb_time_stamp(cpu_buffer->buffer); + rb_time_read(&cpu_buffer->write_stamp, &ts); return ts; } @@ -1619,10 +1472,12 @@ static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, list_add(&bpage->list, pages); - page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags, 0); + page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags, + cpu_buffer->buffer->subbuf_order); if (!page) goto free_pages; bpage->page = page_address(page); + bpage->order = cpu_buffer->buffer->subbuf_order; rb_init_page(bpage->page); if (user_thread && fatal_signal_pending(current)) @@ -1701,7 +1556,8 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) rb_check_bpage(cpu_buffer, bpage); cpu_buffer->reader_page = bpage; - page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, 0); + + page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, cpu_buffer->buffer->subbuf_order); if (!page) goto fail_free_reader; bpage->page = page_address(page); @@ -1784,7 +1640,14 @@ struct trace_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, if (!zalloc_cpumask_var(&buffer->cpumask, GFP_KERNEL)) goto fail_free_buffer; - nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); + /* Default buffer page size - one system page */ + buffer->subbuf_order = 0; + buffer->subbuf_size = PAGE_SIZE - BUF_PAGE_HDR_SIZE; + + /* Max payload is buffer page size - header (8bytes) */ + buffer->max_data_size = buffer->subbuf_size - (sizeof(u32) * 2); + + nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size); buffer->flags = flags; buffer->clock = trace_clock_local; buffer->reader_lock_key = key; @@ -2103,7 +1966,7 @@ static void update_pages_handler(struct work_struct *work) * @size: the new size. * @cpu_id: the cpu buffer to resize * - * Minimum size is 2 * BUF_PAGE_SIZE. + * Minimum size is 2 * buffer->subbuf_size. * * Returns 0 on success and < 0 on failure. */ @@ -2125,7 +1988,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, !cpumask_test_cpu(cpu_id, buffer->cpumask)) return 0; - nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); + nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size); /* we need a minimum of two pages */ if (nr_pages < 2) @@ -2372,7 +2235,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter) */ barrier(); - if ((iter->head + length) > commit || length > BUF_PAGE_SIZE) + if ((iter->head + length) > commit || length > iter->event_size) /* Writer corrupted the read? */ goto reset; @@ -2412,11 +2275,13 @@ rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer) } static __always_inline unsigned -rb_event_index(struct ring_buffer_event *event) +rb_event_index(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) { unsigned long addr = (unsigned long)event; - return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE; + addr &= (PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1; + + return addr - BUF_PAGE_HDR_SIZE; } static void rb_inc_iter(struct ring_buffer_iter *iter) @@ -2605,6 +2470,7 @@ static inline void rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, unsigned long tail, struct rb_event_info *info) { + unsigned long bsize = READ_ONCE(cpu_buffer->buffer->subbuf_size); struct buffer_page *tail_page = info->tail_page; struct ring_buffer_event *event; unsigned long length = info->length; @@ -2613,13 +2479,13 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, * Only the event that crossed the page boundary * must fill the old tail_page with padding. */ - if (tail >= BUF_PAGE_SIZE) { + if (tail >= bsize) { /* * If the page was filled, then we still need * to update the real_end. Reset it to zero * and the reader will ignore it. */ - if (tail == BUF_PAGE_SIZE) + if (tail == bsize) tail_page->real_end = 0; local_sub(length, &tail_page->write); @@ -2647,7 +2513,7 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, * If we are less than the minimum size, we don't need to * worry about it. */ - if (tail > (BUF_PAGE_SIZE - RB_EVNT_MIN_SIZE)) { + if (tail > (bsize - RB_EVNT_MIN_SIZE)) { /* No room for any events */ /* Mark the rest of the page with padding */ @@ -2662,19 +2528,19 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, } /* Put in a discarded event */ - event->array[0] = (BUF_PAGE_SIZE - tail) - RB_EVNT_HDR_SIZE; + event->array[0] = (bsize - tail) - RB_EVNT_HDR_SIZE; event->type_len = RINGBUF_TYPE_PADDING; /* time delta must be non zero */ event->time_delta = 1; /* account for padding bytes */ - local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); + local_add(bsize - tail, &cpu_buffer->entries_bytes); /* Make sure the padding is visible before the tail_page->write update */ smp_wmb(); /* Set write to end of buffer */ - length = (tail + length) - BUF_PAGE_SIZE; + length = (tail + length) - bsize; local_sub(length, &tail_page->write); } @@ -2788,7 +2654,8 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, /* Slow path */ static struct ring_buffer_event * -rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs) +rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer, + struct ring_buffer_event *event, u64 delta, bool abs) { if (abs) event->type_len = RINGBUF_TYPE_TIME_STAMP; @@ -2796,7 +2663,7 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs) event->type_len = RINGBUF_TYPE_TIME_EXTEND; /* Not the first event on the page, or not delta? */ - if (abs || rb_event_index(event)) { + if (abs || rb_event_index(cpu_buffer, event)) { event->time_delta = delta & TS_MASK; event->array[0] = delta >> TS_SHIFT; } else { @@ -2826,7 +2693,7 @@ rb_check_timestamp(struct ring_buffer_per_cpu *cpu_buffer, (unsigned long long)info->ts, (unsigned long long)info->before, (unsigned long long)info->after, - (unsigned long long)(rb_time_read(&cpu_buffer->write_stamp, &write_stamp) ? write_stamp : 0), + (unsigned long long)({rb_time_read(&cpu_buffer->write_stamp, &write_stamp); write_stamp;}), sched_clock_stable() ? "" : "If you just came from a suspend/resume,\n" "please switch to the trace global clock:\n" @@ -2870,7 +2737,7 @@ static void rb_add_timestamp(struct ring_buffer_per_cpu *cpu_buffer, if (!abs) info->delta = 0; } - *event = rb_add_time_stamp(*event, info->delta, abs); + *event = rb_add_time_stamp(cpu_buffer, *event, info->delta, abs); *length -= RB_LEN_TIME_EXTEND; *delta = 0; } @@ -2954,10 +2821,10 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *bpage; unsigned long addr; - new_index = rb_event_index(event); + new_index = rb_event_index(cpu_buffer, event); old_index = new_index + rb_event_ts_length(event); addr = (unsigned long)event; - addr &= PAGE_MASK; + addr &= ~((PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1); bpage = READ_ONCE(cpu_buffer->tail_page); @@ -3344,6 +3211,76 @@ EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit); #define CHECK_FULL_PAGE 1L #ifdef CONFIG_RING_BUFFER_VALIDATE_TIME_DELTAS + +static const char *show_irq_str(int bits) +{ + const char *type[] = { + ".", // 0 + "s", // 1 + "h", // 2 + "Hs", // 3 + "n", // 4 + "Ns", // 5 + "Nh", // 6 + "NHs", // 7 + }; + + return type[bits]; +} + +/* Assume this is an trace event */ +static const char *show_flags(struct ring_buffer_event *event) +{ + struct trace_entry *entry; + int bits = 0; + + if (rb_event_data_length(event) - RB_EVNT_HDR_SIZE < sizeof(*entry)) + return "X"; + + entry = ring_buffer_event_data(event); + + if (entry->flags & TRACE_FLAG_SOFTIRQ) + bits |= 1; + + if (entry->flags & TRACE_FLAG_HARDIRQ) + bits |= 2; + + if (entry->flags & TRACE_FLAG_NMI) + bits |= 4; + + return show_irq_str(bits); +} + +static const char *show_irq(struct ring_buffer_event *event) +{ + struct trace_entry *entry; + + if (rb_event_data_length(event) - RB_EVNT_HDR_SIZE < sizeof(*entry)) + return ""; + + entry = ring_buffer_event_data(event); + if (entry->flags & TRACE_FLAG_IRQS_OFF) + return "d"; + return ""; +} + +static const char *show_interrupt_level(void) +{ + unsigned long pc = preempt_count(); + unsigned char level = 0; + + if (pc & SOFTIRQ_OFFSET) + level |= 1; + + if (pc & HARDIRQ_MASK) + level |= 2; + + if (pc & NMI_MASK) + level |= 4; + + return show_irq_str(level); +} + static void dump_buffer_page(struct buffer_data_page *bpage, struct rb_event_info *info, unsigned long tail) @@ -3364,34 +3301,57 @@ static void dump_buffer_page(struct buffer_data_page *bpage, case RINGBUF_TYPE_TIME_EXTEND: delta = rb_event_time_stamp(event); ts += delta; - pr_warn(" [%lld] delta:%lld TIME EXTEND\n", ts, delta); + pr_warn(" 0x%x: [%lld] delta:%lld TIME EXTEND\n", + e, ts, delta); break; case RINGBUF_TYPE_TIME_STAMP: delta = rb_event_time_stamp(event); ts = rb_fix_abs_ts(delta, ts); - pr_warn(" [%lld] absolute:%lld TIME STAMP\n", ts, delta); + pr_warn(" 0x%x: [%lld] absolute:%lld TIME STAMP\n", + e, ts, delta); break; case RINGBUF_TYPE_PADDING: ts += event->time_delta; - pr_warn(" [%lld] delta:%d PADDING\n", ts, event->time_delta); + pr_warn(" 0x%x: [%lld] delta:%d PADDING\n", + e, ts, event->time_delta); break; case RINGBUF_TYPE_DATA: ts += event->time_delta; - pr_warn(" [%lld] delta:%d\n", ts, event->time_delta); + pr_warn(" 0x%x: [%lld] delta:%d %s%s\n", + e, ts, event->time_delta, + show_flags(event), show_irq(event)); break; default: break; } } + pr_warn("expected end:0x%lx last event actually ended at:0x%x\n", tail, e); } static DEFINE_PER_CPU(atomic_t, checking); static atomic_t ts_dump; +#define buffer_warn_return(fmt, ...) \ + do { \ + /* If another report is happening, ignore this one */ \ + if (atomic_inc_return(&ts_dump) != 1) { \ + atomic_dec(&ts_dump); \ + goto out; \ + } \ + atomic_inc(&cpu_buffer->record_disabled); \ + pr_warn(fmt, ##__VA_ARGS__); \ + dump_buffer_page(bpage, info, tail); \ + atomic_dec(&ts_dump); \ + /* There's some cases in boot up that this can happen */ \ + if (WARN_ON_ONCE(system_state != SYSTEM_BOOTING)) \ + /* Do not re-enable checking */ \ + return; \ + } while (0) + /* * Check if the current event time stamp matches the deltas on * the buffer page. @@ -3445,7 +3405,12 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer, case RINGBUF_TYPE_TIME_STAMP: delta = rb_event_time_stamp(event); - ts = rb_fix_abs_ts(delta, ts); + delta = rb_fix_abs_ts(delta, ts); + if (delta < ts) { + buffer_warn_return("[CPU: %d]ABSOLUTE TIME WENT BACKWARDS: last ts: %lld absolute ts: %lld\n", + cpu_buffer->cpu, ts, delta); + } + ts = delta; break; case RINGBUF_TYPE_PADDING: @@ -3462,23 +3427,11 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer, } if ((full && ts > info->ts) || (!full && ts + info->delta != info->ts)) { - /* If another report is happening, ignore this one */ - if (atomic_inc_return(&ts_dump) != 1) { - atomic_dec(&ts_dump); - goto out; - } - atomic_inc(&cpu_buffer->record_disabled); - /* There's some cases in boot up that this can happen */ - WARN_ON_ONCE(system_state != SYSTEM_BOOTING); - pr_warn("[CPU: %d]TIME DOES NOT MATCH expected:%lld actual:%lld delta:%lld before:%lld after:%lld%s\n", - cpu_buffer->cpu, - ts + info->delta, info->ts, info->delta, - info->before, info->after, - full ? " (full)" : ""); - dump_buffer_page(bpage, info, tail); - atomic_dec(&ts_dump); - /* Do not re-enable checking */ - return; + buffer_warn_return("[CPU: %d]TIME DOES NOT MATCH expected:%lld actual:%lld delta:%lld before:%lld after:%lld%s context:%s\n", + cpu_buffer->cpu, + ts + info->delta, info->ts, info->delta, + info->before, info->after, + full ? " (full)" : "", show_interrupt_level()); } out: atomic_dec(this_cpu_ptr(&checking)); @@ -3498,16 +3451,14 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event; struct buffer_page *tail_page; unsigned long tail, write, w; - bool a_ok; - bool b_ok; /* Don't let the compiler play games with cpu_buffer->tail_page */ tail_page = info->tail_page = READ_ONCE(cpu_buffer->tail_page); /*A*/ w = local_read(&tail_page->write) & RB_WRITE_MASK; barrier(); - b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); - a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); + rb_time_read(&cpu_buffer->before_stamp, &info->before); + rb_time_read(&cpu_buffer->write_stamp, &info->after); barrier(); info->ts = rb_time_stamp(cpu_buffer->buffer); @@ -3522,7 +3473,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, if (!w) { /* Use the sub-buffer timestamp */ info->delta = 0; - } else if (unlikely(!a_ok || !b_ok || info->before != info->after)) { + } else if (unlikely(info->before != info->after)) { info->add_timestamp |= RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND; info->length += RB_LEN_TIME_EXTEND; } else { @@ -3544,7 +3495,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, tail = write - info->length; /* See if we shot pass the end of this buffer page */ - if (unlikely(write > BUF_PAGE_SIZE)) { + if (unlikely(write > cpu_buffer->buffer->subbuf_size)) { check_buffer(cpu_buffer, info, CHECK_FULL_PAGE); return rb_move_tail(cpu_buffer, tail, info); } @@ -3571,8 +3522,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, /* SLOW PATH - Interrupted between A and C */ /* Save the old before_stamp */ - a_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); - RB_WARN_ON(cpu_buffer, !a_ok); + rb_time_read(&cpu_buffer->before_stamp, &info->before); /* * Read a new timestamp and update the before_stamp to make @@ -3584,9 +3534,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, rb_time_set(&cpu_buffer->before_stamp, ts); barrier(); - /*E*/ a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); - /* Was interrupted before here, write_stamp must be valid */ - RB_WARN_ON(cpu_buffer, !a_ok); + /*E*/ rb_time_read(&cpu_buffer->write_stamp, &info->after); barrier(); /*F*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) && info->after == info->before && info->after < ts) { @@ -3678,7 +3626,7 @@ rb_reserve_next_event(struct trace_buffer *buffer, if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) { add_ts_default = RB_ADD_STAMP_ABSOLUTE; info.length += RB_LEN_TIME_EXTEND; - if (info.length > BUF_MAX_DATA_SIZE) + if (info.length > cpu_buffer->buffer->max_data_size) goto out_fail; } else { add_ts_default = RB_ADD_STAMP_NONE; @@ -3753,7 +3701,7 @@ ring_buffer_lock_reserve(struct trace_buffer *buffer, unsigned long length) if (unlikely(atomic_read(&cpu_buffer->record_disabled))) goto out; - if (unlikely(length > BUF_MAX_DATA_SIZE)) + if (unlikely(length > buffer->max_data_size)) goto out; if (unlikely(trace_recursive_lock(cpu_buffer))) @@ -3787,7 +3735,7 @@ rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *bpage = cpu_buffer->commit_page; struct buffer_page *start; - addr &= PAGE_MASK; + addr &= ~((PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1); /* Do the likely case first */ if (likely(bpage->page == (void *)addr)) { @@ -3903,7 +3851,7 @@ int ring_buffer_write(struct trace_buffer *buffer, if (atomic_read(&cpu_buffer->record_disabled)) goto out; - if (length > BUF_MAX_DATA_SIZE) + if (length > buffer->max_data_size) goto out; if (unlikely(trace_recursive_lock(cpu_buffer))) @@ -4483,6 +4431,7 @@ static struct buffer_page * rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) { struct buffer_page *reader = NULL; + unsigned long bsize = READ_ONCE(cpu_buffer->buffer->subbuf_size); unsigned long overwrite; unsigned long flags; int nr_loops = 0; @@ -4618,7 +4567,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) #define USECS_WAIT 1000000 for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) { /* If the write is past the end of page, a writer is still updating it */ - if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE)) + if (likely(!reader || rb_page_write(reader) <= bsize)) break; udelay(1); @@ -5062,7 +5011,8 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags) return NULL; /* Holds the entire event: data and meta data */ - iter->event = kmalloc(BUF_PAGE_SIZE, flags); + iter->event_size = buffer->subbuf_size; + iter->event = kmalloc(iter->event_size, flags); if (!iter->event) { kfree(iter); return NULL; @@ -5178,19 +5128,28 @@ EXPORT_SYMBOL_GPL(ring_buffer_iter_advance); */ unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu) { - /* - * Earlier, this method returned - * BUF_PAGE_SIZE * buffer->nr_pages - * Since the nr_pages field is now removed, we have converted this to - * return the per cpu buffer value. - */ if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; - return BUF_PAGE_SIZE * buffer->buffers[cpu]->nr_pages; + return buffer->subbuf_size * buffer->buffers[cpu]->nr_pages; } EXPORT_SYMBOL_GPL(ring_buffer_size); +/** + * ring_buffer_max_event_size - return the max data size of an event + * @buffer: The ring buffer. + * + * Returns the maximum size an event can be. + */ +unsigned long ring_buffer_max_event_size(struct trace_buffer *buffer) +{ + /* If abs timestamp is requested, events have a timestamp too */ + if (ring_buffer_time_stamp_abs(buffer)) + return buffer->max_data_size - RB_LEN_TIME_EXTEND; + return buffer->max_data_size; +} +EXPORT_SYMBOL_GPL(ring_buffer_max_event_size); + static void rb_clear_buffer_page(struct buffer_page *page) { local_set(&page->write, 0); @@ -5461,6 +5420,9 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a, if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages) goto out; + if (buffer_a->subbuf_order != buffer_b->subbuf_order) + goto out; + ret = -EAGAIN; if (atomic_read(&buffer_a->record_disabled)) @@ -5532,40 +5494,48 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu); * Returns: * The page allocated, or ERR_PTR */ -void *ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu) +struct buffer_data_read_page * +ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; - struct buffer_data_page *bpage = NULL; + struct buffer_data_read_page *bpage = NULL; unsigned long flags; struct page *page; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return ERR_PTR(-ENODEV); + bpage = kzalloc(sizeof(*bpage), GFP_KERNEL); + if (!bpage) + return ERR_PTR(-ENOMEM); + + bpage->order = buffer->subbuf_order; cpu_buffer = buffer->buffers[cpu]; local_irq_save(flags); arch_spin_lock(&cpu_buffer->lock); if (cpu_buffer->free_page) { - bpage = cpu_buffer->free_page; + bpage->data = cpu_buffer->free_page; cpu_buffer->free_page = NULL; } arch_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags); - if (bpage) + if (bpage->data) goto out; - page = alloc_pages_node(cpu_to_node(cpu), - GFP_KERNEL | __GFP_NORETRY, 0); - if (!page) + page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY, + cpu_buffer->buffer->subbuf_order); + if (!page) { + kfree(bpage); return ERR_PTR(-ENOMEM); + } - bpage = page_address(page); + bpage->data = page_address(page); out: - rb_init_page(bpage); + rb_init_page(bpage->data); return bpage; } @@ -5575,14 +5545,15 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page); * ring_buffer_free_read_page - free an allocated read page * @buffer: the buffer the page was allocate for * @cpu: the cpu buffer the page came from - * @data: the page to free + * @data_page: the page to free * * Free a page allocated from ring_buffer_alloc_read_page. */ -void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data) +void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, + struct buffer_data_read_page *data_page) { struct ring_buffer_per_cpu *cpu_buffer; - struct buffer_data_page *bpage = data; + struct buffer_data_page *bpage = data_page->data; struct page *page = virt_to_page(bpage); unsigned long flags; @@ -5591,8 +5562,12 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data cpu_buffer = buffer->buffers[cpu]; - /* If the page is still in use someplace else, we can't reuse it */ - if (page_ref_count(page) > 1) + /* + * If the page is still in use someplace else, or order of the page + * is different from the subbuffer order of the buffer - + * we can't reuse it + */ + if (page_ref_count(page) > 1 || data_page->order != buffer->subbuf_order) goto out; local_irq_save(flags); @@ -5607,7 +5582,8 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data local_irq_restore(flags); out: - free_page((unsigned long)bpage); + free_pages((unsigned long)bpage, data_page->order); + kfree(data_page); } EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); @@ -5628,9 +5604,10 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); * rpage = ring_buffer_alloc_read_page(buffer, cpu); * if (IS_ERR(rpage)) * return PTR_ERR(rpage); - * ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0); + * ret = ring_buffer_read_page(buffer, rpage, len, cpu, 0); * if (ret >= 0) - * process_page(rpage, ret); + * process_page(ring_buffer_read_page_data(rpage), ret); + * ring_buffer_free_read_page(buffer, cpu, rpage); * * When @full is set, the function will not return true unless * the writer is off the reader page. @@ -5645,7 +5622,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); * <0 if no data has been transferred. */ int ring_buffer_read_page(struct trace_buffer *buffer, - void **data_page, size_t len, int cpu, int full) + struct buffer_data_read_page *data_page, + size_t len, int cpu, int full) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; struct ring_buffer_event *event; @@ -5670,10 +5648,12 @@ int ring_buffer_read_page(struct trace_buffer *buffer, len -= BUF_PAGE_HDR_SIZE; - if (!data_page) + if (!data_page || !data_page->data) + goto out; + if (data_page->order != buffer->subbuf_order) goto out; - bpage = *data_page; + bpage = data_page->data; if (!bpage) goto out; @@ -5767,11 +5747,11 @@ int ring_buffer_read_page(struct trace_buffer *buffer, /* swap the pages */ rb_init_page(bpage); bpage = reader->page; - reader->page = *data_page; + reader->page = data_page->data; local_set(&reader->write, 0); local_set(&reader->entries, 0); reader->read = 0; - *data_page = bpage; + data_page->data = bpage; /* * Use the real_end for the data size, @@ -5793,7 +5773,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, /* If there is room at the end of the page to save the * missed events, then record it there. */ - if (BUF_PAGE_SIZE - commit >= sizeof(missed_events)) { + if (buffer->subbuf_size - commit >= sizeof(missed_events)) { memcpy(&bpage->data[commit], &missed_events, sizeof(missed_events)); local_add(RB_MISSED_STORED, &bpage->commit); @@ -5805,8 +5785,8 @@ int ring_buffer_read_page(struct trace_buffer *buffer, /* * This page may be off to user land. Zero it out here. */ - if (commit < BUF_PAGE_SIZE) - memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit); + if (commit < buffer->subbuf_size) + memset(&bpage->data[commit], 0, buffer->subbuf_size - commit); out_unlock: raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); @@ -5816,6 +5796,209 @@ int ring_buffer_read_page(struct trace_buffer *buffer, } EXPORT_SYMBOL_GPL(ring_buffer_read_page); +/** + * ring_buffer_read_page_data - get pointer to the data in the page. + * @page: the page to get the data from + * + * Returns pointer to the actual data in this page. + */ +void *ring_buffer_read_page_data(struct buffer_data_read_page *page) +{ + return page->data; +} +EXPORT_SYMBOL_GPL(ring_buffer_read_page_data); + +/** + * ring_buffer_subbuf_size_get - get size of the sub buffer. + * @buffer: the buffer to get the sub buffer size from + * + * Returns size of the sub buffer, in bytes. + */ +int ring_buffer_subbuf_size_get(struct trace_buffer *buffer) +{ + return buffer->subbuf_size + BUF_PAGE_HDR_SIZE; +} +EXPORT_SYMBOL_GPL(ring_buffer_subbuf_size_get); + +/** + * ring_buffer_subbuf_order_get - get order of system sub pages in one buffer page. + * @buffer: The ring_buffer to get the system sub page order from + * + * By default, one ring buffer sub page equals to one system page. This parameter + * is configurable, per ring buffer. The size of the ring buffer sub page can be + * extended, but must be an order of system page size. + * + * Returns the order of buffer sub page size, in system pages: + * 0 means the sub buffer size is 1 system page and so forth. + * In case of an error < 0 is returned. + */ +int ring_buffer_subbuf_order_get(struct trace_buffer *buffer) +{ + if (!buffer) + return -EINVAL; + + return buffer->subbuf_order; +} +EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_get); + +/** + * ring_buffer_subbuf_order_set - set the size of ring buffer sub page. + * @buffer: The ring_buffer to set the new page size. + * @order: Order of the system pages in one sub buffer page + * + * By default, one ring buffer pages equals to one system page. This API can be + * used to set new size of the ring buffer page. The size must be order of + * system page size, that's why the input parameter @order is the order of + * system pages that are allocated for one ring buffer page: + * 0 - 1 system page + * 1 - 2 system pages + * 3 - 4 system pages + * ... + * + * Returns 0 on success or < 0 in case of an error. + */ +int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct buffer_page *bpage, *tmp; + int old_order, old_size; + int nr_pages; + int psize; + int err; + int cpu; + + if (!buffer || order < 0) + return -EINVAL; + + if (buffer->subbuf_order == order) + return 0; + + psize = (1 << order) * PAGE_SIZE; + if (psize <= BUF_PAGE_HDR_SIZE) + return -EINVAL; + + old_order = buffer->subbuf_order; + old_size = buffer->subbuf_size; + + /* prevent another thread from changing buffer sizes */ + mutex_lock(&buffer->mutex); + atomic_inc(&buffer->record_disabled); + + /* Make sure all commits have finished */ + synchronize_rcu(); + + buffer->subbuf_order = order; + buffer->subbuf_size = psize - BUF_PAGE_HDR_SIZE; + + /* Make sure all new buffers are allocated, before deleting the old ones */ + for_each_buffer_cpu(buffer, cpu) { + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + continue; + + cpu_buffer = buffer->buffers[cpu]; + + /* Update the number of pages to match the new size */ + nr_pages = old_size * buffer->buffers[cpu]->nr_pages; + nr_pages = DIV_ROUND_UP(nr_pages, buffer->subbuf_size); + + /* we need a minimum of two pages */ + if (nr_pages < 2) + nr_pages = 2; + + cpu_buffer->nr_pages_to_update = nr_pages; + + /* Include the reader page */ + nr_pages++; + + /* Allocate the new size buffer */ + INIT_LIST_HEAD(&cpu_buffer->new_pages); + if (__rb_allocate_pages(cpu_buffer, nr_pages, + &cpu_buffer->new_pages)) { + /* not enough memory for new pages */ + err = -ENOMEM; + goto error; + } + } + + for_each_buffer_cpu(buffer, cpu) { + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + continue; + + cpu_buffer = buffer->buffers[cpu]; + + /* Clear the head bit to make the link list normal to read */ + rb_head_page_deactivate(cpu_buffer); + + /* Now walk the list and free all the old sub buffers */ + list_for_each_entry_safe(bpage, tmp, cpu_buffer->pages, list) { + list_del_init(&bpage->list); + free_buffer_page(bpage); + } + /* The above loop stopped an the last page needing to be freed */ + bpage = list_entry(cpu_buffer->pages, struct buffer_page, list); + free_buffer_page(bpage); + + /* Free the current reader page */ + free_buffer_page(cpu_buffer->reader_page); + + /* One page was allocated for the reader page */ + cpu_buffer->reader_page = list_entry(cpu_buffer->new_pages.next, + struct buffer_page, list); + list_del_init(&cpu_buffer->reader_page->list); + + /* The cpu_buffer pages are a link list with no head */ + cpu_buffer->pages = cpu_buffer->new_pages.next; + cpu_buffer->new_pages.next->prev = cpu_buffer->new_pages.prev; + cpu_buffer->new_pages.prev->next = cpu_buffer->new_pages.next; + + /* Clear the new_pages list */ + INIT_LIST_HEAD(&cpu_buffer->new_pages); + + cpu_buffer->head_page + = list_entry(cpu_buffer->pages, struct buffer_page, list); + cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page; + + cpu_buffer->nr_pages = cpu_buffer->nr_pages_to_update; + cpu_buffer->nr_pages_to_update = 0; + + free_pages((unsigned long)cpu_buffer->free_page, old_order); + cpu_buffer->free_page = NULL; + + rb_head_page_activate(cpu_buffer); + + rb_check_pages(cpu_buffer); + } + + atomic_dec(&buffer->record_disabled); + mutex_unlock(&buffer->mutex); + + return 0; + +error: + buffer->subbuf_order = old_order; + buffer->subbuf_size = old_size; + + atomic_dec(&buffer->record_disabled); + mutex_unlock(&buffer->mutex); + + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; + + if (!cpu_buffer->nr_pages_to_update) + continue; + + list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages, list) { + list_del_init(&bpage->list); + free_buffer_page(bpage); + } + } + + return err; +} +EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_set); + /* * We only allocate new buffers, never free them if the CPU goes down. * If we were to free the buffer, then the user would lose any trace that was in diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index aef34673d79d..008187ebd7fe 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -104,10 +104,11 @@ static enum event_status read_event(int cpu) static enum event_status read_page(int cpu) { + struct buffer_data_read_page *bpage; struct ring_buffer_event *event; struct rb_page *rpage; unsigned long commit; - void *bpage; + int page_size; int *entry; int ret; int inc; @@ -117,14 +118,15 @@ static enum event_status read_page(int cpu) if (IS_ERR(bpage)) return EVENT_DROPPED; - ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1); + page_size = ring_buffer_subbuf_size_get(buffer); + ret = ring_buffer_read_page(buffer, bpage, page_size, cpu, 1); if (ret >= 0) { - rpage = bpage; + rpage = ring_buffer_read_page_data(bpage); /* The commit may have missed event flags set, clear them */ commit = local_read(&rpage->commit) & 0xfffff; for (i = 0; i < commit && !test_error ; i += inc) { - if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) { + if (i >= (page_size - offsetof(struct rb_page, data))) { TEST_ERROR(); break; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a0defe156b57..2a7c6fd934e9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1263,10 +1263,17 @@ static void set_buffer_entries(struct array_buffer *buf, unsigned long val); int tracing_alloc_snapshot_instance(struct trace_array *tr) { + int order; int ret; if (!tr->allocated_snapshot) { + /* Make the snapshot buffer have the same order as main buffer */ + order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); + ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order); + if (ret < 0) + return ret; + /* allocate spare buffer */ ret = resize_buffer_duplicate_size(&tr->max_buffer, &tr->array_buffer, RING_BUFFER_ALL_CPUS); @@ -1286,6 +1293,7 @@ static void free_snapshot(struct trace_array *tr) * The max_tr ring buffer has some state (e.g. ring->clock) and * we want preserve it. */ + ring_buffer_subbuf_order_set(tr->max_buffer.buffer, 0); ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); set_buffer_entries(&tr->max_buffer, 1); tracing_reset_online_cpus(&tr->max_buffer); @@ -3767,7 +3775,7 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str, /* OK if part of the temp seq buffer */ if ((addr >= (unsigned long)iter->tmp_seq.buffer) && - (addr < (unsigned long)iter->tmp_seq.buffer + PAGE_SIZE)) + (addr < (unsigned long)iter->tmp_seq.buffer + TRACE_SEQ_BUFFER_SIZE)) return true; /* Core rodata can not be freed */ @@ -5032,7 +5040,7 @@ static int tracing_release(struct inode *inode, struct file *file) return 0; } -static int tracing_release_generic_tr(struct inode *inode, struct file *file) +int tracing_release_generic_tr(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; @@ -6946,8 +6954,8 @@ waitagain: goto out; } - if (cnt >= PAGE_SIZE) - cnt = PAGE_SIZE - 1; + if (cnt >= TRACE_SEQ_BUFFER_SIZE) + cnt = TRACE_SEQ_BUFFER_SIZE - 1; /* reset all but tr, trace, and overruns */ trace_iterator_reset(iter); @@ -7292,8 +7300,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, enum event_trigger_type tt = ETT_NONE; struct trace_buffer *buffer; struct print_entry *entry; + int meta_size; ssize_t written; - int size; + size_t size; int len; /* Used in tracing_mark_raw_write() as well */ @@ -7306,23 +7315,44 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, if (!(tr->trace_flags & TRACE_ITER_MARKERS)) return -EINVAL; - if (cnt > TRACE_BUF_SIZE) - cnt = TRACE_BUF_SIZE; - - BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE); + if ((ssize_t)cnt < 0) + return -EINVAL; - size = sizeof(*entry) + cnt + 2; /* add '\0' and possible '\n' */ + meta_size = sizeof(*entry) + 2; /* add '\0' and possible '\n' */ + again: + size = cnt + meta_size; /* If less than "<faulted>", then make sure we can still add that */ if (cnt < FAULTED_SIZE) size += FAULTED_SIZE - cnt; + if (size > TRACE_SEQ_BUFFER_SIZE) { + cnt -= size - TRACE_SEQ_BUFFER_SIZE; + goto again; + } + buffer = tr->array_buffer.buffer; event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, tracing_gen_ctx()); - if (unlikely(!event)) + if (unlikely(!event)) { + /* + * If the size was greater than what was allowed, then + * make it smaller and try again. + */ + if (size > ring_buffer_max_event_size(buffer)) { + /* cnt < FAULTED size should never be bigger than max */ + if (WARN_ON_ONCE(cnt < FAULTED_SIZE)) + return -EBADF; + cnt = ring_buffer_max_event_size(buffer) - meta_size; + /* The above should only happen once */ + if (WARN_ON_ONCE(cnt + meta_size == size)) + return -EBADF; + goto again; + } + /* Ring buffer disabled, return as if not open for write */ return -EBADF; + } entry = ring_buffer_event_data(event); entry->ip = _THIS_IP_; @@ -7357,9 +7387,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, return written; } -/* Limit it for now to 3K (including tag) */ -#define RAW_DATA_MAX_SIZE (1024*3) - static ssize_t tracing_mark_raw_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) @@ -7381,19 +7408,18 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf, return -EINVAL; /* The marker must at least have a tag id */ - if (cnt < sizeof(unsigned int) || cnt > RAW_DATA_MAX_SIZE) + if (cnt < sizeof(unsigned int)) return -EINVAL; - if (cnt > TRACE_BUF_SIZE) - cnt = TRACE_BUF_SIZE; - - BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE); - size = sizeof(*entry) + cnt; if (cnt < FAULT_SIZE_ID) size += FAULT_SIZE_ID - cnt; buffer = tr->array_buffer.buffer; + + if (size > ring_buffer_max_event_size(buffer)) + return -EINVAL; + event = __trace_buffer_lock_reserve(buffer, TRACE_RAW_DATA, size, tracing_gen_ctx()); if (!event) @@ -7578,6 +7604,7 @@ struct ftrace_buffer_info { struct trace_iterator iter; void *spare; unsigned int spare_cpu; + unsigned int spare_size; unsigned int read; }; @@ -8282,6 +8309,8 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, { struct ftrace_buffer_info *info = filp->private_data; struct trace_iterator *iter = &info->iter; + void *trace_data; + int page_size; ssize_t ret = 0; ssize_t size; @@ -8293,6 +8322,17 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, return -EBUSY; #endif + page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer); + + /* Make sure the spare matches the current sub buffer size */ + if (info->spare) { + if (page_size != info->spare_size) { + ring_buffer_free_read_page(iter->array_buffer->buffer, + info->spare_cpu, info->spare); + info->spare = NULL; + } + } + if (!info->spare) { info->spare = ring_buffer_alloc_read_page(iter->array_buffer->buffer, iter->cpu_file); @@ -8301,19 +8341,20 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, info->spare = NULL; } else { info->spare_cpu = iter->cpu_file; + info->spare_size = page_size; } } if (!info->spare) return ret; /* Do we have previous read data to read? */ - if (info->read < PAGE_SIZE) + if (info->read < page_size) goto read; again: trace_access_lock(iter->cpu_file); ret = ring_buffer_read_page(iter->array_buffer->buffer, - &info->spare, + info->spare, count, iter->cpu_file, 0); trace_access_unlock(iter->cpu_file); @@ -8334,11 +8375,11 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, info->read = 0; read: - size = PAGE_SIZE - info->read; + size = page_size - info->read; if (size > count) size = count; - - ret = copy_to_user(ubuf, info->spare + info->read, size); + trace_data = ring_buffer_read_page_data(info->spare); + ret = copy_to_user(ubuf, trace_data + info->read, size); if (ret == size) return -EFAULT; @@ -8449,6 +8490,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, .spd_release = buffer_spd_release, }; struct buffer_ref *ref; + int page_size; int entries, i; ssize_t ret = 0; @@ -8457,13 +8499,14 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, return -EBUSY; #endif - if (*ppos & (PAGE_SIZE - 1)) + page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer); + if (*ppos & (page_size - 1)) return -EINVAL; - if (len & (PAGE_SIZE - 1)) { - if (len < PAGE_SIZE) + if (len & (page_size - 1)) { + if (len < page_size) return -EINVAL; - len &= PAGE_MASK; + len &= (~(page_size - 1)); } if (splice_grow_spd(pipe, &spd)) @@ -8473,7 +8516,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, trace_access_lock(iter->cpu_file); entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file); - for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= PAGE_SIZE) { + for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= page_size) { struct page *page; int r; @@ -8494,7 +8537,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, } ref->cpu = iter->cpu_file; - r = ring_buffer_read_page(ref->buffer, &ref->page, + r = ring_buffer_read_page(ref->buffer, ref->page, len, iter->cpu_file, 1); if (r < 0) { ring_buffer_free_read_page(ref->buffer, ref->cpu, @@ -8503,14 +8546,14 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, break; } - page = virt_to_page(ref->page); + page = virt_to_page(ring_buffer_read_page_data(ref->page)); spd.pages[i] = page; - spd.partial[i].len = PAGE_SIZE; + spd.partial[i].len = page_size; spd.partial[i].offset = 0; spd.partial[i].private = (unsigned long)ref; spd.nr_pages++; - *ppos += PAGE_SIZE; + *ppos += page_size; entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file); } @@ -9354,6 +9397,103 @@ static const struct file_operations buffer_percent_fops = { .llseek = default_llseek, }; +static ssize_t +buffer_subbuf_size_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + size_t size; + char buf[64]; + int order; + int r; + + order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); + size = (PAGE_SIZE << order) / 1024; + + r = sprintf(buf, "%zd\n", size); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +buffer_subbuf_size_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + unsigned long val; + int old_order; + int order; + int pages; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + val *= 1024; /* value passed in is in KB */ + + pages = DIV_ROUND_UP(val, PAGE_SIZE); + order = fls(pages - 1); + + /* limit between 1 and 128 system pages */ + if (order < 0 || order > 7) + return -EINVAL; + + /* Do not allow tracing while changing the order of the ring buffer */ + tracing_stop_tr(tr); + + old_order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); + if (old_order == order) + goto out; + + ret = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, order); + if (ret) + goto out; + +#ifdef CONFIG_TRACER_MAX_TRACE + + if (!tr->allocated_snapshot) + goto out_max; + + ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order); + if (ret) { + /* Put back the old order */ + cnt = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, old_order); + if (WARN_ON_ONCE(cnt)) { + /* + * AARGH! We are left with different orders! + * The max buffer is our "snapshot" buffer. + * When a tracer needs a snapshot (one of the + * latency tracers), it swaps the max buffer + * with the saved snap shot. We succeeded to + * update the order of the main buffer, but failed to + * update the order of the max buffer. But when we tried + * to reset the main buffer to the original size, we + * failed there too. This is very unlikely to + * happen, but if it does, warn and kill all + * tracing. + */ + tracing_disabled = 1; + } + goto out; + } + out_max: +#endif + (*ppos)++; + out: + if (ret) + cnt = ret; + tracing_start_tr(tr); + return cnt; +} + +static const struct file_operations buffer_subbuf_size_fops = { + .open = tracing_open_generic_tr, + .read = buffer_subbuf_size_read, + .write = buffer_subbuf_size_write, + .release = tracing_release_generic_tr, + .llseek = default_llseek, +}; + static struct dentry *trace_instance_dir; static void @@ -9504,7 +9644,8 @@ static int trace_array_create_dir(struct trace_array *tr) return ret; } -static struct trace_array *trace_array_create(const char *name) +static struct trace_array * +trace_array_create_systems(const char *name, const char *systems) { struct trace_array *tr; int ret; @@ -9524,6 +9665,12 @@ static struct trace_array *trace_array_create(const char *name) if (!zalloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL)) goto out_free_tr; + if (systems) { + tr->system_names = kstrdup_const(systems, GFP_KERNEL); + if (!tr->system_names) + goto out_free_tr; + } + tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS; cpumask_copy(tr->tracing_cpumask, cpu_all_mask); @@ -9570,12 +9717,18 @@ static struct trace_array *trace_array_create(const char *name) free_trace_buffers(tr); free_cpumask_var(tr->pipe_cpumask); free_cpumask_var(tr->tracing_cpumask); + kfree_const(tr->system_names); kfree(tr->name); kfree(tr); return ERR_PTR(ret); } +static struct trace_array *trace_array_create(const char *name) +{ + return trace_array_create_systems(name, NULL); +} + static int instance_mkdir(const char *name) { struct trace_array *tr; @@ -9601,6 +9754,7 @@ out_unlock: /** * trace_array_get_by_name - Create/Lookup a trace array, given its name. * @name: The name of the trace array to be looked up/created. + * @systems: A list of systems to create event directories for (NULL for all) * * Returns pointer to trace array with given name. * NULL, if it cannot be created. @@ -9614,7 +9768,7 @@ out_unlock: * trace_array_put() is called, user space can not delete it. * */ -struct trace_array *trace_array_get_by_name(const char *name) +struct trace_array *trace_array_get_by_name(const char *name, const char *systems) { struct trace_array *tr; @@ -9626,7 +9780,7 @@ struct trace_array *trace_array_get_by_name(const char *name) goto out_unlock; } - tr = trace_array_create(name); + tr = trace_array_create_systems(name, systems); if (IS_ERR(tr)) tr = NULL; @@ -9673,6 +9827,7 @@ static int __remove_instance(struct trace_array *tr) free_cpumask_var(tr->pipe_cpumask); free_cpumask_var(tr->tracing_cpumask); + kfree_const(tr->system_names); kfree(tr->name); kfree(tr); @@ -9805,6 +9960,9 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) trace_create_file("buffer_percent", TRACE_MODE_WRITE, d_tracer, tr, &buffer_percent_fops); + trace_create_file("buffer_subbuf_size_kb", TRACE_MODE_WRITE, d_tracer, + tr, &buffer_subbuf_size_fops); + create_trace_options_dir(tr); #ifdef CONFIG_TRACER_MAX_TRACE @@ -10391,7 +10549,7 @@ __init static void enable_instances(void) if (IS_ENABLED(CONFIG_TRACER_MAX_TRACE)) do_allocate_snapshot(tok); - tr = trace_array_get_by_name(tok); + tr = trace_array_get_by_name(tok, NULL); if (!tr) { pr_warn("Failed to create instance buffer %s\n", curr_str); continue; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 0489e72c8169..00f873910c5d 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -377,6 +377,7 @@ struct trace_array { unsigned char trace_flags_index[TRACE_FLAGS_MAX_SIZE]; unsigned int flags; raw_spinlock_t start_lock; + const char *system_names; struct list_head err_log; struct dentry *dir; struct dentry *options; @@ -615,6 +616,7 @@ void tracing_reset_all_online_cpus(void); void tracing_reset_all_online_cpus_unlocked(void); int tracing_open_generic(struct inode *inode, struct file *filp); int tracing_open_generic_tr(struct inode *inode, struct file *filp); +int tracing_release_generic_tr(struct inode *inode, struct file *file); int tracing_open_file_tr(struct inode *inode, struct file *filp); int tracing_release_file_tr(struct inode *inode, struct file *filp); int tracing_single_release_file_tr(struct inode *inode, struct file *filp); diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c index 7ccc7a8e155b..dbe29b4c6a7a 100644 --- a/kernel/trace/trace_boot.c +++ b/kernel/trace/trace_boot.c @@ -633,7 +633,7 @@ trace_boot_init_instances(struct xbc_node *node) if (!p || *p == '\0') continue; - tr = trace_array_get_by_name(p); + tr = trace_array_get_by_name(p, NULL); if (!tr) { pr_err("Failed to get trace instance %s\n", p); continue; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f29e815ca5b2..7c364b87352e 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1893,9 +1893,9 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, } static ssize_t -show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) +show_header_page_file(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - int (*func)(struct trace_seq *s) = filp->private_data; + struct trace_array *tr = filp->private_data; struct trace_seq *s; int r; @@ -1908,7 +1908,31 @@ show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) trace_seq_init(s); - func(s); + ring_buffer_print_page_header(tr->array_buffer.buffer, s); + r = simple_read_from_buffer(ubuf, cnt, ppos, + s->buffer, trace_seq_used(s)); + + kfree(s); + + return r; +} + +static ssize_t +show_header_event_file(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + struct trace_seq *s; + int r; + + if (*ppos) + return 0; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + trace_seq_init(s); + + ring_buffer_print_entry_header(s); r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, trace_seq_used(s)); @@ -2165,10 +2189,18 @@ static const struct file_operations ftrace_tr_enable_fops = { .release = subsystem_release, }; -static const struct file_operations ftrace_show_header_fops = { - .open = tracing_open_generic, - .read = show_header, +static const struct file_operations ftrace_show_header_page_fops = { + .open = tracing_open_generic_tr, + .read = show_header_page_file, + .llseek = default_llseek, + .release = tracing_release_generic_tr, +}; + +static const struct file_operations ftrace_show_header_event_fops = { + .open = tracing_open_generic_tr, + .read = show_header_event_file, .llseek = default_llseek, + .release = tracing_release_generic_tr, }; static int @@ -2896,6 +2928,27 @@ void trace_event_eval_update(struct trace_eval_map **map, int len) up_write(&trace_event_sem); } +static bool event_in_systems(struct trace_event_call *call, + const char *systems) +{ + const char *system; + const char *p; + + if (!systems) + return true; + + system = call->class->system; + p = strstr(systems, system); + if (!p) + return false; + + if (p != systems && !isspace(*(p - 1)) && *(p - 1) != ',') + return false; + + p += strlen(system); + return !*p || isspace(*p) || *p == ','; +} + static struct trace_event_file * trace_create_new_event(struct trace_event_call *call, struct trace_array *tr) @@ -2905,9 +2958,12 @@ trace_create_new_event(struct trace_event_call *call, struct trace_event_file *file; unsigned int first; + if (!event_in_systems(call, tr->system_names)) + return NULL; + file = kmem_cache_alloc(file_cachep, GFP_TRACE); if (!file) - return NULL; + return ERR_PTR(-ENOMEM); pid_list = rcu_dereference_protected(tr->filtered_pids, lockdep_is_held(&event_mutex)); @@ -2972,8 +3028,17 @@ __trace_add_new_event(struct trace_event_call *call, struct trace_array *tr) struct trace_event_file *file; file = trace_create_new_event(call, tr); + /* + * trace_create_new_event() returns ERR_PTR(-ENOMEM) if failed + * allocation, or NULL if the event is not part of the tr->system_names. + * When the event is not part of the tr->system_names, return zero, not + * an error. + */ if (!file) - return -ENOMEM; + return 0; + + if (IS_ERR(file)) + return PTR_ERR(file); if (eventdir_initialized) return event_create_dir(tr->event_dir, file); @@ -3012,8 +3077,17 @@ __trace_early_add_new_event(struct trace_event_call *call, int ret; file = trace_create_new_event(call, tr); + /* + * trace_create_new_event() returns ERR_PTR(-ENOMEM) if failed + * allocation, or NULL if the event is not part of the tr->system_names. + * When the event is not part of the tr->system_names, return zero, not + * an error. + */ if (!file) - return -ENOMEM; + return 0; + + if (IS_ERR(file)) + return PTR_ERR(file); ret = event_define_fields(call); if (ret) @@ -3752,17 +3826,16 @@ static int events_callback(const char *name, umode_t *mode, void **data, return 1; } - if (strcmp(name, "header_page") == 0) - *data = ring_buffer_print_page_header; - - else if (strcmp(name, "header_event") == 0) - *data = ring_buffer_print_entry_header; + if (strcmp(name, "header_page") == 0) { + *mode = TRACE_MODE_READ; + *fops = &ftrace_show_header_page_fops; - else + } else if (strcmp(name, "header_event") == 0) { + *mode = TRACE_MODE_READ; + *fops = &ftrace_show_header_event_fops; + } else return 0; - *mode = TRACE_MODE_READ; - *fops = &ftrace_show_header_fops; return 1; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 5ecf3c8bde20..6ece1308d36a 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -4805,36 +4805,35 @@ static int parse_actions(struct hist_trigger_data *hist_data) int len; for (i = 0; i < hist_data->attrs->n_actions; i++) { + enum handler_id hid = 0; + char *action_str; + str = hist_data->attrs->action_str[i]; - if ((len = str_has_prefix(str, "onmatch("))) { - char *action_str = str + len; + if ((len = str_has_prefix(str, "onmatch("))) + hid = HANDLER_ONMATCH; + else if ((len = str_has_prefix(str, "onmax("))) + hid = HANDLER_ONMAX; + else if ((len = str_has_prefix(str, "onchange("))) + hid = HANDLER_ONCHANGE; - data = onmatch_parse(tr, action_str); - if (IS_ERR(data)) { - ret = PTR_ERR(data); - break; - } - } else if ((len = str_has_prefix(str, "onmax("))) { - char *action_str = str + len; + action_str = str + len; - data = track_data_parse(hist_data, action_str, - HANDLER_ONMAX); - if (IS_ERR(data)) { - ret = PTR_ERR(data); - break; - } - } else if ((len = str_has_prefix(str, "onchange("))) { - char *action_str = str + len; + switch (hid) { + case HANDLER_ONMATCH: + data = onmatch_parse(tr, action_str); + break; + case HANDLER_ONMAX: + case HANDLER_ONCHANGE: + data = track_data_parse(hist_data, action_str, hid); + break; + default: + data = ERR_PTR(-EINVAL); + break; + } - data = track_data_parse(hist_data, action_str, - HANDLER_ONCHANGE); - if (IS_ERR(data)) { - ret = PTR_ERR(data); - break; - } - } else { - ret = -EINVAL; + if (IS_ERR(data)) { + ret = PTR_ERR(data); break; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 52f8b537dd0a..c4c6e0e0068b 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -487,8 +487,8 @@ static int __register_trace_kprobe(struct trace_kprobe *tk) return -EINVAL; if (within_notrace_func(tk)) { - pr_warn("Could not probe notrace function %s\n", - trace_kprobe_symbol(tk)); + pr_warn("Could not probe notrace function %ps\n", + (void *)trace_kprobe_address(tk)); return -EINVAL; } diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c index 7be97229ddf8..c158d65a8a88 100644 --- a/kernel/trace/trace_seq.c +++ b/kernel/trace/trace_seq.c @@ -13,9 +13,6 @@ * trace_seq_init() more than once to reset the trace_seq to start * from scratch. * - * The buffer size is currently PAGE_SIZE, although it may become dynamic - * in the future. - * * A write to the buffer will either succeed or fail. That is, unlike * sprintf() there will not be a partial write (well it may write into * the buffer but it wont update the pointers). This allows users to diff --git a/lib/fw_table.c b/lib/fw_table.c index c49a09ee3853..c3569d2ba503 100644 --- a/lib/fw_table.c +++ b/lib/fw_table.c @@ -12,12 +12,14 @@ #include <linux/kernel.h> #include <linux/string.h> #include <linux/types.h> +#include <linux/fw_table.h> enum acpi_subtable_type { ACPI_SUBTABLE_COMMON, ACPI_SUBTABLE_HMAT, ACPI_SUBTABLE_PRMT, ACPI_SUBTABLE_CEDT, + CDAT_SUBTABLE, }; struct acpi_subtable_entry { @@ -25,7 +27,7 @@ struct acpi_subtable_entry { enum acpi_subtable_type type; }; -static unsigned long __init_or_acpilib +static unsigned long __init_or_fwtbl_lib acpi_get_entry_type(struct acpi_subtable_entry *entry) { switch (entry->type) { @@ -37,11 +39,13 @@ acpi_get_entry_type(struct acpi_subtable_entry *entry) return 0; case ACPI_SUBTABLE_CEDT: return entry->hdr->cedt.type; + case CDAT_SUBTABLE: + return entry->hdr->cdat.type; } return 0; } -static unsigned long __init_or_acpilib +static unsigned long __init_or_fwtbl_lib acpi_get_entry_length(struct acpi_subtable_entry *entry) { switch (entry->type) { @@ -53,11 +57,16 @@ acpi_get_entry_length(struct acpi_subtable_entry *entry) return entry->hdr->prmt.length; case ACPI_SUBTABLE_CEDT: return entry->hdr->cedt.length; + case CDAT_SUBTABLE: { + __le16 length = (__force __le16)entry->hdr->cdat.length; + + return le16_to_cpu(length); + } } return 0; } -static unsigned long __init_or_acpilib +static unsigned long __init_or_fwtbl_lib acpi_get_subtable_header_length(struct acpi_subtable_entry *entry) { switch (entry->type) { @@ -69,11 +78,13 @@ acpi_get_subtable_header_length(struct acpi_subtable_entry *entry) return sizeof(entry->hdr->prmt); case ACPI_SUBTABLE_CEDT: return sizeof(entry->hdr->cedt); + case CDAT_SUBTABLE: + return sizeof(entry->hdr->cdat); } return 0; } -static enum acpi_subtable_type __init_or_acpilib +static enum acpi_subtable_type __init_or_fwtbl_lib acpi_get_subtable_type(char *id) { if (strncmp(id, ACPI_SIG_HMAT, 4) == 0) @@ -82,12 +93,27 @@ acpi_get_subtable_type(char *id) return ACPI_SUBTABLE_PRMT; if (strncmp(id, ACPI_SIG_CEDT, 4) == 0) return ACPI_SUBTABLE_CEDT; + if (strncmp(id, ACPI_SIG_CDAT, 4) == 0) + return CDAT_SUBTABLE; return ACPI_SUBTABLE_COMMON; } -static __init_or_acpilib int call_handler(struct acpi_subtable_proc *proc, - union acpi_subtable_headers *hdr, - unsigned long end) +static unsigned long __init_or_fwtbl_lib +acpi_table_get_length(enum acpi_subtable_type type, + union fw_table_header *header) +{ + if (type == CDAT_SUBTABLE) { + __le32 length = (__force __le32)header->cdat.length; + + return le32_to_cpu(length); + } + + return header->acpi.length; +} + +static __init_or_fwtbl_lib int call_handler(struct acpi_subtable_proc *proc, + union acpi_subtable_headers *hdr, + unsigned long end) { if (proc->handler) return proc->handler(hdr, end); @@ -119,22 +145,25 @@ static __init_or_acpilib int call_handler(struct acpi_subtable_proc *proc, * On success returns sum of all matching entries for all proc handlers. * Otherwise, -ENODEV or -EINVAL is returned. */ -int __init_or_acpilib +int __init_or_fwtbl_lib acpi_parse_entries_array(char *id, unsigned long table_size, - struct acpi_table_header *table_header, + union fw_table_header *table_header, struct acpi_subtable_proc *proc, int proc_num, unsigned int max_entries) { unsigned long table_end, subtable_len, entry_len; struct acpi_subtable_entry entry; + enum acpi_subtable_type type; int count = 0; int i; - table_end = (unsigned long)table_header + table_header->length; + type = acpi_get_subtable_type(id); + table_end = (unsigned long)table_header + + acpi_table_get_length(type, table_header); /* Parse all entries looking for a match. */ - entry.type = acpi_get_subtable_type(id); + entry.type = type; entry.hdr = (union acpi_subtable_headers *) ((unsigned long)table_header + table_size); subtable_len = acpi_get_subtable_header_length(&entry); @@ -174,3 +203,25 @@ acpi_parse_entries_array(char *id, unsigned long table_size, return count; } + +int __init_or_fwtbl_lib +cdat_table_parse(enum acpi_cdat_type type, + acpi_tbl_entry_handler_arg handler_arg, + void *arg, + struct acpi_table_cdat *table_header) +{ + struct acpi_subtable_proc proc = { + .id = type, + .handler_arg = handler_arg, + .arg = arg, + }; + + if (!table_header) + return -EINVAL; + + return acpi_parse_entries_array(ACPI_SIG_CDAT, + sizeof(struct acpi_table_cdat), + (union fw_table_header *)table_header, + &proc, 1, 0); +} +EXPORT_SYMBOL_FWTBL_LIB(cdat_table_parse); diff --git a/lib/sbitmap.c b/lib/sbitmap.c index d0a5081dfd12..92c6b1fd8989 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -388,11 +388,6 @@ static unsigned int sbq_calc_wake_batch(struct sbitmap_queue *sbq, unsigned int shallow_depth; /* - * For each batch, we wake up one queue. We need to make sure that our - * batch size is small enough that the full depth of the bitmap, - * potentially limited by a shallow depth, is enough to wake up all of - * the queues. - * * Each full word of the bitmap has bits_per_word bits, and there might * be a partial word. There are depth / bits_per_word full words and * depth % bits_per_word bits left over. In bitwise arithmetic: diff --git a/mm/Kconfig b/mm/Kconfig index 1902cfe4cc4f..ffc3a2ba3a8c 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1258,6 +1258,9 @@ config LOCK_MM_AND_FIND_VMA bool depends on !STACK_GROWSUP +config IOMMU_MM_DATA + bool + source "mm/damon/Kconfig" endmenu diff --git a/mm/filemap.c b/mm/filemap.c index ea49677c6338..750e779c23db 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2688,6 +2688,7 @@ int kiocb_write_and_wait(struct kiocb *iocb, size_t count) return filemap_write_and_wait_range(mapping, pos, end); } +EXPORT_SYMBOL_GPL(kiocb_write_and_wait); int kiocb_invalidate_pages(struct kiocb *iocb, size_t count) { @@ -2715,6 +2716,7 @@ int kiocb_invalidate_pages(struct kiocb *iocb, size_t count) return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end >> PAGE_SHIFT); } +EXPORT_SYMBOL_GPL(kiocb_invalidate_pages); /** * generic_file_read_iter - generic filesystem read routine diff --git a/mm/init-mm.c b/mm/init-mm.c index cfd367822cdd..24c809379274 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -44,9 +44,6 @@ struct mm_struct init_mm = { #endif .user_ns = &init_user_ns, .cpu_bitmap = CPU_BITS_NONE, -#ifdef CONFIG_IOMMU_SVA - .pasid = IOMMU_PASID_INVALID, -#endif INIT_MM_CONTEXT(init_mm) }; diff --git a/mm/memblock.c b/mm/memblock.c index 8c194d8afeec..abd92869874d 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1885,7 +1885,7 @@ int __init_memblock memblock_search_pfn_nid(unsigned long pfn, int mid = memblock_search(type, PFN_PHYS(pfn)); if (mid == -1) - return -1; + return NUMA_NO_NODE; *start_pfn = PFN_DOWN(type->regions[mid].base); *end_pfn = PFN_DOWN(type->regions[mid].base + type->regions[mid].size); diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c index 8d5291add2bc..5462d9e3c84c 100644 --- a/mm/memory-tiers.c +++ b/mm/memory-tiers.c @@ -109,7 +109,7 @@ static struct demotion_nodes *node_demotion __read_mostly; static BLOCKING_NOTIFIER_HEAD(mt_adistance_algorithms); static bool default_dram_perf_error; -static struct node_hmem_attrs default_dram_perf; +static struct access_coordinate default_dram_perf; static int default_dram_perf_ref_nid = NUMA_NO_NODE; static const char *default_dram_perf_ref_source; @@ -601,15 +601,15 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype) } EXPORT_SYMBOL_GPL(clear_node_memory_type); -static void dump_hmem_attrs(struct node_hmem_attrs *attrs, const char *prefix) +static void dump_hmem_attrs(struct access_coordinate *coord, const char *prefix) { pr_info( "%sread_latency: %u, write_latency: %u, read_bandwidth: %u, write_bandwidth: %u\n", - prefix, attrs->read_latency, attrs->write_latency, - attrs->read_bandwidth, attrs->write_bandwidth); + prefix, coord->read_latency, coord->write_latency, + coord->read_bandwidth, coord->write_bandwidth); } -int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf, +int mt_set_default_dram_perf(int nid, struct access_coordinate *perf, const char *source) { int rc = 0; @@ -666,7 +666,7 @@ out: return rc; } -int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist) +int mt_perf_to_adistance(struct access_coordinate *perf, int *adist) { if (default_dram_perf_error) return -EIO; diff --git a/mm/percpu.c b/mm/percpu.c index 7b97d31df767..4e11fc1e6def 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -3333,13 +3333,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t if (rc < 0) panic("failed to map percpu area, err=%d\n", rc); - /* - * FIXME: Archs with virtual cache should flush local - * cache for the linear mapping here - something - * equivalent to flush_cache_vmap() on the local cpu. - * flush_cache_vmap() can't be used as most supporting - * data structures are not set up yet. - */ + flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size); /* copy static data */ memcpy((void *)unit_addr, __per_cpu_load, ai->static_size); diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 6adcb45bca75..ed1720890757 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -279,8 +279,17 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_ if ((READ_ONCE(neigh->nud_state) & NUD_CONNECTED) && READ_ONCE(neigh->hh.hh_len)) { + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(skb, net); + if (!br_indev) { + neigh_release(neigh); + goto free_skb; + } + neigh_hh_bridge(&neigh->hh, skb); - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; + ret = br_handle_frame_finish(net, sk, skb); } else { /* the neighbour function below overwrites the complete @@ -352,12 +361,18 @@ br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb, */ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net_device *dev = skb->dev; + struct net_device *dev = skb->dev, *br_indev; struct iphdr *iph = ip_hdr(skb); struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; int err; + br_indev = nf_bridge_get_physindev(skb, net); + if (!br_indev) { + kfree_skb(skb); + return 0; + } + nf_bridge->frag_max_size = IPCB(skb)->frag_max_size; if (nf_bridge->pkt_otherhost) { @@ -397,7 +412,7 @@ free_skb: } else { if (skb_dst(skb)->dev == dev) { bridged_dnat: - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, @@ -410,7 +425,7 @@ bridged_dnat: skb->pkt_type = PACKET_HOST; } } else { - rt = bridge_parent_rtable(nf_bridge->physindev); + rt = bridge_parent_rtable(br_indev); if (!rt) { kfree_skb(skb); return 0; @@ -419,7 +434,7 @@ bridged_dnat: skb_dst_set_noref(skb, &rt->dst); } - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL, @@ -456,7 +471,7 @@ struct net_device *setup_pre_routing(struct sk_buff *skb, const struct net *net) } nf_bridge->in_prerouting = 1; - nf_bridge->physindev = skb->dev; + nf_bridge->physinif = skb->dev->ifindex; skb->dev = brnf_get_logical_dev(skb, skb->dev, net); if (skb->protocol == htons(ETH_P_8021Q)) @@ -553,7 +568,11 @@ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff if (skb->protocol == htons(ETH_P_IPV6)) nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size; - in = nf_bridge->physindev; + in = nf_bridge_get_physindev(skb, net); + if (!in) { + kfree_skb(skb); + return 0; + } if (nf_bridge->pkt_otherhost) { skb->pkt_type = PACKET_OTHERHOST; nf_bridge->pkt_otherhost = false; @@ -899,6 +918,13 @@ static unsigned int ip_sabotage_in(void *priv, static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(skb, dev_net(skb->dev)); + if (!br_indev) { + kfree_skb(skb); + return; + } skb_pull(skb, ETH_HLEN); nf_bridge->bridged_dnat = 0; @@ -908,7 +934,7 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) skb_copy_to_linear_data_offset(skb, -(ETH_HLEN - ETH_ALEN), nf_bridge->neigh_header, ETH_HLEN - ETH_ALEN); - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge->physoutdev = NULL; br_handle_frame_finish(dev_net(skb->dev), NULL, skb); diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 2e24a743f917..e0421eaa3abc 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -102,9 +102,15 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; - struct net_device *dev = skb->dev; + struct net_device *dev = skb->dev, *br_indev; const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); + br_indev = nf_bridge_get_physindev(skb, net); + if (!br_indev) { + kfree_skb(skb); + return 0; + } + nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size; if (nf_bridge->pkt_otherhost) { @@ -122,7 +128,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc } if (skb_dst(skb)->dev == dev) { - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, @@ -133,7 +139,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr); skb->pkt_type = PACKET_HOST; } else { - rt = bridge_parent_rtable(nf_bridge->physindev); + rt = bridge_parent_rtable(br_indev); if (!rt) { kfree_skb(skb); return 0; @@ -142,7 +148,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc skb_dst_set_noref(skb, &rt->dst); } - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index d3a759e052c8..625622016f57 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -5850,8 +5850,6 @@ static inline void convert_extent_map(struct ceph_sparse_read *sr) } #endif -#define MAX_EXTENTS 4096 - static int osd_sparse_read(struct ceph_connection *con, struct ceph_msg_data_cursor *cursor, char **pbuf) @@ -5882,23 +5880,16 @@ next_op: if (count > 0) { if (!sr->sr_extent || count > sr->sr_ext_len) { - /* - * Apply a hard cap to the number of extents. - * If we have more, assume something is wrong. - */ - if (count > MAX_EXTENTS) { - dout("%s: OSD returned 0x%x extents in a single reply!\n", - __func__, count); - return -EREMOTEIO; - } - /* no extent array provided, or too short */ kfree(sr->sr_extent); sr->sr_extent = kmalloc_array(count, sizeof(*sr->sr_extent), GFP_NOIO); - if (!sr->sr_extent) + if (!sr->sr_extent) { + pr_err("%s: failed to allocate %u extents\n", + __func__, count); return -ENOMEM; + } sr->sr_ext_len = count; } ret = count * sizeof(*sr->sr_extent); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5f6ed6da3cfc..f6f29eb03ec2 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2899,13 +2899,6 @@ static int do_setlink(const struct sk_buff *skb, call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); } - if (tb[IFLA_MASTER]) { - err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack); - if (err) - goto errout; - status |= DO_SETLINK_MODIFIED; - } - if (ifm->ifi_flags || ifm->ifi_change) { err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm), extack); @@ -2913,6 +2906,13 @@ static int do_setlink(const struct sk_buff *skb, goto errout; } + if (tb[IFLA_MASTER]) { + err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack); + if (err) + goto errout; + status |= DO_SETLINK_MODIFIED; + } + if (tb[IFLA_CARRIER]) { err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER])); if (err) diff --git a/net/dsa/user.c b/net/dsa/user.c index b738a466e2dc..b15e71cc342c 100644 --- a/net/dsa/user.c +++ b/net/dsa/user.c @@ -2806,13 +2806,14 @@ EXPORT_SYMBOL_GPL(dsa_user_dev_check); static int dsa_user_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { - struct dsa_port *dp = dsa_user_to_port(dev); struct netlink_ext_ack *extack; int err = NOTIFY_DONE; + struct dsa_port *dp; if (!dsa_user_dev_check(dev)) return err; + dp = dsa_user_to_port(dev); extack = netdev_notifier_info_to_extack(&info->info); if (netif_is_bridge_master(info->upper_dev)) { @@ -2865,11 +2866,13 @@ static int dsa_user_changeupper(struct net_device *dev, static int dsa_user_prechangeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { - struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_port *dp; if (!dsa_user_dev_check(dev)) return NOTIFY_DONE; + dp = dsa_user_to_port(dev); + if (netif_is_bridge_master(info->upper_dev) && !info->linking) dsa_port_pre_bridge_leave(dp, info->upper_dev); else if (netif_is_lag_master(info->upper_dev) && !info->linking) diff --git a/net/ethtool/features.c b/net/ethtool/features.c index a79af8c25a07..b6cb101d7f19 100644 --- a/net/ethtool/features.c +++ b/net/ethtool/features.c @@ -234,17 +234,20 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) dev = req_info.dev; rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; ethnl_features_to_bitmap(old_active, dev->features); ethnl_features_to_bitmap(old_wanted, dev->wanted_features); ret = ethnl_parse_bitset(req_wanted, req_mask, NETDEV_FEATURE_COUNT, tb[ETHTOOL_A_FEATURES_WANTED], netdev_features_strings, info->extack); if (ret < 0) - goto out_rtnl; + goto out_ops; if (ethnl_bitmap_to_features(req_mask) & ~NETIF_F_ETHTOOL_BITS) { GENL_SET_ERR_MSG(info, "attempt to change non-ethtool features"); ret = -EINVAL; - goto out_rtnl; + goto out_ops; } /* set req_wanted bits not in req_mask from old_wanted */ @@ -281,6 +284,8 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) if (mod) netdev_features_change(dev); +out_ops: + ethnl_ops_complete(dev); out_rtnl: rtnl_unlock(); ethnl_parse_header_dev_put(&req_info); diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index b099c3150150..cb83c8feb746 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -167,4 +167,5 @@ static void __exit hsr_exit(void) module_init(hsr_init); module_exit(hsr_exit); +MODULE_DESCRIPTION("High-availability Seamless Redundancy (HSR) driver"); MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index f01b038fc1cd..04504b2b51df 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -239,7 +239,6 @@ static int nf_reject_fill_skb_dst(struct sk_buff *skb_in) void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, int hook) { - struct net_device *br_indev __maybe_unused; struct sk_buff *nskb; struct iphdr *niph; const struct tcphdr *oth; @@ -289,9 +288,13 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, * build the eth header using the original destination's MAC as the * source, and send the RST packet directly. */ - br_indev = nf_bridge_get_physindev(oldskb); - if (br_indev) { + if (nf_bridge_info_exists(oldskb)) { struct ethhdr *oeth = eth_hdr(oldskb); + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(oldskb, net); + if (!br_indev) + goto free_nskb; nskb->dev = br_indev; niph->tot_len = htons(nskb->len); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 89e5a806b82e..148ffb007969 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -805,7 +805,7 @@ void udp_flush_pending_frames(struct sock *sk) if (up->pending) { up->len = 0; - up->pending = 0; + WRITE_ONCE(up->pending, 0); ip_flush_pending_frames(sk); } } @@ -993,7 +993,7 @@ int udp_push_pending_frames(struct sock *sk) out: up->len = 0; - up->pending = 0; + WRITE_ONCE(up->pending, 0); return err; } EXPORT_SYMBOL(udp_push_pending_frames); @@ -1070,7 +1070,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; fl4 = &inet->cork.fl.u.ip4; - if (up->pending) { + if (READ_ONCE(up->pending)) { /* * There are pending frames. * The socket lock must be held while it's corked. @@ -1269,7 +1269,7 @@ back_from_confirm: fl4->saddr = saddr; fl4->fl4_dport = dport; fl4->fl4_sport = inet->inet_sport; - up->pending = AF_INET; + WRITE_ONCE(up->pending, AF_INET); do_append_data: up->len += ulen; @@ -1281,7 +1281,7 @@ do_append_data: else if (!corkreq) err = udp_push_pending_frames(sk); else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) - up->pending = 0; + WRITE_ONCE(up->pending, 0); release_sock(sk); out: @@ -1319,7 +1319,7 @@ void udp_splice_eof(struct socket *sock) struct sock *sk = sock->sk; struct udp_sock *up = udp_sk(sk); - if (!up->pending || udp_test_bit(CORK, sk)) + if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk)) return; lock_sock(sk); @@ -3137,16 +3137,18 @@ static struct sock *bpf_iter_udp_batch(struct seq_file *seq) struct bpf_udp_iter_state *iter = seq->private; struct udp_iter_state *state = &iter->state; struct net *net = seq_file_net(seq); + int resume_bucket, resume_offset; struct udp_table *udptable; unsigned int batch_sks = 0; bool resized = false; struct sock *sk; + resume_bucket = state->bucket; + resume_offset = iter->offset; + /* The current batch is done, so advance the bucket. */ - if (iter->st_bucket_done) { + if (iter->st_bucket_done) state->bucket++; - iter->offset = 0; - } udptable = udp_get_table_seq(seq, net); @@ -3166,19 +3168,19 @@ again: for (; state->bucket <= udptable->mask; state->bucket++) { struct udp_hslot *hslot2 = &udptable->hash2[state->bucket]; - if (hlist_empty(&hslot2->head)) { - iter->offset = 0; + if (hlist_empty(&hslot2->head)) continue; - } + iter->offset = 0; spin_lock_bh(&hslot2->lock); udp_portaddr_for_each_entry(sk, &hslot2->head) { if (seq_sk_match(seq, sk)) { /* Resume from the last iterated socket at the * offset in the bucket before iterator was stopped. */ - if (iter->offset) { - --iter->offset; + if (state->bucket == resume_bucket && + iter->offset < resume_offset) { + ++iter->offset; continue; } if (iter->end_sk < iter->max_sk) { @@ -3192,9 +3194,6 @@ again: if (iter->end_sk) break; - - /* Reset the current bucket's offset before moving to the next bucket. */ - iter->offset = 0; } /* All done: no batch made. */ @@ -3213,7 +3212,6 @@ again: /* After allocating a larger batch, retry one more time to grab * the whole bucket. */ - state->bucket--; goto again; } done: diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index b75d3c9d41bb..bc6e0a0bad3c 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2722,8 +2722,12 @@ void ipv6_mc_down(struct inet6_dev *idev) synchronize_net(); mld_query_stop_work(idev); mld_report_stop_work(idev); + + mutex_lock(&idev->mc_lock); mld_ifc_stop_work(idev); mld_gq_stop_work(idev); + mutex_unlock(&idev->mc_lock); + mld_dad_stop_work(idev); } diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index d45bc54b7ea5..196dd4ecb5e2 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -278,7 +278,6 @@ static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in) void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, int hook) { - struct net_device *br_indev __maybe_unused; struct sk_buff *nskb; struct tcphdr _otcph; const struct tcphdr *otcph; @@ -354,9 +353,15 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, * build the eth header using the original destination's MAC as the * source, and send the RST packet directly. */ - br_indev = nf_bridge_get_physindev(oldskb); - if (br_indev) { + if (nf_bridge_info_exists(oldskb)) { struct ethhdr *oeth = eth_hdr(oldskb); + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(oldskb, net); + if (!br_indev) { + kfree_skb(nskb); + return; + } nskb->dev = br_indev; nskb->protocol = htons(ETH_P_IPV6); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 594e3f23c129..3f2249b4cd5f 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1135,7 +1135,7 @@ static void udp_v6_flush_pending_frames(struct sock *sk) udp_flush_pending_frames(sk); else if (up->pending) { up->len = 0; - up->pending = 0; + WRITE_ONCE(up->pending, 0); ip6_flush_pending_frames(sk); } } @@ -1313,7 +1313,7 @@ static int udp_v6_push_pending_frames(struct sock *sk) &inet_sk(sk)->cork.base); out: up->len = 0; - up->pending = 0; + WRITE_ONCE(up->pending, 0); return err; } @@ -1370,7 +1370,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) default: return -EINVAL; } - } else if (!up->pending) { + } else if (!READ_ONCE(up->pending)) { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = &sk->sk_v6_daddr; @@ -1401,8 +1401,8 @@ do_udp_sendmsg: return -EMSGSIZE; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; - if (up->pending) { - if (up->pending == AF_INET) + if (READ_ONCE(up->pending)) { + if (READ_ONCE(up->pending) == AF_INET) return udp_sendmsg(sk, msg, len); /* * There are pending frames. @@ -1593,7 +1593,7 @@ back_from_confirm: goto out; } - up->pending = AF_INET6; + WRITE_ONCE(up->pending, AF_INET6); do_append_data: if (ipc6.dontfrag < 0) @@ -1607,7 +1607,7 @@ do_append_data: else if (!corkreq) err = udp_v6_push_pending_frames(sk); else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) - up->pending = 0; + WRITE_ONCE(up->pending, 0); if (err > 0) err = inet6_test_bit(RECVERR6, sk) ? net_xmit_errno(err) : 0; @@ -1648,7 +1648,7 @@ static void udpv6_splice_eof(struct socket *sock) struct sock *sk = sock->sk; struct udp_sock *up = udp_sk(sk); - if (!up->pending || udp_test_bit(CORK, sk)) + if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk)) return; lock_sock(sk); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index c53914012d01..d2527d189a79 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -123,8 +123,8 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_MP_JOIN: - mp_opt->suboptions |= OPTIONS_MPTCP_MPJ; if (opsize == TCPOLEN_MPTCP_MPJ_SYN) { + mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYN; mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP; mp_opt->join_id = *ptr++; mp_opt->token = get_unaligned_be32(ptr); @@ -135,6 +135,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->backup, mp_opt->join_id, mp_opt->token, mp_opt->nonce); } else if (opsize == TCPOLEN_MPTCP_MPJ_SYNACK) { + mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYNACK; mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP; mp_opt->join_id = *ptr++; mp_opt->thmac = get_unaligned_be64(ptr); @@ -145,11 +146,10 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->backup, mp_opt->join_id, mp_opt->thmac, mp_opt->nonce); } else if (opsize == TCPOLEN_MPTCP_MPJ_ACK) { + mp_opt->suboptions |= OPTION_MPTCP_MPJ_ACK; ptr += 2; memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN); pr_debug("MP_JOIN hmac"); - } else { - mp_opt->suboptions &= ~OPTIONS_MPTCP_MPJ; } break; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 3eacd04e7099..0dcb721c89d1 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -157,8 +157,8 @@ static int subflow_check_req(struct request_sock *req, mptcp_get_options(skb, &mp_opt); - opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC); - opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ); + opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_SYN); + opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_SYN); if (opt_mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); @@ -254,8 +254,8 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, subflow_init_req(req, sk_listener); mptcp_get_options(skb, &mp_opt); - opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC); - opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ); + opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_ACK); + opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK); if (opt_mp_capable && opt_mp_join) return -EINVAL; @@ -486,7 +486,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) mptcp_get_options(skb, &mp_opt); if (subflow->request_mptcp) { - if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) { + if (!(mp_opt.suboptions & OPTION_MPTCP_MPC_SYNACK)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEFALLBACK); mptcp_do_fallback(sk); @@ -506,7 +506,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; - if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ)) { + if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_SYNACK)) { subflow->reset_reason = MPTCP_RST_EMPTCP; goto do_reset; } @@ -783,12 +783,13 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, * options. */ mptcp_get_options(skb, &mp_opt); - if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) + if (!(mp_opt.suboptions & + (OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_ACK))) fallback = true; } else if (subflow_req->mp_join) { mptcp_get_options(skb, &mp_opt); - if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ) || + if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK) || !subflow_hmac_valid(req, &mp_opt) || !mptcp_can_accept_new_subflow(subflow_req->msk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 95aeb31c60e0..30a655e5c4fd 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -138,9 +138,9 @@ hash_netiface4_data_next(struct hash_netiface4_elem *next, #include "ip_set_hash_gen.h" #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) -static const char *get_physindev_name(const struct sk_buff *skb) +static const char *get_physindev_name(const struct sk_buff *skb, struct net *net) { - struct net_device *dev = nf_bridge_get_physindev(skb); + struct net_device *dev = nf_bridge_get_physindev(skb, net); return dev ? dev->name : NULL; } @@ -177,7 +177,7 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb, if (opt->cmdflags & IPSET_FLAG_PHYSDEV) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - const char *eiface = SRCDIR ? get_physindev_name(skb) : + const char *eiface = SRCDIR ? get_physindev_name(skb, xt_net(par)) : get_physoutdev_name(skb); if (!eiface) @@ -395,7 +395,7 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb, if (opt->cmdflags & IPSET_FLAG_PHYSDEV) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - const char *eiface = SRCDIR ? get_physindev_name(skb) : + const char *eiface = SRCDIR ? get_physindev_name(skb, xt_net(par)) : get_physoutdev_name(skb); if (!eiface) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 9193e109e6b3..65e0259178da 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -271,7 +271,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); - __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); return false; } @@ -286,7 +286,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, { if (ip_hdr(skb)->ttl <= 1) { /* Tell the sender its packet died... */ - __IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); + IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0); return false; } diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c index c66689ad2b49..58402226045e 100644 --- a/net/netfilter/nf_log_syslog.c +++ b/net/netfilter/nf_log_syslog.c @@ -111,7 +111,8 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, - const struct nf_loginfo *loginfo, const char *prefix) + const struct nf_loginfo *loginfo, const char *prefix, + struct net *net) { const struct net_device *physoutdev __maybe_unused; const struct net_device *physindev __maybe_unused; @@ -121,7 +122,7 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf, in ? in->name : "", out ? out->name : ""); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - physindev = nf_bridge_get_physindev(skb); + physindev = nf_bridge_get_physindev(skb, net); if (physindev && in != physindev) nf_log_buf_add(m, "PHYSIN=%s ", physindev->name); physoutdev = nf_bridge_get_physoutdev(skb); @@ -148,7 +149,7 @@ static void nf_log_arp_packet(struct net *net, u_int8_t pf, loginfo = &default_loginfo; nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo, - prefix); + prefix, net); dump_arp_packet(m, loginfo, skb, skb_network_offset(skb)); nf_log_buf_close(m); @@ -845,7 +846,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf, loginfo = &default_loginfo; nf_log_dump_packet_common(m, pf, hooknum, skb, in, - out, loginfo, prefix); + out, loginfo, prefix, net); if (in) dump_mac_header(m, loginfo, skb); @@ -880,7 +881,7 @@ static void nf_log_ip6_packet(struct net *net, u_int8_t pf, loginfo = &default_loginfo; nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, - loginfo, prefix); + loginfo, prefix, net); if (in) dump_mac_header(m, loginfo, skb); @@ -916,7 +917,7 @@ static void nf_log_unknown_packet(struct net *net, u_int8_t pf, loginfo = &default_loginfo; nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo, - prefix); + prefix, net); dump_mac_header(m, loginfo, skb); diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 63d1516816b1..e2f334f70281 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -82,11 +82,9 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) const struct sk_buff *skb = entry->skb; - struct nf_bridge_info *nf_bridge; - nf_bridge = nf_bridge_info_get(skb); - if (nf_bridge) { - entry->physin = nf_bridge_get_physindev(skb); + if (nf_bridge_info_exists(skb)) { + entry->physin = nf_bridge_get_physindev(skb, entry->state.net); entry->physout = nf_bridge_get_physoutdev(skb); } else { entry->physin = NULL; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 8438a8922e4a..4b55533ce5ca 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2977,6 +2977,9 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, */ int nft_register_expr(struct nft_expr_type *type) { + if (WARN_ON_ONCE(type->maxattr > NFT_EXPR_MAXATTR)) + return -ENOMEM; + nfnl_lock(NFNL_SUBSYS_NFTABLES); if (type->family == NFPROTO_UNSPEC) list_add_tail_rcu(&type->list, &nf_tables_expressions); @@ -3271,14 +3274,13 @@ int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) { int err; - if (src->ops->clone) { - dst->ops = src->ops; - err = src->ops->clone(dst, src); - if (err < 0) - return err; - } else { - memcpy(dst, src, src->ops->size); - } + if (WARN_ON_ONCE(!src->ops->clone)) + return -EINVAL; + + dst->ops = src->ops; + err = src->ops->clone(dst, src); + if (err < 0) + return err; __module_get(src->ops->type->owner); @@ -4811,8 +4813,8 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr, static int nft_set_desc_concat(struct nft_set_desc *desc, const struct nlattr *nla) { + u32 num_regs = 0, key_num_regs = 0; struct nlattr *attr; - u32 num_regs = 0; int rem, err, i; nla_for_each_nested(attr, nla, rem) { @@ -4827,6 +4829,10 @@ static int nft_set_desc_concat(struct nft_set_desc *desc, for (i = 0; i < desc->field_count; i++) num_regs += DIV_ROUND_UP(desc->field_len[i], sizeof(u32)); + key_num_regs = DIV_ROUND_UP(desc->klen, sizeof(u32)); + if (key_num_regs != num_regs) + return -EINVAL; + if (num_regs > NFT_REG32_COUNT) return -E2BIG; @@ -5048,16 +5054,28 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, } desc.policy = NFT_SET_POL_PERFORMANCE; - if (nla[NFTA_SET_POLICY] != NULL) + if (nla[NFTA_SET_POLICY] != NULL) { desc.policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY])); + switch (desc.policy) { + case NFT_SET_POL_PERFORMANCE: + case NFT_SET_POL_MEMORY: + break; + default: + return -EOPNOTSUPP; + } + } if (nla[NFTA_SET_DESC] != NULL) { err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]); if (err < 0) return err; - if (desc.field_count > 1 && !(flags & NFT_SET_CONCAT)) + if (desc.field_count > 1) { + if (!(flags & NFT_SET_CONCAT)) + return -EINVAL; + } else if (flags & NFT_SET_CONCAT) { return -EINVAL; + } } else if (flags & NFT_SET_CONCAT) { return -EINVAL; } @@ -5704,7 +5722,7 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_set_dump_args *args; - if (nft_set_elem_expired(ext)) + if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext)) return 0; args = container_of(iter, struct nft_set_dump_args, iter); @@ -6568,7 +6586,7 @@ static int nft_setelem_catchall_deactivate(const struct net *net, list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_is_active(net, ext)) + if (!nft_is_active_next(net, ext)) continue; kfree(elem->priv); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index f03f4d4d7d88..134e05d31061 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -508,7 +508,7 @@ __build_packet_message(struct nfnl_log_net *log, htonl(br_port_get_rcu(indev)->br->dev->ifindex))) goto nla_put_failure; } else { - struct net_device *physindev; + int physinif; /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ @@ -516,10 +516,10 @@ __build_packet_message(struct nfnl_log_net *log, htonl(indev->ifindex))) goto nla_put_failure; - physindev = nf_bridge_get_physindev(skb); - if (physindev && + physinif = nf_bridge_get_physinif(skb); + if (physinif && nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV, - htonl(physindev->ifindex))) + htonl(physinif))) goto nla_put_failure; } #endif diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 145dc62c6247..79039afde34e 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -58,6 +58,7 @@ static inline bool nft_limit_eval(struct nft_limit_priv *priv, u64 cost) static int nft_limit_init(struct nft_limit_priv *priv, const struct nlattr * const tb[], bool pkts) { + bool invert = false; u64 unit, tokens; if (tb[NFTA_LIMIT_RATE] == NULL || @@ -90,19 +91,23 @@ static int nft_limit_init(struct nft_limit_priv *priv, priv->rate); } + if (tb[NFTA_LIMIT_FLAGS]) { + u32 flags = ntohl(nla_get_be32(tb[NFTA_LIMIT_FLAGS])); + + if (flags & ~NFT_LIMIT_F_INV) + return -EOPNOTSUPP; + + if (flags & NFT_LIMIT_F_INV) + invert = true; + } + priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL_ACCOUNT); if (!priv->limit) return -ENOMEM; priv->limit->tokens = tokens; priv->tokens_max = priv->limit->tokens; - - if (tb[NFTA_LIMIT_FLAGS]) { - u32 flags = ntohl(nla_get_be32(tb[NFTA_LIMIT_FLAGS])); - - if (flags & NFT_LIMIT_F_INV) - priv->invert = true; - } + priv->invert = invert; priv->limit->last = ktime_get_ns(); spin_lock_init(&priv->limit->lock); diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index ec6ed6fda96c..343e65f377d4 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -59,7 +59,7 @@ physdev_mt(const struct sk_buff *skb, struct xt_action_param *par) (!!outdev ^ !(info->invert & XT_PHYSDEV_OP_BRIDGED))) return false; - physdev = nf_bridge_get_physindev(skb); + physdev = nf_bridge_get_physindev(skb, xt_net(par)); indev = physdev ? physdev->name : NULL; if ((info->bitmask & XT_PHYSDEV_OP_ISIN && diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index d63d2e5dc60c..dae378f1d52b 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -858,4 +858,5 @@ void nfc_digital_unregister_device(struct nfc_digital_dev *ddev) } EXPORT_SYMBOL(nfc_digital_unregister_device); +MODULE_DESCRIPTION("NFC Digital protocol stack"); MODULE_LICENSE("GPL"); diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 6c9592d05120..97348cedb16b 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1577,4 +1577,5 @@ static void nci_cmd_work(struct work_struct *work) } } +MODULE_DESCRIPTION("NFC Controller Interface"); MODULE_LICENSE("GPL"); diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c index b68150c971d0..6a93533c480e 100644 --- a/net/nfc/nci/spi.c +++ b/net/nfc/nci/spi.c @@ -319,4 +319,5 @@ done: } EXPORT_SYMBOL_GPL(nci_spi_read); +MODULE_DESCRIPTION("NFC Controller Interface (NCI) SPI link layer"); MODULE_LICENSE("GPL"); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 2f8b39a614c3..dbeb75c29857 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -1079,6 +1079,7 @@ void rxrpc_send_version_request(struct rxrpc_local *local, /* * local_object.c */ +void rxrpc_local_dont_fragment(const struct rxrpc_local *local, bool set); struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpc *); struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *, enum rxrpc_local_trace); struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *, enum rxrpc_local_trace); diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index c553a30e9c83..34d307368135 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -37,6 +37,17 @@ static void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, int err, } /* + * Set or clear the Don't Fragment flag on a socket. + */ +void rxrpc_local_dont_fragment(const struct rxrpc_local *local, bool set) +{ + if (set) + ip_sock_set_mtu_discover(local->socket->sk, IP_PMTUDISC_DO); + else + ip_sock_set_mtu_discover(local->socket->sk, IP_PMTUDISC_DONT); +} + +/* * Compare a local to an address. Return -ve, 0 or +ve to indicate less than, * same or greater than. * @@ -203,7 +214,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) ip_sock_set_recverr(usk); /* we want to set the don't fragment bit */ - ip_sock_set_mtu_discover(usk, IP_PMTUDISC_DO); + rxrpc_local_dont_fragment(local, true); /* We want receive timestamps. */ sock_enable_timestamps(usk); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 5e53429c6922..a0906145e829 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -494,14 +494,12 @@ send_fragmentable: switch (conn->local->srx.transport.family) { case AF_INET6: case AF_INET: - ip_sock_set_mtu_discover(conn->local->socket->sk, - IP_PMTUDISC_DONT); + rxrpc_local_dont_fragment(conn->local, false); rxrpc_inc_stat(call->rxnet, stat_tx_data_send_frag); ret = do_udp_sendmsg(conn->local->socket, &msg, len); conn->peer->last_tx_at = ktime_get_seconds(); - ip_sock_set_mtu_discover(conn->local->socket->sk, - IP_PMTUDISC_DO); + rxrpc_local_dont_fragment(conn->local, true); break; default: diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 1bf571a66e02..b52dedcebce0 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -724,7 +724,9 @@ static int rxkad_send_response(struct rxrpc_connection *conn, serial = atomic_inc_return(&conn->serial); whdr.serial = htonl(serial); + rxrpc_local_dont_fragment(conn->local, false); ret = kernel_sendmsg(conn->local->socket, &msg, iov, 3, len); + rxrpc_local_dont_fragment(conn->local, true); if (ret < 0) { trace_rxrpc_tx_fail(conn->debug_id, serial, ret, rxrpc_tx_point_rxkad_response); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index e3236a3169c3..92a12e3d0fe6 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1424,6 +1424,14 @@ static void tcf_block_owner_del(struct tcf_block *block, WARN_ON(1); } +static bool tcf_block_tracks_dev(struct tcf_block *block, + struct tcf_block_ext_info *ei) +{ + return tcf_block_shared(block) && + (ei->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS || + ei->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS); +} + int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, struct tcf_block_ext_info *ei, struct netlink_ext_ack *extack) @@ -1462,7 +1470,7 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, if (err) goto err_block_offload_bind; - if (tcf_block_shared(block)) { + if (tcf_block_tracks_dev(block, ei)) { err = xa_insert(&block->ports, dev->ifindex, dev, GFP_KERNEL); if (err) { NL_SET_ERR_MSG(extack, "block dev insert failed"); @@ -1516,7 +1524,7 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, if (!block) return; - if (tcf_block_shared(block)) + if (tcf_block_tracks_dev(block, ei)) xa_erase(&block->ports, dev->ifindex); tcf_chain0_head_change_cb_del(block, ei); tcf_block_owner_del(block, q, ei->binder_type); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 1af71fbb0d80..c7af0220f82f 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -2280,6 +2280,7 @@ static void __exit exit_rpcsec_gss(void) } MODULE_ALIAS("rpc-auth-6"); +MODULE_DESCRIPTION("Sun RPC Kerberos RPCSEC_GSS client authentication"); MODULE_LICENSE("GPL"); module_param_named(expired_cred_retry_delay, gss_expired_cred_retry_delay, diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index e31cfdf7eadc..64cff717c3d9 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -650,6 +650,7 @@ static void __exit cleanup_kerberos_module(void) gss_mech_unregister(&gss_kerberos_mech); } +MODULE_DESCRIPTION("Sun RPC Kerberos 5 module"); MODULE_LICENSE("GPL"); module_init(init_kerberos_module); module_exit(cleanup_kerberos_module); diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index 691c0000e9ea..bab6cab29405 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -148,6 +148,7 @@ cleanup_sunrpc(void) #endif rcu_barrier(); /* Wait for completion of call_rcu()'s */ } +MODULE_DESCRIPTION("Sun RPC core"); MODULE_LICENSE("GPL"); fs_initcall(init_sunrpc); /* Ensure we're initialised before nfs */ module_exit(cleanup_sunrpc); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index e37b4d2e2acd..31e8a94dfc11 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1052,7 +1052,11 @@ alloc_encrypted: if (ret < 0) goto send_end; tls_ctx->pending_open_record_frags = true; - if (full_record || eor || sk_msg_full(msg_pl)) + + if (sk_msg_full(msg_pl)) + full_record = true; + + if (full_record || eor) goto copied; continue; } diff --git a/samples/ftrace/sample-trace-array.c b/samples/ftrace/sample-trace-array.c index 6aba02a31c96..d0ee9001c7b3 100644 --- a/samples/ftrace/sample-trace-array.c +++ b/samples/ftrace/sample-trace-array.c @@ -105,7 +105,7 @@ static int __init sample_trace_array_init(void) * NOTE: This function increments the reference counter * associated with the trace array - "tr". */ - tr = trace_array_get_by_name("sample-instance"); + tr = trace_array_get_by_name("sample-instance", "sched,timer,kprobes"); if (!tr) return -1; diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index c9725685aa76..9b7a37ae28a8 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -82,15 +82,6 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=designated-init) # Warn if there is an enum types mismatch KBUILD_CFLAGS += $(call cc-option,-Wenum-conversion) -# backward compatibility -KBUILD_EXTRA_WARN ?= $(KBUILD_ENABLE_EXTRA_GCC_CHECKS) - -ifeq ("$(origin W)", "command line") - KBUILD_EXTRA_WARN := $(W) -endif - -export KBUILD_EXTRA_WARN - # # W=1 - warnings which may be relevant and do not occur too often # diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 1a965fe68e01..cd5b181060f1 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -83,8 +83,8 @@ dtb-$(CONFIG_OF_ALL_DTBS) += $(dtb-) multi-dtb-y := $(call multi-search, $(dtb-y), .dtb, -dtbs) # Primitive DTB compiled from *.dts real-dtb-y := $(call real-search, $(dtb-y), .dtb, -dtbs) -# Base DTB that overlay is applied onto (each first word of $(*-dtbs) expansion) -base-dtb-y := $(foreach m, $(multi-dtb-y), $(firstword $(call suffix-search, $m, .dtb, -dtbs))) +# Base DTB that overlay is applied onto +base-dtb-y := $(filter %.dtb, $(call real-search, $(multi-dtb-y), .dtb, -dtbs)) always-y += $(dtb-y) diff --git a/scripts/Makefile.package b/scripts/Makefile.package index 3addd1c0b989..a81dfb1f5181 100644 --- a/scripts/Makefile.package +++ b/scripts/Makefile.package @@ -4,27 +4,6 @@ include $(srctree)/scripts/Kbuild.include include $(srctree)/scripts/Makefile.lib -KERNELPATH := kernel-$(subst -,_,$(KERNELRELEASE)) -# Include only those top-level files that are needed by make, plus the GPL copy -TAR_CONTENT := Documentation LICENSES arch block certs crypto drivers fs \ - include init io_uring ipc kernel lib mm net rust \ - samples scripts security sound tools usr virt \ - .config Makefile \ - Kbuild Kconfig COPYING $(wildcard localversion*) - -quiet_cmd_src_tar = TAR $(2).tar.gz - cmd_src_tar = \ -if test "$(objtree)" != "$(srctree)"; then \ - echo >&2; \ - echo >&2 " ERROR:"; \ - echo >&2 " Building source tarball is not possible outside the"; \ - echo >&2 " kernel source tree. Don't set KBUILD_OUTPUT"; \ - echo >&2; \ - false; \ -fi ; \ -tar -I $(KGZIP) -c $(RCS_TAR_IGNORE) -f $(2).tar.gz \ - --transform 's:^:$(2)/:S' $(TAR_CONTENT) $(3) - # Git # --------------------------------------------------------------------------- @@ -130,8 +109,6 @@ debian-orig: linux.tar$(debian-orig-suffix) debian cp $< ../$(orig-name); \ fi -KBUILD_PKG_ROOTCMD ?= 'fakeroot -u' - PHONY += deb-pkg srcdeb-pkg bindeb-pkg deb-pkg: private build-type := source,binary @@ -146,7 +123,7 @@ deb-pkg srcdeb-pkg bindeb-pkg: $(if $(findstring source, $(build-type)), \ --unsigned-source --compression=$(KDEB_SOURCE_COMPRESS)) \ $(if $(findstring binary, $(build-type)), \ - --rules-file='$(MAKE) -f debian/rules' --jobs=1 -r$(KBUILD_PKG_ROOTCMD) -a$$(cat debian/arch), \ + -R'$(MAKE) -f debian/rules' -j1 -a$$(cat debian/arch), \ --no-check-builddeps) \ $(DPKG_FLAGS)) @@ -157,9 +134,8 @@ snap-pkg: rm -rf $(objtree)/snap mkdir $(objtree)/snap $(MAKE) clean - $(call cmd,src_tar,$(KERNELPATH)) sed "s@KERNELRELEASE@$(KERNELRELEASE)@; \ - s@SRCTREE@$(shell realpath $(KERNELPATH).tar.gz)@" \ + s@SRCTREE@$(abs_srctree)@" \ $(srctree)/scripts/package/snapcraft.template > \ $(objtree)/snap/snapcraft.yaml cd $(objtree)/snap && \ diff --git a/scripts/check-uapi.sh b/scripts/check-uapi.sh new file mode 100755 index 000000000000..955581735cb3 --- /dev/null +++ b/scripts/check-uapi.sh @@ -0,0 +1,573 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only +# Script to check commits for UAPI backwards compatibility + +set -o errexit +set -o pipefail + +print_usage() { + name=$(basename "$0") + cat << EOF +$name - check for UAPI header stability across Git commits + +By default, the script will check to make sure the latest commit (or current +dirty changes) did not introduce ABI changes when compared to HEAD^1. You can +check against additional commit ranges with the -b and -p options. + +The script will not check UAPI headers for architectures other than the one +defined in ARCH. + +Usage: $name [-b BASE_REF] [-p PAST_REF] [-j N] [-l ERROR_LOG] [-i] [-q] [-v] + +Options: + -b BASE_REF Base git reference to use for comparison. If unspecified or empty, + will use any dirty changes in tree to UAPI files. If there are no + dirty changes, HEAD will be used. + -p PAST_REF Compare BASE_REF to PAST_REF (e.g. -p v6.1). If unspecified or empty, + will use BASE_REF^1. Must be an ancestor of BASE_REF. Only headers + that exist on PAST_REF will be checked for compatibility. + -j JOBS Number of checks to run in parallel (default: number of CPU cores). + -l ERROR_LOG Write error log to file (default: no error log is generated). + -i Ignore ambiguous changes that may or may not break UAPI compatibility. + -q Quiet operation. + -v Verbose operation (print more information about each header being checked). + +Environmental args: + ABIDIFF Custom path to abidiff binary + CC C compiler (default is "gcc") + ARCH Target architecture for the UAPI check (default is host arch) + +Exit codes: + $SUCCESS) Success + $FAIL_ABI) ABI difference detected + $FAIL_PREREQ) Prerequisite not met +EOF +} + +readonly SUCCESS=0 +readonly FAIL_ABI=1 +readonly FAIL_PREREQ=2 + +# Print to stderr +eprintf() { + # shellcheck disable=SC2059 + printf "$@" >&2 +} + +# Expand an array with a specific character (similar to Python string.join()) +join() { + local IFS="$1" + shift + printf "%s" "$*" +} + +# Create abidiff suppressions +gen_suppressions() { + # Common enum variant names which we don't want to worry about + # being shifted when new variants are added. + local -a enum_regex=( + ".*_AFTER_LAST$" + ".*_CNT$" + ".*_COUNT$" + ".*_END$" + ".*_LAST$" + ".*_MASK$" + ".*_MAX$" + ".*_MAX_BIT$" + ".*_MAX_BPF_ATTACH_TYPE$" + ".*_MAX_ID$" + ".*_MAX_SHIFT$" + ".*_NBITS$" + ".*_NETDEV_NUMHOOKS$" + ".*_NFT_META_IIFTYPE$" + ".*_NL80211_ATTR$" + ".*_NLDEV_NUM_OPS$" + ".*_NUM$" + ".*_NUM_ELEMS$" + ".*_NUM_IRQS$" + ".*_SIZE$" + ".*_TLSMAX$" + "^MAX_.*" + "^NUM_.*" + ) + + # Common padding field names which can be expanded into + # without worrying about users. + local -a padding_regex=( + ".*end$" + ".*pad$" + ".*pad[0-9]?$" + ".*pad_[0-9]?$" + ".*padding$" + ".*padding[0-9]?$" + ".*padding_[0-9]?$" + ".*res$" + ".*resv$" + ".*resv[0-9]?$" + ".*resv_[0-9]?$" + ".*reserved$" + ".*reserved[0-9]?$" + ".*reserved_[0-9]?$" + ".*rsvd[0-9]?$" + ".*unused$" + ) + + cat << EOF +[suppress_type] + type_kind = enum + changed_enumerators_regexp = $(join , "${enum_regex[@]}") +EOF + + for p in "${padding_regex[@]}"; do + cat << EOF +[suppress_type] + type_kind = struct + has_data_member_inserted_at = offset_of_first_data_member_regexp(${p}) +EOF + done + +if [ "$IGNORE_AMBIGUOUS_CHANGES" = "true" ]; then + cat << EOF +[suppress_type] + type_kind = struct + has_data_member_inserted_at = end + has_size_change = yes +EOF +fi +} + +# Check if git tree is dirty +tree_is_dirty() { + ! git diff --quiet +} + +# Get list of files installed in $ref +get_file_list() { + local -r ref="$1" + local -r tree="$(get_header_tree "$ref")" + + # Print all installed headers, filtering out ones that can't be compiled + find "$tree" -type f -name '*.h' -printf '%P\n' | grep -v -f "$INCOMPAT_LIST" +} + +# Add to the list of incompatible headers +add_to_incompat_list() { + local -r ref="$1" + + # Start with the usr/include/Makefile to get a list of the headers + # that don't compile using this method. + if [ ! -f usr/include/Makefile ]; then + eprintf "error - no usr/include/Makefile present at %s\n" "$ref" + eprintf "Note: usr/include/Makefile was added in the v5.3 kernel release\n" + exit "$FAIL_PREREQ" + fi + { + # shellcheck disable=SC2016 + printf 'all: ; @echo $(no-header-test)\n' + cat usr/include/Makefile + } | SRCARCH="$ARCH" make --always-make -f - | tr " " "\n" \ + | grep -v "asm-generic" >> "$INCOMPAT_LIST" + + # The makefile also skips all asm-generic files, but prints "asm-generic/%" + # which won't work for our grep match. Instead, print something grep will match. + printf "asm-generic/.*\.h\n" >> "$INCOMPAT_LIST" +} + +# Compile the simple test app +do_compile() { + local -r inc_dir="$1" + local -r header="$2" + local -r out="$3" + printf "int main(void) { return 0; }\n" | \ + "$CC" -c \ + -o "$out" \ + -x c \ + -O0 \ + -std=c90 \ + -fno-eliminate-unused-debug-types \ + -g \ + "-I${inc_dir}" \ + -include "$header" \ + - +} + +# Run make headers_install +run_make_headers_install() { + local -r ref="$1" + local -r install_dir="$(get_header_tree "$ref")" + make -j "$MAX_THREADS" ARCH="$ARCH" INSTALL_HDR_PATH="$install_dir" \ + headers_install > /dev/null +} + +# Install headers for both git refs +install_headers() { + local -r base_ref="$1" + local -r past_ref="$2" + + for ref in "$base_ref" "$past_ref"; do + printf "Installing user-facing UAPI headers from %s... " "${ref:-dirty tree}" + if [ -n "$ref" ]; then + git archive --format=tar --prefix="${ref}-archive/" "$ref" \ + | (cd "$TMP_DIR" && tar xf -) + ( + cd "${TMP_DIR}/${ref}-archive" + run_make_headers_install "$ref" + add_to_incompat_list "$ref" "$INCOMPAT_LIST" + ) + else + run_make_headers_install "$ref" + add_to_incompat_list "$ref" "$INCOMPAT_LIST" + fi + printf "OK\n" + done + sort -u -o "$INCOMPAT_LIST" "$INCOMPAT_LIST" + sed -i -e '/^$/d' "$INCOMPAT_LIST" +} + +# Print the path to the headers_install tree for a given ref +get_header_tree() { + local -r ref="$1" + printf "%s" "${TMP_DIR}/${ref}/usr" +} + +# Check file list for UAPI compatibility +check_uapi_files() { + local -r base_ref="$1" + local -r past_ref="$2" + local -r abi_error_log="$3" + + local passed=0; + local failed=0; + local -a threads=() + set -o errexit + + printf "Checking changes to UAPI headers between %s and %s...\n" "$past_ref" "${base_ref:-dirty tree}" + # Loop over all UAPI headers that were installed by $past_ref (if they only exist on $base_ref, + # there's no way they're broken and no way to compare anyway) + while read -r file; do + if [ "${#threads[@]}" -ge "$MAX_THREADS" ]; then + if wait "${threads[0]}"; then + passed=$((passed + 1)) + else + failed=$((failed + 1)) + fi + threads=("${threads[@]:1}") + fi + + check_individual_file "$base_ref" "$past_ref" "$file" & + threads+=("$!") + done < <(get_file_list "$past_ref") + + for t in "${threads[@]}"; do + if wait "$t"; then + passed=$((passed + 1)) + else + failed=$((failed + 1)) + fi + done + + if [ -n "$abi_error_log" ]; then + printf 'Generated by "%s %s" from git ref %s\n\n' \ + "$0" "$*" "$(git rev-parse HEAD)" > "$abi_error_log" + fi + + while read -r error_file; do + { + cat "$error_file" + printf "\n\n" + } | tee -a "${abi_error_log:-/dev/null}" >&2 + done < <(find "$TMP_DIR" -type f -name '*.error' | sort) + + total="$((passed + failed))" + if [ "$failed" -gt 0 ]; then + eprintf "error - %d/%d UAPI headers compatible with %s appear _not_ to be backwards compatible\n" \ + "$failed" "$total" "$ARCH" + if [ -n "$abi_error_log" ]; then + eprintf "Failure summary saved to %s\n" "$abi_error_log" + fi + else + printf "All %d UAPI headers compatible with %s appear to be backwards compatible\n" \ + "$total" "$ARCH" + fi + + return "$failed" +} + +# Check an individual file for UAPI compatibility +check_individual_file() { + local -r base_ref="$1" + local -r past_ref="$2" + local -r file="$3" + + local -r base_header="$(get_header_tree "$base_ref")/${file}" + local -r past_header="$(get_header_tree "$past_ref")/${file}" + + if [ ! -f "$base_header" ]; then + mkdir -p "$(dirname "$base_header")" + printf "==== UAPI header %s was removed between %s and %s ====" \ + "$file" "$past_ref" "$base_ref" \ + > "${base_header}.error" + return 1 + fi + + compare_abi "$file" "$base_header" "$past_header" "$base_ref" "$past_ref" +} + +# Perform the A/B compilation and compare output ABI +compare_abi() { + local -r file="$1" + local -r base_header="$2" + local -r past_header="$3" + local -r base_ref="$4" + local -r past_ref="$5" + local -r log="${TMP_DIR}/log/${file}.log" + local -r error_log="${TMP_DIR}/log/${file}.error" + + mkdir -p "$(dirname "$log")" + + if ! do_compile "$(get_header_tree "$base_ref")/include" "$base_header" "${base_header}.bin" 2> "$log"; then + { + warn_str=$(printf "==== Could not compile version of UAPI header %s at %s ====\n" \ + "$file" "$base_ref") + printf "%s\n" "$warn_str" + cat "$log" + printf -- "=%.0s" $(seq 0 ${#warn_str}) + } > "$error_log" + return 1 + fi + + if ! do_compile "$(get_header_tree "$past_ref")/include" "$past_header" "${past_header}.bin" 2> "$log"; then + { + warn_str=$(printf "==== Could not compile version of UAPI header %s at %s ====\n" \ + "$file" "$past_ref") + printf "%s\n" "$warn_str" + cat "$log" + printf -- "=%.0s" $(seq 0 ${#warn_str}) + } > "$error_log" + return 1 + fi + + local ret=0 + "$ABIDIFF" --non-reachable-types \ + --suppressions "$SUPPRESSIONS" \ + "${past_header}.bin" "${base_header}.bin" > "$log" || ret="$?" + if [ "$ret" -eq 0 ]; then + if [ "$VERBOSE" = "true" ]; then + printf "No ABI differences detected in %s from %s -> %s\n" \ + "$file" "$past_ref" "$base_ref" + fi + else + # Bits in abidiff's return code can be used to determine the type of error + if [ $((ret & 0x2)) -gt 0 ]; then + eprintf "error - abidiff did not run properly\n" + exit 1 + fi + + if [ "$IGNORE_AMBIGUOUS_CHANGES" = "true" ] && [ "$ret" -eq 4 ]; then + return 0 + fi + + # If the only changes were additions (not modifications to existing APIs), then + # there's no problem. Ignore these diffs. + if grep "Unreachable types summary" "$log" | grep -q "0 removed" && + grep "Unreachable types summary" "$log" | grep -q "0 changed"; then + return 0 + fi + + { + warn_str=$(printf "==== ABI differences detected in %s from %s -> %s ====" \ + "$file" "$past_ref" "$base_ref") + printf "%s\n" "$warn_str" + sed -e '/summary:/d' -e '/changed type/d' -e '/^$/d' -e 's/^/ /g' "$log" + printf -- "=%.0s" $(seq 0 ${#warn_str}) + if cmp "$past_header" "$base_header" > /dev/null 2>&1; then + printf "\n%s did not change between %s and %s...\n" "$file" "$past_ref" "${base_ref:-dirty tree}" + printf "It's possible a change to one of the headers it includes caused this error:\n" + grep '^#include' "$base_header" + printf "\n" + fi + } > "$error_log" + + return 1 + fi +} + +# Check that a minimum software version number is satisfied +min_version_is_satisfied() { + local -r min_version="$1" + local -r version_installed="$2" + + printf "%s\n%s\n" "$min_version" "$version_installed" \ + | sort -Vc > /dev/null 2>&1 +} + +# Make sure we have the tools we need and the arguments make sense +check_deps() { + ABIDIFF="${ABIDIFF:-abidiff}" + CC="${CC:-gcc}" + ARCH="${ARCH:-$(uname -m)}" + if [ "$ARCH" = "x86_64" ]; then + ARCH="x86" + fi + + local -r abidiff_min_version="2.4" + local -r libdw_min_version_if_clang="0.171" + + if ! command -v "$ABIDIFF" > /dev/null 2>&1; then + eprintf "error - abidiff not found!\n" + eprintf "Please install abigail-tools version %s or greater\n" "$abidiff_min_version" + eprintf "See: https://sourceware.org/libabigail/manual/libabigail-overview.html\n" + return 1 + fi + + local -r abidiff_version="$("$ABIDIFF" --version | cut -d ' ' -f 2)" + if ! min_version_is_satisfied "$abidiff_min_version" "$abidiff_version"; then + eprintf "error - abidiff version too old: %s\n" "$abidiff_version" + eprintf "Please install abigail-tools version %s or greater\n" "$abidiff_min_version" + eprintf "See: https://sourceware.org/libabigail/manual/libabigail-overview.html\n" + return 1 + fi + + if ! command -v "$CC" > /dev/null 2>&1; then + eprintf 'error - %s not found\n' "$CC" + return 1 + fi + + if "$CC" --version | grep -q clang; then + local -r libdw_version="$(ldconfig -v 2>/dev/null | grep -v SKIPPED | grep -m 1 -o 'libdw-[0-9]\+.[0-9]\+' | cut -c 7-)" + if ! min_version_is_satisfied "$libdw_min_version_if_clang" "$libdw_version"; then + eprintf "error - libdw version too old for use with clang: %s\n" "$libdw_version" + eprintf "Please install libdw from elfutils version %s or greater\n" "$libdw_min_version_if_clang" + eprintf "See: https://sourceware.org/elfutils/\n" + return 1 + fi + fi + + if [ ! -d "arch/${ARCH}" ]; then + eprintf 'error - ARCH "%s" is not a subdirectory under arch/\n' "$ARCH" + eprintf "Please set ARCH to one of:\n%s\n" "$(find arch -maxdepth 1 -mindepth 1 -type d -printf '%f ' | fmt)" + return 1 + fi + + if ! git rev-parse --is-inside-work-tree > /dev/null 2>&1; then + eprintf "error - this script requires the kernel tree to be initialized with Git\n" + return 1 + fi + + if ! git rev-parse --verify "$past_ref" > /dev/null 2>&1; then + printf 'error - invalid git reference "%s"\n' "$past_ref" + return 1 + fi + + if [ -n "$base_ref" ]; then + if ! git merge-base --is-ancestor "$past_ref" "$base_ref" > /dev/null 2>&1; then + printf 'error - "%s" is not an ancestor of base ref "%s"\n' "$past_ref" "$base_ref" + return 1 + fi + if [ "$(git rev-parse "$base_ref")" = "$(git rev-parse "$past_ref")" ]; then + printf 'error - "%s" and "%s" are the same reference\n' "$past_ref" "$base_ref" + return 1 + fi + fi +} + +run() { + local base_ref="$1" + local past_ref="$2" + local abi_error_log="$3" + shift 3 + + if [ -z "$KERNEL_SRC" ]; then + KERNEL_SRC="$(realpath "$(dirname "$0")"/..)" + fi + + cd "$KERNEL_SRC" + + if [ -z "$base_ref" ] && ! tree_is_dirty; then + base_ref=HEAD + fi + + if [ -z "$past_ref" ]; then + if [ -n "$base_ref" ]; then + past_ref="${base_ref}^1" + else + past_ref=HEAD + fi + fi + + if ! check_deps; then + exit "$FAIL_PREREQ" + fi + + TMP_DIR=$(mktemp -d) + readonly TMP_DIR + trap 'rm -rf "$TMP_DIR"' EXIT + + readonly INCOMPAT_LIST="${TMP_DIR}/incompat_list.txt" + touch "$INCOMPAT_LIST" + + readonly SUPPRESSIONS="${TMP_DIR}/suppressions.txt" + gen_suppressions > "$SUPPRESSIONS" + + # Run make install_headers for both refs + install_headers "$base_ref" "$past_ref" + + # Check for any differences in the installed header trees + if diff -r -q "$(get_header_tree "$base_ref")" "$(get_header_tree "$past_ref")" > /dev/null 2>&1; then + printf "No changes to UAPI headers were applied between %s and %s\n" "$past_ref" "${base_ref:-dirty tree}" + exit "$SUCCESS" + fi + + if ! check_uapi_files "$base_ref" "$past_ref" "$abi_error_log"; then + exit "$FAIL_ABI" + fi +} + +main() { + MAX_THREADS=$(nproc) + VERBOSE="false" + IGNORE_AMBIGUOUS_CHANGES="false" + quiet="false" + local base_ref="" + while getopts "hb:p:j:l:iqv" opt; do + case $opt in + h) + print_usage + exit "$SUCCESS" + ;; + b) + base_ref="$OPTARG" + ;; + p) + past_ref="$OPTARG" + ;; + j) + MAX_THREADS="$OPTARG" + ;; + l) + abi_error_log="$OPTARG" + ;; + i) + IGNORE_AMBIGUOUS_CHANGES="true" + ;; + q) + quiet="true" + VERBOSE="false" + ;; + v) + VERBOSE="true" + quiet="false" + ;; + *) + exit "$FAIL_PREREQ" + esac + done + + if [ "$quiet" = "true" ]; then + exec > /dev/null 2>&1 + fi + + run "$base_ref" "$past_ref" "$abi_error_log" "$@" +} + +main "$@" diff --git a/scripts/gdb/linux/tasks.py b/scripts/gdb/linux/tasks.py index aa5ab6251f76..6793d6e86e77 100644 --- a/scripts/gdb/linux/tasks.py +++ b/scripts/gdb/linux/tasks.py @@ -82,21 +82,12 @@ LxPs() thread_info_type = utils.CachedType("struct thread_info") -ia64_task_size = None - def get_thread_info(task): thread_info_ptr_type = thread_info_type.get_type().pointer() - if utils.is_target_arch("ia64"): - global ia64_task_size - if ia64_task_size is None: - ia64_task_size = gdb.parse_and_eval("sizeof(struct task_struct)") - thread_info_addr = task.address + ia64_task_size - thread_info = thread_info_addr.cast(thread_info_ptr_type) - else: - if task.type.fields()[0].type == thread_info_type.get_type(): - return task['thread_info'] - thread_info = task['stack'].cast(thread_info_ptr_type) + if task.type.fields()[0].type == thread_info_type.get_type(): + return task['thread_info'] + thread_info = task['stack'].cast(thread_info_ptr_type) return thread_info.dereference() diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs index 3c6cbe2b278d..0da52b548ba5 100644 --- a/scripts/generate_rust_target.rs +++ b/scripts/generate_rust_target.rs @@ -161,6 +161,13 @@ fn main() { ts.push("features", features); ts.push("llvm-target", "x86_64-linux-gnu"); ts.push("target-pointer-width", "64"); + } else if cfg.has("LOONGARCH") { + ts.push("arch", "loongarch64"); + ts.push("data-layout", "e-m:e-p:64:64-i64:64-i128:128-n64-S128"); + ts.push("features", "-f,-d"); + ts.push("llvm-target", "loongarch64-linux-gnusf"); + ts.push("llvm-abiname", "lp64s"); + ts.push("target-pointer-width", "64"); } else { panic!("Unsupported architecture"); } diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c index f5dfdb9d80e9..f3901c55df23 100644 --- a/scripts/genksyms/genksyms.c +++ b/scripts/genksyms/genksyms.c @@ -16,9 +16,7 @@ #include <unistd.h> #include <assert.h> #include <stdarg.h> -#ifdef __GNU_LIBRARY__ #include <getopt.h> -#endif /* __GNU_LIBRARY__ */ #include "genksyms.h" /*----------------------------------------------------------------------*/ @@ -718,8 +716,6 @@ void error_with_pos(const char *fmt, ...) static void genksyms_usage(void) { fputs("Usage:\n" "genksyms [-adDTwqhVR] > /path/to/.tmp_obj.ver\n" "\n" -#ifdef __GNU_LIBRARY__ - " -s, --symbol-prefix Select symbol prefix\n" " -d, --debug Increment the debug level (repeatable)\n" " -D, --dump Dump expanded symbol defs (for debugging only)\n" " -r, --reference file Read reference symbols from a file\n" @@ -729,18 +725,6 @@ static void genksyms_usage(void) " -q, --quiet Disable warnings (default)\n" " -h, --help Print this message\n" " -V, --version Print the release version\n" -#else /* __GNU_LIBRARY__ */ - " -s Select symbol prefix\n" - " -d Increment the debug level (repeatable)\n" - " -D Dump expanded symbol defs (for debugging only)\n" - " -r file Read reference symbols from a file\n" - " -T file Dump expanded types into file\n" - " -p Preserve reference modversions or fail\n" - " -w Enable warnings\n" - " -q Disable warnings (default)\n" - " -h Print this message\n" - " -V Print the release version\n" -#endif /* __GNU_LIBRARY__ */ , stderr); } @@ -749,7 +733,6 @@ int main(int argc, char **argv) FILE *dumpfile = NULL, *ref_file = NULL; int o; -#ifdef __GNU_LIBRARY__ struct option long_opts[] = { {"debug", 0, 0, 'd'}, {"warnings", 0, 0, 'w'}, @@ -763,11 +746,8 @@ int main(int argc, char **argv) {0, 0, 0, 0} }; - while ((o = getopt_long(argc, argv, "s:dwqVDr:T:ph", + while ((o = getopt_long(argc, argv, "dwqVDr:T:ph", &long_opts[0], NULL)) != EOF) -#else /* __GNU_LIBRARY__ */ - while ((o = getopt(argc, argv, "s:dwqVDr:T:ph")) != EOF) -#endif /* __GNU_LIBRARY__ */ switch (o) { case 'd': flag_debug++; diff --git a/scripts/git.orderFile b/scripts/git.orderFile new file mode 100644 index 000000000000..5102ba73357f --- /dev/null +++ b/scripts/git.orderFile @@ -0,0 +1,42 @@ +# SPDX-License-Identifier: GPL-2.0 + +# order file for git, to produce patches which are easier to review +# by diffing the important stuff like header changes first. +# +# one-off usage: +# git diff -O scripts/git.orderFile ... +# +# add to git config: +# git config diff.orderFile scripts/git.orderFile +# + +MAINTAINERS + +# Documentation +Documentation/* +*.rst + +# git-specific +.gitignore +scripts/git.orderFile + +# build system +Kconfig* +*/Kconfig* +Kbuild* +*/Kbuild* +Makefile* +*/Makefile* +*.mak +*.mk +scripts/* + +# semantic patches +*.cocci + +# headers +*types.h +*.h + +# code +*.c diff --git a/scripts/head-object-list.txt b/scripts/head-object-list.txt index 26359968744e..890f69005bab 100644 --- a/scripts/head-object-list.txt +++ b/scripts/head-object-list.txt @@ -17,7 +17,6 @@ arch/arm/kernel/head-nommu.o arch/arm/kernel/head.o arch/csky/kernel/head.o arch/hexagon/kernel/head.o -arch/ia64/kernel/head.o arch/loongarch/kernel/head.o arch/m68k/68000/head.o arch/m68k/coldfire/head.o diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index 4eee155121a8..ea1bf3b3dbde 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -27,6 +27,14 @@ KCONFIG_DEFCONFIG_LIST += \ endif KCONFIG_DEFCONFIG_LIST += arch/$(SRCARCH)/configs/$(KBUILD_DEFCONFIG) +ifneq ($(findstring c, $(KBUILD_EXTRA_WARN)),) +export KCONFIG_WARN_UNKNOWN_SYMBOLS=1 +endif + +ifneq ($(findstring e, $(KBUILD_EXTRA_WARN)),) +export KCONFIG_WERROR=1 +endif + # We need this, in case the user has it in its environment unexport CONFIG_ @@ -99,7 +107,7 @@ config-fragments = $(call configfiles,$@) %.config: $(obj)/conf $(if $(config-fragments),, $(error $@ fragment does not exists on this architecture)) - $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m .config $(config-fragments) + $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m $(KCONFIG_CONFIG) $(config-fragments) $(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig PHONY += tinyconfig @@ -166,7 +174,7 @@ conf-objs := conf.o $(common-objs) # nconf: Used for the nconfig target based on ncurses hostprogs += nconf -nconf-objs := nconf.o nconf.gui.o $(common-objs) +nconf-objs := nconf.o nconf.gui.o mnconf-common.o $(common-objs) HOSTLDLIBS_nconf = $(call read-file, $(obj)/nconf-libs) HOSTCFLAGS_nconf.o = $(call read-file, $(obj)/nconf-cflags) @@ -179,7 +187,7 @@ $(obj)/nconf.o $(obj)/nconf.gui.o: | $(obj)/nconf-cflags hostprogs += mconf lxdialog := $(addprefix lxdialog/, \ checklist.o inputbox.o menubox.o textbox.o util.o yesno.o) -mconf-objs := mconf.o $(lxdialog) $(common-objs) +mconf-objs := mconf.o $(lxdialog) mnconf-common.o $(common-objs) HOSTLDLIBS_mconf = $(call read-file, $(obj)/mconf-libs) $(foreach f, mconf.o $(lxdialog), \ diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c index 33d19e419908..662a5e7c37c2 100644 --- a/scripts/kconfig/conf.c +++ b/scripts/kconfig/conf.c @@ -827,6 +827,9 @@ int main(int ac, char **av) break; } + if (conf_errors()) + exit(1); + if (sync_kconfig) { name = getenv("KCONFIG_NOSILENTUPDATE"); if (name && *name) { @@ -890,6 +893,9 @@ int main(int ac, char **av) break; } + if (sym_dep_errors()) + exit(1); + if (input_mode == savedefconfig) { if (conf_write_defconfig(defconfig_file)) { fprintf(stderr, "n*** Error while saving defconfig to: %s\n\n", diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 4a6811d77d18..f53dcdd44597 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -155,6 +155,13 @@ static void conf_message(const char *fmt, ...) static const char *conf_filename; static int conf_lineno, conf_warnings; +bool conf_errors(void) +{ + if (conf_warnings) + return getenv("KCONFIG_WERROR"); + return false; +} + static void conf_warning(const char *fmt, ...) { va_list ap; @@ -289,16 +296,12 @@ static int conf_set_sym_val(struct symbol *sym, int def, int def_flags, char *p) #define LINE_GROWTH 16 static int add_byte(int c, char **lineptr, size_t slen, size_t *n) { - char *nline; size_t new_size = slen + 1; + if (new_size > *n) { new_size += LINE_GROWTH - 1; new_size *= 2; - nline = xrealloc(*lineptr, new_size); - if (!nline) - return -1; - - *lineptr = nline; + *lineptr = xrealloc(*lineptr, new_size); *n = new_size; } @@ -341,19 +344,37 @@ e_out: return -1; } +/* like getline(), but the newline character is stripped away */ +static ssize_t getline_stripped(char **lineptr, size_t *n, FILE *stream) +{ + ssize_t len; + + len = compat_getline(lineptr, n, stream); + + if (len > 0 && (*lineptr)[len - 1] == '\n') { + len--; + (*lineptr)[len] = '\0'; + + if (len > 0 && (*lineptr)[len - 1] == '\r') { + len--; + (*lineptr)[len] = '\0'; + } + } + + return len; +} + int conf_read_simple(const char *name, int def) { FILE *in = NULL; char *line = NULL; size_t line_asize = 0; - char *p, *p2; + char *p, *val; struct symbol *sym; int i, def_flags; - const char *warn_unknown; - const char *werror; + const char *warn_unknown, *sym_name; warn_unknown = getenv("KCONFIG_WARN_UNKNOWN_SYMBOLS"); - werror = getenv("KCONFIG_WERROR"); if (name) { in = zconf_fopen(name); } else { @@ -417,8 +438,7 @@ load: case S_INT: case S_HEX: case S_STRING: - if (sym->def[def].val) - free(sym->def[def].val); + free(sym->def[def].val); /* fall through */ default: sym->def[def].val = NULL; @@ -426,90 +446,68 @@ load: } } - while (compat_getline(&line, &line_asize, in) != -1) { + while (getline_stripped(&line, &line_asize, in) != -1) { conf_lineno++; - sym = NULL; + + if (!line[0]) /* blank line */ + continue; + if (line[0] == '#') { - if (memcmp(line + 2, CONFIG_, strlen(CONFIG_))) + if (line[1] != ' ') + continue; + p = line + 2; + if (memcmp(p, CONFIG_, strlen(CONFIG_))) continue; - p = strchr(line + 2 + strlen(CONFIG_), ' '); + sym_name = p + strlen(CONFIG_); + p = strchr(sym_name, ' '); if (!p) continue; *p++ = 0; - if (strncmp(p, "is not set", 10)) + if (strcmp(p, "is not set")) continue; - if (def == S_DEF_USER) { - sym = sym_find(line + 2 + strlen(CONFIG_)); - if (!sym) { - if (warn_unknown) - conf_warning("unknown symbol: %s", - line + 2 + strlen(CONFIG_)); - - conf_set_changed(true); - continue; - } - } else { - sym = sym_lookup(line + 2 + strlen(CONFIG_), 0); - if (sym->type == S_UNKNOWN) - sym->type = S_BOOLEAN; - } - if (sym->flags & def_flags) { - conf_warning("override: reassigning to symbol %s", sym->name); - } - switch (sym->type) { - case S_BOOLEAN: - case S_TRISTATE: - sym->def[def].tri = no; - sym->flags |= def_flags; - break; - default: - ; - } - } else if (memcmp(line, CONFIG_, strlen(CONFIG_)) == 0) { - p = strchr(line + strlen(CONFIG_), '='); - if (!p) + + val = "n"; + } else { + if (memcmp(line, CONFIG_, strlen(CONFIG_))) { + conf_warning("unexpected data: %s", line); continue; - *p++ = 0; - p2 = strchr(p, '\n'); - if (p2) { - *p2-- = 0; - if (*p2 == '\r') - *p2 = 0; } - sym = sym_find(line + strlen(CONFIG_)); - if (!sym) { - if (def == S_DEF_AUTO) { - /* - * Reading from include/config/auto.conf - * If CONFIG_FOO previously existed in - * auto.conf but it is missing now, - * include/config/FOO must be touched. - */ - conf_touch_dep(line + strlen(CONFIG_)); - } else { - if (warn_unknown) - conf_warning("unknown symbol: %s", - line + strlen(CONFIG_)); - - conf_set_changed(true); - } + sym_name = line + strlen(CONFIG_); + p = strchr(sym_name, '='); + if (!p) { + conf_warning("unexpected data: %s", line); continue; } + *p = 0; + val = p + 1; + } - if (sym->flags & def_flags) { - conf_warning("override: reassigning to symbol %s", sym->name); - } - if (conf_set_sym_val(sym, def, def_flags, p)) - continue; - } else { - if (line[0] != '\r' && line[0] != '\n') - conf_warning("unexpected data: %.*s", - (int)strcspn(line, "\r\n"), line); + sym = sym_find(sym_name); + if (!sym) { + if (def == S_DEF_AUTO) { + /* + * Reading from include/config/auto.conf. + * If CONFIG_FOO previously existed in auto.conf + * but it is missing now, include/config/FOO + * must be touched. + */ + conf_touch_dep(sym_name); + } else { + if (warn_unknown) + conf_warning("unknown symbol: %s", sym_name); + conf_set_changed(true); + } continue; } + if (sym->flags & def_flags) + conf_warning("override: reassigning to symbol %s", sym->name); + + if (conf_set_sym_val(sym, def, def_flags, val)) + continue; + if (sym && sym_is_choice_value(sym)) { struct symbol *cs = prop_get_symbol(sym_get_choice_prop(sym)); switch (sym->def[def].tri) { @@ -533,9 +531,6 @@ load: free(line); fclose(in); - if (conf_warnings && werror) - exit(1); - return 0; } @@ -594,7 +589,7 @@ int conf_read(const char *name) /* Reset a string value if it's out of range */ if (sym_string_within_range(sym, sym->def[S_DEF_USER].val)) break; - sym->flags &= ~(SYMBOL_VALID|SYMBOL_DEF_USER); + sym->flags &= ~SYMBOL_VALID; conf_unsaved++; break; default: diff --git a/scripts/kconfig/expr.c b/scripts/kconfig/expr.c index 81ebf8108ca7..a290de36307b 100644 --- a/scripts/kconfig/expr.c +++ b/scripts/kconfig/expr.c @@ -1131,7 +1131,6 @@ static int expr_compare_type(enum expr_type t1, enum expr_type t2) default: return -1; } - printf("[%dgt%d?]", t1, t2); return 0; } diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h index 471a59acecec..5cdc8f5e6446 100644 --- a/scripts/kconfig/lkc.h +++ b/scripts/kconfig/lkc.h @@ -99,8 +99,6 @@ bool menu_is_visible(struct menu *menu); bool menu_has_prompt(struct menu *menu); const char *menu_get_prompt(struct menu *menu); struct menu *menu_get_parent_menu(struct menu *menu); -bool menu_has_help(struct menu *menu); -const char *menu_get_help(struct menu *menu); int get_jump_key_char(void); struct gstr get_relations_str(struct symbol **sym_arr, struct list_head *head); void menu_get_ext_help(struct menu *menu, struct gstr *help); diff --git a/scripts/kconfig/lkc_proto.h b/scripts/kconfig/lkc_proto.h index edd1e617b25c..a4ae5e9eadad 100644 --- a/scripts/kconfig/lkc_proto.h +++ b/scripts/kconfig/lkc_proto.h @@ -1,4 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LKC_PROTO_H +#define LKC_PROTO_H + #include <stdarg.h> /* confdata.c */ @@ -12,6 +15,7 @@ void conf_set_changed(bool val); bool conf_get_changed(void); void conf_set_changed_callback(void (*fn)(void)); void conf_set_message_callback(void (*fn)(const char *s)); +bool conf_errors(void); /* symbol.c */ extern struct symbol * symbol_hash[SYMBOL_HASHSIZE]; @@ -22,6 +26,7 @@ void print_symbol_for_listconfig(struct symbol *sym); struct symbol ** sym_re_search(const char *pattern); const char * sym_type_name(enum symbol_type type); void sym_calc_value(struct symbol *sym); +bool sym_dep_errors(void); enum symbol_type sym_get_type(struct symbol *sym); bool sym_tristate_within_range(struct symbol *sym,tristate tri); bool sym_set_tristate_value(struct symbol *sym,tristate tri); @@ -50,3 +55,5 @@ char *expand_one_token(const char **str); /* expr.c */ void expr_print(struct expr *e, void (*fn)(void *, struct symbol *, const char *), void *data, int prevtoken); + +#endif /* LKC_PROTO_H */ diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c index eccc87a441e7..5df32148a869 100644 --- a/scripts/kconfig/mconf.c +++ b/scripts/kconfig/mconf.c @@ -21,6 +21,7 @@ #include "lkc.h" #include "lxdialog/dialog.h" +#include "mnconf-common.h" static const char mconf_readme[] = "Overview\n" @@ -247,7 +248,7 @@ search_help[] = " -> PCI support (PCI [=y])\n" "(1) -> PCI access mode (<choice> [=y])\n" " Defined at drivers/pci/Kconfig:47\n" - " Depends on: X86_LOCAL_APIC && X86_IO_APIC || IA64\n" + " Depends on: X86_LOCAL_APIC && X86_IO_APIC\n" " Selects: LIBCRC32\n" " Selected by: BAR [=n]\n" "-----------------------------------------------------------------\n" @@ -286,7 +287,6 @@ static int single_menu_mode; static int show_all_options; static int save_and_exit; static int silent; -static int jump_key_char; static void conf(struct menu *menu, struct menu *active_menu); @@ -378,58 +378,6 @@ static void show_help(struct menu *menu) str_free(&help); } -struct search_data { - struct list_head *head; - struct menu *target; -}; - -static int next_jump_key(int key) -{ - if (key < '1' || key > '9') - return '1'; - - key++; - - if (key > '9') - key = '1'; - - return key; -} - -static int handle_search_keys(int key, size_t start, size_t end, void *_data) -{ - struct search_data *data = _data; - struct jump_key *pos; - int index = 0; - - if (key < '1' || key > '9') - return 0; - - list_for_each_entry(pos, data->head, entries) { - index = next_jump_key(index); - - if (pos->offset < start) - continue; - - if (pos->offset >= end) - break; - - if (key == index) { - data->target = pos->target; - return 1; - } - } - - return 0; -} - -int get_jump_key_char(void) -{ - jump_key_char = next_jump_key(jump_key_char); - - return jump_key_char; -} - static void search_conf(void) { struct symbol **sym_arr; diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c index 61c442d84aef..2cce8b651f61 100644 --- a/scripts/kconfig/menu.c +++ b/scripts/kconfig/menu.c @@ -673,19 +673,6 @@ struct menu *menu_get_parent_menu(struct menu *menu) return menu; } -bool menu_has_help(struct menu *menu) -{ - return menu->help != NULL; -} - -const char *menu_get_help(struct menu *menu) -{ - if (menu->help) - return menu->help; - else - return ""; -} - static void get_def_str(struct gstr *r, struct menu *menu) { str_printf(r, "Defined at %s:%d\n", @@ -856,10 +843,10 @@ void menu_get_ext_help(struct menu *menu, struct gstr *help) struct symbol *sym = menu->sym; const char *help_text = nohelp_text; - if (menu_has_help(menu)) { + if (menu->help) { if (sym->name) str_printf(help, "%s%s:\n\n", CONFIG_, sym->name); - help_text = menu_get_help(menu); + help_text = menu->help; } str_printf(help, "%s\n", help_text); if (sym) diff --git a/scripts/kconfig/mnconf-common.c b/scripts/kconfig/mnconf-common.c new file mode 100644 index 000000000000..18cb9a6c5aaa --- /dev/null +++ b/scripts/kconfig/mnconf-common.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "expr.h" +#include "list.h" +#include "mnconf-common.h" + +int jump_key_char; + +int next_jump_key(int key) +{ + if (key < '1' || key > '9') + return '1'; + + key++; + + if (key > '9') + key = '1'; + + return key; +} + +int handle_search_keys(int key, size_t start, size_t end, void *_data) +{ + struct search_data *data = _data; + struct jump_key *pos; + int index = 0; + + if (key < '1' || key > '9') + return 0; + + list_for_each_entry(pos, data->head, entries) { + index = next_jump_key(index); + + if (pos->offset < start) + continue; + + if (pos->offset >= end) + break; + + if (key == index) { + data->target = pos->target; + return 1; + } + } + + return 0; +} + +int get_jump_key_char(void) +{ + jump_key_char = next_jump_key(jump_key_char); + + return jump_key_char; +} diff --git a/scripts/kconfig/mnconf-common.h b/scripts/kconfig/mnconf-common.h new file mode 100644 index 000000000000..ab6292cc4bf2 --- /dev/null +++ b/scripts/kconfig/mnconf-common.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef MNCONF_COMMON_H +#define MNCONF_COMMON_H + +#include <stddef.h> + +struct search_data { + struct list_head *head; + struct menu *target; +}; + +extern int jump_key_char; + +int next_jump_key(int key); +int handle_search_keys(int key, size_t start, size_t end, void *_data); +int get_jump_key_char(void); + +#endif /* MNCONF_COMMON_H */ diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c index 143a2c351d57..1148163cfa7e 100644 --- a/scripts/kconfig/nconf.c +++ b/scripts/kconfig/nconf.c @@ -12,6 +12,7 @@ #include <stdlib.h> #include "lkc.h" +#include "mnconf-common.h" #include "nconf.h" #include <ctype.h> @@ -216,7 +217,7 @@ search_help[] = "Symbol: FOO [ = m]\n" "Prompt: Foo bus is used to drive the bar HW\n" "Defined at drivers/pci/Kconfig:47\n" -"Depends on: X86_LOCAL_APIC && X86_IO_APIC || IA64\n" +"Depends on: X86_LOCAL_APIC && X86_IO_APIC\n" "Location:\n" " -> Bus options (PCI, PCMCIA, EISA, ISA)\n" " -> PCI support (PCI [ = y])\n" @@ -279,7 +280,6 @@ static const char *current_instructions = menu_instructions; static char *dialog_input_result; static int dialog_input_result_len; -static int jump_key_char; static void selected_conf(struct menu *menu, struct menu *active_menu); static void conf(struct menu *menu); @@ -691,57 +691,6 @@ static int do_exit(void) return 0; } -struct search_data { - struct list_head *head; - struct menu *target; -}; - -static int next_jump_key(int key) -{ - if (key < '1' || key > '9') - return '1'; - - key++; - - if (key > '9') - key = '1'; - - return key; -} - -static int handle_search_keys(int key, size_t start, size_t end, void *_data) -{ - struct search_data *data = _data; - struct jump_key *pos; - int index = 0; - - if (key < '1' || key > '9') - return 0; - - list_for_each_entry(pos, data->head, entries) { - index = next_jump_key(index); - - if (pos->offset < start) - continue; - - if (pos->offset >= end) - break; - - if (key == index) { - data->target = pos->target; - return 1; - } - } - - return 0; -} - -int get_jump_key_char(void) -{ - jump_key_char = next_jump_key(jump_key_char); - - return jump_key_char; -} static void search_conf(void) { diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c index a76925b46ce6..3e808528aaea 100644 --- a/scripts/kconfig/symbol.c +++ b/scripts/kconfig/symbol.c @@ -29,14 +29,9 @@ struct symbol symbol_no = { .flags = SYMBOL_CONST|SYMBOL_VALID, }; -static struct symbol symbol_empty = { - .name = "", - .curr = { "", no }, - .flags = SYMBOL_VALID, -}; - struct symbol *modules_sym; static tristate modules_val; +static int sym_warnings; enum symbol_type sym_get_type(struct symbol *sym) { @@ -317,6 +312,14 @@ static void sym_warn_unmet_dep(struct symbol *sym) " Selected by [m]:\n"); fputs(str_get(&gs), stderr); + sym_warnings++; +} + +bool sym_dep_errors(void) +{ + if (sym_warnings) + return getenv("KCONFIG_WERROR"); + return false; } void sym_calc_value(struct symbol *sym) @@ -344,9 +347,13 @@ void sym_calc_value(struct symbol *sym) switch (sym->type) { case S_INT: + newval.val = "0"; + break; case S_HEX: + newval.val = "0x0"; + break; case S_STRING: - newval = symbol_empty.curr; + newval.val = ""; break; case S_BOOLEAN: case S_TRISTATE: @@ -697,13 +704,12 @@ const char *sym_get_string_default(struct symbol *sym) { struct property *prop; struct symbol *ds; - const char *str; + const char *str = ""; tristate val; sym_calc_visibility(sym); sym_calc_value(modules_sym); val = symbol_no.curr.tri; - str = symbol_empty.curr.val; /* If symbol has a default value look it up */ prop = sym_get_default_prop(sym); @@ -753,14 +759,17 @@ const char *sym_get_string_default(struct symbol *sym) case yes: return "y"; } case S_INT: + if (!str[0]) + str = "0"; + break; case S_HEX: - return str; - case S_STRING: - return str; - case S_UNKNOWN: + if (!str[0]) + str = "0x0"; + break; + default: break; } - return ""; + return str; } const char *sym_get_string_value(struct symbol *sym) diff --git a/scripts/kconfig/util.c b/scripts/kconfig/util.c index b78f114ad48c..92e5b2b9761d 100644 --- a/scripts/kconfig/util.c +++ b/scripts/kconfig/util.c @@ -42,8 +42,7 @@ struct gstr str_new(void) /* Free storage for growable string */ void str_free(struct gstr *gs) { - if (gs->s) - free(gs->s); + free(gs->s); gs->s = NULL; gs->len = 0; } diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh index c62066825f53..9faa4d3d91e3 100755 --- a/scripts/min-tool-version.sh +++ b/scripts/min-tool-version.sh @@ -26,6 +26,8 @@ gcc) llvm) if [ "$SRCARCH" = s390 ]; then echo 15.0.0 + elif [ "$SRCARCH" = loongarch ]; then + echo 18.0.0 else echo 11.0.0 fi diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index cb6406f485a9..795b21154446 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -60,8 +60,7 @@ static unsigned int nr_unresolved; #define MODULE_NAME_LEN (64 - sizeof(Elf_Addr)) -void __attribute__((format(printf, 2, 3))) -modpost_log(enum loglevel loglevel, const char *fmt, ...) +void modpost_log(enum loglevel loglevel, const char *fmt, ...) { va_list arglist; @@ -91,6 +90,9 @@ modpost_log(enum loglevel loglevel, const char *fmt, ...) error_occurred = true; } +void __attribute__((alias("modpost_log"))) +modpost_log_noret(enum loglevel loglevel, const char *fmt, ...); + static inline bool strends(const char *str, const char *postfix) { if (strlen(str) < strlen(postfix)) @@ -474,11 +476,9 @@ static int parse_elf(struct elf_info *info, const char *filename) fatal("%s: not relocatable object.", filename); /* Check if file offset is correct */ - if (hdr->e_shoff > info->size) { + if (hdr->e_shoff > info->size) fatal("section header offset=%lu in file '%s' is bigger than filesize=%zu\n", (unsigned long)hdr->e_shoff, filename, info->size); - return 0; - } if (hdr->e_shnum == SHN_UNDEF) { /* @@ -516,12 +516,11 @@ static int parse_elf(struct elf_info *info, const char *filename) const char *secname; int nobits = sechdrs[i].sh_type == SHT_NOBITS; - if (!nobits && sechdrs[i].sh_offset > info->size) { + if (!nobits && sechdrs[i].sh_offset > info->size) fatal("%s is truncated. sechdrs[i].sh_offset=%lu > sizeof(*hrd)=%zu\n", filename, (unsigned long)sechdrs[i].sh_offset, sizeof(*hdr)); - return 0; - } + secname = secstrings + sechdrs[i].sh_name; if (strcmp(secname, ".modinfo") == 0) { if (nobits) @@ -1346,6 +1345,14 @@ static Elf_Addr addend_mips_rel(uint32_t *location, unsigned int r_type) #define R_LARCH_SUB32 55 #endif +#ifndef R_LARCH_RELAX +#define R_LARCH_RELAX 100 +#endif + +#ifndef R_LARCH_ALIGN +#define R_LARCH_ALIGN 102 +#endif + static void get_rel_type_and_sym(struct elf_info *elf, uint64_t r_info, unsigned int *r_type, unsigned int *r_sym) { @@ -1400,9 +1407,16 @@ static void section_rela(struct module *mod, struct elf_info *elf, continue; break; case EM_LOONGARCH: - if (!strcmp("__ex_table", fromsec) && - r_type == R_LARCH_SUB32) + switch (r_type) { + case R_LARCH_SUB32: + if (!strcmp("__ex_table", fromsec)) + continue; + break; + case R_LARCH_RELAX: + case R_LARCH_ALIGN: + /* These relocs do not refer to symbols */ continue; + } break; } @@ -1419,7 +1433,7 @@ static void section_rel(struct module *mod, struct elf_info *elf, for (rel = start; rel < stop; rel++) { Elf_Sym *tsym; - Elf_Addr taddr = 0, r_offset; + Elf_Addr taddr, r_offset; unsigned int r_type, r_sym; void *loc; diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h index 69baf014da4f..835cababf1b0 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -197,7 +197,11 @@ enum loglevel { LOG_FATAL }; -void modpost_log(enum loglevel loglevel, const char *fmt, ...); +void __attribute__((format(printf, 2, 3))) +modpost_log(enum loglevel loglevel, const char *fmt, ...); + +void __attribute__((format(printf, 2, 3), noreturn)) +modpost_log_noret(enum loglevel loglevel, const char *fmt, ...); /* * warn - show the given message, then let modpost continue running, still @@ -214,4 +218,4 @@ void modpost_log(enum loglevel loglevel, const char *fmt, ...); */ #define warn(fmt, args...) modpost_log(LOG_WARN, fmt, ##args) #define error(fmt, args...) modpost_log(LOG_ERROR, fmt, ##args) -#define fatal(fmt, args...) modpost_log(LOG_FATAL, fmt, ##args) +#define fatal(fmt, args...) modpost_log_noret(LOG_FATAL, fmt, ##args) diff --git a/scripts/package/builddeb b/scripts/package/builddeb index d7dd0d04c70c..bf96a3c24608 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -25,35 +25,20 @@ if_enabled_echo() { } create_package() { - local pname="$1" pdir="$2" - local dpkg_deb_opts - - mkdir -m 755 -p "$pdir/DEBIAN" - mkdir -p "$pdir/usr/share/doc/$pname" - cp debian/copyright "$pdir/usr/share/doc/$pname/" - cp debian/changelog "$pdir/usr/share/doc/$pname/changelog.Debian" - gzip -n -9 "$pdir/usr/share/doc/$pname/changelog.Debian" - sh -c "cd '$pdir'; find . -type f ! -path './DEBIAN/*' -printf '%P\0' \ - | xargs -r0 md5sum > DEBIAN/md5sums" - - # Fix ownership and permissions - if [ "$DEB_RULES_REQUIRES_ROOT" = "no" ]; then - dpkg_deb_opts="--root-owner-group" - else - chown -R root:root "$pdir" - fi - # a+rX in case we are in a restrictive umask environment like 0077 - # ug-s in case we build in a setuid/setgid directory - chmod -R go-w,a+rX,ug-s "$pdir" - - # Create the package - dpkg-gencontrol -p$pname -P"$pdir" - dpkg-deb $dpkg_deb_opts ${KDEB_COMPRESS:+-Z$KDEB_COMPRESS} --build "$pdir" .. + export DH_OPTIONS="-p${1}" + + dh_installdocs + dh_installchangelogs + dh_compress + dh_fixperms + dh_gencontrol + dh_md5sums + dh_builddeb -- ${KDEB_COMPRESS:+-Z$KDEB_COMPRESS} } install_linux_image () { - pdir=$1 - pname=$2 + pname=$1 + pdir=debian/$1 rm -rf ${pdir} @@ -62,7 +47,7 @@ install_linux_image () { ${MAKE} -f ${srctree}/Makefile INSTALL_DTBS_PATH="${pdir}/usr/lib/linux-image-${KERNELRELEASE}" dtbs_install fi - ${MAKE} -f ${srctree}/Makefile INSTALL_MOD_PATH="${pdir}" modules_install + ${MAKE} -f ${srctree}/Makefile INSTALL_MOD_PATH="${pdir}" INSTALL_MOD_STRIP=1 modules_install rm -f "${pdir}/lib/modules/${KERNELRELEASE}/build" # Install the kernel @@ -122,26 +107,22 @@ install_linux_image () { } install_linux_image_dbg () { - pdir=$1 - image_pdir=$2 + pdir=debian/$1 rm -rf ${pdir} - for module in $(find ${image_pdir}/lib/modules/ -name *.ko -printf '%P\n'); do - module=lib/modules/${module} - mkdir -p $(dirname ${pdir}/usr/lib/debug/${module}) - # only keep debug symbols in the debug file - ${OBJCOPY} --only-keep-debug ${image_pdir}/${module} ${pdir}/usr/lib/debug/${module} - # strip original module from debug symbols - ${OBJCOPY} --strip-debug ${image_pdir}/${module} - # then add a link to those - ${OBJCOPY} --add-gnu-debuglink=${pdir}/usr/lib/debug/${module} ${image_pdir}/${module} - done + # Parse modules.order directly because 'make modules_install' may sign, + # compress modules, and then run unneeded depmod. + while read -r mod; do + mod="${mod%.o}.ko" + dbg="${pdir}/usr/lib/debug/lib/modules/${KERNELRELEASE}/kernel/${mod}" + buildid=$("${READELF}" -n "${mod}" | sed -n 's@^.*Build ID: \(..\)\(.*\)@\1/\2@p') + link="${pdir}/usr/lib/debug/.build-id/${buildid}.debug" - # re-sign stripped modules - if is_enabled CONFIG_MODULE_SIG_ALL; then - ${MAKE} -f ${srctree}/Makefile INSTALL_MOD_PATH="${image_pdir}" modules_sign - fi + mkdir -p "${dbg%/*}" "${link%/*}" + "${OBJCOPY}" --only-keep-debug "${mod}" "${dbg}" + ln -sf --relative "${dbg}" "${link}" + done < modules.order # Build debug package # Different tools want the image in different locations @@ -156,8 +137,8 @@ install_linux_image_dbg () { } install_kernel_headers () { - pdir=$1 - version=$2 + pdir=debian/$1 + version=${1#linux-headers-} rm -rf $pdir @@ -168,18 +149,16 @@ install_kernel_headers () { } install_libc_headers () { - pdir=$1 + pdir=debian/$1 rm -rf $pdir - $MAKE -f $srctree/Makefile headers $MAKE -f $srctree/Makefile headers_install INSTALL_HDR_PATH=$pdir/usr # move asm headers to /usr/include/<libc-machine>/asm to match the structure # used by Debian-based distros (to support multi-arch) - host_arch=$(dpkg-architecture -a$DEB_HOST_ARCH -qDEB_HOST_MULTIARCH) - mkdir $pdir/usr/include/$host_arch - mv $pdir/usr/include/asm $pdir/usr/include/$host_arch/ + mkdir "$pdir/usr/include/${DEB_HOST_MULTIARCH}" + mv "$pdir/usr/include/asm" "$pdir/usr/include/${DEB_HOST_MULTIARCH}" } rm -f debian/files @@ -190,30 +169,13 @@ for package in ${packages_enabled} do case ${package} in *-dbg) - # This must be done after linux-image, that is, we expect the - # debug package appears after linux-image in debian/control. - install_linux_image_dbg debian/linux-image-dbg debian/linux-image;; - linux-image-*|user-mode-linux-*) - install_linux_image debian/linux-image ${package};; - linux-libc-dev) - install_libc_headers debian/linux-libc-dev;; - linux-headers-*) - install_kernel_headers debian/linux-headers ${package#linux-headers-};; - esac -done - -for package in ${packages_enabled} -do - case ${package} in - *-dbg) - create_package ${package} debian/linux-image-dbg;; + install_linux_image_dbg "${package}";; linux-image-*|user-mode-linux-*) - create_package ${package} debian/linux-image;; + install_linux_image "${package}";; linux-libc-dev) - create_package ${package} debian/linux-libc-dev;; + install_libc_headers "${package}";; linux-headers-*) - create_package ${package} debian/linux-headers;; + install_kernel_headers "${package}";; esac + create_package "${package}" done - -exit 0 diff --git a/scripts/package/buildtar b/scripts/package/buildtar index 65b4ea502962..72c91a1b832f 100755 --- a/scripts/package/buildtar +++ b/scripts/package/buildtar @@ -23,7 +23,6 @@ tmpdir=$1 # rm -rf -- "${tmpdir}" mkdir -p -- "${tmpdir}/boot" -dirs=boot # @@ -38,12 +37,9 @@ fi # -# Try to install modules +# Install modules # -if grep -q '^CONFIG_MODULES=y' include/config/auto.conf; then - make ARCH="${ARCH}" -f ${srctree}/Makefile INSTALL_MOD_PATH="${tmpdir}" modules_install - dirs="$dirs lib" -fi +make ARCH="${ARCH}" -f ${srctree}/Makefile INSTALL_MOD_PATH="${tmpdir}" modules_install # diff --git a/scripts/package/deb-build-option b/scripts/package/deb-build-option deleted file mode 100755 index 7950eff01781..000000000000 --- a/scripts/package/deb-build-option +++ /dev/null @@ -1,14 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0-only - -# Set up CROSS_COMPILE if not defined yet -if [ "${CROSS_COMPILE+set}" != "set" -a "${DEB_HOST_ARCH}" != "${DEB_BUILD_ARCH}" ]; then - echo CROSS_COMPILE=${DEB_HOST_GNU_TYPE}- -fi - -version=$(dpkg-parsechangelog -S Version) -debian_revision="${version##*-}" - -if [ "${version}" != "${debian_revision}" ]; then - echo KBUILD_BUILD_VERSION=${debian_revision} -fi diff --git a/scripts/package/debian/copyright b/scripts/package/debian/copyright new file mode 100644 index 000000000000..4f1f06221f09 --- /dev/null +++ b/scripts/package/debian/copyright @@ -0,0 +1,16 @@ +This is a packaged upstream version of the Linux kernel. + +The sources may be found at most Linux archive sites, including: +https://www.kernel.org/pub/linux/kernel + +Copyright: 1991 - 2023 Linus Torvalds and others. + +The git repository for mainline kernel development is at: +git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; version 2 dated June, 1991. + +On Debian GNU/Linux systems, the complete text of the GNU General Public +License version 2 can be found in `/usr/share/common-licenses/GPL-2'. diff --git a/scripts/package/debian/rules b/scripts/package/debian/rules index 3dafa9496c63..098307780062 100755 --- a/scripts/package/debian/rules +++ b/scripts/package/debian/rules @@ -1,33 +1,46 @@ #!/usr/bin/make -f # SPDX-License-Identifier: GPL-2.0-only -include debian/rules.vars +# in case debian/rules is executed directly +export DEB_RULES_REQUIRES_ROOT := no -srctree ?= . +include debian/rules.vars ifneq (,$(filter-out parallel=1,$(filter parallel=%,$(DEB_BUILD_OPTIONS)))) NUMJOBS = $(patsubst parallel=%,%,$(filter parallel=%,$(DEB_BUILD_OPTIONS))) MAKEFLAGS += -j$(NUMJOBS) endif +revision = $(lastword $(subst -, ,$(shell dpkg-parsechangelog -S Version))) +CROSS_COMPILE ?= $(filter-out $(DEB_BUILD_GNU_TYPE)-, $(DEB_HOST_GNU_TYPE)-) +make-opts = ARCH=$(ARCH) KERNELRELEASE=$(KERNELRELEASE) KBUILD_BUILD_VERSION=$(revision) $(addprefix CROSS_COMPILE=,$(CROSS_COMPILE)) + .PHONY: binary binary-indep binary-arch binary: binary-arch binary-indep binary-indep: build-indep binary-arch: build-arch - $(MAKE) -f $(srctree)/Makefile ARCH=$(ARCH) \ - KERNELRELEASE=$(KERNELRELEASE) \ - run-command KBUILD_RUN_COMMAND=+$(srctree)/scripts/package/builddeb + $(MAKE) $(make-opts) \ + run-command KBUILD_RUN_COMMAND='+$$(srctree)/scripts/package/builddeb' .PHONY: build build-indep build-arch build: build-arch build-indep build-indep: build-arch: - $(MAKE) -f $(srctree)/Makefile ARCH=$(ARCH) \ - KERNELRELEASE=$(KERNELRELEASE) \ - $(shell $(srctree)/scripts/package/deb-build-option) \ - olddefconfig all + $(MAKE) $(make-opts) olddefconfig + $(MAKE) $(make-opts) $(if $(filter um,$(ARCH)),,headers) all .PHONY: clean clean: - rm -rf debian/files debian/linux-* - $(MAKE) -f $(srctree)/Makefile ARCH=$(ARCH) clean + rm -rf debian/files debian/linux-* debian/deb-env.vars* + $(MAKE) ARCH=$(ARCH) clean + +# If DEB_HOST_ARCH is empty, it is likely that debian/rules was executed +# directly. Run 'dpkg-architecture --print-set --print-format=make' to +# generate a makefile construct that exports all DEB_* variables. +ifndef DEB_HOST_ARCH +include debian/deb-env.vars + +debian/deb-env.vars: + dpkg-architecture -a$$(cat debian/arch) --print-set --print-format=make > $@.tmp + mv $@.tmp $@ +endif diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build index 8a7051fad087..76e0765dfcd6 100755 --- a/scripts/package/install-extmod-build +++ b/scripts/package/install-extmod-build @@ -20,7 +20,7 @@ mkdir -p "${destdir}" find "arch/${SRCARCH}" -maxdepth 1 -name 'Makefile*' find include scripts -type f -o -type l find "arch/${SRCARCH}" -name Kbuild.platforms -o -name Platform - find "arch/${SRCARCH}" -name include -o -name scripts -type d + find "arch/${SRCARCH}" -name include -type d ) | tar -c -f - -C "${srctree}" -T - | tar -xf - -C "${destdir}" { diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec index 3eee0143e0c5..89298983a169 100644 --- a/scripts/package/kernel.spec +++ b/scripts/package/kernel.spec @@ -56,13 +56,7 @@ patch -p1 < %{SOURCE2} %install mkdir -p %{buildroot}/boot -%ifarch ia64 -mkdir -p %{buildroot}/boot/efi -cp $(%{make} %{makeflags} -s image_name) %{buildroot}/boot/efi/vmlinuz-%{KERNELRELEASE} -ln -s efi/vmlinuz-%{KERNELRELEASE} %{buildroot}/boot/ -%else cp $(%{make} %{makeflags} -s image_name) %{buildroot}/boot/vmlinuz-%{KERNELRELEASE} -%endif %{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} modules_install %{make} %{makeflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install cp System.map %{buildroot}/boot/System.map-%{KERNELRELEASE} diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index 5044224cf671..070149c985fe 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -26,7 +26,7 @@ set_debarch() { # Attempt to find the correct Debian architecture case "$UTS_MACHINE" in - i386|ia64|alpha|m68k|riscv*) + i386|alpha|m68k|riscv*) debarch="$UTS_MACHINE" ;; x86_64) debarch=amd64 ;; @@ -176,8 +176,6 @@ else fi echo $debarch > debian/arch -extra_build_depends=", $(if_enabled_echo CONFIG_UNWINDER_ORC libelf-dev:native)" -extra_build_depends="$extra_build_depends, $(if_enabled_echo CONFIG_SYSTEM_TRUSTED_KEYRING libssl-dev:native)" # Generate a simple changelog template cat <<EOF > debian/changelog @@ -188,26 +186,6 @@ $sourcename ($packageversion) $distribution; urgency=low -- $maintainer $(date -R) EOF -# Generate copyright file -cat <<EOF > debian/copyright -This is a packaged upstream version of the Linux kernel. - -The sources may be found at most Linux archive sites, including: -https://www.kernel.org/pub/linux/kernel - -Copyright: 1991 - 2018 Linus Torvalds and others. - -The git repository for mainline kernel development is at: -git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; version 2 dated June, 1991. - -On Debian GNU/Linux systems, the complete text of the GNU General Public -License version 2 can be found in \`/usr/share/common-licenses/GPL-2'. -EOF - # Generate a control file cat <<EOF > debian/control Source: $sourcename @@ -215,7 +193,8 @@ Section: kernel Priority: optional Maintainer: $maintainer Rules-Requires-Root: no -Build-Depends: bc, debhelper, rsync, kmod, cpio, bison, flex $extra_build_depends +Build-Depends: debhelper-compat (= 12) +Build-Depends-Arch: bc, bison, cpio, flex, kmod, libelf-dev:native, libssl-dev:native, rsync Homepage: https://www.kernel.org/ Package: $packagename-$version @@ -268,6 +247,7 @@ ARCH := ${ARCH} KERNELRELEASE := ${KERNELRELEASE} EOF +cp "${srctree}/scripts/package/debian/copyright" debian/ cp "${srctree}/scripts/package/debian/rules" debian/ exit 0 diff --git a/scripts/package/snapcraft.template b/scripts/package/snapcraft.template index 626d278e4a5a..85d5e07d1b40 100644 --- a/scripts/package/snapcraft.template +++ b/scripts/package/snapcraft.template @@ -10,5 +10,5 @@ parts: kernel: plugin: kernel source: SRCTREE - source-type: tar + source-type: local kernel-with-firmware: false diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index 40ae6b2c7a6d..3e4f54799cc0 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -590,7 +590,6 @@ static int do_file(char const *const fname) ideal_nop = ideal_nop4_arm64; is_fake_mcount64 = arm64_is_fake_mcount; break; - case EM_IA_64: reltype = R_IA64_IMM64; break; case EM_MIPS: /* reltype: e_class */ break; case EM_LOONGARCH: /* reltype: e_class */ break; case EM_PPC: reltype = R_PPC_ADDR32; break; diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 6a4645a57976..f84df9e383fd 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -275,13 +275,6 @@ if ($arch eq "x86_64") { $section_type = '%progbits'; $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_AARCH64_CALL26\\s+_mcount\$"; $type = ".quad"; -} elsif ($arch eq "ia64") { - $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s_mcount\$"; - $type = "data8"; - - if ($is_module eq "0") { - $cc .= " -mconstant-gp"; - } } elsif ($arch eq "sparc64") { # In the objdump output there are giblets like: # 0000000000000000 <igmp_net_exit-0x18>: diff --git a/scripts/xz_wrap.sh b/scripts/xz_wrap.sh index 76e9cbcfbeab..d06baf626abe 100755 --- a/scripts/xz_wrap.sh +++ b/scripts/xz_wrap.sh @@ -15,7 +15,6 @@ LZMA2OPTS= case $SRCARCH in x86) BCJ=--x86 ;; powerpc) BCJ=--powerpc ;; - ia64) BCJ=--ia64; LZMA2OPTS=pb=4 ;; arm) BCJ=--arm ;; sparc) BCJ=--sparc ;; esac diff --git a/security/apparmor/Kconfig b/security/apparmor/Kconfig index e0d1dd0a192a..64cc3044a42c 100644 --- a/security/apparmor/Kconfig +++ b/security/apparmor/Kconfig @@ -57,10 +57,10 @@ config SECURITY_APPARMOR_INTROSPECT_POLICY cpu is paramount. config SECURITY_APPARMOR_HASH - bool "Enable introspection of sha1 hashes for loaded profiles" + bool "Enable introspection of sha256 hashes for loaded profiles" depends on SECURITY_APPARMOR_INTROSPECT_POLICY select CRYPTO - select CRYPTO_SHA1 + select CRYPTO_SHA256 default y help This option selects whether introspection of loaded policy @@ -74,10 +74,10 @@ config SECURITY_APPARMOR_HASH_DEFAULT depends on SECURITY_APPARMOR_HASH default y help - This option selects whether sha1 hashing of loaded policy - is enabled by default. The generation of sha1 hashes for - loaded policy provide system administrators a quick way - to verify that policy in the kernel matches what is expected, + This option selects whether sha256 hashing of loaded policy + is enabled by default. The generation of sha256 hashes for + loaded policy provide system administrators a quick way to + verify that policy in the kernel matches what is expected, however it can slow down policy load on some devices. In these cases policy hashing can be disabled by default and enabled only if needed. diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index f3c77825aa75..bcfea073e3f2 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -1474,7 +1474,7 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata) rawdata->dents[AAFS_LOADDATA_REVISION] = dent; if (aa_g_hash_policy) { - dent = aafs_create_file("sha1", S_IFREG | 0444, dir, + dent = aafs_create_file("sha256", S_IFREG | 0444, dir, rawdata, &seq_rawdata_hash_fops); if (IS_ERR(dent)) goto fail; @@ -1643,11 +1643,11 @@ static const char *rawdata_get_link_base(struct dentry *dentry, return target; } -static const char *rawdata_get_link_sha1(struct dentry *dentry, +static const char *rawdata_get_link_sha256(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { - return rawdata_get_link_base(dentry, inode, done, "sha1"); + return rawdata_get_link_base(dentry, inode, done, "sha256"); } static const char *rawdata_get_link_abi(struct dentry *dentry, @@ -1664,8 +1664,8 @@ static const char *rawdata_get_link_data(struct dentry *dentry, return rawdata_get_link_base(dentry, inode, done, "raw_data"); } -static const struct inode_operations rawdata_link_sha1_iops = { - .get_link = rawdata_get_link_sha1, +static const struct inode_operations rawdata_link_sha256_iops = { + .get_link = rawdata_get_link_sha256, }; static const struct inode_operations rawdata_link_abi_iops = { @@ -1738,7 +1738,7 @@ int __aafs_profile_mkdir(struct aa_profile *profile, struct dentry *parent) profile->dents[AAFS_PROF_ATTACH] = dent; if (profile->hash) { - dent = create_profile_file(dir, "sha1", profile, + dent = create_profile_file(dir, "sha256", profile, &seq_profile_hash_fops); if (IS_ERR(dent)) goto fail; @@ -1748,9 +1748,9 @@ int __aafs_profile_mkdir(struct aa_profile *profile, struct dentry *parent) #ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY if (profile->rawdata) { if (aa_g_hash_policy) { - dent = aafs_create("raw_sha1", S_IFLNK | 0444, dir, + dent = aafs_create("raw_sha256", S_IFLNK | 0444, dir, profile->label.proxy, NULL, NULL, - &rawdata_link_sha1_iops); + &rawdata_link_sha256_iops); if (IS_ERR(dent)) goto fail; aa_get_proxy(profile->label.proxy); diff --git a/security/apparmor/crypto.c b/security/apparmor/crypto.c index 6724e2ff6da8..aad486b2fca6 100644 --- a/security/apparmor/crypto.c +++ b/security/apparmor/crypto.c @@ -106,16 +106,16 @@ static int __init init_profile_hash(void) if (!apparmor_initialized) return 0; - tfm = crypto_alloc_shash("sha1", 0, 0); + tfm = crypto_alloc_shash("sha256", 0, 0); if (IS_ERR(tfm)) { int error = PTR_ERR(tfm); - AA_ERROR("failed to setup profile sha1 hashing: %d\n", error); + AA_ERROR("failed to setup profile sha256 hashing: %d\n", error); return error; } apparmor_tfm = tfm; apparmor_hash_size = crypto_shash_digestsize(apparmor_tfm); - aa_info_message("AppArmor sha1 policy hashing enabled"); + aa_info_message("AppArmor sha256 policy hashing enabled"); return 0; } diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c index 89fbeab4b33b..571158ec6188 100644 --- a/security/apparmor/domain.c +++ b/security/apparmor/domain.c @@ -1311,7 +1311,7 @@ static int change_profile_perms_wrapper(const char *op, const char *name, return error; } -const char *stack_msg = "change_profile unprivileged unconfined converted to stacking"; +static const char *stack_msg = "change_profile unprivileged unconfined converted to stacking"; /** * aa_change_profile - perform a one-way profile transition diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c index 4c198d273f09..cd569fbbfe36 100644 --- a/security/apparmor/lib.c +++ b/security/apparmor/lib.c @@ -41,6 +41,7 @@ void aa_free_str_table(struct aa_str_table *t) kfree_sensitive(t->table[i]); kfree_sensitive(t->table); t->table = NULL; + t->size = 0; } } diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index e490a7000408..7717354ce095 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1023,7 +1023,6 @@ static int apparmor_task_kill(struct task_struct *target, struct kernel_siginfo cl = aa_get_newest_cred_label(cred); error = aa_may_signal(cred, cl, tc, tl, sig); aa_put_label(cl); - return error; } else { cl = __begin_current_label_crit_section(); error = aa_may_signal(current_cred(), cl, tc, tl, sig); @@ -1056,9 +1055,6 @@ static int apparmor_userns_create(const struct cred *cred) return error; } -/** - * apparmor_sk_alloc_security - allocate and attach the sk_security field - */ static int apparmor_sk_alloc_security(struct sock *sk, int family, gfp_t flags) { struct aa_sk_ctx *ctx; @@ -1072,9 +1068,6 @@ static int apparmor_sk_alloc_security(struct sock *sk, int family, gfp_t flags) return 0; } -/** - * apparmor_sk_free_security - free the sk_security field - */ static void apparmor_sk_free_security(struct sock *sk) { struct aa_sk_ctx *ctx = aa_sock(sk); @@ -1087,6 +1080,8 @@ static void apparmor_sk_free_security(struct sock *sk) /** * apparmor_sk_clone_security - clone the sk_security field + * @sk: sock to have security cloned + * @newsk: sock getting clone */ static void apparmor_sk_clone_security(const struct sock *sk, struct sock *newsk) @@ -1103,9 +1098,6 @@ static void apparmor_sk_clone_security(const struct sock *sk, new->peer = aa_get_label(ctx->peer); } -/** - * apparmor_socket_create - check perms before creating a new socket - */ static int apparmor_socket_create(int family, int type, int protocol, int kern) { struct aa_label *label; @@ -1127,10 +1119,14 @@ static int apparmor_socket_create(int family, int type, int protocol, int kern) /** * apparmor_socket_post_create - setup the per-socket security struct + * @sock: socket that is being setup + * @family: family of socket being created + * @type: type of the socket + * @ptotocol: protocol of the socket + * @kern: socket is a special kernel socket * * Note: - * - kernel sockets currently labeled unconfined but we may want to - * move to a special kernel label + * - kernel sockets labeled kernel_t used to use unconfined * - socket may not have sk here if created with sock_create_lite or * sock_alloc. These should be accept cases which will be handled in * sock_graft. @@ -1156,9 +1152,6 @@ static int apparmor_socket_post_create(struct socket *sock, int family, return 0; } -/** - * apparmor_socket_bind - check perms before bind addr to socket - */ static int apparmor_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { @@ -1172,9 +1165,6 @@ static int apparmor_socket_bind(struct socket *sock, aa_sk_perm(OP_BIND, AA_MAY_BIND, sock->sk)); } -/** - * apparmor_socket_connect - check perms before connecting @sock to @address - */ static int apparmor_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen) { @@ -1188,9 +1178,6 @@ static int apparmor_socket_connect(struct socket *sock, aa_sk_perm(OP_CONNECT, AA_MAY_CONNECT, sock->sk)); } -/** - * apparmor_socket_listen - check perms before allowing listen - */ static int apparmor_socket_listen(struct socket *sock, int backlog) { AA_BUG(!sock); @@ -1202,9 +1189,7 @@ static int apparmor_socket_listen(struct socket *sock, int backlog) aa_sk_perm(OP_LISTEN, AA_MAY_LISTEN, sock->sk)); } -/** - * apparmor_socket_accept - check perms before accepting a new connection. - * +/* * Note: while @newsock is created and has some information, the accept * has not been done. */ @@ -1233,18 +1218,12 @@ static int aa_sock_msg_perm(const char *op, u32 request, struct socket *sock, aa_sk_perm(op, request, sock->sk)); } -/** - * apparmor_socket_sendmsg - check perms before sending msg to another socket - */ static int apparmor_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return aa_sock_msg_perm(OP_SENDMSG, AA_MAY_SEND, sock, msg, size); } -/** - * apparmor_socket_recvmsg - check perms before receiving a message - */ static int apparmor_socket_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags) { @@ -1263,17 +1242,11 @@ static int aa_sock_perm(const char *op, u32 request, struct socket *sock) aa_sk_perm(op, request, sock->sk)); } -/** - * apparmor_socket_getsockname - check perms before getting the local address - */ static int apparmor_socket_getsockname(struct socket *sock) { return aa_sock_perm(OP_GETSOCKNAME, AA_MAY_GETATTR, sock); } -/** - * apparmor_socket_getpeername - check perms before getting remote address - */ static int apparmor_socket_getpeername(struct socket *sock) { return aa_sock_perm(OP_GETPEERNAME, AA_MAY_GETATTR, sock); @@ -1292,9 +1265,6 @@ static int aa_sock_opt_perm(const char *op, u32 request, struct socket *sock, aa_sk_perm(op, request, sock->sk)); } -/** - * apparmor_socket_getsockopt - check perms before getting socket options - */ static int apparmor_socket_getsockopt(struct socket *sock, int level, int optname) { @@ -1302,9 +1272,6 @@ static int apparmor_socket_getsockopt(struct socket *sock, int level, level, optname); } -/** - * apparmor_socket_setsockopt - check perms before setting socket options - */ static int apparmor_socket_setsockopt(struct socket *sock, int level, int optname) { @@ -1312,9 +1279,6 @@ static int apparmor_socket_setsockopt(struct socket *sock, int level, level, optname); } -/** - * apparmor_socket_shutdown - check perms before shutting down @sock conn - */ static int apparmor_socket_shutdown(struct socket *sock, int how) { return aa_sock_perm(OP_SHUTDOWN, AA_MAY_SHUTDOWN, sock); @@ -1323,6 +1287,8 @@ static int apparmor_socket_shutdown(struct socket *sock, int how) #ifdef CONFIG_NETWORK_SECMARK /** * apparmor_socket_sock_rcv_skb - check perms before associating skb to sk + * @sk: sk to associate @skb with + * @skb: skb to check for perms * * Note: can not sleep may be called with locks held * @@ -1354,6 +1320,11 @@ static struct aa_label *sk_peer_label(struct sock *sk) /** * apparmor_socket_getpeersec_stream - get security context of peer + * @sock: socket that we are trying to get the peer context of + * @optval: output - buffer to copy peer name to + * @optlen: output - size of copied name in @optval + * @len: size of @optval buffer + * Returns: 0 on success, -errno of failure * * Note: for tcp only valid if using ipsec or cipso on lan */ @@ -2182,7 +2153,7 @@ __initcall(apparmor_nf_ip_init); static char nulldfa_src[] = { #include "nulldfa.in" }; -struct aa_dfa *nulldfa; +static struct aa_dfa *nulldfa; static char stacksplitdfa_src[] = { #include "stacksplitdfa.in" diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index ed4c9803c8fa..957654d253dd 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -99,13 +99,14 @@ const char *const aa_profile_mode_names[] = { }; -static void aa_free_pdb(struct aa_policydb *policy) +static void aa_free_pdb(struct aa_policydb *pdb) { - if (policy) { - aa_put_dfa(policy->dfa); - if (policy->perms) - kvfree(policy->perms); - aa_free_str_table(&policy->trans); + if (pdb) { + aa_put_dfa(pdb->dfa); + if (pdb->perms) + kvfree(pdb->perms); + aa_free_str_table(&pdb->trans); + kfree(pdb); } } diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 47ec097d6741..5e578ef0ddff 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -478,6 +478,8 @@ static bool unpack_trans_table(struct aa_ext *e, struct aa_str_table *strs) if (!table) goto fail; + strs->table = table; + strs->size = size; for (i = 0; i < size; i++) { char *str; int c, j, pos, size2 = aa_unpack_strdup(e, &str, NULL); @@ -520,14 +522,11 @@ static bool unpack_trans_table(struct aa_ext *e, struct aa_str_table *strs) goto fail; if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL)) goto fail; - - strs->table = table; - strs->size = size; } return true; fail: - kfree_sensitive(table); + aa_free_str_table(strs); e->pos = saved_pos; return false; } @@ -833,6 +832,10 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) tmpname = aa_splitn_fqname(name, strlen(name), &tmpns, &ns_len); if (tmpns) { + if (!tmpname) { + info = "empty profile name"; + goto fail; + } *ns_name = kstrndup(tmpns, ns_len, GFP_KERNEL); if (!*ns_name) { info = "out of memory"; @@ -1022,8 +1025,10 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) } } else if (rules->policy->dfa && rules->policy->start[AA_CLASS_FILE]) { + aa_put_pdb(rules->file); rules->file = aa_get_pdb(rules->policy); } else { + aa_put_pdb(rules->file); rules->file = aa_get_pdb(nullpdb); } error = -EPROTO; diff --git a/security/apparmor/task.c b/security/apparmor/task.c index f29a2e80e6bf..c87fb9f4ac18 100644 --- a/security/apparmor/task.c +++ b/security/apparmor/task.c @@ -278,7 +278,9 @@ static int profile_tracer_perm(const struct cred *cred, /** * aa_may_ptrace - test if tracer task can trace the tracee + * @tracer_cred: cred of task doing the tracing (NOT NULL) * @tracer: label of the task doing the tracing (NOT NULL) + * @tracee_cred: cred of task to be traced * @tracee: task label to be traced * @request: permission request * diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c index e87dc67f33c6..1c65e0a3b13c 100644 --- a/sound/drivers/aloop.c +++ b/sound/drivers/aloop.c @@ -322,6 +322,17 @@ static int loopback_snd_timer_close_cable(struct loopback_pcm *dpcm) return 0; } +static bool is_access_interleaved(snd_pcm_access_t access) +{ + switch (access) { + case SNDRV_PCM_ACCESS_MMAP_INTERLEAVED: + case SNDRV_PCM_ACCESS_RW_INTERLEAVED: + return true; + default: + return false; + } +}; + static int loopback_check_format(struct loopback_cable *cable, int stream) { struct snd_pcm_runtime *runtime, *cruntime; @@ -341,7 +352,8 @@ static int loopback_check_format(struct loopback_cable *cable, int stream) check = runtime->format != cruntime->format || runtime->rate != cruntime->rate || runtime->channels != cruntime->channels || - runtime->access != cruntime->access; + is_access_interleaved(runtime->access) != + is_access_interleaved(cruntime->access); if (!check) return 0; if (stream == SNDRV_PCM_STREAM_CAPTURE) { @@ -369,7 +381,8 @@ static int loopback_check_format(struct loopback_cable *cable, int stream) &setup->channels_id); setup->channels = runtime->channels; } - if (setup->access != runtime->access) { + if (is_access_interleaved(setup->access) != + is_access_interleaved(runtime->access)) { snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &setup->access_id); setup->access = runtime->access; @@ -584,8 +597,7 @@ static void copy_play_buf(struct loopback_pcm *play, size = play->pcm_buffer_size - src_off; if (dst_off + size > capt->pcm_buffer_size) size = capt->pcm_buffer_size - dst_off; - if (runtime->access == SNDRV_PCM_ACCESS_RW_NONINTERLEAVED || - runtime->access == SNDRV_PCM_ACCESS_MMAP_NONINTERLEAVED) + if (!is_access_interleaved(runtime->access)) copy_play_buf_part_n(play, capt, size, src_off, dst_off); else memcpy(dst + dst_off, src + src_off, size); @@ -1544,8 +1556,7 @@ static int loopback_access_get(struct snd_kcontrol *kcontrol, mutex_lock(&loopback->cable_lock); access = loopback->setup[kcontrol->id.subdevice][kcontrol->id.device].access; - ucontrol->value.enumerated.item[0] = access == SNDRV_PCM_ACCESS_RW_NONINTERLEAVED || - access == SNDRV_PCM_ACCESS_MMAP_NONINTERLEAVED; + ucontrol->value.enumerated.item[0] = !is_access_interleaved(access); mutex_unlock(&loopback->cable_lock); return 0; diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index bf685d01259d..de2a3d08c73c 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -3946,7 +3946,6 @@ static int create_mute_led_cdev(struct hda_codec *codec, cdev->max_brightness = 1; cdev->default_trigger = micmute ? "audio-micmute" : "audio-mute"; cdev->brightness_set_blocking = callback; - cdev->brightness = ledtrig_audio_get(idx); cdev->flags = LED_CORE_SUSPENDRESUME; err = led_classdev_register(&codec->core.dev, cdev); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 200779296a1b..495d63101186 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2301,6 +2301,7 @@ static int generic_hdmi_build_pcms(struct hda_codec *codec) codec_dbg(codec, "hdmi: pcm_num set to %d\n", pcm_num); for (idx = 0; idx < pcm_num; idx++) { + struct hdmi_spec_per_cvt *per_cvt; struct hda_pcm *info; struct hda_pcm_stream *pstr; @@ -2316,6 +2317,11 @@ static int generic_hdmi_build_pcms(struct hda_codec *codec) pstr = &info->stream[SNDRV_PCM_STREAM_PLAYBACK]; pstr->substreams = 1; pstr->ops = generic_ops; + + per_cvt = get_cvt(spec, 0); + pstr->channels_min = per_cvt->channels_min; + pstr->channels_max = per_cvt->channels_max; + /* pcm number is less than pcm_rec array size */ if (spec->pcm_used >= ARRAY_SIZE(spec->pcm_rec)) break; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index b68c94757051..f6f16622f9cc 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9861,6 +9861,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87f6, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP), SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP), + SND_PCI_QUIRK(0x103c, 0x87fe, "HP Laptop 15s-fq2xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8805, "HP ProBook 650 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x880d, "HP EliteBook 830 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8811, "HP Spectre x360 15-eb1xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1), @@ -9955,6 +9956,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c97, "HP ZBook", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), @@ -10231,6 +10233,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3176, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x31af, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340), + SND_PCI_QUIRK(0x17aa, 0x334b, "Lenovo ThinkCentre M70 Gen5", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x3801, "Lenovo Yoga9 14IAP7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x3802, "Lenovo Yoga DuetITL 2021", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3813, "Legion 7i 15IMHG05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS), diff --git a/sound/pci/oxygen/oxygen_mixer.c b/sound/pci/oxygen/oxygen_mixer.c index 46705ec77b48..eb3aca16359c 100644 --- a/sound/pci/oxygen/oxygen_mixer.c +++ b/sound/pci/oxygen/oxygen_mixer.c @@ -718,7 +718,7 @@ static int ac97_fp_rec_volume_put(struct snd_kcontrol *ctl, oldreg = oxygen_read_ac97(chip, 1, AC97_REC_GAIN); newreg = oldreg & ~0x0707; newreg = newreg | (value->value.integer.value[0] & 7); - newreg = newreg | ((value->value.integer.value[0] & 7) << 8); + newreg = newreg | ((value->value.integer.value[1] & 7) << 8); change = newreg != oldreg; if (change) oxygen_write_ac97(chip, 1, AC97_REC_GAIN, newreg); diff --git a/sound/soc/codecs/rtq9128.c b/sound/soc/codecs/rtq9128.c index c22b047115cc..aa3eadecd974 100644 --- a/sound/soc/codecs/rtq9128.c +++ b/sound/soc/codecs/rtq9128.c @@ -59,6 +59,7 @@ struct rtq9128_data { struct gpio_desc *enable; + unsigned int daifmt; int tdm_slots; int tdm_slot_width; bool tdm_input_data2_select; @@ -391,7 +392,11 @@ static int rtq9128_component_probe(struct snd_soc_component *comp) unsigned int val; int i, ret; - pm_runtime_resume_and_get(comp->dev); + ret = pm_runtime_resume_and_get(comp->dev); + if (ret < 0) { + dev_err(comp->dev, "Failed to resume device (%d)\n", ret); + return ret; + } val = snd_soc_component_read(comp, RTQ9128_REG_EFUSE_DATA); @@ -437,10 +442,7 @@ static const struct snd_soc_component_driver rtq9128_comp_driver = { static int rtq9128_dai_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) { struct rtq9128_data *data = snd_soc_dai_get_drvdata(dai); - struct snd_soc_component *comp = dai->component; struct device *dev = dai->dev; - unsigned int audfmt, fmtval; - int ret; dev_dbg(dev, "%s: fmt 0x%8x\n", __func__, fmt); @@ -450,35 +452,10 @@ static int rtq9128_dai_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) return -EINVAL; } - fmtval = fmt & SND_SOC_DAIFMT_FORMAT_MASK; - if (data->tdm_slots && fmtval != SND_SOC_DAIFMT_DSP_A && fmtval != SND_SOC_DAIFMT_DSP_B) { - dev_err(dev, "TDM is used, format only support DSP_A or DSP_B\n"); - return -EINVAL; - } + /* Store here and will be used in runtime hw_params for DAI format setting */ + data->daifmt = fmt; - switch (fmtval) { - case SND_SOC_DAIFMT_I2S: - audfmt = 8; - break; - case SND_SOC_DAIFMT_LEFT_J: - audfmt = 9; - break; - case SND_SOC_DAIFMT_RIGHT_J: - audfmt = 10; - break; - case SND_SOC_DAIFMT_DSP_A: - audfmt = data->tdm_slots ? 12 : 11; - break; - case SND_SOC_DAIFMT_DSP_B: - audfmt = data->tdm_slots ? 4 : 3; - break; - default: - dev_err(dev, "Unsupported format 0x%8x\n", fmt); - return -EINVAL; - } - - ret = snd_soc_component_write_field(comp, RTQ9128_REG_I2S_OPT, RTQ9128_AUDFMT_MASK, audfmt); - return ret < 0 ? ret : 0; + return 0; } static int rtq9128_dai_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask, @@ -554,10 +531,38 @@ static int rtq9128_dai_hw_params(struct snd_pcm_substream *stream, struct snd_pc unsigned int width, slot_width, bitrate, audbit, dolen; struct snd_soc_component *comp = dai->component; struct device *dev = dai->dev; + unsigned int fmtval, audfmt; int ret; dev_dbg(dev, "%s: width %d\n", __func__, params_width(param)); + fmtval = FIELD_GET(SND_SOC_DAIFMT_FORMAT_MASK, data->daifmt); + if (data->tdm_slots && fmtval != SND_SOC_DAIFMT_DSP_A && fmtval != SND_SOC_DAIFMT_DSP_B) { + dev_err(dev, "TDM is used, format only support DSP_A or DSP_B\n"); + return -EINVAL; + } + + switch (fmtval) { + case SND_SOC_DAIFMT_I2S: + audfmt = 8; + break; + case SND_SOC_DAIFMT_LEFT_J: + audfmt = 9; + break; + case SND_SOC_DAIFMT_RIGHT_J: + audfmt = 10; + break; + case SND_SOC_DAIFMT_DSP_A: + audfmt = data->tdm_slots ? 12 : 11; + break; + case SND_SOC_DAIFMT_DSP_B: + audfmt = data->tdm_slots ? 4 : 3; + break; + default: + dev_err(dev, "Unsupported format 0x%8x\n", fmtval); + return -EINVAL; + } + switch (width = params_width(param)) { case 16: audbit = 0; @@ -611,6 +616,10 @@ static int rtq9128_dai_hw_params(struct snd_pcm_substream *stream, struct snd_pc return -EINVAL; } + ret = snd_soc_component_write_field(comp, RTQ9128_REG_I2S_OPT, RTQ9128_AUDFMT_MASK, audfmt); + if (ret < 0) + return ret; + ret = snd_soc_component_write_field(comp, RTQ9128_REG_I2S_OPT, RTQ9128_AUDBIT_MASK, audbit); if (ret < 0) return ret; diff --git a/sound/soc/codecs/tas2562.c b/sound/soc/codecs/tas2562.c index 962c2cdfa017..54561ae598b8 100644 --- a/sound/soc/codecs/tas2562.c +++ b/sound/soc/codecs/tas2562.c @@ -59,7 +59,6 @@ struct tas2562_data { enum tas256x_model { TAS2562, - TAS2563, TAS2564, TAS2110, }; @@ -721,7 +720,6 @@ static int tas2562_parse_dt(struct tas2562_data *tas2562) static const struct i2c_device_id tas2562_id[] = { { "tas2562", TAS2562 }, - { "tas2563", TAS2563 }, { "tas2564", TAS2564 }, { "tas2110", TAS2110 }, { } @@ -770,7 +768,6 @@ static int tas2562_probe(struct i2c_client *client) #ifdef CONFIG_OF static const struct of_device_id tas2562_of_match[] = { { .compatible = "ti,tas2562", }, - { .compatible = "ti,tas2563", }, { .compatible = "ti,tas2564", }, { .compatible = "ti,tas2110", }, { }, diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index 917b1c15f71d..32913bd1a623 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -1,13 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 // -// ALSA SoC Texas Instruments TAS2781 Audio Smart Amplifier +// ALSA SoC Texas Instruments TAS2563/TAS2781 Audio Smart Amplifier // // Copyright (C) 2022 - 2023 Texas Instruments Incorporated // https://www.ti.com // -// The TAS2781 driver implements a flexible and configurable +// The TAS2563/TAS2781 driver implements a flexible and configurable // algo coefficient setting for one, two, or even multiple -// TAS2781 chips. +// TAS2563/TAS2781 chips. // // Author: Shenghao Ding <shenghao-ding@ti.com> // Author: Kevin Lu <kevin-lu@ti.com> @@ -32,6 +32,7 @@ #include <sound/tas2781-tlv.h> static const struct i2c_device_id tasdevice_id[] = { + { "tas2563", TAS2563 }, { "tas2781", TAS2781 }, {} }; @@ -39,6 +40,7 @@ MODULE_DEVICE_TABLE(i2c, tasdevice_id); #ifdef CONFIG_OF static const struct of_device_id tasdevice_of_match[] = { + { .compatible = "ti,tas2563" }, { .compatible = "ti,tas2781" }, {}, }; diff --git a/sound/soc/generic/audio-graph-card2.c b/sound/soc/generic/audio-graph-card2.c index 9c94677f681a..62606e20be9a 100644 --- a/sound/soc/generic/audio-graph-card2.c +++ b/sound/soc/generic/audio-graph-card2.c @@ -556,7 +556,7 @@ static int graph_parse_node_multi_nm(struct snd_soc_dai_link *dai_link, struct device_node *mcodec_port; int codec_idx; - if (*nm_idx >= nm_max) + if (*nm_idx > nm_max) break; mcpu_ep_n = of_get_next_child(mcpu_port, mcpu_ep_n); diff --git a/sound/soc/intel/boards/bxt_da7219_max98357a.c b/sound/soc/intel/boards/bxt_da7219_max98357a.c index 816fad8c1ff0..540f7a29310a 100644 --- a/sound/soc/intel/boards/bxt_da7219_max98357a.c +++ b/sound/soc/intel/boards/bxt_da7219_max98357a.c @@ -797,6 +797,9 @@ static int broxton_audio_probe(struct platform_device *pdev) broxton_audio_card.name = "glkda7219max"; /* Fixup the SSP entries for geminilake */ for (i = 0; i < ARRAY_SIZE(broxton_dais); i++) { + if (!broxton_dais[i].codecs->dai_name) + continue; + /* MAXIM_CODEC is connected to SSP1. */ if (!strcmp(broxton_dais[i].codecs->dai_name, BXT_MAXIM_CODEC_DAI)) { @@ -822,6 +825,9 @@ static int broxton_audio_probe(struct platform_device *pdev) broxton_audio_card.name = "cmlda7219max"; for (i = 0; i < ARRAY_SIZE(broxton_dais); i++) { + if (!broxton_dais[i].codecs->dai_name) + continue; + /* MAXIM_CODEC is connected to SSP1. */ if (!strcmp(broxton_dais[i].codecs->dai_name, BXT_MAXIM_CODEC_DAI)) { diff --git a/sound/soc/intel/boards/bxt_rt298.c b/sound/soc/intel/boards/bxt_rt298.c index 4631106f2a28..c0eb65c14aa9 100644 --- a/sound/soc/intel/boards/bxt_rt298.c +++ b/sound/soc/intel/boards/bxt_rt298.c @@ -604,7 +604,8 @@ static int broxton_audio_probe(struct platform_device *pdev) int i; for (i = 0; i < ARRAY_SIZE(broxton_rt298_dais); i++) { - if (!strncmp(card->dai_link[i].codecs->name, "i2c-INT343A:00", + if (card->dai_link[i].codecs->name && + !strncmp(card->dai_link[i].codecs->name, "i2c-INT343A:00", I2C_NAME_SIZE)) { if (!strncmp(card->name, "broxton-rt298", PLATFORM_NAME_SIZE)) { diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 9ecee43ad84d..300391fbc2fc 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -1256,11 +1256,11 @@ static int fill_sdw_codec_dlc(struct device *dev, else if (is_unique_device(adr_link, sdw_version, mfg_id, part_id, class_id, adr_index)) codec->name = devm_kasprintf(dev, GFP_KERNEL, - "sdw:%01x:%04x:%04x:%02x", link_id, + "sdw:0:%01x:%04x:%04x:%02x", link_id, mfg_id, part_id, class_id); else codec->name = devm_kasprintf(dev, GFP_KERNEL, - "sdw:%01x:%04x:%04x:%02x:%01x", link_id, + "sdw:0:%01x:%04x:%04x:%02x:%01x", link_id, mfg_id, part_id, class_id, unique_id); if (!codec->name) diff --git a/sound/soc/mediatek/common/mtk-dsp-sof-common.c b/sound/soc/mediatek/common/mtk-dsp-sof-common.c index f3894010f656..7ec8965a70c0 100644 --- a/sound/soc/mediatek/common/mtk-dsp-sof-common.c +++ b/sound/soc/mediatek/common/mtk-dsp-sof-common.c @@ -24,7 +24,7 @@ int mtk_sof_dai_link_fixup(struct snd_soc_pcm_runtime *rtd, struct snd_soc_dai_link *sof_dai_link = NULL; const struct sof_conn_stream *conn = &sof_priv->conn_streams[i]; - if (strcmp(rtd->dai_link->name, conn->normal_link)) + if (conn->normal_link && strcmp(rtd->dai_link->name, conn->normal_link)) continue; for_each_card_rtds(card, runtime) { diff --git a/sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c b/sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c index 5bd6addd1450..bfcb2c486c39 100644 --- a/sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c +++ b/sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c @@ -1208,7 +1208,8 @@ static int mt8192_mt6359_dev_probe(struct platform_device *pdev) dai_link->ignore = 0; } - if (strcmp(dai_link->codecs[0].dai_name, RT1015_CODEC_DAI) == 0) + if (dai_link->num_codecs && dai_link->codecs[0].dai_name && + strcmp(dai_link->codecs[0].dai_name, RT1015_CODEC_DAI) == 0) dai_link->ops = &mt8192_rt1015_i2s_ops; if (!dai_link->platforms->name) diff --git a/sound/soc/mediatek/mt8195/mt8195-afe-pcm.c b/sound/soc/mediatek/mt8195/mt8195-afe-pcm.c index 1e33863c85ca..620d7ade1992 100644 --- a/sound/soc/mediatek/mt8195/mt8195-afe-pcm.c +++ b/sound/soc/mediatek/mt8195/mt8195-afe-pcm.c @@ -1795,10 +1795,6 @@ static const struct snd_kcontrol_new mt8195_memif_controls[] = { MT8195_AFE_IRQ_28), }; -static const struct snd_soc_component_driver mt8195_afe_pcm_dai_component = { - .name = "mt8195-afe-pcm-dai", -}; - static const struct mtk_base_memif_data memif_data[MT8195_AFE_MEMIF_NUM] = { [MT8195_AFE_MEMIF_DL2] = { .name = "DL2", @@ -3037,7 +3033,6 @@ static int mt8195_afe_pcm_dev_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct reset_control *rstc; int i, irq_id, ret; - struct snd_soc_component *component; ret = of_reserved_mem_device_init(dev); if (ret) @@ -3170,36 +3165,12 @@ static int mt8195_afe_pcm_dev_probe(struct platform_device *pdev) /* register component */ ret = devm_snd_soc_register_component(dev, &mt8195_afe_component, - NULL, 0); + afe->dai_drivers, afe->num_dai_drivers); if (ret) { dev_warn(dev, "err_platform\n"); goto err_pm_put; } - component = devm_kzalloc(dev, sizeof(*component), GFP_KERNEL); - if (!component) { - ret = -ENOMEM; - goto err_pm_put; - } - - ret = snd_soc_component_initialize(component, - &mt8195_afe_pcm_dai_component, - dev); - if (ret) - goto err_pm_put; - -#ifdef CONFIG_DEBUG_FS - component->debugfs_prefix = "pcm"; -#endif - - ret = snd_soc_add_component(component, - afe->dai_drivers, - afe->num_dai_drivers); - if (ret) { - dev_warn(dev, "err_dai_component\n"); - goto err_pm_put; - } - ret = regmap_multi_reg_write(afe->regmap, mt8195_afe_reg_defaults, ARRAY_SIZE(mt8195_afe_reg_defaults)); if (ret) @@ -3224,8 +3195,6 @@ err_pm_put: static void mt8195_afe_pcm_dev_remove(struct platform_device *pdev) { - snd_soc_unregister_component(&pdev->dev); - pm_runtime_disable(&pdev->dev); if (!pm_runtime_status_suspended(&pdev->dev)) mt8195_afe_runtime_suspend(&pdev->dev); diff --git a/sound/soc/mediatek/mt8195/mt8195-mt6359.c b/sound/soc/mediatek/mt8195/mt8195-mt6359.c index 4feb9fb76967..53fd8a897b9d 100644 --- a/sound/soc/mediatek/mt8195/mt8195-mt6359.c +++ b/sound/soc/mediatek/mt8195/mt8195-mt6359.c @@ -934,12 +934,11 @@ SND_SOC_DAILINK_DEFS(ETDM1_IN_BE, SND_SOC_DAILINK_DEFS(ETDM2_IN_BE, DAILINK_COMP_ARRAY(COMP_CPU("ETDM2_IN")), - DAILINK_COMP_ARRAY(COMP_DUMMY()), + DAILINK_COMP_ARRAY(COMP_EMPTY()), DAILINK_COMP_ARRAY(COMP_EMPTY())); SND_SOC_DAILINK_DEFS(ETDM1_OUT_BE, DAILINK_COMP_ARRAY(COMP_CPU("ETDM1_OUT")), - DAILINK_COMP_ARRAY(COMP_DUMMY()), DAILINK_COMP_ARRAY(COMP_EMPTY())); SND_SOC_DAILINK_DEFS(ETDM2_OUT_BE, @@ -1237,8 +1236,6 @@ static struct snd_soc_dai_link mt8195_mt6359_dai_links[] = { SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBS_CFS, .dpcm_capture = 1, - .init = mt8195_rt5682_init, - .ops = &mt8195_rt5682_etdm_ops, .be_hw_params_fixup = mt8195_etdm_hw_params_fixup, SND_SOC_DAILINK_REG(ETDM2_IN_BE), }, @@ -1249,7 +1246,6 @@ static struct snd_soc_dai_link mt8195_mt6359_dai_links[] = { SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBS_CFS, .dpcm_playback = 1, - .ops = &mt8195_rt5682_etdm_ops, .be_hw_params_fixup = mt8195_etdm_hw_params_fixup, SND_SOC_DAILINK_REG(ETDM1_OUT_BE), }, @@ -1381,7 +1377,7 @@ static int mt8195_mt6359_dev_probe(struct platform_device *pdev) struct snd_soc_dai_link *dai_link; struct mtk_soc_card_data *soc_card_data; struct mt8195_mt6359_priv *mach_priv; - struct device_node *platform_node, *adsp_node, *dp_node, *hdmi_node; + struct device_node *platform_node, *adsp_node, *codec_node, *dp_node, *hdmi_node; struct mt8195_card_data *card_data; int is5682s = 0; int init6359 = 0; @@ -1401,8 +1397,12 @@ static int mt8195_mt6359_dev_probe(struct platform_device *pdev) if (!card->name) card->name = card_data->name; - if (strstr(card->name, "_5682s")) + if (strstr(card->name, "_5682s")) { + codec_node = of_find_compatible_node(NULL, NULL, "realtek,rt5682s"); is5682s = 1; + } else + codec_node = of_find_compatible_node(NULL, NULL, "realtek,rt5682i"); + soc_card_data = devm_kzalloc(&pdev->dev, sizeof(*card_data), GFP_KERNEL); if (!soc_card_data) return -ENOMEM; @@ -1488,12 +1488,27 @@ static int mt8195_mt6359_dev_probe(struct platform_device *pdev) dai_link->codecs->dai_name = "i2s-hifi"; dai_link->init = mt8195_hdmi_codec_init; } - } else if (strcmp(dai_link->name, "ETDM1_OUT_BE") == 0 || - strcmp(dai_link->name, "ETDM2_IN_BE") == 0) { - dai_link->codecs->name = - is5682s ? RT5682S_DEV0_NAME : RT5682_DEV0_NAME; - dai_link->codecs->dai_name = - is5682s ? RT5682S_CODEC_DAI : RT5682_CODEC_DAI; + } else if (strcmp(dai_link->name, "ETDM1_OUT_BE") == 0) { + if (!codec_node) { + dev_err(&pdev->dev, "Codec not found!\n"); + } else { + dai_link->codecs->of_node = codec_node; + dai_link->codecs->name = NULL; + dai_link->codecs->dai_name = + is5682s ? RT5682S_CODEC_DAI : RT5682_CODEC_DAI; + dai_link->init = mt8195_rt5682_init; + dai_link->ops = &mt8195_rt5682_etdm_ops; + } + } else if (strcmp(dai_link->name, "ETDM2_IN_BE") == 0) { + if (!codec_node) { + dev_err(&pdev->dev, "Codec not found!\n"); + } else { + dai_link->codecs->of_node = codec_node; + dai_link->codecs->name = NULL; + dai_link->codecs->dai_name = + is5682s ? RT5682S_CODEC_DAI : RT5682_CODEC_DAI; + dai_link->ops = &mt8195_rt5682_etdm_ops; + } } else if (strcmp(dai_link->name, "DL_SRC_BE") == 0 || strcmp(dai_link->name, "UL_SRC1_BE") == 0 || strcmp(dai_link->name, "UL_SRC2_BE") == 0) { diff --git a/sound/soc/rockchip/rk3399_gru_sound.c b/sound/soc/rockchip/rk3399_gru_sound.c index 1a504ebd3a0e..6c89c7331229 100644 --- a/sound/soc/rockchip/rk3399_gru_sound.c +++ b/sound/soc/rockchip/rk3399_gru_sound.c @@ -446,7 +446,7 @@ static const struct rockchip_sound_route rockchip_routes[] = { struct dailink_match_data { const char *compatible; - struct bus_type *bus_type; + const struct bus_type *bus_type; }; static const struct dailink_match_data dailink_match[] = { diff --git a/sound/soc/sof/ipc3-dtrace.c b/sound/soc/sof/ipc3-dtrace.c index 93b189c2d2ee..0dca139322f3 100644 --- a/sound/soc/sof/ipc3-dtrace.c +++ b/sound/soc/sof/ipc3-dtrace.c @@ -137,7 +137,6 @@ static int trace_filter_parse(struct snd_sof_dev *sdev, char *string, dev_err(sdev->dev, "Parsing filter entry '%s' failed with %d\n", entry, entry_len); - kfree(*out); return -EINVAL; } } @@ -209,13 +208,13 @@ static ssize_t dfsentry_trace_filter_write(struct file *file, const char __user ret = ipc3_trace_update_filter(sdev, num_elems, elems); if (ret < 0) { dev_err(sdev->dev, "Filter update failed: %d\n", ret); - kfree(elems); goto error; } } ret = count; error: kfree(string); + kfree(elems); return ret; } diff --git a/sound/soc/sof/ipc4-loader.c b/sound/soc/sof/ipc4-loader.c index 3539b0a66e1b..c79479afa8d0 100644 --- a/sound/soc/sof/ipc4-loader.c +++ b/sound/soc/sof/ipc4-loader.c @@ -482,13 +482,10 @@ void sof_ipc4_update_cpc_from_manifest(struct snd_sof_dev *sdev, msg = "No CPC match in the firmware file's manifest"; no_cpc: - dev_warn(sdev->dev, "%s (UUID: %pUL): %s (ibs/obs: %u/%u)\n", - fw_module->man4_module_entry.name, - &fw_module->man4_module_entry.uuid, msg, basecfg->ibs, - basecfg->obs); - dev_warn_once(sdev->dev, "Please try to update the firmware.\n"); - dev_warn_once(sdev->dev, "If the issue persists, file a bug at\n"); - dev_warn_once(sdev->dev, "https://github.com/thesofproject/sof/issues/\n"); + dev_dbg(sdev->dev, "%s (UUID: %pUL): %s (ibs/obs: %u/%u)\n", + fw_module->man4_module_entry.name, + &fw_module->man4_module_entry.uuid, msg, basecfg->ibs, + basecfg->obs); } const struct sof_ipc_fw_loader_ops ipc4_loader_ops = { diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c index 39039a647cca..85d3f390e4b2 100644 --- a/sound/soc/sof/ipc4-pcm.c +++ b/sound/soc/sof/ipc4-pcm.c @@ -768,10 +768,8 @@ static void sof_ipc4_build_time_info(struct snd_sof_dev *sdev, struct snd_sof_pc info->llp_offset = offsetof(struct sof_ipc4_fw_registers, llp_evad_reading_slot) + sdev->fw_info_box.offset; sof_mailbox_read(sdev, info->llp_offset, &llp_slot, sizeof(llp_slot)); - if (llp_slot.node_id != dai_copier->data.gtw_cfg.node_id) { - dev_info(sdev->dev, "no llp found, fall back to default HDA path"); + if (llp_slot.node_id != dai_copier->data.gtw_cfg.node_id) info->llp_offset = 0; - } } static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component, diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c index 1de3ddc50eb6..6de605a601e5 100644 --- a/sound/usb/mixer_scarlett2.c +++ b/sound/usb/mixer_scarlett2.c @@ -5361,9 +5361,9 @@ static int scarlett2_add_line_out_ctls(struct usb_mixer_interface *mixer) if (private->vol_sw_hw_switch[index]) scarlett2_vol_ctl_set_writable(mixer, i, 0); - snprintf(s, sizeof(s), - "Line Out %02d Volume Control Playback Enum", - i + 1); + scnprintf(s, sizeof(s), + "Line Out %02d Volume Control Playback Enum", + i + 1); err = scarlett2_add_new_ctl(mixer, &scarlett2_sw_hw_enum_ctl, i, 1, s, @@ -5406,8 +5406,8 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer) /* Add input level (line/inst) controls */ for (i = 0; i < info->level_input_count; i++) { - snprintf(s, sizeof(s), fmt, i + 1 + info->level_input_first, - "Level", "Enum"); + scnprintf(s, sizeof(s), fmt, i + 1 + info->level_input_first, + "Level", "Enum"); err = scarlett2_add_new_ctl(mixer, &scarlett2_level_enum_ctl, i, 1, s, &private->level_ctls[i]); if (err < 0) @@ -5416,7 +5416,7 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer) /* Add input pad controls */ for (i = 0; i < info->pad_input_count; i++) { - snprintf(s, sizeof(s), fmt, i + 1, "Pad", "Switch"); + scnprintf(s, sizeof(s), fmt, i + 1, "Pad", "Switch"); err = scarlett2_add_new_ctl(mixer, &scarlett2_pad_ctl, i, 1, s, &private->pad_ctls[i]); if (err < 0) @@ -5425,8 +5425,8 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer) /* Add input air controls */ for (i = 0; i < info->air_input_count; i++) { - snprintf(s, sizeof(s), fmt, i + 1 + info->air_input_first, - "Air", info->air_option ? "Enum" : "Switch"); + scnprintf(s, sizeof(s), fmt, i + 1 + info->air_input_first, + "Air", info->air_option ? "Enum" : "Switch"); err = scarlett2_add_new_ctl( mixer, &scarlett2_air_ctl[info->air_option], i, 1, s, &private->air_ctls[i]); @@ -5481,9 +5481,9 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer) for (i = 0; i < info->gain_input_count; i++) { if (i % 2) { - snprintf(s, sizeof(s), - "Line In %d-%d Link Capture Switch", - i, i + 1); + scnprintf(s, sizeof(s), + "Line In %d-%d Link Capture Switch", + i, i + 1); err = scarlett2_add_new_ctl( mixer, &scarlett2_input_link_ctl, i / 2, 1, s, @@ -5492,30 +5492,30 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer) return err; } - snprintf(s, sizeof(s), fmt, i + 1, - "Gain", "Volume"); + scnprintf(s, sizeof(s), fmt, i + 1, + "Gain", "Volume"); err = scarlett2_add_new_ctl( mixer, &scarlett2_input_gain_ctl, i, 1, s, &private->input_gain_ctls[i]); if (err < 0) return err; - snprintf(s, sizeof(s), fmt, i + 1, - "Autogain", "Switch"); + scnprintf(s, sizeof(s), fmt, i + 1, + "Autogain", "Switch"); err = scarlett2_add_new_ctl( mixer, &scarlett2_autogain_switch_ctl, i, 1, s, &private->autogain_ctls[i]); if (err < 0) return err; - snprintf(s, sizeof(s), fmt, i + 1, - "Autogain Status", "Enum"); + scnprintf(s, sizeof(s), fmt, i + 1, + "Autogain Status", "Enum"); err = scarlett2_add_new_ctl( mixer, &scarlett2_autogain_status_ctl, i, 1, s, &private->autogain_status_ctls[i]); - snprintf(s, sizeof(s), fmt, i + 1, - "Safe", "Switch"); + scnprintf(s, sizeof(s), fmt, i + 1, + "Safe", "Switch"); err = scarlett2_add_new_ctl( mixer, &scarlett2_safe_ctl, i, 1, s, &private->safe_ctls[i]); @@ -5902,8 +5902,8 @@ static int scarlett2_add_direct_monitor_ctls(struct usb_mixer_interface *mixer) for (k = 0; k < private->num_mix_in; k++, index++) { char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; - snprintf(name, sizeof(name), format, - mix_type, 'A' + j, k + 1); + scnprintf(name, sizeof(name), format, + mix_type, 'A' + j, k + 1); err = scarlett2_add_new_ctl( mixer, &scarlett2_monitor_mix_ctl, diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index c5a42ac309fd..afd09571c482 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -6695,6 +6695,67 @@ static struct { /* all other program types don't have "named" context structs */ }; +static bool need_func_arg_type_fixup(const struct btf *btf, const struct bpf_program *prog, + const char *subprog_name, int arg_idx, + int arg_type_id, const char *ctx_name) +{ + const struct btf_type *t; + const char *tname; + + /* check if existing parameter already matches verifier expectations */ + t = skip_mods_and_typedefs(btf, arg_type_id, NULL); + if (!btf_is_ptr(t)) + goto out_warn; + + /* typedef bpf_user_pt_regs_t is a special PITA case, valid for kprobe + * and perf_event programs, so check this case early on and forget + * about it for subsequent checks + */ + while (btf_is_mod(t)) + t = btf__type_by_id(btf, t->type); + if (btf_is_typedef(t) && + (prog->type == BPF_PROG_TYPE_KPROBE || prog->type == BPF_PROG_TYPE_PERF_EVENT)) { + tname = btf__str_by_offset(btf, t->name_off) ?: "<anon>"; + if (strcmp(tname, "bpf_user_pt_regs_t") == 0) + return false; /* canonical type for kprobe/perf_event */ + } + + /* now we can ignore typedefs moving forward */ + t = skip_mods_and_typedefs(btf, t->type, NULL); + + /* if it's `void *`, definitely fix up BTF info */ + if (btf_is_void(t)) + return true; + + /* if it's already proper canonical type, no need to fix up */ + tname = btf__str_by_offset(btf, t->name_off) ?: "<anon>"; + if (btf_is_struct(t) && strcmp(tname, ctx_name) == 0) + return false; + + /* special cases */ + switch (prog->type) { + case BPF_PROG_TYPE_KPROBE: + case BPF_PROG_TYPE_PERF_EVENT: + /* `struct pt_regs *` is expected, but we need to fix up */ + if (btf_is_struct(t) && strcmp(tname, "pt_regs") == 0) + return true; + break; + case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return true; + break; + default: + break; + } + +out_warn: + pr_warn("prog '%s': subprog '%s' arg#%d is expected to be of `struct %s *` type\n", + prog->name, subprog_name, arg_idx, ctx_name); + return false; +} + static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_program *prog) { int fn_id, fn_proto_id, ret_type_id, orig_proto_id; @@ -6757,6 +6818,69 @@ static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_progr return fn_id; } +static int probe_kern_arg_ctx_tag(void) +{ + /* To minimize merge conflicts with BPF token series that refactors + * feature detection code a lot, we don't integrate + * probe_kern_arg_ctx_tag() into kernel_supports() feature-detection + * framework yet, doing our own caching internally. + * This will be cleaned up a bit later when bpf/bpf-next trees settle. + */ + static int cached_result = -1; + static const char strs[] = "\0a\0b\0arg:ctx\0"; + const __u32 types[] = { + /* [1] INT */ + BTF_TYPE_INT_ENC(1 /* "a" */, BTF_INT_SIGNED, 0, 32, 4), + /* [2] PTR -> VOID */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0), + /* [3] FUNC_PROTO `int(void *a)` */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1), + BTF_PARAM_ENC(1 /* "a" */, 2), + /* [4] FUNC 'a' -> FUNC_PROTO (main prog) */ + BTF_TYPE_ENC(1 /* "a" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 3), + /* [5] FUNC_PROTO `int(void *b __arg_ctx)` */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1), + BTF_PARAM_ENC(3 /* "b" */, 2), + /* [6] FUNC 'b' -> FUNC_PROTO (subprog) */ + BTF_TYPE_ENC(3 /* "b" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 5), + /* [7] DECL_TAG 'arg:ctx' -> func 'b' arg 'b' */ + BTF_TYPE_DECL_TAG_ENC(5 /* "arg:ctx" */, 6, 0), + }; + const struct bpf_insn insns[] = { + /* main prog */ + BPF_CALL_REL(+1), + BPF_EXIT_INSN(), + /* global subprog */ + BPF_EMIT_CALL(BPF_FUNC_get_func_ip), /* needs PTR_TO_CTX */ + BPF_EXIT_INSN(), + }; + const struct bpf_func_info_min func_infos[] = { + { 0, 4 }, /* main prog -> FUNC 'a' */ + { 2, 6 }, /* subprog -> FUNC 'b' */ + }; + LIBBPF_OPTS(bpf_prog_load_opts, opts); + int prog_fd, btf_fd, insn_cnt = ARRAY_SIZE(insns); + + if (cached_result >= 0) + return cached_result; + + btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs)); + if (btf_fd < 0) + return 0; + + opts.prog_btf_fd = btf_fd; + opts.func_info = &func_infos; + opts.func_info_cnt = ARRAY_SIZE(func_infos); + opts.func_info_rec_size = sizeof(func_infos[0]); + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, "det_arg_ctx", + "GPL", insns, insn_cnt, &opts); + close(btf_fd); + + cached_result = probe_fd(prog_fd); + return cached_result; +} + /* Check if main program or global subprog's function prototype has `arg:ctx` * argument tags, and, if necessary, substitute correct type to match what BPF * verifier would expect, taking into account specific program type. This @@ -6766,7 +6890,7 @@ static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_progr */ static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_program *prog) { - const char *ctx_name = NULL, *ctx_tag = "arg:ctx"; + const char *ctx_name = NULL, *ctx_tag = "arg:ctx", *fn_name; struct bpf_func_info_min *func_rec; struct btf_type *fn_t, *fn_proto_t; struct btf *btf = obj->btf; @@ -6780,6 +6904,10 @@ static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_progra if (!obj->btf_ext || !prog->func_info) return 0; + /* don't do any fix ups if kernel natively supports __arg_ctx */ + if (probe_kern_arg_ctx_tag() > 0) + return 0; + /* some BPF program types just don't have named context structs, so * this fallback mechanism doesn't work for them */ @@ -6842,15 +6970,11 @@ static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_progra if (arg_idx < 0 || arg_idx >= arg_cnt) continue; - /* check if existing parameter already matches verifier expectations */ + /* check if we should fix up argument type */ p = &btf_params(fn_proto_t)[arg_idx]; - t = skip_mods_and_typedefs(btf, p->type, NULL); - if (btf_is_ptr(t) && - (t = skip_mods_and_typedefs(btf, t->type, NULL)) && - btf_is_struct(t) && - strcmp(btf__str_by_offset(btf, t->name_off), ctx_name) == 0) { - continue; /* no need for fix up */ - } + fn_name = btf__str_by_offset(btf, fn_t->name_off) ?: "<anon>"; + if (!need_func_arg_type_fixup(btf, prog, fn_name, arg_idx, p->type, ctx_name)) + continue; /* clone fn/fn_proto, unless we already did it for another arg */ if (func_rec->type_id == orig_fn_id) { diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index 95dc58b94178..0b12c36902d8 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -58,6 +58,7 @@ cxl_core-y += $(CXL_CORE_SRC)/mbox.o cxl_core-y += $(CXL_CORE_SRC)/pci.o cxl_core-y += $(CXL_CORE_SRC)/hdm.o cxl_core-y += $(CXL_CORE_SRC)/pmu.o +cxl_core-y += $(CXL_CORE_SRC)/cdat.o cxl_core-$(CONFIG_TRACING) += $(CXL_CORE_SRC)/trace.o cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o cxl_core-y += config_check.o diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index f4e517a0c774..a3cdbb2be038 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -68,15 +68,19 @@ static struct acpi_device acpi0017_mock; static struct acpi_device host_bridge[NR_BRIDGES] = { [0] = { .handle = &host_bridge[0], + .pnp.unique_id = "0", }, [1] = { .handle = &host_bridge[1], + .pnp.unique_id = "1", }, [2] = { .handle = &host_bridge[2], + .pnp.unique_id = "2", }, [3] = { .handle = &host_bridge[3], + .pnp.unique_id = "3", }, }; diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index ee61fa3a2411..35ee41e435ab 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -251,7 +251,8 @@ static int mock_get_event(struct device *dev, struct cxl_mbox_cmd *cmd) for (i = 0; i < CXL_TEST_EVENT_CNT && !event_log_empty(log); i++) { memcpy(&pl->records[i], event_get_current(log), sizeof(pl->records[i])); - pl->records[i].hdr.handle = event_get_cur_event_handle(log); + pl->records[i].event.generic.hdr.handle = + event_get_cur_event_handle(log); log->cur_idx++; } @@ -337,87 +338,109 @@ static void cxl_mock_event_trigger(struct device *dev) } struct cxl_event_record_raw maint_needed = { - .hdr = { - .id = UUID_INIT(0xBA5EBA11, 0xABCD, 0xEFEB, - 0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5), - .length = sizeof(struct cxl_event_record_raw), - .flags[0] = CXL_EVENT_RECORD_FLAG_MAINT_NEEDED, - /* .handle = Set dynamically */ - .related_handle = cpu_to_le16(0xa5b6), + .id = UUID_INIT(0xBA5EBA11, 0xABCD, 0xEFEB, + 0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5), + .event.generic = { + .hdr = { + .length = sizeof(struct cxl_event_record_raw), + .flags[0] = CXL_EVENT_RECORD_FLAG_MAINT_NEEDED, + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0xa5b6), + }, + .data = { 0xDE, 0xAD, 0xBE, 0xEF }, }, - .data = { 0xDE, 0xAD, 0xBE, 0xEF }, }; struct cxl_event_record_raw hardware_replace = { - .hdr = { - .id = UUID_INIT(0xABCDEFEB, 0xBA11, 0xBA5E, - 0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5), - .length = sizeof(struct cxl_event_record_raw), - .flags[0] = CXL_EVENT_RECORD_FLAG_HW_REPLACE, - /* .handle = Set dynamically */ - .related_handle = cpu_to_le16(0xb6a5), + .id = UUID_INIT(0xABCDEFEB, 0xBA11, 0xBA5E, + 0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5), + .event.generic = { + .hdr = { + .length = sizeof(struct cxl_event_record_raw), + .flags[0] = CXL_EVENT_RECORD_FLAG_HW_REPLACE, + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0xb6a5), + }, + .data = { 0xDE, 0xAD, 0xBE, 0xEF }, }, - .data = { 0xDE, 0xAD, 0xBE, 0xEF }, }; -struct cxl_event_gen_media gen_media = { - .hdr = { - .id = UUID_INIT(0xfbcd0a77, 0xc260, 0x417f, - 0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6), - .length = sizeof(struct cxl_event_gen_media), - .flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT, - /* .handle = Set dynamically */ - .related_handle = cpu_to_le16(0), +struct cxl_test_gen_media { + uuid_t id; + struct cxl_event_gen_media rec; +} __packed; + +struct cxl_test_gen_media gen_media = { + .id = CXL_EVENT_GEN_MEDIA_UUID, + .rec = { + .hdr = { + .length = sizeof(struct cxl_test_gen_media), + .flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT, + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0), + }, + .phys_addr = cpu_to_le64(0x2000), + .descriptor = CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT, + .type = CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR, + .transaction_type = CXL_GMER_TRANS_HOST_WRITE, + /* .validity_flags = <set below> */ + .channel = 1, + .rank = 30 }, - .phys_addr = cpu_to_le64(0x2000), - .descriptor = CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT, - .type = CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR, - .transaction_type = CXL_GMER_TRANS_HOST_WRITE, - /* .validity_flags = <set below> */ - .channel = 1, - .rank = 30 }; -struct cxl_event_dram dram = { - .hdr = { - .id = UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, - 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24), - .length = sizeof(struct cxl_event_dram), - .flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED, - /* .handle = Set dynamically */ - .related_handle = cpu_to_le16(0), +struct cxl_test_dram { + uuid_t id; + struct cxl_event_dram rec; +} __packed; + +struct cxl_test_dram dram = { + .id = CXL_EVENT_DRAM_UUID, + .rec = { + .hdr = { + .length = sizeof(struct cxl_test_dram), + .flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED, + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0), + }, + .phys_addr = cpu_to_le64(0x8000), + .descriptor = CXL_GMER_EVT_DESC_THRESHOLD_EVENT, + .type = CXL_GMER_MEM_EVT_TYPE_INV_ADDR, + .transaction_type = CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB, + /* .validity_flags = <set below> */ + .channel = 1, + .bank_group = 5, + .bank = 2, + .column = {0xDE, 0xAD}, }, - .phys_addr = cpu_to_le64(0x8000), - .descriptor = CXL_GMER_EVT_DESC_THRESHOLD_EVENT, - .type = CXL_GMER_MEM_EVT_TYPE_INV_ADDR, - .transaction_type = CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB, - /* .validity_flags = <set below> */ - .channel = 1, - .bank_group = 5, - .bank = 2, - .column = {0xDE, 0xAD}, }; -struct cxl_event_mem_module mem_module = { - .hdr = { - .id = UUID_INIT(0xfe927475, 0xdd59, 0x4339, - 0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74), - .length = sizeof(struct cxl_event_mem_module), - /* .handle = Set dynamically */ - .related_handle = cpu_to_le16(0), +struct cxl_test_mem_module { + uuid_t id; + struct cxl_event_mem_module rec; +} __packed; + +struct cxl_test_mem_module mem_module = { + .id = CXL_EVENT_MEM_MODULE_UUID, + .rec = { + .hdr = { + .length = sizeof(struct cxl_test_mem_module), + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0), + }, + .event_type = CXL_MMER_TEMP_CHANGE, + .info = { + .health_status = CXL_DHI_HS_PERFORMANCE_DEGRADED, + .media_status = CXL_DHI_MS_ALL_DATA_LOST, + .add_status = (CXL_DHI_AS_CRITICAL << 2) | + (CXL_DHI_AS_WARNING << 4) | + (CXL_DHI_AS_WARNING << 5), + .device_temp = { 0xDE, 0xAD}, + .dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef }, + .cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef }, + .cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef }, + } }, - .event_type = CXL_MMER_TEMP_CHANGE, - .info = { - .health_status = CXL_DHI_HS_PERFORMANCE_DEGRADED, - .media_status = CXL_DHI_MS_ALL_DATA_LOST, - .add_status = (CXL_DHI_AS_CRITICAL << 2) | - (CXL_DHI_AS_WARNING << 4) | - (CXL_DHI_AS_WARNING << 5), - .device_temp = { 0xDE, 0xAD}, - .dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef }, - .cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef }, - .cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef }, - } }; static int mock_set_timestamp(struct cxl_dev_state *cxlds, @@ -439,11 +462,11 @@ static int mock_set_timestamp(struct cxl_dev_state *cxlds, static void cxl_mock_add_event_logs(struct mock_event_store *mes) { put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK, - &gen_media.validity_flags); + &gen_media.rec.validity_flags); put_unaligned_le16(CXL_DER_VALID_CHANNEL | CXL_DER_VALID_BANK_GROUP | CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN, - &dram.validity_flags); + &dram.rec.validity_flags); mes_add_event(mes, CXL_EVENT_TYPE_INFO, &maint_needed); mes_add_event(mes, CXL_EVENT_TYPE_INFO, diff --git a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c new file mode 100644 index 000000000000..0c365f36c73b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2024 Meta + +#include <test_progs.h> +#include "network_helpers.h" +#include "sock_iter_batch.skel.h" + +#define TEST_NS "sock_iter_batch_netns" + +static const int nr_soreuse = 4; + +static void do_test(int sock_type, bool onebyone) +{ + int err, i, nread, to_read, total_read, iter_fd = -1; + int first_idx, second_idx, indices[nr_soreuse]; + struct bpf_link *link = NULL; + struct sock_iter_batch *skel; + int *fds[2] = {}; + + skel = sock_iter_batch__open(); + if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open")) + return; + + /* Prepare 2 buckets of sockets in the kernel hashtable */ + for (i = 0; i < ARRAY_SIZE(fds); i++) { + int local_port; + + fds[i] = start_reuseport_server(AF_INET6, sock_type, "::1", 0, 0, + nr_soreuse); + if (!ASSERT_OK_PTR(fds[i], "start_reuseport_server")) + goto done; + local_port = get_socket_local_port(*fds[i]); + if (!ASSERT_GE(local_port, 0, "get_socket_local_port")) + goto done; + skel->rodata->ports[i] = ntohs(local_port); + } + + err = sock_iter_batch__load(skel); + if (!ASSERT_OK(err, "sock_iter_batch__load")) + goto done; + + link = bpf_program__attach_iter(sock_type == SOCK_STREAM ? + skel->progs.iter_tcp_soreuse : + skel->progs.iter_udp_soreuse, + NULL); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter")) + goto done; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (!ASSERT_GE(iter_fd, 0, "bpf_iter_create")) + goto done; + + /* Test reading a bucket (either from fds[0] or fds[1]). + * Only read "nr_soreuse - 1" number of sockets + * from a bucket and leave one socket out from + * that bucket on purpose. + */ + to_read = (nr_soreuse - 1) * sizeof(*indices); + total_read = 0; + first_idx = -1; + do { + nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read); + if (nread <= 0 || nread % sizeof(*indices)) + break; + total_read += nread; + + if (first_idx == -1) + first_idx = indices[0]; + for (i = 0; i < nread / sizeof(*indices); i++) + ASSERT_EQ(indices[i], first_idx, "first_idx"); + } while (total_read < to_read); + ASSERT_EQ(nread, onebyone ? sizeof(*indices) : to_read, "nread"); + ASSERT_EQ(total_read, to_read, "total_read"); + + free_fds(fds[first_idx], nr_soreuse); + fds[first_idx] = NULL; + + /* Read the "whole" second bucket */ + to_read = nr_soreuse * sizeof(*indices); + total_read = 0; + second_idx = !first_idx; + do { + nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read); + if (nread <= 0 || nread % sizeof(*indices)) + break; + total_read += nread; + + for (i = 0; i < nread / sizeof(*indices); i++) + ASSERT_EQ(indices[i], second_idx, "second_idx"); + } while (total_read <= to_read); + ASSERT_EQ(nread, 0, "nread"); + /* Both so_reuseport ports should be in different buckets, so + * total_read must equal to the expected to_read. + * + * For a very unlikely case, both ports collide at the same bucket, + * the bucket offset (i.e. 3) will be skipped and it cannot + * expect the to_read number of bytes. + */ + if (skel->bss->bucket[0] != skel->bss->bucket[1]) + ASSERT_EQ(total_read, to_read, "total_read"); + +done: + for (i = 0; i < ARRAY_SIZE(fds); i++) + free_fds(fds[i], nr_soreuse); + if (iter_fd < 0) + close(iter_fd); + bpf_link__destroy(link); + sock_iter_batch__destroy(skel); +} + +void test_sock_iter_batch(void) +{ + struct nstoken *nstoken = NULL; + + SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null"); + SYS(done, "ip netns add %s", TEST_NS); + SYS(done, "ip -net %s link set dev lo up", TEST_NS); + + nstoken = open_netns(TEST_NS); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto done; + + if (test__start_subtest("tcp")) { + do_test(SOCK_STREAM, true); + do_test(SOCK_STREAM, false); + } + if (test__start_subtest("udp")) { + do_test(SOCK_DGRAM, true); + do_test(SOCK_DGRAM, false); + } + close_netns(nstoken); + +done: + SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null"); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c index 67d4ef9e62b3..e905cbaf6b3d 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c +++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c @@ -47,6 +47,19 @@ static void subtest_ctx_arg_rewrite(void) struct btf *btf = NULL; __u32 info_len = sizeof(info); int err, fd, i; + struct btf *kern_btf = NULL; + + kern_btf = btf__load_vmlinux_btf(); + if (!ASSERT_OK_PTR(kern_btf, "kern_btf_load")) + return; + + /* simple detection of kernel native arg:ctx tag support */ + if (btf__find_by_name_kind(kern_btf, "bpf_subprog_arg_info", BTF_KIND_STRUCT) > 0) { + test__skip(); + btf__free(kern_btf); + return; + } + btf__free(kern_btf); skel = test_global_func_ctx_args__open(); if (!ASSERT_OK_PTR(skel, "skel_open")) diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index 1bdc680b0e0e..e8bd4b7b5ef7 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -72,6 +72,8 @@ #define inet_rcv_saddr sk.__sk_common.skc_rcv_saddr #define inet_dport sk.__sk_common.skc_dport +#define udp_portaddr_hash inet.sk.__sk_common.skc_u16hashes[1] + #define ir_loc_addr req.__req_common.skc_rcv_saddr #define ir_num req.__req_common.skc_num #define ir_rmt_addr req.__req_common.skc_daddr @@ -85,6 +87,7 @@ #define sk_rmem_alloc sk_backlog.rmem_alloc #define sk_refcnt __sk_common.skc_refcnt #define sk_state __sk_common.skc_state +#define sk_net __sk_common.skc_net #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_flags __sk_common.skc_flags diff --git a/tools/testing/selftests/bpf/progs/sock_iter_batch.c b/tools/testing/selftests/bpf/progs/sock_iter_batch.c new file mode 100644 index 000000000000..ffbbfe1fa1c1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sock_iter_batch.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2024 Meta + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_endian.h> +#include "bpf_tracing_net.h" +#include "bpf_kfuncs.h" + +#define ATTR __always_inline +#include "test_jhash.h" + +static bool ipv6_addr_loopback(const struct in6_addr *a) +{ + return (a->s6_addr32[0] | a->s6_addr32[1] | + a->s6_addr32[2] | (a->s6_addr32[3] ^ bpf_htonl(1))) == 0; +} + +volatile const __u16 ports[2]; +unsigned int bucket[2]; + +SEC("iter/tcp") +int iter_tcp_soreuse(struct bpf_iter__tcp *ctx) +{ + struct sock *sk = (struct sock *)ctx->sk_common; + struct inet_hashinfo *hinfo; + unsigned int hash; + struct net *net; + int idx; + + if (!sk) + return 0; + + sk = bpf_rdonly_cast(sk, bpf_core_type_id_kernel(struct sock)); + if (sk->sk_family != AF_INET6 || + sk->sk_state != TCP_LISTEN || + !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr)) + return 0; + + if (sk->sk_num == ports[0]) + idx = 0; + else if (sk->sk_num == ports[1]) + idx = 1; + else + return 0; + + /* bucket selection as in inet_lhash2_bucket_sk() */ + net = sk->sk_net.net; + hash = jhash2(sk->sk_v6_rcv_saddr.s6_addr32, 4, net->hash_mix); + hash ^= sk->sk_num; + hinfo = net->ipv4.tcp_death_row.hashinfo; + bucket[idx] = hash & hinfo->lhash2_mask; + bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx)); + + return 0; +} + +#define udp_sk(ptr) container_of(ptr, struct udp_sock, inet.sk) + +SEC("iter/udp") +int iter_udp_soreuse(struct bpf_iter__udp *ctx) +{ + struct sock *sk = (struct sock *)ctx->udp_sk; + struct udp_table *udptable; + int idx; + + if (!sk) + return 0; + + sk = bpf_rdonly_cast(sk, bpf_core_type_id_kernel(struct sock)); + if (sk->sk_family != AF_INET6 || + !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr)) + return 0; + + if (sk->sk_num == ports[0]) + idx = 0; + else if (sk->sk_num == ports[1]) + idx = 1; + else + return 0; + + /* bucket selection as in udp_hashslot2() */ + udptable = sk->sk_net.net->ipv4.udp_table; + bucket[idx] = udp_sk(sk)->udp_portaddr_hash & udptable->mask; + bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx)); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_jhash.h b/tools/testing/selftests/bpf/progs/test_jhash.h index c300734d26f6..ef53559bbbdf 100644 --- a/tools/testing/selftests/bpf/progs/test_jhash.h +++ b/tools/testing/selftests/bpf/progs/test_jhash.h @@ -69,3 +69,34 @@ u32 jhash(const void *key, u32 length, u32 initval) return c; } + +static __always_inline u32 jhash2(const u32 *k, u32 length, u32 initval) +{ + u32 a, b, c; + + /* Set up the internal state */ + a = b = c = JHASH_INITVAL + (length<<2) + initval; + + /* Handle most of the key */ + while (length > 3) { + a += k[0]; + b += k[1]; + c += k[2]; + __jhash_mix(a, b, c); + length -= 3; + k += 3; + } + + /* Handle the last 3 u32's */ + switch (length) { + case 3: c += k[2]; + case 2: b += k[1]; + case 1: a += k[0]; + __jhash_final(a, b, c); + break; + case 0: /* Nothing left to add */ + break; + } + + return c; +} diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c index 9eeb2d89cda8..67dddd941891 100644 --- a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c +++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c @@ -3,6 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> #include "bpf_misc.h" #include "xdp_metadata.h" #include "bpf_kfuncs.h" @@ -138,25 +139,182 @@ __weak int subprog_ctx_tag(void *ctx __arg_ctx) return bpf_get_stack(ctx, stack, sizeof(stack), 0); } +__weak int raw_tp_canonical(struct bpf_raw_tracepoint_args *ctx __arg_ctx) +{ + return 0; +} + +__weak int raw_tp_u64_array(u64 *ctx __arg_ctx) +{ + return 0; +} + SEC("?raw_tp") __success __log_level(2) int arg_tag_ctx_raw_tp(void *ctx) { - return subprog_ctx_tag(ctx); + return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx); +} + +SEC("?raw_tp.w") +__success __log_level(2) +int arg_tag_ctx_raw_tp_writable(void *ctx) +{ + return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx); +} + +SEC("?tp_btf/sys_enter") +__success __log_level(2) +int arg_tag_ctx_raw_tp_btf(void *ctx) +{ + return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx); +} + +struct whatever { }; + +__weak int tp_whatever(struct whatever *ctx __arg_ctx) +{ + return 0; } SEC("?tp") __success __log_level(2) int arg_tag_ctx_tp(void *ctx) { - return subprog_ctx_tag(ctx); + return subprog_ctx_tag(ctx) + tp_whatever(ctx); +} + +__weak int kprobe_subprog_pt_regs(struct pt_regs *ctx __arg_ctx) +{ + return 0; +} + +__weak int kprobe_subprog_typedef(bpf_user_pt_regs_t *ctx __arg_ctx) +{ + return 0; } SEC("?kprobe") __success __log_level(2) int arg_tag_ctx_kprobe(void *ctx) { - return subprog_ctx_tag(ctx); + return subprog_ctx_tag(ctx) + + kprobe_subprog_pt_regs(ctx) + + kprobe_subprog_typedef(ctx); +} + +__weak int perf_subprog_regs( +#if defined(bpf_target_riscv) + struct user_regs_struct *ctx __arg_ctx +#elif defined(bpf_target_s390) + /* user_pt_regs typedef is anonymous struct, so only `void *` works */ + void *ctx __arg_ctx +#elif defined(bpf_target_loongarch) || defined(bpf_target_arm64) || defined(bpf_target_powerpc) + struct user_pt_regs *ctx __arg_ctx +#else + struct pt_regs *ctx __arg_ctx +#endif +) +{ + return 0; +} + +__weak int perf_subprog_typedef(bpf_user_pt_regs_t *ctx __arg_ctx) +{ + return 0; +} + +__weak int perf_subprog_canonical(struct bpf_perf_event_data *ctx __arg_ctx) +{ + return 0; +} + +SEC("?perf_event") +__success __log_level(2) +int arg_tag_ctx_perf(void *ctx) +{ + return subprog_ctx_tag(ctx) + + perf_subprog_regs(ctx) + + perf_subprog_typedef(ctx) + + perf_subprog_canonical(ctx); +} + +__weak int iter_subprog_void(void *ctx __arg_ctx) +{ + return 0; +} + +__weak int iter_subprog_typed(struct bpf_iter__task *ctx __arg_ctx) +{ + return 0; +} + +SEC("?iter/task") +__success __log_level(2) +int arg_tag_ctx_iter_task(struct bpf_iter__task *ctx) +{ + return (iter_subprog_void(ctx) + iter_subprog_typed(ctx)) & 1; +} + +__weak int tracing_subprog_void(void *ctx __arg_ctx) +{ + return 0; +} + +__weak int tracing_subprog_u64(u64 *ctx __arg_ctx) +{ + return 0; +} + +int acc; + +SEC("?fentry/" SYS_PREFIX "sys_nanosleep") +__success __log_level(2) +int BPF_PROG(arg_tag_ctx_fentry) +{ + acc += tracing_subprog_void(ctx) + tracing_subprog_u64(ctx); + return 0; +} + +SEC("?fexit/" SYS_PREFIX "sys_nanosleep") +__success __log_level(2) +int BPF_PROG(arg_tag_ctx_fexit) +{ + acc += tracing_subprog_void(ctx) + tracing_subprog_u64(ctx); + return 0; +} + +SEC("?fmod_ret/" SYS_PREFIX "sys_nanosleep") +__success __log_level(2) +int BPF_PROG(arg_tag_ctx_fmod_ret) +{ + return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx); +} + +SEC("?lsm/bpf") +__success __log_level(2) +int BPF_PROG(arg_tag_ctx_lsm) +{ + return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx); +} + +SEC("?struct_ops/test_1") +__success __log_level(2) +int BPF_PROG(arg_tag_ctx_struct_ops) +{ + return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx); +} + +SEC(".struct_ops") +struct bpf_dummy_ops dummy_1 = { + .test_1 = (void *)arg_tag_ctx_struct_ops, +}; + +SEC("?syscall") +__success __log_level(2) +int arg_tag_ctx_syscall(void *ctx) +{ + return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx) + tp_whatever(ctx); } __weak int subprog_dynptr(struct bpf_dynptr *dptr) diff --git a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c index 71814a753216..a9ab37d3b9e2 100644 --- a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c +++ b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c @@ -146,4 +146,23 @@ l0_%=: exit; \ : __clobber_all); } +SEC("flow_dissector") +__description("flow_keys illegal alu op with variable offset") +__failure __msg("R7 pointer arithmetic on flow_keys prohibited") +__naked void flow_keys_illegal_variable_offset_alu(void) +{ + asm volatile(" \ + r6 = r1; \ + r7 = *(u64*)(r6 + %[flow_keys_off]); \ + r8 = 8; \ + r8 /= 1; \ + r8 &= 8; \ + r7 += r8; \ + r0 = *(u64*)(r7 + 0); \ + exit; \ +" : + : __imm_const(flow_keys_off, offsetof(struct __sk_buff, flow_keys)) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config index 70638fa50b2c..899d7fb6ea8e 100644 --- a/tools/testing/selftests/drivers/net/bonding/config +++ b/tools/testing/selftests/drivers/net/bonding/config @@ -1,2 +1,10 @@ CONFIG_BONDING=y +CONFIG_BRIDGE=y +CONFIG_DUMMY=y +CONFIG_IPV6=y CONFIG_MACVLAN=y +CONFIG_NET_ACT_GACT=y +CONFIG_NET_CLS_FLOWER=y +CONFIG_NET_SCH_INGRESS=y +CONFIG_NLMON=y +CONFIG_VETH=y diff --git a/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh b/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh index ad4c845a4ac7..b76bf5030952 100755 --- a/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh +++ b/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Regression Test: diff --git a/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh b/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh index 2330d37453f9..8c2619002147 100755 --- a/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh +++ b/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Regression Test: diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh index 42ce602d8d49..0f0f4f05807c 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh @@ -40,7 +40,6 @@ # | + $swp1 $swp3 + + $swp4 | # | | iPOOL1 iPOOL0 | | iPOOL2 | # | | ePOOL4 ePOOL5 | | ePOOL4 | -# | | 1Gbps | | 1Gbps | # | | PFC:enabled=1 | | PFC:enabled=1 | # | +-|----------------------|-+ +-|------------------------+ | # | | + $swp1.111 $swp3.111 + | | + $swp4.111 | | @@ -120,6 +119,9 @@ h2_destroy() switch_create() { + local lanes_swp4 + local pg1_size + # pools # ----- @@ -229,7 +231,20 @@ switch_create() dcb pfc set dev $swp4 prio-pfc all:off 1:on # PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which # is (-2*MTU) about 80K of delay provision. - dcb buffer set dev $swp4 buffer-size all:0 1:$_100KB + pg1_size=$_100KB + + setup_wait_dev_with_timeout $swp4 + + lanes_swp4=$(ethtool $swp4 | grep 'Lanes:') + lanes_swp4=${lanes_swp4#*"Lanes: "} + + # 8-lane ports use two buffers among which the configured buffer + # is split, so double the size to get twice (20K + 80K). + if [[ $lanes_swp4 -eq 8 ]]; then + pg1_size=$((pg1_size * 2)) + fi + + dcb buffer set dev $swp4 buffer-size all:0 1:$pg1_size # bridges # ------- diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh index fb850e0ec837..616d3581419c 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh @@ -10,7 +10,8 @@ lib_dir=$(dirname $0)/../../../../net/forwarding ALL_TESTS="single_mask_test identical_filters_test two_masks_test \ multiple_masks_test ctcam_edge_cases_test delta_simple_test \ delta_two_masks_one_key_test delta_simple_rehash_test \ - bloom_simple_test bloom_complex_test bloom_delta_test" + bloom_simple_test bloom_complex_test bloom_delta_test \ + max_erp_entries_test max_group_size_test" NUM_NETIFS=2 source $lib_dir/lib.sh source $lib_dir/tc_common.sh @@ -983,6 +984,109 @@ bloom_delta_test() log_test "bloom delta test ($tcflags)" } +max_erp_entries_test() +{ + # The number of eRP entries is limited. Once the maximum number of eRPs + # has been reached, filters cannot be added. This test verifies that + # when this limit is reached, inserstion fails without crashing. + + RET=0 + + local num_masks=32 + local num_regions=15 + local chain_failed + local mask_failed + local ret + + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + + for ((i=1; i < $num_regions; i++)); do + for ((j=$num_masks; j >= 0; j--)); do + tc filter add dev $h2 ingress chain $i protocol ip \ + pref $i handle $j flower $tcflags \ + dst_ip 192.1.0.0/$j &> /dev/null + ret=$? + + if [ $ret -ne 0 ]; then + chain_failed=$i + mask_failed=$j + break 2 + fi + done + done + + # We expect to exceed the maximum number of eRP entries, so that + # insertion eventually fails. Otherwise, the test should be adjusted to + # add more filters. + check_fail $ret "expected to exceed number of eRP entries" + + for ((; i >= 1; i--)); do + for ((j=0; j <= $num_masks; j++)); do + tc filter del dev $h2 ingress chain $i protocol ip \ + pref $i handle $j flower &> /dev/null + done + done + + log_test "max eRP entries test ($tcflags). " \ + "max chain $chain_failed, mask $mask_failed" +} + +max_group_size_test() +{ + # The number of ACLs in an ACL group is limited. Once the maximum + # number of ACLs has been reached, filters cannot be added. This test + # verifies that when this limit is reached, insertion fails without + # crashing. + + RET=0 + + local num_acls=32 + local max_size + local ret + + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + + for ((i=1; i < $num_acls; i++)); do + if [[ $(( i % 2 )) == 1 ]]; then + tc filter add dev $h2 ingress pref $i proto ipv4 \ + flower $tcflags dst_ip 198.51.100.1/32 \ + ip_proto tcp tcp_flags 0x01/0x01 \ + action drop &> /dev/null + else + tc filter add dev $h2 ingress pref $i proto ipv6 \ + flower $tcflags dst_ip 2001:db8:1::1/128 \ + action drop &> /dev/null + fi + + ret=$? + [[ $ret -ne 0 ]] && max_size=$((i - 1)) && break + done + + # We expect to exceed the maximum number of ACLs in a group, so that + # insertion eventually fails. Otherwise, the test should be adjusted to + # add more filters. + check_fail $ret "expected to exceed number of ACLs in a group" + + for ((; i >= 1; i--)); do + if [[ $(( i % 2 )) == 1 ]]; then + tc filter del dev $h2 ingress pref $i proto ipv4 \ + flower $tcflags dst_ip 198.51.100.1/32 \ + ip_proto tcp tcp_flags 0x01/0x01 \ + action drop &> /dev/null + else + tc filter del dev $h2 ingress pref $i proto ipv6 \ + flower $tcflags dst_ip 2001:db8:1::1/128 \ + action drop &> /dev/null + fi + done + + log_test "max ACL group size test ($tcflags). max size $max_size" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/drivers/net/netdevsim/config b/tools/testing/selftests/drivers/net/netdevsim/config new file mode 100644 index 000000000000..adf45a3a78b4 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/config @@ -0,0 +1,10 @@ +CONFIG_DUMMY=y +CONFIG_GENEVE=m +CONFIG_IPV6=y +CONFIG_NETDEVSIM=m +CONFIG_NET_SCH_MQPRIO=y +CONFIG_NET_SCH_MULTIQ=y +CONFIG_NET_SCH_PRIO=y +CONFIG_PSAMPLE=y +CONFIG_PTP_1588_CLOCK_MOCK=y +CONFIG_VXLAN=m diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh index 922744059aaa..80160579e0cc 100644 --- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh @@ -51,6 +51,7 @@ function make_netdev { fi echo $NSIM_ID $@ > /sys/bus/netdevsim/new_device + udevadm settle # get new device name ls /sys/bus/netdevsim/devices/netdevsim${NSIM_ID}/net/ } diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh index 0c56746e9ce0..7d7829f57550 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh @@ -8,16 +8,20 @@ NSIM_NETDEV=$(make_netdev) set -o pipefail +# Since commit 2b3ddcb35357 ("ethtool: fec: Change the prompt ...") +# in ethtool CLI the Configured lines start with Supported/Configured. +configured=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2 | head -1 | cut -d' ' -f1) + # netdevsim starts out with None/None s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) -check $? "$s" "Configured FEC encodings: None +check $? "$s" "$configured FEC encodings: None Active FEC encoding: None" # Test Auto $ETHTOOL --set-fec $NSIM_NETDEV encoding auto check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) -check $? "$s" "Configured FEC encodings: Auto +check $? "$s" "$configured FEC encodings: Auto Active FEC encoding: Off" # Test case in-sensitivity @@ -25,7 +29,7 @@ for o in off Off OFF; do $ETHTOOL --set-fec $NSIM_NETDEV encoding $o check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) - check $? "$s" "Configured FEC encodings: Off + check $? "$s" "$configured FEC encodings: Off Active FEC encoding: Off" done @@ -33,7 +37,7 @@ for o in BaseR baser BAser; do $ETHTOOL --set-fec $NSIM_NETDEV encoding $o check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) - check $? "$s" "Configured FEC encodings: BaseR + check $? "$s" "$configured FEC encodings: BaseR Active FEC encoding: BaseR" done @@ -41,7 +45,7 @@ for o in llrs rs; do $ETHTOOL --set-fec $NSIM_NETDEV encoding $o check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) - check $? "$s" "Configured FEC encodings: ${o^^} + check $? "$s" "$configured FEC encodings: ${o^^} Active FEC encoding: ${o^^}" done @@ -49,13 +53,13 @@ done $ETHTOOL --set-fec $NSIM_NETDEV encoding rs llrs check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) -check $? "$s" "Configured FEC encodings: RS LLRS +check $? "$s" "$configured FEC encodings: RS LLRS Active FEC encoding: LLRS" $ETHTOOL --set-fec $NSIM_NETDEV encoding rs off auto check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) -check $? "$s" "Configured FEC encodings: Auto Off RS +check $? "$s" "$configured FEC encodings: Auto Off RS Active FEC encoding: RS" # Make sure other link modes are rejected diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh index 1b08e042cf94..4855ef597a15 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh @@ -233,6 +233,7 @@ function print_tables { function get_netdev_name { local -n old=$1 + udevadm settle new=$(ls /sys/class/net) for netdev in $new; do diff --git a/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_subbuf_size.tc b/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_subbuf_size.tc new file mode 100644 index 000000000000..d44d09a33a74 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_subbuf_size.tc @@ -0,0 +1,95 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Change the ringbuffer sub-buffer size +# requires: buffer_subbuf_size_kb +# flags: instance + +get_buffer_data_size() { + sed -ne 's/^.*data.*size:\([0-9][0-9]*\).*/\1/p' events/header_page +} + +get_buffer_data_offset() { + sed -ne 's/^.*data.*offset:\([0-9][0-9]*\).*/\1/p' events/header_page +} + +get_event_header_size() { + type_len=`sed -ne 's/^.*type_len.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event` + time_len=`sed -ne 's/^.*time_delta.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event` + array_len=`sed -ne 's/^.*array.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event` + total_bits=$((type_len+time_len+array_len)) + total_bits=$((total_bits+7)) + echo $((total_bits/8)) +} + +get_print_event_buf_offset() { + sed -ne 's/^.*buf.*offset:\([0-9][0-9]*\).*/\1/p' events/ftrace/print/format +} + +event_header_size=`get_event_header_size` +print_header_size=`get_print_event_buf_offset` + +data_offset=`get_buffer_data_offset` + +marker_meta=$((event_header_size+print_header_size)) + +make_str() { + cnt=$1 + printf -- 'X%.0s' $(seq $cnt) +} + +write_buffer() { + size=$1 + + str=`make_str $size` + + # clear the buffer + echo > trace + + # write the string into the marker + echo $str > trace_marker + + echo $str +} + +test_buffer() { + size_kb=$1 + page_size=$((size_kb*1024)) + + size=`get_buffer_data_size` + + # the size must be greater than or equal to page_size - data_offset + page_size=$((page_size-data_offset)) + if [ $size -lt $page_size ]; then + exit fail + fi + + # Now add a little more the meta data overhead will overflow + + str=`write_buffer $size` + + # Make sure the line was broken + new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; exit}' trace` + + if [ "$new_str" = "$str" ]; then + exit fail; + fi + + # Make sure the entire line can be found + new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; }' trace` + + if [ "$new_str" != "$str" ]; then + exit fail; + fi +} + +ORIG=`cat buffer_subbuf_size_kb` + +# Could test bigger sizes than 32K, but then creating the string +# to write into the ring buffer takes too long +for a in 4 8 16 32 ; do + echo $a > buffer_subbuf_size_kb + test_buffer $a +done + +echo $ORIG > buffer_subbuf_size_kb + diff --git a/tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc b/tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc new file mode 100644 index 000000000000..9aa0db2b84fc --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc @@ -0,0 +1,82 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Basic tests on writing to trace_marker +# requires: trace_marker +# flags: instance + +get_buffer_data_size() { + sed -ne 's/^.*data.*size:\([0-9][0-9]*\).*/\1/p' events/header_page +} + +get_buffer_data_offset() { + sed -ne 's/^.*data.*offset:\([0-9][0-9]*\).*/\1/p' events/header_page +} + +get_event_header_size() { + type_len=`sed -ne 's/^.*type_len.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event` + time_len=`sed -ne 's/^.*time_delta.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event` + array_len=`sed -ne 's/^.*array.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event` + total_bits=$((type_len+time_len+array_len)) + total_bits=$((total_bits+7)) + echo $((total_bits/8)) +} + +get_print_event_buf_offset() { + sed -ne 's/^.*buf.*offset:\([0-9][0-9]*\).*/\1/p' events/ftrace/print/format +} + +event_header_size=`get_event_header_size` +print_header_size=`get_print_event_buf_offset` + +data_offset=`get_buffer_data_offset` + +marker_meta=$((event_header_size+print_header_size)) + +make_str() { + cnt=$1 + # subtract two for \n\0 as marker adds these + cnt=$((cnt-2)) + printf -- 'X%.0s' $(seq $cnt) +} + +write_buffer() { + size=$1 + + str=`make_str $size` + + # clear the buffer + echo > trace + + # write the string into the marker + echo -n $str > trace_marker + + echo $str +} + +test_buffer() { + + size=`get_buffer_data_size` + oneline_size=$((size-marker_meta)) + echo size = $size + echo meta size = $marker_meta + + # Now add a little more the meta data overhead will overflow + + str=`write_buffer $size` + + # Make sure the line was broken + new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; exit}' trace` + + if [ "$new_str" = "$str" ]; then + exit fail; + fi + + # Make sure the entire line can be found + new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; }' trace` + + if [ "$new_str" != "$str" ]; then + exit fail; + fi +} + +test_buffer diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 6ed328c863c4..1a881e7a21d1 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -116,6 +116,7 @@ TEST_F(iommufd, cmd_length) TEST_LENGTH(iommu_destroy, IOMMU_DESTROY, id); TEST_LENGTH(iommu_hw_info, IOMMU_GET_HW_INFO, __reserved); TEST_LENGTH(iommu_hwpt_alloc, IOMMU_HWPT_ALLOC, __reserved); + TEST_LENGTH(iommu_hwpt_invalidate, IOMMU_HWPT_INVALIDATE, __reserved); TEST_LENGTH(iommu_ioas_alloc, IOMMU_IOAS_ALLOC, out_ioas_id); TEST_LENGTH(iommu_ioas_iova_ranges, IOMMU_IOAS_IOVA_RANGES, out_iova_alignment); @@ -271,7 +272,9 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested) struct iommu_hwpt_selftest data = { .iotlb = IOMMU_TEST_IOTLB_DEFAULT, }; + struct iommu_hwpt_invalidate_selftest inv_reqs[2] = {}; uint32_t nested_hwpt_id[2] = {}; + uint32_t num_inv; uint32_t parent_hwpt_id = 0; uint32_t parent_hwpt_id_not_work = 0; uint32_t test_hwpt_id = 0; @@ -330,6 +333,10 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested) &nested_hwpt_id[1], IOMMU_HWPT_DATA_SELFTEST, &data, sizeof(data)); + test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[0], + IOMMU_TEST_IOTLB_DEFAULT); + test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[1], + IOMMU_TEST_IOTLB_DEFAULT); /* Negative test: a nested hwpt on top of a nested hwpt */ test_err_hwpt_alloc_nested(EINVAL, self->device_id, @@ -340,6 +347,151 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested) EXPECT_ERRNO(EBUSY, _test_ioctl_destroy(self->fd, parent_hwpt_id)); + /* hwpt_invalidate only supports a user-managed hwpt (nested) */ + num_inv = 1; + test_err_hwpt_invalidate(ENOENT, parent_hwpt_id, inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Check data_type by passing zero-length array */ + num_inv = 0; + test_cmd_hwpt_invalidate(nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: Invalid data_type */ + num_inv = 1; + test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST_INVALID, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: structure size sanity */ + num_inv = 1; + test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs) + 1, &num_inv); + assert(!num_inv); + + num_inv = 1; + test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + 1, &num_inv); + assert(!num_inv); + + /* Negative test: invalid flag is passed */ + num_inv = 1; + inv_reqs[0].flags = 0xffffffff; + test_err_hwpt_invalidate(EOPNOTSUPP, nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: invalid data_uptr when array is not empty */ + num_inv = 1; + inv_reqs[0].flags = 0; + test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], NULL, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: invalid entry_len when array is not empty */ + num_inv = 1; + inv_reqs[0].flags = 0; + test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + 0, &num_inv); + assert(!num_inv); + + /* Negative test: invalid iotlb_id */ + num_inv = 1; + inv_reqs[0].flags = 0; + inv_reqs[0].iotlb_id = MOCK_NESTED_DOMAIN_IOTLB_ID_MAX + 1; + test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* + * Invalidate the 1st iotlb entry but fail the 2nd request + * due to invalid flags configuration in the 2nd request. + */ + num_inv = 2; + inv_reqs[0].flags = 0; + inv_reqs[0].iotlb_id = 0; + inv_reqs[1].flags = 0xffffffff; + inv_reqs[1].iotlb_id = 1; + test_err_hwpt_invalidate(EOPNOTSUPP, nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 1); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 0, 0); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 1, + IOMMU_TEST_IOTLB_DEFAULT); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 2, + IOMMU_TEST_IOTLB_DEFAULT); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 3, + IOMMU_TEST_IOTLB_DEFAULT); + + /* + * Invalidate the 1st iotlb entry but fail the 2nd request + * due to invalid iotlb_id configuration in the 2nd request. + */ + num_inv = 2; + inv_reqs[0].flags = 0; + inv_reqs[0].iotlb_id = 0; + inv_reqs[1].flags = 0; + inv_reqs[1].iotlb_id = MOCK_NESTED_DOMAIN_IOTLB_ID_MAX + 1; + test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 1); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 0, 0); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 1, + IOMMU_TEST_IOTLB_DEFAULT); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 2, + IOMMU_TEST_IOTLB_DEFAULT); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 3, + IOMMU_TEST_IOTLB_DEFAULT); + + /* Invalidate the 2nd iotlb entry and verify */ + num_inv = 1; + inv_reqs[0].flags = 0; + inv_reqs[0].iotlb_id = 1; + test_cmd_hwpt_invalidate(nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 1); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 0, 0); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 1, 0); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 2, + IOMMU_TEST_IOTLB_DEFAULT); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 3, + IOMMU_TEST_IOTLB_DEFAULT); + + /* Invalidate the 3rd and 4th iotlb entries and verify */ + num_inv = 2; + inv_reqs[0].flags = 0; + inv_reqs[0].iotlb_id = 2; + inv_reqs[1].flags = 0; + inv_reqs[1].iotlb_id = 3; + test_cmd_hwpt_invalidate(nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 2); + test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[0], 0); + + /* Invalidate all iotlb entries for nested_hwpt_id[1] and verify */ + num_inv = 1; + inv_reqs[0].flags = IOMMU_TEST_INVALIDATE_FLAG_ALL; + test_cmd_hwpt_invalidate(nested_hwpt_id[1], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 1); + test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[1], 0); + /* Attach device to nested_hwpt_id[0] that then will be busy */ test_cmd_mock_domain_replace(self->stdev_id, nested_hwpt_id[0]); EXPECT_ERRNO(EBUSY, diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index ad9202335656..c646264aa41f 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -195,6 +195,61 @@ static int _test_cmd_hwpt_alloc(int fd, __u32 device_id, __u32 pt_id, _test_cmd_hwpt_alloc(self->fd, device_id, pt_id, flags, \ hwpt_id, data_type, data, data_len)) +#define test_cmd_hwpt_check_iotlb(hwpt_id, iotlb_id, expected) \ + ({ \ + struct iommu_test_cmd test_cmd = { \ + .size = sizeof(test_cmd), \ + .op = IOMMU_TEST_OP_MD_CHECK_IOTLB, \ + .id = hwpt_id, \ + .check_iotlb = { \ + .id = iotlb_id, \ + .iotlb = expected, \ + }, \ + }; \ + ASSERT_EQ(0, \ + ioctl(self->fd, \ + _IOMMU_TEST_CMD(IOMMU_TEST_OP_MD_CHECK_IOTLB), \ + &test_cmd)); \ + }) + +#define test_cmd_hwpt_check_iotlb_all(hwpt_id, expected) \ + ({ \ + int i; \ + for (i = 0; i < MOCK_NESTED_DOMAIN_IOTLB_NUM; i++) \ + test_cmd_hwpt_check_iotlb(hwpt_id, i, expected); \ + }) + +static int _test_cmd_hwpt_invalidate(int fd, __u32 hwpt_id, void *reqs, + uint32_t data_type, uint32_t lreq, + uint32_t *nreqs) +{ + struct iommu_hwpt_invalidate cmd = { + .size = sizeof(cmd), + .hwpt_id = hwpt_id, + .data_type = data_type, + .data_uptr = (uint64_t)reqs, + .entry_len = lreq, + .entry_num = *nreqs, + }; + int rc = ioctl(fd, IOMMU_HWPT_INVALIDATE, &cmd); + *nreqs = cmd.entry_num; + return rc; +} + +#define test_cmd_hwpt_invalidate(hwpt_id, reqs, data_type, lreq, nreqs) \ + ({ \ + ASSERT_EQ(0, \ + _test_cmd_hwpt_invalidate(self->fd, hwpt_id, reqs, \ + data_type, lreq, nreqs)); \ + }) +#define test_err_hwpt_invalidate(_errno, hwpt_id, reqs, data_type, lreq, \ + nreqs) \ + ({ \ + EXPECT_ERRNO(_errno, _test_cmd_hwpt_invalidate( \ + self->fd, hwpt_id, reqs, \ + data_type, lreq, nreqs)); \ + }) + static int _test_cmd_access_replace_ioas(int fd, __u32 access_id, unsigned int ioas_id) { diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 8a61464ab6eb..8a61464ab6eb 100755..100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index a10a32952f21..4667d74579d1 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -28,6 +28,7 @@ ALL_TESTS=" kci_test_neigh_get kci_test_bridge_parent_id kci_test_address_proto + kci_test_enslave_bonding " devdummy="test-dummy0" @@ -1241,6 +1242,31 @@ kci_test_address_proto() return $ret } +kci_test_enslave_bonding() +{ + local bond="bond123" + local ret=0 + + setup_ns testns + if [ $? -ne 0 ]; then + end_test "SKIP bonding tests: cannot add net namespace $testns" + return $ksft_skip + fi + + run_cmd ip -netns $testns link add dev $bond type bond mode balance-rr + run_cmd ip -netns $testns link add dev $devdummy type dummy + run_cmd ip -netns $testns link set dev $devdummy up + run_cmd ip -netns $testns link set dev $devdummy master $bond down + if [ $ret -ne 0 ]; then + end_test "FAIL: initially up interface added to a bond and set down" + ip netns del "$testns" + return 1 + fi + + end_test "PASS: enslave interface in a bond" + ip netns del "$testns" +} + kci_test_rtnl() { local current_test diff --git a/tools/testing/selftests/net/tcp_ao/Makefile b/tools/testing/selftests/net/tcp_ao/Makefile index 8e60bae67aa9..522d991e310e 100644 --- a/tools/testing/selftests/net/tcp_ao/Makefile +++ b/tools/testing/selftests/net/tcp_ao/Makefile @@ -52,5 +52,5 @@ $(OUTPUT)/%_ipv6: %.c $(OUTPUT)/icmps-accept_ipv4: CFLAGS+= -DTEST_ICMPS_ACCEPT $(OUTPUT)/icmps-accept_ipv6: CFLAGS+= -DTEST_ICMPS_ACCEPT -$(OUTPUT)/bench-lookups_ipv4: LDFLAGS+= -lm -$(OUTPUT)/bench-lookups_ipv6: LDFLAGS+= -lm +$(OUTPUT)/bench-lookups_ipv4: LDLIBS+= -lm +$(OUTPUT)/bench-lookups_ipv6: LDLIBS+= -lm diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 464853a7f982..7799e042a971 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -707,6 +707,20 @@ TEST_F(tls, splice_from_pipe) EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); } +TEST_F(tls, splice_more) +{ + unsigned int f = SPLICE_F_NONBLOCK | SPLICE_F_MORE | SPLICE_F_GIFT; + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + int i, send_pipe = 1; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_GE(write(p[1], mem_send, send_len), 0); + for (i = 0; i < 32; i++) + EXPECT_EQ(splice(p[0], NULL, self->fd, NULL, send_pipe, f), 1); +} + TEST_F(tls, splice_from_pipe2) { int send_len = 16000; diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile index 50aab6b57da3..867f88ce2570 100644 --- a/tools/testing/selftests/sgx/Makefile +++ b/tools/testing/selftests/sgx/Makefile @@ -12,14 +12,16 @@ OBJCOPY := $(CROSS_COMPILE)objcopy endif INCLUDES := -I$(top_srcdir)/tools/include -HOST_CFLAGS := -Wall -Werror -g $(INCLUDES) -fPIC -z noexecstack -ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \ +HOST_CFLAGS := -Wall -Werror -g $(INCLUDES) -fPIC +HOST_LDFLAGS := -z noexecstack -lcrypto +ENCL_CFLAGS += -Wall -Werror -static-pie -nostdlib -ffreestanding -fPIE \ -fno-stack-protector -mrdrnd $(INCLUDES) +ENCL_LDFLAGS := -Wl,-T,test_encl.lds,--build-id=none +ifeq ($(CAN_BUILD_X86_64), 1) TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx TEST_FILES := $(OUTPUT)/test_encl.elf -ifeq ($(CAN_BUILD_X86_64), 1) all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/test_encl.elf endif @@ -28,7 +30,7 @@ $(OUTPUT)/test_sgx: $(OUTPUT)/main.o \ $(OUTPUT)/sigstruct.o \ $(OUTPUT)/call.o \ $(OUTPUT)/sign_key.o - $(CC) $(HOST_CFLAGS) -o $@ $^ -lcrypto + $(CC) $(HOST_CFLAGS) -o $@ $^ $(HOST_LDFLAGS) $(OUTPUT)/main.o: main.c $(CC) $(HOST_CFLAGS) -c $< -o $@ @@ -45,8 +47,8 @@ $(OUTPUT)/call.o: call.S $(OUTPUT)/sign_key.o: sign_key.S $(CC) $(HOST_CFLAGS) -c $< -o $@ -$(OUTPUT)/test_encl.elf: test_encl.lds test_encl.c test_encl_bootstrap.S - $(CC) $(ENCL_CFLAGS) -T $^ -o $@ -Wl,--build-id=none +$(OUTPUT)/test_encl.elf: test_encl.c test_encl_bootstrap.S + $(CC) $(ENCL_CFLAGS) $^ -o $@ $(ENCL_LDFLAGS) EXTRA_CLEAN := \ $(OUTPUT)/test_encl.elf \ diff --git a/tools/testing/selftests/sgx/defines.h b/tools/testing/selftests/sgx/defines.h index d8587c971941..402f8787a71c 100644 --- a/tools/testing/selftests/sgx/defines.h +++ b/tools/testing/selftests/sgx/defines.h @@ -13,6 +13,8 @@ #define __aligned(x) __attribute__((__aligned__(x))) #define __packed __attribute__((packed)) +#define __used __attribute__((used)) +#define __section(x)__attribute__((__section__(x))) #include "../../../../arch/x86/include/asm/sgx.h" #include "../../../../arch/x86/include/asm/enclu.h" diff --git a/tools/testing/selftests/sgx/load.c b/tools/testing/selftests/sgx/load.c index 94bdeac1cf04..c9f658e44de6 100644 --- a/tools/testing/selftests/sgx/load.c +++ b/tools/testing/selftests/sgx/load.c @@ -136,11 +136,11 @@ static bool encl_ioc_add_pages(struct encl *encl, struct encl_segment *seg) */ uint64_t encl_get_entry(struct encl *encl, const char *symbol) { + Elf64_Sym *symtab = NULL; + char *sym_names = NULL; Elf64_Shdr *sections; - Elf64_Sym *symtab; Elf64_Ehdr *ehdr; - char *sym_names; - int num_sym; + int num_sym = 0; int i; ehdr = encl->bin; @@ -161,6 +161,9 @@ uint64_t encl_get_entry(struct encl *encl, const char *symbol) } } + if (!symtab || !sym_names) + return 0; + for (i = 0; i < num_sym; i++) { Elf64_Sym *sym = &symtab[i]; diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c index a07896a46364..d73b29becf5b 100644 --- a/tools/testing/selftests/sgx/sigstruct.c +++ b/tools/testing/selftests/sgx/sigstruct.c @@ -318,9 +318,9 @@ bool encl_measure(struct encl *encl) struct sgx_sigstruct *sigstruct = &encl->sigstruct; struct sgx_sigstruct_payload payload; uint8_t digest[SHA256_DIGEST_LENGTH]; + EVP_MD_CTX *ctx = NULL; unsigned int siglen; RSA *key = NULL; - EVP_MD_CTX *ctx; int i; memset(sigstruct, 0, sizeof(*sigstruct)); @@ -384,7 +384,8 @@ bool encl_measure(struct encl *encl) return true; err: - EVP_MD_CTX_destroy(ctx); + if (ctx) + EVP_MD_CTX_destroy(ctx); RSA_free(key); return false; } diff --git a/tools/testing/selftests/sgx/test_encl.c b/tools/testing/selftests/sgx/test_encl.c index c0d6397295e3..2c4d709cce2d 100644 --- a/tools/testing/selftests/sgx/test_encl.c +++ b/tools/testing/selftests/sgx/test_encl.c @@ -5,11 +5,12 @@ #include "defines.h" /* - * Data buffer spanning two pages that will be placed first in .data - * segment. Even if not used internally the second page is needed by - * external test manipulating page permissions. + * Data buffer spanning two pages that will be placed first in the .data + * segment via the linker script. Even if not used internally the second page + * is needed by external test manipulating page permissions, so mark + * encl_buffer as "used" to make sure it is entirely preserved by the compiler. */ -static uint8_t encl_buffer[8192] = { 1 }; +static uint8_t __used __section(".data.encl_buffer") encl_buffer[8192] = { 1 }; enum sgx_enclu_function { EACCEPT = 0x5, @@ -24,10 +25,11 @@ static void do_encl_emodpe(void *_op) secinfo.flags = op->flags; asm volatile(".byte 0x0f, 0x01, 0xd7" - : + : /* no outputs */ : "a" (EMODPE), "b" (&secinfo), - "c" (op->epc_addr)); + "c" (op->epc_addr) + : "memory" /* read from secinfo pointer */); } static void do_encl_eaccept(void *_op) @@ -42,7 +44,8 @@ static void do_encl_eaccept(void *_op) : "=a" (rax) : "a" (EACCEPT), "b" (&secinfo), - "c" (op->epc_addr)); + "c" (op->epc_addr) + : "memory" /* read from secinfo pointer */); op->ret = rax; } @@ -119,21 +122,41 @@ static void do_encl_op_nop(void *_op) } +/* + * Symbol placed at the start of the enclave image by the linker script. + * Declare this extern symbol with visibility "hidden" to ensure the compiler + * does not access it through the GOT and generates position-independent + * addressing as __encl_base(%rip), so we can get the actual enclave base + * during runtime. + */ +extern const uint8_t __attribute__((visibility("hidden"))) __encl_base; + +typedef void (*encl_op_t)(void *); +static const encl_op_t encl_op_array[ENCL_OP_MAX] = { + do_encl_op_put_to_buf, + do_encl_op_get_from_buf, + do_encl_op_put_to_addr, + do_encl_op_get_from_addr, + do_encl_op_nop, + do_encl_eaccept, + do_encl_emodpe, + do_encl_init_tcs_page, +}; + void encl_body(void *rdi, void *rsi) { - const void (*encl_op_array[ENCL_OP_MAX])(void *) = { - do_encl_op_put_to_buf, - do_encl_op_get_from_buf, - do_encl_op_put_to_addr, - do_encl_op_get_from_addr, - do_encl_op_nop, - do_encl_eaccept, - do_encl_emodpe, - do_encl_init_tcs_page, - }; - - struct encl_op_header *op = (struct encl_op_header *)rdi; - - if (op->type < ENCL_OP_MAX) - (*encl_op_array[op->type])(op); + struct encl_op_header *header = (struct encl_op_header *)rdi; + encl_op_t op; + + if (header->type >= ENCL_OP_MAX) + return; + + /* + * The enclave base address needs to be added, as this call site + * *cannot be* made rip-relative by the compiler, or fixed up by + * any other possible means. + */ + op = ((uint64_t)&__encl_base) + encl_op_array[header->type]; + + (*op)(header); } diff --git a/tools/testing/selftests/sgx/test_encl.lds b/tools/testing/selftests/sgx/test_encl.lds index a1ec64f7d91f..ffe851a1cac4 100644 --- a/tools/testing/selftests/sgx/test_encl.lds +++ b/tools/testing/selftests/sgx/test_encl.lds @@ -10,6 +10,7 @@ PHDRS SECTIONS { . = 0; + __encl_base = .; .tcs : { *(.tcs*) } : tcs @@ -23,6 +24,7 @@ SECTIONS } : text .data : { + *(.data.encl_buffer) *(.data*) } : data @@ -31,11 +33,9 @@ SECTIONS *(.note*) *(.debug*) *(.eh_frame*) + *(.dyn*) + *(.gnu.hash) } } -ASSERT(!DEFINED(.altinstructions), "ALTERNATIVES are not supported in enclaves") -ASSERT(!DEFINED(.altinstr_replacement), "ALTERNATIVES are not supported in enclaves") -ASSERT(!DEFINED(.discard.retpoline_safe), "RETPOLINE ALTERNATIVES are not supported in enclaves") -ASSERT(!DEFINED(.discard.nospec), "RETPOLINE ALTERNATIVES are not supported in enclaves") -ASSERT(!DEFINED(.got.plt), "Libcalls are not supported in enclaves") +ASSERT(!DEFINED(_GLOBAL_OFFSET_TABLE_), "Libcalls through GOT are not supported in enclaves") diff --git a/tools/testing/selftests/sgx/test_encl_bootstrap.S b/tools/testing/selftests/sgx/test_encl_bootstrap.S index 03ae0f57e29d..d8c4ac94e032 100644 --- a/tools/testing/selftests/sgx/test_encl_bootstrap.S +++ b/tools/testing/selftests/sgx/test_encl_bootstrap.S @@ -42,9 +42,12 @@ encl_entry: # RBX contains the base address for TCS, which is the first address # inside the enclave for TCS #1 and one page into the enclave for - # TCS #2. By adding the value of encl_stack to it, we get - # the absolute address for the stack. - lea (encl_stack)(%rbx), %rax + # TCS #2. First make it relative by substracting __encl_base and + # then add the address of encl_stack to get the address for the stack. + lea __encl_base(%rip), %rax + sub %rax, %rbx + lea encl_stack(%rip), %rax + add %rbx, %rax jmp encl_entry_core encl_dyn_entry: # Entry point for dynamically created TCS page expected to follow @@ -55,25 +58,12 @@ encl_entry_core: push %rax push %rcx # push the address after EENTER - push %rbx # push the enclave base address + # NOTE: as the selftest enclave is *not* intended for production, + # simplify the code by not initializing ABI registers on entry or + # cleansing caller-save registers on exit. call encl_body - pop %rbx # pop the enclave base address - - /* Clear volatile GPRs, except RAX (EEXIT function). */ - xor %rcx, %rcx - xor %rdx, %rdx - xor %rdi, %rdi - xor %rsi, %rsi - xor %r8, %r8 - xor %r9, %r9 - xor %r10, %r10 - xor %r11, %r11 - - # Reset status flags. - add %rdx, %rdx # OF = SF = AF = CF = 0; ZF = PF = 1 - # Prepare EEXIT target by popping the address of the instruction after # EENTER to RBX. pop %rbx diff --git a/usr/gen_init_cpio.c b/usr/gen_init_cpio.c index 61230532fef1..edcdb8abfa31 100644 --- a/usr/gen_init_cpio.c +++ b/usr/gen_init_cpio.c @@ -27,6 +27,7 @@ static unsigned int offset; static unsigned int ino = 721; static time_t default_mtime; +static bool do_file_mtime; static bool do_csum = false; struct file_handler { @@ -329,6 +330,7 @@ static int cpio_mkfile(const char *name, const char *location, int file; int retval; int rc = -1; + time_t mtime; int namesize; unsigned int i; uint32_t csum = 0; @@ -347,16 +349,21 @@ static int cpio_mkfile(const char *name, const char *location, goto error; } - if (buf.st_mtime > 0xffffffff) { - fprintf(stderr, "%s: Timestamp exceeds maximum cpio timestamp, clipping.\n", - location); - buf.st_mtime = 0xffffffff; - } + if (do_file_mtime) { + mtime = default_mtime; + } else { + mtime = buf.st_mtime; + if (mtime > 0xffffffff) { + fprintf(stderr, "%s: Timestamp exceeds maximum cpio timestamp, clipping.\n", + location); + mtime = 0xffffffff; + } - if (buf.st_mtime < 0) { - fprintf(stderr, "%s: Timestamp negative, clipping.\n", - location); - buf.st_mtime = 0; + if (mtime < 0) { + fprintf(stderr, "%s: Timestamp negative, clipping.\n", + location); + mtime = 0; + } } if (buf.st_size > 0xffffffff) { @@ -387,7 +394,7 @@ static int cpio_mkfile(const char *name, const char *location, (long) uid, /* uid */ (long) gid, /* gid */ nlinks, /* nlink */ - (long) buf.st_mtime, /* mtime */ + (long) mtime, /* mtime */ size, /* filesize */ 3, /* major */ 1, /* minor */ @@ -536,8 +543,9 @@ static void usage(const char *prog) "file /sbin/kinit /usr/src/klibc/kinit/kinit 0755 0 0\n" "\n" "<timestamp> is time in seconds since Epoch that will be used\n" - "as mtime for symlinks, special files and directories. The default\n" - "is to use the current time for these entries.\n" + "as mtime for symlinks, directories, regular and special files.\n" + "The default is to use the current time for all files, but\n" + "preserve modification time for regular files.\n" "-c: calculate and store 32-bit checksums for file data.\n", prog); } @@ -594,6 +602,7 @@ int main (int argc, char *argv[]) usage(argv[0]); exit(1); } + do_file_mtime = true; break; case 'c': do_csum = true; |