diff options
115 files changed, 3571 insertions, 1786 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats new file mode 100644 index 000000000000..4b0318c99507 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats @@ -0,0 +1,122 @@ +========================== +PCIe Device AER statistics +========================== +These attributes show up under all the devices that are AER capable. These +statistical counters indicate the errors "as seen/reported by the device". +Note that this may mean that if an endpoint is causing problems, the AER +counters may increment at its link partner (e.g. root port) because the +errors may be "seen" / reported by the link partner and not the +problematic endpoint itself (which may report all counters as 0 as it never +saw any problems). + +Where: /sys/bus/pci/devices/<dev>/aer_dev_correctable +Date: July 2018 +Kernel Version: 4.19.0 +Contact: linux-pci@vger.kernel.org, rajatja@google.com +Description: List of correctable errors seen and reported by this + PCI device using ERR_COR. Note that since multiple errors may + be reported using a single ERR_COR message, thus + TOTAL_ERR_COR at the end of the file may not match the actual + total of all the errors in the file. Sample output: +------------------------------------------------------------------------- +localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_correctable +Receiver Error 2 +Bad TLP 0 +Bad DLLP 0 +RELAY_NUM Rollover 0 +Replay Timer Timeout 0 +Advisory Non-Fatal 0 +Corrected Internal Error 0 +Header Log Overflow 0 +TOTAL_ERR_COR 2 +------------------------------------------------------------------------- + +Where: /sys/bus/pci/devices/<dev>/aer_dev_fatal +Date: July 2018 +Kernel Version: 4.19.0 +Contact: linux-pci@vger.kernel.org, rajatja@google.com +Description: List of uncorrectable fatal errors seen and reported by this + PCI device using ERR_FATAL. Note that since multiple errors may + be reported using a single ERR_FATAL message, thus + TOTAL_ERR_FATAL at the end of the file may not match the actual + total of all the errors in the file. Sample output: +------------------------------------------------------------------------- +localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_fatal +Undefined 0 +Data Link Protocol 0 +Surprise Down Error 0 +Poisoned TLP 0 +Flow Control Protocol 0 +Completion Timeout 0 +Completer Abort 0 +Unexpected Completion 0 +Receiver Overflow 0 +Malformed TLP 0 +ECRC 0 +Unsupported Request 0 +ACS Violation 0 +Uncorrectable Internal Error 0 +MC Blocked TLP 0 +AtomicOp Egress Blocked 0 +TLP Prefix Blocked Error 0 +TOTAL_ERR_FATAL 0 +------------------------------------------------------------------------- + +Where: /sys/bus/pci/devices/<dev>/aer_dev_nonfatal +Date: July 2018 +Kernel Version: 4.19.0 +Contact: linux-pci@vger.kernel.org, rajatja@google.com +Description: List of uncorrectable nonfatal errors seen and reported by this + PCI device using ERR_NONFATAL. Note that since multiple errors + may be reported using a single ERR_FATAL message, thus + TOTAL_ERR_NONFATAL at the end of the file may not match the + actual total of all the errors in the file. Sample output: +------------------------------------------------------------------------- +localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_nonfatal +Undefined 0 +Data Link Protocol 0 +Surprise Down Error 0 +Poisoned TLP 0 +Flow Control Protocol 0 +Completion Timeout 0 +Completer Abort 0 +Unexpected Completion 0 +Receiver Overflow 0 +Malformed TLP 0 +ECRC 0 +Unsupported Request 0 +ACS Violation 0 +Uncorrectable Internal Error 0 +MC Blocked TLP 0 +AtomicOp Egress Blocked 0 +TLP Prefix Blocked Error 0 +TOTAL_ERR_NONFATAL 0 +------------------------------------------------------------------------- + +============================ +PCIe Rootport AER statistics +============================ +These attributes show up under only the rootports (or root complex event +collectors) that are AER capable. These indicate the number of error messages as +"reported to" the rootport. Please note that the rootports also transmit +(internally) the ERR_* messages for errors seen by the internal rootport PCI +device, so these counters include them and are thus cumulative of all the error +messages on the PCI hierarchy originating at that root port. + +Where: /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_cor +Date: July 2018 +Kernel Version: 4.19.0 +Contact: linux-pci@vger.kernel.org, rajatja@google.com +Description: Total number of ERR_COR messages reported to rootport. + +Where: /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_fatal +Date: July 2018 +Kernel Version: 4.19.0 +Contact: linux-pci@vger.kernel.org, rajatja@google.com +Description: Total number of ERR_FATAL messages reported to rootport. + +Where: /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_nonfatal +Date: July 2018 +Kernel Version: 4.19.0 +Contact: linux-pci@vger.kernel.org, rajatja@google.com +Description: Total number of ERR_NONFATAL messages reported to rootport. diff --git a/Documentation/PCI/00-INDEX b/Documentation/PCI/00-INDEX index 00c9a90b6f38..206b1d5c1e71 100644 --- a/Documentation/PCI/00-INDEX +++ b/Documentation/PCI/00-INDEX @@ -1,5 +1,7 @@ 00-INDEX - this file +acpi-info.txt + - info on how PCI host bridges are represented in ACPI MSI-HOWTO.txt - the Message Signaled Interrupts (MSI) Driver Guide HOWTO and FAQ. PCIEBUS-HOWTO.txt diff --git a/Documentation/PCI/acpi-info.txt b/Documentation/PCI/acpi-info.txt new file mode 100644 index 000000000000..3ffa3b03970e --- /dev/null +++ b/Documentation/PCI/acpi-info.txt @@ -0,0 +1,187 @@ + ACPI considerations for PCI host bridges + +The general rule is that the ACPI namespace should describe everything the +OS might use unless there's another way for the OS to find it [1, 2]. + +For example, there's no standard hardware mechanism for enumerating PCI +host bridges, so the ACPI namespace must describe each host bridge, the +method for accessing PCI config space below it, the address space windows +the host bridge forwards to PCI (using _CRS), and the routing of legacy +INTx interrupts (using _PRT). + +PCI devices, which are below the host bridge, generally do not need to be +described via ACPI. The OS can discover them via the standard PCI +enumeration mechanism, using config accesses to discover and identify +devices and read and size their BARs. However, ACPI may describe PCI +devices if it provides power management or hotplug functionality for them +or if the device has INTx interrupts connected by platform interrupt +controllers and a _PRT is needed to describe those connections. + +ACPI resource description is done via _CRS objects of devices in the ACPI +namespace [2].  The _CRS is like a generalized PCI BAR: the OS can read +_CRS and figure out what resource is being consumed even if it doesn't have +a driver for the device [3].  That's important because it means an old OS +can work correctly even on a system with new devices unknown to the OS. +The new devices might not do anything, but the OS can at least make sure no +resources conflict with them. + +Static tables like MCFG, HPET, ECDT, etc., are *not* mechanisms for +reserving address space. The static tables are for things the OS needs to +know early in boot, before it can parse the ACPI namespace. If a new table +is defined, an old OS needs to operate correctly even though it ignores the +table. _CRS allows that because it is generic and understood by the old +OS; a static table does not. + +If the OS is expected to manage a non-discoverable device described via +ACPI, that device will have a specific _HID/_CID that tells the OS what +driver to bind to it, and the _CRS tells the OS and the driver where the +device's registers are. + +PCI host bridges are PNP0A03 or PNP0A08 devices.  Their _CRS should +describe all the address space they consume.  This includes all the windows +they forward down to the PCI bus, as well as registers of the host bridge +itself that are not forwarded to PCI.  The host bridge registers include +things like secondary/subordinate bus registers that determine the bus +range below the bridge, window registers that describe the apertures, etc. +These are all device-specific, non-architected things, so the only way a +PNP0A03/PNP0A08 driver can manage them is via _PRS/_CRS/_SRS, which contain +the device-specific details.  The host bridge registers also include ECAM +space, since it is consumed by the host bridge. + +ACPI defines a Consumer/Producer bit to distinguish the bridge registers +("Consumer") from the bridge apertures ("Producer") [4, 5], but early +BIOSes didn't use that bit correctly. The result is that the current ACPI +spec defines Consumer/Producer only for the Extended Address Space +descriptors; the bit should be ignored in the older QWord/DWord/Word +Address Space descriptors. Consequently, OSes have to assume all +QWord/DWord/Word descriptors are windows. + +Prior to the addition of Extended Address Space descriptors, the failure of +Consumer/Producer meant there was no way to describe bridge registers in +the PNP0A03/PNP0A08 device itself. The workaround was to describe the +bridge registers (including ECAM space) in PNP0C02 catch-all devices [6]. +With the exception of ECAM, the bridge register space is device-specific +anyway, so the generic PNP0A03/PNP0A08 driver (pci_root.c) has no need to +know about it.  + +New architectures should be able to use "Consumer" Extended Address Space +descriptors in the PNP0A03 device for bridge registers, including ECAM, +although a strict interpretation of [6] might prohibit this. Old x86 and +ia64 kernels assume all address space descriptors, including "Consumer" +Extended Address Space ones, are windows, so it would not be safe to +describe bridge registers this way on those architectures. + +PNP0C02 "motherboard" devices are basically a catch-all.  There's no +programming model for them other than "don't use these resources for +anything else."  So a PNP0C02 _CRS should claim any address space that is +(1) not claimed by _CRS under any other device object in the ACPI namespace +and (2) should not be assigned by the OS to something else. + +The PCIe spec requires the Enhanced Configuration Access Method (ECAM) +unless there's a standard firmware interface for config access, e.g., the +ia64 SAL interface [7]. A host bridge consumes ECAM memory address space +and converts memory accesses into PCI configuration accesses. The spec +defines the ECAM address space layout and functionality; only the base of +the address space is device-specific. An ACPI OS learns the base address +from either the static MCFG table or a _CBA method in the PNP0A03 device. + +The MCFG table must describe the ECAM space of non-hot pluggable host +bridges [8]. Since MCFG is a static table and can't be updated by hotplug, +a _CBA method in the PNP0A03 device describes the ECAM space of a +hot-pluggable host bridge [9]. Note that for both MCFG and _CBA, the base +address always corresponds to bus 0, even if the bus range below the bridge +(which is reported via _CRS) doesn't start at 0. + + +[1] ACPI 6.2, sec 6.1: + For any device that is on a non-enumerable type of bus (for example, an + ISA bus), OSPM enumerates the devices' identifier(s) and the ACPI + system firmware must supply an _HID object ... for each device to + enable OSPM to do that. + +[2] ACPI 6.2, sec 3.7: + The OS enumerates motherboard devices simply by reading through the + ACPI Namespace looking for devices with hardware IDs. + + Each device enumerated by ACPI includes ACPI-defined objects in the + ACPI Namespace that report the hardware resources the device could + occupy [_PRS], an object that reports the resources that are currently + used by the device [_CRS], and objects for configuring those resources + [_SRS]. The information is used by the Plug and Play OS (OSPM) to + configure the devices. + +[3] ACPI 6.2, sec 6.2: + OSPM uses device configuration objects to configure hardware resources + for devices enumerated via ACPI. Device configuration objects provide + information about current and possible resource requirements, the + relationship between shared resources, and methods for configuring + hardware resources. + + When OSPM enumerates a device, it calls _PRS to determine the resource + requirements of the device. It may also call _CRS to find the current + resource settings for the device. Using this information, the Plug and + Play system determines what resources the device should consume and + sets those resources by calling the device’s _SRS control method. + + In ACPI, devices can consume resources (for example, legacy keyboards), + provide resources (for example, a proprietary PCI bridge), or do both. + Unless otherwise specified, resources for a device are assumed to be + taken from the nearest matching resource above the device in the device + hierarchy. + +[4] ACPI 6.2, sec 6.4.3.5.1, 2, 3, 4: + QWord/DWord/Word Address Space Descriptor (.1, .2, .3) + General Flags: Bit [0] Ignored + + Extended Address Space Descriptor (.4) + General Flags: Bit [0] Consumer/Producer: + 1–This device consumes this resource + 0–This device produces and consumes this resource + +[5] ACPI 6.2, sec 19.6.43: + ResourceUsage specifies whether the Memory range is consumed by + this device (ResourceConsumer) or passed on to child devices + (ResourceProducer). If nothing is specified, then + ResourceConsumer is assumed. + +[6] PCI Firmware 3.2, sec 4.1.2: + If the operating system does not natively comprehend reserving the + MMCFG region, the MMCFG region must be reserved by firmware. The + address range reported in the MCFG table or by _CBA method (see Section + 4.1.3) must be reserved by declaring a motherboard resource. For most + systems, the motherboard resource would appear at the root of the ACPI + namespace (under \_SB) in a node with a _HID of EISAID (PNP0C02), and + the resources in this case should not be claimed in the root PCI bus’s + _CRS. The resources can optionally be returned in Int15 E820 or + EFIGetMemoryMap as reserved memory but must always be reported through + ACPI as a motherboard resource. + +[7] PCI Express 4.0, sec 7.2.2: + For systems that are PC-compatible, or that do not implement a + processor-architecture-specific firmware interface standard that allows + access to the Configuration Space, the ECAM is required as defined in + this section. + +[8] PCI Firmware 3.2, sec 4.1.2: + The MCFG table is an ACPI table that is used to communicate the base + addresses corresponding to the non-hot removable PCI Segment Groups + range within a PCI Segment Group available to the operating system at + boot. This is required for the PC-compatible systems. + + The MCFG table is only used to communicate the base addresses + corresponding to the PCI Segment Groups available to the system at + boot. + +[9] PCI Firmware 3.2, sec 4.1.3: + The _CBA (Memory mapped Configuration Base Address) control method is + an optional ACPI object that returns the 64-bit memory mapped + configuration base address for the hot plug capable host bridge. The + base address returned by _CBA is processor-relative address. The _CBA + control method evaluates to an Integer. + + This control method appears under a host bridge object. When the _CBA + method appears under an active host bridge object, the operating system + evaluates this structure to identify the memory mapped configuration + base address corresponding to the PCI Segment Group for the bus number + range specified in _CRS method. An ACPI name space object that contains + the _CBA method must also contain a corresponding _SEG method. diff --git a/Documentation/PCI/endpoint/function/binding/pci-test.txt b/Documentation/PCI/endpoint/function/binding/pci-test.txt index 3b68b955fb50..cd76ba47394b 100644 --- a/Documentation/PCI/endpoint/function/binding/pci-test.txt +++ b/Documentation/PCI/endpoint/function/binding/pci-test.txt @@ -15,3 +15,5 @@ subsys_id : don't care interrupt_pin : Should be 1 - INTA, 2 - INTB, 3 - INTC, 4 -INTD msi_interrupts : Should be 1 to 32 depending on the number of MSI interrupts to test +msix_interrupts : Should be 1 to 2048 depending on the number of MSI-X + interrupts to test diff --git a/Documentation/PCI/endpoint/pci-endpoint.txt b/Documentation/PCI/endpoint/pci-endpoint.txt index 9b1d66829290..e86a96b66a6a 100644 --- a/Documentation/PCI/endpoint/pci-endpoint.txt +++ b/Documentation/PCI/endpoint/pci-endpoint.txt @@ -44,7 +44,7 @@ by the PCI controller driver. * clear_bar: ops to reset the BAR * alloc_addr_space: ops to allocate in PCI controller address space * free_addr_space: ops to free the allocated address space - * raise_irq: ops to raise a legacy or MSI interrupt + * raise_irq: ops to raise a legacy, MSI or MSI-X interrupt * start: ops to start the PCI link * stop: ops to stop the PCI link @@ -96,7 +96,7 @@ by the PCI endpoint function driver. *) pci_epc_raise_irq() The PCI endpoint function driver should use pci_epc_raise_irq() to raise - Legacy Interrupt or MSI Interrupt. + Legacy Interrupt, MSI or MSI-X Interrupt. *) pci_epc_mem_alloc_addr() diff --git a/Documentation/PCI/endpoint/pci-test-function.txt b/Documentation/PCI/endpoint/pci-test-function.txt index 0c519c9bf94a..5916f1f592bb 100644 --- a/Documentation/PCI/endpoint/pci-test-function.txt +++ b/Documentation/PCI/endpoint/pci-test-function.txt @@ -20,6 +20,8 @@ The PCI endpoint test device has the following registers: 5) PCI_ENDPOINT_TEST_DST_ADDR 6) PCI_ENDPOINT_TEST_SIZE 7) PCI_ENDPOINT_TEST_CHECKSUM + 8) PCI_ENDPOINT_TEST_IRQ_TYPE + 9) PCI_ENDPOINT_TEST_IRQ_NUMBER *) PCI_ENDPOINT_TEST_MAGIC @@ -34,10 +36,10 @@ that the endpoint device must perform. Bitfield Description: Bit 0 : raise legacy IRQ Bit 1 : raise MSI IRQ - Bit 2 - 7 : MSI interrupt number - Bit 8 : read command (read data from RC buffer) - Bit 9 : write command (write data to RC buffer) - Bit 10 : copy command (copy data from one RC buffer to another + Bit 2 : raise MSI-X IRQ + Bit 3 : read command (read data from RC buffer) + Bit 4 : write command (write data to RC buffer) + Bit 5 : copy command (copy data from one RC buffer to another RC buffer) *) PCI_ENDPOINT_TEST_STATUS @@ -64,3 +66,22 @@ COPY/READ command. This register contains the destination address (RC buffer address) for the COPY/WRITE command. + +*) PCI_ENDPOINT_TEST_IRQ_TYPE + +This register contains the interrupt type (Legacy/MSI) triggered +for the READ/WRITE/COPY and raise IRQ (Legacy/MSI) commands. + +Possible types: + - Legacy : 0 + - MSI : 1 + - MSI-X : 2 + +*) PCI_ENDPOINT_TEST_IRQ_NUMBER + +This register contains the triggered ID interrupt. + +Admissible values: + - Legacy : 0 + - MSI : [1 .. 32] + - MSI-X : [1 .. 2048] diff --git a/Documentation/PCI/endpoint/pci-test-howto.txt b/Documentation/PCI/endpoint/pci-test-howto.txt index 75f48c3bb191..e40cf0fb58d7 100644 --- a/Documentation/PCI/endpoint/pci-test-howto.txt +++ b/Documentation/PCI/endpoint/pci-test-howto.txt @@ -45,9 +45,9 @@ The PCI endpoint framework populates the directory with the following configurable fields. # ls functions/pci_epf_test/func1 - baseclass_code interrupt_pin revid subsys_vendor_id - cache_line_size msi_interrupts subclass_code vendorid - deviceid progif_code subsys_id + baseclass_code interrupt_pin progif_code subsys_id + cache_line_size msi_interrupts revid subsys_vendorid + deviceid msix_interrupts subclass_code vendorid The PCI endpoint function driver populates these entries with default values when the device is bound to the driver. The pci-epf-test driver populates @@ -67,6 +67,7 @@ device, the following commands can be used. # echo 0x104c > functions/pci_epf_test/func1/vendorid # echo 0xb500 > functions/pci_epf_test/func1/deviceid # echo 16 > functions/pci_epf_test/func1/msi_interrupts + # echo 8 > functions/pci_epf_test/func1/msix_interrupts 1.5 Binding pci-epf-test Device to EP Controller @@ -120,7 +121,9 @@ following commands. Interrupt tests + SET IRQ TYPE TO LEGACY: OKAY LEGACY IRQ: NOT OKAY + SET IRQ TYPE TO MSI: OKAY MSI1: OKAY MSI2: OKAY MSI3: OKAY @@ -153,9 +156,30 @@ following commands. MSI30: NOT OKAY MSI31: NOT OKAY MSI32: NOT OKAY + SET IRQ TYPE TO MSI-X: OKAY + MSI-X1: OKAY + MSI-X2: OKAY + MSI-X3: OKAY + MSI-X4: OKAY + MSI-X5: OKAY + MSI-X6: OKAY + MSI-X7: OKAY + MSI-X8: OKAY + MSI-X9: NOT OKAY + MSI-X10: NOT OKAY + MSI-X11: NOT OKAY + MSI-X12: NOT OKAY + MSI-X13: NOT OKAY + MSI-X14: NOT OKAY + MSI-X15: NOT OKAY + MSI-X16: NOT OKAY + [...] + MSI-X2047: NOT OKAY + MSI-X2048: NOT OKAY Read Tests + SET IRQ TYPE TO MSI: OKAY READ ( 1 bytes): OKAY READ ( 1024 bytes): OKAY READ ( 1025 bytes): OKAY diff --git a/Documentation/PCI/pcieaer-howto.txt b/Documentation/PCI/pcieaer-howto.txt index acd0dddd6bb8..48ce7903e3c6 100644 --- a/Documentation/PCI/pcieaer-howto.txt +++ b/Documentation/PCI/pcieaer-howto.txt @@ -73,6 +73,11 @@ In the example, 'Requester ID' means the ID of the device who sends the error message to root port. Pls. refer to pci express specs for other fields. +2.4 AER Statistics / Counters + +When PCIe AER errors are captured, the counters / statistics are also exposed +in the form of sysfs attributes which are documented at +Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats 3. Developer Guide diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 0c883029881a..adafe47ac376 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3089,8 +3089,31 @@ See header of drivers/block/paride/pcd.c. See also Documentation/blockdev/paride.txt. - pci=option[,option...] [PCI] various PCI subsystem options: - earlydump [X86] dump PCI config space before the kernel + pci=option[,option...] [PCI] various PCI subsystem options. + + Some options herein operate on a specific device + or a set of devices (<pci_dev>). These are + specified in one of the following formats: + + [<domain>:]<bus>:<dev>.<func>[/<dev>.<func>]* + pci:<vendor>:<device>[:<subvendor>:<subdevice>] + + Note: the first format specifies a PCI + bus/device/function address which may change + if new hardware is inserted, if motherboard + firmware changes, or due to changes caused + by other kernel parameters. If the + domain is left unspecified, it is + taken to be zero. Optionally, a path + to a device through multiple device/function + addresses can be specified after the base + address (this is more robust against + renumbering issues). The second format + selects devices using IDs from the + configuration space which may match multiple + devices in the system. + + earlydump dump PCI config space before the kernel changes anything off [X86] don't probe for the PCI bus bios [X86-32] force use of PCI BIOS, don't access @@ -3218,11 +3241,10 @@ window. The default value is 64 megabytes. resource_alignment= Format: - [<order of align>@][<domain>:]<bus>:<slot>.<func>[; ...] - [<order of align>@]pci:<vendor>:<device>\ - [:<subvendor>:<subdevice>][; ...] + [<order of align>@]<pci_dev>[; ...] Specifies alignment and device to reassign - aligned memory resources. + aligned memory resources. How to + specify the device is described above. If <order of align> is not specified, PAGE_SIZE is used as alignment. PCI-PCI bridge can be specified, if resource @@ -3265,6 +3287,15 @@ Adding the window is slightly risky (it may conflict with unreported devices), so this taints the kernel. + disable_acs_redir=<pci_dev>[; ...] + Specify one or more PCI devices (in the format + specified above) separated by semicolons. + Each device specified will have the PCI ACS + redirect capabilities forced off which will + allow P2P traffic between devices through + bridges without forcing it upstream. Note: + this removes isolation between devices and + may put more devices in an IOMMU group. pcie_aspm= [PCIE] Forcibly enable or disable PCIe Active State Power Management. diff --git a/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-ep.txt b/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-ep.txt index 9a305237fa6e..4a0475e2ba7e 100644 --- a/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-ep.txt +++ b/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-ep.txt @@ -9,6 +9,9 @@ Required properties: Optional properties: - max-functions: Maximum number of functions that can be configured (default 1). +- phys: From PHY bindings: List of Generic PHY phandles. One per lane if more + than one in the list. If only one PHY listed it must manage all lanes. +- phy-names: List of names to identify the PHY. Example: @@ -19,4 +22,6 @@ pcie@fc000000 { reg-names = "reg", "mem"; cdns,max-outbound-regions = <16>; max-functions = /bits/ 8 <8>; + phys = <&ep_phy0 &ep_phy1>; + phy-names = "pcie-lane0","pcie-lane1"; }; diff --git a/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-host.txt b/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-host.txt index 20a33f38f69d..91de69c713a9 100644 --- a/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-host.txt +++ b/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-host.txt @@ -24,6 +24,9 @@ Optional properties: translations (default 32) - vendor-id: The PCI vendor ID (16 bits, default is design dependent) - device-id: The PCI device ID (16 bits, default is design dependent) +- phys: From PHY bindings: List of Generic PHY phandles. One per lane if more + than one in the list. If only one PHY listed it must manage all lanes. +- phy-names: List of names to identify the PHY. Example: @@ -57,4 +60,7 @@ pcie@fb000000 { interrupt-map-mask = <0x0 0x0 0x0 0x7>; msi-parent = <&its_pci>; + + phys = <&pcie_phy0>; + phy-names = "pcie-phy"; }; diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index 9aeb5f0ea701..d6ed527985cf 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -166,6 +166,7 @@ Code Seq#(hex) Include File Comments 'P' all linux/soundcard.h conflict! 'P' 60-6F sound/sscape_ioctl.h conflict! 'P' 00-0F drivers/usb/class/usblp.c conflict! +'P' 01-09 drivers/misc/pci_endpoint_test.c conflict! 'Q' all linux/soundcard.h 'R' 00-1F linux/random.h conflict! 'R' 01 linux/rfkill.h conflict! diff --git a/Documentation/misc-devices/pci-endpoint-test.txt b/Documentation/misc-devices/pci-endpoint-test.txt index 4ebc3594b32c..58ccca4416b1 100644 --- a/Documentation/misc-devices/pci-endpoint-test.txt +++ b/Documentation/misc-devices/pci-endpoint-test.txt @@ -10,6 +10,7 @@ The PCI driver for the test device performs the following tests *) verifying addresses programmed in BAR *) raise legacy IRQ *) raise MSI IRQ + *) raise MSI-X IRQ *) read data *) write data *) copy data @@ -25,6 +26,11 @@ ioctl PCITEST_LEGACY_IRQ: Tests legacy IRQ PCITEST_MSI: Tests message signalled interrupts. The MSI number to be tested should be passed as argument. + PCITEST_MSIX: Tests message signalled interrupts. The MSI-X number + to be tested should be passed as argument. + PCITEST_SET_IRQTYPE: Changes driver IRQ type configuration. The IRQ type + should be passed as argument (0: Legacy, 1:MSI, 2:MSI-X). + PCITEST_GET_IRQTYPE: Gets driver IRQ type configuration. PCITEST_WRITE: Perform write tests. The size of the buffer should be passed as argument. PCITEST_READ: Perform read tests. The size of the buffer should be passed diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 155170d70324..dbfc7056d7df 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -357,9 +357,6 @@ EXPORT_SYMBOL_GPL(dma_get_required_mask); static int __init dma_init(void) { -#ifdef CONFIG_PCI - dma_debug_add_bus(&pci_bus_type); -#endif #ifdef CONFIG_IBMVIO dma_debug_add_bus(&vio_bus_type); #endif diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c index e5b7437ab4af..8256626bc53c 100644 --- a/arch/sh/drivers/pci/pci.c +++ b/arch/sh/drivers/pci/pci.c @@ -160,8 +160,6 @@ static int __init pcibios_init(void) for (hose = hose_head; hose; hose = hose->next) pcibios_scanbus(hose); - dma_debug_add_bus(&pci_bus_type); - pci_initialized = 1; return 0; diff --git a/arch/x86/include/asm/pci-direct.h b/arch/x86/include/asm/pci-direct.h index e1084f71a295..94597a3cf3d0 100644 --- a/arch/x86/include/asm/pci-direct.h +++ b/arch/x86/include/asm/pci-direct.h @@ -15,8 +15,4 @@ extern void write_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset, u8 val); extern void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val); extern int early_pci_allowed(void); - -extern unsigned int pci_early_dump_regs; -extern void early_dump_pci_device(u8 bus, u8 slot, u8 func); -extern void early_dump_pci_devices(void); #endif /* _ASM_X86_PCI_DIRECT_H */ diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 80f9fe8d27d0..acfd04121da3 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -155,9 +155,6 @@ static int __init pci_iommu_init(void) { struct iommu_table_entry *p; -#ifdef CONFIG_PCI - dma_debug_add_bus(&pci_bus_type); -#endif x86_init.iommu.iommu_init(); for (p = __iommu_table; p < __iommu_table_end; p++) { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 8fe740e22030..b4866badb235 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -999,11 +999,6 @@ void __init setup_arch(char **cmdline_p) setup_clear_cpu_cap(X86_FEATURE_APIC); } -#ifdef CONFIG_PCI - if (pci_early_dump_regs) - early_dump_pci_devices(); -#endif - e820__reserve_setup_data(); e820__finish_early_params(); diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 563049c483a1..d4ec117c1142 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -22,7 +22,6 @@ unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 | PCI_PROBE_MMCONF; -unsigned int pci_early_dump_regs; static int pci_bf_sort; int pci_routeirq; int noioapicquirk; @@ -599,9 +598,6 @@ char *__init pcibios_setup(char *str) pci_probe |= PCI_BIG_ROOT_WINDOW; return NULL; #endif - } else if (!strcmp(str, "earlydump")) { - pci_early_dump_regs = 1; - return NULL; } else if (!strcmp(str, "routeirq")) { pci_routeirq = 1; return NULL; diff --git a/arch/x86/pci/early.c b/arch/x86/pci/early.c index e5f753cbb1c3..f5fc953e5848 100644 --- a/arch/x86/pci/early.c +++ b/arch/x86/pci/early.c @@ -57,47 +57,3 @@ int early_pci_allowed(void) PCI_PROBE_CONF1; } -void early_dump_pci_device(u8 bus, u8 slot, u8 func) -{ - u32 value[256 / 4]; - int i; - - pr_info("pci 0000:%02x:%02x.%d config space:\n", bus, slot, func); - - for (i = 0; i < 256; i += 4) - value[i / 4] = read_pci_config(bus, slot, func, i); - - print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 1, value, 256, false); -} - -void early_dump_pci_devices(void) -{ - unsigned bus, slot, func; - - if (!early_pci_allowed()) - return; - - for (bus = 0; bus < 256; bus++) { - for (slot = 0; slot < 32; slot++) { - for (func = 0; func < 8; func++) { - u32 class; - u8 type; - - class = read_pci_config(bus, slot, func, - PCI_CLASS_REVISION); - if (class == 0xffffffff) - continue; - - early_dump_pci_device(bus, slot, func); - - if (func == 0) { - type = read_pci_config_byte(bus, slot, - func, - PCI_HEADER_TYPE); - if (!(type & 0x80)) - break; - } - } - } - } -} diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index 4d4371bf2c7c..baf7c324f7b8 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -905,9 +905,7 @@ static int trigger_sbr(struct hfi1_devdata *dd) * delay after a reset is required. Per spec requirements, * the link is either working or not after that point. */ - pci_reset_bridge_secondary_bus(dev->bus->self); - - return 0; + return pci_reset_bus(dev); } /* diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c index 7b370466a227..896e2df9400f 100644 --- a/drivers/misc/pci_endpoint_test.c +++ b/drivers/misc/pci_endpoint_test.c @@ -35,38 +35,45 @@ #include <uapi/linux/pcitest.h> -#define DRV_MODULE_NAME "pci-endpoint-test" - -#define PCI_ENDPOINT_TEST_MAGIC 0x0 - -#define PCI_ENDPOINT_TEST_COMMAND 0x4 -#define COMMAND_RAISE_LEGACY_IRQ BIT(0) -#define COMMAND_RAISE_MSI_IRQ BIT(1) -#define MSI_NUMBER_SHIFT 2 -/* 6 bits for MSI number */ -#define COMMAND_READ BIT(8) -#define COMMAND_WRITE BIT(9) -#define COMMAND_COPY BIT(10) - -#define PCI_ENDPOINT_TEST_STATUS 0x8 -#define STATUS_READ_SUCCESS BIT(0) -#define STATUS_READ_FAIL BIT(1) -#define STATUS_WRITE_SUCCESS BIT(2) -#define STATUS_WRITE_FAIL BIT(3) -#define STATUS_COPY_SUCCESS BIT(4) -#define STATUS_COPY_FAIL BIT(5) -#define STATUS_IRQ_RAISED BIT(6) -#define STATUS_SRC_ADDR_INVALID BIT(7) -#define STATUS_DST_ADDR_INVALID BIT(8) - -#define PCI_ENDPOINT_TEST_LOWER_SRC_ADDR 0xc +#define DRV_MODULE_NAME "pci-endpoint-test" + +#define IRQ_TYPE_UNDEFINED -1 +#define IRQ_TYPE_LEGACY 0 +#define IRQ_TYPE_MSI 1 +#define IRQ_TYPE_MSIX 2 + +#define PCI_ENDPOINT_TEST_MAGIC 0x0 + +#define PCI_ENDPOINT_TEST_COMMAND 0x4 +#define COMMAND_RAISE_LEGACY_IRQ BIT(0) +#define COMMAND_RAISE_MSI_IRQ BIT(1) +#define COMMAND_RAISE_MSIX_IRQ BIT(2) +#define COMMAND_READ BIT(3) +#define COMMAND_WRITE BIT(4) +#define COMMAND_COPY BIT(5) + +#define PCI_ENDPOINT_TEST_STATUS 0x8 +#define STATUS_READ_SUCCESS BIT(0) +#define STATUS_READ_FAIL BIT(1) +#define STATUS_WRITE_SUCCESS BIT(2) +#define STATUS_WRITE_FAIL BIT(3) +#define STATUS_COPY_SUCCESS BIT(4) +#define STATUS_COPY_FAIL BIT(5) +#define STATUS_IRQ_RAISED BIT(6) +#define STATUS_SRC_ADDR_INVALID BIT(7) +#define STATUS_DST_ADDR_INVALID BIT(8) + +#define PCI_ENDPOINT_TEST_LOWER_SRC_ADDR 0x0c #define PCI_ENDPOINT_TEST_UPPER_SRC_ADDR 0x10 #define PCI_ENDPOINT_TEST_LOWER_DST_ADDR 0x14 #define PCI_ENDPOINT_TEST_UPPER_DST_ADDR 0x18 -#define PCI_ENDPOINT_TEST_SIZE 0x1c -#define PCI_ENDPOINT_TEST_CHECKSUM 0x20 +#define PCI_ENDPOINT_TEST_SIZE 0x1c +#define PCI_ENDPOINT_TEST_CHECKSUM 0x20 + +#define PCI_ENDPOINT_TEST_IRQ_TYPE 0x24 +#define PCI_ENDPOINT_TEST_IRQ_NUMBER 0x28 static DEFINE_IDA(pci_endpoint_test_ida); @@ -77,6 +84,10 @@ static bool no_msi; module_param(no_msi, bool, 0444); MODULE_PARM_DESC(no_msi, "Disable MSI interrupt in pci_endpoint_test"); +static int irq_type = IRQ_TYPE_MSI; +module_param(irq_type, int, 0444); +MODULE_PARM_DESC(irq_type, "IRQ mode selection in pci_endpoint_test (0 - Legacy, 1 - MSI, 2 - MSI-X)"); + enum pci_barno { BAR_0, BAR_1, @@ -103,7 +114,7 @@ struct pci_endpoint_test { struct pci_endpoint_test_data { enum pci_barno test_reg_bar; size_t alignment; - bool no_msi; + int irq_type; }; static inline u32 pci_endpoint_test_readl(struct pci_endpoint_test *test, @@ -147,6 +158,100 @@ static irqreturn_t pci_endpoint_test_irqhandler(int irq, void *dev_id) return IRQ_HANDLED; } +static void pci_endpoint_test_free_irq_vectors(struct pci_endpoint_test *test) +{ + struct pci_dev *pdev = test->pdev; + + pci_free_irq_vectors(pdev); +} + +static bool pci_endpoint_test_alloc_irq_vectors(struct pci_endpoint_test *test, + int type) +{ + int irq = -1; + struct pci_dev *pdev = test->pdev; + struct device *dev = &pdev->dev; + bool res = true; + + switch (type) { + case IRQ_TYPE_LEGACY: + irq = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_LEGACY); + if (irq < 0) + dev_err(dev, "Failed to get Legacy interrupt\n"); + break; + case IRQ_TYPE_MSI: + irq = pci_alloc_irq_vectors(pdev, 1, 32, PCI_IRQ_MSI); + if (irq < 0) + dev_err(dev, "Failed to get MSI interrupts\n"); + break; + case IRQ_TYPE_MSIX: + irq = pci_alloc_irq_vectors(pdev, 1, 2048, PCI_IRQ_MSIX); + if (irq < 0) + dev_err(dev, "Failed to get MSI-X interrupts\n"); + break; + default: + dev_err(dev, "Invalid IRQ type selected\n"); + } + + if (irq < 0) { + irq = 0; + res = false; + } + test->num_irqs = irq; + + return res; +} + +static void pci_endpoint_test_release_irq(struct pci_endpoint_test *test) +{ + int i; + struct pci_dev *pdev = test->pdev; + struct device *dev = &pdev->dev; + + for (i = 0; i < test->num_irqs; i++) + devm_free_irq(dev, pci_irq_vector(pdev, i), test); + + test->num_irqs = 0; +} + +static bool pci_endpoint_test_request_irq(struct pci_endpoint_test *test) +{ + int i; + int err; + struct pci_dev *pdev = test->pdev; + struct device *dev = &pdev->dev; + + for (i = 0; i < test->num_irqs; i++) { + err = devm_request_irq(dev, pci_irq_vector(pdev, i), + pci_endpoint_test_irqhandler, + IRQF_SHARED, DRV_MODULE_NAME, test); + if (err) + goto fail; + } + + return true; + +fail: + switch (irq_type) { + case IRQ_TYPE_LEGACY: + dev_err(dev, "Failed to request IRQ %d for Legacy\n", + pci_irq_vector(pdev, i)); + break; + case IRQ_TYPE_MSI: + dev_err(dev, "Failed to request IRQ %d for MSI %d\n", + pci_irq_vector(pdev, i), + i + 1); + break; + case IRQ_TYPE_MSIX: + dev_err(dev, "Failed to request IRQ %d for MSI-X %d\n", + pci_irq_vector(pdev, i), + i + 1); + break; + } + + return false; +} + static bool pci_endpoint_test_bar(struct pci_endpoint_test *test, enum pci_barno barno) { @@ -179,6 +284,9 @@ static bool pci_endpoint_test_legacy_irq(struct pci_endpoint_test *test) { u32 val; + pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE, + IRQ_TYPE_LEGACY); + pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 0); pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND, COMMAND_RAISE_LEGACY_IRQ); val = wait_for_completion_timeout(&test->irq_raised, @@ -190,14 +298,18 @@ static bool pci_endpoint_test_legacy_irq(struct pci_endpoint_test *test) } static bool pci_endpoint_test_msi_irq(struct pci_endpoint_test *test, - u8 msi_num) + u16 msi_num, bool msix) { u32 val; struct pci_dev *pdev = test->pdev; + pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE, + msix == false ? IRQ_TYPE_MSI : + IRQ_TYPE_MSIX); + pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, msi_num); pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND, - msi_num << MSI_NUMBER_SHIFT | - COMMAND_RAISE_MSI_IRQ); + msix == false ? COMMAND_RAISE_MSI_IRQ : + COMMAND_RAISE_MSIX_IRQ); val = wait_for_completion_timeout(&test->irq_raised, msecs_to_jiffies(1000)); if (!val) @@ -230,6 +342,11 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test, size_t size) if (size > SIZE_MAX - alignment) goto err; + if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) { + dev_err(dev, "Invalid IRQ type option\n"); + goto err; + } + orig_src_addr = dma_alloc_coherent(dev, size + alignment, &orig_src_phys_addr, GFP_KERNEL); if (!orig_src_addr) { @@ -281,8 +398,10 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test, size_t size) pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_SIZE, size); + pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE, irq_type); + pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 1); pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND, - 1 << MSI_NUMBER_SHIFT | COMMAND_COPY); + COMMAND_COPY); wait_for_completion(&test->irq_raised); @@ -318,6 +437,11 @@ static bool pci_endpoint_test_write(struct pci_endpoint_test *test, size_t size) if (size > SIZE_MAX - alignment) goto err; + if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) { + dev_err(dev, "Invalid IRQ type option\n"); + goto err; + } + orig_addr = dma_alloc_coherent(dev, size + alignment, &orig_phys_addr, GFP_KERNEL); if (!orig_addr) { @@ -348,8 +472,10 @@ static bool pci_endpoint_test_write(struct pci_endpoint_test *test, size_t size) pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_SIZE, size); + pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE, irq_type); + pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 1); pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND, - 1 << MSI_NUMBER_SHIFT | COMMAND_READ); + COMMAND_READ); wait_for_completion(&test->irq_raised); @@ -379,6 +505,11 @@ static bool pci_endpoint_test_read(struct pci_endpoint_test *test, size_t size) if (size > SIZE_MAX - alignment) goto err; + if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) { + dev_err(dev, "Invalid IRQ type option\n"); + goto err; + } + orig_addr = dma_alloc_coherent(dev, size + alignment, &orig_phys_addr, GFP_KERNEL); if (!orig_addr) { @@ -403,8 +534,10 @@ static bool pci_endpoint_test_read(struct pci_endpoint_test *test, size_t size) pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_SIZE, size); + pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE, irq_type); + pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 1); pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND, - 1 << MSI_NUMBER_SHIFT | COMMAND_WRITE); + COMMAND_WRITE); wait_for_completion(&test->irq_raised); @@ -417,6 +550,38 @@ err: return ret; } +static bool pci_endpoint_test_set_irq(struct pci_endpoint_test *test, + int req_irq_type) +{ + struct pci_dev *pdev = test->pdev; + struct device *dev = &pdev->dev; + + if (req_irq_type < IRQ_TYPE_LEGACY || req_irq_type > IRQ_TYPE_MSIX) { + dev_err(dev, "Invalid IRQ type option\n"); + return false; + } + + if (irq_type == req_irq_type) + return true; + + pci_endpoint_test_release_irq(test); + pci_endpoint_test_free_irq_vectors(test); + + if (!pci_endpoint_test_alloc_irq_vectors(test, req_irq_type)) + goto err; + + if (!pci_endpoint_test_request_irq(test)) + goto err; + + irq_type = req_irq_type; + return true; + +err: + pci_endpoint_test_free_irq_vectors(test); + irq_type = IRQ_TYPE_UNDEFINED; + return false; +} + static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -436,7 +601,8 @@ static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd, ret = pci_endpoint_test_legacy_irq(test); break; case PCITEST_MSI: - ret = pci_endpoint_test_msi_irq(test, arg); + case PCITEST_MSIX: + ret = pci_endpoint_test_msi_irq(test, arg, cmd == PCITEST_MSIX); break; case PCITEST_WRITE: ret = pci_endpoint_test_write(test, arg); @@ -447,6 +613,12 @@ static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd, case PCITEST_COPY: ret = pci_endpoint_test_copy(test, arg); break; + case PCITEST_SET_IRQTYPE: + ret = pci_endpoint_test_set_irq(test, arg); + break; + case PCITEST_GET_IRQTYPE: + ret = irq_type; + break; } ret: @@ -462,9 +634,7 @@ static const struct file_operations pci_endpoint_test_fops = { static int pci_endpoint_test_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { - int i; int err; - int irq = 0; int id; char name[20]; enum pci_barno bar; @@ -486,11 +656,14 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev, test->alignment = 0; test->pdev = pdev; + if (no_msi) + irq_type = IRQ_TYPE_LEGACY; + data = (struct pci_endpoint_test_data *)ent->driver_data; if (data) { test_reg_bar = data->test_reg_bar; test->alignment = data->alignment; - no_msi = data->no_msi; + irq_type = data->irq_type; } init_completion(&test->irq_raised); @@ -510,28 +683,11 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev, pci_set_master(pdev); - if (!no_msi) { - irq = pci_alloc_irq_vectors(pdev, 1, 32, PCI_IRQ_MSI); - if (irq < 0) - dev_err(dev, "Failed to get MSI interrupts\n"); - test->num_irqs = irq; - } - - err = devm_request_irq(dev, pdev->irq, pci_endpoint_test_irqhandler, - IRQF_SHARED, DRV_MODULE_NAME, test); - if (err) { - dev_err(dev, "Failed to request IRQ %d\n", pdev->irq); - goto err_disable_msi; - } + if (!pci_endpoint_test_alloc_irq_vectors(test, irq_type)) + goto err_disable_irq; - for (i = 1; i < irq; i++) { - err = devm_request_irq(dev, pci_irq_vector(pdev, i), - pci_endpoint_test_irqhandler, - IRQF_SHARED, DRV_MODULE_NAME, test); - if (err) - dev_err(dev, "failed to request IRQ %d for MSI %d\n", - pci_irq_vector(pdev, i), i + 1); - } + if (!pci_endpoint_test_request_irq(test)) + goto err_disable_irq; for (bar = BAR_0; bar <= BAR_5; bar++) { if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) { @@ -590,12 +746,10 @@ err_iounmap: if (test->bar[bar]) pci_iounmap(pdev, test->bar[bar]); } + pci_endpoint_test_release_irq(test); - for (i = 0; i < irq; i++) - devm_free_irq(&pdev->dev, pci_irq_vector(pdev, i), test); - -err_disable_msi: - pci_disable_msi(pdev); +err_disable_irq: + pci_endpoint_test_free_irq_vectors(test); pci_release_regions(pdev); err_disable_pdev: @@ -607,7 +761,6 @@ err_disable_pdev: static void pci_endpoint_test_remove(struct pci_dev *pdev) { int id; - int i; enum pci_barno bar; struct pci_endpoint_test *test = pci_get_drvdata(pdev); struct miscdevice *misc_device = &test->miscdev; @@ -624,9 +777,10 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev) if (test->bar[bar]) pci_iounmap(pdev, test->bar[bar]); } - for (i = 0; i < test->num_irqs; i++) - devm_free_irq(&pdev->dev, pci_irq_vector(pdev, i), test); - pci_disable_msi(pdev); + + pci_endpoint_test_release_irq(test); + pci_endpoint_test_free_irq_vectors(test); + pci_release_regions(pdev); pci_disable_device(pdev); } diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 221a735dc956..d03c2f0d7592 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -22,7 +22,6 @@ #include <linux/if.h> #include <linux/if_vlan.h> #include <linux/pci.h> -#include <linux/pci-aspm.h> #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/ip.h> diff --git a/drivers/net/wireless/ath/ath9k/pci.c b/drivers/net/wireless/ath/ath9k/pci.c index 645f0fbd9179..92b2dd396436 100644 --- a/drivers/net/wireless/ath/ath9k/pci.c +++ b/drivers/net/wireless/ath/ath9k/pci.c @@ -18,7 +18,6 @@ #include <linux/nl80211.h> #include <linux/pci.h> -#include <linux/pci-aspm.h> #include <linux/module.h> #include "ath9k.h" diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 562cc79288a6..b150da4c6721 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -72,7 +72,6 @@ #include <linux/module.h> #include <linux/pm_runtime.h> #include <linux/pci.h> -#include <linux/pci-aspm.h> #include <linux/acpi.h> #include "fw/acpi.h" diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00pci.h b/drivers/net/wireless/ralink/rt2x00/rt2x00pci.h index bc0ca5f58f38..283e2e607bba 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00pci.h +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00pci.h @@ -28,12 +28,6 @@ #include <linux/pci.h> /* - * This variable should be used with the - * pci_driver structure initialization. - */ -#define PCI_DEVICE_DATA(__ops) .driver_data = (kernel_ulong_t)(__ops) - -/* * PCI driver handlers. */ int rt2x00pci_probe(struct pci_dev *pci_dev, const struct rt2x00_ops *ops); diff --git a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c index f624ae27eabe..5ee5f40b4dfc 100644 --- a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c +++ b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c @@ -19,6 +19,7 @@ #include <linux/kthread.h> #include <linux/interrupt.h> #include <linux/ntb.h> +#include <linux/pci.h> MODULE_DESCRIPTION("Microsemi Switchtec(tm) NTB Driver"); MODULE_VERSION("0.1"); @@ -1487,7 +1488,7 @@ static int switchtec_ntb_add(struct device *dev, stdev->sndev = NULL; - if (stdev->pdev->class != MICROSEMI_NTB_CLASSCODE) + if (stdev->pdev->class != (PCI_CLASS_BRIDGE_OTHER << 8)) return -ENODEV; sndev = kzalloc_node(sizeof(*sndev), GFP_KERNEL, dev_to_node(dev)); diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index 4923a2a8e14b..5b78f3b1b918 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -273,6 +273,9 @@ int pci_enable_pasid(struct pci_dev *pdev, int features) if (WARN_ON(pdev->pasid_enabled)) return -EBUSY; + if (!pdev->eetlp_prefix_path) + return -EINVAL; + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID); if (!pos) return -EINVAL; diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig index cc9fa02d32a0..028b287466fb 100644 --- a/drivers/pci/controller/Kconfig +++ b/drivers/pci/controller/Kconfig @@ -102,7 +102,7 @@ config PCI_HOST_GENERIC config PCIE_XILINX bool "Xilinx AXI PCIe host bridge support" - depends on ARCH_ZYNQ || MICROBLAZE || (MIPS && PCI_DRIVERS_GENERIC) || COMPILE_TEST + depends on OF || COMPILE_TEST help Say 'Y' here if you want kernel to support the Xilinx AXI PCIe Host Bridge driver. @@ -239,6 +239,16 @@ config PCIE_MEDIATEK Say Y here if you want to enable PCIe controller support on MediaTek SoCs. +config PCIE_MOBIVEIL + bool "Mobiveil AXI PCIe controller" + depends on ARCH_ZYNQMP || COMPILE_TEST + depends on OF + depends on PCI_MSI_IRQ_DOMAIN + help + Say Y here if you want to enable support for the Mobiveil AXI PCIe + Soft IP. It has up to 8 outbound and inbound windows + for address translation and it is a PCIe Gen4 IP. + config PCIE_TANGO_SMP8759 bool "Tango SMP8759 PCIe controller (DANGEROUS)" depends on ARCH_TANGO && PCI_MSI && OF diff --git a/drivers/pci/controller/Makefile b/drivers/pci/controller/Makefile index 24322b92f200..d56a507495c5 100644 --- a/drivers/pci/controller/Makefile +++ b/drivers/pci/controller/Makefile @@ -26,6 +26,7 @@ obj-$(CONFIG_PCIE_ROCKCHIP) += pcie-rockchip.o obj-$(CONFIG_PCIE_ROCKCHIP_EP) += pcie-rockchip-ep.o obj-$(CONFIG_PCIE_ROCKCHIP_HOST) += pcie-rockchip-host.o obj-$(CONFIG_PCIE_MEDIATEK) += pcie-mediatek.o +obj-$(CONFIG_PCIE_MOBIVEIL) += pcie-mobiveil.o obj-$(CONFIG_PCIE_TANGO_SMP8759) += pcie-tango.o obj-$(CONFIG_VMD) += vmd.o # pcie-hisi.o quirks are needed even without CONFIG_PCIE_DW diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c index 345aab56ce8b..ce9224a36f62 100644 --- a/drivers/pci/controller/dwc/pci-dra7xx.c +++ b/drivers/pci/controller/dwc/pci-dra7xx.c @@ -370,7 +370,7 @@ static void dra7xx_pcie_raise_msi_irq(struct dra7xx_pcie *dra7xx, } static int dra7xx_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, - enum pci_epc_irq_type type, u8 interrupt_num) + enum pci_epc_irq_type type, u16 interrupt_num) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c index 4cc1e5df8c79..cee5f2f590e2 100644 --- a/drivers/pci/controller/dwc/pci-exynos.c +++ b/drivers/pci/controller/dwc/pci-exynos.c @@ -421,7 +421,6 @@ static int __init exynos_add_pcie_port(struct exynos_pcie *ep, } } - pp->root_bus_nr = -1; pp->ops = &exynos_pcie_host_ops; ret = dw_pcie_host_init(pp); diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c index 80f604602783..4a9a673b4777 100644 --- a/drivers/pci/controller/dwc/pci-imx6.c +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -667,7 +667,6 @@ static int imx6_add_pcie_port(struct imx6_pcie *imx6_pcie, } } - pp->root_bus_nr = -1; pp->ops = &imx6_pcie_host_ops; ret = dw_pcie_host_init(pp); diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c index 3722a5f31e5e..e88bd221fffe 100644 --- a/drivers/pci/controller/dwc/pci-keystone.c +++ b/drivers/pci/controller/dwc/pci-keystone.c @@ -347,7 +347,6 @@ static int __init ks_add_pcie_port(struct keystone_pcie *ks_pcie, } } - pp->root_bus_nr = -1; pp->ops = &keystone_pcie_host_ops; ret = ks_dw_pcie_host_init(ks_pcie, ks_pcie->msi_intc_np); if (ret) { diff --git a/drivers/pci/controller/dwc/pcie-armada8k.c b/drivers/pci/controller/dwc/pcie-armada8k.c index 072fd7ecc29f..0c389a30ef5d 100644 --- a/drivers/pci/controller/dwc/pcie-armada8k.c +++ b/drivers/pci/controller/dwc/pcie-armada8k.c @@ -172,7 +172,6 @@ static int armada8k_add_pcie_port(struct armada8k_pcie *pcie, struct device *dev = &pdev->dev; int ret; - pp->root_bus_nr = -1; pp->ops = &armada8k_pcie_host_ops; pp->irq = platform_get_irq(pdev, 0); diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c index 321b56cfd5d0..dba83abfe764 100644 --- a/drivers/pci/controller/dwc/pcie-artpec6.c +++ b/drivers/pci/controller/dwc/pcie-artpec6.c @@ -399,7 +399,6 @@ static int artpec6_add_pcie_port(struct artpec6_pcie *artpec6_pcie, } } - pp->root_bus_nr = -1; pp->ops = &artpec6_pcie_host_ops; ret = dw_pcie_host_init(pp); @@ -428,7 +427,7 @@ static void artpec6_pcie_ep_init(struct dw_pcie_ep *ep) } static int artpec6_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, - enum pci_epc_irq_type type, u8 interrupt_num) + enum pci_epc_irq_type type, u16 interrupt_num) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index 8650416f6f9e..1e7b02221eac 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -40,6 +40,39 @@ void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar) __dw_pcie_ep_reset_bar(pci, bar, 0); } +static u8 __dw_pcie_ep_find_next_cap(struct dw_pcie *pci, u8 cap_ptr, + u8 cap) +{ + u8 cap_id, next_cap_ptr; + u16 reg; + + reg = dw_pcie_readw_dbi(pci, cap_ptr); + next_cap_ptr = (reg & 0xff00) >> 8; + cap_id = (reg & 0x00ff); + + if (!next_cap_ptr || cap_id > PCI_CAP_ID_MAX) + return 0; + + if (cap_id == cap) + return cap_ptr; + + return __dw_pcie_ep_find_next_cap(pci, next_cap_ptr, cap); +} + +static u8 dw_pcie_ep_find_capability(struct dw_pcie *pci, u8 cap) +{ + u8 next_cap_ptr; + u16 reg; + + reg = dw_pcie_readw_dbi(pci, PCI_CAPABILITY_LIST); + next_cap_ptr = (reg & 0x00ff); + + if (!next_cap_ptr) + return 0; + + return __dw_pcie_ep_find_next_cap(pci, next_cap_ptr, cap); +} + static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no, struct pci_epf_header *hdr) { @@ -213,36 +246,84 @@ static int dw_pcie_ep_map_addr(struct pci_epc *epc, u8 func_no, static int dw_pcie_ep_get_msi(struct pci_epc *epc, u8 func_no) { - int val; struct dw_pcie_ep *ep = epc_get_drvdata(epc); struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + u32 val, reg; + + if (!ep->msi_cap) + return -EINVAL; + + reg = ep->msi_cap + PCI_MSI_FLAGS; + val = dw_pcie_readw_dbi(pci, reg); + if (!(val & PCI_MSI_FLAGS_ENABLE)) + return -EINVAL; + + val = (val & PCI_MSI_FLAGS_QSIZE) >> 4; + + return val; +} + +static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + u32 val, reg; + + if (!ep->msi_cap) + return -EINVAL; + + reg = ep->msi_cap + PCI_MSI_FLAGS; + val = dw_pcie_readw_dbi(pci, reg); + val &= ~PCI_MSI_FLAGS_QMASK; + val |= (interrupts << 1) & PCI_MSI_FLAGS_QMASK; + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writew_dbi(pci, reg, val); + dw_pcie_dbi_ro_wr_dis(pci); + + return 0; +} + +static int dw_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + u32 val, reg; - val = dw_pcie_readw_dbi(pci, MSI_MESSAGE_CONTROL); - if (!(val & MSI_CAP_MSI_EN_MASK)) + if (!ep->msix_cap) return -EINVAL; - val = (val & MSI_CAP_MME_MASK) >> MSI_CAP_MME_SHIFT; + reg = ep->msix_cap + PCI_MSIX_FLAGS; + val = dw_pcie_readw_dbi(pci, reg); + if (!(val & PCI_MSIX_FLAGS_ENABLE)) + return -EINVAL; + + val &= PCI_MSIX_FLAGS_QSIZE; + return val; } -static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 encode_int) +static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts) { - int val; struct dw_pcie_ep *ep = epc_get_drvdata(epc); struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + u32 val, reg; + + if (!ep->msix_cap) + return -EINVAL; - val = dw_pcie_readw_dbi(pci, MSI_MESSAGE_CONTROL); - val &= ~MSI_CAP_MMC_MASK; - val |= (encode_int << MSI_CAP_MMC_SHIFT) & MSI_CAP_MMC_MASK; + reg = ep->msix_cap + PCI_MSIX_FLAGS; + val = dw_pcie_readw_dbi(pci, reg); + val &= ~PCI_MSIX_FLAGS_QSIZE; + val |= interrupts; dw_pcie_dbi_ro_wr_en(pci); - dw_pcie_writew_dbi(pci, MSI_MESSAGE_CONTROL, val); + dw_pcie_writew_dbi(pci, reg, val); dw_pcie_dbi_ro_wr_dis(pci); return 0; } static int dw_pcie_ep_raise_irq(struct pci_epc *epc, u8 func_no, - enum pci_epc_irq_type type, u8 interrupt_num) + enum pci_epc_irq_type type, u16 interrupt_num) { struct dw_pcie_ep *ep = epc_get_drvdata(epc); @@ -282,32 +363,52 @@ static const struct pci_epc_ops epc_ops = { .unmap_addr = dw_pcie_ep_unmap_addr, .set_msi = dw_pcie_ep_set_msi, .get_msi = dw_pcie_ep_get_msi, + .set_msix = dw_pcie_ep_set_msix, + .get_msix = dw_pcie_ep_get_msix, .raise_irq = dw_pcie_ep_raise_irq, .start = dw_pcie_ep_start, .stop = dw_pcie_ep_stop, }; +int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct device *dev = pci->dev; + + dev_err(dev, "EP cannot trigger legacy IRQs\n"); + + return -EINVAL; +} + int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, u8 interrupt_num) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); struct pci_epc *epc = ep->epc; u16 msg_ctrl, msg_data; - u32 msg_addr_lower, msg_addr_upper; + u32 msg_addr_lower, msg_addr_upper, reg; u64 msg_addr; bool has_upper; int ret; + if (!ep->msi_cap) + return -EINVAL; + /* Raise MSI per the PCI Local Bus Specification Revision 3.0, 6.8.1. */ - msg_ctrl = dw_pcie_readw_dbi(pci, MSI_MESSAGE_CONTROL); + reg = ep->msi_cap + PCI_MSI_FLAGS; + msg_ctrl = dw_pcie_readw_dbi(pci, reg); has_upper = !!(msg_ctrl & PCI_MSI_FLAGS_64BIT); - msg_addr_lower = dw_pcie_readl_dbi(pci, MSI_MESSAGE_ADDR_L32); + reg = ep->msi_cap + PCI_MSI_ADDRESS_LO; + msg_addr_lower = dw_pcie_readl_dbi(pci, reg); if (has_upper) { - msg_addr_upper = dw_pcie_readl_dbi(pci, MSI_MESSAGE_ADDR_U32); - msg_data = dw_pcie_readw_dbi(pci, MSI_MESSAGE_DATA_64); + reg = ep->msi_cap + PCI_MSI_ADDRESS_HI; + msg_addr_upper = dw_pcie_readl_dbi(pci, reg); + reg = ep->msi_cap + PCI_MSI_DATA_64; + msg_data = dw_pcie_readw_dbi(pci, reg); } else { msg_addr_upper = 0; - msg_data = dw_pcie_readw_dbi(pci, MSI_MESSAGE_DATA_32); + reg = ep->msi_cap + PCI_MSI_DATA_32; + msg_data = dw_pcie_readw_dbi(pci, reg); } msg_addr = ((u64) msg_addr_upper) << 32 | msg_addr_lower; ret = dw_pcie_ep_map_addr(epc, func_no, ep->msi_mem_phys, msg_addr, @@ -322,6 +423,64 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, return 0; } +int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, + u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct pci_epc *epc = ep->epc; + u16 tbl_offset, bir; + u32 bar_addr_upper, bar_addr_lower; + u32 msg_addr_upper, msg_addr_lower; + u32 reg, msg_data, vec_ctrl; + u64 tbl_addr, msg_addr, reg_u64; + void __iomem *msix_tbl; + int ret; + + reg = ep->msix_cap + PCI_MSIX_TABLE; + tbl_offset = dw_pcie_readl_dbi(pci, reg); + bir = (tbl_offset & PCI_MSIX_TABLE_BIR); + tbl_offset &= PCI_MSIX_TABLE_OFFSET; + tbl_offset >>= 3; + + reg = PCI_BASE_ADDRESS_0 + (4 * bir); + bar_addr_upper = 0; + bar_addr_lower = dw_pcie_readl_dbi(pci, reg); + reg_u64 = (bar_addr_lower & PCI_BASE_ADDRESS_MEM_TYPE_MASK); + if (reg_u64 == PCI_BASE_ADDRESS_MEM_TYPE_64) + bar_addr_upper = dw_pcie_readl_dbi(pci, reg + 4); + + tbl_addr = ((u64) bar_addr_upper) << 32 | bar_addr_lower; + tbl_addr += (tbl_offset + ((interrupt_num - 1) * PCI_MSIX_ENTRY_SIZE)); + tbl_addr &= PCI_BASE_ADDRESS_MEM_MASK; + + msix_tbl = ioremap_nocache(ep->phys_base + tbl_addr, + PCI_MSIX_ENTRY_SIZE); + if (!msix_tbl) + return -EINVAL; + + msg_addr_lower = readl(msix_tbl + PCI_MSIX_ENTRY_LOWER_ADDR); + msg_addr_upper = readl(msix_tbl + PCI_MSIX_ENTRY_UPPER_ADDR); + msg_addr = ((u64) msg_addr_upper) << 32 | msg_addr_lower; + msg_data = readl(msix_tbl + PCI_MSIX_ENTRY_DATA); + vec_ctrl = readl(msix_tbl + PCI_MSIX_ENTRY_VECTOR_CTRL); + + iounmap(msix_tbl); + + if (vec_ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT) + return -EPERM; + + ret = dw_pcie_ep_map_addr(epc, func_no, ep->msi_mem_phys, msg_addr, + epc->mem->page_size); + if (ret) + return ret; + + writel(msg_data, ep->msi_mem); + + dw_pcie_ep_unmap_addr(epc, func_no, ep->msi_mem_phys); + + return 0; +} + void dw_pcie_ep_exit(struct dw_pcie_ep *ep) { struct pci_epc *epc = ep->epc; @@ -386,15 +545,18 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep) return -ENOMEM; ep->outbound_addr = addr; - if (ep->ops->ep_init) - ep->ops->ep_init(ep); - epc = devm_pci_epc_create(dev, &epc_ops); if (IS_ERR(epc)) { dev_err(dev, "Failed to create epc device\n"); return PTR_ERR(epc); } + ep->epc = epc; + epc_set_drvdata(epc, ep); + + if (ep->ops->ep_init) + ep->ops->ep_init(ep); + ret = of_property_read_u8(np, "max-functions", &epc->max_functions); if (ret < 0) epc->max_functions = 1; @@ -409,15 +571,13 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep) ep->msi_mem = pci_epc_mem_alloc_addr(epc, &ep->msi_mem_phys, epc->mem->page_size); if (!ep->msi_mem) { - dev_err(dev, "Failed to reserve memory for MSI\n"); + dev_err(dev, "Failed to reserve memory for MSI/MSI-X\n"); return -ENOMEM; } + ep->msi_cap = dw_pcie_ep_find_capability(pci, PCI_CAP_ID_MSI); - epc->features = EPC_FEATURE_NO_LINKUP_NOTIFIER; - EPC_FEATURE_SET_BAR(epc->features, BAR_0); + ep->msix_cap = dw_pcie_ep_find_capability(pci, PCI_CAP_ID_MSIX); - ep->epc = epc; - epc_set_drvdata(epc, ep); dw_pcie_setup(pci); return 0; diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c index 5937fed4c938..c12bf794d69c 100644 --- a/drivers/pci/controller/dwc/pcie-designware-plat.c +++ b/drivers/pci/controller/dwc/pcie-designware-plat.c @@ -70,24 +70,29 @@ static const struct dw_pcie_ops dw_pcie_ops = { static void dw_plat_pcie_ep_init(struct dw_pcie_ep *ep) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct pci_epc *epc = ep->epc; enum pci_barno bar; for (bar = BAR_0; bar <= BAR_5; bar++) dw_pcie_ep_reset_bar(pci, bar); + + epc->features |= EPC_FEATURE_NO_LINKUP_NOTIFIER; + epc->features |= EPC_FEATURE_MSIX_AVAILABLE; } static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, enum pci_epc_irq_type type, - u8 interrupt_num) + u16 interrupt_num) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); switch (type) { case PCI_EPC_IRQ_LEGACY: - dev_err(pci->dev, "EP cannot trigger legacy IRQs\n"); - return -EINVAL; + return dw_pcie_ep_raise_legacy_irq(ep, func_no); case PCI_EPC_IRQ_MSI: return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num); + case PCI_EPC_IRQ_MSIX: + return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num); default: dev_err(pci->dev, "UNKNOWN IRQ type\n"); } @@ -118,7 +123,6 @@ static int dw_plat_add_pcie_port(struct dw_plat_pcie *dw_plat_pcie, return pp->msi_irq; } - pp->root_bus_nr = -1; pp->ops = &dw_plat_pcie_host_ops; ret = dw_pcie_host_init(pp); diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h index bee4e2535a61..96126fd8403c 100644 --- a/drivers/pci/controller/dwc/pcie-designware.h +++ b/drivers/pci/controller/dwc/pcie-designware.h @@ -96,17 +96,6 @@ #define PCIE_GET_ATU_INB_UNR_REG_OFFSET(region) \ ((0x3 << 20) | ((region) << 9) | (0x1 << 8)) -#define MSI_MESSAGE_CONTROL 0x52 -#define MSI_CAP_MMC_SHIFT 1 -#define MSI_CAP_MMC_MASK (7 << MSI_CAP_MMC_SHIFT) -#define MSI_CAP_MME_SHIFT 4 -#define MSI_CAP_MSI_EN_MASK 0x1 -#define MSI_CAP_MME_MASK (7 << MSI_CAP_MME_SHIFT) -#define MSI_MESSAGE_ADDR_L32 0x54 -#define MSI_MESSAGE_ADDR_U32 0x58 -#define MSI_MESSAGE_DATA_32 0x58 -#define MSI_MESSAGE_DATA_64 0x5C - #define MAX_MSI_IRQS 256 #define MAX_MSI_IRQS_PER_CTRL 32 #define MAX_MSI_CTRLS (MAX_MSI_IRQS / MAX_MSI_IRQS_PER_CTRL) @@ -191,7 +180,7 @@ enum dw_pcie_as_type { struct dw_pcie_ep_ops { void (*ep_init)(struct dw_pcie_ep *ep); int (*raise_irq)(struct dw_pcie_ep *ep, u8 func_no, - enum pci_epc_irq_type type, u8 interrupt_num); + enum pci_epc_irq_type type, u16 interrupt_num); }; struct dw_pcie_ep { @@ -208,6 +197,8 @@ struct dw_pcie_ep { u32 num_ob_windows; void __iomem *msi_mem; phys_addr_t msi_mem_phys; + u8 msi_cap; /* MSI capability offset */ + u8 msix_cap; /* MSI-X capability offset */ }; struct dw_pcie_ops { @@ -357,8 +348,11 @@ static inline int dw_pcie_allocate_domains(struct pcie_port *pp) void dw_pcie_ep_linkup(struct dw_pcie_ep *ep); int dw_pcie_ep_init(struct dw_pcie_ep *ep); void dw_pcie_ep_exit(struct dw_pcie_ep *ep); +int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no); int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, u8 interrupt_num); +int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, + u16 interrupt_num); void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar); #else static inline void dw_pcie_ep_linkup(struct dw_pcie_ep *ep) @@ -374,12 +368,23 @@ static inline void dw_pcie_ep_exit(struct dw_pcie_ep *ep) { } +static inline int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no) +{ + return 0; +} + static inline int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, u8 interrupt_num) { return 0; } +static inline int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, + u16 interrupt_num) +{ + return 0; +} + static inline void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar) { } diff --git a/drivers/pci/controller/dwc/pcie-histb.c b/drivers/pci/controller/dwc/pcie-histb.c index 3611d6ce9a92..7b32e619b959 100644 --- a/drivers/pci/controller/dwc/pcie-histb.c +++ b/drivers/pci/controller/dwc/pcie-histb.c @@ -420,7 +420,6 @@ static int histb_pcie_probe(struct platform_device *pdev) phy_init(hipcie->phy); } - pp->root_bus_nr = -1; pp->ops = &histb_pcie_host_ops; platform_set_drvdata(pdev, hipcie); diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c index d2970a009eb5..5352e0c3be82 100644 --- a/drivers/pci/controller/dwc/pcie-kirin.c +++ b/drivers/pci/controller/dwc/pcie-kirin.c @@ -430,6 +430,9 @@ static int kirin_pcie_host_init(struct pcie_port *pp) { kirin_pcie_establish_link(pp); + if (IS_ENABLED(CONFIG_PCI_MSI)) + dw_pcie_msi_init(pp); + return 0; } @@ -445,9 +448,34 @@ static const struct dw_pcie_host_ops kirin_pcie_host_ops = { .host_init = kirin_pcie_host_init, }; +static int kirin_pcie_add_msi(struct dw_pcie *pci, + struct platform_device *pdev) +{ + int irq; + + if (IS_ENABLED(CONFIG_PCI_MSI)) { + irq = platform_get_irq(pdev, 0); + if (irq < 0) { + dev_err(&pdev->dev, + "failed to get MSI IRQ (%d)\n", irq); + return irq; + } + + pci->pp.msi_irq = irq; + } + + return 0; +} + static int __init kirin_add_pcie_port(struct dw_pcie *pci, struct platform_device *pdev) { + int ret; + + ret = kirin_pcie_add_msi(pci, pdev); + if (ret) + return ret; + pci->pp.ops = &kirin_pcie_host_ops; return dw_pcie_host_init(&pci->pp); diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index a1d0198081a6..4352c1cb926d 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -1251,7 +1251,6 @@ static int qcom_pcie_probe(struct platform_device *pdev) if (ret) return ret; - pp->root_bus_nr = -1; pp->ops = &qcom_pcie_dw_ops; if (IS_ENABLED(CONFIG_PCI_MSI)) { diff --git a/drivers/pci/controller/dwc/pcie-spear13xx.c b/drivers/pci/controller/dwc/pcie-spear13xx.c index ecb58f7b7566..7d0cdfd8138b 100644 --- a/drivers/pci/controller/dwc/pcie-spear13xx.c +++ b/drivers/pci/controller/dwc/pcie-spear13xx.c @@ -210,7 +210,6 @@ static int spear13xx_add_pcie_port(struct spear13xx_pcie *spear13xx_pcie, return ret; } - pp->root_bus_nr = -1; pp->ops = &spear13xx_pcie_host_ops; ret = dw_pcie_host_init(pp); diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index 0fae816fba39..6b4555ff2548 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -111,24 +111,6 @@ #define PCIE_MSI_MASK_REG (CONTROL_BASE_ADDR + 0x5C) #define PCIE_MSI_PAYLOAD_REG (CONTROL_BASE_ADDR + 0x9C) -/* PCIe window configuration */ -#define OB_WIN_BASE_ADDR 0x4c00 -#define OB_WIN_BLOCK_SIZE 0x20 -#define OB_WIN_REG_ADDR(win, offset) (OB_WIN_BASE_ADDR + \ - OB_WIN_BLOCK_SIZE * (win) + \ - (offset)) -#define OB_WIN_MATCH_LS(win) OB_WIN_REG_ADDR(win, 0x00) -#define OB_WIN_MATCH_MS(win) OB_WIN_REG_ADDR(win, 0x04) -#define OB_WIN_REMAP_LS(win) OB_WIN_REG_ADDR(win, 0x08) -#define OB_WIN_REMAP_MS(win) OB_WIN_REG_ADDR(win, 0x0c) -#define OB_WIN_MASK_LS(win) OB_WIN_REG_ADDR(win, 0x10) -#define OB_WIN_MASK_MS(win) OB_WIN_REG_ADDR(win, 0x14) -#define OB_WIN_ACTIONS(win) OB_WIN_REG_ADDR(win, 0x18) - -/* PCIe window types */ -#define OB_PCIE_MEM 0x0 -#define OB_PCIE_IO 0x4 - /* LMI registers base address and register offsets */ #define LMI_BASE_ADDR 0x6000 #define CFG_REG (LMI_BASE_ADDR + 0x0) @@ -247,34 +229,9 @@ static int advk_pcie_wait_for_link(struct advk_pcie *pcie) return -ETIMEDOUT; } -/* - * Set PCIe address window register which could be used for memory - * mapping. - */ -static void advk_pcie_set_ob_win(struct advk_pcie *pcie, - u32 win_num, u32 match_ms, - u32 match_ls, u32 mask_ms, - u32 mask_ls, u32 remap_ms, - u32 remap_ls, u32 action) -{ - advk_writel(pcie, match_ls, OB_WIN_MATCH_LS(win_num)); - advk_writel(pcie, match_ms, OB_WIN_MATCH_MS(win_num)); - advk_writel(pcie, mask_ms, OB_WIN_MASK_MS(win_num)); - advk_writel(pcie, mask_ls, OB_WIN_MASK_LS(win_num)); - advk_writel(pcie, remap_ms, OB_WIN_REMAP_MS(win_num)); - advk_writel(pcie, remap_ls, OB_WIN_REMAP_LS(win_num)); - advk_writel(pcie, action, OB_WIN_ACTIONS(win_num)); - advk_writel(pcie, match_ls | BIT(0), OB_WIN_MATCH_LS(win_num)); -} - static void advk_pcie_setup_hw(struct advk_pcie *pcie) { u32 reg; - int i; - - /* Point PCIe unit MBUS decode windows to DRAM space */ - for (i = 0; i < 8; i++) - advk_pcie_set_ob_win(pcie, i, 0, 0, 0, 0, 0, 0, 0); /* Set to Direct mode */ reg = advk_readl(pcie, CTRL_CONFIG_REG); @@ -433,6 +390,15 @@ static int advk_pcie_wait_pio(struct advk_pcie *pcie) return -ETIMEDOUT; } +static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus, + int devfn) +{ + if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0) + return false; + + return true; +} + static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where, int size, u32 *val) { @@ -440,7 +406,7 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, u32 reg; int ret; - if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0) { + if (!advk_pcie_valid_device(pcie, bus, devfn)) { *val = 0xffffffff; return PCIBIOS_DEVICE_NOT_FOUND; } @@ -494,7 +460,7 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn, int offset; int ret; - if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0) + if (!advk_pcie_valid_device(pcie, bus, devfn)) return PCIBIOS_DEVICE_NOT_FOUND; if (where % size) @@ -843,12 +809,6 @@ static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie) switch (resource_type(res)) { case IORESOURCE_IO: - advk_pcie_set_ob_win(pcie, 1, - upper_32_bits(res->start), - lower_32_bits(res->start), - 0, 0xF8000000, 0, - lower_32_bits(res->start), - OB_PCIE_IO); err = devm_pci_remap_iospace(dev, res, iobase); if (err) { dev_warn(dev, "error %d: failed to map resource %pR\n", @@ -857,12 +817,6 @@ static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie) } break; case IORESOURCE_MEM: - advk_pcie_set_ob_win(pcie, 0, - upper_32_bits(res->start), - lower_32_bits(res->start), - 0x0, 0xF8000000, 0, - lower_32_bits(res->start), - (2 << 20) | OB_PCIE_MEM); res_valid |= !(res->flags & IORESOURCE_PREFETCH); break; case IORESOURCE_BUS: @@ -889,7 +843,6 @@ static int advk_pcie_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct advk_pcie *pcie; struct resource *res; - struct pci_bus *bus, *child; struct pci_host_bridge *bridge; int ret, irq; @@ -943,21 +896,13 @@ static int advk_pcie_probe(struct platform_device *pdev) bridge->map_irq = of_irq_parse_and_map_pci; bridge->swizzle_irq = pci_common_swizzle; - ret = pci_scan_root_bus_bridge(bridge); + ret = pci_host_probe(bridge); if (ret < 0) { advk_pcie_remove_msi_irq_domain(pcie); advk_pcie_remove_irq_domain(pcie); return ret; } - bus = bridge->bus; - - pci_bus_assign_resources(bus); - - list_for_each_entry(child, &bus->children, node) - pcie_bus_configure_settings(child); - - pci_bus_add_devices(bus); return 0; } diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index d4d4a55f09f8..c00f82cc54aa 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -1546,7 +1546,7 @@ static struct hv_pci_dev *new_pcichild_device(struct hv_pcibus_device *hbus, unsigned long flags; int ret; - hpdev = kzalloc(sizeof(*hpdev), GFP_ATOMIC); + hpdev = kzalloc(sizeof(*hpdev), GFP_KERNEL); if (!hpdev) return NULL; diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c index 23e270839e6a..50eb0729385b 100644 --- a/drivers/pci/controller/pci-mvebu.c +++ b/drivers/pci/controller/pci-mvebu.c @@ -125,6 +125,7 @@ struct mvebu_pcie { struct platform_device *pdev; struct mvebu_pcie_port *ports; struct msi_controller *msi; + struct list_head resources; struct resource io; struct resource realio; struct resource mem; @@ -800,7 +801,7 @@ static struct mvebu_pcie_port *mvebu_pcie_find_port(struct mvebu_pcie *pcie, static int mvebu_pcie_wr_conf(struct pci_bus *bus, u32 devfn, int where, int size, u32 val) { - struct mvebu_pcie *pcie = sys_to_pcie(bus->sysdata); + struct mvebu_pcie *pcie = bus->sysdata; struct mvebu_pcie_port *port; int ret; @@ -826,7 +827,7 @@ static int mvebu_pcie_wr_conf(struct pci_bus *bus, u32 devfn, static int mvebu_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where, int size, u32 *val) { - struct mvebu_pcie *pcie = sys_to_pcie(bus->sysdata); + struct mvebu_pcie *pcie = bus->sysdata; struct mvebu_pcie_port *port; int ret; @@ -857,36 +858,6 @@ static struct pci_ops mvebu_pcie_ops = { .write = mvebu_pcie_wr_conf, }; -static int mvebu_pcie_setup(int nr, struct pci_sys_data *sys) -{ - struct mvebu_pcie *pcie = sys_to_pcie(sys); - int err, i; - - pcie->mem.name = "PCI MEM"; - pcie->realio.name = "PCI I/O"; - - if (resource_size(&pcie->realio) != 0) - pci_add_resource_offset(&sys->resources, &pcie->realio, - sys->io_offset); - - pci_add_resource_offset(&sys->resources, &pcie->mem, sys->mem_offset); - pci_add_resource(&sys->resources, &pcie->busn); - - err = devm_request_pci_bus_resources(&pcie->pdev->dev, &sys->resources); - if (err) - return 0; - - for (i = 0; i < pcie->nports; i++) { - struct mvebu_pcie_port *port = &pcie->ports[i]; - - if (!port->base) - continue; - mvebu_pcie_setup_hw(port); - } - - return 1; -} - static resource_size_t mvebu_pcie_align_resource(struct pci_dev *dev, const struct resource *res, resource_size_t start, @@ -917,31 +888,6 @@ static resource_size_t mvebu_pcie_align_resource(struct pci_dev *dev, return start; } -static void mvebu_pcie_enable(struct mvebu_pcie *pcie) -{ - struct hw_pci hw; - - memset(&hw, 0, sizeof(hw)); - -#ifdef CONFIG_PCI_MSI - hw.msi_ctrl = pcie->msi; -#endif - - hw.nr_controllers = 1; - hw.private_data = (void **)&pcie; - hw.setup = mvebu_pcie_setup; - hw.map_irq = of_irq_parse_and_map_pci; - hw.ops = &mvebu_pcie_ops; - hw.align_resource = mvebu_pcie_align_resource; - - pci_common_init_dev(&pcie->pdev->dev, &hw); -} - -/* - * Looks up the list of register addresses encoded into the reg = - * <...> property for one that matches the given port/lane. Once - * found, maps it. - */ static void __iomem *mvebu_pcie_map_registers(struct platform_device *pdev, struct device_node *np, struct mvebu_pcie_port *port) @@ -1190,46 +1136,79 @@ static void mvebu_pcie_powerdown(struct mvebu_pcie_port *port) clk_disable_unprepare(port->clk); } -static int mvebu_pcie_probe(struct platform_device *pdev) +/* + * We can't use devm_of_pci_get_host_bridge_resources() because we + * need to parse our special DT properties encoding the MEM and IO + * apertures. + */ +static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie) { - struct device *dev = &pdev->dev; - struct mvebu_pcie *pcie; + struct device *dev = &pcie->pdev->dev; struct device_node *np = dev->of_node; - struct device_node *child; - int num, i, ret; + unsigned int i; + int ret; - pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); - if (!pcie) - return -ENOMEM; + INIT_LIST_HEAD(&pcie->resources); - pcie->pdev = pdev; - platform_set_drvdata(pdev, pcie); + /* Get the bus range */ + ret = of_pci_parse_bus_range(np, &pcie->busn); + if (ret) { + dev_err(dev, "failed to parse bus-range property: %d\n", ret); + return ret; + } + pci_add_resource(&pcie->resources, &pcie->busn); - /* Get the PCIe memory and I/O aperture */ + /* Get the PCIe memory aperture */ mvebu_mbus_get_pcie_mem_aperture(&pcie->mem); if (resource_size(&pcie->mem) == 0) { dev_err(dev, "invalid memory aperture size\n"); return -EINVAL; } + pcie->mem.name = "PCI MEM"; + pci_add_resource(&pcie->resources, &pcie->mem); + + /* Get the PCIe IO aperture */ mvebu_mbus_get_pcie_io_aperture(&pcie->io); if (resource_size(&pcie->io) != 0) { pcie->realio.flags = pcie->io.flags; pcie->realio.start = PCIBIOS_MIN_IO; pcie->realio.end = min_t(resource_size_t, - IO_SPACE_LIMIT, - resource_size(&pcie->io)); - } else - pcie->realio = pcie->io; + IO_SPACE_LIMIT - SZ_64K, + resource_size(&pcie->io) - 1); + pcie->realio.name = "PCI I/O"; - /* Get the bus range */ - ret = of_pci_parse_bus_range(np, &pcie->busn); - if (ret) { - dev_err(dev, "failed to parse bus-range property: %d\n", ret); - return ret; + for (i = 0; i < resource_size(&pcie->realio); i += SZ_64K) + pci_ioremap_io(i, pcie->io.start + i); + + pci_add_resource(&pcie->resources, &pcie->realio); } + return devm_request_pci_bus_resources(dev, &pcie->resources); +} + +static int mvebu_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct mvebu_pcie *pcie; + struct pci_host_bridge *bridge; + struct device_node *np = dev->of_node; + struct device_node *child; + int num, i, ret; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(struct mvebu_pcie)); + if (!bridge) + return -ENOMEM; + + pcie = pci_host_bridge_priv(bridge); + pcie->pdev = pdev; + platform_set_drvdata(pdev, pcie); + + ret = mvebu_pcie_parse_request_resources(pcie); + if (ret) + return ret; + num = of_get_available_child_count(np); pcie->ports = devm_kcalloc(dev, num, sizeof(*pcie->ports), GFP_KERNEL); @@ -1272,20 +1251,24 @@ static int mvebu_pcie_probe(struct platform_device *pdev) continue; } + mvebu_pcie_setup_hw(port); mvebu_pcie_set_local_dev_nr(port, 1); mvebu_sw_pci_bridge_init(port); } pcie->nports = i; - for (i = 0; i < (IO_SPACE_LIMIT - SZ_64K); i += SZ_64K) - pci_ioremap_io(i, pcie->io.start + i); - - mvebu_pcie_enable(pcie); - - platform_set_drvdata(pdev, pcie); - - return 0; + list_splice_init(&pcie->resources, &bridge->windows); + bridge->dev.parent = dev; + bridge->sysdata = pcie; + bridge->busnr = 0; + bridge->ops = &mvebu_pcie_ops; + bridge->map_irq = of_irq_parse_and_map_pci; + bridge->swizzle_irq = pci_common_swizzle; + bridge->align_resource = mvebu_pcie_align_resource; + bridge->msi = pcie->msi; + + return pci_host_probe(bridge); } static const struct of_device_id mvebu_pcie_of_match_table[] = { diff --git a/drivers/pci/controller/pcie-cadence-ep.c b/drivers/pci/controller/pcie-cadence-ep.c index e3fe4124e3af..9e87dd7f9ac3 100644 --- a/drivers/pci/controller/pcie-cadence-ep.c +++ b/drivers/pci/controller/pcie-cadence-ep.c @@ -238,7 +238,7 @@ static int cdns_pcie_ep_get_msi(struct pci_epc *epc, u8 fn) struct cdns_pcie_ep *ep = epc_get_drvdata(epc); struct cdns_pcie *pcie = &ep->pcie; u32 cap = CDNS_PCIE_EP_FUNC_MSI_CAP_OFFSET; - u16 flags, mmc, mme; + u16 flags, mme; /* Validate that the MSI feature is actually enabled. */ flags = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_FLAGS); @@ -249,7 +249,6 @@ static int cdns_pcie_ep_get_msi(struct pci_epc *epc, u8 fn) * Get the Multiple Message Enable bitfield from the Message Control * register. */ - mmc = (flags & PCI_MSI_FLAGS_QMASK) >> 1; mme = (flags & PCI_MSI_FLAGS_QSIZE) >> 4; return mme; @@ -363,7 +362,8 @@ static int cdns_pcie_ep_send_msi_irq(struct cdns_pcie_ep *ep, u8 fn, } static int cdns_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, - enum pci_epc_irq_type type, u8 interrupt_num) + enum pci_epc_irq_type type, + u16 interrupt_num) { struct cdns_pcie_ep *ep = epc_get_drvdata(epc); @@ -439,6 +439,7 @@ static int cdns_pcie_ep_probe(struct platform_device *pdev) struct pci_epc *epc; struct resource *res; int ret; + int phy_count; ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL); if (!ep) @@ -473,6 +474,12 @@ static int cdns_pcie_ep_probe(struct platform_device *pdev) if (!ep->ob_addr) return -ENOMEM; + ret = cdns_pcie_init_phy(dev, pcie); + if (ret) { + dev_err(dev, "failed to init phy\n"); + return ret; + } + platform_set_drvdata(pdev, pcie); pm_runtime_enable(dev); ret = pm_runtime_get_sync(dev); if (ret < 0) { @@ -521,6 +528,10 @@ static int cdns_pcie_ep_probe(struct platform_device *pdev) err_get_sync: pm_runtime_disable(dev); + cdns_pcie_disable_phy(pcie); + phy_count = pcie->phy_count; + while (phy_count--) + device_link_del(pcie->link[phy_count]); return ret; } @@ -528,6 +539,7 @@ static int cdns_pcie_ep_probe(struct platform_device *pdev) static void cdns_pcie_ep_shutdown(struct platform_device *pdev) { struct device *dev = &pdev->dev; + struct cdns_pcie *pcie = dev_get_drvdata(dev); int ret; ret = pm_runtime_put_sync(dev); @@ -536,13 +548,14 @@ static void cdns_pcie_ep_shutdown(struct platform_device *pdev) pm_runtime_disable(dev); - /* The PCIe controller can't be disabled. */ + cdns_pcie_disable_phy(pcie); } static struct platform_driver cdns_pcie_ep_driver = { .driver = { .name = "cdns-pcie-ep", .of_match_table = cdns_pcie_ep_of_match, + .pm = &cdns_pcie_pm_ops, }, .probe = cdns_pcie_ep_probe, .shutdown = cdns_pcie_ep_shutdown, diff --git a/drivers/pci/controller/pcie-cadence-host.c b/drivers/pci/controller/pcie-cadence-host.c index a4ebbd37b553..ec394f6a19c8 100644 --- a/drivers/pci/controller/pcie-cadence-host.c +++ b/drivers/pci/controller/pcie-cadence-host.c @@ -58,6 +58,11 @@ static void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int devfn, return pcie->reg_base + (where & 0xfff); } + /* Check that the link is up */ + if (!(cdns_pcie_readl(pcie, CDNS_PCIE_LM_BASE) & 0x1)) + return NULL; + /* Clear AXI link-down status */ + cdns_pcie_writel(pcie, CDNS_PCIE_AT_LINKDOWN, 0x0); /* Update Output registers for AXI region 0. */ addr0 = CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_NBITS(12) | @@ -239,6 +244,7 @@ static int cdns_pcie_host_probe(struct platform_device *pdev) struct cdns_pcie *pcie; struct resource *res; int ret; + int phy_count; bridge = devm_pci_alloc_host_bridge(dev, sizeof(*rc)); if (!bridge) @@ -290,6 +296,13 @@ static int cdns_pcie_host_probe(struct platform_device *pdev) } pcie->mem_res = res; + ret = cdns_pcie_init_phy(dev, pcie); + if (ret) { + dev_err(dev, "failed to init phy\n"); + return ret; + } + platform_set_drvdata(pdev, pcie); + pm_runtime_enable(dev); ret = pm_runtime_get_sync(dev); if (ret < 0) { @@ -322,15 +335,35 @@ static int cdns_pcie_host_probe(struct platform_device *pdev) err_get_sync: pm_runtime_disable(dev); + cdns_pcie_disable_phy(pcie); + phy_count = pcie->phy_count; + while (phy_count--) + device_link_del(pcie->link[phy_count]); return ret; } +static void cdns_pcie_shutdown(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct cdns_pcie *pcie = dev_get_drvdata(dev); + int ret; + + ret = pm_runtime_put_sync(dev); + if (ret < 0) + dev_dbg(dev, "pm_runtime_put_sync failed\n"); + + pm_runtime_disable(dev); + cdns_pcie_disable_phy(pcie); +} + static struct platform_driver cdns_pcie_host_driver = { .driver = { .name = "cdns-pcie-host", .of_match_table = cdns_pcie_host_of_match, + .pm = &cdns_pcie_pm_ops, }, .probe = cdns_pcie_host_probe, + .shutdown = cdns_pcie_shutdown, }; builtin_platform_driver(cdns_pcie_host_driver); diff --git a/drivers/pci/controller/pcie-cadence.c b/drivers/pci/controller/pcie-cadence.c index 138d113eb45d..86f1b002c846 100644 --- a/drivers/pci/controller/pcie-cadence.c +++ b/drivers/pci/controller/pcie-cadence.c @@ -124,3 +124,126 @@ void cdns_pcie_reset_outbound_region(struct cdns_pcie *pcie, u32 r) cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR0(r), 0); cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR1(r), 0); } + +void cdns_pcie_disable_phy(struct cdns_pcie *pcie) +{ + int i = pcie->phy_count; + + while (i--) { + phy_power_off(pcie->phy[i]); + phy_exit(pcie->phy[i]); + } +} + +int cdns_pcie_enable_phy(struct cdns_pcie *pcie) +{ + int ret; + int i; + + for (i = 0; i < pcie->phy_count; i++) { + ret = phy_init(pcie->phy[i]); + if (ret < 0) + goto err_phy; + + ret = phy_power_on(pcie->phy[i]); + if (ret < 0) { + phy_exit(pcie->phy[i]); + goto err_phy; + } + } + + return 0; + +err_phy: + while (--i >= 0) { + phy_power_off(pcie->phy[i]); + phy_exit(pcie->phy[i]); + } + + return ret; +} + +int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie) +{ + struct device_node *np = dev->of_node; + int phy_count; + struct phy **phy; + struct device_link **link; + int i; + int ret; + const char *name; + + phy_count = of_property_count_strings(np, "phy-names"); + if (phy_count < 1) { + dev_err(dev, "no phy-names. PHY will not be initialized\n"); + pcie->phy_count = 0; + return 0; + } + + phy = devm_kzalloc(dev, sizeof(*phy) * phy_count, GFP_KERNEL); + if (!phy) + return -ENOMEM; + + link = devm_kzalloc(dev, sizeof(*link) * phy_count, GFP_KERNEL); + if (!link) + return -ENOMEM; + + for (i = 0; i < phy_count; i++) { + of_property_read_string_index(np, "phy-names", i, &name); + phy[i] = devm_phy_optional_get(dev, name); + if (IS_ERR(phy)) + return PTR_ERR(phy); + + link[i] = device_link_add(dev, &phy[i]->dev, DL_FLAG_STATELESS); + if (!link[i]) { + ret = -EINVAL; + goto err_link; + } + } + + pcie->phy_count = phy_count; + pcie->phy = phy; + pcie->link = link; + + ret = cdns_pcie_enable_phy(pcie); + if (ret) + goto err_link; + + return 0; + +err_link: + while (--i >= 0) + device_link_del(link[i]); + + return ret; +} + +#ifdef CONFIG_PM_SLEEP +static int cdns_pcie_suspend_noirq(struct device *dev) +{ + struct cdns_pcie *pcie = dev_get_drvdata(dev); + + cdns_pcie_disable_phy(pcie); + + return 0; +} + +static int cdns_pcie_resume_noirq(struct device *dev) +{ + struct cdns_pcie *pcie = dev_get_drvdata(dev); + int ret; + + ret = cdns_pcie_enable_phy(pcie); + if (ret) { + dev_err(dev, "failed to enable phy\n"); + return ret; + } + + return 0; +} +#endif + +const struct dev_pm_ops cdns_pcie_pm_ops = { + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(cdns_pcie_suspend_noirq, + cdns_pcie_resume_noirq) +}; diff --git a/drivers/pci/controller/pcie-cadence.h b/drivers/pci/controller/pcie-cadence.h index 4bb27333b05c..ae6bf2a2b3d3 100644 --- a/drivers/pci/controller/pcie-cadence.h +++ b/drivers/pci/controller/pcie-cadence.h @@ -8,6 +8,7 @@ #include <linux/kernel.h> #include <linux/pci.h> +#include <linux/phy/phy.h> /* * Local Management Registers @@ -165,6 +166,9 @@ #define CDNS_PCIE_AT_IB_RP_BAR_ADDR1(bar) \ (CDNS_PCIE_AT_BASE + 0x0804 + (bar) * 0x0008) +/* AXI link down register */ +#define CDNS_PCIE_AT_LINKDOWN (CDNS_PCIE_AT_BASE + 0x0824) + enum cdns_pcie_rp_bar { RP_BAR0, RP_BAR1, @@ -229,6 +233,9 @@ struct cdns_pcie { struct resource *mem_res; bool is_rc; u8 bus; + int phy_count; + struct phy **phy; + struct device_link **link; }; /* Register access */ @@ -279,7 +286,7 @@ static inline void cdns_pcie_ep_fn_writew(struct cdns_pcie *pcie, u8 fn, } static inline void cdns_pcie_ep_fn_writel(struct cdns_pcie *pcie, u8 fn, - u32 reg, u16 value) + u32 reg, u32 value) { writel(value, pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg); } @@ -307,5 +314,9 @@ void cdns_pcie_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie, u8 fn, u32 r, u64 cpu_addr); void cdns_pcie_reset_outbound_region(struct cdns_pcie *pcie, u32 r); +void cdns_pcie_disable_phy(struct cdns_pcie *pcie); +int cdns_pcie_enable_phy(struct cdns_pcie *pcie); +int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie); +extern const struct dev_pm_ops cdns_pcie_pm_ops; #endif /* _PCIE_CADENCE_H */ diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c index 3c76c5fa4f32..3160e9342a2f 100644 --- a/drivers/pci/controller/pcie-iproc.c +++ b/drivers/pci/controller/pcie-iproc.c @@ -85,6 +85,8 @@ #define IMAP_VALID_SHIFT 0 #define IMAP_VALID BIT(IMAP_VALID_SHIFT) +#define IPROC_PCI_PM_CAP 0x48 +#define IPROC_PCI_PM_CAP_MASK 0xffff #define IPROC_PCI_EXP_CAP 0xac #define IPROC_PCIE_REG_INVALID 0xffff @@ -375,6 +377,17 @@ static const u16 iproc_pcie_reg_paxc_v2[] = { [IPROC_PCIE_CFG_DATA] = 0x1fc, }; +/* + * List of device IDs of controllers that have corrupted capability list that + * require SW fixup + */ +static const u16 iproc_pcie_corrupt_cap_did[] = { + 0x16cd, + 0x16f0, + 0xd802, + 0xd804 +}; + static inline struct iproc_pcie *iproc_data(struct pci_bus *bus) { struct iproc_pcie *pcie = bus->sysdata; @@ -495,6 +508,49 @@ static unsigned int iproc_pcie_cfg_retry(void __iomem *cfg_data_p) return data; } +static void iproc_pcie_fix_cap(struct iproc_pcie *pcie, int where, u32 *val) +{ + u32 i, dev_id; + + switch (where & ~0x3) { + case PCI_VENDOR_ID: + dev_id = *val >> 16; + + /* + * Activate fixup for those controllers that have corrupted + * capability list registers + */ + for (i = 0; i < ARRAY_SIZE(iproc_pcie_corrupt_cap_did); i++) + if (dev_id == iproc_pcie_corrupt_cap_did[i]) + pcie->fix_paxc_cap = true; + break; + + case IPROC_PCI_PM_CAP: + if (pcie->fix_paxc_cap) { + /* advertise PM, force next capability to PCIe */ + *val &= ~IPROC_PCI_PM_CAP_MASK; + *val |= IPROC_PCI_EXP_CAP << 8 | PCI_CAP_ID_PM; + } + break; + + case IPROC_PCI_EXP_CAP: + if (pcie->fix_paxc_cap) { + /* advertise root port, version 2, terminate here */ + *val = (PCI_EXP_TYPE_ROOT_PORT << 4 | 2) << 16 | + PCI_CAP_ID_EXP; + } + break; + + case IPROC_PCI_EXP_CAP + PCI_EXP_RTCTL: + /* Don't advertise CRS SV support */ + *val &= ~(PCI_EXP_RTCAP_CRSVIS << 16); + break; + + default: + break; + } +} + static int iproc_pcie_config_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { @@ -509,13 +565,10 @@ static int iproc_pcie_config_read(struct pci_bus *bus, unsigned int devfn, /* root complex access */ if (busno == 0) { ret = pci_generic_config_read32(bus, devfn, where, size, val); - if (ret != PCIBIOS_SUCCESSFUL) - return ret; + if (ret == PCIBIOS_SUCCESSFUL) + iproc_pcie_fix_cap(pcie, where, val); - /* Don't advertise CRS SV support */ - if ((where & ~0x3) == IPROC_PCI_EXP_CAP + PCI_EXP_RTCTL) - *val &= ~(PCI_EXP_RTCAP_CRSVIS << 16); - return PCIBIOS_SUCCESSFUL; + return ret; } cfg_data_p = iproc_pcie_map_ep_cfg_reg(pcie, busno, slot, fn, where); @@ -529,6 +582,25 @@ static int iproc_pcie_config_read(struct pci_bus *bus, unsigned int devfn, if (size <= 2) *val = (data >> (8 * (where & 3))) & ((1 << (size * 8)) - 1); + /* + * For PAXC and PAXCv2, the total number of PFs that one can enumerate + * depends on the firmware configuration. Unfortunately, due to an ASIC + * bug, unconfigured PFs cannot be properly hidden from the root + * complex. As a result, write access to these PFs will cause bus lock + * up on the embedded processor + * + * Since all unconfigured PFs are left with an incorrect, staled device + * ID of 0x168e (PCI_DEVICE_ID_NX2_57810), we try to catch those access + * early here and reject them all + */ +#define DEVICE_ID_MASK 0xffff0000 +#define DEVICE_ID_SHIFT 16 + if (pcie->rej_unconfig_pf && + (where & CFG_ADDR_REG_NUM_MASK) == PCI_VENDOR_ID) + if ((*val & DEVICE_ID_MASK) == + (PCI_DEVICE_ID_NX2_57810 << DEVICE_ID_SHIFT)) + return PCIBIOS_FUNC_NOT_SUPPORTED; + return PCIBIOS_SUCCESSFUL; } @@ -628,7 +700,7 @@ static int iproc_pcie_config_read32(struct pci_bus *bus, unsigned int devfn, struct iproc_pcie *pcie = iproc_data(bus); iproc_pcie_apb_err_disable(bus, true); - if (pcie->type == IPROC_PCIE_PAXB_V2) + if (pcie->iproc_cfg_read) ret = iproc_pcie_config_read(bus, devfn, where, size, val); else ret = pci_generic_config_read32(bus, devfn, where, size, val); @@ -808,14 +880,14 @@ static inline int iproc_pcie_ob_write(struct iproc_pcie *pcie, int window_idx, writel(lower_32_bits(pci_addr), pcie->base + omap_offset); writel(upper_32_bits(pci_addr), pcie->base + omap_offset + 4); - dev_info(dev, "ob window [%d]: offset 0x%x axi %pap pci %pap\n", - window_idx, oarr_offset, &axi_addr, &pci_addr); - dev_info(dev, "oarr lo 0x%x oarr hi 0x%x\n", - readl(pcie->base + oarr_offset), - readl(pcie->base + oarr_offset + 4)); - dev_info(dev, "omap lo 0x%x omap hi 0x%x\n", - readl(pcie->base + omap_offset), - readl(pcie->base + omap_offset + 4)); + dev_dbg(dev, "ob window [%d]: offset 0x%x axi %pap pci %pap\n", + window_idx, oarr_offset, &axi_addr, &pci_addr); + dev_dbg(dev, "oarr lo 0x%x oarr hi 0x%x\n", + readl(pcie->base + oarr_offset), + readl(pcie->base + oarr_offset + 4)); + dev_dbg(dev, "omap lo 0x%x omap hi 0x%x\n", + readl(pcie->base + omap_offset), + readl(pcie->base + omap_offset + 4)); return 0; } @@ -982,8 +1054,8 @@ static int iproc_pcie_ib_write(struct iproc_pcie *pcie, int region_idx, iproc_pcie_reg_is_invalid(imap_offset)) return -EINVAL; - dev_info(dev, "ib region [%d]: offset 0x%x axi %pap pci %pap\n", - region_idx, iarr_offset, &axi_addr, &pci_addr); + dev_dbg(dev, "ib region [%d]: offset 0x%x axi %pap pci %pap\n", + region_idx, iarr_offset, &axi_addr, &pci_addr); /* * Program the IARR registers. The upper 32-bit IARR register is @@ -993,9 +1065,9 @@ static int iproc_pcie_ib_write(struct iproc_pcie *pcie, int region_idx, pcie->base + iarr_offset); writel(upper_32_bits(pci_addr), pcie->base + iarr_offset + 4); - dev_info(dev, "iarr lo 0x%x iarr hi 0x%x\n", - readl(pcie->base + iarr_offset), - readl(pcie->base + iarr_offset + 4)); + dev_dbg(dev, "iarr lo 0x%x iarr hi 0x%x\n", + readl(pcie->base + iarr_offset), + readl(pcie->base + iarr_offset + 4)); /* * Now program the IMAP registers. Each IARR region may have one or @@ -1009,10 +1081,10 @@ static int iproc_pcie_ib_write(struct iproc_pcie *pcie, int region_idx, writel(upper_32_bits(axi_addr), pcie->base + imap_offset + ib_map->imap_addr_offset); - dev_info(dev, "imap window [%d] lo 0x%x hi 0x%x\n", - window_idx, readl(pcie->base + imap_offset), - readl(pcie->base + imap_offset + - ib_map->imap_addr_offset)); + dev_dbg(dev, "imap window [%d] lo 0x%x hi 0x%x\n", + window_idx, readl(pcie->base + imap_offset), + readl(pcie->base + imap_offset + + ib_map->imap_addr_offset)); imap_offset += ib_map->imap_window_offset; axi_addr += size; @@ -1144,10 +1216,22 @@ static int iproc_pcie_paxb_v2_msi_steer(struct iproc_pcie *pcie, u64 msi_addr) return ret; } -static void iproc_pcie_paxc_v2_msi_steer(struct iproc_pcie *pcie, u64 msi_addr) +static void iproc_pcie_paxc_v2_msi_steer(struct iproc_pcie *pcie, u64 msi_addr, + bool enable) { u32 val; + if (!enable) { + /* + * Disable PAXC MSI steering. All write transfers will be + * treated as non-MSI transfers + */ + val = iproc_pcie_read_reg(pcie, IPROC_PCIE_MSI_EN_CFG); + val &= ~MSI_ENABLE_CFG; + iproc_pcie_write_reg(pcie, IPROC_PCIE_MSI_EN_CFG, val); + return; + } + /* * Program bits [43:13] of address of GITS_TRANSLATER register into * bits [30:0] of the MSI base address register. In fact, in all iProc @@ -1201,7 +1285,7 @@ static int iproc_pcie_msi_steer(struct iproc_pcie *pcie, return ret; break; case IPROC_PCIE_PAXC_V2: - iproc_pcie_paxc_v2_msi_steer(pcie, msi_addr); + iproc_pcie_paxc_v2_msi_steer(pcie, msi_addr, true); break; default: return -EINVAL; @@ -1271,6 +1355,7 @@ static int iproc_pcie_rev_init(struct iproc_pcie *pcie) break; case IPROC_PCIE_PAXB: regs = iproc_pcie_reg_paxb; + pcie->iproc_cfg_read = true; pcie->has_apb_err_disable = true; if (pcie->need_ob_cfg) { pcie->ob_map = paxb_ob_map; @@ -1293,10 +1378,14 @@ static int iproc_pcie_rev_init(struct iproc_pcie *pcie) case IPROC_PCIE_PAXC: regs = iproc_pcie_reg_paxc; pcie->ep_is_internal = true; + pcie->iproc_cfg_read = true; + pcie->rej_unconfig_pf = true; break; case IPROC_PCIE_PAXC_V2: regs = iproc_pcie_reg_paxc_v2; pcie->ep_is_internal = true; + pcie->iproc_cfg_read = true; + pcie->rej_unconfig_pf = true; pcie->need_msi_steer = true; break; default: @@ -1427,6 +1516,24 @@ int iproc_pcie_remove(struct iproc_pcie *pcie) } EXPORT_SYMBOL(iproc_pcie_remove); +/* + * The MSI parsing logic in certain revisions of Broadcom PAXC based root + * complex does not work and needs to be disabled + */ +static void quirk_paxc_disable_msi_parsing(struct pci_dev *pdev) +{ + struct iproc_pcie *pcie = iproc_data(pdev->bus); + + if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE) + iproc_pcie_paxc_v2_msi_steer(pcie, 0, false); +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16f0, + quirk_paxc_disable_msi_parsing); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802, + quirk_paxc_disable_msi_parsing); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804, + quirk_paxc_disable_msi_parsing); + MODULE_AUTHOR("Ray Jui <rjui@broadcom.com>"); MODULE_DESCRIPTION("Broadcom iPROC PCIe common driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-iproc.h b/drivers/pci/controller/pcie-iproc.h index 814b600b383a..4f03ea539805 100644 --- a/drivers/pci/controller/pcie-iproc.h +++ b/drivers/pci/controller/pcie-iproc.h @@ -58,8 +58,13 @@ struct iproc_msi; * @phy: optional PHY device that controls the Serdes * @map_irq: function callback to map interrupts * @ep_is_internal: indicates an internal emulated endpoint device is connected + * @iproc_cfg_read: indicates the iProc config read function should be used + * @rej_unconfig_pf: indicates the root complex needs to detect and reject + * enumeration against unconfigured physical functions emulated in the ASIC * @has_apb_err_disable: indicates the controller can be configured to prevent * unsupported request from being forwarded as an APB bus error + * @fix_paxc_cap: indicates the controller has corrupted capability list in its + * config space registers and requires SW based fixup * * @need_ob_cfg: indicates SW needs to configure the outbound mapping window * @ob: outbound mapping related parameters @@ -84,7 +89,10 @@ struct iproc_pcie { struct phy *phy; int (*map_irq)(const struct pci_dev *, u8, u8); bool ep_is_internal; + bool iproc_cfg_read; + bool rej_unconfig_pf; bool has_apb_err_disable; + bool fix_paxc_cap; bool need_ob_cfg; struct iproc_pcie_ob ob; diff --git a/drivers/pci/controller/pcie-mobiveil.c b/drivers/pci/controller/pcie-mobiveil.c index cf0aa7cee5b0..a939e8d31735 100644 --- a/drivers/pci/controller/pcie-mobiveil.c +++ b/drivers/pci/controller/pcie-mobiveil.c @@ -23,6 +23,8 @@ #include <linux/platform_device.h> #include <linux/slab.h> +#include "../pci.h" + /* register offsets and bit positions */ /* @@ -130,7 +132,7 @@ struct mobiveil_pcie { void __iomem *config_axi_slave_base; /* endpoint config base */ void __iomem *csr_axi_slave_base; /* root port config base */ void __iomem *apb_csr_base; /* MSI register base */ - void __iomem *pcie_reg_base; /* Physical PCIe Controller Base */ + phys_addr_t pcie_reg_base; /* Physical PCIe Controller Base */ struct irq_domain *intx_domain; raw_spinlock_t intx_mask_lock; int irq; diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c index 6beba8ed7b84..b8163c56a142 100644 --- a/drivers/pci/controller/pcie-rockchip-ep.c +++ b/drivers/pci/controller/pcie-rockchip-ep.c @@ -472,7 +472,7 @@ static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn, static int rockchip_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, enum pci_epc_irq_type type, - u8 interrupt_num) + u16 interrupt_num) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index 942b64fc7f1f..fd2dbd7eed7b 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -197,9 +197,20 @@ static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd, struct msi_desc *d int i, best = 1; unsigned long flags; - if (pci_is_bridge(msi_desc_to_pci_dev(desc)) || vmd->msix_count == 1) + if (vmd->msix_count == 1) return &vmd->irqs[0]; + /* + * White list for fast-interrupt handlers. All others will share the + * "slow" interrupt vector. + */ + switch (msi_desc_to_pci_dev(desc)->class) { + case PCI_CLASS_STORAGE_EXPRESS: + break; + default: + return &vmd->irqs[0]; + } + raw_spin_lock_irqsave(&list_lock, flags); for (i = 1; i < vmd->msix_count; i++) if (vmd->irqs[i].count < vmd->irqs[best].count) diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c index 63ed706445b9..3e86fa3c7da3 100644 --- a/drivers/pci/endpoint/functions/pci-epf-test.c +++ b/drivers/pci/endpoint/functions/pci-epf-test.c @@ -18,13 +18,16 @@ #include <linux/pci-epf.h> #include <linux/pci_regs.h> +#define IRQ_TYPE_LEGACY 0 +#define IRQ_TYPE_MSI 1 +#define IRQ_TYPE_MSIX 2 + #define COMMAND_RAISE_LEGACY_IRQ BIT(0) #define COMMAND_RAISE_MSI_IRQ BIT(1) -#define MSI_NUMBER_SHIFT 2 -#define MSI_NUMBER_MASK (0x3f << MSI_NUMBER_SHIFT) -#define COMMAND_READ BIT(8) -#define COMMAND_WRITE BIT(9) -#define COMMAND_COPY BIT(10) +#define COMMAND_RAISE_MSIX_IRQ BIT(2) +#define COMMAND_READ BIT(3) +#define COMMAND_WRITE BIT(4) +#define COMMAND_COPY BIT(5) #define STATUS_READ_SUCCESS BIT(0) #define STATUS_READ_FAIL BIT(1) @@ -45,6 +48,7 @@ struct pci_epf_test { struct pci_epf *epf; enum pci_barno test_reg_bar; bool linkup_notifier; + bool msix_available; struct delayed_work cmd_handler; }; @@ -56,6 +60,8 @@ struct pci_epf_test_reg { u64 dst_addr; u32 size; u32 checksum; + u32 irq_type; + u32 irq_number; } __packed; static struct pci_epf_header test_header = { @@ -244,31 +250,42 @@ err: return ret; } -static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test, u8 irq) +static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test, u8 irq_type, + u16 irq) { - u8 msi_count; struct pci_epf *epf = epf_test->epf; + struct device *dev = &epf->dev; struct pci_epc *epc = epf->epc; enum pci_barno test_reg_bar = epf_test->test_reg_bar; struct pci_epf_test_reg *reg = epf_test->reg[test_reg_bar]; reg->status |= STATUS_IRQ_RAISED; - msi_count = pci_epc_get_msi(epc, epf->func_no); - if (irq > msi_count || msi_count <= 0) + + switch (irq_type) { + case IRQ_TYPE_LEGACY: pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_LEGACY, 0); - else + break; + case IRQ_TYPE_MSI: pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSI, irq); + break; + case IRQ_TYPE_MSIX: + pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSIX, irq); + break; + default: + dev_err(dev, "Failed to raise IRQ, unknown type\n"); + break; + } } static void pci_epf_test_cmd_handler(struct work_struct *work) { int ret; - u8 irq; - u8 msi_count; + int count; u32 command; struct pci_epf_test *epf_test = container_of(work, struct pci_epf_test, cmd_handler.work); struct pci_epf *epf = epf_test->epf; + struct device *dev = &epf->dev; struct pci_epc *epc = epf->epc; enum pci_barno test_reg_bar = epf_test->test_reg_bar; struct pci_epf_test_reg *reg = epf_test->reg[test_reg_bar]; @@ -280,7 +297,10 @@ static void pci_epf_test_cmd_handler(struct work_struct *work) reg->command = 0; reg->status = 0; - irq = (command & MSI_NUMBER_MASK) >> MSI_NUMBER_SHIFT; + if (reg->irq_type > IRQ_TYPE_MSIX) { + dev_err(dev, "Failed to detect IRQ type\n"); + goto reset_handler; + } if (command & COMMAND_RAISE_LEGACY_IRQ) { reg->status = STATUS_IRQ_RAISED; @@ -294,7 +314,8 @@ static void pci_epf_test_cmd_handler(struct work_struct *work) reg->status |= STATUS_WRITE_FAIL; else reg->status |= STATUS_WRITE_SUCCESS; - pci_epf_test_raise_irq(epf_test, irq); + pci_epf_test_raise_irq(epf_test, reg->irq_type, + reg->irq_number); goto reset_handler; } @@ -304,7 +325,8 @@ static void pci_epf_test_cmd_handler(struct work_struct *work) reg->status |= STATUS_READ_SUCCESS; else reg->status |= STATUS_READ_FAIL; - pci_epf_test_raise_irq(epf_test, irq); + pci_epf_test_raise_irq(epf_test, reg->irq_type, + reg->irq_number); goto reset_handler; } @@ -314,16 +336,28 @@ static void pci_epf_test_cmd_handler(struct work_struct *work) reg->status |= STATUS_COPY_SUCCESS; else reg->status |= STATUS_COPY_FAIL; - pci_epf_test_raise_irq(epf_test, irq); + pci_epf_test_raise_irq(epf_test, reg->irq_type, + reg->irq_number); goto reset_handler; } if (command & COMMAND_RAISE_MSI_IRQ) { - msi_count = pci_epc_get_msi(epc, epf->func_no); - if (irq > msi_count || msi_count <= 0) + count = pci_epc_get_msi(epc, epf->func_no); + if (reg->irq_number > count || count <= 0) goto reset_handler; reg->status = STATUS_IRQ_RAISED; - pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSI, irq); + pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSI, + reg->irq_number); + goto reset_handler; + } + + if (command & COMMAND_RAISE_MSIX_IRQ) { + count = pci_epc_get_msix(epc, epf->func_no); + if (reg->irq_number > count || count <= 0) + goto reset_handler; + reg->status = STATUS_IRQ_RAISED; + pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSIX, + reg->irq_number); goto reset_handler; } @@ -440,6 +474,8 @@ static int pci_epf_test_bind(struct pci_epf *epf) else epf_test->linkup_notifier = true; + epf_test->msix_available = epc->features & EPC_FEATURE_MSIX_AVAILABLE; + epf_test->test_reg_bar = EPC_FEATURE_GET_BAR(epc->features); ret = pci_epc_write_header(epc, epf->func_no, header); @@ -457,8 +493,18 @@ static int pci_epf_test_bind(struct pci_epf *epf) return ret; ret = pci_epc_set_msi(epc, epf->func_no, epf->msi_interrupts); - if (ret) + if (ret) { + dev_err(dev, "MSI configuration failed\n"); return ret; + } + + if (epf_test->msix_available) { + ret = pci_epc_set_msix(epc, epf->func_no, epf->msix_interrupts); + if (ret) { + dev_err(dev, "MSI-X configuration failed\n"); + return ret; + } + } if (!epf_test->linkup_notifier) queue_work(kpcitest_workqueue, &epf_test->cmd_handler.work); diff --git a/drivers/pci/endpoint/pci-ep-cfs.c b/drivers/pci/endpoint/pci-ep-cfs.c index 018ea3433cb5..d1288a0bd530 100644 --- a/drivers/pci/endpoint/pci-ep-cfs.c +++ b/drivers/pci/endpoint/pci-ep-cfs.c @@ -286,6 +286,28 @@ static ssize_t pci_epf_msi_interrupts_show(struct config_item *item, to_pci_epf_group(item)->epf->msi_interrupts); } +static ssize_t pci_epf_msix_interrupts_store(struct config_item *item, + const char *page, size_t len) +{ + u16 val; + int ret; + + ret = kstrtou16(page, 0, &val); + if (ret) + return ret; + + to_pci_epf_group(item)->epf->msix_interrupts = val; + + return len; +} + +static ssize_t pci_epf_msix_interrupts_show(struct config_item *item, + char *page) +{ + return sprintf(page, "%d\n", + to_pci_epf_group(item)->epf->msix_interrupts); +} + PCI_EPF_HEADER_R(vendorid) PCI_EPF_HEADER_W_u16(vendorid) @@ -327,6 +349,7 @@ CONFIGFS_ATTR(pci_epf_, subsys_vendor_id); CONFIGFS_ATTR(pci_epf_, subsys_id); CONFIGFS_ATTR(pci_epf_, interrupt_pin); CONFIGFS_ATTR(pci_epf_, msi_interrupts); +CONFIGFS_ATTR(pci_epf_, msix_interrupts); static struct configfs_attribute *pci_epf_attrs[] = { &pci_epf_attr_vendorid, @@ -340,6 +363,7 @@ static struct configfs_attribute *pci_epf_attrs[] = { &pci_epf_attr_subsys_id, &pci_epf_attr_interrupt_pin, &pci_epf_attr_msi_interrupts, + &pci_epf_attr_msix_interrupts, NULL, }; diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index b0ee42739c3c..094dcc3203b8 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -131,13 +131,13 @@ EXPORT_SYMBOL_GPL(pci_epc_start); * pci_epc_raise_irq() - interrupt the host system * @epc: the EPC device which has to interrupt the host * @func_no: the endpoint function number in the EPC device - * @type: specify the type of interrupt; legacy or MSI - * @interrupt_num: the MSI interrupt number + * @type: specify the type of interrupt; legacy, MSI or MSI-X + * @interrupt_num: the MSI or MSI-X interrupt number * - * Invoke to raise an MSI or legacy interrupt + * Invoke to raise an legacy, MSI or MSI-X interrupt */ int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, - enum pci_epc_irq_type type, u8 interrupt_num) + enum pci_epc_irq_type type, u16 interrupt_num) { int ret; unsigned long flags; @@ -201,7 +201,8 @@ int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts) u8 encode_int; unsigned long flags; - if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions) + if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions || + interrupts > 32) return -EINVAL; if (!epc->ops->set_msi) @@ -218,6 +219,63 @@ int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts) EXPORT_SYMBOL_GPL(pci_epc_set_msi); /** + * pci_epc_get_msix() - get the number of MSI-X interrupt numbers allocated + * @epc: the EPC device to which MSI-X interrupts was requested + * @func_no: the endpoint function number in the EPC device + * + * Invoke to get the number of MSI-X interrupts allocated by the RC + */ +int pci_epc_get_msix(struct pci_epc *epc, u8 func_no) +{ + int interrupt; + unsigned long flags; + + if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions) + return 0; + + if (!epc->ops->get_msix) + return 0; + + spin_lock_irqsave(&epc->lock, flags); + interrupt = epc->ops->get_msix(epc, func_no); + spin_unlock_irqrestore(&epc->lock, flags); + + if (interrupt < 0) + return 0; + + return interrupt + 1; +} +EXPORT_SYMBOL_GPL(pci_epc_get_msix); + +/** + * pci_epc_set_msix() - set the number of MSI-X interrupt numbers required + * @epc: the EPC device on which MSI-X has to be configured + * @func_no: the endpoint function number in the EPC device + * @interrupts: number of MSI-X interrupts required by the EPF + * + * Invoke to set the required number of MSI-X interrupts. + */ +int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts) +{ + int ret; + unsigned long flags; + + if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions || + interrupts < 1 || interrupts > 2048) + return -EINVAL; + + if (!epc->ops->set_msix) + return 0; + + spin_lock_irqsave(&epc->lock, flags); + ret = epc->ops->set_msix(epc, func_no, interrupts - 1); + spin_unlock_irqrestore(&epc->lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(pci_epc_set_msix); + +/** * pci_epc_unmap_addr() - unmap CPU address from PCI address * @epc: the EPC device on which address is allocated * @func_no: the endpoint function number in the EPC device diff --git a/drivers/pci/hotplug/acpi_pcihp.c b/drivers/pci/hotplug/acpi_pcihp.c index 5bd6c1573295..6b7c1ed58e7e 100644 --- a/drivers/pci/hotplug/acpi_pcihp.c +++ b/drivers/pci/hotplug/acpi_pcihp.c @@ -74,20 +74,6 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev) struct acpi_buffer string = { ACPI_ALLOCATE_BUFFER, NULL }; /* - * Per PCI firmware specification, we should run the ACPI _OSC - * method to get control of hotplug hardware before using it. If - * an _OSC is missing, we look for an OSHP to do the same thing. - * To handle different BIOS behavior, we look for _OSC on a root - * bridge preferentially (according to PCI fw spec). Later for - * OSHP within the scope of the hotplug controller and its parents, - * up to the host bridge under which this controller exists. - */ - if (shpchp_is_native(pdev)) - return 0; - - /* If _OSC exists, we should not evaluate OSHP */ - - /* * If there's no ACPI host bridge (i.e., ACPI support is compiled * into the kernel but the hardware platform doesn't support ACPI), * there's nothing to do here. @@ -97,9 +83,25 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev) if (!root) return 0; - if (root->osc_support_set) - goto no_control; + /* + * If _OSC exists, it determines whether we're allowed to manage + * the SHPC. We executed it while enumerating the host bridge. + */ + if (root->osc_support_set) { + if (host->native_shpc_hotplug) + return 0; + return -ENODEV; + } + /* + * In the absence of _OSC, we're always allowed to manage the SHPC. + * However, if an OSHP method is present, we must execute it so the + * firmware can transfer control to the OS, e.g., direct interrupts + * to the OS instead of to the firmware. + * + * N.B. The PCI Firmware Spec (r3.2, sec 4.8) does not endorse + * searching up the ACPI hierarchy, so the loops below are suspect. + */ handle = ACPI_HANDLE(&pdev->dev); if (!handle) { /* @@ -128,7 +130,7 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev) if (ACPI_FAILURE(status)) break; } -no_control: + pci_info(pdev, "Cannot get control of SHPC hotplug\n"); kfree(string.pointer); return -ENODEV; diff --git a/drivers/pci/hotplug/acpiphp_core.c b/drivers/pci/hotplug/acpiphp_core.c index 12b5655fd390..ad32ffbc4b91 100644 --- a/drivers/pci/hotplug/acpiphp_core.c +++ b/drivers/pci/hotplug/acpiphp_core.c @@ -254,20 +254,6 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) return 0; } -/** - * release_slot - free up the memory used by a slot - * @hotplug_slot: slot to free - */ -static void release_slot(struct hotplug_slot *hotplug_slot) -{ - struct slot *slot = hotplug_slot->private; - - pr_debug("%s - physical_slot = %s\n", __func__, slot_name(slot)); - - kfree(slot->hotplug_slot); - kfree(slot); -} - /* callback routine to initialize 'struct slot' for each slot */ int acpiphp_register_hotplug_slot(struct acpiphp_slot *acpiphp_slot, unsigned int sun) @@ -287,7 +273,6 @@ int acpiphp_register_hotplug_slot(struct acpiphp_slot *acpiphp_slot, slot->hotplug_slot->info = &slot->info; slot->hotplug_slot->private = slot; - slot->hotplug_slot->release = &release_slot; slot->hotplug_slot->ops = &acpi_hotplug_slot_ops; slot->acpi_slot = acpiphp_slot; @@ -324,13 +309,12 @@ error: void acpiphp_unregister_hotplug_slot(struct acpiphp_slot *acpiphp_slot) { struct slot *slot = acpiphp_slot->slot; - int retval = 0; pr_info("Slot [%s] unregistered\n", slot_name(slot)); - retval = pci_hp_deregister(slot->hotplug_slot); - if (retval) - pr_err("pci_hp_deregister failed with error %d\n", retval); + pci_hp_deregister(slot->hotplug_slot); + kfree(slot->hotplug_slot); + kfree(slot); } diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c index 07b533adc9df..52a339baf06c 100644 --- a/drivers/pci/hotplug/cpci_hotplug_core.c +++ b/drivers/pci/hotplug/cpci_hotplug_core.c @@ -195,10 +195,8 @@ get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value) return 0; } -static void release_slot(struct hotplug_slot *hotplug_slot) +static void release_slot(struct slot *slot) { - struct slot *slot = hotplug_slot->private; - kfree(slot->hotplug_slot->info); kfree(slot->hotplug_slot); pci_dev_put(slot->dev); @@ -253,7 +251,6 @@ cpci_hp_register_bus(struct pci_bus *bus, u8 first, u8 last) snprintf(name, SLOT_NAME_SIZE, "%02x:%02x", bus->number, i); hotplug_slot->private = slot; - hotplug_slot->release = &release_slot; hotplug_slot->ops = &cpci_hotplug_slot_ops; /* @@ -308,12 +305,8 @@ cpci_hp_unregister_bus(struct pci_bus *bus) slots--; dbg("deregistering slot %s", slot_name(slot)); - status = pci_hp_deregister(slot->hotplug_slot); - if (status) { - err("pci_hp_deregister failed with error %d", - status); - break; - } + pci_hp_deregister(slot->hotplug_slot); + release_slot(slot); } } up_write(&list_rwsem); @@ -623,6 +616,7 @@ cleanup_slots(void) list_for_each_entry_safe(slot, tmp, &slot_list, slot_list) { list_del(&slot->slot_list); pci_hp_deregister(slot->hotplug_slot); + release_slot(slot); } cleanup_null: up_write(&list_rwsem); diff --git a/drivers/pci/hotplug/cpqphp_core.c b/drivers/pci/hotplug/cpqphp_core.c index 1797e36ec586..5a06636e910a 100644 --- a/drivers/pci/hotplug/cpqphp_core.c +++ b/drivers/pci/hotplug/cpqphp_core.c @@ -266,17 +266,6 @@ static void __iomem *get_SMBIOS_entry(void __iomem *smbios_start, return previous; } -static void release_slot(struct hotplug_slot *hotplug_slot) -{ - struct slot *slot = hotplug_slot->private; - - dbg("%s - physical_slot = %s\n", __func__, slot_name(slot)); - - kfree(slot->hotplug_slot->info); - kfree(slot->hotplug_slot); - kfree(slot); -} - static int ctrl_slot_cleanup(struct controller *ctrl) { struct slot *old_slot, *next_slot; @@ -285,9 +274,11 @@ static int ctrl_slot_cleanup(struct controller *ctrl) ctrl->slot = NULL; while (old_slot) { - /* memory will be freed by the release_slot callback */ next_slot = old_slot->next; pci_hp_deregister(old_slot->hotplug_slot); + kfree(old_slot->hotplug_slot->info); + kfree(old_slot->hotplug_slot); + kfree(old_slot); old_slot = next_slot; } @@ -678,7 +669,6 @@ static int ctrl_slot_setup(struct controller *ctrl, ((read_slot_enable(ctrl) << 2) >> ctrl_slot) & 0x04; /* register this slot with the hotplug pci core */ - hotplug_slot->release = &release_slot; hotplug_slot->private = slot; snprintf(name, SLOT_NAME_SIZE, "%u", slot->number); hotplug_slot->ops = &cpqphp_hotplug_slot_ops; diff --git a/drivers/pci/hotplug/ibmphp_core.c b/drivers/pci/hotplug/ibmphp_core.c index 1869b0411ce0..4ea57e9019f1 100644 --- a/drivers/pci/hotplug/ibmphp_core.c +++ b/drivers/pci/hotplug/ibmphp_core.c @@ -673,7 +673,20 @@ static void free_slots(void) list_for_each_entry_safe(slot_cur, next, &ibmphp_slot_head, ibm_slot_list) { - pci_hp_deregister(slot_cur->hotplug_slot); + pci_hp_del(slot_cur->hotplug_slot); + slot_cur->ctrl = NULL; + slot_cur->bus_on = NULL; + + /* + * We don't want to actually remove the resources, + * since ibmphp_free_resources() will do just that. + */ + ibmphp_unconfigure_card(&slot_cur, -1); + + pci_hp_destroy(slot_cur->hotplug_slot); + kfree(slot_cur->hotplug_slot->info); + kfree(slot_cur->hotplug_slot); + kfree(slot_cur); } debug("%s -- exit\n", __func__); } diff --git a/drivers/pci/hotplug/ibmphp_ebda.c b/drivers/pci/hotplug/ibmphp_ebda.c index 64549aa24c0f..6f8e90e3ec08 100644 --- a/drivers/pci/hotplug/ibmphp_ebda.c +++ b/drivers/pci/hotplug/ibmphp_ebda.c @@ -699,25 +699,6 @@ static int fillslotinfo(struct hotplug_slot *hotplug_slot) return rc; } -static void release_slot(struct hotplug_slot *hotplug_slot) -{ - struct slot *slot; - - if (!hotplug_slot || !hotplug_slot->private) - return; - - slot = hotplug_slot->private; - kfree(slot->hotplug_slot->info); - kfree(slot->hotplug_slot); - slot->ctrl = NULL; - slot->bus_on = NULL; - - /* we don't want to actually remove the resources, since free_resources will do just that */ - ibmphp_unconfigure_card(&slot, -1); - - kfree(slot); -} - static struct pci_driver ibmphp_driver; /* @@ -941,7 +922,6 @@ static int __init ebda_rsrc_controller(void) tmp_slot->hotplug_slot = hp_slot_ptr; hp_slot_ptr->private = tmp_slot; - hp_slot_ptr->release = release_slot; rc = fillslotinfo(hp_slot_ptr); if (rc) diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c index af92fed46ab7..90fde5f106d8 100644 --- a/drivers/pci/hotplug/pci_hotplug_core.c +++ b/drivers/pci/hotplug/pci_hotplug_core.c @@ -396,8 +396,9 @@ static struct hotplug_slot *get_slot_from_name(const char *name) * @owner: caller module owner * @mod_name: caller module name * - * Registers a hotplug slot with the pci hotplug subsystem, which will allow - * userspace interaction to the slot. + * Prepares a hotplug slot for in-kernel use and immediately publishes it to + * user space in one go. Drivers may alternatively carry out the two steps + * separately by invoking pci_hp_initialize() and pci_hp_add(). * * Returns 0 if successful, anything else for an error. */ @@ -406,45 +407,91 @@ int __pci_hp_register(struct hotplug_slot *slot, struct pci_bus *bus, struct module *owner, const char *mod_name) { int result; + + result = __pci_hp_initialize(slot, bus, devnr, name, owner, mod_name); + if (result) + return result; + + result = pci_hp_add(slot); + if (result) + pci_hp_destroy(slot); + + return result; +} +EXPORT_SYMBOL_GPL(__pci_hp_register); + +/** + * __pci_hp_initialize - prepare hotplug slot for in-kernel use + * @slot: pointer to the &struct hotplug_slot to initialize + * @bus: bus this slot is on + * @devnr: slot number + * @name: name registered with kobject core + * @owner: caller module owner + * @mod_name: caller module name + * + * Allocate and fill in a PCI slot for use by a hotplug driver. Once this has + * been called, the driver may invoke hotplug_slot_name() to get the slot's + * unique name. The driver must be prepared to handle a ->reset_slot callback + * from this point on. + * + * Returns 0 on success or a negative int on error. + */ +int __pci_hp_initialize(struct hotplug_slot *slot, struct pci_bus *bus, + int devnr, const char *name, struct module *owner, + const char *mod_name) +{ struct pci_slot *pci_slot; if (slot == NULL) return -ENODEV; if ((slot->info == NULL) || (slot->ops == NULL)) return -EINVAL; - if (slot->release == NULL) { - dbg("Why are you trying to register a hotplug slot without a proper release function?\n"); - return -EINVAL; - } slot->ops->owner = owner; slot->ops->mod_name = mod_name; - mutex_lock(&pci_hp_mutex); /* * No problems if we call this interface from both ACPI_PCI_SLOT * driver and call it here again. If we've already created the * pci_slot, the interface will simply bump the refcount. */ pci_slot = pci_create_slot(bus, devnr, name, slot); - if (IS_ERR(pci_slot)) { - result = PTR_ERR(pci_slot); - goto out; - } + if (IS_ERR(pci_slot)) + return PTR_ERR(pci_slot); slot->pci_slot = pci_slot; pci_slot->hotplug = slot; + return 0; +} +EXPORT_SYMBOL_GPL(__pci_hp_initialize); - list_add(&slot->slot_list, &pci_hotplug_slot_list); +/** + * pci_hp_add - publish hotplug slot to user space + * @slot: pointer to the &struct hotplug_slot to publish + * + * Make a hotplug slot's sysfs interface available and inform user space of its + * addition by sending a uevent. The hotplug driver must be prepared to handle + * all &struct hotplug_slot_ops callbacks from this point on. + * + * Returns 0 on success or a negative int on error. + */ +int pci_hp_add(struct hotplug_slot *slot) +{ + struct pci_slot *pci_slot = slot->pci_slot; + int result; result = fs_add_slot(pci_slot); + if (result) + return result; + kobject_uevent(&pci_slot->kobj, KOBJ_ADD); - dbg("Added slot %s to the list\n", name); -out: + mutex_lock(&pci_hp_mutex); + list_add(&slot->slot_list, &pci_hotplug_slot_list); mutex_unlock(&pci_hp_mutex); - return result; + dbg("Added slot %s to the list\n", hotplug_slot_name(slot)); + return 0; } -EXPORT_SYMBOL_GPL(__pci_hp_register); +EXPORT_SYMBOL_GPL(pci_hp_add); /** * pci_hp_deregister - deregister a hotplug_slot with the PCI hotplug subsystem @@ -455,35 +502,62 @@ EXPORT_SYMBOL_GPL(__pci_hp_register); * * Returns 0 if successful, anything else for an error. */ -int pci_hp_deregister(struct hotplug_slot *slot) +void pci_hp_deregister(struct hotplug_slot *slot) +{ + pci_hp_del(slot); + pci_hp_destroy(slot); +} +EXPORT_SYMBOL_GPL(pci_hp_deregister); + +/** + * pci_hp_del - unpublish hotplug slot from user space + * @slot: pointer to the &struct hotplug_slot to unpublish + * + * Remove a hotplug slot's sysfs interface. + * + * Returns 0 on success or a negative int on error. + */ +void pci_hp_del(struct hotplug_slot *slot) { struct hotplug_slot *temp; - struct pci_slot *pci_slot; - if (!slot) - return -ENODEV; + if (WARN_ON(!slot)) + return; mutex_lock(&pci_hp_mutex); temp = get_slot_from_name(hotplug_slot_name(slot)); - if (temp != slot) { + if (WARN_ON(temp != slot)) { mutex_unlock(&pci_hp_mutex); - return -ENODEV; + return; } list_del(&slot->slot_list); - - pci_slot = slot->pci_slot; - fs_remove_slot(pci_slot); + mutex_unlock(&pci_hp_mutex); dbg("Removed slot %s from the list\n", hotplug_slot_name(slot)); + fs_remove_slot(slot->pci_slot); +} +EXPORT_SYMBOL_GPL(pci_hp_del); - slot->release(slot); +/** + * pci_hp_destroy - remove hotplug slot from in-kernel use + * @slot: pointer to the &struct hotplug_slot to destroy + * + * Destroy a PCI slot used by a hotplug driver. Once this has been called, + * the driver may no longer invoke hotplug_slot_name() to get the slot's + * unique name. The driver no longer needs to handle a ->reset_slot callback + * from this point on. + * + * Returns 0 on success or a negative int on error. + */ +void pci_hp_destroy(struct hotplug_slot *slot) +{ + struct pci_slot *pci_slot = slot->pci_slot; + + slot->pci_slot = NULL; pci_slot->hotplug = NULL; pci_destroy_slot(pci_slot); - mutex_unlock(&pci_hp_mutex); - - return 0; } -EXPORT_SYMBOL_GPL(pci_hp_deregister); +EXPORT_SYMBOL_GPL(pci_hp_destroy); /** * pci_hp_change_slot_info - changes the slot's information structure in the core diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h index 5f892065585e..811cf83f956d 100644 --- a/drivers/pci/hotplug/pciehp.h +++ b/drivers/pci/hotplug/pciehp.h @@ -21,6 +21,7 @@ #include <linux/delay.h> #include <linux/sched/signal.h> /* signal_pending() */ #include <linux/mutex.h> +#include <linux/rwsem.h> #include <linux/workqueue.h> #include "../pcie/portdrv.h" @@ -57,49 +58,111 @@ do { \ dev_warn(&ctrl->pcie->device, format, ## arg) #define SLOT_NAME_SIZE 10 + +/** + * struct slot - PCIe hotplug slot + * @state: current state machine position + * @ctrl: pointer to the slot's controller structure + * @hotplug_slot: pointer to the structure registered with the PCI hotplug core + * @work: work item to turn the slot on or off after 5 seconds in response to + * an Attention Button press + * @lock: protects reads and writes of @state; + * protects scheduling, execution and cancellation of @work + */ struct slot { u8 state; struct controller *ctrl; struct hotplug_slot *hotplug_slot; - struct delayed_work work; /* work for button event */ + struct delayed_work work; struct mutex lock; - struct mutex hotplug_lock; - struct workqueue_struct *wq; -}; - -struct event_info { - u32 event_type; - struct slot *p_slot; - struct work_struct work; }; +/** + * struct controller - PCIe hotplug controller + * @ctrl_lock: serializes writes to the Slot Control register + * @pcie: pointer to the controller's PCIe port service device + * @reset_lock: prevents access to the Data Link Layer Link Active bit in the + * Link Status register and to the Presence Detect State bit in the Slot + * Status register during a slot reset which may cause them to flap + * @slot: pointer to the controller's slot structure + * @queue: wait queue to wake up on reception of a Command Completed event, + * used for synchronous writes to the Slot Control register + * @slot_cap: cached copy of the Slot Capabilities register + * @slot_ctrl: cached copy of the Slot Control register + * @poll_thread: thread to poll for slot events if no IRQ is available, + * enabled with pciehp_poll_mode module parameter + * @cmd_started: jiffies when the Slot Control register was last written; + * the next write is allowed 1 second later, absent a Command Completed + * interrupt (PCIe r4.0, sec 6.7.3.2) + * @cmd_busy: flag set on Slot Control register write, cleared by IRQ handler + * on reception of a Command Completed event + * @link_active_reporting: cached copy of Data Link Layer Link Active Reporting + * Capable bit in Link Capabilities register; if this bit is zero, the + * Data Link Layer Link Active bit in the Link Status register will never + * be set and the driver is thus confined to wait 1 second before assuming + * the link to a hotplugged device is up and accessing it + * @notification_enabled: whether the IRQ was requested successfully + * @power_fault_detected: whether a power fault was detected by the hardware + * that has not yet been cleared by the user + * @pending_events: used by the IRQ handler to save events retrieved from the + * Slot Status register for later consumption by the IRQ thread + * @request_result: result of last user request submitted to the IRQ thread + * @requester: wait queue to wake up on completion of user request, + * used for synchronous slot enable/disable request via sysfs + */ struct controller { - struct mutex ctrl_lock; /* controller lock */ - struct pcie_device *pcie; /* PCI Express port service */ + struct mutex ctrl_lock; + struct pcie_device *pcie; + struct rw_semaphore reset_lock; struct slot *slot; - wait_queue_head_t queue; /* sleep & wake process */ + wait_queue_head_t queue; u32 slot_cap; u16 slot_ctrl; - struct timer_list poll_timer; + struct task_struct *poll_thread; unsigned long cmd_started; /* jiffies */ unsigned int cmd_busy:1; unsigned int link_active_reporting:1; unsigned int notification_enabled:1; unsigned int power_fault_detected; + atomic_t pending_events; + int request_result; + wait_queue_head_t requester; }; -#define INT_PRESENCE_ON 1 -#define INT_PRESENCE_OFF 2 -#define INT_POWER_FAULT 3 -#define INT_BUTTON_PRESS 4 -#define INT_LINK_UP 5 -#define INT_LINK_DOWN 6 - -#define STATIC_STATE 0 +/** + * DOC: Slot state + * + * @OFF_STATE: slot is powered off, no subordinate devices are enumerated + * @BLINKINGON_STATE: slot will be powered on after the 5 second delay, + * green led is blinking + * @BLINKINGOFF_STATE: slot will be powered off after the 5 second delay, + * green led is blinking + * @POWERON_STATE: slot is currently powering on + * @POWEROFF_STATE: slot is currently powering off + * @ON_STATE: slot is powered on, subordinate devices have been enumerated + */ +#define OFF_STATE 0 #define BLINKINGON_STATE 1 #define BLINKINGOFF_STATE 2 #define POWERON_STATE 3 #define POWEROFF_STATE 4 +#define ON_STATE 5 + +/** + * DOC: Flags to request an action from the IRQ thread + * + * These are stored together with events read from the Slot Status register, + * hence must be greater than its 16-bit width. + * + * %DISABLE_SLOT: Disable the slot in response to a user request via sysfs or + * an Attention Button press after the 5 second delay + * %RERUN_ISR: Used by the IRQ handler to inform the IRQ thread that the + * hotplug port was inaccessible when the interrupt occurred, requiring + * that the IRQ handler is rerun by the IRQ thread after it has made the + * hotplug port accessible by runtime resuming its parents to D0 + */ +#define DISABLE_SLOT (1 << 16) +#define RERUN_ISR (1 << 17) #define ATTN_BUTTN(ctrl) ((ctrl)->slot_cap & PCI_EXP_SLTCAP_ABP) #define POWER_CTRL(ctrl) ((ctrl)->slot_cap & PCI_EXP_SLTCAP_PCP) @@ -113,15 +176,17 @@ struct controller { int pciehp_sysfs_enable_slot(struct slot *slot); int pciehp_sysfs_disable_slot(struct slot *slot); -void pciehp_queue_interrupt_event(struct slot *slot, u32 event_type); +void pciehp_request(struct controller *ctrl, int action); +void pciehp_handle_button_press(struct slot *slot); +void pciehp_handle_disable_request(struct slot *slot); +void pciehp_handle_presence_or_link_change(struct slot *slot, u32 events); int pciehp_configure_device(struct slot *p_slot); -int pciehp_unconfigure_device(struct slot *p_slot); +void pciehp_unconfigure_device(struct slot *p_slot); void pciehp_queue_pushbutton_work(struct work_struct *work); struct controller *pcie_init(struct pcie_device *dev); int pcie_init_notification(struct controller *ctrl); -int pciehp_enable_slot(struct slot *p_slot); -int pciehp_disable_slot(struct slot *p_slot); -void pcie_reenable_notification(struct controller *ctrl); +void pcie_shutdown_notification(struct controller *ctrl); +void pcie_clear_hotplug_events(struct controller *ctrl); int pciehp_power_on_slot(struct slot *slot); void pciehp_power_off_slot(struct slot *slot); void pciehp_get_power_status(struct slot *slot, u8 *status); diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c index 44a6a63802d5..ec48c9433ae5 100644 --- a/drivers/pci/hotplug/pciehp_core.c +++ b/drivers/pci/hotplug/pciehp_core.c @@ -26,11 +26,12 @@ #include <linux/interrupt.h> #include <linux/time.h> +#include "../pci.h" + /* Global variables */ bool pciehp_debug; bool pciehp_poll_mode; int pciehp_poll_time; -static bool pciehp_force; /* * not really modular, but the easiest way to keep compat with existing @@ -39,11 +40,9 @@ static bool pciehp_force; module_param(pciehp_debug, bool, 0644); module_param(pciehp_poll_mode, bool, 0644); module_param(pciehp_poll_time, int, 0644); -module_param(pciehp_force, bool, 0644); MODULE_PARM_DESC(pciehp_debug, "Debugging mode enabled or not"); MODULE_PARM_DESC(pciehp_poll_mode, "Using polling mechanism for hot-plug events or not"); MODULE_PARM_DESC(pciehp_poll_time, "Polling mechanism frequency, in seconds"); -MODULE_PARM_DESC(pciehp_force, "Force pciehp, even if OSHP is missing"); #define PCIE_MODULE_NAME "pciehp" @@ -56,17 +55,6 @@ static int get_latch_status(struct hotplug_slot *slot, u8 *value); static int get_adapter_status(struct hotplug_slot *slot, u8 *value); static int reset_slot(struct hotplug_slot *slot, int probe); -/** - * release_slot - free up the memory used by a slot - * @hotplug_slot: slot to free - */ -static void release_slot(struct hotplug_slot *hotplug_slot) -{ - kfree(hotplug_slot->ops); - kfree(hotplug_slot->info); - kfree(hotplug_slot); -} - static int init_slot(struct controller *ctrl) { struct slot *slot = ctrl->slot; @@ -107,15 +95,14 @@ static int init_slot(struct controller *ctrl) /* register this slot with the hotplug pci core */ hotplug->info = info; hotplug->private = slot; - hotplug->release = &release_slot; hotplug->ops = ops; slot->hotplug_slot = hotplug; snprintf(name, SLOT_NAME_SIZE, "%u", PSN(ctrl)); - retval = pci_hp_register(hotplug, - ctrl->pcie->port->subordinate, 0, name); + retval = pci_hp_initialize(hotplug, + ctrl->pcie->port->subordinate, 0, name); if (retval) - ctrl_err(ctrl, "pci_hp_register failed: error %d\n", retval); + ctrl_err(ctrl, "pci_hp_initialize failed: error %d\n", retval); out: if (retval) { kfree(ops); @@ -127,7 +114,12 @@ out: static void cleanup_slot(struct controller *ctrl) { - pci_hp_deregister(ctrl->slot->hotplug_slot); + struct hotplug_slot *hotplug_slot = ctrl->slot->hotplug_slot; + + pci_hp_destroy(hotplug_slot); + kfree(hotplug_slot->ops); + kfree(hotplug_slot->info); + kfree(hotplug_slot); } /* @@ -136,8 +128,11 @@ static void cleanup_slot(struct controller *ctrl) static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status) { struct slot *slot = hotplug_slot->private; + struct pci_dev *pdev = slot->ctrl->pcie->port; + pci_config_pm_runtime_get(pdev); pciehp_set_attention_status(slot, status); + pci_config_pm_runtime_put(pdev); return 0; } @@ -160,8 +155,11 @@ static int disable_slot(struct hotplug_slot *hotplug_slot) static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) { struct slot *slot = hotplug_slot->private; + struct pci_dev *pdev = slot->ctrl->pcie->port; + pci_config_pm_runtime_get(pdev); pciehp_get_power_status(slot, value); + pci_config_pm_runtime_put(pdev); return 0; } @@ -176,16 +174,22 @@ static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value) static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value) { struct slot *slot = hotplug_slot->private; + struct pci_dev *pdev = slot->ctrl->pcie->port; + pci_config_pm_runtime_get(pdev); pciehp_get_latch_status(slot, value); + pci_config_pm_runtime_put(pdev); return 0; } static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) { struct slot *slot = hotplug_slot->private; + struct pci_dev *pdev = slot->ctrl->pcie->port; + pci_config_pm_runtime_get(pdev); pciehp_get_adapter_status(slot, value); + pci_config_pm_runtime_put(pdev); return 0; } @@ -196,12 +200,40 @@ static int reset_slot(struct hotplug_slot *hotplug_slot, int probe) return pciehp_reset_slot(slot, probe); } +/** + * pciehp_check_presence() - synthesize event if presence has changed + * + * On probe and resume, an explicit presence check is necessary to bring up an + * occupied slot or bring down an unoccupied slot. This can't be triggered by + * events in the Slot Status register, they may be stale and are therefore + * cleared. Secondly, sending an interrupt for "events that occur while + * interrupt generation is disabled [when] interrupt generation is subsequently + * enabled" is optional per PCIe r4.0, sec 6.7.3.4. + */ +static void pciehp_check_presence(struct controller *ctrl) +{ + struct slot *slot = ctrl->slot; + u8 occupied; + + down_read(&ctrl->reset_lock); + mutex_lock(&slot->lock); + + pciehp_get_adapter_status(slot, &occupied); + if ((occupied && (slot->state == OFF_STATE || + slot->state == BLINKINGON_STATE)) || + (!occupied && (slot->state == ON_STATE || + slot->state == BLINKINGOFF_STATE))) + pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC); + + mutex_unlock(&slot->lock); + up_read(&ctrl->reset_lock); +} + static int pciehp_probe(struct pcie_device *dev) { int rc; struct controller *ctrl; struct slot *slot; - u8 occupied, poweron; /* If this is not a "hotplug" service, we have no business here. */ if (dev->service != PCIE_PORT_SERVICE_HP) @@ -238,21 +270,20 @@ static int pciehp_probe(struct pcie_device *dev) goto err_out_free_ctrl_slot; } - /* Check if slot is occupied */ + /* Publish to user space */ slot = ctrl->slot; - pciehp_get_adapter_status(slot, &occupied); - pciehp_get_power_status(slot, &poweron); - if (occupied && pciehp_force) { - mutex_lock(&slot->hotplug_lock); - pciehp_enable_slot(slot); - mutex_unlock(&slot->hotplug_lock); + rc = pci_hp_add(slot->hotplug_slot); + if (rc) { + ctrl_err(ctrl, "Publication to user space failed (%d)\n", rc); + goto err_out_shutdown_notification; } - /* If empty slot's power status is on, turn power off */ - if (!occupied && poweron && POWER_CTRL(ctrl)) - pciehp_power_off_slot(slot); + + pciehp_check_presence(ctrl); return 0; +err_out_shutdown_notification: + pcie_shutdown_notification(ctrl); err_out_free_ctrl_slot: cleanup_slot(ctrl); err_out_release_ctlr: @@ -264,6 +295,8 @@ static void pciehp_remove(struct pcie_device *dev) { struct controller *ctrl = get_service_data(dev); + pci_hp_del(ctrl->slot->hotplug_slot); + pcie_shutdown_notification(ctrl); cleanup_slot(ctrl); pciehp_release_ctrl(ctrl); } @@ -274,27 +307,28 @@ static int pciehp_suspend(struct pcie_device *dev) return 0; } -static int pciehp_resume(struct pcie_device *dev) +static int pciehp_resume_noirq(struct pcie_device *dev) { - struct controller *ctrl; - struct slot *slot; - u8 status; + struct controller *ctrl = get_service_data(dev); + struct slot *slot = ctrl->slot; - ctrl = get_service_data(dev); + /* pci_restore_state() just wrote to the Slot Control register */ + ctrl->cmd_started = jiffies; + ctrl->cmd_busy = true; - /* reinitialize the chipset's event detection logic */ - pcie_reenable_notification(ctrl); + /* clear spurious events from rediscovery of inserted card */ + if (slot->state == ON_STATE || slot->state == BLINKINGOFF_STATE) + pcie_clear_hotplug_events(ctrl); - slot = ctrl->slot; + return 0; +} + +static int pciehp_resume(struct pcie_device *dev) +{ + struct controller *ctrl = get_service_data(dev); + + pciehp_check_presence(ctrl); - /* Check if slot is occupied */ - pciehp_get_adapter_status(slot, &status); - mutex_lock(&slot->hotplug_lock); - if (status) - pciehp_enable_slot(slot); - else - pciehp_disable_slot(slot); - mutex_unlock(&slot->hotplug_lock); return 0; } #endif /* PM */ @@ -309,6 +343,7 @@ static struct pcie_port_service_driver hpdriver_portdrv = { #ifdef CONFIG_PM .suspend = pciehp_suspend, + .resume_noirq = pciehp_resume_noirq, .resume = pciehp_resume, #endif /* PM */ }; diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c index c684faa43387..da7c72372ffc 100644 --- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -17,28 +17,11 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/slab.h> +#include <linux/pm_runtime.h> #include <linux/pci.h> #include "../pci.h" #include "pciehp.h" -static void interrupt_event_handler(struct work_struct *work); - -void pciehp_queue_interrupt_event(struct slot *p_slot, u32 event_type) -{ - struct event_info *info; - - info = kmalloc(sizeof(*info), GFP_ATOMIC); - if (!info) { - ctrl_err(p_slot->ctrl, "dropped event %d (ENOMEM)\n", event_type); - return; - } - - INIT_WORK(&info->work, interrupt_event_handler); - info->event_type = event_type; - info->p_slot = p_slot; - queue_work(p_slot->wq, &info->work); -} - /* The following routines constitute the bulk of the hotplug controller logic */ @@ -119,14 +102,11 @@ err_exit: * remove_board - Turns off slot and LEDs * @p_slot: slot where board is being removed */ -static int remove_board(struct slot *p_slot) +static void remove_board(struct slot *p_slot) { - int retval; struct controller *ctrl = p_slot->ctrl; - retval = pciehp_unconfigure_device(p_slot); - if (retval) - return retval; + pciehp_unconfigure_device(p_slot); if (POWER_CTRL(ctrl)) { pciehp_power_off_slot(p_slot); @@ -141,86 +121,30 @@ static int remove_board(struct slot *p_slot) /* turn off Green LED */ pciehp_green_led_off(p_slot); - return 0; } -struct power_work_info { - struct slot *p_slot; - struct work_struct work; - unsigned int req; -#define DISABLE_REQ 0 -#define ENABLE_REQ 1 -}; - -/** - * pciehp_power_thread - handle pushbutton events - * @work: &struct work_struct describing work to be done - * - * Scheduled procedure to handle blocking stuff for the pushbuttons. - * Handles all pending events and exits. - */ -static void pciehp_power_thread(struct work_struct *work) -{ - struct power_work_info *info = - container_of(work, struct power_work_info, work); - struct slot *p_slot = info->p_slot; - int ret; - - switch (info->req) { - case DISABLE_REQ: - mutex_lock(&p_slot->hotplug_lock); - pciehp_disable_slot(p_slot); - mutex_unlock(&p_slot->hotplug_lock); - mutex_lock(&p_slot->lock); - p_slot->state = STATIC_STATE; - mutex_unlock(&p_slot->lock); - break; - case ENABLE_REQ: - mutex_lock(&p_slot->hotplug_lock); - ret = pciehp_enable_slot(p_slot); - mutex_unlock(&p_slot->hotplug_lock); - if (ret) - pciehp_green_led_off(p_slot); - mutex_lock(&p_slot->lock); - p_slot->state = STATIC_STATE; - mutex_unlock(&p_slot->lock); - break; - default: - break; - } - - kfree(info); -} +static int pciehp_enable_slot(struct slot *slot); +static int pciehp_disable_slot(struct slot *slot); -static void pciehp_queue_power_work(struct slot *p_slot, int req) +void pciehp_request(struct controller *ctrl, int action) { - struct power_work_info *info; - - p_slot->state = (req == ENABLE_REQ) ? POWERON_STATE : POWEROFF_STATE; - - info = kmalloc(sizeof(*info), GFP_KERNEL); - if (!info) { - ctrl_err(p_slot->ctrl, "no memory to queue %s request\n", - (req == ENABLE_REQ) ? "poweron" : "poweroff"); - return; - } - info->p_slot = p_slot; - INIT_WORK(&info->work, pciehp_power_thread); - info->req = req; - queue_work(p_slot->wq, &info->work); + atomic_or(action, &ctrl->pending_events); + if (!pciehp_poll_mode) + irq_wake_thread(ctrl->pcie->irq, ctrl); } void pciehp_queue_pushbutton_work(struct work_struct *work) { struct slot *p_slot = container_of(work, struct slot, work.work); + struct controller *ctrl = p_slot->ctrl; mutex_lock(&p_slot->lock); switch (p_slot->state) { case BLINKINGOFF_STATE: - pciehp_queue_power_work(p_slot, DISABLE_REQ); + pciehp_request(ctrl, DISABLE_SLOT); break; case BLINKINGON_STATE: - pciehp_queue_power_work(p_slot, ENABLE_REQ); + pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC); break; default: break; @@ -228,18 +152,15 @@ void pciehp_queue_pushbutton_work(struct work_struct *work) mutex_unlock(&p_slot->lock); } -/* - * Note: This function must be called with slot->lock held - */ -static void handle_button_press_event(struct slot *p_slot) +void pciehp_handle_button_press(struct slot *p_slot) { struct controller *ctrl = p_slot->ctrl; - u8 getstatus; + mutex_lock(&p_slot->lock); switch (p_slot->state) { - case STATIC_STATE: - pciehp_get_power_status(p_slot, &getstatus); - if (getstatus) { + case OFF_STATE: + case ON_STATE: + if (p_slot->state == ON_STATE) { p_slot->state = BLINKINGOFF_STATE; ctrl_info(ctrl, "Slot(%s): Powering off due to button press\n", slot_name(p_slot)); @@ -251,7 +172,7 @@ static void handle_button_press_event(struct slot *p_slot) /* blink green LED and turn off amber */ pciehp_green_led_blink(p_slot); pciehp_set_attention_status(p_slot, 0); - queue_delayed_work(p_slot->wq, &p_slot->work, 5*HZ); + schedule_delayed_work(&p_slot->work, 5 * HZ); break; case BLINKINGOFF_STATE: case BLINKINGON_STATE: @@ -262,118 +183,104 @@ static void handle_button_press_event(struct slot *p_slot) */ ctrl_info(ctrl, "Slot(%s): Button cancel\n", slot_name(p_slot)); cancel_delayed_work(&p_slot->work); - if (p_slot->state == BLINKINGOFF_STATE) + if (p_slot->state == BLINKINGOFF_STATE) { + p_slot->state = ON_STATE; pciehp_green_led_on(p_slot); - else + } else { + p_slot->state = OFF_STATE; pciehp_green_led_off(p_slot); + } pciehp_set_attention_status(p_slot, 0); ctrl_info(ctrl, "Slot(%s): Action canceled due to button press\n", slot_name(p_slot)); - p_slot->state = STATIC_STATE; - break; - case POWEROFF_STATE: - case POWERON_STATE: - /* - * Ignore if the slot is on power-on or power-off state; - * this means that the previous attention button action - * to hot-add or hot-remove is undergoing - */ - ctrl_info(ctrl, "Slot(%s): Button ignored\n", - slot_name(p_slot)); break; default: ctrl_err(ctrl, "Slot(%s): Ignoring invalid state %#x\n", slot_name(p_slot), p_slot->state); break; } + mutex_unlock(&p_slot->lock); } -/* - * Note: This function must be called with slot->lock held - */ -static void handle_link_event(struct slot *p_slot, u32 event) +void pciehp_handle_disable_request(struct slot *slot) { - struct controller *ctrl = p_slot->ctrl; + struct controller *ctrl = slot->ctrl; - switch (p_slot->state) { + mutex_lock(&slot->lock); + switch (slot->state) { case BLINKINGON_STATE: case BLINKINGOFF_STATE: - cancel_delayed_work(&p_slot->work); - /* Fall through */ - case STATIC_STATE: - pciehp_queue_power_work(p_slot, event == INT_LINK_UP ? - ENABLE_REQ : DISABLE_REQ); - break; - case POWERON_STATE: - if (event == INT_LINK_UP) { - ctrl_info(ctrl, "Slot(%s): Link Up event ignored; already powering on\n", - slot_name(p_slot)); - } else { - ctrl_info(ctrl, "Slot(%s): Link Down event queued; currently getting powered on\n", - slot_name(p_slot)); - pciehp_queue_power_work(p_slot, DISABLE_REQ); - } - break; - case POWEROFF_STATE: - if (event == INT_LINK_UP) { - ctrl_info(ctrl, "Slot(%s): Link Up event queued; currently getting powered off\n", - slot_name(p_slot)); - pciehp_queue_power_work(p_slot, ENABLE_REQ); - } else { - ctrl_info(ctrl, "Slot(%s): Link Down event ignored; already powering off\n", - slot_name(p_slot)); - } - break; - default: - ctrl_err(ctrl, "Slot(%s): Ignoring invalid state %#x\n", - slot_name(p_slot), p_slot->state); + cancel_delayed_work(&slot->work); break; } + slot->state = POWEROFF_STATE; + mutex_unlock(&slot->lock); + + ctrl->request_result = pciehp_disable_slot(slot); } -static void interrupt_event_handler(struct work_struct *work) +void pciehp_handle_presence_or_link_change(struct slot *slot, u32 events) { - struct event_info *info = container_of(work, struct event_info, work); - struct slot *p_slot = info->p_slot; - struct controller *ctrl = p_slot->ctrl; - - mutex_lock(&p_slot->lock); - switch (info->event_type) { - case INT_BUTTON_PRESS: - handle_button_press_event(p_slot); - break; - case INT_POWER_FAULT: - if (!POWER_CTRL(ctrl)) - break; - pciehp_set_attention_status(p_slot, 1); - pciehp_green_led_off(p_slot); - break; - case INT_PRESENCE_ON: - pciehp_queue_power_work(p_slot, ENABLE_REQ); + struct controller *ctrl = slot->ctrl; + bool link_active; + u8 present; + + /* + * If the slot is on and presence or link has changed, turn it off. + * Even if it's occupied again, we cannot assume the card is the same. + */ + mutex_lock(&slot->lock); + switch (slot->state) { + case BLINKINGOFF_STATE: + cancel_delayed_work(&slot->work); + /* fall through */ + case ON_STATE: + slot->state = POWEROFF_STATE; + mutex_unlock(&slot->lock); + if (events & PCI_EXP_SLTSTA_DLLSC) + ctrl_info(ctrl, "Slot(%s): Link Down\n", + slot_name(slot)); + if (events & PCI_EXP_SLTSTA_PDC) + ctrl_info(ctrl, "Slot(%s): Card not present\n", + slot_name(slot)); + pciehp_disable_slot(slot); break; - case INT_PRESENCE_OFF: - /* - * Regardless of surprise capability, we need to - * definitely remove a card that has been pulled out! - */ - pciehp_queue_power_work(p_slot, DISABLE_REQ); + default: + mutex_unlock(&slot->lock); break; - case INT_LINK_UP: - case INT_LINK_DOWN: - handle_link_event(p_slot, info->event_type); + } + + /* Turn the slot on if it's occupied or link is up */ + mutex_lock(&slot->lock); + pciehp_get_adapter_status(slot, &present); + link_active = pciehp_check_link_active(ctrl); + if (!present && !link_active) { + mutex_unlock(&slot->lock); + return; + } + + switch (slot->state) { + case BLINKINGON_STATE: + cancel_delayed_work(&slot->work); + /* fall through */ + case OFF_STATE: + slot->state = POWERON_STATE; + mutex_unlock(&slot->lock); + if (present) + ctrl_info(ctrl, "Slot(%s): Card present\n", + slot_name(slot)); + if (link_active) + ctrl_info(ctrl, "Slot(%s): Link Up\n", + slot_name(slot)); + ctrl->request_result = pciehp_enable_slot(slot); break; default: + mutex_unlock(&slot->lock); break; } - mutex_unlock(&p_slot->lock); - - kfree(info); } -/* - * Note: This function must be called with slot->hotplug_lock held - */ -int pciehp_enable_slot(struct slot *p_slot) +static int __pciehp_enable_slot(struct slot *p_slot) { u8 getstatus = 0; struct controller *ctrl = p_slot->ctrl; @@ -404,17 +311,29 @@ int pciehp_enable_slot(struct slot *p_slot) return board_added(p_slot); } -/* - * Note: This function must be called with slot->hotplug_lock held - */ -int pciehp_disable_slot(struct slot *p_slot) +static int pciehp_enable_slot(struct slot *slot) +{ + struct controller *ctrl = slot->ctrl; + int ret; + + pm_runtime_get_sync(&ctrl->pcie->port->dev); + ret = __pciehp_enable_slot(slot); + if (ret && ATTN_BUTTN(ctrl)) + pciehp_green_led_off(slot); /* may be blinking */ + pm_runtime_put(&ctrl->pcie->port->dev); + + mutex_lock(&slot->lock); + slot->state = ret ? OFF_STATE : ON_STATE; + mutex_unlock(&slot->lock); + + return ret; +} + +static int __pciehp_disable_slot(struct slot *p_slot) { u8 getstatus = 0; struct controller *ctrl = p_slot->ctrl; - if (!p_slot->ctrl) - return 1; - if (POWER_CTRL(p_slot->ctrl)) { pciehp_get_power_status(p_slot, &getstatus); if (!getstatus) { @@ -424,32 +343,50 @@ int pciehp_disable_slot(struct slot *p_slot) } } - return remove_board(p_slot); + remove_board(p_slot); + return 0; +} + +static int pciehp_disable_slot(struct slot *slot) +{ + struct controller *ctrl = slot->ctrl; + int ret; + + pm_runtime_get_sync(&ctrl->pcie->port->dev); + ret = __pciehp_disable_slot(slot); + pm_runtime_put(&ctrl->pcie->port->dev); + + mutex_lock(&slot->lock); + slot->state = OFF_STATE; + mutex_unlock(&slot->lock); + + return ret; } int pciehp_sysfs_enable_slot(struct slot *p_slot) { - int retval = -ENODEV; struct controller *ctrl = p_slot->ctrl; mutex_lock(&p_slot->lock); switch (p_slot->state) { case BLINKINGON_STATE: - cancel_delayed_work(&p_slot->work); - case STATIC_STATE: - p_slot->state = POWERON_STATE; + case OFF_STATE: mutex_unlock(&p_slot->lock); - mutex_lock(&p_slot->hotplug_lock); - retval = pciehp_enable_slot(p_slot); - mutex_unlock(&p_slot->hotplug_lock); - mutex_lock(&p_slot->lock); - p_slot->state = STATIC_STATE; - break; + /* + * The IRQ thread becomes a no-op if the user pulls out the + * card before the thread wakes up, so initialize to -ENODEV. + */ + ctrl->request_result = -ENODEV; + pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC); + wait_event(ctrl->requester, + !atomic_read(&ctrl->pending_events)); + return ctrl->request_result; case POWERON_STATE: ctrl_info(ctrl, "Slot(%s): Already in powering on state\n", slot_name(p_slot)); break; case BLINKINGOFF_STATE: + case ON_STATE: case POWEROFF_STATE: ctrl_info(ctrl, "Slot(%s): Already enabled\n", slot_name(p_slot)); @@ -461,32 +398,28 @@ int pciehp_sysfs_enable_slot(struct slot *p_slot) } mutex_unlock(&p_slot->lock); - return retval; + return -ENODEV; } int pciehp_sysfs_disable_slot(struct slot *p_slot) { - int retval = -ENODEV; struct controller *ctrl = p_slot->ctrl; mutex_lock(&p_slot->lock); switch (p_slot->state) { case BLINKINGOFF_STATE: - cancel_delayed_work(&p_slot->work); - case STATIC_STATE: - p_slot->state = POWEROFF_STATE; + case ON_STATE: mutex_unlock(&p_slot->lock); - mutex_lock(&p_slot->hotplug_lock); - retval = pciehp_disable_slot(p_slot); - mutex_unlock(&p_slot->hotplug_lock); - mutex_lock(&p_slot->lock); - p_slot->state = STATIC_STATE; - break; + pciehp_request(ctrl, DISABLE_SLOT); + wait_event(ctrl->requester, + !atomic_read(&ctrl->pending_events)); + return ctrl->request_result; case POWEROFF_STATE: ctrl_info(ctrl, "Slot(%s): Already in powering off state\n", slot_name(p_slot)); break; case BLINKINGON_STATE: + case OFF_STATE: case POWERON_STATE: ctrl_info(ctrl, "Slot(%s): Already disabled\n", slot_name(p_slot)); @@ -498,5 +431,5 @@ int pciehp_sysfs_disable_slot(struct slot *p_slot) } mutex_unlock(&p_slot->lock); - return retval; + return -ENODEV; } diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 718b6073afad..7136e3430925 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -17,8 +17,9 @@ #include <linux/types.h> #include <linux/signal.h> #include <linux/jiffies.h> -#include <linux/timer.h> +#include <linux/kthread.h> #include <linux/pci.h> +#include <linux/pm_runtime.h> #include <linux/interrupt.h> #include <linux/time.h> #include <linux/slab.h> @@ -31,47 +32,24 @@ static inline struct pci_dev *ctrl_dev(struct controller *ctrl) return ctrl->pcie->port; } -static irqreturn_t pcie_isr(int irq, void *dev_id); -static void start_int_poll_timer(struct controller *ctrl, int sec); - -/* This is the interrupt polling timeout function. */ -static void int_poll_timeout(struct timer_list *t) -{ - struct controller *ctrl = from_timer(ctrl, t, poll_timer); - - /* Poll for interrupt events. regs == NULL => polling */ - pcie_isr(0, ctrl); - - if (!pciehp_poll_time) - pciehp_poll_time = 2; /* default polling interval is 2 sec */ - - start_int_poll_timer(ctrl, pciehp_poll_time); -} - -/* This function starts the interrupt polling timer. */ -static void start_int_poll_timer(struct controller *ctrl, int sec) -{ - /* Clamp to sane value */ - if ((sec <= 0) || (sec > 60)) - sec = 2; - - ctrl->poll_timer.expires = jiffies + sec * HZ; - add_timer(&ctrl->poll_timer); -} +static irqreturn_t pciehp_isr(int irq, void *dev_id); +static irqreturn_t pciehp_ist(int irq, void *dev_id); +static int pciehp_poll(void *data); static inline int pciehp_request_irq(struct controller *ctrl) { int retval, irq = ctrl->pcie->irq; - /* Install interrupt polling timer. Start with 10 sec delay */ if (pciehp_poll_mode) { - timer_setup(&ctrl->poll_timer, int_poll_timeout, 0); - start_int_poll_timer(ctrl, 10); - return 0; + ctrl->poll_thread = kthread_run(&pciehp_poll, ctrl, + "pciehp_poll-%s", + slot_name(ctrl->slot)); + return PTR_ERR_OR_ZERO(ctrl->poll_thread); } /* Installs the interrupt handler */ - retval = request_irq(irq, pcie_isr, IRQF_SHARED, MY_NAME, ctrl); + retval = request_threaded_irq(irq, pciehp_isr, pciehp_ist, + IRQF_SHARED, MY_NAME, ctrl); if (retval) ctrl_err(ctrl, "Cannot get irq %d for the hotplug controller\n", irq); @@ -81,7 +59,7 @@ static inline int pciehp_request_irq(struct controller *ctrl) static inline void pciehp_free_irq(struct controller *ctrl) { if (pciehp_poll_mode) - del_timer_sync(&ctrl->poll_timer); + kthread_stop(ctrl->poll_thread); else free_irq(ctrl->pcie->irq, ctrl); } @@ -293,6 +271,11 @@ int pciehp_check_link_status(struct controller *ctrl) found = pci_bus_check_dev(ctrl->pcie->port->subordinate, PCI_DEVFN(0, 0)); + /* ignore link or presence changes up to this point */ + if (found) + atomic_and(~(PCI_EXP_SLTSTA_DLLSC | PCI_EXP_SLTSTA_PDC), + &ctrl->pending_events); + pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status); ctrl_dbg(ctrl, "%s: lnk_status = %x\n", __func__, lnk_status); if ((lnk_status & PCI_EXP_LNKSTA_LT) || @@ -339,7 +322,9 @@ int pciehp_get_raw_indicator_status(struct hotplug_slot *hotplug_slot, struct pci_dev *pdev = ctrl_dev(slot->ctrl); u16 slot_ctrl; + pci_config_pm_runtime_get(pdev); pcie_capability_read_word(pdev, PCI_EXP_SLTCTL, &slot_ctrl); + pci_config_pm_runtime_put(pdev); *status = (slot_ctrl & (PCI_EXP_SLTCTL_AIC | PCI_EXP_SLTCTL_PIC)) >> 6; return 0; } @@ -350,7 +335,9 @@ void pciehp_get_attention_status(struct slot *slot, u8 *status) struct pci_dev *pdev = ctrl_dev(ctrl); u16 slot_ctrl; + pci_config_pm_runtime_get(pdev); pcie_capability_read_word(pdev, PCI_EXP_SLTCTL, &slot_ctrl); + pci_config_pm_runtime_put(pdev); ctrl_dbg(ctrl, "%s: SLOTCTRL %x, value read %x\n", __func__, pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_ctrl); @@ -425,9 +412,12 @@ int pciehp_set_raw_indicator_status(struct hotplug_slot *hotplug_slot, { struct slot *slot = hotplug_slot->private; struct controller *ctrl = slot->ctrl; + struct pci_dev *pdev = ctrl_dev(ctrl); + pci_config_pm_runtime_get(pdev); pcie_write_cmd_nowait(ctrl, status << 6, PCI_EXP_SLTCTL_AIC | PCI_EXP_SLTCTL_PIC); + pci_config_pm_runtime_put(pdev); return 0; } @@ -539,20 +529,35 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id) { struct controller *ctrl = (struct controller *)dev_id; struct pci_dev *pdev = ctrl_dev(ctrl); - struct pci_bus *subordinate = pdev->subordinate; - struct pci_dev *dev; - struct slot *slot = ctrl->slot; + struct device *parent = pdev->dev.parent; u16 status, events; - u8 present; - bool link; - /* Interrupts cannot originate from a controller that's asleep */ + /* + * Interrupts only occur in D3hot or shallower (PCIe r4.0, sec 6.7.3.4). + */ if (pdev->current_state == PCI_D3cold) return IRQ_NONE; + /* + * Keep the port accessible by holding a runtime PM ref on its parent. + * Defer resume of the parent to the IRQ thread if it's suspended. + * Mask the interrupt until then. + */ + if (parent) { + pm_runtime_get_noresume(parent); + if (!pm_runtime_active(parent)) { + pm_runtime_put(parent); + disable_irq_nosync(irq); + atomic_or(RERUN_ISR, &ctrl->pending_events); + return IRQ_WAKE_THREAD; + } + } + pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &status); if (status == (u16) ~0) { ctrl_info(ctrl, "%s: no response from device\n", __func__); + if (parent) + pm_runtime_put(parent); return IRQ_NONE; } @@ -571,86 +576,119 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id) if (ctrl->power_fault_detected) events &= ~PCI_EXP_SLTSTA_PFD; - if (!events) + if (!events) { + if (parent) + pm_runtime_put(parent); return IRQ_NONE; - - /* Capture link status before clearing interrupts */ - if (events & PCI_EXP_SLTSTA_DLLSC) - link = pciehp_check_link_active(ctrl); + } pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, events); ctrl_dbg(ctrl, "pending interrupts %#06x from Slot Status\n", events); + if (parent) + pm_runtime_put(parent); - /* Check Command Complete Interrupt Pending */ + /* + * Command Completed notifications are not deferred to the + * IRQ thread because it may be waiting for their arrival. + */ if (events & PCI_EXP_SLTSTA_CC) { ctrl->cmd_busy = 0; smp_mb(); wake_up(&ctrl->queue); + + if (events == PCI_EXP_SLTSTA_CC) + return IRQ_HANDLED; + + events &= ~PCI_EXP_SLTSTA_CC; + } + + if (pdev->ignore_hotplug) { + ctrl_dbg(ctrl, "ignoring hotplug event %#06x\n", events); + return IRQ_HANDLED; } - if (subordinate) { - list_for_each_entry(dev, &subordinate->devices, bus_list) { - if (dev->ignore_hotplug) { - ctrl_dbg(ctrl, "ignoring hotplug event %#06x (%s requested no hotplug)\n", - events, pci_name(dev)); - return IRQ_HANDLED; - } + /* Save pending events for consumption by IRQ thread. */ + atomic_or(events, &ctrl->pending_events); + return IRQ_WAKE_THREAD; +} + +static irqreturn_t pciehp_ist(int irq, void *dev_id) +{ + struct controller *ctrl = (struct controller *)dev_id; + struct pci_dev *pdev = ctrl_dev(ctrl); + struct slot *slot = ctrl->slot; + irqreturn_t ret; + u32 events; + + pci_config_pm_runtime_get(pdev); + + /* rerun pciehp_isr() if the port was inaccessible on interrupt */ + if (atomic_fetch_and(~RERUN_ISR, &ctrl->pending_events) & RERUN_ISR) { + ret = pciehp_isr(irq, dev_id); + enable_irq(irq); + if (ret != IRQ_WAKE_THREAD) { + pci_config_pm_runtime_put(pdev); + return ret; } } + synchronize_hardirq(irq); + events = atomic_xchg(&ctrl->pending_events, 0); + if (!events) { + pci_config_pm_runtime_put(pdev); + return IRQ_NONE; + } + /* Check Attention Button Pressed */ if (events & PCI_EXP_SLTSTA_ABP) { ctrl_info(ctrl, "Slot(%s): Attention button pressed\n", slot_name(slot)); - pciehp_queue_interrupt_event(slot, INT_BUTTON_PRESS); + pciehp_handle_button_press(slot); } /* - * Check Link Status Changed at higher precedence than Presence - * Detect Changed. The PDS value may be set to "card present" from - * out-of-band detection, which may be in conflict with a Link Down - * and cause the wrong event to queue. + * Disable requests have higher priority than Presence Detect Changed + * or Data Link Layer State Changed events. */ - if (events & PCI_EXP_SLTSTA_DLLSC) { - ctrl_info(ctrl, "Slot(%s): Link %s\n", slot_name(slot), - link ? "Up" : "Down"); - pciehp_queue_interrupt_event(slot, link ? INT_LINK_UP : - INT_LINK_DOWN); - } else if (events & PCI_EXP_SLTSTA_PDC) { - present = !!(status & PCI_EXP_SLTSTA_PDS); - ctrl_info(ctrl, "Slot(%s): Card %spresent\n", slot_name(slot), - present ? "" : "not "); - pciehp_queue_interrupt_event(slot, present ? INT_PRESENCE_ON : - INT_PRESENCE_OFF); - } + down_read(&ctrl->reset_lock); + if (events & DISABLE_SLOT) + pciehp_handle_disable_request(slot); + else if (events & (PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC)) + pciehp_handle_presence_or_link_change(slot, events); + up_read(&ctrl->reset_lock); /* Check Power Fault Detected */ if ((events & PCI_EXP_SLTSTA_PFD) && !ctrl->power_fault_detected) { ctrl->power_fault_detected = 1; ctrl_err(ctrl, "Slot(%s): Power fault\n", slot_name(slot)); - pciehp_queue_interrupt_event(slot, INT_POWER_FAULT); + pciehp_set_attention_status(slot, 1); + pciehp_green_led_off(slot); } + pci_config_pm_runtime_put(pdev); + wake_up(&ctrl->requester); return IRQ_HANDLED; } -static irqreturn_t pcie_isr(int irq, void *dev_id) +static int pciehp_poll(void *data) { - irqreturn_t rc, handled = IRQ_NONE; + struct controller *ctrl = data; - /* - * To guarantee that all interrupt events are serviced, we need to - * re-inspect Slot Status register after clearing what is presumed - * to be the last pending interrupt. - */ - do { - rc = pciehp_isr(irq, dev_id); - if (rc == IRQ_HANDLED) - handled = IRQ_HANDLED; - } while (rc == IRQ_HANDLED); + schedule_timeout_idle(10 * HZ); /* start with 10 sec delay */ + + while (!kthread_should_stop()) { + /* poll for interrupt events or user requests */ + while (pciehp_isr(IRQ_NOTCONNECTED, ctrl) == IRQ_WAKE_THREAD || + atomic_read(&ctrl->pending_events)) + pciehp_ist(IRQ_NOTCONNECTED, ctrl); - /* Return IRQ_HANDLED if we handled one or more events */ - return handled; + if (pciehp_poll_time <= 0 || pciehp_poll_time > 60) + pciehp_poll_time = 2; /* clamp to sane value */ + + schedule_timeout_idle(pciehp_poll_time * HZ); + } + + return 0; } static void pcie_enable_notification(struct controller *ctrl) @@ -691,17 +729,6 @@ static void pcie_enable_notification(struct controller *ctrl) pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, cmd); } -void pcie_reenable_notification(struct controller *ctrl) -{ - /* - * Clear both Presence and Data Link Layer Changed to make sure - * those events still fire after we have re-enabled them. - */ - pcie_capability_write_word(ctrl->pcie->port, PCI_EXP_SLTSTA, - PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC); - pcie_enable_notification(ctrl); -} - static void pcie_disable_notification(struct controller *ctrl) { u16 mask; @@ -715,6 +742,12 @@ static void pcie_disable_notification(struct controller *ctrl) pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, 0); } +void pcie_clear_hotplug_events(struct controller *ctrl) +{ + pcie_capability_write_word(ctrl_dev(ctrl), PCI_EXP_SLTSTA, + PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC); +} + /* * pciehp has a 1:1 bus:slot relationship so we ultimately want a secondary * bus reset of the bridge, but at the same time we want to ensure that it is @@ -728,10 +761,13 @@ int pciehp_reset_slot(struct slot *slot, int probe) struct controller *ctrl = slot->ctrl; struct pci_dev *pdev = ctrl_dev(ctrl); u16 stat_mask = 0, ctrl_mask = 0; + int rc; if (probe) return 0; + down_write(&ctrl->reset_lock); + if (!ATTN_BUTTN(ctrl)) { ctrl_mask |= PCI_EXP_SLTCTL_PDCE; stat_mask |= PCI_EXP_SLTSTA_PDC; @@ -742,18 +778,16 @@ int pciehp_reset_slot(struct slot *slot, int probe) pcie_write_cmd(ctrl, 0, ctrl_mask); ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__, pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, 0); - if (pciehp_poll_mode) - del_timer_sync(&ctrl->poll_timer); - pci_reset_bridge_secondary_bus(ctrl->pcie->port); + rc = pci_bridge_secondary_bus_reset(ctrl->pcie->port); pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, stat_mask); pcie_write_cmd_nowait(ctrl, ctrl_mask, ctrl_mask); ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__, pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, ctrl_mask); - if (pciehp_poll_mode) - int_poll_timeout(&ctrl->poll_timer); - return 0; + + up_write(&ctrl->reset_lock); + return rc; } int pcie_init_notification(struct controller *ctrl) @@ -765,7 +799,7 @@ int pcie_init_notification(struct controller *ctrl) return 0; } -static void pcie_shutdown_notification(struct controller *ctrl) +void pcie_shutdown_notification(struct controller *ctrl) { if (ctrl->notification_enabled) { pcie_disable_notification(ctrl); @@ -776,32 +810,29 @@ static void pcie_shutdown_notification(struct controller *ctrl) static int pcie_init_slot(struct controller *ctrl) { + struct pci_bus *subordinate = ctrl_dev(ctrl)->subordinate; struct slot *slot; slot = kzalloc(sizeof(*slot), GFP_KERNEL); if (!slot) return -ENOMEM; - slot->wq = alloc_ordered_workqueue("pciehp-%u", 0, PSN(ctrl)); - if (!slot->wq) - goto abort; + down_read(&pci_bus_sem); + slot->state = list_empty(&subordinate->devices) ? OFF_STATE : ON_STATE; + up_read(&pci_bus_sem); slot->ctrl = ctrl; mutex_init(&slot->lock); - mutex_init(&slot->hotplug_lock); INIT_DELAYED_WORK(&slot->work, pciehp_queue_pushbutton_work); ctrl->slot = slot; return 0; -abort: - kfree(slot); - return -ENOMEM; } static void pcie_cleanup_slot(struct controller *ctrl) { struct slot *slot = ctrl->slot; - cancel_delayed_work(&slot->work); - destroy_workqueue(slot->wq); + + cancel_delayed_work_sync(&slot->work); kfree(slot); } @@ -826,6 +857,7 @@ struct controller *pcie_init(struct pcie_device *dev) { struct controller *ctrl; u32 slot_cap, link_cap; + u8 occupied, poweron; struct pci_dev *pdev = dev->port; ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); @@ -847,6 +879,8 @@ struct controller *pcie_init(struct pcie_device *dev) ctrl->slot_cap = slot_cap; mutex_init(&ctrl->ctrl_lock); + init_rwsem(&ctrl->reset_lock); + init_waitqueue_head(&ctrl->requester); init_waitqueue_head(&ctrl->queue); dbg_ctrl(ctrl); @@ -855,16 +889,11 @@ struct controller *pcie_init(struct pcie_device *dev) if (link_cap & PCI_EXP_LNKCAP_DLLLARC) ctrl->link_active_reporting = 1; - /* - * Clear all remaining event bits in Slot Status register except - * Presence Detect Changed. We want to make sure possible - * hotplug event is triggered when the interrupt is unmasked so - * that we don't lose that event. - */ + /* Clear all remaining event bits in Slot Status register. */ pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, PCI_EXP_SLTSTA_ABP | PCI_EXP_SLTSTA_PFD | PCI_EXP_SLTSTA_MRLSC | PCI_EXP_SLTSTA_CC | - PCI_EXP_SLTSTA_DLLSC); + PCI_EXP_SLTSTA_DLLSC | PCI_EXP_SLTSTA_PDC); ctrl_info(ctrl, "Slot #%d AttnBtn%c PwrCtrl%c MRL%c AttnInd%c PwrInd%c HotPlug%c Surprise%c Interlock%c NoCompl%c LLActRep%c%s\n", (slot_cap & PCI_EXP_SLTCAP_PSN) >> 19, @@ -883,6 +912,19 @@ struct controller *pcie_init(struct pcie_device *dev) if (pcie_init_slot(ctrl)) goto abort_ctrl; + /* + * If empty slot's power status is on, turn power off. The IRQ isn't + * requested yet, so avoid triggering a notification with this command. + */ + if (POWER_CTRL(ctrl)) { + pciehp_get_adapter_status(ctrl->slot, &occupied); + pciehp_get_power_status(ctrl->slot, &poweron); + if (!occupied && poweron) { + pcie_disable_notification(ctrl); + pciehp_power_off_slot(ctrl->slot); + } + } + return ctrl; abort_ctrl: @@ -893,7 +935,6 @@ abort: void pciehp_release_ctrl(struct controller *ctrl) { - pcie_shutdown_notification(ctrl); pcie_cleanup_slot(ctrl); kfree(ctrl); } diff --git a/drivers/pci/hotplug/pciehp_pci.c b/drivers/pci/hotplug/pciehp_pci.c index 3f518dea856d..5c58c22e0c08 100644 --- a/drivers/pci/hotplug/pciehp_pci.c +++ b/drivers/pci/hotplug/pciehp_pci.c @@ -62,9 +62,8 @@ int pciehp_configure_device(struct slot *p_slot) return ret; } -int pciehp_unconfigure_device(struct slot *p_slot) +void pciehp_unconfigure_device(struct slot *p_slot) { - int rc = 0; u8 presence = 0; struct pci_dev *dev, *temp; struct pci_bus *parent = p_slot->ctrl->pcie->port->subordinate; @@ -107,5 +106,4 @@ int pciehp_unconfigure_device(struct slot *p_slot) } pci_unlock_rescan_remove(); - return rc; } diff --git a/drivers/pci/hotplug/pcihp_skeleton.c b/drivers/pci/hotplug/pcihp_skeleton.c deleted file mode 100644 index c19694a04d2c..000000000000 --- a/drivers/pci/hotplug/pcihp_skeleton.c +++ /dev/null @@ -1,348 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * PCI Hot Plug Controller Skeleton Driver - 0.3 - * - * Copyright (C) 2001,2003 Greg Kroah-Hartman (greg@kroah.com) - * Copyright (C) 2001,2003 IBM Corp. - * - * All rights reserved. - * - * This driver is to be used as a skeleton driver to show how to interface - * with the pci hotplug core easily. - * - * Send feedback to <greg@kroah.com> - * - */ - -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/kernel.h> -#include <linux/slab.h> -#include <linux/pci.h> -#include <linux/pci_hotplug.h> -#include <linux/init.h> - -#define SLOT_NAME_SIZE 10 -struct slot { - u8 number; - struct hotplug_slot *hotplug_slot; - struct list_head slot_list; - char name[SLOT_NAME_SIZE]; -}; - -static LIST_HEAD(slot_list); - -#define MY_NAME "pcihp_skeleton" - -#define dbg(format, arg...) \ - do { \ - if (debug) \ - printk(KERN_DEBUG "%s: " format "\n", \ - MY_NAME, ## arg); \ - } while (0) -#define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME, ## arg) -#define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME, ## arg) -#define warn(format, arg...) printk(KERN_WARNING "%s: " format "\n", MY_NAME, ## arg) - -/* local variables */ -static bool debug; -static int num_slots; - -#define DRIVER_VERSION "0.3" -#define DRIVER_AUTHOR "Greg Kroah-Hartman <greg@kroah.com>" -#define DRIVER_DESC "Hot Plug PCI Controller Skeleton Driver" - -MODULE_AUTHOR(DRIVER_AUTHOR); -MODULE_DESCRIPTION(DRIVER_DESC); -MODULE_LICENSE("GPL"); -module_param(debug, bool, 0644); -MODULE_PARM_DESC(debug, "Debugging mode enabled or not"); - -static int enable_slot(struct hotplug_slot *slot); -static int disable_slot(struct hotplug_slot *slot); -static int set_attention_status(struct hotplug_slot *slot, u8 value); -static int hardware_test(struct hotplug_slot *slot, u32 value); -static int get_power_status(struct hotplug_slot *slot, u8 *value); -static int get_attention_status(struct hotplug_slot *slot, u8 *value); -static int get_latch_status(struct hotplug_slot *slot, u8 *value); -static int get_adapter_status(struct hotplug_slot *slot, u8 *value); - -static struct hotplug_slot_ops skel_hotplug_slot_ops = { - .enable_slot = enable_slot, - .disable_slot = disable_slot, - .set_attention_status = set_attention_status, - .hardware_test = hardware_test, - .get_power_status = get_power_status, - .get_attention_status = get_attention_status, - .get_latch_status = get_latch_status, - .get_adapter_status = get_adapter_status, -}; - -static int enable_slot(struct hotplug_slot *hotplug_slot) -{ - struct slot *slot = hotplug_slot->private; - int retval = 0; - - dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name); - - /* - * Fill in code here to enable the specified slot - */ - - return retval; -} - -static int disable_slot(struct hotplug_slot *hotplug_slot) -{ - struct slot *slot = hotplug_slot->private; - int retval = 0; - - dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name); - - /* - * Fill in code here to disable the specified slot - */ - - return retval; -} - -static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status) -{ - struct slot *slot = hotplug_slot->private; - int retval = 0; - - dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name); - - switch (status) { - case 0: - /* - * Fill in code here to turn light off - */ - break; - - case 1: - default: - /* - * Fill in code here to turn light on - */ - break; - } - - return retval; -} - -static int hardware_test(struct hotplug_slot *hotplug_slot, u32 value) -{ - struct slot *slot = hotplug_slot->private; - int retval = 0; - - dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name); - - switch (value) { - case 0: - /* Specify a test here */ - break; - case 1: - /* Specify another test here */ - break; - } - - return retval; -} - -static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) -{ - struct slot *slot = hotplug_slot->private; - int retval = 0; - - dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name); - - /* - * Fill in logic to get the current power status of the specific - * slot and store it in the *value location. - */ - - return retval; -} - -static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value) -{ - struct slot *slot = hotplug_slot->private; - int retval = 0; - - dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name); - - /* - * Fill in logic to get the current attention status of the specific - * slot and store it in the *value location. - */ - - return retval; -} - -static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value) -{ - struct slot *slot = hotplug_slot->private; - int retval = 0; - - dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name); - - /* - * Fill in logic to get the current latch status of the specific - * slot and store it in the *value location. - */ - - return retval; -} - -static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) -{ - struct slot *slot = hotplug_slot->private; - int retval = 0; - - dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name); - - /* - * Fill in logic to get the current adapter status of the specific - * slot and store it in the *value location. - */ - - return retval; -} - -static void release_slot(struct hotplug_slot *hotplug_slot) -{ - struct slot *slot = hotplug_slot->private; - - dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name); - kfree(slot->hotplug_slot->info); - kfree(slot->hotplug_slot); - kfree(slot); -} - -static void make_slot_name(struct slot *slot) -{ - /* - * Stupid way to make a filename out of the slot name. - * replace this if your hardware provides a better way to name slots. - */ - snprintf(slot->hotplug_slot->name, SLOT_NAME_SIZE, "%d", slot->number); -} - -/** - * init_slots - initialize 'struct slot' structures for each slot - * - */ -static int __init init_slots(void) -{ - struct slot *slot; - struct hotplug_slot *hotplug_slot; - struct hotplug_slot_info *info; - int retval; - int i; - - /* - * Create a structure for each slot, and register that slot - * with the pci_hotplug subsystem. - */ - for (i = 0; i < num_slots; ++i) { - slot = kzalloc(sizeof(*slot), GFP_KERNEL); - if (!slot) { - retval = -ENOMEM; - goto error; - } - - hotplug_slot = kzalloc(sizeof(*hotplug_slot), GFP_KERNEL); - if (!hotplug_slot) { - retval = -ENOMEM; - goto error_slot; - } - slot->hotplug_slot = hotplug_slot; - - info = kzalloc(sizeof(*info), GFP_KERNEL); - if (!info) { - retval = -ENOMEM; - goto error_hpslot; - } - hotplug_slot->info = info; - - slot->number = i; - - hotplug_slot->name = slot->name; - hotplug_slot->private = slot; - hotplug_slot->release = &release_slot; - make_slot_name(slot); - hotplug_slot->ops = &skel_hotplug_slot_ops; - - /* - * Initialize the slot info structure with some known - * good values. - */ - get_power_status(hotplug_slot, &info->power_status); - get_attention_status(hotplug_slot, &info->attention_status); - get_latch_status(hotplug_slot, &info->latch_status); - get_adapter_status(hotplug_slot, &info->adapter_status); - - dbg("registering slot %d\n", i); - retval = pci_hp_register(slot->hotplug_slot); - if (retval) { - err("pci_hp_register failed with error %d\n", retval); - goto error_info; - } - - /* add slot to our internal list */ - list_add(&slot->slot_list, &slot_list); - } - - return 0; -error_info: - kfree(info); -error_hpslot: - kfree(hotplug_slot); -error_slot: - kfree(slot); -error: - return retval; -} - -static void __exit cleanup_slots(void) -{ - struct slot *slot, *next; - - /* - * Unregister all of our slots with the pci_hotplug subsystem. - * Memory will be freed in release_slot() callback after slot's - * lifespan is finished. - */ - list_for_each_entry_safe(slot, next, &slot_list, slot_list) { - list_del(&slot->slot_list); - pci_hp_deregister(slot->hotplug_slot); - } -} - -static int __init pcihp_skel_init(void) -{ - int retval; - - info(DRIVER_DESC " version: " DRIVER_VERSION "\n"); - /* - * Do specific initialization stuff for your driver here - * like initializing your controller hardware (if any) and - * determining the number of slots you have in the system - * right now. - */ - num_slots = 5; - - return init_slots(); -} - -static void __exit pcihp_skel_exit(void) -{ - /* - * Clean everything up. - */ - cleanup_slots(); -} - -module_init(pcihp_skel_init); -module_exit(pcihp_skel_exit); diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c index 6c2e8d7307c6..3276a5e4c430 100644 --- a/drivers/pci/hotplug/pnv_php.c +++ b/drivers/pci/hotplug/pnv_php.c @@ -538,9 +538,8 @@ static struct hotplug_slot_ops php_slot_ops = { .disable_slot = pnv_php_disable_slot, }; -static void pnv_php_release(struct hotplug_slot *slot) +static void pnv_php_release(struct pnv_php_slot *php_slot) { - struct pnv_php_slot *php_slot = slot->private; unsigned long flags; /* Remove from global or child list */ @@ -596,7 +595,6 @@ static struct pnv_php_slot *pnv_php_alloc_slot(struct device_node *dn) php_slot->power_state_check = false; php_slot->slot.ops = &php_slot_ops; php_slot->slot.info = &php_slot->slot_info; - php_slot->slot.release = pnv_php_release; php_slot->slot.private = php_slot; INIT_LIST_HEAD(&php_slot->children); @@ -924,6 +922,7 @@ static void pnv_php_unregister_one(struct device_node *dn) php_slot->state = PNV_PHP_STATE_OFFLINE; pci_hp_deregister(&php_slot->slot); + pnv_php_release(php_slot); pnv_php_put_slot(php_slot); } diff --git a/drivers/pci/hotplug/rpaphp_core.c b/drivers/pci/hotplug/rpaphp_core.c index fb5e0845429d..857c358b727b 100644 --- a/drivers/pci/hotplug/rpaphp_core.c +++ b/drivers/pci/hotplug/rpaphp_core.c @@ -404,13 +404,13 @@ static void __exit cleanup_slots(void) /* * Unregister all of our slots with the pci_hotplug subsystem, * and free up all memory that we had allocated. - * memory will be freed in release_slot callback. */ list_for_each_entry_safe(slot, next, &rpaphp_slot_head, rpaphp_slot_list) { list_del(&slot->rpaphp_slot_list); pci_hp_deregister(slot->hotplug_slot); + dealloc_slot_struct(slot); } return; } diff --git a/drivers/pci/hotplug/rpaphp_slot.c b/drivers/pci/hotplug/rpaphp_slot.c index 3840a2075e6a..b916c8e4372d 100644 --- a/drivers/pci/hotplug/rpaphp_slot.c +++ b/drivers/pci/hotplug/rpaphp_slot.c @@ -19,12 +19,6 @@ #include "rpaphp.h" /* free up the memory used by a slot */ -static void rpaphp_release_slot(struct hotplug_slot *hotplug_slot) -{ - struct slot *slot = (struct slot *) hotplug_slot->private; - dealloc_slot_struct(slot); -} - void dealloc_slot_struct(struct slot *slot) { kfree(slot->hotplug_slot->info); @@ -56,7 +50,6 @@ struct slot *alloc_slot_struct(struct device_node *dn, slot->power_domain = power_domain; slot->hotplug_slot->private = slot; slot->hotplug_slot->ops = &rpaphp_hotplug_slot_ops; - slot->hotplug_slot->release = &rpaphp_release_slot; return (slot); @@ -90,10 +83,8 @@ int rpaphp_deregister_slot(struct slot *slot) __func__, slot->name); list_del(&slot->rpaphp_slot_list); - - retval = pci_hp_deregister(php_slot); - if (retval) - err("Problem unregistering a slot %s\n", slot->name); + pci_hp_deregister(php_slot); + dealloc_slot_struct(slot); dbg("%s - Exit: rc[%d]\n", __func__, retval); return retval; diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c index ffdc2977395d..93b5341d282c 100644 --- a/drivers/pci/hotplug/s390_pci_hpc.c +++ b/drivers/pci/hotplug/s390_pci_hpc.c @@ -130,15 +130,6 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) return 0; } -static void release_slot(struct hotplug_slot *hotplug_slot) -{ - struct slot *slot = hotplug_slot->private; - - kfree(slot->hotplug_slot->info); - kfree(slot->hotplug_slot); - kfree(slot); -} - static struct hotplug_slot_ops s390_hotplug_slot_ops = { .enable_slot = enable_slot, .disable_slot = disable_slot, @@ -175,7 +166,6 @@ int zpci_init_slot(struct zpci_dev *zdev) hotplug_slot->info = info; hotplug_slot->ops = &s390_hotplug_slot_ops; - hotplug_slot->release = &release_slot; get_power_status(hotplug_slot, &info->power_status); get_adapter_status(hotplug_slot, &info->adapter_status); @@ -209,5 +199,8 @@ void zpci_exit_slot(struct zpci_dev *zdev) continue; list_del(&slot->slot_list); pci_hp_deregister(slot->hotplug_slot); + kfree(slot->hotplug_slot->info); + kfree(slot->hotplug_slot); + kfree(slot); } } diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c index 78b6bdbb3a39..babd23409f61 100644 --- a/drivers/pci/hotplug/sgi_hotplug.c +++ b/drivers/pci/hotplug/sgi_hotplug.c @@ -628,7 +628,6 @@ static int sn_hotplug_slot_register(struct pci_bus *pci_bus) goto alloc_err; } bss_hotplug_slot->ops = &sn_hotplug_slot_ops; - bss_hotplug_slot->release = &sn_release_slot; rc = pci_hp_register(bss_hotplug_slot, pci_bus, device, name); if (rc) @@ -656,8 +655,10 @@ alloc_err: sn_release_slot(bss_hotplug_slot); /* destroy anything else on the list */ - while ((bss_hotplug_slot = sn_hp_destroy())) + while ((bss_hotplug_slot = sn_hp_destroy())) { pci_hp_deregister(bss_hotplug_slot); + sn_release_slot(bss_hotplug_slot); + } return rc; } @@ -703,8 +704,10 @@ static void __exit sn_pci_hotplug_exit(void) { struct hotplug_slot *bss_hotplug_slot; - while ((bss_hotplug_slot = sn_hp_destroy())) + while ((bss_hotplug_slot = sn_hp_destroy())) { pci_hp_deregister(bss_hotplug_slot); + sn_release_slot(bss_hotplug_slot); + } if (!list_empty(&sn_hp_list)) printk(KERN_ERR "%s: internal list is not empty\n", __FILE__); diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c index e91be287f292..97cee23f3d51 100644 --- a/drivers/pci/hotplug/shpchp_core.c +++ b/drivers/pci/hotplug/shpchp_core.c @@ -61,22 +61,6 @@ static struct hotplug_slot_ops shpchp_hotplug_slot_ops = { .get_adapter_status = get_adapter_status, }; -/** - * release_slot - free up the memory used by a slot - * @hotplug_slot: slot to free - */ -static void release_slot(struct hotplug_slot *hotplug_slot) -{ - struct slot *slot = hotplug_slot->private; - - ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n", - __func__, slot_name(slot)); - - kfree(slot->hotplug_slot->info); - kfree(slot->hotplug_slot); - kfree(slot); -} - static int init_slots(struct controller *ctrl) { struct slot *slot; @@ -125,7 +109,6 @@ static int init_slots(struct controller *ctrl) /* register this slot with the hotplug pci core */ hotplug_slot->private = slot; - hotplug_slot->release = &release_slot; snprintf(name, SLOT_NAME_SIZE, "%d", slot->number); hotplug_slot->ops = &shpchp_hotplug_slot_ops; @@ -171,6 +154,9 @@ void cleanup_slots(struct controller *ctrl) cancel_delayed_work(&slot->work); destroy_workqueue(slot->wq); pci_hp_deregister(slot->hotplug_slot); + kfree(slot->hotplug_slot->info); + kfree(slot->hotplug_slot); + kfree(slot); } } @@ -270,11 +256,30 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) return 0; } +static bool shpc_capable(struct pci_dev *bridge) +{ + /* + * It is assumed that AMD GOLAM chips support SHPC but they do not + * have SHPC capability. + */ + if (bridge->vendor == PCI_VENDOR_ID_AMD && + bridge->device == PCI_DEVICE_ID_AMD_GOLAM_7450) + return true; + + if (pci_find_capability(bridge, PCI_CAP_ID_SHPC)) + return true; + + return false; +} + static int shpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { int rc; struct controller *ctrl; + if (!shpc_capable(pdev)) + return -ENODEV; + if (acpi_get_hp_hw_control_from_firmware(pdev)) return -ENODEV; @@ -303,6 +308,7 @@ static int shpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) goto err_cleanup_slots; + pdev->shpc_managed = 1; return 0; err_cleanup_slots: @@ -319,6 +325,7 @@ static void shpc_remove(struct pci_dev *dev) { struct controller *ctrl = pci_get_drvdata(dev); + dev->shpc_managed = 0; shpchp_remove_ctrl_files(ctrl); ctrl->hpc_ops->release_ctlr(ctrl); kfree(ctrl); diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c index 1047b56e5730..1267dcc5a531 100644 --- a/drivers/pci/hotplug/shpchp_ctrl.c +++ b/drivers/pci/hotplug/shpchp_ctrl.c @@ -654,6 +654,7 @@ int shpchp_sysfs_enable_slot(struct slot *p_slot) switch (p_slot->state) { case BLINKINGON_STATE: cancel_delayed_work(&p_slot->work); + /* fall through */ case STATIC_STATE: p_slot->state = POWERON_STATE; mutex_unlock(&p_slot->lock); @@ -689,6 +690,7 @@ int shpchp_sysfs_disable_slot(struct slot *p_slot) switch (p_slot->state) { case BLINKINGOFF_STATE: cancel_delayed_work(&p_slot->work); + /* fall through */ case STATIC_STATE: p_slot->state = POWEROFF_STATE; mutex_unlock(&p_slot->lock); diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 0f04ae648cf1..c5f3cd4ed766 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -818,15 +818,15 @@ int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs) { if (!dev->is_physfn) return -ENOSYS; + if (numvfs > dev->sriov->total_VFs) return -EINVAL; /* Shouldn't change if VFs already enabled */ if (dev->sriov->ctrl & PCI_SRIOV_CTRL_VFE) return -EBUSY; - else - dev->sriov->driver_max_VFs = numvfs; + dev->sriov->driver_max_VFs = numvfs; return 0; } EXPORT_SYMBOL_GPL(pci_sriov_set_totalvfs); diff --git a/drivers/pci/irq.c b/drivers/pci/irq.c index 2a808e10645f..a1de501a2729 100644 --- a/drivers/pci/irq.c +++ b/drivers/pci/irq.c @@ -86,13 +86,17 @@ int pci_request_irq(struct pci_dev *dev, unsigned int nr, irq_handler_t handler, va_list ap; int ret; char *devname; + unsigned long irqflags = IRQF_SHARED; + + if (!handler) + irqflags |= IRQF_ONESHOT; va_start(ap, fmt); devname = kvasprintf(GFP_KERNEL, fmt, ap); va_end(ap); ret = request_threaded_irq(pci_irq_vector(dev, nr), handler, thread_fn, - IRQF_SHARED, devname, dev_id); + irqflags, devname, dev_id); if (ret) kfree(devname); return ret; diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 4d88afdfc843..f2ef896464b3 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1446,6 +1446,9 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE)) info->flags |= MSI_FLAG_MUST_REACTIVATE; + /* PCI-MSI is oneshot-safe */ + info->chip->flags |= IRQCHIP_ONESHOT_SAFE; + domain = msi_create_irq_domain(fwnode, info, parent); if (!domain) return NULL; diff --git a/drivers/pci/of.c b/drivers/pci/of.c index 69a60d6ebd73..1836b8ddf292 100644 --- a/drivers/pci/of.c +++ b/drivers/pci/of.c @@ -266,7 +266,7 @@ int devm_of_pci_get_host_bridge_resources(struct device *dev, struct list_head *resources, resource_size_t *io_base) { struct device_node *dev_node = dev->of_node; - struct resource *res; + struct resource *res, tmp_res; struct resource *bus_range; struct of_pci_range range; struct of_pci_range_parser parser; @@ -320,18 +320,16 @@ int devm_of_pci_get_host_bridge_resources(struct device *dev, if (range.cpu_addr == OF_BAD_ADDR || range.size == 0) continue; - res = devm_kzalloc(dev, sizeof(struct resource), GFP_KERNEL); + err = of_pci_range_to_resource(&range, dev_node, &tmp_res); + if (err) + continue; + + res = devm_kmemdup(dev, &tmp_res, sizeof(tmp_res), GFP_KERNEL); if (!res) { err = -ENOMEM; goto failed; } - err = of_pci_range_to_resource(&range, dev_node, res); - if (err) { - devm_kfree(dev, res); - continue; - } - if (resource_type(res) == IORESOURCE_IO) { if (!io_base) { dev_err(dev, "I/O range found for %pOF. Please provide an io_base pointer to save CPU base address\n", diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 89ee6a2b6eb8..738e3546abb1 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -403,24 +403,7 @@ bool pciehp_is_native(struct pci_dev *bridge) */ bool shpchp_is_native(struct pci_dev *bridge) { - const struct pci_host_bridge *host; - - if (!IS_ENABLED(CONFIG_HOTPLUG_PCI_SHPC)) - return false; - - /* - * It is assumed that AMD GOLAM chips support SHPC but they do not - * have SHPC capability. - */ - if (bridge->vendor == PCI_VENDOR_ID_AMD && - bridge->device == PCI_DEVICE_ID_AMD_GOLAM_7450) - return true; - - if (!pci_find_capability(bridge, PCI_CAP_ID_SHPC)) - return false; - - host = pci_find_host_bridge(bridge->bus); - return host->native_shpc_hotplug; + return bridge->shpc_managed; } /** diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 6792292b5fc7..bef17c3fca67 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -1668,7 +1668,7 @@ static int __init pci_driver_init(void) if (ret) return ret; #endif - + dma_debug_add_bus(&pci_bus_type); return 0; } postcore_initcall(pci_driver_init); diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 0c4653c1d2ce..9ecfe13157c0 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -23,7 +23,6 @@ #include <linux/fs.h> #include <linux/capability.h> #include <linux/security.h> -#include <linux/pci-aspm.h> #include <linux/slab.h> #include <linux/vgaarb.h> #include <linux/pm_runtime.h> @@ -1449,7 +1448,9 @@ static ssize_t reset_store(struct device *dev, struct device_attribute *attr, if (val != 1) return -EINVAL; + pm_runtime_get_sync(dev); result = pci_reset_function(pdev); + pm_runtime_put(dev); if (result < 0) return result; @@ -1746,6 +1747,9 @@ static const struct attribute_group *pci_dev_attr_groups[] = { #endif &pci_bridge_attr_group, &pcie_dev_attr_group, +#ifdef CONFIG_PCIEAER + &aer_stats_attr_group, +#endif NULL, }; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index aa1684d99b70..29ff9619b5fa 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -23,7 +23,6 @@ #include <linux/string.h> #include <linux/log2.h> #include <linux/logic_pio.h> -#include <linux/pci-aspm.h> #include <linux/pm_wakeup.h> #include <linux/interrupt.h> #include <linux/device.h> @@ -115,6 +114,9 @@ static bool pcie_ari_disabled; /* If set, the PCIe ATS capability will not be used. */ static bool pcie_ats_disabled; +/* If set, the PCI config space of each device is printed during boot. */ +bool pci_early_dump; + bool pci_ats_disabled(void) { return pcie_ats_disabled; @@ -191,6 +193,168 @@ void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar) EXPORT_SYMBOL_GPL(pci_ioremap_wc_bar); #endif +/** + * pci_dev_str_match_path - test if a path string matches a device + * @dev: the PCI device to test + * @p: string to match the device against + * @endptr: pointer to the string after the match + * + * Test if a string (typically from a kernel parameter) formatted as a + * path of device/function addresses matches a PCI device. The string must + * be of the form: + * + * [<domain>:]<bus>:<device>.<func>[/<device>.<func>]* + * + * A path for a device can be obtained using 'lspci -t'. Using a path + * is more robust against bus renumbering than using only a single bus, + * device and function address. + * + * Returns 1 if the string matches the device, 0 if it does not and + * a negative error code if it fails to parse the string. + */ +static int pci_dev_str_match_path(struct pci_dev *dev, const char *path, + const char **endptr) +{ + int ret; + int seg, bus, slot, func; + char *wpath, *p; + char end; + + *endptr = strchrnul(path, ';'); + + wpath = kmemdup_nul(path, *endptr - path, GFP_KERNEL); + if (!wpath) + return -ENOMEM; + + while (1) { + p = strrchr(wpath, '/'); + if (!p) + break; + ret = sscanf(p, "/%x.%x%c", &slot, &func, &end); + if (ret != 2) { + ret = -EINVAL; + goto free_and_exit; + } + + if (dev->devfn != PCI_DEVFN(slot, func)) { + ret = 0; + goto free_and_exit; + } + + /* + * Note: we don't need to get a reference to the upstream + * bridge because we hold a reference to the top level + * device which should hold a reference to the bridge, + * and so on. + */ + dev = pci_upstream_bridge(dev); + if (!dev) { + ret = 0; + goto free_and_exit; + } + + *p = 0; + } + + ret = sscanf(wpath, "%x:%x:%x.%x%c", &seg, &bus, &slot, + &func, &end); + if (ret != 4) { + seg = 0; + ret = sscanf(wpath, "%x:%x.%x%c", &bus, &slot, &func, &end); + if (ret != 3) { + ret = -EINVAL; + goto free_and_exit; + } + } + + ret = (seg == pci_domain_nr(dev->bus) && + bus == dev->bus->number && + dev->devfn == PCI_DEVFN(slot, func)); + +free_and_exit: + kfree(wpath); + return ret; +} + +/** + * pci_dev_str_match - test if a string matches a device + * @dev: the PCI device to test + * @p: string to match the device against + * @endptr: pointer to the string after the match + * + * Test if a string (typically from a kernel parameter) matches a specified + * PCI device. The string may be of one of the following formats: + * + * [<domain>:]<bus>:<device>.<func>[/<device>.<func>]* + * pci:<vendor>:<device>[:<subvendor>:<subdevice>] + * + * The first format specifies a PCI bus/device/function address which + * may change if new hardware is inserted, if motherboard firmware changes, + * or due to changes caused in kernel parameters. If the domain is + * left unspecified, it is taken to be 0. In order to be robust against + * bus renumbering issues, a path of PCI device/function numbers may be used + * to address the specific device. The path for a device can be determined + * through the use of 'lspci -t'. + * + * The second format matches devices using IDs in the configuration + * space which may match multiple devices in the system. A value of 0 + * for any field will match all devices. (Note: this differs from + * in-kernel code that uses PCI_ANY_ID which is ~0; this is for + * legacy reasons and convenience so users don't have to specify + * FFFFFFFFs on the command line.) + * + * Returns 1 if the string matches the device, 0 if it does not and + * a negative error code if the string cannot be parsed. + */ +static int pci_dev_str_match(struct pci_dev *dev, const char *p, + const char **endptr) +{ + int ret; + int count; + unsigned short vendor, device, subsystem_vendor, subsystem_device; + + if (strncmp(p, "pci:", 4) == 0) { + /* PCI vendor/device (subvendor/subdevice) IDs are specified */ + p += 4; + ret = sscanf(p, "%hx:%hx:%hx:%hx%n", &vendor, &device, + &subsystem_vendor, &subsystem_device, &count); + if (ret != 4) { + ret = sscanf(p, "%hx:%hx%n", &vendor, &device, &count); + if (ret != 2) + return -EINVAL; + + subsystem_vendor = 0; + subsystem_device = 0; + } + + p += count; + + if ((!vendor || vendor == dev->vendor) && + (!device || device == dev->device) && + (!subsystem_vendor || + subsystem_vendor == dev->subsystem_vendor) && + (!subsystem_device || + subsystem_device == dev->subsystem_device)) + goto found; + } else { + /* + * PCI Bus, Device, Function IDs are specified + * (optionally, may include a path of devfns following it) + */ + ret = pci_dev_str_match_path(dev, p, &p); + if (ret < 0) + return ret; + else if (ret) + goto found; + } + + *endptr = p; + return 0; + +found: + *endptr = p; + return 1; +} static int __pci_find_next_cap_ttl(struct pci_bus *bus, unsigned int devfn, u8 pos, int cap, int *ttl) @@ -1171,6 +1335,33 @@ static void pci_restore_config_space(struct pci_dev *pdev) } } +static void pci_restore_rebar_state(struct pci_dev *pdev) +{ + unsigned int pos, nbars, i; + u32 ctrl; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_REBAR); + if (!pos) + return; + + pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); + nbars = (ctrl & PCI_REBAR_CTRL_NBAR_MASK) >> + PCI_REBAR_CTRL_NBAR_SHIFT; + + for (i = 0; i < nbars; i++, pos += 8) { + struct resource *res; + int bar_idx, size; + + pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); + bar_idx = ctrl & PCI_REBAR_CTRL_BAR_IDX; + res = pdev->resource + bar_idx; + size = order_base_2((resource_size(res) >> 20) | 1) - 1; + ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE; + ctrl |= size << PCI_REBAR_CTRL_BAR_SHIFT; + pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl); + } +} + /** * pci_restore_state - Restore the saved state of a PCI device * @dev: - PCI device that we're dealing with @@ -1186,6 +1377,7 @@ void pci_restore_state(struct pci_dev *dev) pci_restore_pri_state(dev); pci_restore_ats_state(dev); pci_restore_vc_state(dev); + pci_restore_rebar_state(dev); pci_cleanup_aer_error_status_regs(dev); @@ -2045,6 +2237,7 @@ static pci_power_t pci_target_state(struct pci_dev *dev, bool wakeup) case PCI_D2: if (pci_no_d1d2(dev)) break; + /* else: fall through */ default: target_state = state; } @@ -2290,7 +2483,7 @@ void pci_config_pm_runtime_put(struct pci_dev *pdev) * @bridge: Bridge to check * * This function checks if it is possible to move the bridge to D3. - * Currently we only allow D3 for recent enough PCIe ports. + * Currently we only allow D3 for recent enough PCIe ports and Thunderbolt. */ bool pci_bridge_d3_possible(struct pci_dev *bridge) { @@ -2305,18 +2498,27 @@ bool pci_bridge_d3_possible(struct pci_dev *bridge) return false; /* - * Hotplug interrupts cannot be delivered if the link is down, - * so parents of a hotplug port must stay awake. In addition, - * hotplug ports handled by firmware in System Management Mode + * Hotplug ports handled by firmware in System Management Mode * may not be put into D3 by the OS (Thunderbolt on non-Macs). - * For simplicity, disallow in general for now. */ - if (bridge->is_hotplug_bridge) + if (bridge->is_hotplug_bridge && !pciehp_is_native(bridge)) return false; if (pci_bridge_d3_force) return true; + /* Even the oldest 2010 Thunderbolt controller supports D3. */ + if (bridge->is_thunderbolt) + return true; + + /* + * Hotplug ports handled natively by the OS were not validated + * by vendors for runtime D3 at least until 2018 because there + * was no OS support. + */ + if (bridge->is_hotplug_bridge) + return false; + /* * It should be safe to put PCIe ports from 2015 or newer * to D3. @@ -2820,6 +3022,66 @@ void pci_request_acs(void) pci_acs_enable = 1; } +static const char *disable_acs_redir_param; + +/** + * pci_disable_acs_redir - disable ACS redirect capabilities + * @dev: the PCI device + * + * For only devices specified in the disable_acs_redir parameter. + */ +static void pci_disable_acs_redir(struct pci_dev *dev) +{ + int ret = 0; + const char *p; + int pos; + u16 ctrl; + + if (!disable_acs_redir_param) + return; + + p = disable_acs_redir_param; + while (*p) { + ret = pci_dev_str_match(dev, p, &p); + if (ret < 0) { + pr_info_once("PCI: Can't parse disable_acs_redir parameter: %s\n", + disable_acs_redir_param); + + break; + } else if (ret == 1) { + /* Found a match */ + break; + } + + if (*p != ';' && *p != ',') { + /* End of param or invalid format */ + break; + } + p++; + } + + if (ret != 1) + return; + + if (!pci_dev_specific_disable_acs_redir(dev)) + return; + + pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS); + if (!pos) { + pci_warn(dev, "cannot disable ACS redirect for this hardware as it does not have ACS capabilities\n"); + return; + } + + pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl); + + /* P2P Request & Completion Redirect */ + ctrl &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC); + + pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl); + + pci_info(dev, "disabled ACS redirect\n"); +} + /** * pci_std_enable_acs - enable ACS on devices using standard ACS capabilites * @dev: the PCI device @@ -2859,12 +3121,22 @@ static void pci_std_enable_acs(struct pci_dev *dev) void pci_enable_acs(struct pci_dev *dev) { if (!pci_acs_enable) - return; + goto disable_acs_redir; if (!pci_dev_specific_enable_acs(dev)) - return; + goto disable_acs_redir; pci_std_enable_acs(dev); + +disable_acs_redir: + /* + * Note: pci_disable_acs_redir() must be called even if ACS was not + * enabled by the kernel because it may have been enabled by + * platform firmware. So if we are told to disable it, we should + * always disable it after setting the kernel's default + * preferences. + */ + pci_disable_acs_redir(dev); } static bool pci_acs_flags_enabled(struct pci_dev *pdev, u16 acs_flags) @@ -3070,7 +3342,7 @@ int pci_rebar_get_current_size(struct pci_dev *pdev, int bar) return pos; pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); - return (ctrl & PCI_REBAR_CTRL_BAR_SIZE) >> 8; + return (ctrl & PCI_REBAR_CTRL_BAR_SIZE) >> PCI_REBAR_CTRL_BAR_SHIFT; } /** @@ -3093,7 +3365,7 @@ int pci_rebar_set_size(struct pci_dev *pdev, int bar, int size) pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE; - ctrl |= size << 8; + ctrl |= size << PCI_REBAR_CTRL_BAR_SHIFT; pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl); return 0; } @@ -4077,7 +4349,7 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) * Returns true if the device advertises support for PCIe function level * resets. */ -static bool pcie_has_flr(struct pci_dev *dev) +bool pcie_has_flr(struct pci_dev *dev) { u32 cap; @@ -4087,6 +4359,7 @@ static bool pcie_has_flr(struct pci_dev *dev) pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &cap); return cap & PCI_EXP_DEVCAP_FLR; } +EXPORT_SYMBOL_GPL(pcie_has_flr); /** * pcie_flr - initiate a PCIe function level reset @@ -4262,19 +4535,18 @@ void __weak pcibios_reset_secondary_bus(struct pci_dev *dev) } /** - * pci_reset_bridge_secondary_bus - Reset the secondary bus on a PCI bridge. + * pci_bridge_secondary_bus_reset - Reset the secondary bus on a PCI bridge. * @dev: Bridge device * * Use the bridge control register to assert reset on the secondary bus. * Devices on the secondary bus are left in power-on state. */ -int pci_reset_bridge_secondary_bus(struct pci_dev *dev) +int pci_bridge_secondary_bus_reset(struct pci_dev *dev) { pcibios_reset_secondary_bus(dev); return pci_dev_wait(dev, "bus reset", PCIE_RESET_READY_POLL_MS); } -EXPORT_SYMBOL_GPL(pci_reset_bridge_secondary_bus); static int pci_parent_bus_reset(struct pci_dev *dev, int probe) { @@ -4291,9 +4563,7 @@ static int pci_parent_bus_reset(struct pci_dev *dev, int probe) if (probe) return 0; - pci_reset_bridge_secondary_bus(dev->bus->self); - - return 0; + return pci_bridge_secondary_bus_reset(dev->bus->self); } static int pci_reset_hotplug_slot(struct hotplug_slot *hotplug, int probe) @@ -4825,7 +5095,7 @@ int pci_probe_reset_slot(struct pci_slot *slot) EXPORT_SYMBOL_GPL(pci_probe_reset_slot); /** - * pci_reset_slot - reset a PCI slot + * __pci_reset_slot - Try to reset a PCI slot * @slot: PCI slot to reset * * A PCI bus may host multiple slots, each slot may support a reset mechanism @@ -4837,33 +5107,9 @@ EXPORT_SYMBOL_GPL(pci_probe_reset_slot); * through this function. PCI config space of all devices in the slot and * behind the slot is saved before and restored after reset. * - * Return 0 on success, non-zero on error. - */ -int pci_reset_slot(struct pci_slot *slot) -{ - int rc; - - rc = pci_slot_reset(slot, 1); - if (rc) - return rc; - - pci_slot_save_and_disable(slot); - - rc = pci_slot_reset(slot, 0); - - pci_slot_restore(slot); - - return rc; -} -EXPORT_SYMBOL_GPL(pci_reset_slot); - -/** - * pci_try_reset_slot - Try to reset a PCI slot - * @slot: PCI slot to reset - * * Same as above except return -EAGAIN if the slot cannot be locked */ -int pci_try_reset_slot(struct pci_slot *slot) +static int __pci_reset_slot(struct pci_slot *slot) { int rc; @@ -4884,10 +5130,11 @@ int pci_try_reset_slot(struct pci_slot *slot) return rc; } -EXPORT_SYMBOL_GPL(pci_try_reset_slot); static int pci_bus_reset(struct pci_bus *bus, int probe) { + int ret; + if (!bus->self || !pci_bus_resetable(bus)) return -ENOTTY; @@ -4898,11 +5145,11 @@ static int pci_bus_reset(struct pci_bus *bus, int probe) might_sleep(); - pci_reset_bridge_secondary_bus(bus->self); + ret = pci_bridge_secondary_bus_reset(bus->self); pci_bus_unlock(bus); - return 0; + return ret; } /** @@ -4918,15 +5165,12 @@ int pci_probe_reset_bus(struct pci_bus *bus) EXPORT_SYMBOL_GPL(pci_probe_reset_bus); /** - * pci_reset_bus - reset a PCI bus + * __pci_reset_bus - Try to reset a PCI bus * @bus: top level PCI bus to reset * - * Do a bus reset on the given bus and any subordinate buses, saving - * and restoring state of all devices. - * - * Return 0 on success, non-zero on error. + * Same as above except return -EAGAIN if the bus cannot be locked */ -int pci_reset_bus(struct pci_bus *bus) +static int __pci_reset_bus(struct pci_bus *bus) { int rc; @@ -4936,42 +5180,30 @@ int pci_reset_bus(struct pci_bus *bus) pci_bus_save_and_disable(bus); - rc = pci_bus_reset(bus, 0); + if (pci_bus_trylock(bus)) { + might_sleep(); + rc = pci_bridge_secondary_bus_reset(bus->self); + pci_bus_unlock(bus); + } else + rc = -EAGAIN; pci_bus_restore(bus); return rc; } -EXPORT_SYMBOL_GPL(pci_reset_bus); /** - * pci_try_reset_bus - Try to reset a PCI bus - * @bus: top level PCI bus to reset + * pci_reset_bus - Try to reset a PCI bus + * @pdev: top level PCI device to reset via slot/bus * * Same as above except return -EAGAIN if the bus cannot be locked */ -int pci_try_reset_bus(struct pci_bus *bus) +int pci_reset_bus(struct pci_dev *pdev) { - int rc; - - rc = pci_bus_reset(bus, 1); - if (rc) - return rc; - - pci_bus_save_and_disable(bus); - - if (pci_bus_trylock(bus)) { - might_sleep(); - pci_reset_bridge_secondary_bus(bus->self); - pci_bus_unlock(bus); - } else - rc = -EAGAIN; - - pci_bus_restore(bus); - - return rc; + return pci_probe_reset_slot(pdev->slot) ? + __pci_reset_slot(pdev->slot) : __pci_reset_bus(pdev->bus); } -EXPORT_SYMBOL_GPL(pci_try_reset_bus); +EXPORT_SYMBOL_GPL(pci_reset_bus); /** * pcix_get_max_mmrbc - get PCI-X maximum designed memory read byte count @@ -5304,14 +5536,16 @@ u32 pcie_bandwidth_capable(struct pci_dev *dev, enum pci_bus_speed *speed, } /** - * pcie_print_link_status - Report the PCI device's link speed and width + * __pcie_print_link_status - Report the PCI device's link speed and width * @dev: PCI device to query + * @verbose: Print info even when enough bandwidth is available * - * Report the available bandwidth at the device. If this is less than the - * device is capable of, report the device's maximum possible bandwidth and - * the upstream link that limits its performance to less than that. + * If the available bandwidth at the device is less than the device is + * capable of, report the device's maximum possible bandwidth and the + * upstream link that limits its performance. If @verbose, always print + * the available bandwidth, even if the device isn't constrained. */ -void pcie_print_link_status(struct pci_dev *dev) +void __pcie_print_link_status(struct pci_dev *dev, bool verbose) { enum pcie_link_width width, width_cap; enum pci_bus_speed speed, speed_cap; @@ -5321,11 +5555,11 @@ void pcie_print_link_status(struct pci_dev *dev) bw_cap = pcie_bandwidth_capable(dev, &speed_cap, &width_cap); bw_avail = pcie_bandwidth_available(dev, &limiting_dev, &speed, &width); - if (bw_avail >= bw_cap) + if (bw_avail >= bw_cap && verbose) pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth (%s x%d link)\n", bw_cap / 1000, bw_cap % 1000, PCIE_SPEED2STR(speed_cap), width_cap); - else + else if (bw_avail < bw_cap) pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth, limited by %s x%d link at %s (capable of %u.%03u Gb/s with %s x%d link)\n", bw_avail / 1000, bw_avail % 1000, PCIE_SPEED2STR(speed), width, @@ -5333,6 +5567,17 @@ void pcie_print_link_status(struct pci_dev *dev) bw_cap / 1000, bw_cap % 1000, PCIE_SPEED2STR(speed_cap), width_cap); } + +/** + * pcie_print_link_status - Report the PCI device's link speed and width + * @dev: PCI device to query + * + * Report the available bandwidth at the device. + */ +void pcie_print_link_status(struct pci_dev *dev) +{ + __pcie_print_link_status(dev, true); +} EXPORT_SYMBOL(pcie_print_link_status); /** @@ -5427,8 +5672,19 @@ int pci_set_vga_state(struct pci_dev *dev, bool decode, * @dev: the PCI device for which alias is added * @devfn: alias slot and function * - * This helper encodes 8-bit devfn as bit number in dma_alias_mask. - * It should be called early, preferably as PCI fixup header quirk. + * This helper encodes an 8-bit devfn as a bit number in dma_alias_mask + * which is used to program permissible bus-devfn source addresses for DMA + * requests in an IOMMU. These aliases factor into IOMMU group creation + * and are useful for devices generating DMA requests beyond or different + * from their logical bus-devfn. Examples include device quirks where the + * device simply uses the wrong devfn, as well as non-transparent bridges + * where the alias may be a proxy for devices in another domain. + * + * IOMMU group creation is performed during device discovery or addition, + * prior to any potential DMA mapping and therefore prior to driver probing + * (especially for userspace assigned devices where IOMMU group definition + * cannot be left as a userspace activity). DMA aliases should therefore + * be configured via quirks, such as the PCI fixup header quirk. */ void pci_add_dma_alias(struct pci_dev *dev, u8 devfn) { @@ -5494,10 +5750,10 @@ static DEFINE_SPINLOCK(resource_alignment_lock); static resource_size_t pci_specified_resource_alignment(struct pci_dev *dev, bool *resize) { - int seg, bus, slot, func, align_order, count; - unsigned short vendor, device, subsystem_vendor, subsystem_device; + int align_order, count; resource_size_t align = pcibios_default_alignment(); - char *p; + const char *p; + int ret; spin_lock(&resource_alignment_lock); p = resource_alignment_param; @@ -5517,58 +5773,21 @@ static resource_size_t pci_specified_resource_alignment(struct pci_dev *dev, } else { align_order = -1; } - if (strncmp(p, "pci:", 4) == 0) { - /* PCI vendor/device (subvendor/subdevice) ids are specified */ - p += 4; - if (sscanf(p, "%hx:%hx:%hx:%hx%n", - &vendor, &device, &subsystem_vendor, &subsystem_device, &count) != 4) { - if (sscanf(p, "%hx:%hx%n", &vendor, &device, &count) != 2) { - printk(KERN_ERR "PCI: Can't parse resource_alignment parameter: pci:%s\n", - p); - break; - } - subsystem_vendor = subsystem_device = 0; - } - p += count; - if ((!vendor || (vendor == dev->vendor)) && - (!device || (device == dev->device)) && - (!subsystem_vendor || (subsystem_vendor == dev->subsystem_vendor)) && - (!subsystem_device || (subsystem_device == dev->subsystem_device))) { - *resize = true; - if (align_order == -1) - align = PAGE_SIZE; - else - align = 1 << align_order; - /* Found */ - break; - } - } - else { - if (sscanf(p, "%x:%x:%x.%x%n", - &seg, &bus, &slot, &func, &count) != 4) { - seg = 0; - if (sscanf(p, "%x:%x.%x%n", - &bus, &slot, &func, &count) != 3) { - /* Invalid format */ - printk(KERN_ERR "PCI: Can't parse resource_alignment parameter: %s\n", - p); - break; - } - } - p += count; - if (seg == pci_domain_nr(dev->bus) && - bus == dev->bus->number && - slot == PCI_SLOT(dev->devfn) && - func == PCI_FUNC(dev->devfn)) { - *resize = true; - if (align_order == -1) - align = PAGE_SIZE; - else - align = 1 << align_order; - /* Found */ - break; - } + + ret = pci_dev_str_match(dev, p, &p); + if (ret == 1) { + *resize = true; + if (align_order == -1) + align = PAGE_SIZE; + else + align = 1 << align_order; + break; + } else if (ret < 0) { + pr_err("PCI: Can't parse resource_alignment parameter: %s\n", + p); + break; } + if (*p != ';' && *p != ',') { /* End of param or invalid format */ break; @@ -5845,6 +6064,8 @@ static int __init pci_setup(char *str) pcie_ats_disabled = true; } else if (!strcmp(str, "noaer")) { pci_no_aer(); + } else if (!strcmp(str, "earlydump")) { + pci_early_dump = true; } else if (!strncmp(str, "realloc=", 8)) { pci_realloc_get_opt(str + 8); } else if (!strncmp(str, "realloc", 7)) { @@ -5881,6 +6102,8 @@ static int __init pci_setup(char *str) pcie_bus_config = PCIE_BUS_PEER2PEER; } else if (!strncmp(str, "pcie_scan_all", 13)) { pci_add_flags(PCI_SCAN_ALL_PCIE_DEVS); + } else if (!strncmp(str, "disable_acs_redir=", 18)) { + disable_acs_redir_param = str + 18; } else { printk(KERN_ERR "PCI: Unknown option `%s'\n", str); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 08817253c8a2..6e0d1528d471 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -7,6 +7,7 @@ #define PCI_VSEC_ID_INTEL_TBT 0x1234 /* Thunderbolt */ extern const unsigned char pcie_link_speed[]; +extern bool pci_early_dump; bool pcie_cap_has_lnkctl(const struct pci_dev *dev); @@ -33,6 +34,7 @@ int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vmai, enum pci_mmap_api mmap_api); int pci_probe_reset_function(struct pci_dev *dev); +int pci_bridge_secondary_bus_reset(struct pci_dev *dev); /** * struct pci_platform_pm_ops - Firmware PM callbacks @@ -225,6 +227,10 @@ enum pci_bar_type { int pci_configure_extended_tags(struct pci_dev *dev, void *ign); bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl, int crs_timeout); +bool pci_bus_generic_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl, + int crs_timeout); +int pci_idt_bus_quirk(struct pci_bus *bus, int devfn, u32 *pl, int crs_timeout); + int pci_setup_device(struct pci_dev *dev); int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, struct resource *res, unsigned int reg); @@ -259,6 +265,7 @@ enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev); enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev); u32 pcie_bandwidth_capable(struct pci_dev *dev, enum pci_bus_speed *speed, enum pcie_link_width *width); +void __pcie_print_link_status(struct pci_dev *dev, bool verbose); /* Single Root I/O Virtualization */ struct pci_sriov { @@ -311,6 +318,34 @@ static inline bool pci_dev_is_added(const struct pci_dev *dev) return test_bit(PCI_DEV_ADDED, &dev->priv_flags); } +#ifdef CONFIG_PCIEAER +#include <linux/aer.h> + +#define AER_MAX_MULTI_ERR_DEVICES 5 /* Not likely to have more */ + +struct aer_err_info { + struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES]; + int error_dev_num; + + unsigned int id:16; + + unsigned int severity:2; /* 0:NONFATAL | 1:FATAL | 2:COR */ + unsigned int __pad1:5; + unsigned int multi_error_valid:1; + + unsigned int first_error:5; + unsigned int __pad2:2; + unsigned int tlp_header_valid:1; + + unsigned int status; /* COR/UNCOR Error Status */ + unsigned int mask; /* COR/UNCOR Error Mask */ + struct aer_header_log_regs tlp; /* TLP Header */ +}; + +int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info); +void aer_print_error(struct pci_dev *dev, struct aer_err_info *info); +#endif /* CONFIG_PCIEAER */ + #ifdef CONFIG_PCI_ATS void pci_restore_ats_state(struct pci_dev *dev); #else @@ -367,6 +402,25 @@ static inline resource_size_t pci_resource_alignment(struct pci_dev *dev, } void pci_enable_acs(struct pci_dev *dev); +#ifdef CONFIG_PCI_QUIRKS +int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags); +int pci_dev_specific_enable_acs(struct pci_dev *dev); +int pci_dev_specific_disable_acs_redir(struct pci_dev *dev); +#else +static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev, + u16 acs_flags) +{ + return -ENOTTY; +} +static inline int pci_dev_specific_enable_acs(struct pci_dev *dev) +{ + return -ENOTTY; +} +static inline int pci_dev_specific_disable_acs_redir(struct pci_dev *dev) +{ + return -ENOTTY; +} +#endif /* PCI error reporting and recovery */ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service); @@ -467,4 +521,19 @@ static inline int devm_of_pci_get_host_bridge_resources(struct device *dev, } #endif +#ifdef CONFIG_PCIEAER +void pci_no_aer(void); +void pci_aer_init(struct pci_dev *dev); +void pci_aer_exit(struct pci_dev *dev); +extern const struct attribute_group aer_stats_attr_group; +void pci_aer_clear_fatal_status(struct pci_dev *dev); +void pci_aer_clear_device_status(struct pci_dev *dev); +#else +static inline void pci_no_aer(void) { } +static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; } +static inline void pci_aer_exit(struct pci_dev *d) { } +static inline void pci_aer_clear_fatal_status(struct pci_dev *dev) { } +static inline void pci_aer_clear_device_status(struct pci_dev *dev) { } +#endif + #endif /* DRIVERS_PCI_H */ diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index a2e88386af28..83180edd6ed4 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -31,26 +31,9 @@ #include "portdrv.h" #define AER_ERROR_SOURCES_MAX 100 -#define AER_MAX_MULTI_ERR_DEVICES 5 /* Not likely to have more */ -struct aer_err_info { - struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES]; - int error_dev_num; - - unsigned int id:16; - - unsigned int severity:2; /* 0:NONFATAL | 1:FATAL | 2:COR */ - unsigned int __pad1:5; - unsigned int multi_error_valid:1; - - unsigned int first_error:5; - unsigned int __pad2:2; - unsigned int tlp_header_valid:1; - - unsigned int status; /* COR/UNCOR Error Status */ - unsigned int mask; /* COR/UNCOR Error Mask */ - struct aer_header_log_regs tlp; /* TLP Header */ -}; +#define AER_MAX_TYPEOF_COR_ERRS 16 /* as per PCI_ERR_COR_STATUS */ +#define AER_MAX_TYPEOF_UNCOR_ERRS 26 /* as per PCI_ERR_UNCOR_STATUS*/ struct aer_err_source { unsigned int status; @@ -76,6 +59,42 @@ struct aer_rpc { */ }; +/* AER stats for the device */ +struct aer_stats { + + /* + * Fields for all AER capable devices. They indicate the errors + * "as seen by this device". Note that this may mean that if an + * end point is causing problems, the AER counters may increment + * at its link partner (e.g. root port) because the errors will be + * "seen" by the link partner and not the the problematic end point + * itself (which may report all counters as 0 as it never saw any + * problems). + */ + /* Counters for different type of correctable errors */ + u64 dev_cor_errs[AER_MAX_TYPEOF_COR_ERRS]; + /* Counters for different type of fatal uncorrectable errors */ + u64 dev_fatal_errs[AER_MAX_TYPEOF_UNCOR_ERRS]; + /* Counters for different type of nonfatal uncorrectable errors */ + u64 dev_nonfatal_errs[AER_MAX_TYPEOF_UNCOR_ERRS]; + /* Total number of ERR_COR sent by this device */ + u64 dev_total_cor_errs; + /* Total number of ERR_FATAL sent by this device */ + u64 dev_total_fatal_errs; + /* Total number of ERR_NONFATAL sent by this device */ + u64 dev_total_nonfatal_errs; + + /* + * Fields for Root ports & root complex event collectors only, these + * indicate the total number of ERR_COR, ERR_FATAL, and ERR_NONFATAL + * messages received by the root port / event collector, INCLUDING the + * ones that are generated internally (by the rootport itself) + */ + u64 rootport_total_cor_errs; + u64 rootport_total_fatal_errs; + u64 rootport_total_nonfatal_errs; +}; + #define AER_LOG_TLP_MASKS (PCI_ERR_UNC_POISON_TLP| \ PCI_ERR_UNC_ECRC| \ PCI_ERR_UNC_UNSUP| \ @@ -303,12 +322,13 @@ int pcie_aer_get_firmware_first(struct pci_dev *dev) if (!pci_is_pcie(dev)) return 0; + if (pcie_ports_native) + return 0; + if (!dev->__aer_firmware_first_valid) aer_set_firmware_first(dev); return dev->__aer_firmware_first; } -#define PCI_EXP_AER_FLAGS (PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | \ - PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE) static bool aer_firmware_first; @@ -323,6 +343,9 @@ bool aer_acpi_firmware_first(void) .firmware_first = 0, }; + if (pcie_ports_native) + return false; + if (!parsed) { apei_hest_parse(aer_hest_parse, &info); aer_firmware_first = info.firmware_first; @@ -357,16 +380,30 @@ int pci_disable_pcie_error_reporting(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting); +void pci_aer_clear_device_status(struct pci_dev *dev) +{ + u16 sta; + + pcie_capability_read_word(dev, PCI_EXP_DEVSTA, &sta); + pcie_capability_write_word(dev, PCI_EXP_DEVSTA, sta); +} + int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev) { int pos; - u32 status; + u32 status, sev; pos = dev->aer_cap; if (!pos) return -EIO; + if (pcie_aer_get_firmware_first(dev)) + return -EIO; + + /* Clear status bits for ERR_NONFATAL errors only */ pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status); + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &sev); + status &= ~sev; if (status) pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status); @@ -374,6 +411,26 @@ int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status); +void pci_aer_clear_fatal_status(struct pci_dev *dev) +{ + int pos; + u32 status, sev; + + pos = dev->aer_cap; + if (!pos) + return; + + if (pcie_aer_get_firmware_first(dev)) + return; + + /* Clear status bits for ERR_FATAL errors only */ + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status); + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &sev); + status &= sev; + if (status) + pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status); +} + int pci_cleanup_aer_error_status_regs(struct pci_dev *dev) { int pos; @@ -387,6 +444,9 @@ int pci_cleanup_aer_error_status_regs(struct pci_dev *dev) if (!pos) return -EIO; + if (pcie_aer_get_firmware_first(dev)) + return -EIO; + port_type = pci_pcie_type(dev); if (port_type == PCI_EXP_TYPE_ROOT_PORT) { pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &status); @@ -402,10 +462,20 @@ int pci_cleanup_aer_error_status_regs(struct pci_dev *dev) return 0; } -int pci_aer_init(struct pci_dev *dev) +void pci_aer_init(struct pci_dev *dev) { dev->aer_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); - return pci_cleanup_aer_error_status_regs(dev); + + if (dev->aer_cap) + dev->aer_stats = kzalloc(sizeof(struct aer_stats), GFP_KERNEL); + + pci_cleanup_aer_error_status_regs(dev); +} + +void pci_aer_exit(struct pci_dev *dev) +{ + kfree(dev->aer_stats); + dev->aer_stats = NULL; } #define AER_AGENT_RECEIVER 0 @@ -458,52 +528,52 @@ static const char *aer_error_layer[] = { "Transaction Layer" }; -static const char *aer_correctable_error_string[] = { - "Receiver Error", /* Bit Position 0 */ +static const char *aer_correctable_error_string[AER_MAX_TYPEOF_COR_ERRS] = { + "RxErr", /* Bit Position 0 */ NULL, NULL, NULL, NULL, NULL, - "Bad TLP", /* Bit Position 6 */ - "Bad DLLP", /* Bit Position 7 */ - "RELAY_NUM Rollover", /* Bit Position 8 */ + "BadTLP", /* Bit Position 6 */ + "BadDLLP", /* Bit Position 7 */ + "Rollover", /* Bit Position 8 */ NULL, NULL, NULL, - "Replay Timer Timeout", /* Bit Position 12 */ - "Advisory Non-Fatal", /* Bit Position 13 */ - "Corrected Internal Error", /* Bit Position 14 */ - "Header Log Overflow", /* Bit Position 15 */ + "Timeout", /* Bit Position 12 */ + "NonFatalErr", /* Bit Position 13 */ + "CorrIntErr", /* Bit Position 14 */ + "HeaderOF", /* Bit Position 15 */ }; -static const char *aer_uncorrectable_error_string[] = { +static const char *aer_uncorrectable_error_string[AER_MAX_TYPEOF_UNCOR_ERRS] = { "Undefined", /* Bit Position 0 */ NULL, NULL, NULL, - "Data Link Protocol", /* Bit Position 4 */ - "Surprise Down Error", /* Bit Position 5 */ + "DLP", /* Bit Position 4 */ + "SDES", /* Bit Position 5 */ NULL, NULL, NULL, NULL, NULL, NULL, - "Poisoned TLP", /* Bit Position 12 */ - "Flow Control Protocol", /* Bit Position 13 */ - "Completion Timeout", /* Bit Position 14 */ - "Completer Abort", /* Bit Position 15 */ - "Unexpected Completion", /* Bit Position 16 */ - "Receiver Overflow", /* Bit Position 17 */ - "Malformed TLP", /* Bit Position 18 */ + "TLP", /* Bit Position 12 */ + "FCP", /* Bit Position 13 */ + "CmpltTO", /* Bit Position 14 */ + "CmpltAbrt", /* Bit Position 15 */ + "UnxCmplt", /* Bit Position 16 */ + "RxOF", /* Bit Position 17 */ + "MalfTLP", /* Bit Position 18 */ "ECRC", /* Bit Position 19 */ - "Unsupported Request", /* Bit Position 20 */ - "ACS Violation", /* Bit Position 21 */ - "Uncorrectable Internal Error", /* Bit Position 22 */ - "MC Blocked TLP", /* Bit Position 23 */ - "AtomicOp Egress Blocked", /* Bit Position 24 */ - "TLP Prefix Blocked Error", /* Bit Position 25 */ + "UnsupReq", /* Bit Position 20 */ + "ACSViol", /* Bit Position 21 */ + "UncorrIntErr", /* Bit Position 22 */ + "BlockedTLP", /* Bit Position 23 */ + "AtomicOpBlocked", /* Bit Position 24 */ + "TLPBlockedErr", /* Bit Position 25 */ }; static const char *aer_agent_string[] = { @@ -513,6 +583,144 @@ static const char *aer_agent_string[] = { "Transmitter ID" }; +#define aer_stats_dev_attr(name, stats_array, strings_array, \ + total_string, total_field) \ + static ssize_t \ + name##_show(struct device *dev, struct device_attribute *attr, \ + char *buf) \ +{ \ + unsigned int i; \ + char *str = buf; \ + struct pci_dev *pdev = to_pci_dev(dev); \ + u64 *stats = pdev->aer_stats->stats_array; \ + \ + for (i = 0; i < ARRAY_SIZE(strings_array); i++) { \ + if (strings_array[i]) \ + str += sprintf(str, "%s %llu\n", \ + strings_array[i], stats[i]); \ + else if (stats[i]) \ + str += sprintf(str, #stats_array "_bit[%d] %llu\n",\ + i, stats[i]); \ + } \ + str += sprintf(str, "TOTAL_%s %llu\n", total_string, \ + pdev->aer_stats->total_field); \ + return str-buf; \ +} \ +static DEVICE_ATTR_RO(name) + +aer_stats_dev_attr(aer_dev_correctable, dev_cor_errs, + aer_correctable_error_string, "ERR_COR", + dev_total_cor_errs); +aer_stats_dev_attr(aer_dev_fatal, dev_fatal_errs, + aer_uncorrectable_error_string, "ERR_FATAL", + dev_total_fatal_errs); +aer_stats_dev_attr(aer_dev_nonfatal, dev_nonfatal_errs, + aer_uncorrectable_error_string, "ERR_NONFATAL", + dev_total_nonfatal_errs); + +#define aer_stats_rootport_attr(name, field) \ + static ssize_t \ + name##_show(struct device *dev, struct device_attribute *attr, \ + char *buf) \ +{ \ + struct pci_dev *pdev = to_pci_dev(dev); \ + return sprintf(buf, "%llu\n", pdev->aer_stats->field); \ +} \ +static DEVICE_ATTR_RO(name) + +aer_stats_rootport_attr(aer_rootport_total_err_cor, + rootport_total_cor_errs); +aer_stats_rootport_attr(aer_rootport_total_err_fatal, + rootport_total_fatal_errs); +aer_stats_rootport_attr(aer_rootport_total_err_nonfatal, + rootport_total_nonfatal_errs); + +static struct attribute *aer_stats_attrs[] __ro_after_init = { + &dev_attr_aer_dev_correctable.attr, + &dev_attr_aer_dev_fatal.attr, + &dev_attr_aer_dev_nonfatal.attr, + &dev_attr_aer_rootport_total_err_cor.attr, + &dev_attr_aer_rootport_total_err_fatal.attr, + &dev_attr_aer_rootport_total_err_nonfatal.attr, + NULL +}; + +static umode_t aer_stats_attrs_are_visible(struct kobject *kobj, + struct attribute *a, int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct pci_dev *pdev = to_pci_dev(dev); + + if (!pdev->aer_stats) + return 0; + + if ((a == &dev_attr_aer_rootport_total_err_cor.attr || + a == &dev_attr_aer_rootport_total_err_fatal.attr || + a == &dev_attr_aer_rootport_total_err_nonfatal.attr) && + pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT) + return 0; + + return a->mode; +} + +const struct attribute_group aer_stats_attr_group = { + .attrs = aer_stats_attrs, + .is_visible = aer_stats_attrs_are_visible, +}; + +static void pci_dev_aer_stats_incr(struct pci_dev *pdev, + struct aer_err_info *info) +{ + int status, i, max = -1; + u64 *counter = NULL; + struct aer_stats *aer_stats = pdev->aer_stats; + + if (!aer_stats) + return; + + switch (info->severity) { + case AER_CORRECTABLE: + aer_stats->dev_total_cor_errs++; + counter = &aer_stats->dev_cor_errs[0]; + max = AER_MAX_TYPEOF_COR_ERRS; + break; + case AER_NONFATAL: + aer_stats->dev_total_nonfatal_errs++; + counter = &aer_stats->dev_nonfatal_errs[0]; + max = AER_MAX_TYPEOF_UNCOR_ERRS; + break; + case AER_FATAL: + aer_stats->dev_total_fatal_errs++; + counter = &aer_stats->dev_fatal_errs[0]; + max = AER_MAX_TYPEOF_UNCOR_ERRS; + break; + } + + status = (info->status & ~info->mask); + for (i = 0; i < max; i++) + if (status & (1 << i)) + counter[i]++; +} + +static void pci_rootport_aer_stats_incr(struct pci_dev *pdev, + struct aer_err_source *e_src) +{ + struct aer_stats *aer_stats = pdev->aer_stats; + + if (!aer_stats) + return; + + if (e_src->status & PCI_ERR_ROOT_COR_RCV) + aer_stats->rootport_total_cor_errs++; + + if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) { + if (e_src->status & PCI_ERR_ROOT_FATAL_RCV) + aer_stats->rootport_total_fatal_errs++; + else + aer_stats->rootport_total_nonfatal_errs++; + } +} + static void __print_tlp_header(struct pci_dev *dev, struct aer_header_log_regs *t) { @@ -545,9 +753,10 @@ static void __aer_print_error(struct pci_dev *dev, pci_err(dev, " [%2d] Unknown Error Bit%s\n", i, info->first_error == i ? " (First)" : ""); } + pci_dev_aer_stats_incr(dev, info); } -static void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) +void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) { int layer, agent; int id = ((dev->bus->number << 8) | dev->devfn); @@ -799,6 +1008,7 @@ static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info) if (pos) pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS, info->status); + pci_aer_clear_device_status(dev); } else if (info->severity == AER_NONFATAL) pcie_do_nonfatal_recovery(dev); else if (info->severity == AER_FATAL) @@ -876,7 +1086,7 @@ EXPORT_SYMBOL_GPL(aer_recover_queue); #endif /** - * get_device_error_info - read error status from dev and store it to info + * aer_get_device_error_info - read error status from dev and store it to info * @dev: pointer to the device expected to have a error record * @info: pointer to structure to store the error record * @@ -884,7 +1094,7 @@ EXPORT_SYMBOL_GPL(aer_recover_queue); * * Note that @info is reused among all error devices. Clear fields properly. */ -static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info) +int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info) { int pos, temp; @@ -942,11 +1152,11 @@ static inline void aer_process_err_devices(struct aer_err_info *e_info) /* Report all before handle them, not to lost records by reset etc. */ for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) { - if (get_device_error_info(e_info->dev[i], e_info)) + if (aer_get_device_error_info(e_info->dev[i], e_info)) aer_print_error(e_info->dev[i], e_info); } for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) { - if (get_device_error_info(e_info->dev[i], e_info)) + if (aer_get_device_error_info(e_info->dev[i], e_info)) handle_error_source(e_info->dev[i], e_info); } } @@ -962,6 +1172,8 @@ static void aer_isr_one_error(struct aer_rpc *rpc, struct pci_dev *pdev = rpc->rpd; struct aer_err_info *e_info = &rpc->e_info; + pci_rootport_aer_stats_incr(pdev, e_src); + /* * There is a possibility that both correctable error and * uncorrectable error being logged. Report correctable error first. @@ -1305,6 +1517,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev) { u32 reg32; int pos; + int rc; pos = dev->aer_cap; @@ -1313,7 +1526,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev) reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK; pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32); - pci_reset_bridge_secondary_bus(dev); + rc = pci_bridge_secondary_bus_reset(dev); pci_printk(KERN_DEBUG, dev, "Root Port link has been reset\n"); /* Clear Root Error Status */ @@ -1325,7 +1538,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev) reg32 |= ROOT_PORT_INTR_ON_MESG_MASK; pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32); - return PCI_ERS_RESULT_RECOVERED; + return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED; } /** @@ -1336,20 +1549,8 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev) */ static void aer_error_resume(struct pci_dev *dev) { - int pos; - u32 status, mask; - u16 reg16; - - /* Clean up Root device status */ - pcie_capability_read_word(dev, PCI_EXP_DEVSTA, ®16); - pcie_capability_write_word(dev, PCI_EXP_DEVSTA, reg16); - - /* Clean AER Root Error Status */ - pos = dev->aer_cap; - pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status); - pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &mask); - status &= ~mask; /* Clear corresponding nonfatal bits */ - pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status); + pci_aer_clear_device_status(dev); + pci_cleanup_aer_uncorrect_error_status(dev); } static struct pcie_port_service_driver aerdriver = { diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index c687c817b47d..5326916715d2 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1127,11 +1127,9 @@ static int pcie_aspm_set_policy(const char *val, if (aspm_disabled) return -EPERM; - for (i = 0; i < ARRAY_SIZE(policy_str); i++) - if (!strncmp(val, policy_str[i], strlen(policy_str[i]))) - break; - if (i >= ARRAY_SIZE(policy_str)) - return -EINVAL; + i = sysfs_match_string(policy_str, val); + if (i < 0) + return i; if (i == aspm_policy) return 0; diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index 921ed979109d..f03279fc87cd 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -6,6 +6,7 @@ * Copyright (C) 2016 Intel Corp. */ +#include <linux/aer.h> #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/init.h> @@ -16,10 +17,8 @@ struct dpc_dev { struct pcie_device *dev; - struct work_struct work; u16 cap_pos; bool rp_extensions; - u32 rp_pio_status; u8 rp_log_size; }; @@ -65,19 +64,13 @@ static int dpc_wait_rp_inactive(struct dpc_dev *dpc) return 0; } -static void dpc_wait_link_inactive(struct dpc_dev *dpc) -{ - struct pci_dev *pdev = dpc->dev->port; - - pcie_wait_for_link(pdev, false); -} - static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev) { struct dpc_dev *dpc; struct pcie_device *pciedev; struct device *devdpc; - u16 cap, ctl; + + u16 cap; /* * DPC disables the Link automatically in hardware, so it has @@ -92,34 +85,17 @@ static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev) * Wait until the Link is inactive, then clear DPC Trigger Status * to allow the Port to leave DPC. */ - dpc_wait_link_inactive(dpc); + pcie_wait_for_link(pdev, false); if (dpc->rp_extensions && dpc_wait_rp_inactive(dpc)) return PCI_ERS_RESULT_DISCONNECT; - if (dpc->rp_extensions && dpc->rp_pio_status) { - pci_write_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_STATUS, - dpc->rp_pio_status); - dpc->rp_pio_status = 0; - } pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS, PCI_EXP_DPC_STATUS_TRIGGER); - pci_read_config_word(pdev, cap + PCI_EXP_DPC_CTL, &ctl); - pci_write_config_word(pdev, cap + PCI_EXP_DPC_CTL, - ctl | PCI_EXP_DPC_CTL_INT_EN); - return PCI_ERS_RESULT_RECOVERED; } -static void dpc_work(struct work_struct *work) -{ - struct dpc_dev *dpc = container_of(work, struct dpc_dev, work); - struct pci_dev *pdev = dpc->dev->port; - - /* We configure DPC so it only triggers on ERR_FATAL */ - pcie_do_fatal_recovery(pdev, PCIE_PORT_SERVICE_DPC); -} static void dpc_process_rp_pio_error(struct dpc_dev *dpc) { @@ -134,8 +110,6 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc) dev_err(dev, "rp_pio_status: %#010x, rp_pio_mask: %#010x\n", status, mask); - dpc->rp_pio_status = status; - pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_SEVERITY, &sev); pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_SYSERROR, &syserr); pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_EXCEPTION, &exc); @@ -146,15 +120,14 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc) pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &dpc_status); first_error = (dpc_status & 0x1f00) >> 8; - status &= ~mask; for (i = 0; i < ARRAY_SIZE(rp_pio_error_string); i++) { - if (status & (1 << i)) + if ((status & ~mask) & (1 << i)) dev_err(dev, "[%2d] %s%s\n", i, rp_pio_error_string[i], first_error == i ? " (First)" : ""); } if (dpc->rp_log_size < 4) - return; + goto clear_status; pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_HEADER_LOG, &dw0); pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_HEADER_LOG + 4, @@ -167,7 +140,7 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc) dw0, dw1, dw2, dw3); if (dpc->rp_log_size < 5) - return; + goto clear_status; pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_IMPSPEC_LOG, &log); dev_err(dev, "RP PIO ImpSpec Log %#010x\n", log); @@ -176,43 +149,26 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc) cap + PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG, &prefix); dev_err(dev, "TLP Prefix Header: dw%d, %#010x\n", i, prefix); } + clear_status: + pci_write_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_STATUS, status); } -static irqreturn_t dpc_irq(int irq, void *context) +static irqreturn_t dpc_handler(int irq, void *context) { - struct dpc_dev *dpc = (struct dpc_dev *)context; + struct aer_err_info info; + struct dpc_dev *dpc = context; struct pci_dev *pdev = dpc->dev->port; struct device *dev = &dpc->dev->device; - u16 cap = dpc->cap_pos, ctl, status, source, reason, ext_reason; - - pci_read_config_word(pdev, cap + PCI_EXP_DPC_CTL, &ctl); - - if (!(ctl & PCI_EXP_DPC_CTL_INT_EN) || ctl == (u16)(~0)) - return IRQ_NONE; + u16 cap = dpc->cap_pos, status, source, reason, ext_reason; pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status); - - if (!(status & PCI_EXP_DPC_STATUS_INTERRUPT)) - return IRQ_NONE; - - if (!(status & PCI_EXP_DPC_STATUS_TRIGGER)) { - pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS, - PCI_EXP_DPC_STATUS_INTERRUPT); - return IRQ_HANDLED; - } - - pci_write_config_word(pdev, cap + PCI_EXP_DPC_CTL, - ctl & ~PCI_EXP_DPC_CTL_INT_EN); - - pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID, - &source); + pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID, &source); dev_info(dev, "DPC containment event, status:%#06x source:%#06x\n", - status, source); + status, source); reason = (status & PCI_EXP_DPC_STATUS_TRIGGER_RSN) >> 1; ext_reason = (status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT) >> 5; - dev_warn(dev, "DPC %s detected, remove downstream devices\n", (reason == 0) ? "unmasked uncorrectable error" : (reason == 1) ? "ERR_NONFATAL" : @@ -220,15 +176,36 @@ static irqreturn_t dpc_irq(int irq, void *context) (ext_reason == 0) ? "RP PIO error" : (ext_reason == 1) ? "software trigger" : "reserved error"); + /* show RP PIO error detail information */ if (dpc->rp_extensions && reason == 3 && ext_reason == 0) dpc_process_rp_pio_error(dpc); + else if (reason == 0 && aer_get_device_error_info(pdev, &info)) { + aer_print_error(pdev, &info); + pci_cleanup_aer_uncorrect_error_status(pdev); + } - pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS, - PCI_EXP_DPC_STATUS_INTERRUPT); + /* We configure DPC so it only triggers on ERR_FATAL */ + pcie_do_fatal_recovery(pdev, PCIE_PORT_SERVICE_DPC); + + return IRQ_HANDLED; +} + +static irqreturn_t dpc_irq(int irq, void *context) +{ + struct dpc_dev *dpc = (struct dpc_dev *)context; + struct pci_dev *pdev = dpc->dev->port; + u16 cap = dpc->cap_pos, status; + + pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status); - schedule_work(&dpc->work); + if (!(status & PCI_EXP_DPC_STATUS_INTERRUPT) || status == (u16)(~0)) + return IRQ_NONE; + pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS, + PCI_EXP_DPC_STATUS_INTERRUPT); + if (status & PCI_EXP_DPC_STATUS_TRIGGER) + return IRQ_WAKE_THREAD; return IRQ_HANDLED; } @@ -250,11 +227,11 @@ static int dpc_probe(struct pcie_device *dev) dpc->cap_pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DPC); dpc->dev = dev; - INIT_WORK(&dpc->work, dpc_work); set_service_data(dev, dpc); - status = devm_request_irq(device, dev->irq, dpc_irq, IRQF_SHARED, - "pcie-dpc", dpc); + status = devm_request_threaded_irq(device, dev->irq, dpc_irq, + dpc_handler, IRQF_SHARED, + "pcie-dpc", dpc); if (status) { dev_warn(device, "request IRQ%d failed: %d\n", dev->irq, status); diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index f02e334beb45..708fd3a0d646 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -175,9 +175,11 @@ out: */ static pci_ers_result_t default_reset_link(struct pci_dev *dev) { - pci_reset_bridge_secondary_bus(dev); + int rc; + + rc = pci_bridge_secondary_bus_reset(dev); pci_printk(KERN_DEBUG, dev, "downstream link has been reset\n"); - return PCI_ERS_RESULT_RECOVERED; + return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED; } static pci_ers_result_t reset_link(struct pci_dev *dev, u32 service) @@ -252,6 +254,7 @@ static pci_ers_result_t broadcast_error_message(struct pci_dev *dev, dev->error_state = state; pci_walk_bus(dev->subordinate, cb, &result_data); if (cb == report_resume) { + pci_aer_clear_device_status(dev); pci_cleanup_aer_uncorrect_error_status(dev); dev->error_state = pci_channel_io_normal; } @@ -259,15 +262,10 @@ static pci_ers_result_t broadcast_error_message(struct pci_dev *dev, /* * If the error is reported by an end point, we think this * error is related to the upstream link of the end point. + * The error is non fatal so the bus is ok; just invoke + * the callback for the function that logged the error. */ - if (state == pci_channel_io_normal) - /* - * the error is non fatal so the bus is ok, just invoke - * the callback for the function that logged the error. - */ - cb(dev, &result_data); - else - pci_walk_bus(dev->bus, cb, &result_data); + cb(dev, &result_data); } return result_data.result; @@ -317,7 +315,8 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service) * do error recovery on all subordinates of the bridge instead * of the bridge and clear the error status of the bridge. */ - pci_cleanup_aer_uncorrect_error_status(dev); + pci_aer_clear_fatal_status(dev); + pci_aer_clear_device_status(dev); } if (result == PCI_ERS_RESULT_RECOVERED) { diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h index 6ffc797a0dc1..d59afa42fc14 100644 --- a/drivers/pci/pcie/portdrv.h +++ b/drivers/pci/pcie/portdrv.h @@ -50,6 +50,7 @@ struct pcie_port_service_driver { int (*probe) (struct pcie_device *dev); void (*remove) (struct pcie_device *dev); int (*suspend) (struct pcie_device *dev); + int (*resume_noirq) (struct pcie_device *dev); int (*resume) (struct pcie_device *dev); /* Device driver may resume normal operations */ @@ -82,6 +83,7 @@ extern struct bus_type pcie_port_bus_type; int pcie_port_device_register(struct pci_dev *dev); #ifdef CONFIG_PM int pcie_port_device_suspend(struct device *dev); +int pcie_port_device_resume_noirq(struct device *dev); int pcie_port_device_resume(struct device *dev); #endif void pcie_port_device_remove(struct pci_dev *dev); diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c index e0261ad4bcdd..7c37d815229e 100644 --- a/drivers/pci/pcie/portdrv_core.c +++ b/drivers/pci/pcie/portdrv_core.c @@ -353,14 +353,19 @@ error_disable: } #ifdef CONFIG_PM -static int suspend_iter(struct device *dev, void *data) +typedef int (*pcie_pm_callback_t)(struct pcie_device *); + +static int pm_iter(struct device *dev, void *data) { struct pcie_port_service_driver *service_driver; + size_t offset = *(size_t *)data; + pcie_pm_callback_t cb; if ((dev->bus == &pcie_port_bus_type) && dev->driver) { service_driver = to_service_driver(dev->driver); - if (service_driver->suspend) - service_driver->suspend(to_pcie_device(dev)); + cb = *(pcie_pm_callback_t *)((void *)service_driver + offset); + if (cb) + return cb(to_pcie_device(dev)); } return 0; } @@ -371,20 +376,14 @@ static int suspend_iter(struct device *dev, void *data) */ int pcie_port_device_suspend(struct device *dev) { - return device_for_each_child(dev, NULL, suspend_iter); + size_t off = offsetof(struct pcie_port_service_driver, suspend); + return device_for_each_child(dev, &off, pm_iter); } -static int resume_iter(struct device *dev, void *data) +int pcie_port_device_resume_noirq(struct device *dev) { - struct pcie_port_service_driver *service_driver; - - if ((dev->bus == &pcie_port_bus_type) && - (dev->driver)) { - service_driver = to_service_driver(dev->driver); - if (service_driver->resume) - service_driver->resume(to_pcie_device(dev)); - } - return 0; + size_t off = offsetof(struct pcie_port_service_driver, resume_noirq); + return device_for_each_child(dev, &off, pm_iter); } /** @@ -393,7 +392,8 @@ static int resume_iter(struct device *dev, void *data) */ int pcie_port_device_resume(struct device *dev) { - return device_for_each_child(dev, NULL, resume_iter); + size_t off = offsetof(struct pcie_port_service_driver, resume); + return device_for_each_child(dev, &off, pm_iter); } #endif /* PM */ diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c index 973f1b80a038..eef22dc29140 100644 --- a/drivers/pci/pcie/portdrv_pci.c +++ b/drivers/pci/pcie/portdrv_pci.c @@ -42,17 +42,6 @@ __setup("pcie_ports=", pcie_port_setup); /* global data */ -static int pcie_portdrv_restore_config(struct pci_dev *dev) -{ - int retval; - - retval = pci_enable_device(dev); - if (retval) - return retval; - pci_set_master(dev); - return 0; -} - #ifdef CONFIG_PM static int pcie_port_runtime_suspend(struct device *dev) { @@ -76,10 +65,12 @@ static int pcie_port_runtime_idle(struct device *dev) static const struct dev_pm_ops pcie_portdrv_pm_ops = { .suspend = pcie_port_device_suspend, + .resume_noirq = pcie_port_device_resume_noirq, .resume = pcie_port_device_resume, .freeze = pcie_port_device_suspend, .thaw = pcie_port_device_resume, .poweroff = pcie_port_device_suspend, + .restore_noirq = pcie_port_device_resume_noirq, .restore = pcie_port_device_resume, .runtime_suspend = pcie_port_runtime_suspend, .runtime_resume = pcie_port_runtime_resume, @@ -160,19 +151,6 @@ static pci_ers_result_t pcie_portdrv_mmio_enabled(struct pci_dev *dev) return PCI_ERS_RESULT_RECOVERED; } -static pci_ers_result_t pcie_portdrv_slot_reset(struct pci_dev *dev) -{ - /* If fatal, restore cfg space for possible link reset at upstream */ - if (dev->error_state == pci_channel_io_frozen) { - dev->state_saved = true; - pci_restore_state(dev); - pcie_portdrv_restore_config(dev); - pci_enable_pcie_error_reporting(dev); - } - - return PCI_ERS_RESULT_RECOVERED; -} - static int resume_iter(struct device *device, void *data) { struct pcie_device *pcie_device; @@ -208,7 +186,6 @@ static const struct pci_device_id port_pci_ids[] = { { static const struct pci_error_handlers pcie_portdrv_err_handler = { .error_detected = pcie_portdrv_error_detected, .mmio_enabled = pcie_portdrv_mmio_enabled, - .slot_reset = pcie_portdrv_slot_reset, .resume = pcie_portdrv_err_resume, }; diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 611adcd9c169..ec784009a36b 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -13,7 +13,6 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/cpumask.h> -#include <linux/pci-aspm.h> #include <linux/aer.h> #include <linux/acpi.h> #include <linux/hypervisor.h> @@ -1549,6 +1548,20 @@ static int pci_intx_mask_broken(struct pci_dev *dev) return 0; } +static void early_dump_pci_device(struct pci_dev *pdev) +{ + u32 value[256 / 4]; + int i; + + pci_info(pdev, "config space:\n"); + + for (i = 0; i < 256; i += 4) + pci_read_config_dword(pdev, i, &value[i / 4]); + + print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 1, + value, 256, false); +} + /** * pci_setup_device - Fill in class and map information of a device * @dev: the device structure to fill @@ -1598,6 +1611,9 @@ int pci_setup_device(struct pci_dev *dev) pci_printk(KERN_DEBUG, dev, "[%04x:%04x] type %02x class %#08x\n", dev->vendor, dev->device, dev->hdr_type, dev->class); + if (pci_early_dump) + early_dump_pci_device(dev); + /* Need to have dev->class ready */ dev->cfg_size = pci_cfg_space_size(dev); @@ -1725,11 +1741,15 @@ int pci_setup_device(struct pci_dev *dev) static void pci_configure_mps(struct pci_dev *dev) { struct pci_dev *bridge = pci_upstream_bridge(dev); - int mps, p_mps, rc; + int mps, mpss, p_mps, rc; if (!pci_is_pcie(dev) || !bridge || !pci_is_pcie(bridge)) return; + /* MPS and MRRS fields are of type 'RsvdP' for VFs, short-circuit out */ + if (dev->is_virtfn) + return; + mps = pcie_get_mps(dev); p_mps = pcie_get_mps(bridge); @@ -1749,6 +1769,14 @@ static void pci_configure_mps(struct pci_dev *dev) if (pcie_bus_config != PCIE_BUS_DEFAULT) return; + mpss = 128 << dev->pcie_mpss; + if (mpss < p_mps && pci_pcie_type(bridge) == PCI_EXP_TYPE_ROOT_PORT) { + pcie_set_mps(bridge, mpss); + pci_info(dev, "Upstream bridge's Max Payload Size set to %d (was %d, max %d)\n", + mpss, p_mps, 128 << bridge->pcie_mpss); + p_mps = pcie_get_mps(bridge); + } + rc = pcie_set_mps(dev, p_mps); if (rc) { pci_warn(dev, "can't set Max Payload Size to %d; if necessary, use \"pci=pcie_bus_safe\" and report a bug\n", @@ -1757,7 +1785,7 @@ static void pci_configure_mps(struct pci_dev *dev) } pci_info(dev, "Max Payload Size set to %d (was %d, max %d)\n", - p_mps, mps, 128 << dev->pcie_mpss); + p_mps, mps, mpss); } static struct hpp_type0 pci_default_type0 = { @@ -2042,6 +2070,29 @@ static void pci_configure_ltr(struct pci_dev *dev) #endif } +static void pci_configure_eetlp_prefix(struct pci_dev *dev) +{ +#ifdef CONFIG_PCI_PASID + struct pci_dev *bridge; + u32 cap; + + if (!pci_is_pcie(dev)) + return; + + pcie_capability_read_dword(dev, PCI_EXP_DEVCAP2, &cap); + if (!(cap & PCI_EXP_DEVCAP2_EE_PREFIX)) + return; + + if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) + dev->eetlp_prefix_path = 1; + else { + bridge = pci_upstream_bridge(dev); + if (bridge && bridge->eetlp_prefix_path) + dev->eetlp_prefix_path = 1; + } +#endif +} + static void pci_configure_device(struct pci_dev *dev) { struct hotplug_params hpp; @@ -2051,6 +2102,7 @@ static void pci_configure_device(struct pci_dev *dev) pci_configure_extended_tags(dev, NULL); pci_configure_relaxed_ordering(dev); pci_configure_ltr(dev); + pci_configure_eetlp_prefix(dev); memset(&hpp, 0, sizeof(hpp)); ret = pci_get_hp_params(dev, &hpp); @@ -2064,6 +2116,7 @@ static void pci_configure_device(struct pci_dev *dev) static void pci_release_capabilities(struct pci_dev *dev) { + pci_aer_exit(dev); pci_vpd_release(dev); pci_iov_release(dev); pci_free_cap_save_buffers(dev); @@ -2156,8 +2209,8 @@ static bool pci_bus_wait_crs(struct pci_bus *bus, int devfn, u32 *l, return true; } -bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l, - int timeout) +bool pci_bus_generic_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l, + int timeout) { if (pci_bus_read_config_dword(bus, devfn, PCI_VENDOR_ID, l)) return false; @@ -2172,6 +2225,24 @@ bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l, return true; } + +bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l, + int timeout) +{ +#ifdef CONFIG_PCI_QUIRKS + struct pci_dev *bridge = bus->self; + + /* + * Certain IDT switches have an issue where they improperly trigger + * ACS Source Validation errors on completions for config reads. + */ + if (bridge && bridge->vendor == PCI_VENDOR_ID_IDT && + bridge->device == 0x80b5) + return pci_idt_bus_quirk(bus, devfn, l, timeout); +#endif + + return pci_bus_generic_read_dev_vendor_id(bus, devfn, l, timeout); +} EXPORT_SYMBOL(pci_bus_read_dev_vendor_id); /* @@ -2205,6 +2276,25 @@ static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn) return dev; } +static void pcie_report_downtraining(struct pci_dev *dev) +{ + if (!pci_is_pcie(dev)) + return; + + /* Look from the device up to avoid downstream ports with no devices */ + if ((pci_pcie_type(dev) != PCI_EXP_TYPE_ENDPOINT) && + (pci_pcie_type(dev) != PCI_EXP_TYPE_LEG_END) && + (pci_pcie_type(dev) != PCI_EXP_TYPE_UPSTREAM)) + return; + + /* Multi-function PCIe devices share the same link/status */ + if (PCI_FUNC(dev->devfn) != 0 || dev->is_virtfn) + return; + + /* Print link status only if the device is constrained by the fabric */ + __pcie_print_link_status(dev, false); +} + static void pci_init_capabilities(struct pci_dev *dev) { /* Enhanced Allocation */ @@ -2240,6 +2330,8 @@ static void pci_init_capabilities(struct pci_dev *dev) /* Advanced Error Reporting */ pci_aer_init(dev); + pcie_report_downtraining(dev); + if (pci_probe_reset_function(dev) == 0) dev->reset_fn = 1; } diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index f439de848658..46f58a9771d7 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -25,8 +25,10 @@ #include <linux/sched.h> #include <linux/ktime.h> #include <linux/mm.h> +#include <linux/nvme.h> #include <linux/platform_data/x86/apple.h> #include <linux/pm_runtime.h> +#include <linux/switchtec.h> #include <asm/dma.h> /* isa_dma_bridge_buggy */ #include "pci.h" @@ -460,6 +462,7 @@ static void quirk_nfp6000(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME, PCI_DEVICE_ID_NETRONOME_NFP4000, quirk_nfp6000); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME, PCI_DEVICE_ID_NETRONOME_NFP6000, quirk_nfp6000); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME, PCI_DEVICE_ID_NETRONOME_NFP5000, quirk_nfp6000); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME, PCI_DEVICE_ID_NETRONOME_NFP6000_VF, quirk_nfp6000); /* On IBM Crocodile ipr SAS adapters, expand BAR to system page size */ @@ -2105,6 +2108,7 @@ static void quirk_netmos(struct pci_dev *dev) if (dev->subsystem_vendor == PCI_VENDOR_ID_IBM && dev->subsystem_device == 0x0299) return; + /* else: fall through */ case PCI_DEVICE_ID_NETMOS_9735: case PCI_DEVICE_ID_NETMOS_9745: case PCI_DEVICE_ID_NETMOS_9845: @@ -2352,6 +2356,9 @@ static void quirk_paxc_bridge(struct pci_dev *pdev) } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16cd, quirk_paxc_bridge); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16f0, quirk_paxc_bridge); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd750, quirk_paxc_bridge); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802, quirk_paxc_bridge); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804, quirk_paxc_bridge); #endif /* @@ -3664,6 +3671,108 @@ static int reset_chelsio_generic_dev(struct pci_dev *dev, int probe) #define PCI_DEVICE_ID_INTEL_IVB_M_VGA 0x0156 #define PCI_DEVICE_ID_INTEL_IVB_M2_VGA 0x0166 +/* + * The Samsung SM961/PM961 controller can sometimes enter a fatal state after + * FLR where config space reads from the device return -1. We seem to be + * able to avoid this condition if we disable the NVMe controller prior to + * FLR. This quirk is generic for any NVMe class device requiring similar + * assistance to quiesce the device prior to FLR. + * + * NVMe specification: https://nvmexpress.org/resources/specifications/ + * Revision 1.0e: + * Chapter 2: Required and optional PCI config registers + * Chapter 3: NVMe control registers + * Chapter 7.3: Reset behavior + */ +static int nvme_disable_and_flr(struct pci_dev *dev, int probe) +{ + void __iomem *bar; + u16 cmd; + u32 cfg; + + if (dev->class != PCI_CLASS_STORAGE_EXPRESS || + !pcie_has_flr(dev) || !pci_resource_start(dev, 0)) + return -ENOTTY; + + if (probe) + return 0; + + bar = pci_iomap(dev, 0, NVME_REG_CC + sizeof(cfg)); + if (!bar) + return -ENOTTY; + + pci_read_config_word(dev, PCI_COMMAND, &cmd); + pci_write_config_word(dev, PCI_COMMAND, cmd | PCI_COMMAND_MEMORY); + + cfg = readl(bar + NVME_REG_CC); + + /* Disable controller if enabled */ + if (cfg & NVME_CC_ENABLE) { + u32 cap = readl(bar + NVME_REG_CAP); + unsigned long timeout; + + /* + * Per nvme_disable_ctrl() skip shutdown notification as it + * could complete commands to the admin queue. We only intend + * to quiesce the device before reset. + */ + cfg &= ~(NVME_CC_SHN_MASK | NVME_CC_ENABLE); + + writel(cfg, bar + NVME_REG_CC); + + /* + * Some controllers require an additional delay here, see + * NVME_QUIRK_DELAY_BEFORE_CHK_RDY. None of those are yet + * supported by this quirk. + */ + + /* Cap register provides max timeout in 500ms increments */ + timeout = ((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies; + + for (;;) { + u32 status = readl(bar + NVME_REG_CSTS); + + /* Ready status becomes zero on disable complete */ + if (!(status & NVME_CSTS_RDY)) + break; + + msleep(100); + + if (time_after(jiffies, timeout)) { + pci_warn(dev, "Timeout waiting for NVMe ready status to clear after disable\n"); + break; + } + } + } + + pci_iounmap(dev, bar); + + pcie_flr(dev); + + return 0; +} + +/* + * Intel DC P3700 NVMe controller will timeout waiting for ready status + * to change after NVMe enable if the driver starts interacting with the + * device too soon after FLR. A 250ms delay after FLR has heuristically + * proven to produce reliably working results for device assignment cases. + */ +static int delay_250ms_after_flr(struct pci_dev *dev, int probe) +{ + if (!pcie_has_flr(dev)) + return -ENOTTY; + + if (probe) + return 0; + + pcie_flr(dev); + + msleep(250); + + return 0; +} + static const struct pci_dev_reset_methods pci_dev_reset_methods[] = { { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82599_SFP_VF, reset_intel_82599_sfp_virtfn }, @@ -3671,6 +3780,8 @@ static const struct pci_dev_reset_methods pci_dev_reset_methods[] = { reset_ivb_igd }, { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_M2_VGA, reset_ivb_igd }, + { PCI_VENDOR_ID_SAMSUNG, 0xa804, nvme_disable_and_flr }, + { PCI_VENDOR_ID_INTEL, 0x0953, delay_250ms_after_flr }, { PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID, reset_chelsio_generic_dev }, { 0 } @@ -3740,6 +3851,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x917a, /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c78 */ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9182, quirk_dma_func1_alias); +/* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c134 */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9183, + quirk_dma_func1_alias); /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c46 */ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x91a0, quirk_dma_func1_alias); @@ -4553,27 +4667,79 @@ static int pci_quirk_enable_intel_spt_pch_acs(struct pci_dev *dev) return 0; } -static const struct pci_dev_enable_acs { +static int pci_quirk_disable_intel_spt_pch_acs_redir(struct pci_dev *dev) +{ + int pos; + u32 cap, ctrl; + + if (!pci_quirk_intel_spt_pch_acs_match(dev)) + return -ENOTTY; + + pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS); + if (!pos) + return -ENOTTY; + + pci_read_config_dword(dev, pos + PCI_ACS_CAP, &cap); + pci_read_config_dword(dev, pos + INTEL_SPT_ACS_CTRL, &ctrl); + + ctrl &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC); + + pci_write_config_dword(dev, pos + INTEL_SPT_ACS_CTRL, ctrl); + + pci_info(dev, "Intel SPT PCH root port workaround: disabled ACS redirect\n"); + + return 0; +} + +static const struct pci_dev_acs_ops { u16 vendor; u16 device; int (*enable_acs)(struct pci_dev *dev); -} pci_dev_enable_acs[] = { - { PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_enable_intel_pch_acs }, - { PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_enable_intel_spt_pch_acs }, - { 0 } + int (*disable_acs_redir)(struct pci_dev *dev); +} pci_dev_acs_ops[] = { + { PCI_VENDOR_ID_INTEL, PCI_ANY_ID, + .enable_acs = pci_quirk_enable_intel_pch_acs, + }, + { PCI_VENDOR_ID_INTEL, PCI_ANY_ID, + .enable_acs = pci_quirk_enable_intel_spt_pch_acs, + .disable_acs_redir = pci_quirk_disable_intel_spt_pch_acs_redir, + }, }; int pci_dev_specific_enable_acs(struct pci_dev *dev) { - const struct pci_dev_enable_acs *i; - int ret; + const struct pci_dev_acs_ops *p; + int i, ret; + + for (i = 0; i < ARRAY_SIZE(pci_dev_acs_ops); i++) { + p = &pci_dev_acs_ops[i]; + if ((p->vendor == dev->vendor || + p->vendor == (u16)PCI_ANY_ID) && + (p->device == dev->device || + p->device == (u16)PCI_ANY_ID) && + p->enable_acs) { + ret = p->enable_acs(dev); + if (ret >= 0) + return ret; + } + } - for (i = pci_dev_enable_acs; i->enable_acs; i++) { - if ((i->vendor == dev->vendor || - i->vendor == (u16)PCI_ANY_ID) && - (i->device == dev->device || - i->device == (u16)PCI_ANY_ID)) { - ret = i->enable_acs(dev); + return -ENOTTY; +} + +int pci_dev_specific_disable_acs_redir(struct pci_dev *dev) +{ + const struct pci_dev_acs_ops *p; + int i, ret; + + for (i = 0; i < ARRAY_SIZE(pci_dev_acs_ops); i++) { + p = &pci_dev_acs_ops[i]; + if ((p->vendor == dev->vendor || + p->vendor == (u16)PCI_ANY_ID) && + (p->device == dev->device || + p->device == (u16)PCI_ANY_ID) && + p->disable_acs_redir) { + ret = p->disable_acs_redir(dev); if (ret >= 0) return ret; } @@ -4753,3 +4919,197 @@ DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_AMD, PCI_ANY_ID, PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8, quirk_gpu_hda); DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8, quirk_gpu_hda); + +/* + * Some IDT switches incorrectly flag an ACS Source Validation error on + * completions for config read requests even though PCIe r4.0, sec + * 6.12.1.1, says that completions are never affected by ACS Source + * Validation. Here's the text of IDT 89H32H8G3-YC, erratum #36: + * + * Item #36 - Downstream port applies ACS Source Validation to Completions + * Section 6.12.1.1 of the PCI Express Base Specification 3.1 states that + * completions are never affected by ACS Source Validation. However, + * completions received by a downstream port of the PCIe switch from a + * device that has not yet captured a PCIe bus number are incorrectly + * dropped by ACS Source Validation by the switch downstream port. + * + * The workaround suggested by IDT is to issue a config write to the + * downstream device before issuing the first config read. This allows the + * downstream device to capture its bus and device numbers (see PCIe r4.0, + * sec 2.2.9), thus avoiding the ACS error on the completion. + * + * However, we don't know when the device is ready to accept the config + * write, so we do config reads until we receive a non-Config Request Retry + * Status, then do the config write. + * + * To avoid hitting the erratum when doing the config reads, we disable ACS + * SV around this process. + */ +int pci_idt_bus_quirk(struct pci_bus *bus, int devfn, u32 *l, int timeout) +{ + int pos; + u16 ctrl = 0; + bool found; + struct pci_dev *bridge = bus->self; + + pos = pci_find_ext_capability(bridge, PCI_EXT_CAP_ID_ACS); + + /* Disable ACS SV before initial config reads */ + if (pos) { + pci_read_config_word(bridge, pos + PCI_ACS_CTRL, &ctrl); + if (ctrl & PCI_ACS_SV) + pci_write_config_word(bridge, pos + PCI_ACS_CTRL, + ctrl & ~PCI_ACS_SV); + } + + found = pci_bus_generic_read_dev_vendor_id(bus, devfn, l, timeout); + + /* Write Vendor ID (read-only) so the endpoint latches its bus/dev */ + if (found) + pci_bus_write_config_word(bus, devfn, PCI_VENDOR_ID, 0); + + /* Re-enable ACS_SV if it was previously enabled */ + if (ctrl & PCI_ACS_SV) + pci_write_config_word(bridge, pos + PCI_ACS_CTRL, ctrl); + + return found; +} + +/* + * Microsemi Switchtec NTB uses devfn proxy IDs to move TLPs between + * NT endpoints via the internal switch fabric. These IDs replace the + * originating requestor ID TLPs which access host memory on peer NTB + * ports. Therefore, all proxy IDs must be aliased to the NTB device + * to permit access when the IOMMU is turned on. + */ +static void quirk_switchtec_ntb_dma_alias(struct pci_dev *pdev) +{ + void __iomem *mmio; + struct ntb_info_regs __iomem *mmio_ntb; + struct ntb_ctrl_regs __iomem *mmio_ctrl; + struct sys_info_regs __iomem *mmio_sys_info; + u64 partition_map; + u8 partition; + int pp; + + if (pci_enable_device(pdev)) { + pci_err(pdev, "Cannot enable Switchtec device\n"); + return; + } + + mmio = pci_iomap(pdev, 0, 0); + if (mmio == NULL) { + pci_disable_device(pdev); + pci_err(pdev, "Cannot iomap Switchtec device\n"); + return; + } + + pci_info(pdev, "Setting Switchtec proxy ID aliases\n"); + + mmio_ntb = mmio + SWITCHTEC_GAS_NTB_OFFSET; + mmio_ctrl = (void __iomem *) mmio_ntb + SWITCHTEC_NTB_REG_CTRL_OFFSET; + mmio_sys_info = mmio + SWITCHTEC_GAS_SYS_INFO_OFFSET; + + partition = ioread8(&mmio_ntb->partition_id); + + partition_map = ioread32(&mmio_ntb->ep_map); + partition_map |= ((u64) ioread32(&mmio_ntb->ep_map + 4)) << 32; + partition_map &= ~(1ULL << partition); + + for (pp = 0; pp < (sizeof(partition_map) * 8); pp++) { + struct ntb_ctrl_regs __iomem *mmio_peer_ctrl; + u32 table_sz = 0; + int te; + + if (!(partition_map & (1ULL << pp))) + continue; + + pci_dbg(pdev, "Processing partition %d\n", pp); + + mmio_peer_ctrl = &mmio_ctrl[pp]; + + table_sz = ioread16(&mmio_peer_ctrl->req_id_table_size); + if (!table_sz) { + pci_warn(pdev, "Partition %d table_sz 0\n", pp); + continue; + } + + if (table_sz > 512) { + pci_warn(pdev, + "Invalid Switchtec partition %d table_sz %d\n", + pp, table_sz); + continue; + } + + for (te = 0; te < table_sz; te++) { + u32 rid_entry; + u8 devfn; + + rid_entry = ioread32(&mmio_peer_ctrl->req_id_table[te]); + devfn = (rid_entry >> 1) & 0xFF; + pci_dbg(pdev, + "Aliasing Partition %d Proxy ID %02x.%d\n", + pp, PCI_SLOT(devfn), PCI_FUNC(devfn)); + pci_add_dma_alias(pdev, devfn); + } + } + + pci_iounmap(pdev, mmio); + pci_disable_device(pdev); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8531, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8532, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8533, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8534, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8535, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8536, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8543, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8544, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8545, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8546, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8551, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8552, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8553, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8554, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8555, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8556, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8561, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8562, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8563, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8564, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8565, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8566, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8571, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8572, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8573, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8574, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8575, + quirk_switchtec_ntb_dma_alias); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8576, + quirk_switchtec_ntb_dma_alias); diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 5e3d0dced2b8..461e7fd2756f 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/pci.h> #include <linux/module.h> -#include <linux/pci-aspm.h> #include "pci.h" static void pci_free_resources(struct pci_dev *dev) diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c index a7b5c37a85ec..137bf0cee897 100644 --- a/drivers/pci/rom.c +++ b/drivers/pci/rom.c @@ -80,7 +80,8 @@ EXPORT_SYMBOL_GPL(pci_disable_rom); * The PCI window size could be much larger than the * actual image size. */ -size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size) +static size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, + size_t size) { void __iomem *image; int last_image; @@ -106,8 +107,14 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size) length = readw(pds + 16); image += length * 512; /* Avoid iterating through memory outside the resource window */ - if (image > rom + size) + if (image >= rom + size) break; + if (!last_image) { + if (readw(image) != 0xAA55) { + pci_info(pdev, "No more image in the PCI ROM\n"); + break; + } + } } while (length && !last_image); /* never return a size larger than the PCI resource window */ diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 47cd0c037433..9940cc70f38b 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -641,7 +641,7 @@ static int ioctl_event_summary(struct switchtec_dev *stdev, for (i = 0; i < SWITCHTEC_MAX_PFF_CSR; i++) { reg = ioread16(&stdev->mmio_pff_csr[i].vendor_id); - if (reg != MICROSEMI_VENDOR_ID) + if (reg != PCI_VENDOR_ID_MICROSEMI) break; reg = ioread32(&stdev->mmio_pff_csr[i].pff_event_summary); @@ -1203,7 +1203,7 @@ static void init_pff(struct switchtec_dev *stdev) for (i = 0; i < SWITCHTEC_MAX_PFF_CSR; i++) { reg = ioread16(&stdev->mmio_pff_csr[i].vendor_id); - if (reg != MICROSEMI_VENDOR_ID) + if (reg != PCI_VENDOR_ID_MICROSEMI) break; } @@ -1267,7 +1267,7 @@ static int switchtec_pci_probe(struct pci_dev *pdev, struct switchtec_dev *stdev; int rc; - if (pdev->class == MICROSEMI_NTB_CLASSCODE) + if (pdev->class == (PCI_CLASS_BRIDGE_OTHER << 8)) request_module_nowait("ntb_hw_switchtec"); stdev = stdev_create(pdev); @@ -1321,19 +1321,19 @@ static void switchtec_pci_remove(struct pci_dev *pdev) #define SWITCHTEC_PCI_DEVICE(device_id) \ { \ - .vendor = MICROSEMI_VENDOR_ID, \ + .vendor = PCI_VENDOR_ID_MICROSEMI, \ .device = device_id, \ .subvendor = PCI_ANY_ID, \ .subdevice = PCI_ANY_ID, \ - .class = MICROSEMI_MGMT_CLASSCODE, \ + .class = (PCI_CLASS_MEMORY_OTHER << 8), \ .class_mask = 0xFFFFFFFF, \ }, \ { \ - .vendor = MICROSEMI_VENDOR_ID, \ + .vendor = PCI_VENDOR_ID_MICROSEMI, \ .device = device_id, \ .subvendor = PCI_ANY_ID, \ .subdevice = PCI_ANY_ID, \ - .class = MICROSEMI_NTB_CLASSCODE, \ + .class = (PCI_CLASS_BRIDGE_OTHER << 8), \ .class_mask = 0xFFFFFFFF, \ } diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c index 8617565ba561..4963c2e2bd4c 100644 --- a/drivers/pci/vpd.c +++ b/drivers/pci/vpd.c @@ -146,7 +146,7 @@ static int pci_vpd_wait(struct pci_dev *dev) if (!vpd->busy) return 0; - while (time_before(jiffies, timeout)) { + do { ret = pci_user_read_config_word(dev, vpd->cap + PCI_VPD_ADDR, &status); if (ret < 0) @@ -160,10 +160,13 @@ static int pci_vpd_wait(struct pci_dev *dev) if (fatal_signal_pending(current)) return -EINTR; + if (time_after(jiffies, timeout)) + break; + usleep_range(10, max_sleep); if (max_sleep < 1024) max_sleep *= 2; - } + } while (true); pci_warn(dev, "VPD access failed. This is likely a firmware bug on this device. Contact the card vendor for a firmware update\n"); return -ETIMEDOUT; diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 3d523ca64694..d67f32a29bb4 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -858,12 +858,6 @@ static int asus_get_adapter_status(struct hotplug_slot *hotplug_slot, return 0; } -static void asus_cleanup_pci_hotplug(struct hotplug_slot *hotplug_slot) -{ - kfree(hotplug_slot->info); - kfree(hotplug_slot); -} - static struct hotplug_slot_ops asus_hotplug_slot_ops = { .owner = THIS_MODULE, .get_adapter_status = asus_get_adapter_status, @@ -905,7 +899,6 @@ static int asus_setup_pci_hotplug(struct asus_wmi *asus) goto error_info; asus->hotplug_slot->private = asus; - asus->hotplug_slot->release = &asus_cleanup_pci_hotplug; asus->hotplug_slot->ops = &asus_hotplug_slot_ops; asus_get_adapter_status(asus->hotplug_slot, &asus->hotplug_slot->info->adapter_status); @@ -1051,8 +1044,11 @@ static void asus_wmi_rfkill_exit(struct asus_wmi *asus) * asus_unregister_rfkill_notifier() */ asus_rfkill_hotplug(asus); - if (asus->hotplug_slot) + if (asus->hotplug_slot) { pci_hp_deregister(asus->hotplug_slot); + kfree(asus->hotplug_slot->info); + kfree(asus->hotplug_slot); + } if (asus->hotplug_workqueue) destroy_workqueue(asus->hotplug_workqueue); diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c index 4c38904a8a32..a4bbf6ecd1f0 100644 --- a/drivers/platform/x86/eeepc-laptop.c +++ b/drivers/platform/x86/eeepc-laptop.c @@ -726,12 +726,6 @@ static int eeepc_get_adapter_status(struct hotplug_slot *hotplug_slot, return 0; } -static void eeepc_cleanup_pci_hotplug(struct hotplug_slot *hotplug_slot) -{ - kfree(hotplug_slot->info); - kfree(hotplug_slot); -} - static struct hotplug_slot_ops eeepc_hotplug_slot_ops = { .owner = THIS_MODULE, .get_adapter_status = eeepc_get_adapter_status, @@ -758,7 +752,6 @@ static int eeepc_setup_pci_hotplug(struct eeepc_laptop *eeepc) goto error_info; eeepc->hotplug_slot->private = eeepc; - eeepc->hotplug_slot->release = &eeepc_cleanup_pci_hotplug; eeepc->hotplug_slot->ops = &eeepc_hotplug_slot_ops; eeepc_get_adapter_status(eeepc->hotplug_slot, &eeepc->hotplug_slot->info->adapter_status); @@ -837,8 +830,11 @@ static void eeepc_rfkill_exit(struct eeepc_laptop *eeepc) eeepc->wlan_rfkill = NULL; } - if (eeepc->hotplug_slot) + if (eeepc->hotplug_slot) { pci_hp_deregister(eeepc->hotplug_slot); + kfree(eeepc->hotplug_slot->info); + kfree(eeepc->hotplug_slot); + } if (eeepc->bluetooth_rfkill) { rfkill_unregister(eeepc->bluetooth_rfkill); diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 125b58eff936..3b1083fdb898 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -1014,8 +1014,7 @@ reset_info_exit: &info, slot); if (!ret) /* User has access, do the reset */ - ret = slot ? pci_try_reset_slot(vdev->pdev->slot) : - pci_try_reset_bus(vdev->pdev->bus); + ret = pci_reset_bus(vdev->pdev); hot_reset_release: for (i--; i >= 0; i--) @@ -1377,8 +1376,7 @@ static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev) } if (needs_reset) - ret = slot ? pci_try_reset_slot(vdev->pdev->slot) : - pci_try_reset_bus(vdev->pdev->bus); + ret = pci_reset_bus(vdev->pdev); put_devs: for (i = 0; i < devs.cur_index; i++) { diff --git a/include/linux/dma-direction.h b/include/linux/dma-direction.h index 3649a031893a..9c96e30e6a0b 100644 --- a/include/linux/dma-direction.h +++ b/include/linux/dma-direction.h @@ -1,14 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_DMA_DIRECTION_H #define _LINUX_DMA_DIRECTION_H -/* - * These definitions mirror those in pci.h, so they can be used - * interchangeably with their PCI_ counterparts. - */ + enum dma_data_direction { DMA_BIDIRECTIONAL = 0, DMA_TO_DEVICE = 1, DMA_FROM_DEVICE = 2, DMA_NONE = 3, }; + #endif diff --git a/include/linux/pci-dma-compat.h b/include/linux/pci-dma-compat.h index 0dd1a3f7b309..c3f1b44ade29 100644 --- a/include/linux/pci-dma-compat.h +++ b/include/linux/pci-dma-compat.h @@ -8,10 +8,10 @@ #include <linux/dma-mapping.h> /* This defines the direction arg to the DMA mapping routines. */ -#define PCI_DMA_BIDIRECTIONAL 0 -#define PCI_DMA_TODEVICE 1 -#define PCI_DMA_FROMDEVICE 2 -#define PCI_DMA_NONE 3 +#define PCI_DMA_BIDIRECTIONAL DMA_BIDIRECTIONAL +#define PCI_DMA_TODEVICE DMA_TO_DEVICE +#define PCI_DMA_FROMDEVICE DMA_FROM_DEVICE +#define PCI_DMA_NONE DMA_NONE static inline void * pci_alloc_consistent(struct pci_dev *hwdev, size_t size, diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index 243eaa5a66ff..37dab8116901 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -17,6 +17,7 @@ enum pci_epc_irq_type { PCI_EPC_IRQ_UNKNOWN, PCI_EPC_IRQ_LEGACY, PCI_EPC_IRQ_MSI, + PCI_EPC_IRQ_MSIX, }; /** @@ -30,7 +31,11 @@ enum pci_epc_irq_type { * capability register * @get_msi: ops to get the number of MSI interrupts allocated by the RC from * the MSI capability register - * @raise_irq: ops to raise a legacy or MSI interrupt + * @set_msix: ops to set the requested number of MSI-X interrupts in the + * MSI-X capability register + * @get_msix: ops to get the number of MSI-X interrupts allocated by the RC + * from the MSI-X capability register + * @raise_irq: ops to raise a legacy, MSI or MSI-X interrupt * @start: ops to start the PCI link * @stop: ops to stop the PCI link * @owner: the module owner containing the ops @@ -48,8 +53,10 @@ struct pci_epc_ops { phys_addr_t addr); int (*set_msi)(struct pci_epc *epc, u8 func_no, u8 interrupts); int (*get_msi)(struct pci_epc *epc, u8 func_no); + int (*set_msix)(struct pci_epc *epc, u8 func_no, u16 interrupts); + int (*get_msix)(struct pci_epc *epc, u8 func_no); int (*raise_irq)(struct pci_epc *epc, u8 func_no, - enum pci_epc_irq_type type, u8 interrupt_num); + enum pci_epc_irq_type type, u16 interrupt_num); int (*start)(struct pci_epc *epc); void (*stop)(struct pci_epc *epc); struct module *owner; @@ -95,6 +102,7 @@ struct pci_epc { #define EPC_FEATURE_NO_LINKUP_NOTIFIER BIT(0) #define EPC_FEATURE_BAR_MASK (BIT(1) | BIT(2) | BIT(3)) +#define EPC_FEATURE_MSIX_AVAILABLE BIT(4) #define EPC_FEATURE_SET_BAR(features, bar) \ (features |= (EPC_FEATURE_BAR_MASK & (bar << 1))) #define EPC_FEATURE_GET_BAR(features) \ @@ -144,8 +152,10 @@ void pci_epc_unmap_addr(struct pci_epc *epc, u8 func_no, phys_addr_t phys_addr); int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts); int pci_epc_get_msi(struct pci_epc *epc, u8 func_no); +int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts); +int pci_epc_get_msix(struct pci_epc *epc, u8 func_no); int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, - enum pci_epc_irq_type type, u8 interrupt_num); + enum pci_epc_irq_type type, u16 interrupt_num); int pci_epc_start(struct pci_epc *epc); void pci_epc_stop(struct pci_epc *epc); struct pci_epc *pci_epc_get(const char *epc_name); diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 4e7764935fa8..ec02f58758c8 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -119,6 +119,7 @@ struct pci_epf { struct pci_epf_header *header; struct pci_epf_bar bar[6]; u8 msi_interrupts; + u16 msix_interrupts; u8 func_no; struct pci_epc *epc; diff --git a/include/linux/pci.h b/include/linux/pci.h index 5f13cdbc73cd..9b87f1936906 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -302,6 +302,7 @@ struct pci_dev { u8 hdr_type; /* PCI header type (`multi' flag masked out) */ #ifdef CONFIG_PCIEAER u16 aer_cap; /* AER capability offset */ + struct aer_stats *aer_stats; /* AER stats for this device */ #endif u8 pcie_cap; /* PCIe capability offset */ u8 msi_cap; /* MSI capability offset */ @@ -353,6 +354,7 @@ struct pci_dev { unsigned int ltr_path:1; /* Latency Tolerance Reporting supported from root to here */ #endif + unsigned int eetlp_prefix_path:1; /* End-to-End TLP Prefix */ pci_channel_state_t error_state; /* Current connectivity state */ struct device dev; /* Generic device interface */ @@ -390,6 +392,7 @@ struct pci_dev { unsigned int is_virtfn:1; unsigned int reset_fn:1; unsigned int is_hotplug_bridge:1; + unsigned int shpc_managed:1; /* SHPC owned by shpchp */ unsigned int is_thunderbolt:1; /* Thunderbolt controller */ unsigned int __aer_firmware_first_valid:1; unsigned int __aer_firmware_first:1; @@ -821,6 +824,21 @@ struct pci_driver { .vendor = PCI_VENDOR_ID_##vend, .device = (dev), \ .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, 0, 0 +/** + * PCI_DEVICE_DATA - macro used to describe a specific PCI device in very short form + * @vend: the vendor name (without PCI_VENDOR_ID_ prefix) + * @dev: the device name (without PCI_DEVICE_ID_<vend>_ prefix) + * @data: the driver data to be filled + * + * This macro is used to create a struct pci_device_id that matches a + * specific PCI device. The subvendor, and subdevice fields will be set + * to PCI_ANY_ID. + */ +#define PCI_DEVICE_DATA(vend, dev, data) \ + .vendor = PCI_VENDOR_ID_##vend, .device = PCI_DEVICE_ID_##vend##_##dev, \ + .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, 0, 0, \ + .driver_data = (kernel_ulong_t)(data) + enum { PCI_REASSIGN_ALL_RSRC = 0x00000001, /* Ignore firmware setup */ PCI_REASSIGN_ALL_BUS = 0x00000002, /* Reassign all bus numbers */ @@ -1091,20 +1109,17 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev, enum pci_bus_speed *speed, enum pcie_link_width *width); void pcie_print_link_status(struct pci_dev *dev); +bool pcie_has_flr(struct pci_dev *dev); int pcie_flr(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); int pci_reset_function_locked(struct pci_dev *dev); int pci_try_reset_function(struct pci_dev *dev); int pci_probe_reset_slot(struct pci_slot *slot); -int pci_reset_slot(struct pci_slot *slot); -int pci_try_reset_slot(struct pci_slot *slot); int pci_probe_reset_bus(struct pci_bus *bus); -int pci_reset_bus(struct pci_bus *bus); -int pci_try_reset_bus(struct pci_bus *bus); +int pci_reset_bus(struct pci_dev *dev); void pci_reset_secondary_bus(struct pci_dev *dev); void pcibios_reset_secondary_bus(struct pci_dev *dev); -int pci_reset_bridge_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align); @@ -1124,7 +1139,6 @@ int pci_enable_rom(struct pci_dev *pdev); void pci_disable_rom(struct pci_dev *pdev); void __iomem __must_check *pci_map_rom(struct pci_dev *pdev, size_t *size); void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom); -size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size); void __iomem __must_check *pci_platform_rom(struct pci_dev *pdev, size_t *size); /* Power management related routines */ @@ -1472,13 +1486,9 @@ static inline bool pcie_aspm_support_enabled(void) { return false; } #endif #ifdef CONFIG_PCIEAER -void pci_no_aer(void); bool pci_aer_available(void); -int pci_aer_init(struct pci_dev *dev); #else -static inline void pci_no_aer(void) { } static inline bool pci_aer_available(void) { return false; } -static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; } #endif #ifdef CONFIG_PCIE_ECRC @@ -1880,20 +1890,9 @@ enum pci_fixup_pass { #ifdef CONFIG_PCI_QUIRKS void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev); -int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags); -int pci_dev_specific_enable_acs(struct pci_dev *dev); #else static inline void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev) { } -static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev, - u16 acs_flags) -{ - return -ENOTTY; -} -static inline int pci_dev_specific_enable_acs(struct pci_dev *dev) -{ - return -ENOTTY; -} #endif void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen); diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index cf5e22103f68..a6d6650a0490 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -80,15 +80,12 @@ struct hotplug_slot_info { * @ops: pointer to the &struct hotplug_slot_ops to be used for this slot * @info: pointer to the &struct hotplug_slot_info for the initial values for * this slot. - * @release: called during pci_hp_deregister to free memory allocated in a - * hotplug_slot structure. * @private: used by the hotplug pci controller driver to store whatever it * needs. */ struct hotplug_slot { struct hotplug_slot_ops *ops; struct hotplug_slot_info *info; - void (*release) (struct hotplug_slot *slot); void *private; /* Variables below this are for use only by the hotplug pci core. */ @@ -104,13 +101,23 @@ static inline const char *hotplug_slot_name(const struct hotplug_slot *slot) int __pci_hp_register(struct hotplug_slot *slot, struct pci_bus *pbus, int nr, const char *name, struct module *owner, const char *mod_name); -int pci_hp_deregister(struct hotplug_slot *slot); +int __pci_hp_initialize(struct hotplug_slot *slot, struct pci_bus *bus, int nr, + const char *name, struct module *owner, + const char *mod_name); +int pci_hp_add(struct hotplug_slot *slot); + +void pci_hp_del(struct hotplug_slot *slot); +void pci_hp_destroy(struct hotplug_slot *slot); +void pci_hp_deregister(struct hotplug_slot *slot); + int __must_check pci_hp_change_slot_info(struct hotplug_slot *slot, struct hotplug_slot_info *info); /* use a define to avoid include chaining to get THIS_MODULE & friends */ #define pci_hp_register(slot, pbus, devnr, name) \ __pci_hp_register(slot, pbus, devnr, name, THIS_MODULE, KBUILD_MODNAME) +#define pci_hp_initialize(slot, bus, nr, name) \ + __pci_hp_initialize(slot, bus, nr, name, THIS_MODULE, KBUILD_MODNAME) /* PCI Setting Record (Type 0) */ struct hpp_type0 { diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 29502238e510..99d366cb0e9f 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1668,6 +1668,7 @@ #define PCI_DEVICE_ID_COMPEX_ENET100VG4 0x0112 #define PCI_VENDOR_ID_PMC_Sierra 0x11f8 +#define PCI_VENDOR_ID_MICROSEMI 0x11f8 #define PCI_VENDOR_ID_RP 0x11fe #define PCI_DEVICE_ID_RP32INTF 0x0001 @@ -2541,6 +2542,7 @@ #define PCI_DEVICE_ID_NETRONOME_NFP3200 0x3200 #define PCI_DEVICE_ID_NETRONOME_NFP3240 0x3240 #define PCI_DEVICE_ID_NETRONOME_NFP4000 0x4000 +#define PCI_DEVICE_ID_NETRONOME_NFP5000 0x5000 #define PCI_DEVICE_ID_NETRONOME_NFP6000 0x6000 #define PCI_DEVICE_ID_NETRONOME_NFP6000_VF 0x6003 diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index ec93e93371fa..ab400af6f0ce 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -19,10 +19,6 @@ #include <linux/pci.h> #include <linux/cdev.h> -#define MICROSEMI_VENDOR_ID 0x11f8 -#define MICROSEMI_NTB_CLASSCODE 0x068000 -#define MICROSEMI_MGMT_CLASSCODE 0x058000 - #define SWITCHTEC_MRPC_PAYLOAD_SIZE 1024 #define SWITCHTEC_MAX_PFF_CSR 48 diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 4da87e2ef8a8..ee556ccc93f4 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -636,6 +636,7 @@ #define PCI_EXP_DEVCAP2_OBFF_MASK 0x000c0000 /* OBFF support mechanism */ #define PCI_EXP_DEVCAP2_OBFF_MSG 0x00040000 /* New message signaling */ #define PCI_EXP_DEVCAP2_OBFF_WAKE 0x00080000 /* Re-use WAKE# for OBFF */ +#define PCI_EXP_DEVCAP2_EE_PREFIX 0x00200000 /* End-End TLP Prefix */ #define PCI_EXP_DEVCTL2 40 /* Device Control 2 */ #define PCI_EXP_DEVCTL2_COMP_TIMEOUT 0x000f /* Completion Timeout Value */ #define PCI_EXP_DEVCTL2_COMP_TMOUT_DIS 0x0010 /* Completion Timeout Disable */ @@ -960,8 +961,9 @@ #define PCI_REBAR_CTRL 8 /* control register */ #define PCI_REBAR_CTRL_BAR_IDX 0x00000007 /* BAR index */ #define PCI_REBAR_CTRL_NBAR_MASK 0x000000E0 /* # of resizable BARs */ -#define PCI_REBAR_CTRL_NBAR_SHIFT 5 /* shift for # of BARs */ +#define PCI_REBAR_CTRL_NBAR_SHIFT 5 /* shift for # of BARs */ #define PCI_REBAR_CTRL_BAR_SIZE 0x00001F00 /* BAR size */ +#define PCI_REBAR_CTRL_BAR_SHIFT 8 /* shift for BAR size */ /* Dynamic Power Allocation */ #define PCI_DPA_CAP 4 /* capability register */ diff --git a/include/uapi/linux/pcitest.h b/include/uapi/linux/pcitest.h index 953cf036cb26..cbf422e56696 100644 --- a/include/uapi/linux/pcitest.h +++ b/include/uapi/linux/pcitest.h @@ -16,5 +16,8 @@ #define PCITEST_WRITE _IOW('P', 0x4, unsigned long) #define PCITEST_READ _IOW('P', 0x5, unsigned long) #define PCITEST_COPY _IOW('P', 0x6, unsigned long) +#define PCITEST_MSIX _IOW('P', 0x7, int) +#define PCITEST_SET_IRQTYPE _IOW('P', 0x8, int) +#define PCITEST_GET_IRQTYPE _IO('P', 0x9) #endif /* __UAPI_LINUX_PCITEST_H */ diff --git a/tools/pci/pcitest.c b/tools/pci/pcitest.c index 9074b477bff0..af146bb03b4d 100644 --- a/tools/pci/pcitest.c +++ b/tools/pci/pcitest.c @@ -31,12 +31,17 @@ #define BILLION 1E9 static char *result[] = { "NOT OKAY", "OKAY" }; +static char *irq[] = { "LEGACY", "MSI", "MSI-X" }; struct pci_test { char *device; char barnum; bool legacyirq; unsigned int msinum; + unsigned int msixnum; + int irqtype; + bool set_irqtype; + bool get_irqtype; bool read; bool write; bool copy; @@ -65,6 +70,24 @@ static int run_test(struct pci_test *test) fprintf(stdout, "%s\n", result[ret]); } + if (test->set_irqtype) { + ret = ioctl(fd, PCITEST_SET_IRQTYPE, test->irqtype); + fprintf(stdout, "SET IRQ TYPE TO %s:\t\t", irq[test->irqtype]); + if (ret < 0) + fprintf(stdout, "FAILED\n"); + else + fprintf(stdout, "%s\n", result[ret]); + } + + if (test->get_irqtype) { + ret = ioctl(fd, PCITEST_GET_IRQTYPE); + fprintf(stdout, "GET IRQ TYPE:\t\t"); + if (ret < 0) + fprintf(stdout, "FAILED\n"); + else + fprintf(stdout, "%s\n", irq[ret]); + } + if (test->legacyirq) { ret = ioctl(fd, PCITEST_LEGACY_IRQ, 0); fprintf(stdout, "LEGACY IRQ:\t"); @@ -83,6 +106,15 @@ static int run_test(struct pci_test *test) fprintf(stdout, "%s\n", result[ret]); } + if (test->msixnum > 0 && test->msixnum <= 2048) { + ret = ioctl(fd, PCITEST_MSIX, test->msixnum); + fprintf(stdout, "MSI-X%d:\t\t", test->msixnum); + if (ret < 0) + fprintf(stdout, "TEST FAILED\n"); + else + fprintf(stdout, "%s\n", result[ret]); + } + if (test->write) { ret = ioctl(fd, PCITEST_WRITE, test->size); fprintf(stdout, "WRITE (%7ld bytes):\t\t", test->size); @@ -133,7 +165,7 @@ int main(int argc, char **argv) /* set default endpoint device */ test->device = "/dev/pci-endpoint-test.0"; - while ((c = getopt(argc, argv, "D:b:m:lrwcs:")) != EOF) + while ((c = getopt(argc, argv, "D:b:m:x:i:Ilrwcs:")) != EOF) switch (c) { case 'D': test->device = optarg; @@ -151,6 +183,20 @@ int main(int argc, char **argv) if (test->msinum < 1 || test->msinum > 32) goto usage; continue; + case 'x': + test->msixnum = atoi(optarg); + if (test->msixnum < 1 || test->msixnum > 2048) + goto usage; + continue; + case 'i': + test->irqtype = atoi(optarg); + if (test->irqtype < 0 || test->irqtype > 2) + goto usage; + test->set_irqtype = true; + continue; + case 'I': + test->get_irqtype = true; + continue; case 'r': test->read = true; continue; @@ -173,6 +219,9 @@ usage: "\t-D <dev> PCI endpoint test device {default: /dev/pci-endpoint-test.0}\n" "\t-b <bar num> BAR test (bar number between 0..5)\n" "\t-m <msi num> MSI test (msi number between 1..32)\n" + "\t-x <msix num> \tMSI-X test (msix number between 1..2048)\n" + "\t-i <irq type> \tSet IRQ type (0 - Legacy, 1 - MSI, 2 - MSI-X)\n" + "\t-I Get current IRQ type configured\n" "\t-l Legacy IRQ test\n" "\t-r Read buffer test\n" "\t-w Write buffer test\n" diff --git a/tools/pci/pcitest.sh b/tools/pci/pcitest.sh index 77e8c85ef744..75ed48ff2990 100644 --- a/tools/pci/pcitest.sh +++ b/tools/pci/pcitest.sh @@ -16,7 +16,10 @@ echo echo "Interrupt tests" echo +pcitest -i 0 pcitest -l + +pcitest -i 1 msi=1 while [ $msi -lt 33 ] @@ -26,9 +29,21 @@ do done echo +pcitest -i 2 +msix=1 + +while [ $msix -lt 2049 ] +do + pcitest -x $msix + msix=`expr $msix + 1` +done +echo + echo "Read Tests" echo +pcitest -i 1 + pcitest -r -s 1 pcitest -r -s 1024 pcitest -r -s 1025 |