diff options
479 files changed, 6631 insertions, 2529 deletions
diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 7ca8df5451d4..68b21395a743 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -1458,11 +1458,22 @@ unprivileged_bpf_disabled ========================= Writing 1 to this entry will disable unprivileged calls to ``bpf()``; -once disabled, calling ``bpf()`` without ``CAP_SYS_ADMIN`` will return -``-EPERM``. +once disabled, calling ``bpf()`` without ``CAP_SYS_ADMIN`` or ``CAP_BPF`` +will return ``-EPERM``. Once set to 1, this can't be cleared from the +running kernel anymore. -Once set, this can't be cleared. +Writing 2 to this entry will also disable unprivileged calls to ``bpf()``, +however, an admin can still change this setting later on, if needed, by +writing 0 or 1 to this entry. +If ``BPF_UNPRIV_DEFAULT_OFF`` is enabled in the kernel config, then this +entry will default to 2 instead of 0. + += ============================================================= +0 Unprivileged calls to ``bpf()`` are enabled +1 Unprivileged calls to ``bpf()`` are disabled without recovery +2 Unprivileged calls to ``bpf()`` are disabled += ============================================================= watchdog ======== diff --git a/Documentation/devicetree/bindings/i2c/i2c-mpc.yaml b/Documentation/devicetree/bindings/i2c/i2c-mpc.yaml index 7b553d559c83..98c6fcf7bf26 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-mpc.yaml +++ b/Documentation/devicetree/bindings/i2c/i2c-mpc.yaml @@ -46,6 +46,13 @@ properties: description: | I2C bus timeout in microseconds + fsl,i2c-erratum-a004447: + $ref: /schemas/types.yaml#/definitions/flag + description: | + Indicates the presence of QorIQ erratum A-004447, which + says that the standard i2c recovery scheme mechanism does + not work and an alternate implementation is needed. + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/net/renesas,ether.yaml b/Documentation/devicetree/bindings/net/renesas,ether.yaml index 8ce5ed8a58dd..c101a1ec846e 100644 --- a/Documentation/devicetree/bindings/net/renesas,ether.yaml +++ b/Documentation/devicetree/bindings/net/renesas,ether.yaml @@ -10,7 +10,7 @@ allOf: - $ref: ethernet-controller.yaml# maintainers: - - Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> + - Sergei Shtylyov <sergei.shtylyov@gmail.com> properties: compatible: diff --git a/Documentation/driver-api/usb/usb.rst b/Documentation/driver-api/usb/usb.rst index 820e867af45a..2c94ff2f4385 100644 --- a/Documentation/driver-api/usb/usb.rst +++ b/Documentation/driver-api/usb/usb.rst @@ -123,6 +123,8 @@ are in ``drivers/usb/common/common.c``. In addition, some functions useful for creating debugging output are defined in ``drivers/usb/common/debug.c``. +.. _usb_header: + Host-Side Data Types and Macros =============================== diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst index bd9165241b6c..6efb41cc8072 100644 --- a/Documentation/userspace-api/seccomp_filter.rst +++ b/Documentation/userspace-api/seccomp_filter.rst @@ -250,14 +250,14 @@ Users can read via ``ioctl(SECCOMP_IOCTL_NOTIF_RECV)`` (or ``poll()``) on a seccomp notification fd to receive a ``struct seccomp_notif``, which contains five members: the input length of the structure, a unique-per-filter ``id``, the ``pid`` of the task which triggered this request (which may be 0 if the -task is in a pid ns not visible from the listener's pid namespace), a ``flags`` -member which for now only has ``SECCOMP_NOTIF_FLAG_SIGNALED``, representing -whether or not the notification is a result of a non-fatal signal, and the -``data`` passed to seccomp. Userspace can then make a decision based on this -information about what to do, and ``ioctl(SECCOMP_IOCTL_NOTIF_SEND)`` a -response, indicating what should be returned to userspace. The ``id`` member of -``struct seccomp_notif_resp`` should be the same ``id`` as in ``struct -seccomp_notif``. +task is in a pid ns not visible from the listener's pid namespace). The +notification also contains the ``data`` passed to seccomp, and a filters flag. +The structure should be zeroed out prior to calling the ioctl. + +Userspace can then make a decision based on this information about what to do, +and ``ioctl(SECCOMP_IOCTL_NOTIF_SEND)`` a response, indicating what should be +returned to userspace. The ``id`` member of ``struct seccomp_notif_resp`` should +be the same ``id`` as in ``struct seccomp_notif``. It is worth noting that ``struct seccomp_data`` contains the values of register arguments to the syscall, but does not contain pointers to memory. The task's diff --git a/Documentation/virt/kvm/vcpu-requests.rst b/Documentation/virt/kvm/vcpu-requests.rst index 5feb3706a7ae..af1b37441e0a 100644 --- a/Documentation/virt/kvm/vcpu-requests.rst +++ b/Documentation/virt/kvm/vcpu-requests.rst @@ -118,10 +118,12 @@ KVM_REQ_MMU_RELOAD necessary to inform each VCPU to completely refresh the tables. This request is used for that. -KVM_REQ_PENDING_TIMER +KVM_REQ_UNBLOCK - This request may be made from a timer handler run on the host on behalf - of a VCPU. It informs the VCPU thread to inject a timer interrupt. + This request informs the vCPU to exit kvm_vcpu_block. It is used for + example from timer handlers that run on the host on behalf of a vCPU, + or in order to update the interrupt routing and ensure that assigned + devices will wake up the vCPU. KVM_REQ_UNHALT diff --git a/MAINTAINERS b/MAINTAINERS index 04babfa8fc76..673cadd5107a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4138,6 +4138,14 @@ S: Odd Fixes F: Documentation/devicetree/bindings/arm/cavium-thunder2.txt F: arch/arm64/boot/dts/cavium/thunder2-99xx* +CBS/ETF/TAPRIO QDISCS +M: Vinicius Costa Gomes <vinicius.gomes@intel.com> +S: Maintained +L: netdev@vger.kernel.org +F: net/sched/sch_cbs.c +F: net/sched/sch_etf.c +F: net/sched/sch_taprio.c + CC2520 IEEE-802.15.4 RADIO DRIVER M: Varka Bhadram <varkabhadram@gmail.com> L: linux-wpan@vger.kernel.org @@ -5569,7 +5577,6 @@ F: drivers/soc/fsl/dpio DPAA2 ETHERNET DRIVER M: Ioana Ciornei <ioana.ciornei@nxp.com> -M: Ioana Radulescu <ruxandra.radulescu@nxp.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/device_drivers/ethernet/freescale/dpaa2/ethernet-driver.rst @@ -6938,6 +6945,7 @@ F: net/core/failover.c FANOTIFY M: Jan Kara <jack@suse.cz> R: Amir Goldstein <amir73il@gmail.com> +R: Matthew Bobrowski <repnop@google.com> L: linux-fsdevel@vger.kernel.org S: Maintained F: fs/notify/fanotify/ @@ -12681,9 +12689,9 @@ F: drivers/rtc/rtc-ntxec.c F: include/linux/mfd/ntxec.h NETRONOME ETHERNET DRIVERS -M: Simon Horman <simon.horman@netronome.com> +M: Simon Horman <simon.horman@corigine.com> R: Jakub Kicinski <kuba@kernel.org> -L: oss-drivers@netronome.com +L: oss-drivers@corigine.com S: Maintained F: drivers/net/ethernet/netronome/ @@ -12710,7 +12718,6 @@ M: "David S. Miller" <davem@davemloft.net> M: Jakub Kicinski <kuba@kernel.org> L: netdev@vger.kernel.org S: Maintained -W: http://www.linuxfoundation.org/en/Net Q: https://patchwork.kernel.org/project/netdevbpf/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git @@ -12755,7 +12762,6 @@ M: "David S. Miller" <davem@davemloft.net> M: Jakub Kicinski <kuba@kernel.org> L: netdev@vger.kernel.org S: Maintained -W: http://www.linuxfoundation.org/en/Net Q: https://patchwork.kernel.org/project/netdevbpf/list/ B: mailto:netdev@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git @@ -12897,8 +12903,10 @@ F: include/uapi/linux/nexthop.h F: net/ipv4/nexthop.c NFC SUBSYSTEM +M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +L: linux-nfc@lists.01.org (moderated for non-subscribers) L: netdev@vger.kernel.org -S: Orphan +S: Maintained F: Documentation/devicetree/bindings/net/nfc/ F: drivers/nfc/ F: include/linux/platform_data/nfcmrvl.h @@ -13206,7 +13214,6 @@ F: Documentation/devicetree/bindings/sound/tfa9879.txt F: sound/soc/codecs/tfa9879* NXP-NCI NFC DRIVER -M: Clément Perrochaud <clement.perrochaud@effinnov.com> R: Charles Gorand <charles.gorand@effinnov.com> L: linux-nfc@lists.01.org (moderated for non-subscribers) S: Supported @@ -14318,10 +14325,12 @@ PER-CPU MEMORY ALLOCATOR M: Dennis Zhou <dennis@kernel.org> M: Tejun Heo <tj@kernel.org> M: Christoph Lameter <cl@linux.com> +L: linux-mm@kvack.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percpu.git F: arch/*/include/asm/percpu.h F: include/linux/percpu*.h +F: lib/percpu*.c F: mm/percpu*.c PER-TASK DELAY ACCOUNTING @@ -15945,6 +15954,7 @@ S390 IUCV NETWORK LAYER M: Julian Wiedmann <jwi@linux.ibm.com> M: Karsten Graul <kgraul@linux.ibm.com> L: linux-s390@vger.kernel.org +L: netdev@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ F: drivers/s390/net/*iucv* @@ -15955,6 +15965,7 @@ S390 NETWORK DRIVERS M: Julian Wiedmann <jwi@linux.ibm.com> M: Karsten Graul <kgraul@linux.ibm.com> L: linux-s390@vger.kernel.org +L: netdev@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ F: drivers/s390/net/ @@ -17668,7 +17679,6 @@ R: Mika Westerberg <mika.westerberg@linux.intel.com> L: linux-i2c@vger.kernel.org S: Maintained F: drivers/i2c/busses/i2c-designware-* -F: include/linux/platform_data/i2c-designware.h SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER M: Jaehoon Chung <jh80.chung@samsung.com> @@ -20004,6 +20014,7 @@ F: arch/x86/xen/*swiotlb* F: drivers/xen/*swiotlb* XFS FILESYSTEM +C: irc://irc.oftc.net/xfs M: Darrick J. Wong <djwong@kernel.org> M: linux-xfs@vger.kernel.org L: linux-xfs@vger.kernel.org @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 13 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Frozen Wasteland # *DOCUMENTATION* @@ -928,6 +928,11 @@ CC_FLAGS_LTO += -fvisibility=hidden # Limit inlining across translation units to reduce binary size KBUILD_LDFLAGS += -mllvm -import-instr-limit=5 + +# Check for frame size exceeding threshold during prolog/epilog insertion. +ifneq ($(CONFIG_FRAME_WARN),0) +KBUILD_LDFLAGS += -plugin-opt=-warn-stack-size=$(CONFIG_FRAME_WARN) +endif endif ifdef CONFIG_LTO diff --git a/arch/arm64/Kbuild b/arch/arm64/Kbuild index d6465823b281..7b393cfec071 100644 --- a/arch/arm64/Kbuild +++ b/arch/arm64/Kbuild @@ -1,6 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-y += kernel/ mm/ -obj-$(CONFIG_NET) += net/ +obj-y += kernel/ mm/ net/ obj-$(CONFIG_KVM) += kvm/ obj-$(CONFIG_XEN) += xen/ obj-$(CONFIG_CRYPTO) += crypto/ diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 2175ec0004ed..451e11e5fd23 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -74,7 +74,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long idx, * This insanity brought to you by speculative system register reads, * out-of-order memory accesses, sequence locks and Thomas Gleixner. * - * http://lists.infradead.org/pipermail/linux-arm-kernel/2019-February/631195.html + * https://lore.kernel.org/r/alpine.DEB.2.21.1902081950260.1662@nanos.tec.linutronix.de/ */ #define arch_counter_enforce_ordering(val) do { \ u64 tmp, _val = (val); \ diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index cf8df032b9c3..5e9b33cbac51 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -63,6 +63,7 @@ #define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector 18 #define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize 19 #define __KVM_HOST_SMCCC_FUNC___pkvm_mark_hyp 20 +#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc 21 #ifndef __ASSEMBLY__ @@ -201,6 +202,8 @@ extern void __kvm_timer_set_cntvoff(u64 cntvoff); extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); +extern void __kvm_adjust_pc(struct kvm_vcpu *vcpu); + extern u64 __vgic_v3_get_gic_config(void); extern u64 __vgic_v3_read_vmcr(void); extern void __vgic_v3_write_vmcr(u32 vmcr); diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index f612c090f2e4..01b9857757f2 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -463,4 +463,9 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) vcpu->arch.flags |= KVM_ARM64_INCREMENT_PC; } +static inline bool vcpu_has_feature(struct kvm_vcpu *vcpu, int feature) +{ + return test_bit(feature, vcpu->arch.features); +} + #endif /* __ARM64_KVM_EMULATE_H__ */ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 1cb39c0803a4..e720148232a0 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -720,11 +720,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) return ret; } - if (run->immediate_exit) - return -EINTR; - vcpu_load(vcpu); + if (run->immediate_exit) { + ret = -EINTR; + goto out; + } + kvm_sigset_activate(vcpu); ret = 1; @@ -897,6 +899,18 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_sigset_deactivate(vcpu); +out: + /* + * In the unlikely event that we are returning to userspace + * with pending exceptions or PC adjustment, commit these + * adjustments in order to give userspace a consistent view of + * the vcpu state. Note that this relies on __kvm_adjust_pc() + * being preempt-safe on VHE. + */ + if (unlikely(vcpu->arch.flags & (KVM_ARM64_PENDING_EXCEPTION | + KVM_ARM64_INCREMENT_PC))) + kvm_call_hyp(__kvm_adjust_pc, vcpu); + vcpu_put(vcpu); return ret; } diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c index 73629094f903..11541b94b328 100644 --- a/arch/arm64/kvm/hyp/exception.c +++ b/arch/arm64/kvm/hyp/exception.c @@ -296,7 +296,7 @@ static void enter_exception32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) *vcpu_pc(vcpu) = vect_offset; } -void kvm_inject_exception(struct kvm_vcpu *vcpu) +static void kvm_inject_exception(struct kvm_vcpu *vcpu) { if (vcpu_el1_is_32bit(vcpu)) { switch (vcpu->arch.flags & KVM_ARM64_EXCEPT_MASK) { @@ -329,3 +329,19 @@ void kvm_inject_exception(struct kvm_vcpu *vcpu) } } } + +/* + * Adjust the guest PC (and potentially exception state) depending on + * flags provided by the emulation code. + */ +void __kvm_adjust_pc(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.flags & KVM_ARM64_PENDING_EXCEPTION) { + kvm_inject_exception(vcpu); + vcpu->arch.flags &= ~(KVM_ARM64_PENDING_EXCEPTION | + KVM_ARM64_EXCEPT_MASK); + } else if (vcpu->arch.flags & KVM_ARM64_INCREMENT_PC) { + kvm_skip_instr(vcpu); + vcpu->arch.flags &= ~KVM_ARM64_INCREMENT_PC; + } +} diff --git a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h index 61716359035d..4fdfeabefeb4 100644 --- a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h +++ b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h @@ -13,8 +13,6 @@ #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> -void kvm_inject_exception(struct kvm_vcpu *vcpu); - static inline void kvm_skip_instr(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) { @@ -44,22 +42,6 @@ static inline void __kvm_skip_instr(struct kvm_vcpu *vcpu) } /* - * Adjust the guest PC on entry, depending on flags provided by EL1 - * for the purpose of emulation (MMIO, sysreg) or exception injection. - */ -static inline void __adjust_pc(struct kvm_vcpu *vcpu) -{ - if (vcpu->arch.flags & KVM_ARM64_PENDING_EXCEPTION) { - kvm_inject_exception(vcpu); - vcpu->arch.flags &= ~(KVM_ARM64_PENDING_EXCEPTION | - KVM_ARM64_EXCEPT_MASK); - } else if (vcpu->arch.flags & KVM_ARM64_INCREMENT_PC) { - kvm_skip_instr(vcpu); - vcpu->arch.flags &= ~KVM_ARM64_INCREMENT_PC; - } -} - -/* * Skip an instruction while host sysregs are live. * Assumes host is always 64-bit. */ diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index f36420a80474..1632f001f4ed 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -28,6 +28,13 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt) cpu_reg(host_ctxt, 1) = __kvm_vcpu_run(kern_hyp_va(vcpu)); } +static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1); + + __kvm_adjust_pc(kern_hyp_va(vcpu)); +} + static void handle___kvm_flush_vm_context(struct kvm_cpu_context *host_ctxt) { __kvm_flush_vm_context(); @@ -170,6 +177,7 @@ typedef void (*hcall_t)(struct kvm_cpu_context *); static const hcall_t host_hcall[] = { HANDLE_FUNC(__kvm_vcpu_run), + HANDLE_FUNC(__kvm_adjust_pc), HANDLE_FUNC(__kvm_flush_vm_context), HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa), HANDLE_FUNC(__kvm_tlb_flush_vmid), diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index e342f7f4f4fb..4b60c0056c04 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -23,8 +23,8 @@ extern unsigned long hyp_nr_cpus; struct host_kvm host_kvm; -struct hyp_pool host_s2_mem; -struct hyp_pool host_s2_dev; +static struct hyp_pool host_s2_mem; +static struct hyp_pool host_s2_dev; /* * Copies of the host's CPU features registers holding sanitized values. diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index 7488f53b0aa2..a3d3a275344e 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -17,7 +17,6 @@ #include <nvhe/trap_handler.h> struct hyp_pool hpool; -struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops; unsigned long hyp_nr_cpus; #define hyp_percpu_size ((unsigned long)__per_cpu_end - \ @@ -27,6 +26,7 @@ static void *vmemmap_base; static void *hyp_pgt_base; static void *host_s2_mem_pgt_base; static void *host_s2_dev_pgt_base; +static struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops; static int divide_memory_pool(void *virt, unsigned long size) { diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index e9f6ea704d07..f7af9688c1f7 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -4,7 +4,6 @@ * Author: Marc Zyngier <marc.zyngier@arm.com> */ -#include <hyp/adjust_pc.h> #include <hyp/switch.h> #include <hyp/sysreg-sr.h> @@ -201,7 +200,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) */ __debug_save_host_buffers_nvhe(vcpu); - __adjust_pc(vcpu); + __kvm_adjust_pc(vcpu); /* * We must restore the 32-bit state before the sysregs, thanks diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 7b8f7db5c1ed..b3229924d243 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -4,7 +4,6 @@ * Author: Marc Zyngier <marc.zyngier@arm.com> */ -#include <hyp/adjust_pc.h> #include <hyp/switch.h> #include <linux/arm-smccc.h> @@ -132,7 +131,7 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) __load_guest_stage2(vcpu->arch.hw_mmu); __activate_traps(vcpu); - __adjust_pc(vcpu); + __kvm_adjust_pc(vcpu); sysreg_restore_guest_state_vhe(guest_ctxt); __debug_switch_to_guest(vcpu); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index c5d1f3c87dbd..c10207fed2f3 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1156,13 +1156,13 @@ out_unlock: bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { if (!kvm->arch.mmu.pgt) - return 0; + return false; __unmap_stage2_range(&kvm->arch.mmu, range->start << PAGE_SHIFT, (range->end - range->start) << PAGE_SHIFT, range->may_block); - return 0; + return false; } bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) @@ -1170,7 +1170,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) kvm_pfn_t pfn = pte_pfn(range->pte); if (!kvm->arch.mmu.pgt) - return 0; + return false; WARN_ON(range->end - range->start != 1); @@ -1190,7 +1190,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) PAGE_SIZE, __pfn_to_phys(pfn), KVM_PGTABLE_PROT_R, NULL); - return 0; + return false; } bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) @@ -1200,7 +1200,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) pte_t pte; if (!kvm->arch.mmu.pgt) - return 0; + return false; WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); @@ -1213,7 +1213,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { if (!kvm->arch.mmu.pgt) - return 0; + return false; return kvm_pgtable_stage2_is_young(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT); diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 956cdc240148..d37ebee085cf 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -166,6 +166,25 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) return 0; } +static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu *tmp; + bool is32bit; + int i; + + is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT); + if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit) + return false; + + /* Check that the vcpus are either all 32bit or all 64bit */ + kvm_for_each_vcpu(i, tmp, vcpu->kvm) { + if (vcpu_has_feature(tmp, KVM_ARM_VCPU_EL1_32BIT) != is32bit) + return false; + } + + return true; +} + /** * kvm_reset_vcpu - sets core registers and sys_regs to reset value * @vcpu: The VCPU pointer @@ -217,13 +236,14 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) } } + if (!vcpu_allowed_register_width(vcpu)) { + ret = -EINVAL; + goto out; + } + switch (vcpu->arch.target) { default: if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) { - if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) { - ret = -EINVAL; - goto out; - } pstate = VCPU_RESET_PSTATE_SVC; } else { pstate = VCPU_RESET_PSTATE_EL1; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 76ea2800c33e..1a7968ad078c 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -399,14 +399,14 @@ static bool trap_bvr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); return true; } @@ -414,7 +414,7 @@ static bool trap_bvr(struct kvm_vcpu *vcpu, static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -424,7 +424,7 @@ static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -434,21 +434,21 @@ static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm] = rd->val; } static bool trap_bcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); return true; } @@ -456,7 +456,7 @@ static bool trap_bcr(struct kvm_vcpu *vcpu, static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -467,7 +467,7 @@ static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -477,22 +477,22 @@ static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm] = rd->val; } static bool trap_wvr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, - vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]); + trace_trap_reg(__func__, rd->CRm, p->is_write, + vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]); return true; } @@ -500,7 +500,7 @@ static bool trap_wvr(struct kvm_vcpu *vcpu, static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -510,7 +510,7 @@ static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -520,21 +520,21 @@ static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm] = rd->val; } static bool trap_wcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); return true; } @@ -542,7 +542,7 @@ static bool trap_wcr(struct kvm_vcpu *vcpu, static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -552,7 +552,7 @@ static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -562,7 +562,7 @@ static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm] = rd->val; } static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 6dd9369e3ea0..89b66ef43a0f 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -515,7 +515,8 @@ static void __init map_mem(pgd_t *pgdp) */ BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end)); - if (rodata_full || crash_mem_map || debug_pagealloc_enabled()) + if (rodata_full || crash_mem_map || debug_pagealloc_enabled() || + IS_ENABLED(CONFIG_KFENCE)) flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; /* diff --git a/arch/mips/alchemy/board-xxs1500.c b/arch/mips/alchemy/board-xxs1500.c index b184baa4e56a..f175bce2987f 100644 --- a/arch/mips/alchemy/board-xxs1500.c +++ b/arch/mips/alchemy/board-xxs1500.c @@ -18,6 +18,7 @@ #include <asm/reboot.h> #include <asm/setup.h> #include <asm/mach-au1x00/au1000.h> +#include <asm/mach-au1x00/gpio-au1000.h> #include <prom.h> const char *get_system_type(void) diff --git a/arch/mips/include/asm/mips-boards/launch.h b/arch/mips/include/asm/mips-boards/launch.h index f93aa5ee2e2e..3481ed4c117b 100644 --- a/arch/mips/include/asm/mips-boards/launch.h +++ b/arch/mips/include/asm/mips-boards/launch.h @@ -3,6 +3,9 @@ * */ +#ifndef _ASM_MIPS_BOARDS_LAUNCH_H +#define _ASM_MIPS_BOARDS_LAUNCH_H + #ifndef _ASSEMBLER_ struct cpulaunch { @@ -34,3 +37,5 @@ struct cpulaunch { /* Polling period in count cycles for secondary CPU's */ #define LAUNCHPERIOD 10000 + +#endif /* _ASM_MIPS_BOARDS_LAUNCH_H */ diff --git a/arch/mips/lib/mips-atomic.c b/arch/mips/lib/mips-atomic.c index de03838b343b..a9b72eacfc0b 100644 --- a/arch/mips/lib/mips-atomic.c +++ b/arch/mips/lib/mips-atomic.c @@ -37,7 +37,7 @@ */ notrace void arch_local_irq_disable(void) { - preempt_disable(); + preempt_disable_notrace(); __asm__ __volatile__( " .set push \n" @@ -53,7 +53,7 @@ notrace void arch_local_irq_disable(void) : /* no inputs */ : "memory"); - preempt_enable(); + preempt_enable_notrace(); } EXPORT_SYMBOL(arch_local_irq_disable); @@ -61,7 +61,7 @@ notrace unsigned long arch_local_irq_save(void) { unsigned long flags; - preempt_disable(); + preempt_disable_notrace(); __asm__ __volatile__( " .set push \n" @@ -78,7 +78,7 @@ notrace unsigned long arch_local_irq_save(void) : /* no inputs */ : "memory"); - preempt_enable(); + preempt_enable_notrace(); return flags; } @@ -88,7 +88,7 @@ notrace void arch_local_irq_restore(unsigned long flags) { unsigned long __tmp1; - preempt_disable(); + preempt_disable_notrace(); __asm__ __volatile__( " .set push \n" @@ -106,7 +106,7 @@ notrace void arch_local_irq_restore(unsigned long flags) : "0" (flags) : "memory"); - preempt_enable(); + preempt_enable_notrace(); } EXPORT_SYMBOL(arch_local_irq_restore); diff --git a/arch/mips/ralink/of.c b/arch/mips/ralink/of.c index 0c5de07da097..0135376c5de5 100644 --- a/arch/mips/ralink/of.c +++ b/arch/mips/ralink/of.c @@ -8,6 +8,7 @@ #include <linux/io.h> #include <linux/clk.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/sizes.h> #include <linux/of_fdt.h> @@ -25,6 +26,7 @@ __iomem void *rt_sysc_membase; __iomem void *rt_memc_membase; +EXPORT_SYMBOL_GPL(rt_sysc_membase); __iomem void *plat_of_remap_node(const char *node) { diff --git a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi index c2717f31925a..ccda0a91abf0 100644 --- a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi @@ -122,7 +122,15 @@ }; /include/ "pq3-i2c-0.dtsi" + i2c@3000 { + fsl,i2c-erratum-a004447; + }; + /include/ "pq3-i2c-1.dtsi" + i2c@3100 { + fsl,i2c-erratum-a004447; + }; + /include/ "pq3-duart-0.dtsi" /include/ "pq3-espi-0.dtsi" spi0: spi@7000 { diff --git a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi index 872e4485dc3f..ddc018d42252 100644 --- a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi @@ -371,7 +371,23 @@ }; /include/ "qoriq-i2c-0.dtsi" + i2c@118000 { + fsl,i2c-erratum-a004447; + }; + + i2c@118100 { + fsl,i2c-erratum-a004447; + }; + /include/ "qoriq-i2c-1.dtsi" + i2c@119000 { + fsl,i2c-erratum-a004447; + }; + + i2c@119100 { + fsl,i2c-erratum-a004447; + }; + /include/ "qoriq-duart-0.dtsi" /include/ "qoriq-duart-1.dtsi" /include/ "qoriq-gpio-0.dtsi" diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 1e83359f286b..7f2e90db2050 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -51,6 +51,7 @@ /* PPC-specific vcpu->requests bit members */ #define KVM_REQ_WATCHDOG KVM_ARCH_REQ(0) #define KVM_REQ_EPR_EXIT KVM_ARCH_REQ(1) +#define KVM_REQ_PENDING_TIMER KVM_ARCH_REQ(2) #include <linux/mmu_notifier.h> diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 28a80d240b76..7360350e66ff 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3936,7 +3936,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) break; } cur = ktime_get(); - } while (single_task_running() && ktime_before(cur, stop)); + } while (kvm_vcpu_can_poll(cur, stop)); spin_lock(&vc->lock); vc->vcore_state = VCORE_INACTIVE; diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index a8ad8eb76120..c5914e70a0fd 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -34,6 +34,7 @@ config RISCV select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT select ARCH_SUPPORTS_HUGETLBFS if MMU + select ARCH_USE_MEMTEST select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_HUGE_PMD_SHARE if 64BIT diff --git a/arch/riscv/include/asm/kexec.h b/arch/riscv/include/asm/kexec.h index 1e954101906a..e4e291d40759 100644 --- a/arch/riscv/include/asm/kexec.h +++ b/arch/riscv/include/asm/kexec.h @@ -42,8 +42,8 @@ struct kimage_arch { unsigned long fdt_addr; }; -const extern unsigned char riscv_kexec_relocate[]; -const extern unsigned int riscv_kexec_relocate_size; +extern const unsigned char riscv_kexec_relocate[]; +extern const unsigned int riscv_kexec_relocate_size; typedef void (*riscv_kexec_method)(unsigned long first_ind_entry, unsigned long jump_addr, diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c index cc048143fba5..9e99e1db156b 100644 --- a/arch/riscv/kernel/machine_kexec.c +++ b/arch/riscv/kernel/machine_kexec.c @@ -14,8 +14,9 @@ #include <asm/set_memory.h> /* For set_memory_x() */ #include <linux/compiler.h> /* For unreachable() */ #include <linux/cpu.h> /* For cpu_down() */ +#include <linux/reboot.h> -/** +/* * kexec_image_info - Print received image details */ static void @@ -39,7 +40,7 @@ kexec_image_info(const struct kimage *image) } } -/** +/* * machine_kexec_prepare - Initialize kexec * * This function is called from do_kexec_load, when the user has @@ -100,7 +101,7 @@ machine_kexec_prepare(struct kimage *image) } -/** +/* * machine_kexec_cleanup - Cleanup any leftovers from * machine_kexec_prepare * @@ -135,7 +136,7 @@ void machine_shutdown(void) #endif } -/** +/* * machine_crash_shutdown - Prepare to kexec after a kernel crash * * This function is called by crash_kexec just before machine_kexec @@ -151,7 +152,7 @@ machine_crash_shutdown(struct pt_regs *regs) pr_info("Starting crashdump kernel...\n"); } -/** +/* * machine_kexec - Jump to the loaded kimage * * This function is called by kernel_kexec which is called by the diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index 10b965c34536..15cc65ac7ca6 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -84,6 +84,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) return 0; } +#ifdef CONFIG_MMU void *alloc_insn_page(void) { return __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, VMALLOC_END, @@ -91,6 +92,7 @@ void *alloc_insn_page(void) VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, __builtin_return_address(0)); } +#endif /* install breakpoint in text */ void __kprobes arch_arm_kprobe(struct kprobe *p) diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 2b3e0cb90d78..bde85fc53357 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -27,10 +27,10 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, fp = frame_pointer(regs); sp = user_stack_pointer(regs); pc = instruction_pointer(regs); - } else if (task == NULL || task == current) { - fp = (unsigned long)__builtin_frame_address(0); - sp = sp_in_global; - pc = (unsigned long)walk_stackframe; + } else if (task == current) { + fp = (unsigned long)__builtin_frame_address(1); + sp = (unsigned long)__builtin_frame_address(0); + pc = (unsigned long)__builtin_return_address(0); } else { /* task blocked in __switch_to */ fp = task->thread.s[0]; @@ -106,15 +106,15 @@ static bool print_trace_address(void *arg, unsigned long pc) return true; } -void dump_backtrace(struct pt_regs *regs, struct task_struct *task, +noinline void dump_backtrace(struct pt_regs *regs, struct task_struct *task, const char *loglvl) { - pr_cont("%sCall Trace:\n", loglvl); walk_stackframe(task, regs, print_trace_address, (void *)loglvl); } void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl) { + pr_cont("%sCall Trace:\n", loglvl); dump_backtrace(NULL, task, loglvl); } @@ -139,7 +139,7 @@ unsigned long get_wchan(struct task_struct *task) #ifdef CONFIG_STACKTRACE -void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, +noinline void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task, struct pt_regs *regs) { walk_stackframe(task, regs, consume_entry, cookie); diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 323641097f63..e7bef91cee04 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -99,6 +99,7 @@ KVM_X86_OP_NULL(post_block) KVM_X86_OP_NULL(vcpu_blocking) KVM_X86_OP_NULL(vcpu_unblocking) KVM_X86_OP_NULL(update_pi_irte) +KVM_X86_OP_NULL(start_assignment) KVM_X86_OP_NULL(apicv_post_state_restore) KVM_X86_OP_NULL(dy_apicv_has_pending_interrupt) KVM_X86_OP_NULL(set_hv_timer) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 55efbacfc244..9c7ced0e3171 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1352,6 +1352,7 @@ struct kvm_x86_ops { int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); + void (*start_assignment)(struct kvm *kvm); void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu); bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 8a0ccdb56076..5e5de05a8fbf 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -5111,7 +5111,7 @@ done: return rc; } -int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) +int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int emulation_type) { int rc = X86EMUL_CONTINUE; int mode = ctxt->mode; @@ -5322,7 +5322,8 @@ done_prefixes: ctxt->execute = opcode.u.execute; - if (unlikely(ctxt->ud) && likely(!(ctxt->d & EmulateOnUD))) + if (unlikely(emulation_type & EMULTYPE_TRAP_UD) && + likely(!(ctxt->d & EmulateOnUD))) return EMULATION_FAILED; if (unlikely(ctxt->d & diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index f98370a39936..f00830e5202f 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1172,6 +1172,7 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm) { struct kvm_hv *hv = to_kvm_hv(kvm); u64 gfn; + int idx; if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN || hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET || @@ -1190,9 +1191,16 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm) gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; hv->tsc_ref.tsc_sequence = 0; + + /* + * Take the srcu lock as memslots will be accessed to check the gfn + * cache generation against the memslots generation. + */ + idx = srcu_read_lock(&kvm->srcu); if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN; + srcu_read_unlock(&kvm->srcu, idx); out_unlock: mutex_unlock(&hv->hv_lock); diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index f016838faedd..3e870bf9ca4d 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -314,7 +314,6 @@ struct x86_emulate_ctxt { int interruptibility; bool perm_ok; /* do not check permissions if true */ - bool ud; /* inject an #UD if host doesn't support insn */ bool tf; /* TF value before instruction (after for syscall/sysret) */ bool have_exception; @@ -491,7 +490,7 @@ enum x86_intercept { #define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64 #endif -int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len); +int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int emulation_type); bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt); #define EMULATION_FAILED -1 #define EMULATION_OK 0 diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index c0ebef560bd1..8120e8614b92 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1598,11 +1598,19 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu) guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); apic->lapic_timer.advance_expire_delta = guest_tsc - tsc_deadline; + if (lapic_timer_advance_dynamic) { + adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta); + /* + * If the timer fired early, reread the TSC to account for the + * overhead of the above adjustment to avoid waiting longer + * than is necessary. + */ + if (guest_tsc < tsc_deadline) + guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); + } + if (guest_tsc < tsc_deadline) __wait_lapic_expire(vcpu, tsc_deadline - guest_tsc); - - if (lapic_timer_advance_dynamic) - adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta); } void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu) @@ -1661,7 +1669,7 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn) } atomic_inc(&apic->lapic_timer.pending); - kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu); + kvm_make_request(KVM_REQ_UNBLOCK, vcpu); if (from_timer_fn) kvm_vcpu_kick(vcpu); } diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 95eeb5ac6a8a..237317b1eddd 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1192,9 +1192,9 @@ bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) } /* - * Remove write access from all the SPTEs mapping GFNs [start, end). If - * skip_4k is set, SPTEs that map 4k pages, will not be write-protected. - * Returns true if an SPTE has been changed and the TLBs need to be flushed. + * Remove write access from all SPTEs at or above min_level that map GFNs + * [start, end). Returns true if an SPTE has been changed and the TLBs need to + * be flushed. */ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end, int min_level) diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 712b4e0de481..0e62e6a2438c 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -28,10 +28,8 @@ #include "svm.h" /* enable / disable AVIC */ -int avic; -#ifdef CONFIG_X86_LOCAL_APIC -module_param(avic, int, S_IRUGO); -#endif +bool avic; +module_param(avic, bool, S_IRUGO); #define SVM_AVIC_DOORBELL 0xc001011b diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 05eca131eaf2..e088086f3de6 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1010,9 +1010,7 @@ static __init int svm_hardware_setup(void) } if (avic) { - if (!npt_enabled || - !boot_cpu_has(X86_FEATURE_AVIC) || - !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) { + if (!npt_enabled || !boot_cpu_has(X86_FEATURE_AVIC)) { avic = false; } else { pr_info("AVIC enabled\n"); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 2c9ece618b29..2908c6ab5bb4 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -480,7 +480,7 @@ extern struct kvm_x86_nested_ops svm_nested_ops; #define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL -extern int avic; +extern bool avic; static inline void avic_update_vapic_bar(struct vcpu_svm *svm, u64 data) { diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 8dee8a5fbc17..aa0e7872fcc9 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -90,8 +90,7 @@ static inline bool cpu_has_vmx_preemption_timer(void) static inline bool cpu_has_vmx_posted_intr(void) { - return IS_ENABLED(CONFIG_X86_LOCAL_APIC) && - vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR; + return vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR; } static inline bool cpu_has_load_ia32_efer(void) diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 459748680daf..5f81ef092bd4 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -238,6 +238,20 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu) /* + * Bail out of the block loop if the VM has an assigned + * device, but the blocking vCPU didn't reconfigure the + * PI.NV to the wakeup vector, i.e. the assigned device + * came along after the initial check in pi_pre_block(). + */ +void vmx_pi_start_assignment(struct kvm *kvm) +{ + if (!irq_remapping_cap(IRQ_POSTING_CAP)) + return; + + kvm_make_all_cpus_request(kvm, KVM_REQ_UNBLOCK); +} + +/* * pi_update_irte - set IRTE for Posted-Interrupts * * @kvm: kvm diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 0bdc41391c5b..7f7b2326caf5 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -95,5 +95,6 @@ void __init pi_init_cpu(int cpu); bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu); int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); +void vmx_pi_start_assignment(struct kvm *kvm); #endif /* __KVM_X86_VMX_POSTED_INTR_H */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 4bceb5ca3a89..50b42d7a8a11 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4843,7 +4843,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_run *kvm_run = vcpu->run; u32 intr_info, ex_no, error_code; - unsigned long cr2, rip, dr6; + unsigned long cr2, dr6; u32 vect_info; vect_info = vmx->idt_vectoring_info; @@ -4933,8 +4933,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) vmx->vcpu.arch.event_exit_inst_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); kvm_run->exit_reason = KVM_EXIT_DEBUG; - rip = kvm_rip_read(vcpu); - kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip; + kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu); kvm_run->debug.arch.exception = ex_no; break; case AC_VECTOR: @@ -7721,6 +7720,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .nested_ops = &vmx_nested_ops, .update_pi_irte = pi_update_irte, + .start_assignment = vmx_pi_start_assignment, #ifdef CONFIG_X86_64 .set_hv_timer = vmx_set_hv_timer, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bbc4e04e67ad..b594275d49b5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3105,6 +3105,8 @@ static void record_steal_time(struct kvm_vcpu *vcpu) st->preempted & KVM_VCPU_FLUSH_TLB); if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb_guest(vcpu); + } else { + st->preempted = 0; } vcpu->arch.st.preempted = 0; @@ -7226,6 +7228,11 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK); + ctxt->interruptibility = 0; + ctxt->have_exception = false; + ctxt->exception.vector = -1; + ctxt->perm_ok = false; + init_decode_cache(ctxt); vcpu->arch.emulate_regs_need_sync_from_vcpu = false; } @@ -7561,14 +7568,7 @@ int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, kvm_vcpu_check_breakpoint(vcpu, &r)) return r; - ctxt->interruptibility = 0; - ctxt->have_exception = false; - ctxt->exception.vector = -1; - ctxt->perm_ok = false; - - ctxt->ud = emulation_type & EMULTYPE_TRAP_UD; - - r = x86_decode_insn(ctxt, insn, insn_len); + r = x86_decode_insn(ctxt, insn, insn_len, emulation_type); trace_kvm_emulate_insn_start(vcpu); ++vcpu->stat.insn_emulation; @@ -8360,6 +8360,9 @@ static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) vcpu->stat.directed_yield_attempted++; + if (single_task_running()) + goto no_yield; + rcu_read_lock(); map = rcu_dereference(vcpu->kvm->arch.apic_map); @@ -9496,7 +9499,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (r <= 0) break; - kvm_clear_request(KVM_REQ_PENDING_TIMER, vcpu); + kvm_clear_request(KVM_REQ_UNBLOCK, vcpu); if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); @@ -10115,8 +10118,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, kvm_update_dr7(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) + - get_segment_base(vcpu, VCPU_SREG_CS); + vcpu->arch.singlestep_rip = kvm_get_linear_rip(vcpu); /* * Trigger an rflags update that will inject or remove the trace @@ -11499,7 +11501,8 @@ bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu) void kvm_arch_start_assignment(struct kvm *kvm) { - atomic_inc(&kvm->arch.assigned_device_count); + if (atomic_inc_return(&kvm->arch.assigned_device_count) == 1) + static_call_cond(kvm_x86_start_assignment)(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_start_assignment); diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c index 0ec5b3f69112..6e02448d15d9 100644 --- a/drivers/acpi/acpi_apd.c +++ b/drivers/acpi/acpi_apd.c @@ -226,6 +226,7 @@ static const struct acpi_device_id acpi_apd_device_ids[] = { { "AMDI0010", APD_ADDR(wt_i2c_desc) }, { "AMD0020", APD_ADDR(cz_uart_desc) }, { "AMDI0020", APD_ADDR(cz_uart_desc) }, + { "AMDI0022", APD_ADDR(cz_uart_desc) }, { "AMD0030", }, { "AMD0040", APD_ADDR(fch_misc_desc)}, { "HYGO0010", APD_ADDR(wt_i2c_desc) }, diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index f973bbe90e5e..e21611c9a170 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -134,7 +134,7 @@ int acpi_power_init(void); void acpi_power_resources_list_free(struct list_head *list); int acpi_extract_power_resources(union acpi_object *package, unsigned int start, struct list_head *list); -int acpi_add_power_resource(acpi_handle handle); +struct acpi_device *acpi_add_power_resource(acpi_handle handle); void acpi_power_add_remove_device(struct acpi_device *adev, bool add); int acpi_power_wakeup_list_init(struct list_head *list, int *system_level); int acpi_device_sleep_wake(struct acpi_device *dev, @@ -142,7 +142,7 @@ int acpi_device_sleep_wake(struct acpi_device *dev, int acpi_power_get_inferred_state(struct acpi_device *device, int *state); int acpi_power_on_resources(struct acpi_device *device, int state); int acpi_power_transition(struct acpi_device *device, int state); -void acpi_turn_off_unused_power_resources(void); +void acpi_turn_off_unused_power_resources(bool init); /* -------------------------------------------------------------------------- Device Power Management diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index 56102eaaa2da..97c9a94a1a30 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -52,6 +52,7 @@ struct acpi_power_resource { u32 system_level; u32 order; unsigned int ref_count; + unsigned int users; bool wakeup_enabled; struct mutex resource_lock; struct list_head dependents; @@ -147,6 +148,7 @@ int acpi_extract_power_resources(union acpi_object *package, unsigned int start, for (i = start; i < package->package.count; i++) { union acpi_object *element = &package->package.elements[i]; + struct acpi_device *rdev; acpi_handle rhandle; if (element->type != ACPI_TYPE_LOCAL_REFERENCE) { @@ -163,13 +165,16 @@ int acpi_extract_power_resources(union acpi_object *package, unsigned int start, if (acpi_power_resource_is_dup(package, start, i)) continue; - err = acpi_add_power_resource(rhandle); - if (err) + rdev = acpi_add_power_resource(rhandle); + if (!rdev) { + err = -ENODEV; break; - + } err = acpi_power_resources_list_add(rhandle, list); if (err) break; + + to_power_resource(rdev)->users++; } if (err) acpi_power_resources_list_free(list); @@ -907,7 +912,7 @@ static void acpi_power_add_resource_to_list(struct acpi_power_resource *resource mutex_unlock(&power_resource_list_lock); } -int acpi_add_power_resource(acpi_handle handle) +struct acpi_device *acpi_add_power_resource(acpi_handle handle) { struct acpi_power_resource *resource; struct acpi_device *device = NULL; @@ -918,11 +923,11 @@ int acpi_add_power_resource(acpi_handle handle) acpi_bus_get_device(handle, &device); if (device) - return 0; + return device; resource = kzalloc(sizeof(*resource), GFP_KERNEL); if (!resource) - return -ENOMEM; + return NULL; device = &resource->device; acpi_init_device_object(device, handle, ACPI_BUS_TYPE_POWER); @@ -959,11 +964,11 @@ int acpi_add_power_resource(acpi_handle handle) acpi_power_add_resource_to_list(resource); acpi_device_add_finalize(device); - return 0; + return device; err: acpi_release_power_resource(&device->dev); - return result; + return NULL; } #ifdef CONFIG_ACPI_SLEEP @@ -997,7 +1002,38 @@ void acpi_resume_power_resources(void) } #endif -void acpi_turn_off_unused_power_resources(void) +static void acpi_power_turn_off_if_unused(struct acpi_power_resource *resource, + bool init) +{ + if (resource->ref_count > 0) + return; + + if (init) { + if (resource->users > 0) + return; + } else { + int result, state; + + result = acpi_power_get_state(resource->device.handle, &state); + if (result || state == ACPI_POWER_RESOURCE_STATE_OFF) + return; + } + + dev_info(&resource->device.dev, "Turning OFF\n"); + __acpi_power_off(resource); +} + +/** + * acpi_turn_off_unused_power_resources - Turn off power resources not in use. + * @init: Control switch. + * + * If @ainit is set, unconditionally turn off all of the ACPI power resources + * without any users. + * + * Otherwise, turn off all ACPI power resources without active references (that + * is, the ones that should be "off" at the moment) that are "on". + */ +void acpi_turn_off_unused_power_resources(bool init) { struct acpi_power_resource *resource; @@ -1006,10 +1042,7 @@ void acpi_turn_off_unused_power_resources(void) list_for_each_entry_reverse(resource, &acpi_power_resource_list, list_node) { mutex_lock(&resource->resource_lock); - if (!resource->ref_count) { - dev_info(&resource->device.dev, "Turning OFF\n"); - __acpi_power_off(resource); - } + acpi_power_turn_off_if_unused(resource, init); mutex_unlock(&resource->resource_lock); } diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 453eff8ec8c3..e10d38ac7cf2 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2360,7 +2360,7 @@ int __init acpi_scan_init(void) } } - acpi_turn_off_unused_power_resources(); + acpi_turn_off_unused_power_resources(true); acpi_scan_initialized = true; diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 09fd13757b65..df386571da98 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -504,7 +504,7 @@ static void acpi_pm_start(u32 acpi_state) */ static void acpi_pm_end(void) { - acpi_turn_off_unused_power_resources(); + acpi_turn_off_unused_power_resources(false); acpi_scan_lock_release(); /* * This is necessary in case acpi_pm_finish() is not called during a diff --git a/drivers/base/core.c b/drivers/base/core.c index 628e33939aca..54ba506e5a89 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -194,6 +194,17 @@ int device_links_read_lock_held(void) { return srcu_read_lock_held(&device_links_srcu); } + +static void device_link_synchronize_removal(void) +{ + synchronize_srcu(&device_links_srcu); +} + +static void device_link_remove_from_lists(struct device_link *link) +{ + list_del_rcu(&link->s_node); + list_del_rcu(&link->c_node); +} #else /* !CONFIG_SRCU */ static DECLARE_RWSEM(device_links_lock); @@ -224,6 +235,16 @@ int device_links_read_lock_held(void) return lockdep_is_held(&device_links_lock); } #endif + +static inline void device_link_synchronize_removal(void) +{ +} + +static void device_link_remove_from_lists(struct device_link *link) +{ + list_del(&link->s_node); + list_del(&link->c_node); +} #endif /* !CONFIG_SRCU */ static bool device_is_ancestor(struct device *dev, struct device *target) @@ -445,8 +466,13 @@ static struct attribute *devlink_attrs[] = { }; ATTRIBUTE_GROUPS(devlink); -static void device_link_free(struct device_link *link) +static void device_link_release_fn(struct work_struct *work) { + struct device_link *link = container_of(work, struct device_link, rm_work); + + /* Ensure that all references to the link object have been dropped. */ + device_link_synchronize_removal(); + while (refcount_dec_not_one(&link->rpm_active)) pm_runtime_put(link->supplier); @@ -455,24 +481,19 @@ static void device_link_free(struct device_link *link) kfree(link); } -#ifdef CONFIG_SRCU -static void __device_link_free_srcu(struct rcu_head *rhead) -{ - device_link_free(container_of(rhead, struct device_link, rcu_head)); -} - static void devlink_dev_release(struct device *dev) { struct device_link *link = to_devlink(dev); - call_srcu(&device_links_srcu, &link->rcu_head, __device_link_free_srcu); -} -#else -static void devlink_dev_release(struct device *dev) -{ - device_link_free(to_devlink(dev)); + INIT_WORK(&link->rm_work, device_link_release_fn); + /* + * It may take a while to complete this work because of the SRCU + * synchronization in device_link_release_fn() and if the consumer or + * supplier devices get deleted when it runs, so put it into the "long" + * workqueue. + */ + queue_work(system_long_wq, &link->rm_work); } -#endif static struct class devlink_class = { .name = "devlink", @@ -846,7 +867,6 @@ out: } EXPORT_SYMBOL_GPL(device_link_add); -#ifdef CONFIG_SRCU static void __device_link_del(struct kref *kref) { struct device_link *link = container_of(kref, struct device_link, kref); @@ -856,25 +876,9 @@ static void __device_link_del(struct kref *kref) pm_runtime_drop_link(link); - list_del_rcu(&link->s_node); - list_del_rcu(&link->c_node); - device_unregister(&link->link_dev); -} -#else /* !CONFIG_SRCU */ -static void __device_link_del(struct kref *kref) -{ - struct device_link *link = container_of(kref, struct device_link, kref); - - dev_info(link->consumer, "Dropping the link to %s\n", - dev_name(link->supplier)); - - pm_runtime_drop_link(link); - - list_del(&link->s_node); - list_del(&link->c_node); + device_link_remove_from_lists(link); device_unregister(&link->link_dev); } -#endif /* !CONFIG_SRCU */ static void device_link_put_kref(struct device_link *link) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c index fad3b91f74f5..d39cff4a1fe3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c @@ -156,16 +156,16 @@ static uint32_t get_sdma_rlc_reg_offset(struct amdgpu_device *adev, mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL; break; case 1: - sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA1, 0, + sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA0, 0, mmSDMA1_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL; break; case 2: - sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA2, 0, - mmSDMA2_RLC0_RB_CNTL) - mmSDMA2_RLC0_RB_CNTL; + sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA0, 0, + mmSDMA2_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL; break; case 3: - sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA3, 0, - mmSDMA3_RLC0_RB_CNTL) - mmSDMA2_RLC0_RB_CNTL; + sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA0, 0, + mmSDMA3_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL; break; } @@ -450,7 +450,7 @@ static int hqd_sdma_dump_v10_3(struct kgd_dev *kgd, engine_id, queue_id); uint32_t i = 0, reg; #undef HQD_N_REGS -#define HQD_N_REGS (19+6+7+10) +#define HQD_N_REGS (19+6+7+12) *dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL); if (*dump == NULL) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c index de5abceced0d..85967a5570cb 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c @@ -172,6 +172,8 @@ static int jpeg_v2_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + cancel_delayed_work_sync(&adev->vcn.idle_work); + if (adev->jpeg.cur_state != AMD_PG_STATE_GATE && RREG32_SOC15(JPEG, 0, mmUVD_JRBC_STATUS)) jpeg_v2_0_set_powergating_state(adev, AMD_PG_STATE_GATE); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c index 938ef4ce5b76..46096ad7f0d9 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c @@ -187,14 +187,14 @@ static int jpeg_v2_5_hw_init(void *handle) static int jpeg_v2_5_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - struct amdgpu_ring *ring; int i; + cancel_delayed_work_sync(&adev->vcn.idle_work); + for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { if (adev->jpeg.harvest_config & (1 << i)) continue; - ring = &adev->jpeg.inst[i].ring_dec; if (adev->jpeg.cur_state != AMD_PG_STATE_GATE && RREG32_SOC15(JPEG, i, mmUVD_JRBC_STATUS)) jpeg_v2_5_set_powergating_state(adev, AMD_PG_STATE_GATE); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c index 94be35357f7d..bd77794315bc 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c @@ -159,9 +159,9 @@ static int jpeg_v3_0_hw_init(void *handle) static int jpeg_v3_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - struct amdgpu_ring *ring; - ring = &adev->jpeg.inst->ring_dec; + cancel_delayed_work_sync(&adev->vcn.idle_work); + if (adev->jpeg.cur_state != AMD_PG_STATE_GATE && RREG32_SOC15(JPEG, 0, mmUVD_JRBC_STATUS)) jpeg_v3_0_set_powergating_state(adev, AMD_PG_STATE_GATE); diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index 0c1beefa3e49..27b1ced145d2 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -231,9 +231,13 @@ static int vcn_v1_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + cancel_delayed_work_sync(&adev->vcn.idle_work); + if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || - RREG32_SOC15(VCN, 0, mmUVD_STATUS)) + (adev->vcn.cur_state != AMD_PG_STATE_GATE && + RREG32_SOC15(VCN, 0, mmUVD_STATUS))) { vcn_v1_0_set_powergating_state(adev, AMD_PG_STATE_GATE); + } return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index 116b9643d5ba..8af567c546db 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -262,6 +262,8 @@ static int vcn_v2_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + cancel_delayed_work_sync(&adev->vcn.idle_work); + if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || (adev->vcn.cur_state != AMD_PG_STATE_GATE && RREG32_SOC15(VCN, 0, mmUVD_STATUS))) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index 948813d7caa0..888b17d84691 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -321,6 +321,8 @@ static int vcn_v2_5_hw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int i; + cancel_delayed_work_sync(&adev->vcn.idle_work); + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { if (adev->vcn.harvest_config & (1 << i)) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 14470da52113..3b23de996db2 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -372,15 +372,14 @@ done: static int vcn_v3_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - struct amdgpu_ring *ring; int i; + cancel_delayed_work_sync(&adev->vcn.idle_work); + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { if (adev->vcn.harvest_config & (1 << i)) continue; - ring = &adev->vcn.inst[i].ring_dec; - if (!amdgpu_sriov_vf(adev)) { if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || (adev->vcn.cur_state != AMD_PG_STATE_GATE && diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index ac13042672ea..0eaf86b5e698 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -2925,6 +2925,8 @@ static ssize_t navi1x_get_gpu_metrics(struct smu_context *smu, static int navi10_enable_mgpu_fan_boost(struct smu_context *smu) { + struct smu_table_context *table_context = &smu->smu_table; + PPTable_t *smc_pptable = table_context->driver_pptable; struct amdgpu_device *adev = smu->adev; uint32_t param = 0; @@ -2932,6 +2934,13 @@ static int navi10_enable_mgpu_fan_boost(struct smu_context *smu) if (adev->asic_type == CHIP_NAVI12) return 0; + /* + * Skip the MGpuFanBoost setting for those ASICs + * which do not support it + */ + if (!smc_pptable->MGpuFanBoostLimitRpm) + return 0; + /* Workaround for WS SKU */ if (adev->pdev->device == 0x7312 && adev->pdev->revision == 0) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index d2fd44b903ca..b124a5e40dd6 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -3027,6 +3027,16 @@ static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu, static int sienna_cichlid_enable_mgpu_fan_boost(struct smu_context *smu) { + struct smu_table_context *table_context = &smu->smu_table; + PPTable_t *smc_pptable = table_context->driver_pptable; + + /* + * Skip the MGpuFanBoost setting for those ASICs + * which do not support it + */ + if (!smc_pptable->MGpuFanBoostLimitRpm) + return 0; + return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetMGpuFanBoostLimitRpm, 0, diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index 02a003fd48fb..50cae0198a3d 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -128,49 +128,13 @@ intel_dp_set_lttpr_transparent_mode(struct intel_dp *intel_dp, bool enable) return drm_dp_dpcd_write(&intel_dp->aux, DP_PHY_REPEATER_MODE, &val, 1) == 1; } -/** - * intel_dp_init_lttpr_and_dprx_caps - detect LTTPR and DPRX caps, init the LTTPR link training mode - * @intel_dp: Intel DP struct - * - * Read the LTTPR common and DPRX capabilities and switch to non-transparent - * link training mode if any is detected and read the PHY capabilities for all - * detected LTTPRs. In case of an LTTPR detection error or if the number of - * LTTPRs is more than is supported (8), fall back to the no-LTTPR, - * transparent mode link training mode. - * - * Returns: - * >0 if LTTPRs were detected and the non-transparent LT mode was set. The - * DPRX capabilities are read out. - * 0 if no LTTPRs or more than 8 LTTPRs were detected or in case of a - * detection failure and the transparent LT mode was set. The DPRX - * capabilities are read out. - * <0 Reading out the DPRX capabilities failed. - */ -int intel_dp_init_lttpr_and_dprx_caps(struct intel_dp *intel_dp) +static int intel_dp_init_lttpr(struct intel_dp *intel_dp) { int lttpr_count; - bool ret; int i; - ret = intel_dp_read_lttpr_common_caps(intel_dp); - - /* The DPTX shall read the DPRX caps after LTTPR detection. */ - if (drm_dp_read_dpcd_caps(&intel_dp->aux, intel_dp->dpcd)) { - intel_dp_reset_lttpr_common_caps(intel_dp); - return -EIO; - } - - if (!ret) - return 0; - - /* - * The 0xF0000-0xF02FF range is only valid if the DPCD revision is - * at least 1.4. - */ - if (intel_dp->dpcd[DP_DPCD_REV] < 0x14) { - intel_dp_reset_lttpr_common_caps(intel_dp); + if (!intel_dp_read_lttpr_common_caps(intel_dp)) return 0; - } lttpr_count = drm_dp_lttpr_count(intel_dp->lttpr_common_caps); /* @@ -211,6 +175,37 @@ int intel_dp_init_lttpr_and_dprx_caps(struct intel_dp *intel_dp) return lttpr_count; } + +/** + * intel_dp_init_lttpr_and_dprx_caps - detect LTTPR and DPRX caps, init the LTTPR link training mode + * @intel_dp: Intel DP struct + * + * Read the LTTPR common and DPRX capabilities and switch to non-transparent + * link training mode if any is detected and read the PHY capabilities for all + * detected LTTPRs. In case of an LTTPR detection error or if the number of + * LTTPRs is more than is supported (8), fall back to the no-LTTPR, + * transparent mode link training mode. + * + * Returns: + * >0 if LTTPRs were detected and the non-transparent LT mode was set. The + * DPRX capabilities are read out. + * 0 if no LTTPRs or more than 8 LTTPRs were detected or in case of a + * detection failure and the transparent LT mode was set. The DPRX + * capabilities are read out. + * <0 Reading out the DPRX capabilities failed. + */ +int intel_dp_init_lttpr_and_dprx_caps(struct intel_dp *intel_dp) +{ + int lttpr_count = intel_dp_init_lttpr(intel_dp); + + /* The DPTX shall read the DPRX caps after LTTPR detection. */ + if (drm_dp_read_dpcd_caps(&intel_dp->aux, intel_dp->dpcd)) { + intel_dp_reset_lttpr_common_caps(intel_dp); + return -EIO; + } + + return lttpr_count; +} EXPORT_SYMBOL(intel_dp_init_lttpr_and_dprx_caps); static u8 dp_voltage_max(u8 preemph) diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index 453d8b4c5763..07fcd12dca16 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -485,11 +485,12 @@ static int meson_probe_remote(struct platform_device *pdev, static void meson_drv_shutdown(struct platform_device *pdev) { struct meson_drm *priv = dev_get_drvdata(&pdev->dev); - struct drm_device *drm = priv->drm; - DRM_DEBUG_DRIVER("\n"); - drm_kms_helper_poll_fini(drm); - drm_atomic_helper_shutdown(drm); + if (!priv) + return; + + drm_kms_helper_poll_fini(priv->drm); + drm_atomic_helper_shutdown(priv->drm); } static int meson_drv_probe(struct platform_device *pdev) diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c index 510e3e001dab..a1dcf7d55c90 100644 --- a/drivers/gpu/drm/ttm/ttm_device.c +++ b/drivers/gpu/drm/ttm/ttm_device.c @@ -145,7 +145,7 @@ int ttm_device_swapout(struct ttm_device *bdev, struct ttm_operation_ctx *ctx, list_for_each_entry(bo, &man->lru[j], lru) { uint32_t num_pages; - if (!bo->ttm || + if (!bo->ttm || !ttm_tt_is_populated(bo->ttm) || bo->ttm->page_flags & TTM_PAGE_FLAG_SG || bo->ttm->page_flags & TTM_PAGE_FLAG_SWAPPED) continue; diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 281a65d9b44b..10acece9d7b9 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -647,7 +647,7 @@ config I2C_HIGHLANDER config I2C_HISI tristate "HiSilicon I2C controller" - depends on ARM64 || COMPILE_TEST + depends on (ARM64 && ACPI) || COMPILE_TEST help Say Y here if you want to have Hisilicon I2C controller support available on the Kunpeng Server. diff --git a/drivers/i2c/busses/i2c-ali1563.c b/drivers/i2c/busses/i2c-ali1563.c index 4d12e3da12f0..55a9e93fbfeb 100644 --- a/drivers/i2c/busses/i2c-ali1563.c +++ b/drivers/i2c/busses/i2c-ali1563.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * i2c-ali1563.c - i2c driver for the ALi 1563 Southbridge * * Copyright (C) 2004 Patrick Mochel diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c index c1bbc4caeb5c..66aafa7d1123 100644 --- a/drivers/i2c/busses/i2c-cadence.c +++ b/drivers/i2c/busses/i2c-cadence.c @@ -144,7 +144,7 @@ enum cdns_i2c_mode { }; /** - * enum cdns_i2c_slave_mode - Slave state when I2C is operating in slave mode + * enum cdns_i2c_slave_state - Slave state when I2C is operating in slave mode * * @CDNS_I2C_SLAVE_STATE_IDLE: I2C slave idle * @CDNS_I2C_SLAVE_STATE_SEND: I2C slave sending data to master diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index 13be1d678c39..9b08bb5df38d 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -165,7 +165,7 @@ static int i2c_dw_set_timings_master(struct dw_i2c_dev *dev) } /** - * i2c_dw_init() - Initialize the designware I2C master hardware + * i2c_dw_init_master() - Initialize the designware I2C master hardware * @dev: device private data * * This functions configures and enables the I2C master. diff --git a/drivers/i2c/busses/i2c-eg20t.c b/drivers/i2c/busses/i2c-eg20t.c index 843b31a0f752..321b2770feab 100644 --- a/drivers/i2c/busses/i2c-eg20t.c +++ b/drivers/i2c/busses/i2c-eg20t.c @@ -148,7 +148,7 @@ struct i2c_algo_pch_data { /** * struct adapter_info - This structure holds the adapter information for the - PCH i2c controller + * PCH i2c controller * @pch_data: stores a list of i2c_algo_pch_data * @pch_i2c_suspended: specifies whether the system is suspended or not * perhaps with more lines and words. @@ -358,6 +358,7 @@ static void pch_i2c_repstart(struct i2c_algo_pch_data *adap) /** * pch_i2c_writebytes() - write data to I2C bus in normal mode * @i2c_adap: Pointer to the struct i2c_adapter. + * @msgs: Pointer to the i2c message structure. * @last: specifies whether last message or not. * In the case of compound mode it will be 1 for last message, * otherwise 0. diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 99d446763530..f9e1c2ceaac0 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -395,11 +395,9 @@ static int i801_check_post(struct i801_priv *priv, int status) dev_err(&priv->pci_dev->dev, "Transaction timeout\n"); /* try to stop the current command */ dev_dbg(&priv->pci_dev->dev, "Terminating the current operation\n"); - outb_p(inb_p(SMBHSTCNT(priv)) | SMBHSTCNT_KILL, - SMBHSTCNT(priv)); + outb_p(SMBHSTCNT_KILL, SMBHSTCNT(priv)); usleep_range(1000, 2000); - outb_p(inb_p(SMBHSTCNT(priv)) & (~SMBHSTCNT_KILL), - SMBHSTCNT(priv)); + outb_p(0, SMBHSTCNT(priv)); /* Check if it worked */ status = inb_p(SMBHSTSTS(priv)); diff --git a/drivers/i2c/busses/i2c-icy.c b/drivers/i2c/busses/i2c-icy.c index c8c422e9dda4..5dae7cab7260 100644 --- a/drivers/i2c/busses/i2c-icy.c +++ b/drivers/i2c/busses/i2c-icy.c @@ -123,7 +123,6 @@ static int icy_probe(struct zorro_dev *z, { struct icy_i2c *i2c; struct i2c_algo_pcf_data *algo_data; - struct fwnode_handle *new_fwnode; struct i2c_board_info ltc2990_info = { .type = "ltc2990", .swnode = &icy_ltc2990_node, diff --git a/drivers/i2c/busses/i2c-mpc.c b/drivers/i2c/busses/i2c-mpc.c index 30d9e89a3db2..dcca9c2396db 100644 --- a/drivers/i2c/busses/i2c-mpc.c +++ b/drivers/i2c/busses/i2c-mpc.c @@ -19,6 +19,7 @@ #include <linux/clk.h> #include <linux/io.h> +#include <linux/iopoll.h> #include <linux/fsl_devices.h> #include <linux/i2c.h> #include <linux/interrupt.h> @@ -45,6 +46,7 @@ #define CCR_MTX 0x10 #define CCR_TXAK 0x08 #define CCR_RSTA 0x04 +#define CCR_RSVD 0x02 #define CSR_MCF 0x80 #define CSR_MAAS 0x40 @@ -97,7 +99,7 @@ struct mpc_i2c { u32 block; int rc; int expect_rxack; - + bool has_errata_A004447; }; struct mpc_i2c_divider { @@ -136,6 +138,75 @@ static void mpc_i2c_fixup(struct mpc_i2c *i2c) } } +static int i2c_mpc_wait_sr(struct mpc_i2c *i2c, int mask) +{ + void __iomem *addr = i2c->base + MPC_I2C_SR; + u8 val; + + return readb_poll_timeout(addr, val, val & mask, 0, 100); +} + +/* + * Workaround for Erratum A004447. From the P2040CE Rev Q + * + * 1. Set up the frequency divider and sampling rate. + * 2. I2CCR - a0h + * 3. Poll for I2CSR[MBB] to get set. + * 4. If I2CSR[MAL] is set (an indication that SDA is stuck low), then go to + * step 5. If MAL is not set, then go to step 13. + * 5. I2CCR - 00h + * 6. I2CCR - 22h + * 7. I2CCR - a2h + * 8. Poll for I2CSR[MBB] to get set. + * 9. Issue read to I2CDR. + * 10. Poll for I2CSR[MIF] to be set. + * 11. I2CCR - 82h + * 12. Workaround complete. Skip the next steps. + * 13. Issue read to I2CDR. + * 14. Poll for I2CSR[MIF] to be set. + * 15. I2CCR - 80h + */ +static void mpc_i2c_fixup_A004447(struct mpc_i2c *i2c) +{ + int ret; + u32 val; + + writeccr(i2c, CCR_MEN | CCR_MSTA); + ret = i2c_mpc_wait_sr(i2c, CSR_MBB); + if (ret) { + dev_err(i2c->dev, "timeout waiting for CSR_MBB\n"); + return; + } + + val = readb(i2c->base + MPC_I2C_SR); + + if (val & CSR_MAL) { + writeccr(i2c, 0x00); + writeccr(i2c, CCR_MSTA | CCR_RSVD); + writeccr(i2c, CCR_MEN | CCR_MSTA | CCR_RSVD); + ret = i2c_mpc_wait_sr(i2c, CSR_MBB); + if (ret) { + dev_err(i2c->dev, "timeout waiting for CSR_MBB\n"); + return; + } + val = readb(i2c->base + MPC_I2C_DR); + ret = i2c_mpc_wait_sr(i2c, CSR_MIF); + if (ret) { + dev_err(i2c->dev, "timeout waiting for CSR_MIF\n"); + return; + } + writeccr(i2c, CCR_MEN | CCR_RSVD); + } else { + val = readb(i2c->base + MPC_I2C_DR); + ret = i2c_mpc_wait_sr(i2c, CSR_MIF); + if (ret) { + dev_err(i2c->dev, "timeout waiting for CSR_MIF\n"); + return; + } + writeccr(i2c, CCR_MEN); + } +} + #if defined(CONFIG_PPC_MPC52xx) || defined(CONFIG_PPC_MPC512x) static const struct mpc_i2c_divider mpc_i2c_dividers_52xx[] = { {20, 0x20}, {22, 0x21}, {24, 0x22}, {26, 0x23}, @@ -670,7 +741,10 @@ static int fsl_i2c_bus_recovery(struct i2c_adapter *adap) { struct mpc_i2c *i2c = i2c_get_adapdata(adap); - mpc_i2c_fixup(i2c); + if (i2c->has_errata_A004447) + mpc_i2c_fixup_A004447(i2c); + else + mpc_i2c_fixup(i2c); return 0; } @@ -767,6 +841,9 @@ static int fsl_i2c_probe(struct platform_device *op) } dev_info(i2c->dev, "timeout %u us\n", mpc_ops.timeout * 1000000 / HZ); + if (of_property_read_bool(op->dev.of_node, "fsl,i2c-erratum-a004447")) + i2c->has_errata_A004447 = true; + i2c->adap = mpc_ops; scnprintf(i2c->adap.name, sizeof(i2c->adap.name), "MPC adapter (%s)", of_node_full_name(op->dev.of_node)); diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c index 5ddfa4e56ee2..4e9fb6b44436 100644 --- a/drivers/i2c/busses/i2c-mt65xx.c +++ b/drivers/i2c/busses/i2c-mt65xx.c @@ -479,6 +479,11 @@ static void mtk_i2c_clock_disable(struct mtk_i2c *i2c) static void mtk_i2c_init_hw(struct mtk_i2c *i2c) { u16 control_reg; + u16 intr_stat_reg; + + mtk_i2c_writew(i2c, I2C_CHN_CLR_FLAG, OFFSET_START); + intr_stat_reg = mtk_i2c_readw(i2c, OFFSET_INTR_STAT); + mtk_i2c_writew(i2c, intr_stat_reg, OFFSET_INTR_STAT); if (i2c->dev_comp->apdma_sync) { writel(I2C_DMA_WARM_RST, i2c->pdmabase + OFFSET_RST); diff --git a/drivers/i2c/busses/i2c-nomadik.c b/drivers/i2c/busses/i2c-nomadik.c index dc77e1c4e80f..a2d12a5b1c34 100644 --- a/drivers/i2c/busses/i2c-nomadik.c +++ b/drivers/i2c/busses/i2c-nomadik.c @@ -159,7 +159,7 @@ struct i2c_nmk_client { * @clk_freq: clock frequency for the operation mode * @tft: Tx FIFO Threshold in bytes * @rft: Rx FIFO Threshold in bytes - * @timeout Slave response timeout (ms) + * @timeout: Slave response timeout (ms) * @sm: speed mode * @stop: stop condition. * @xfer_complete: acknowledge completion for a I2C message. diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c index 273222e38056..a0af027db04c 100644 --- a/drivers/i2c/busses/i2c-ocores.c +++ b/drivers/i2c/busses/i2c-ocores.c @@ -250,7 +250,7 @@ static irqreturn_t ocores_isr(int irq, void *dev_id) } /** - * Process timeout event + * ocores_process_timeout() - Process timeout event * @i2c: ocores I2C device instance */ static void ocores_process_timeout(struct ocores_i2c *i2c) @@ -264,7 +264,7 @@ static void ocores_process_timeout(struct ocores_i2c *i2c) } /** - * Wait until something change in a given register + * ocores_wait() - Wait until something change in a given register * @i2c: ocores I2C device instance * @reg: register to query * @mask: bitmask to apply on register value @@ -296,7 +296,7 @@ static int ocores_wait(struct ocores_i2c *i2c, } /** - * Wait until is possible to process some data + * ocores_poll_wait() - Wait until is possible to process some data * @i2c: ocores I2C device instance * * Used when the device is in polling mode (interrupts disabled). @@ -334,7 +334,7 @@ static int ocores_poll_wait(struct ocores_i2c *i2c) } /** - * It handles an IRQ-less transfer + * ocores_process_polling() - It handles an IRQ-less transfer * @i2c: ocores I2C device instance * * Even if IRQ are disabled, the I2C OpenCore IP behavior is exactly the same diff --git a/drivers/i2c/busses/i2c-pnx.c b/drivers/i2c/busses/i2c-pnx.c index 8c4ec7f13f5a..50f21cdbe90d 100644 --- a/drivers/i2c/busses/i2c-pnx.c +++ b/drivers/i2c/busses/i2c-pnx.c @@ -138,7 +138,7 @@ static inline void i2c_pnx_arm_timer(struct i2c_pnx_algo_data *alg_data) /** * i2c_pnx_start - start a device * @slave_addr: slave address - * @adap: pointer to adapter structure + * @alg_data: pointer to local driver data structure * * Generate a START signal in the desired mode. */ @@ -194,7 +194,7 @@ static int i2c_pnx_start(unsigned char slave_addr, /** * i2c_pnx_stop - stop a device - * @adap: pointer to I2C adapter structure + * @alg_data: pointer to local driver data structure * * Generate a STOP signal to terminate the master transaction. */ @@ -223,7 +223,7 @@ static void i2c_pnx_stop(struct i2c_pnx_algo_data *alg_data) /** * i2c_pnx_master_xmit - transmit data to slave - * @adap: pointer to I2C adapter structure + * @alg_data: pointer to local driver data structure * * Sends one byte of data to the slave */ @@ -293,7 +293,7 @@ static int i2c_pnx_master_xmit(struct i2c_pnx_algo_data *alg_data) /** * i2c_pnx_master_rcv - receive data from slave - * @adap: pointer to I2C adapter structure + * @alg_data: pointer to local driver data structure * * Reads one byte data from the slave */ diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 214b4c913a13..07b710a774df 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -100,7 +100,7 @@ static const struct geni_i2c_err_log gi2c_log[] = { [GP_IRQ0] = {-EIO, "Unknown I2C err GP_IRQ0"}, [NACK] = {-ENXIO, "NACK: slv unresponsive, check its power/reset-ln"}, [GP_IRQ2] = {-EIO, "Unknown I2C err GP IRQ2"}, - [BUS_PROTO] = {-EPROTO, "Bus proto err, noisy/unepxected start/stop"}, + [BUS_PROTO] = {-EPROTO, "Bus proto err, noisy/unexpected start/stop"}, [ARB_LOST] = {-EAGAIN, "Bus arbitration lost, clock line undriveable"}, [GP_IRQ5] = {-EIO, "Unknown I2C err GP IRQ5"}, [GENI_OVERRUN] = {-EIO, "Cmd overrun, check GENI cmd-state machine"}, diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c index ab928613afba..4d82761e1585 100644 --- a/drivers/i2c/busses/i2c-s3c2410.c +++ b/drivers/i2c/busses/i2c-s3c2410.c @@ -480,7 +480,10 @@ static int i2c_s3c_irq_nextbyte(struct s3c24xx_i2c *i2c, unsigned long iicstat) * forces us to send a new START * when we change direction */ + dev_dbg(i2c->dev, + "missing START before write->read\n"); s3c24xx_i2c_stop(i2c, -EINVAL); + break; } goto retry_write; diff --git a/drivers/i2c/busses/i2c-sh_mobile.c b/drivers/i2c/busses/i2c-sh_mobile.c index 3ae6ca21a02c..2d2e630fd438 100644 --- a/drivers/i2c/busses/i2c-sh_mobile.c +++ b/drivers/i2c/busses/i2c-sh_mobile.c @@ -807,7 +807,7 @@ static const struct sh_mobile_dt_config r8a7740_dt_config = { static const struct of_device_id sh_mobile_i2c_dt_ids[] = { { .compatible = "renesas,iic-r8a73a4", .data = &fast_clock_dt_config }, { .compatible = "renesas,iic-r8a7740", .data = &r8a7740_dt_config }, - { .compatible = "renesas,iic-r8a774c0", .data = &fast_clock_dt_config }, + { .compatible = "renesas,iic-r8a774c0", .data = &v2_freq_calc_dt_config }, { .compatible = "renesas,iic-r8a7790", .data = &v2_freq_calc_dt_config }, { .compatible = "renesas,iic-r8a7791", .data = &v2_freq_calc_dt_config }, { .compatible = "renesas,iic-r8a7792", .data = &v2_freq_calc_dt_config }, diff --git a/drivers/i2c/busses/i2c-st.c b/drivers/i2c/busses/i2c-st.c index faa81a95551f..88482316d22a 100644 --- a/drivers/i2c/busses/i2c-st.c +++ b/drivers/i2c/busses/i2c-st.c @@ -524,7 +524,7 @@ static void st_i2c_handle_write(struct st_i2c_dev *i2c_dev) } /** - * st_i2c_handle_write() - Handle FIFO enmpty interrupt in case of read + * st_i2c_handle_read() - Handle FIFO empty interrupt in case of read * @i2c_dev: Controller's private data */ static void st_i2c_handle_read(struct st_i2c_dev *i2c_dev) @@ -558,7 +558,7 @@ static void st_i2c_handle_read(struct st_i2c_dev *i2c_dev) } /** - * st_i2c_isr() - Interrupt routine + * st_i2c_isr_thread() - Interrupt routine * @irq: interrupt number * @data: Controller's private data */ diff --git a/drivers/i2c/busses/i2c-stm32f4.c b/drivers/i2c/busses/i2c-stm32f4.c index 4933fc8ce3fd..eebce7ecef25 100644 --- a/drivers/i2c/busses/i2c-stm32f4.c +++ b/drivers/i2c/busses/i2c-stm32f4.c @@ -313,7 +313,7 @@ static int stm32f4_i2c_wait_free_bus(struct stm32f4_i2c_dev *i2c_dev) } /** - * stm32f4_i2c_write_ byte() - Write a byte in the data register + * stm32f4_i2c_write_byte() - Write a byte in the data register * @i2c_dev: Controller's private data * @byte: Data to write in the register */ diff --git a/drivers/i2c/muxes/i2c-arb-gpio-challenge.c b/drivers/i2c/muxes/i2c-arb-gpio-challenge.c index 6dc88902c189..1c78657631f4 100644 --- a/drivers/i2c/muxes/i2c-arb-gpio-challenge.c +++ b/drivers/i2c/muxes/i2c-arb-gpio-challenge.c @@ -34,7 +34,7 @@ struct i2c_arbitrator_data { }; -/** +/* * i2c_arbitrator_select - claim the I2C bus * * Use the GPIO-based signalling protocol; return -EBUSY if we fail. @@ -77,7 +77,7 @@ static int i2c_arbitrator_select(struct i2c_mux_core *muxc, u32 chan) return -EBUSY; } -/** +/* * i2c_arbitrator_deselect - release the I2C bus * * Release the I2C bus using the GPIO-based signalling protocol. diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c index 9d3952b4674f..a27db78ea13e 100644 --- a/drivers/iio/adc/ad7124.c +++ b/drivers/iio/adc/ad7124.c @@ -771,6 +771,13 @@ static int ad7124_of_parse_channel_config(struct iio_dev *indio_dev, if (ret) goto err; + if (channel >= indio_dev->num_channels) { + dev_err(indio_dev->dev.parent, + "Channel index >= number of channels\n"); + ret = -EINVAL; + goto err; + } + ret = of_property_read_u32_array(child, "diff-channels", ain, 2); if (ret) @@ -850,6 +857,11 @@ static int ad7124_setup(struct ad7124_state *st) return ret; } +static void ad7124_reg_disable(void *r) +{ + regulator_disable(r); +} + static int ad7124_probe(struct spi_device *spi) { const struct ad7124_chip_info *info; @@ -895,17 +907,20 @@ static int ad7124_probe(struct spi_device *spi) ret = regulator_enable(st->vref[i]); if (ret) return ret; + + ret = devm_add_action_or_reset(&spi->dev, ad7124_reg_disable, + st->vref[i]); + if (ret) + return ret; } st->mclk = devm_clk_get(&spi->dev, "mclk"); - if (IS_ERR(st->mclk)) { - ret = PTR_ERR(st->mclk); - goto error_regulator_disable; - } + if (IS_ERR(st->mclk)) + return PTR_ERR(st->mclk); ret = clk_prepare_enable(st->mclk); if (ret < 0) - goto error_regulator_disable; + return ret; ret = ad7124_soft_reset(st); if (ret < 0) @@ -935,11 +950,6 @@ error_remove_trigger: ad_sd_cleanup_buffer_and_trigger(indio_dev); error_clk_disable_unprepare: clk_disable_unprepare(st->mclk); -error_regulator_disable: - for (i = ARRAY_SIZE(st->vref) - 1; i >= 0; i--) { - if (!IS_ERR_OR_NULL(st->vref[i])) - regulator_disable(st->vref[i]); - } return ret; } @@ -948,17 +958,11 @@ static int ad7124_remove(struct spi_device *spi) { struct iio_dev *indio_dev = spi_get_drvdata(spi); struct ad7124_state *st = iio_priv(indio_dev); - int i; iio_device_unregister(indio_dev); ad_sd_cleanup_buffer_and_trigger(indio_dev); clk_disable_unprepare(st->mclk); - for (i = ARRAY_SIZE(st->vref) - 1; i >= 0; i--) { - if (!IS_ERR_OR_NULL(st->vref[i])) - regulator_disable(st->vref[i]); - } - return 0; } diff --git a/drivers/iio/adc/ad7192.c b/drivers/iio/adc/ad7192.c index 2ed580521d81..1141cc13a124 100644 --- a/drivers/iio/adc/ad7192.c +++ b/drivers/iio/adc/ad7192.c @@ -912,7 +912,7 @@ static int ad7192_probe(struct spi_device *spi) { struct ad7192_state *st; struct iio_dev *indio_dev; - int ret, voltage_uv = 0; + int ret; if (!spi->irq) { dev_err(&spi->dev, "no IRQ?\n"); @@ -949,15 +949,12 @@ static int ad7192_probe(struct spi_device *spi) goto error_disable_avdd; } - voltage_uv = regulator_get_voltage(st->avdd); - - if (voltage_uv > 0) { - st->int_vref_mv = voltage_uv / 1000; - } else { - ret = voltage_uv; + ret = regulator_get_voltage(st->avdd); + if (ret < 0) { dev_err(&spi->dev, "Device tree error, reference voltage undefined\n"); goto error_disable_avdd; } + st->int_vref_mv = ret / 1000; spi_set_drvdata(spi, indio_dev); st->chip_info = of_device_get_match_data(&spi->dev); @@ -1014,7 +1011,9 @@ static int ad7192_probe(struct spi_device *spi) return 0; error_disable_clk: - clk_disable_unprepare(st->mclk); + if (st->clock_sel == AD7192_CLK_EXT_MCLK1_2 || + st->clock_sel == AD7192_CLK_EXT_MCLK2) + clk_disable_unprepare(st->mclk); error_remove_trigger: ad_sd_cleanup_buffer_and_trigger(indio_dev); error_disable_dvdd: @@ -1031,7 +1030,9 @@ static int ad7192_remove(struct spi_device *spi) struct ad7192_state *st = iio_priv(indio_dev); iio_device_unregister(indio_dev); - clk_disable_unprepare(st->mclk); + if (st->clock_sel == AD7192_CLK_EXT_MCLK1_2 || + st->clock_sel == AD7192_CLK_EXT_MCLK2) + clk_disable_unprepare(st->mclk); ad_sd_cleanup_buffer_and_trigger(indio_dev); regulator_disable(st->dvdd); diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c index c945f1349623..60f21fed6dcb 100644 --- a/drivers/iio/adc/ad7768-1.c +++ b/drivers/iio/adc/ad7768-1.c @@ -167,6 +167,10 @@ struct ad7768_state { * transfer buffers to live in their own cache lines. */ union { + struct { + __be32 chan; + s64 timestamp; + } scan; __be32 d32; u8 d8[2]; } data ____cacheline_aligned; @@ -469,11 +473,11 @@ static irqreturn_t ad7768_trigger_handler(int irq, void *p) mutex_lock(&st->lock); - ret = spi_read(st->spi, &st->data.d32, 3); + ret = spi_read(st->spi, &st->data.scan.chan, 3); if (ret < 0) goto err_unlock; - iio_push_to_buffers_with_timestamp(indio_dev, &st->data.d32, + iio_push_to_buffers_with_timestamp(indio_dev, &st->data.scan, iio_get_time_ns(indio_dev)); iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/adc/ad7793.c b/drivers/iio/adc/ad7793.c index 5e980a06258e..440ef4c7be07 100644 --- a/drivers/iio/adc/ad7793.c +++ b/drivers/iio/adc/ad7793.c @@ -279,6 +279,7 @@ static int ad7793_setup(struct iio_dev *indio_dev, id &= AD7793_ID_MASK; if (id != st->chip_info->id) { + ret = -ENODEV; dev_err(&st->sd.spi->dev, "device ID query failed\n"); goto out; } diff --git a/drivers/iio/adc/ad7923.c b/drivers/iio/adc/ad7923.c index 9a649745cd0a..069b561ee768 100644 --- a/drivers/iio/adc/ad7923.c +++ b/drivers/iio/adc/ad7923.c @@ -59,8 +59,10 @@ struct ad7923_state { /* * DMA (thus cache coherency maintenance) requires the * transfer buffers to live in their own cache lines. + * Ensure rx_buf can be directly used in iio_push_to_buffers_with_timetamp + * Length = 8 channels + 4 extra for 8 byte timestamp */ - __be16 rx_buf[4] ____cacheline_aligned; + __be16 rx_buf[12] ____cacheline_aligned; __be16 tx_buf[4]; }; diff --git a/drivers/iio/dac/ad5770r.c b/drivers/iio/dac/ad5770r.c index 7ab2ccf90863..8107f7bbbe3c 100644 --- a/drivers/iio/dac/ad5770r.c +++ b/drivers/iio/dac/ad5770r.c @@ -524,23 +524,29 @@ static int ad5770r_channel_config(struct ad5770r_state *st) device_for_each_child_node(&st->spi->dev, child) { ret = fwnode_property_read_u32(child, "num", &num); if (ret) - return ret; - if (num >= AD5770R_MAX_CHANNELS) - return -EINVAL; + goto err_child_out; + if (num >= AD5770R_MAX_CHANNELS) { + ret = -EINVAL; + goto err_child_out; + } ret = fwnode_property_read_u32_array(child, "adi,range-microamp", tmp, 2); if (ret) - return ret; + goto err_child_out; min = tmp[0] / 1000; max = tmp[1] / 1000; ret = ad5770r_store_output_range(st, min, max, num); if (ret) - return ret; + goto err_child_out; } + return 0; + +err_child_out: + fwnode_handle_put(child); return ret; } diff --git a/drivers/iio/gyro/fxas21002c_core.c b/drivers/iio/gyro/fxas21002c_core.c index 1a20c6b88e7d..645461c70454 100644 --- a/drivers/iio/gyro/fxas21002c_core.c +++ b/drivers/iio/gyro/fxas21002c_core.c @@ -399,6 +399,7 @@ static int fxas21002c_temp_get(struct fxas21002c_data *data, int *val) ret = regmap_field_read(data->regmap_fields[F_TEMP], &temp); if (ret < 0) { dev_err(dev, "failed to read temp: %d\n", ret); + fxas21002c_pm_put(data); goto data_unlock; } @@ -432,6 +433,7 @@ static int fxas21002c_axis_get(struct fxas21002c_data *data, &axis_be, sizeof(axis_be)); if (ret < 0) { dev_err(dev, "failed to read axis: %d: %d\n", index, ret); + fxas21002c_pm_put(data); goto data_unlock; } diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 4388afeff251..9662cd39c7ff 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -743,10 +743,10 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev) ent->xlt = (1 << ent->order) * sizeof(struct mlx5_mtt) / MLX5_IB_UMR_OCTOWORD; ent->access_mode = MLX5_MKC_ACCESS_MODE_MTT; - if ((dev->mdev->profile->mask & MLX5_PROF_MASK_MR_CACHE) && + if ((dev->mdev->profile.mask & MLX5_PROF_MASK_MR_CACHE) && !dev->is_rep && mlx5_core_is_pf(dev->mdev) && mlx5_ib_can_load_pas_with_umr(dev, 0)) - ent->limit = dev->mdev->profile->mr_cache[i].limit; + ent->limit = dev->mdev->profile.mr_cache[i].limit; else ent->limit = 0; spin_lock_irq(&ent->lock); diff --git a/drivers/interconnect/qcom/bcm-voter.c b/drivers/interconnect/qcom/bcm-voter.c index d1591a28b743..8f385f9c2dd3 100644 --- a/drivers/interconnect/qcom/bcm-voter.c +++ b/drivers/interconnect/qcom/bcm-voter.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright (c) 2020, The Linux Foundation. All rights reserved. + * Copyright (c) 2020-2021, The Linux Foundation. All rights reserved. */ #include <asm/div64.h> @@ -205,6 +205,7 @@ struct bcm_voter *of_bcm_voter_get(struct device *dev, const char *name) } mutex_unlock(&bcm_voter_lock); + of_node_put(node); return voter; } EXPORT_SYMBOL_GPL(of_bcm_voter_get); @@ -362,6 +363,7 @@ static const struct of_device_id bcm_voter_of_match[] = { { .compatible = "qcom,bcm-voter" }, { } }; +MODULE_DEVICE_TABLE(of, bcm_voter_of_match); static struct platform_driver qcom_icc_bcm_voter_driver = { .probe = qcom_icc_bcm_voter_probe, diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 80e8e1916dd1..3ac42bbdefc6 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -884,7 +884,7 @@ static inline u64 build_inv_address(u64 address, size_t size) * The msb-bit must be clear on the address. Just set all the * lower bits. */ - address |= 1ull << (msb_diff - 1); + address |= (1ull << msb_diff) - 1; } /* Clear bits 11:0 */ @@ -1714,6 +1714,8 @@ static void amd_iommu_probe_finalize(struct device *dev) domain = iommu_get_domain_for_dev(dev); if (domain->type == IOMMU_DOMAIN_DMA) iommu_setup_dma_ops(dev, IOVA_START_PFN << PAGE_SHIFT, 0); + else + set_dma_ops(dev, NULL); } static void amd_iommu_release_device(struct device *dev) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 1757ac1e1623..84057cb9596c 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1142,7 +1142,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) err = iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL); if (err) - goto err_unmap; + goto err_sysfs; } drhd->iommu = iommu; @@ -1150,6 +1150,8 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) return 0; +err_sysfs: + iommu_device_sysfs_remove(&iommu->iommu); err_unmap: unmap_iommu(iommu); error_free_seq_id: diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 708f430af1c4..be35284a2016 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2525,9 +2525,9 @@ static int domain_setup_first_level(struct intel_iommu *iommu, struct device *dev, u32 pasid) { - int flags = PASID_FLAG_SUPERVISOR_MODE; struct dma_pte *pgd = domain->pgd; int agaw, level; + int flags = 0; /* * Skip top levels of page tables for iommu which has @@ -2543,7 +2543,10 @@ static int domain_setup_first_level(struct intel_iommu *iommu, if (level != 4 && level != 5) return -EINVAL; - flags |= (level == 5) ? PASID_FLAG_FL5LP : 0; + if (pasid != PASID_RID2PASID) + flags |= PASID_FLAG_SUPERVISOR_MODE; + if (level == 5) + flags |= PASID_FLAG_FL5LP; if (domain->domain.type == IOMMU_DOMAIN_UNMANAGED) flags |= PASID_FLAG_PAGE_SNOOP; @@ -4606,6 +4609,8 @@ static int auxiliary_link_device(struct dmar_domain *domain, if (!sinfo) { sinfo = kzalloc(sizeof(*sinfo), GFP_ATOMIC); + if (!sinfo) + return -ENOMEM; sinfo->domain = domain; sinfo->pdev = dev; list_add(&sinfo->link_phys, &info->subdevices); diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index 72646bafc52f..72dc84821dad 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -699,7 +699,8 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu, * Since it is a second level only translation setup, we should * set SRE bit as well (addresses are expected to be GPAs). */ - pasid_set_sre(pte); + if (pasid != PASID_RID2PASID) + pasid_set_sre(pte); pasid_set_present(pte); pasid_flush_caches(iommu, pte, pasid, did); diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 7c02481a81b4..c6e5ee4d9cef 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -1136,6 +1136,7 @@ static struct virtio_device_id id_table[] = { { VIRTIO_ID_IOMMU, VIRTIO_DEV_ANY_ID }, { 0 }, }; +MODULE_DEVICE_TABLE(virtio, id_table); static struct virtio_driver virtio_iommu_drv = { .driver.name = KBUILD_MODNAME, diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c index ee925b58bbce..2a1ddd47a096 100644 --- a/drivers/isdn/hardware/mISDN/netjet.c +++ b/drivers/isdn/hardware/mISDN/netjet.c @@ -1100,7 +1100,6 @@ nj_probe(struct pci_dev *pdev, const struct pci_device_id *ent) card->typ = NETJET_S_TJ300; card->base = pci_resource_start(pdev, 0); - card->irq = pdev->irq; pci_set_drvdata(pdev, card); err = setup_instance(card); if (err) diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index b8e4d31124ea..751ec5ea1dbb 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -859,7 +859,8 @@ static uint32_t __minimum_chunk_size(struct origin *o) if (o) list_for_each_entry(snap, &o->snapshots, list) - chunk_size = min(chunk_size, snap->store->chunk_size); + chunk_size = min_not_zero(chunk_size, + snap->store->chunk_size); return (uint32_t) chunk_size; } diff --git a/drivers/md/dm-verity-verify-sig.c b/drivers/md/dm-verity-verify-sig.c index 29385dc470d5..db61a1f43ae9 100644 --- a/drivers/md/dm-verity-verify-sig.c +++ b/drivers/md/dm-verity-verify-sig.c @@ -15,7 +15,7 @@ #define DM_VERITY_VERIFY_ERR(s) DM_VERITY_ROOT_HASH_VERIFICATION " " s static bool require_signatures; -module_param(require_signatures, bool, false); +module_param(require_signatures, bool, 0444); MODULE_PARM_DESC(require_signatures, "Verify the roothash of dm-verity hash tree"); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 841e1c1aa5e6..7d4ff8a5c55e 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5311,8 +5311,6 @@ static int in_chunk_boundary(struct mddev *mddev, struct bio *bio) unsigned int chunk_sectors; unsigned int bio_sectors = bio_sectors(bio); - WARN_ON_ONCE(bio->bi_bdev->bd_partno); - chunk_sectors = min(conf->chunk_sectors, conf->prev_chunk_sectors); return chunk_sectors >= ((sector & (chunk_sectors - 1)) + bio_sectors); diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c index 64d33e368509..67c5b452dd35 100644 --- a/drivers/misc/kgdbts.c +++ b/drivers/misc/kgdbts.c @@ -101,8 +101,9 @@ printk(KERN_INFO a); \ } while (0) #define v2printk(a...) do { \ - if (verbose > 1) \ + if (verbose > 1) { \ printk(KERN_INFO a); \ + } \ touch_nmi_watchdog(); \ } while (0) #define eprintk(a...) do { \ diff --git a/drivers/misc/mei/interrupt.c b/drivers/misc/mei/interrupt.c index a98f6b895af7..aab3ebfa9fc4 100644 --- a/drivers/misc/mei/interrupt.c +++ b/drivers/misc/mei/interrupt.c @@ -277,6 +277,9 @@ static int mei_cl_irq_read(struct mei_cl *cl, struct mei_cl_cb *cb, return ret; } + pm_runtime_mark_last_busy(dev->dev); + pm_request_autosuspend(dev->dev); + list_move_tail(&cb->list, &cl->rd_pending); return 0; diff --git a/drivers/mtd/nand/raw/cs553x_nand.c b/drivers/mtd/nand/raw/cs553x_nand.c index 6edf78c16fc8..df40927e5678 100644 --- a/drivers/mtd/nand/raw/cs553x_nand.c +++ b/drivers/mtd/nand/raw/cs553x_nand.c @@ -18,6 +18,7 @@ #include <linux/module.h> #include <linux/delay.h> #include <linux/mtd/mtd.h> +#include <linux/mtd/nand-ecc-sw-hamming.h> #include <linux/mtd/rawnand.h> #include <linux/mtd/partitions.h> #include <linux/iopoll.h> @@ -240,6 +241,15 @@ static int cs_calculate_ecc(struct nand_chip *this, const u_char *dat, return 0; } +static int cs553x_ecc_correct(struct nand_chip *chip, + unsigned char *buf, + unsigned char *read_ecc, + unsigned char *calc_ecc) +{ + return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, + chip->ecc.size, false); +} + static struct cs553x_nand_controller *controllers[4]; static int cs553x_attach_chip(struct nand_chip *chip) @@ -251,7 +261,7 @@ static int cs553x_attach_chip(struct nand_chip *chip) chip->ecc.bytes = 3; chip->ecc.hwctl = cs_enable_hwecc; chip->ecc.calculate = cs_calculate_ecc; - chip->ecc.correct = rawnand_sw_hamming_correct; + chip->ecc.correct = cs553x_ecc_correct; chip->ecc.strength = 1; return 0; diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index bf695255b43a..a3e66155ae40 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -25,6 +25,7 @@ #include <linux/sched.h> #include <linux/types.h> #include <linux/mtd/mtd.h> +#include <linux/mtd/nand-ecc-sw-hamming.h> #include <linux/mtd/rawnand.h> #include <linux/platform_device.h> #include <linux/of.h> @@ -432,6 +433,15 @@ static int fsmc_read_hwecc_ecc1(struct nand_chip *chip, const u8 *data, return 0; } +static int fsmc_correct_ecc1(struct nand_chip *chip, + unsigned char *buf, + unsigned char *read_ecc, + unsigned char *calc_ecc) +{ + return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, + chip->ecc.size, false); +} + /* Count the number of 0's in buff upto a max of max_bits */ static int count_written_bits(u8 *buff, int size, int max_bits) { @@ -917,7 +927,7 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand) case NAND_ECC_ENGINE_TYPE_ON_HOST: dev_info(host->dev, "Using 1-bit HW ECC scheme\n"); nand->ecc.calculate = fsmc_read_hwecc_ecc1; - nand->ecc.correct = rawnand_sw_hamming_correct; + nand->ecc.correct = fsmc_correct_ecc1; nand->ecc.hwctl = fsmc_enable_hwecc; nand->ecc.bytes = 3; nand->ecc.strength = 1; diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c index 6b7269cfb7d8..d7dfc6fd85ca 100644 --- a/drivers/mtd/nand/raw/lpc32xx_slc.c +++ b/drivers/mtd/nand/raw/lpc32xx_slc.c @@ -27,6 +27,7 @@ #include <linux/of.h> #include <linux/of_gpio.h> #include <linux/mtd/lpc32xx_slc.h> +#include <linux/mtd/nand-ecc-sw-hamming.h> #define LPC32XX_MODNAME "lpc32xx-nand" @@ -345,6 +346,18 @@ static int lpc32xx_nand_ecc_calculate(struct nand_chip *chip, } /* + * Corrects the data + */ +static int lpc32xx_nand_ecc_correct(struct nand_chip *chip, + unsigned char *buf, + unsigned char *read_ecc, + unsigned char *calc_ecc) +{ + return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, + chip->ecc.size, false); +} + +/* * Read a single byte from NAND device */ static uint8_t lpc32xx_nand_read_byte(struct nand_chip *chip) @@ -802,7 +815,7 @@ static int lpc32xx_nand_attach_chip(struct nand_chip *chip) chip->ecc.write_oob = lpc32xx_nand_write_oob_syndrome; chip->ecc.read_oob = lpc32xx_nand_read_oob_syndrome; chip->ecc.calculate = lpc32xx_nand_ecc_calculate; - chip->ecc.correct = rawnand_sw_hamming_correct; + chip->ecc.correct = lpc32xx_nand_ecc_correct; chip->ecc.hwctl = lpc32xx_nand_ecc_enable; /* diff --git a/drivers/mtd/nand/raw/ndfc.c b/drivers/mtd/nand/raw/ndfc.c index 338d6b1a189e..98d5a94c3a24 100644 --- a/drivers/mtd/nand/raw/ndfc.c +++ b/drivers/mtd/nand/raw/ndfc.c @@ -22,6 +22,7 @@ #include <linux/mtd/ndfc.h> #include <linux/slab.h> #include <linux/mtd/mtd.h> +#include <linux/mtd/nand-ecc-sw-hamming.h> #include <linux/of_address.h> #include <linux/of_platform.h> #include <asm/io.h> @@ -100,6 +101,15 @@ static int ndfc_calculate_ecc(struct nand_chip *chip, return 0; } +static int ndfc_correct_ecc(struct nand_chip *chip, + unsigned char *buf, + unsigned char *read_ecc, + unsigned char *calc_ecc) +{ + return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, + chip->ecc.size, false); +} + /* * Speedups for buffer read/write/verify * @@ -145,7 +155,7 @@ static int ndfc_chip_init(struct ndfc_controller *ndfc, chip->controller = &ndfc->ndfc_control; chip->legacy.read_buf = ndfc_read_buf; chip->legacy.write_buf = ndfc_write_buf; - chip->ecc.correct = rawnand_sw_hamming_correct; + chip->ecc.correct = ndfc_correct_ecc; chip->ecc.hwctl = ndfc_enable_hwecc; chip->ecc.calculate = ndfc_calculate_ecc; chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; diff --git a/drivers/mtd/nand/raw/sharpsl.c b/drivers/mtd/nand/raw/sharpsl.c index 5612ee628425..2f1fe464e663 100644 --- a/drivers/mtd/nand/raw/sharpsl.c +++ b/drivers/mtd/nand/raw/sharpsl.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/delay.h> #include <linux/mtd/mtd.h> +#include <linux/mtd/nand-ecc-sw-hamming.h> #include <linux/mtd/rawnand.h> #include <linux/mtd/partitions.h> #include <linux/mtd/sharpsl.h> @@ -96,6 +97,15 @@ static int sharpsl_nand_calculate_ecc(struct nand_chip *chip, return readb(sharpsl->io + ECCCNTR) != 0; } +static int sharpsl_nand_correct_ecc(struct nand_chip *chip, + unsigned char *buf, + unsigned char *read_ecc, + unsigned char *calc_ecc) +{ + return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, + chip->ecc.size, false); +} + static int sharpsl_attach_chip(struct nand_chip *chip) { if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) @@ -106,7 +116,7 @@ static int sharpsl_attach_chip(struct nand_chip *chip) chip->ecc.strength = 1; chip->ecc.hwctl = sharpsl_nand_enable_hwecc; chip->ecc.calculate = sharpsl_nand_calculate_ecc; - chip->ecc.correct = rawnand_sw_hamming_correct; + chip->ecc.correct = sharpsl_nand_correct_ecc; return 0; } diff --git a/drivers/mtd/nand/raw/tmio_nand.c b/drivers/mtd/nand/raw/tmio_nand.c index de8e919d0ebe..6d93dd31969b 100644 --- a/drivers/mtd/nand/raw/tmio_nand.c +++ b/drivers/mtd/nand/raw/tmio_nand.c @@ -34,6 +34,7 @@ #include <linux/interrupt.h> #include <linux/ioport.h> #include <linux/mtd/mtd.h> +#include <linux/mtd/nand-ecc-sw-hamming.h> #include <linux/mtd/rawnand.h> #include <linux/mtd/partitions.h> #include <linux/slab.h> @@ -292,11 +293,12 @@ static int tmio_nand_correct_data(struct nand_chip *chip, unsigned char *buf, int r0, r1; /* assume ecc.size = 512 and ecc.bytes = 6 */ - r0 = rawnand_sw_hamming_correct(chip, buf, read_ecc, calc_ecc); + r0 = ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, + chip->ecc.size, false); if (r0 < 0) return r0; - r1 = rawnand_sw_hamming_correct(chip, buf + 256, read_ecc + 3, - calc_ecc + 3); + r1 = ecc_sw_hamming_correct(buf + 256, read_ecc + 3, calc_ecc + 3, + chip->ecc.size, false); if (r1 < 0) return r1; return r0 + r1; diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c index 1a9449e53bf9..b8894ac27073 100644 --- a/drivers/mtd/nand/raw/txx9ndfmc.c +++ b/drivers/mtd/nand/raw/txx9ndfmc.c @@ -13,6 +13,7 @@ #include <linux/platform_device.h> #include <linux/delay.h> #include <linux/mtd/mtd.h> +#include <linux/mtd/nand-ecc-sw-hamming.h> #include <linux/mtd/rawnand.h> #include <linux/mtd/partitions.h> #include <linux/io.h> @@ -193,8 +194,8 @@ static int txx9ndfmc_correct_data(struct nand_chip *chip, unsigned char *buf, int stat; for (eccsize = chip->ecc.size; eccsize > 0; eccsize -= 256) { - stat = rawnand_sw_hamming_correct(chip, buf, read_ecc, - calc_ecc); + stat = ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, + chip->ecc.size, false); if (stat < 0) return stat; corrected += stat; diff --git a/drivers/mtd/parsers/ofpart_core.c b/drivers/mtd/parsers/ofpart_core.c index 0fd8d2a0db97..192190c42fc8 100644 --- a/drivers/mtd/parsers/ofpart_core.c +++ b/drivers/mtd/parsers/ofpart_core.c @@ -57,20 +57,22 @@ static int parse_fixed_partitions(struct mtd_info *master, if (!mtd_node) return 0; - ofpart_node = of_get_child_by_name(mtd_node, "partitions"); - if (!ofpart_node && !master->parent) { - /* - * We might get here even when ofpart isn't used at all (e.g., - * when using another parser), so don't be louder than - * KERN_DEBUG - */ - pr_debug("%s: 'partitions' subnode not found on %pOF. Trying to parse direct subnodes as partitions.\n", - master->name, mtd_node); + if (!master->parent) { /* Master */ + ofpart_node = of_get_child_by_name(mtd_node, "partitions"); + if (!ofpart_node) { + /* + * We might get here even when ofpart isn't used at all (e.g., + * when using another parser), so don't be louder than + * KERN_DEBUG + */ + pr_debug("%s: 'partitions' subnode not found on %pOF. Trying to parse direct subnodes as partitions.\n", + master->name, mtd_node); + ofpart_node = mtd_node; + dedicated = false; + } + } else { /* Partition */ ofpart_node = mtd_node; - dedicated = false; } - if (!ofpart_node) - return 0; of_id = of_match_node(parse_ofpart_match_table, ofpart_node); if (dedicated && !of_id) { diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c index ba8e70a8e312..6b12ce822e51 100644 --- a/drivers/net/appletalk/cops.c +++ b/drivers/net/appletalk/cops.c @@ -327,6 +327,8 @@ static int __init cops_probe1(struct net_device *dev, int ioaddr) break; } + dev->base_addr = ioaddr; + /* Reserve any actual interrupt. */ if (dev->irq) { retval = request_irq(dev->irq, cops_interrupt, 0, dev->name, dev); @@ -334,8 +336,6 @@ static int __init cops_probe1(struct net_device *dev, int ioaddr) goto err_out; } - dev->base_addr = ioaddr; - lp = netdev_priv(dev); spin_lock_init(&lp->lock); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 20bbda1b36e1..c5a646d06102 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1526,6 +1526,7 @@ static struct slave *bond_alloc_slave(struct bonding *bond, slave->bond = bond; slave->dev = slave_dev; + INIT_DELAYED_WORK(&slave->notify_work, bond_netdev_notify_work); if (bond_kobj_init(slave)) return NULL; @@ -1538,7 +1539,6 @@ static struct slave *bond_alloc_slave(struct bonding *bond, return NULL; } } - INIT_DELAYED_WORK(&slave->notify_work, bond_netdev_notify_work); return slave; } diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 9150038b60cb..3b018fcf4412 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -821,11 +821,9 @@ static void bcm_sf2_sw_mac_link_up(struct dsa_switch *ds, int port, bcm_sf2_sw_mac_link_set(ds, port, interface, true); if (port != core_readl(priv, CORE_IMP0_PRT_ID)) { - u32 reg_rgmii_ctrl; + u32 reg_rgmii_ctrl = 0; u32 reg, offset; - reg_rgmii_ctrl = bcm_sf2_reg_rgmii_cntrl(priv, port); - if (priv->type == BCM4908_DEVICE_ID || priv->type == BCM7445_DEVICE_ID) offset = CORE_STS_OVERRIDE_GMIIP_PORT(port); @@ -836,6 +834,7 @@ static void bcm_sf2_sw_mac_link_up(struct dsa_switch *ds, int port, interface == PHY_INTERFACE_MODE_RGMII_TXID || interface == PHY_INTERFACE_MODE_MII || interface == PHY_INTERFACE_MODE_REVMII) { + reg_rgmii_ctrl = bcm_sf2_reg_rgmii_cntrl(priv, port); reg = reg_readl(priv, reg_rgmii_ctrl); reg &= ~(RX_PAUSE_EN | TX_PAUSE_EN); diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 55e5d479acce..854e25f43fa7 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -1530,6 +1530,7 @@ static const struct ksz_chip_data ksz9477_switch_chips[] = { .num_statics = 16, .cpu_ports = 0x7F, /* can be configured as cpu port */ .port_cnt = 7, /* total physical port count */ + .phy_errata_9477 = true, }, }; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 96f7c9eede35..9b90f3d3a8f5 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1262,14 +1262,6 @@ mt7530_port_set_vlan_aware(struct dsa_switch *ds, int port) { struct mt7530_priv *priv = ds->priv; - /* The real fabric path would be decided on the membership in the - * entry of VLAN table. PCR_MATRIX set up here with ALL_MEMBERS - * means potential VLAN can be consisting of certain subset of all - * ports. - */ - mt7530_rmw(priv, MT7530_PCR_P(port), - PCR_MATRIX_MASK, PCR_MATRIX(MT7530_ALL_MEMBERS)); - /* Trapped into security mode allows packet forwarding through VLAN * table lookup. CPU port is set to fallback mode to let untagged * frames pass through. diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 2473bebe48e6..f966a253d1c7 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1227,12 +1227,17 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port, if (taprio->num_entries > VSC9959_TAS_GCL_ENTRY_MAX) return -ERANGE; - /* Set port num and disable ALWAYS_GUARD_BAND_SCH_Q, which means set - * guard band to be implemented for nonschedule queues to schedule - * queues transition. + /* Enable guard band. The switch will schedule frames without taking + * their length into account. Thus we'll always need to enable the + * guard band which reserves the time of a maximum sized frame at the + * end of the time window. + * + * Although the ALWAYS_GUARD_BAND_SCH_Q bit is global for all ports, we + * need to set PORT_NUM, because subsequent writes to PARAM_CFG_REG_n + * operate on the port number. */ - ocelot_rmw(ocelot, - QSYS_TAS_PARAM_CFG_CTRL_PORT_NUM(port), + ocelot_rmw(ocelot, QSYS_TAS_PARAM_CFG_CTRL_PORT_NUM(port) | + QSYS_TAS_PARAM_CFG_CTRL_ALWAYS_GUARD_BAND_SCH_Q, QSYS_TAS_PARAM_CFG_CTRL_PORT_NUM_M | QSYS_TAS_PARAM_CFG_CTRL_ALWAYS_GUARD_BAND_SCH_Q, QSYS_TAS_PARAM_CFG_CTRL); diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c index b777d3f37573..12cd04b56803 100644 --- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c +++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c @@ -167,9 +167,10 @@ enum sja1105_hostcmd { SJA1105_HOSTCMD_INVALIDATE = 4, }; +/* Command and entry overlap */ static void -sja1105_vl_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, - enum packing_op op) +sja1105et_vl_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) { const int size = SJA1105_SIZE_DYN_CMD; @@ -179,6 +180,20 @@ sja1105_vl_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, sja1105_packing(buf, &cmd->index, 9, 0, size, op); } +/* Command and entry are separate */ +static void +sja1105pqrs_vl_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1105_SIZE_VL_LOOKUP_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->errors, 30, 30, size, op); + sja1105_packing(p, &cmd->rdwrset, 29, 29, size, op); + sja1105_packing(p, &cmd->index, 9, 0, size, op); +} + static size_t sja1105et_vl_lookup_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -641,7 +656,7 @@ static size_t sja1105pqrs_cbs_entry_packing(void *buf, void *entry_ptr, const struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = { [BLK_IDX_VL_LOOKUP] = { .entry_packing = sja1105et_vl_lookup_entry_packing, - .cmd_packing = sja1105_vl_lookup_cmd_packing, + .cmd_packing = sja1105et_vl_lookup_cmd_packing, .access = OP_WRITE, .max_entry_count = SJA1105_MAX_VL_LOOKUP_COUNT, .packed_size = SJA1105ET_SIZE_VL_LOOKUP_DYN_CMD, @@ -725,7 +740,7 @@ const struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = { const struct sja1105_dynamic_table_ops sja1105pqrs_dyn_ops[BLK_IDX_MAX_DYN] = { [BLK_IDX_VL_LOOKUP] = { .entry_packing = sja1105_vl_lookup_entry_packing, - .cmd_packing = sja1105_vl_lookup_cmd_packing, + .cmd_packing = sja1105pqrs_vl_lookup_cmd_packing, .access = (OP_READ | OP_WRITE), .max_entry_count = SJA1105_MAX_VL_LOOKUP_COUNT, .packed_size = SJA1105PQRS_SIZE_VL_LOOKUP_DYN_CMD, diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 405024b637d6..b88d9ef45a1f 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -26,6 +26,7 @@ #include "sja1105_tas.h" #define SJA1105_UNKNOWN_MULTICAST 0x010000000000ull +#define SJA1105_DEFAULT_VLAN (VLAN_N_VID - 1) static const struct dsa_switch_ops sja1105_switch_ops; @@ -207,6 +208,7 @@ static int sja1105_init_mii_settings(struct sja1105_private *priv, default: dev_err(dev, "Unsupported PHY mode %s!\n", phy_modes(ports[i].phy_mode)); + return -EINVAL; } /* Even though the SerDes port is able to drive SGMII autoneg @@ -321,6 +323,13 @@ static int sja1105_init_l2_lookup_params(struct sja1105_private *priv) return 0; } +/* Set up a default VLAN for untagged traffic injected from the CPU + * using management routes (e.g. STP, PTP) as opposed to tag_8021q. + * All DT-defined ports are members of this VLAN, and there are no + * restrictions on forwarding (since the CPU selects the destination). + * Frames from this VLAN will always be transmitted as untagged, and + * neither the bridge nor the 8021q module cannot create this VLAN ID. + */ static int sja1105_init_static_vlan(struct sja1105_private *priv) { struct sja1105_table *table; @@ -330,17 +339,13 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv) .vmemb_port = 0, .vlan_bc = 0, .tag_port = 0, - .vlanid = 1, + .vlanid = SJA1105_DEFAULT_VLAN, }; struct dsa_switch *ds = priv->ds; int port; table = &priv->static_config.tables[BLK_IDX_VLAN_LOOKUP]; - /* The static VLAN table will only contain the initial pvid of 1. - * All other VLANs are to be configured through dynamic entries, - * and kept in the static configuration table as backing memory. - */ if (table->entry_count) { kfree(table->entries); table->entry_count = 0; @@ -353,9 +358,6 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv) table->entry_count = 1; - /* VLAN 1: all DT-defined ports are members; no restrictions on - * forwarding; always transmit as untagged. - */ for (port = 0; port < ds->num_ports; port++) { struct sja1105_bridge_vlan *v; @@ -366,15 +368,12 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv) pvid.vlan_bc |= BIT(port); pvid.tag_port &= ~BIT(port); - /* Let traffic that don't need dsa_8021q (e.g. STP, PTP) be - * transmitted as untagged. - */ v = kzalloc(sizeof(*v), GFP_KERNEL); if (!v) return -ENOMEM; v->port = port; - v->vid = 1; + v->vid = SJA1105_DEFAULT_VLAN; v->untagged = true; if (dsa_is_cpu_port(ds, port)) v->pvid = true; @@ -2817,11 +2816,22 @@ static int sja1105_vlan_add_one(struct dsa_switch *ds, int port, u16 vid, bool pvid = flags & BRIDGE_VLAN_INFO_PVID; struct sja1105_bridge_vlan *v; - list_for_each_entry(v, vlan_list, list) - if (v->port == port && v->vid == vid && - v->untagged == untagged && v->pvid == pvid) + list_for_each_entry(v, vlan_list, list) { + if (v->port == port && v->vid == vid) { /* Already added */ - return 0; + if (v->untagged == untagged && v->pvid == pvid) + /* Nothing changed */ + return 0; + + /* It's the same VLAN, but some of the flags changed + * and the user did not bother to delete it first. + * Update it and trigger sja1105_build_vlan_table. + */ + v->untagged = untagged; + v->pvid = pvid; + return 1; + } + } v = kzalloc(sizeof(*v), GFP_KERNEL); if (!v) { @@ -2976,13 +2986,13 @@ static int sja1105_setup(struct dsa_switch *ds) rc = sja1105_static_config_load(priv, ports); if (rc < 0) { dev_err(ds->dev, "Failed to load static config: %d\n", rc); - return rc; + goto out_ptp_clock_unregister; } /* Configure the CGU (PHY link modes and speeds) */ rc = sja1105_clocking_setup(priv); if (rc < 0) { dev_err(ds->dev, "Failed to configure MII clocking: %d\n", rc); - return rc; + goto out_static_config_free; } /* On SJA1105, VLAN filtering per se is always enabled in hardware. * The only thing we can do to disable it is lie about what the 802.1Q @@ -3003,7 +3013,7 @@ static int sja1105_setup(struct dsa_switch *ds) rc = sja1105_devlink_setup(ds); if (rc < 0) - return rc; + goto out_static_config_free; /* The DSA/switchdev model brings up switch ports in standalone mode by * default, and that means vlan_filtering is 0 since they're not under @@ -3012,6 +3022,17 @@ static int sja1105_setup(struct dsa_switch *ds) rtnl_lock(); rc = sja1105_setup_8021q_tagging(ds, true); rtnl_unlock(); + if (rc) + goto out_devlink_teardown; + + return 0; + +out_devlink_teardown: + sja1105_devlink_teardown(ds); +out_ptp_clock_unregister: + sja1105_ptp_clock_unregister(ds); +out_static_config_free: + sja1105_static_config_free(&priv->static_config); return rc; } @@ -3646,8 +3667,10 @@ static int sja1105_probe(struct spi_device *spi) priv->cbs = devm_kcalloc(dev, priv->info->num_cbs_shapers, sizeof(struct sja1105_cbs_entry), GFP_KERNEL); - if (!priv->cbs) - return -ENOMEM; + if (!priv->cbs) { + rc = -ENOMEM; + goto out_unregister_switch; + } } /* Connections between dsa_port and sja1105_port */ @@ -3672,7 +3695,7 @@ static int sja1105_probe(struct spi_device *spi) dev_err(ds->dev, "failed to create deferred xmit thread: %d\n", rc); - goto out; + goto out_destroy_workers; } skb_queue_head_init(&sp->xmit_queue); sp->xmit_tpid = ETH_P_SJA1105; @@ -3682,7 +3705,8 @@ static int sja1105_probe(struct spi_device *spi) } return 0; -out: + +out_destroy_workers: while (port-- > 0) { struct sja1105_port *sp = &priv->ports[port]; @@ -3691,6 +3715,10 @@ out: kthread_destroy_worker(sp->xmit_worker); } + +out_unregister_switch: + dsa_unregister_switch(ds); + return rc; } diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index c0986096c701..5bace8a93d73 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -8247,9 +8247,9 @@ bnx2_init_board(struct pci_dev *pdev, struct net_device *dev) BNX2_WR(bp, PCI_COMMAND, reg); } else if ((BNX2_CHIP_ID(bp) == BNX2_CHIP_ID_5706_A1) && !(bp->flags & BNX2_FLAG_PCIX)) { - dev_err(&pdev->dev, "5706 A1 can only be used in a PCIX bus, aborting\n"); + rc = -EPERM; goto err_out_unmap; } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index d21f085044cd..27943b0446c2 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -1223,8 +1223,10 @@ int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param, goto failed; /* SR-IOV capability was enabled but there are no VFs*/ - if (iov->total == 0) + if (iov->total == 0) { + err = -EINVAL; goto failed; + } iov->nr_virtfn = min_t(u16, iov->total, num_vfs_param); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 2985844634c8..fcc729d52b17 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -282,7 +282,8 @@ static bool bnxt_vf_pciid(enum board_idx idx) { return (idx == NETXTREME_C_VF || idx == NETXTREME_E_VF || idx == NETXTREME_S_VF || idx == NETXTREME_C_VF_HV || - idx == NETXTREME_E_VF_HV || idx == NETXTREME_E_P5_VF); + idx == NETXTREME_E_VF_HV || idx == NETXTREME_E_P5_VF || + idx == NETXTREME_E_P5_VF_HV); } #define DB_CP_REARM_FLAGS (DB_KEY_CP | DB_IDX_VALID) @@ -6932,17 +6933,10 @@ ctx_err: static void bnxt_hwrm_set_pg_attr(struct bnxt_ring_mem_info *rmem, u8 *pg_attr, __le64 *pg_dir) { - u8 pg_size = 0; - if (!rmem->nr_pages) return; - if (BNXT_PAGE_SHIFT == 13) - pg_size = 1 << 4; - else if (BNXT_PAGE_SIZE == 16) - pg_size = 2 << 4; - - *pg_attr = pg_size; + BNXT_SET_CTX_PAGE_ATTR(*pg_attr); if (rmem->depth >= 1) { if (rmem->depth == 2) *pg_attr |= 2; @@ -10785,37 +10779,125 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features) return rc; } +static bool bnxt_exthdr_check(struct bnxt *bp, struct sk_buff *skb, int nw_off, + u8 **nextp) +{ + struct ipv6hdr *ip6h = (struct ipv6hdr *)(skb->data + nw_off); + int hdr_count = 0; + u8 *nexthdr; + int start; + + /* Check that there are at most 2 IPv6 extension headers, no + * fragment header, and each is <= 64 bytes. + */ + start = nw_off + sizeof(*ip6h); + nexthdr = &ip6h->nexthdr; + while (ipv6_ext_hdr(*nexthdr)) { + struct ipv6_opt_hdr *hp; + int hdrlen; + + if (hdr_count >= 3 || *nexthdr == NEXTHDR_NONE || + *nexthdr == NEXTHDR_FRAGMENT) + return false; + hp = __skb_header_pointer(NULL, start, sizeof(*hp), skb->data, + skb_headlen(skb), NULL); + if (!hp) + return false; + if (*nexthdr == NEXTHDR_AUTH) + hdrlen = ipv6_authlen(hp); + else + hdrlen = ipv6_optlen(hp); + + if (hdrlen > 64) + return false; + nexthdr = &hp->nexthdr; + start += hdrlen; + hdr_count++; + } + if (nextp) { + /* Caller will check inner protocol */ + if (skb->encapsulation) { + *nextp = nexthdr; + return true; + } + *nextp = NULL; + } + /* Only support TCP/UDP for non-tunneled ipv6 and inner ipv6 */ + return *nexthdr == IPPROTO_TCP || *nexthdr == IPPROTO_UDP; +} + +/* For UDP, we can only handle 1 Vxlan port and 1 Geneve port. */ +static bool bnxt_udp_tunl_check(struct bnxt *bp, struct sk_buff *skb) +{ + struct udphdr *uh = udp_hdr(skb); + __be16 udp_port = uh->dest; + + if (udp_port != bp->vxlan_port && udp_port != bp->nge_port) + return false; + if (skb->inner_protocol_type == ENCAP_TYPE_ETHER) { + struct ethhdr *eh = inner_eth_hdr(skb); + + switch (eh->h_proto) { + case htons(ETH_P_IP): + return true; + case htons(ETH_P_IPV6): + return bnxt_exthdr_check(bp, skb, + skb_inner_network_offset(skb), + NULL); + } + } + return false; +} + +static bool bnxt_tunl_check(struct bnxt *bp, struct sk_buff *skb, u8 l4_proto) +{ + switch (l4_proto) { + case IPPROTO_UDP: + return bnxt_udp_tunl_check(bp, skb); + case IPPROTO_IPIP: + return true; + case IPPROTO_GRE: { + switch (skb->inner_protocol) { + default: + return false; + case htons(ETH_P_IP): + return true; + case htons(ETH_P_IPV6): + fallthrough; + } + } + case IPPROTO_IPV6: + /* Check ext headers of inner ipv6 */ + return bnxt_exthdr_check(bp, skb, skb_inner_network_offset(skb), + NULL); + } + return false; +} + static netdev_features_t bnxt_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { - struct bnxt *bp; - __be16 udp_port; - u8 l4_proto = 0; + struct bnxt *bp = netdev_priv(dev); + u8 *l4_proto; features = vlan_features_check(skb, features); - if (!skb->encapsulation) - return features; - switch (vlan_get_protocol(skb)) { case htons(ETH_P_IP): - l4_proto = ip_hdr(skb)->protocol; + if (!skb->encapsulation) + return features; + l4_proto = &ip_hdr(skb)->protocol; + if (bnxt_tunl_check(bp, skb, *l4_proto)) + return features; break; case htons(ETH_P_IPV6): - l4_proto = ipv6_hdr(skb)->nexthdr; + if (!bnxt_exthdr_check(bp, skb, skb_network_offset(skb), + &l4_proto)) + break; + if (!l4_proto || bnxt_tunl_check(bp, skb, *l4_proto)) + return features; break; - default: - return features; } - - if (l4_proto != IPPROTO_UDP) - return features; - - bp = netdev_priv(dev); - /* For UDP, we can only handle 1 Vxlan port and 1 Geneve port. */ - udp_port = udp_hdr(skb)->dest; - if (udp_port == bp->vxlan_port || udp_port == bp->nge_port) - return features; return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 98e0cef4532c..30e47ea343f9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1457,6 +1457,16 @@ struct bnxt_ctx_pg_info { #define BNXT_BACKING_STORE_CFG_LEGACY_LEN 256 +#define BNXT_SET_CTX_PAGE_ATTR(attr) \ +do { \ + if (BNXT_PAGE_SIZE == 0x2000) \ + attr = FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8K; \ + else if (BNXT_PAGE_SIZE == 0x10000) \ + attr = FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_64K; \ + else \ + attr = FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_4K; \ +} while (0) + struct bnxt_ctx_mem_info { u32 qp_max_entries; u16 qp_min_qp1_entries; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 6bc7d41d519b..a0c7b1167dbb 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -2867,6 +2867,9 @@ static struct net_device_stats *gem_get_stats(struct macb *bp) struct gem_stats *hwstat = &bp->hw_stats.gem; struct net_device_stats *nstat = &bp->dev->stats; + if (!netif_running(bp->dev)) + return nstat; + gem_update_stats(bp); nstat->rx_errors = (hwstat->rx_frame_check_sequence_errors + diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index bc581b149b11..22c9ac922eba 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -1042,7 +1042,7 @@ void clear_all_filters(struct adapter *adapter) cxgb4_del_filter(dev, f->tid, &f->fs); } - sb = t4_read_reg(adapter, LE_DB_SRVR_START_INDEX_A); + sb = adapter->tids.stid_base; for (i = 0; i < sb; i++) { f = (struct filter_entry *)adapter->tids.tid_tab[i]; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 6264bc66a4fc..421bd9b88028 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -6480,9 +6480,9 @@ static void cxgb4_ktls_dev_del(struct net_device *netdev, adap->uld[CXGB4_ULD_KTLS].tlsdev_ops->tls_dev_del(netdev, tls_ctx, direction); - cxgb4_set_ktls_feature(adap, FW_PARAMS_PARAM_DEV_KTLS_HW_DISABLE); out_unlock: + cxgb4_set_ktls_feature(adap, FW_PARAMS_PARAM_DEV_KTLS_HW_DISABLE); mutex_unlock(&uld_mutex); } diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c index ef3f1e92632f..59683f79959c 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c @@ -59,6 +59,7 @@ static int chcr_get_nfrags_to_send(struct sk_buff *skb, u32 start, u32 len) } static int chcr_init_tcb_fields(struct chcr_ktls_info *tx_info); +static void clear_conn_resources(struct chcr_ktls_info *tx_info); /* * chcr_ktls_save_keys: calculate and save crypto keys. * @tx_info - driver specific tls info. @@ -364,10 +365,14 @@ static void chcr_ktls_dev_del(struct net_device *netdev, chcr_get_ktls_tx_context(tls_ctx); struct chcr_ktls_info *tx_info = tx_ctx->chcr_info; struct ch_ktls_port_stats_debug *port_stats; + struct chcr_ktls_uld_ctx *u_ctx; if (!tx_info) return; + u_ctx = tx_info->adap->uld[CXGB4_ULD_KTLS].handle; + if (u_ctx && u_ctx->detach) + return; /* clear l2t entry */ if (tx_info->l2te) cxgb4_l2t_release(tx_info->l2te); @@ -384,6 +389,8 @@ static void chcr_ktls_dev_del(struct net_device *netdev, if (tx_info->tid != -1) { cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan, tx_info->tid, tx_info->ip_family); + + xa_erase(&u_ctx->tid_list, tx_info->tid); } port_stats = &tx_info->adap->ch_ktls_stats.ktls_port[tx_info->port_id]; @@ -411,6 +418,7 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk, struct tls_context *tls_ctx = tls_get_ctx(sk); struct ch_ktls_port_stats_debug *port_stats; struct chcr_ktls_ofld_ctx_tx *tx_ctx; + struct chcr_ktls_uld_ctx *u_ctx; struct chcr_ktls_info *tx_info; struct dst_entry *dst; struct adapter *adap; @@ -425,6 +433,7 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk, adap = pi->adapter; port_stats = &adap->ch_ktls_stats.ktls_port[pi->port_id]; atomic64_inc(&port_stats->ktls_tx_connection_open); + u_ctx = adap->uld[CXGB4_ULD_KTLS].handle; if (direction == TLS_OFFLOAD_CTX_DIR_RX) { pr_err("not expecting for RX direction\n"); @@ -434,6 +443,9 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk, if (tx_ctx->chcr_info) goto out; + if (u_ctx && u_ctx->detach) + goto out; + tx_info = kvzalloc(sizeof(*tx_info), GFP_KERNEL); if (!tx_info) goto out; @@ -569,6 +581,8 @@ free_tid: cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan, tx_info->tid, tx_info->ip_family); + xa_erase(&u_ctx->tid_list, tx_info->tid); + put_module: /* release module refcount */ module_put(THIS_MODULE); @@ -633,8 +647,12 @@ static int chcr_ktls_cpl_act_open_rpl(struct adapter *adap, { const struct cpl_act_open_rpl *p = (void *)input; struct chcr_ktls_info *tx_info = NULL; + struct chcr_ktls_ofld_ctx_tx *tx_ctx; + struct chcr_ktls_uld_ctx *u_ctx; unsigned int atid, tid, status; + struct tls_context *tls_ctx; struct tid_info *t; + int ret = 0; tid = GET_TID(p); status = AOPEN_STATUS_G(ntohl(p->atid_status)); @@ -666,14 +684,29 @@ static int chcr_ktls_cpl_act_open_rpl(struct adapter *adap, if (!status) { tx_info->tid = tid; cxgb4_insert_tid(t, tx_info, tx_info->tid, tx_info->ip_family); + /* Adding tid */ + tls_ctx = tls_get_ctx(tx_info->sk); + tx_ctx = chcr_get_ktls_tx_context(tls_ctx); + u_ctx = adap->uld[CXGB4_ULD_KTLS].handle; + if (u_ctx) { + ret = xa_insert_bh(&u_ctx->tid_list, tid, tx_ctx, + GFP_NOWAIT); + if (ret < 0) { + pr_err("%s: Failed to allocate tid XA entry = %d\n", + __func__, tx_info->tid); + tx_info->open_state = CH_KTLS_OPEN_FAILURE; + goto out; + } + } tx_info->open_state = CH_KTLS_OPEN_SUCCESS; } else { tx_info->open_state = CH_KTLS_OPEN_FAILURE; } +out: spin_unlock(&tx_info->lock); complete(&tx_info->completion); - return 0; + return ret; } /* @@ -2090,6 +2123,8 @@ static void *chcr_ktls_uld_add(const struct cxgb4_lld_info *lldi) goto out; } u_ctx->lldi = *lldi; + u_ctx->detach = false; + xa_init_flags(&u_ctx->tid_list, XA_FLAGS_LOCK_BH); out: return u_ctx; } @@ -2123,6 +2158,45 @@ static int chcr_ktls_uld_rx_handler(void *handle, const __be64 *rsp, return 0; } +static void clear_conn_resources(struct chcr_ktls_info *tx_info) +{ + /* clear l2t entry */ + if (tx_info->l2te) + cxgb4_l2t_release(tx_info->l2te); + +#if IS_ENABLED(CONFIG_IPV6) + /* clear clip entry */ + if (tx_info->ip_family == AF_INET6) + cxgb4_clip_release(tx_info->netdev, (const u32 *) + &tx_info->sk->sk_v6_rcv_saddr, + 1); +#endif + + /* clear tid */ + if (tx_info->tid != -1) + cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan, + tx_info->tid, tx_info->ip_family); +} + +static void ch_ktls_reset_all_conn(struct chcr_ktls_uld_ctx *u_ctx) +{ + struct ch_ktls_port_stats_debug *port_stats; + struct chcr_ktls_ofld_ctx_tx *tx_ctx; + struct chcr_ktls_info *tx_info; + unsigned long index; + + xa_for_each(&u_ctx->tid_list, index, tx_ctx) { + tx_info = tx_ctx->chcr_info; + clear_conn_resources(tx_info); + port_stats = &tx_info->adap->ch_ktls_stats.ktls_port[tx_info->port_id]; + atomic64_inc(&port_stats->ktls_tx_connection_close); + kvfree(tx_info); + tx_ctx->chcr_info = NULL; + /* release module refcount */ + module_put(THIS_MODULE); + } +} + static int chcr_ktls_uld_state_change(void *handle, enum cxgb4_state new_state) { struct chcr_ktls_uld_ctx *u_ctx = handle; @@ -2139,7 +2213,10 @@ static int chcr_ktls_uld_state_change(void *handle, enum cxgb4_state new_state) case CXGB4_STATE_DETACH: pr_info("%s: Down\n", pci_name(u_ctx->lldi.pdev)); mutex_lock(&dev_mutex); + u_ctx->detach = true; list_del(&u_ctx->entry); + ch_ktls_reset_all_conn(u_ctx); + xa_destroy(&u_ctx->tid_list); mutex_unlock(&dev_mutex); break; default: @@ -2178,6 +2255,7 @@ static void __exit chcr_ktls_exit(void) adap = pci_get_drvdata(u_ctx->lldi.pdev); memset(&adap->ch_ktls_stats, 0, sizeof(adap->ch_ktls_stats)); list_del(&u_ctx->entry); + xa_destroy(&u_ctx->tid_list); kfree(u_ctx); } mutex_unlock(&dev_mutex); diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h index 18b3b1f02415..10572dc55365 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h @@ -75,6 +75,8 @@ struct chcr_ktls_ofld_ctx_tx { struct chcr_ktls_uld_ctx { struct list_head entry; struct cxgb4_lld_info lldi; + struct xarray tid_list; + bool detach; }; static inline struct chcr_ktls_ofld_ctx_tx * diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c index 188d871f6b8c..c320cc8ca68d 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c @@ -1564,8 +1564,10 @@ found_ok_skb: cerr = put_cmsg(msg, SOL_TLS, TLS_GET_RECORD_TYPE, sizeof(thdr->type), &thdr->type); - if (cerr && thdr->type != TLS_RECORD_TYPE_DATA) - return -EIO; + if (cerr && thdr->type != TLS_RECORD_TYPE_DATA) { + copied = -EIO; + break; + } /* don't send tls header, skip copy */ goto skip_copy; } diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index f2065f9d02e6..ad82cffc6f3f 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1662,7 +1662,7 @@ static int fec_enet_rx_napi(struct napi_struct *napi, int budget) } /* ------------------------------------------------------------------------- */ -static void fec_get_mac(struct net_device *ndev) +static int fec_get_mac(struct net_device *ndev) { struct fec_enet_private *fep = netdev_priv(ndev); unsigned char *iap, tmpaddr[ETH_ALEN]; @@ -1685,6 +1685,8 @@ static void fec_get_mac(struct net_device *ndev) ret = of_get_mac_address(np, tmpaddr); if (!ret) iap = tmpaddr; + else if (ret == -EPROBE_DEFER) + return ret; } } @@ -1723,7 +1725,7 @@ static void fec_get_mac(struct net_device *ndev) eth_hw_addr_random(ndev); dev_info(&fep->pdev->dev, "Using random MAC address: %pM\n", ndev->dev_addr); - return; + return 0; } memcpy(ndev->dev_addr, iap, ETH_ALEN); @@ -1731,6 +1733,8 @@ static void fec_get_mac(struct net_device *ndev) /* Adjust MAC if using macaddr */ if (iap == macaddr) ndev->dev_addr[ETH_ALEN-1] = macaddr[ETH_ALEN-1] + fep->dev_id; + + return 0; } /* ------------------------------------------------------------------------- */ @@ -3290,7 +3294,9 @@ static int fec_enet_init(struct net_device *ndev) return ret; } - fec_enet_alloc_queue(ndev); + ret = fec_enet_alloc_queue(ndev); + if (ret) + return ret; bd_size = (fep->total_tx_ring_size + fep->total_rx_ring_size) * dsize; @@ -3298,11 +3304,15 @@ static int fec_enet_init(struct net_device *ndev) cbd_base = dmam_alloc_coherent(&fep->pdev->dev, bd_size, &bd_dma, GFP_KERNEL); if (!cbd_base) { - return -ENOMEM; + ret = -ENOMEM; + goto free_queue_mem; } /* Get the Ethernet address */ - fec_get_mac(ndev); + ret = fec_get_mac(ndev); + if (ret) + goto free_queue_mem; + /* make sure MAC we just acquired is programmed into the hw */ fec_set_mac_address(ndev, NULL); @@ -3376,6 +3386,10 @@ static int fec_enet_init(struct net_device *ndev) fec_enet_update_ethtool_stats(ndev); return 0; + +free_queue_mem: + fec_enet_free_queue(ndev); + return ret; } #ifdef CONFIG_OF diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 7302498c6df3..bbc423e93122 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -180,7 +180,7 @@ static int gve_napi_poll(struct napi_struct *napi, int budget) /* Double check we have no extra work. * Ensure unmask synchronizes with checking for work. */ - dma_rmb(); + mb(); if (block->tx) reschedule |= gve_tx_poll(block, -1); if (block->rx) @@ -220,6 +220,7 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv) int vecs_left = new_num_ntfy_blks % 2; priv->num_ntfy_blks = new_num_ntfy_blks; + priv->mgmt_msix_idx = priv->num_ntfy_blks; priv->tx_cfg.max_queues = min_t(int, priv->tx_cfg.max_queues, vecs_per_type); priv->rx_cfg.max_queues = min_t(int, priv->rx_cfg.max_queues, @@ -300,20 +301,22 @@ static void gve_free_notify_blocks(struct gve_priv *priv) { int i; - /* Free the irqs */ - for (i = 0; i < priv->num_ntfy_blks; i++) { - struct gve_notify_block *block = &priv->ntfy_blocks[i]; - int msix_idx = i; + if (priv->msix_vectors) { + /* Free the irqs */ + for (i = 0; i < priv->num_ntfy_blks; i++) { + struct gve_notify_block *block = &priv->ntfy_blocks[i]; + int msix_idx = i; - irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector, - NULL); - free_irq(priv->msix_vectors[msix_idx].vector, block); + irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector, + NULL); + free_irq(priv->msix_vectors[msix_idx].vector, block); + } + free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv); } dma_free_coherent(&priv->pdev->dev, priv->num_ntfy_blks * sizeof(*priv->ntfy_blocks), priv->ntfy_blocks, priv->ntfy_block_bus); priv->ntfy_blocks = NULL; - free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv); pci_disable_msix(priv->pdev); kvfree(priv->msix_vectors); priv->msix_vectors = NULL; diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index 6938f3a939d6..3e04a3973d68 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -212,10 +212,11 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx) tx->dev = &priv->pdev->dev; if (!tx->raw_addressing) { tx->tx_fifo.qpl = gve_assign_tx_qpl(priv); - + if (!tx->tx_fifo.qpl) + goto abort_with_desc; /* map Tx FIFO */ if (gve_tx_fifo_init(priv, &tx->tx_fifo)) - goto abort_with_desc; + goto abort_with_qpl; } tx->q_resources = @@ -236,6 +237,9 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx) abort_with_fifo: if (!tx->raw_addressing) gve_tx_fifo_release(priv, &tx->tx_fifo); +abort_with_qpl: + if (!tx->raw_addressing) + gve_unassign_qpl(priv, tx->tx_fifo.qpl->id); abort_with_desc: dma_free_coherent(hdev, bytes, tx->desc, tx->bus); tx->desc = NULL; @@ -589,7 +593,7 @@ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev) struct gve_tx_ring *tx; int nsegs; - WARN(skb_get_queue_mapping(skb) > priv->tx_cfg.num_queues, + WARN(skb_get_queue_mapping(skb) >= priv->tx_cfg.num_queues, "skb queue index out of range"); tx = &priv->tx[skb_get_queue_mapping(skb)]; if (unlikely(gve_maybe_stop_tx(tx, skb))) { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index da48c05435ea..7e62dcff2426 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -192,7 +192,7 @@ static int hns_nic_get_link_ksettings(struct net_device *net_dev, } /** - *hns_nic_set_link_settings - implement ethtool set link ksettings + *hns_nic_set_link_ksettings - implement ethtool set link ksettings *@net_dev: net_device *@cmd: ethtool_link_ksettings *retuen 0 - success , negative --fail @@ -827,7 +827,7 @@ hns_get_channels(struct net_device *net_dev, struct ethtool_channels *ch) } /** - * get_ethtool_stats - get detail statistics. + * hns_get_ethtool_stats - get detail statistics. * @netdev: net device * @stats: statistics info. * @data: statistics data. @@ -885,7 +885,7 @@ static void hns_get_ethtool_stats(struct net_device *netdev, } /** - * get_strings: Return a set of strings that describe the requested objects + * hns_get_strings: Return a set of strings that describe the requested objects * @netdev: net device * @stringset: string set ID. * @data: objects data. diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 783fdaf8f8d6..026558f8e04b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -264,22 +264,17 @@ static void hns3_vector_coalesce_init(struct hns3_enet_tqp_vector *tqp_vector, struct hnae3_ae_dev *ae_dev = pci_get_drvdata(priv->ae_handle->pdev); struct hns3_enet_coalesce *tx_coal = &tqp_vector->tx_group.coal; struct hns3_enet_coalesce *rx_coal = &tqp_vector->rx_group.coal; + struct hns3_enet_coalesce *ptx_coal = &priv->tx_coal; + struct hns3_enet_coalesce *prx_coal = &priv->rx_coal; - /* initialize the configuration for interrupt coalescing. - * 1. GL (Interrupt Gap Limiter) - * 2. RL (Interrupt Rate Limiter) - * 3. QL (Interrupt Quantity Limiter) - * - * Default: enable interrupt coalescing self-adaptive and GL - */ - tx_coal->adapt_enable = 1; - rx_coal->adapt_enable = 1; + tx_coal->adapt_enable = ptx_coal->adapt_enable; + rx_coal->adapt_enable = prx_coal->adapt_enable; - tx_coal->int_gl = HNS3_INT_GL_50K; - rx_coal->int_gl = HNS3_INT_GL_50K; + tx_coal->int_gl = ptx_coal->int_gl; + rx_coal->int_gl = prx_coal->int_gl; - rx_coal->flow_level = HNS3_FLOW_LOW; - tx_coal->flow_level = HNS3_FLOW_LOW; + rx_coal->flow_level = prx_coal->flow_level; + tx_coal->flow_level = ptx_coal->flow_level; /* device version above V3(include V3), GL can configure 1us * unit, so uses 1us unit. @@ -294,8 +289,8 @@ static void hns3_vector_coalesce_init(struct hns3_enet_tqp_vector *tqp_vector, rx_coal->ql_enable = 1; tx_coal->int_ql_max = ae_dev->dev_specs.int_ql_max; rx_coal->int_ql_max = ae_dev->dev_specs.int_ql_max; - tx_coal->int_ql = HNS3_INT_QL_DEFAULT_CFG; - rx_coal->int_ql = HNS3_INT_QL_DEFAULT_CFG; + tx_coal->int_ql = ptx_coal->int_ql; + rx_coal->int_ql = prx_coal->int_ql; } } @@ -846,8 +841,6 @@ static bool hns3_tunnel_csum_bug(struct sk_buff *skb) l4.udp->dest == htons(4790)))) return false; - skb_checksum_help(skb); - return true; } @@ -924,8 +917,7 @@ static int hns3_set_l2l3l4(struct sk_buff *skb, u8 ol4_proto, /* the stack computes the IP header already, * driver calculate l4 checksum when not TSO. */ - skb_checksum_help(skb); - return 0; + return skb_checksum_help(skb); } hns3_set_outer_l2l3l4(skb, ol4_proto, ol_type_vlan_len_msec); @@ -970,7 +962,7 @@ static int hns3_set_l2l3l4(struct sk_buff *skb, u8 ol4_proto, break; case IPPROTO_UDP: if (hns3_tunnel_csum_bug(skb)) - break; + return skb_checksum_help(skb); hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1); hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4T_S, @@ -995,8 +987,7 @@ static int hns3_set_l2l3l4(struct sk_buff *skb, u8 ol4_proto, /* the stack computes the IP header already, * driver calculate l4 checksum when not TSO. */ - skb_checksum_help(skb); - return 0; + return skb_checksum_help(skb); } return 0; @@ -3844,6 +3835,34 @@ map_ring_fail: return ret; } +static void hns3_nic_init_coal_cfg(struct hns3_nic_priv *priv) +{ + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(priv->ae_handle->pdev); + struct hns3_enet_coalesce *tx_coal = &priv->tx_coal; + struct hns3_enet_coalesce *rx_coal = &priv->rx_coal; + + /* initialize the configuration for interrupt coalescing. + * 1. GL (Interrupt Gap Limiter) + * 2. RL (Interrupt Rate Limiter) + * 3. QL (Interrupt Quantity Limiter) + * + * Default: enable interrupt coalescing self-adaptive and GL + */ + tx_coal->adapt_enable = 1; + rx_coal->adapt_enable = 1; + + tx_coal->int_gl = HNS3_INT_GL_50K; + rx_coal->int_gl = HNS3_INT_GL_50K; + + rx_coal->flow_level = HNS3_FLOW_LOW; + tx_coal->flow_level = HNS3_FLOW_LOW; + + if (ae_dev->dev_specs.int_ql_max) { + tx_coal->int_ql = HNS3_INT_QL_DEFAULT_CFG; + rx_coal->int_ql = HNS3_INT_QL_DEFAULT_CFG; + } +} + static int hns3_nic_alloc_vector_data(struct hns3_nic_priv *priv) { struct hnae3_handle *h = priv->ae_handle; @@ -4295,6 +4314,8 @@ static int hns3_client_init(struct hnae3_handle *handle) goto out_get_ring_cfg; } + hns3_nic_init_coal_cfg(priv); + ret = hns3_nic_alloc_vector_data(priv); if (ret) { ret = -ENOMEM; @@ -4317,12 +4338,6 @@ static int hns3_client_init(struct hnae3_handle *handle) if (ret) goto out_init_phy; - ret = register_netdev(netdev); - if (ret) { - dev_err(priv->dev, "probe register netdev fail!\n"); - goto out_reg_netdev_fail; - } - /* the device can work without cpu rmap, only aRFS needs it */ ret = hns3_set_rx_cpu_rmap(netdev); if (ret) @@ -4355,17 +4370,23 @@ static int hns3_client_init(struct hnae3_handle *handle) if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3) set_bit(HNAE3_PFLAG_LIMIT_PROMISC, &handle->supported_pflags); + ret = register_netdev(netdev); + if (ret) { + dev_err(priv->dev, "probe register netdev fail!\n"); + goto out_reg_netdev_fail; + } + if (netif_msg_drv(handle)) hns3_info_show(priv); return ret; +out_reg_netdev_fail: + hns3_dbg_uninit(handle); out_client_start: hns3_free_rx_cpu_rmap(netdev); hns3_nic_uninit_irq(priv); out_init_irq_fail: - unregister_netdev(netdev); -out_reg_netdev_fail: hns3_uninit_phy(netdev); out_init_phy: hns3_uninit_all_ring(priv); @@ -4571,31 +4592,6 @@ int hns3_nic_reset_all_ring(struct hnae3_handle *h) return 0; } -static void hns3_store_coal(struct hns3_nic_priv *priv) -{ - /* ethtool only support setting and querying one coal - * configuration for now, so save the vector 0' coal - * configuration here in order to restore it. - */ - memcpy(&priv->tx_coal, &priv->tqp_vector[0].tx_group.coal, - sizeof(struct hns3_enet_coalesce)); - memcpy(&priv->rx_coal, &priv->tqp_vector[0].rx_group.coal, - sizeof(struct hns3_enet_coalesce)); -} - -static void hns3_restore_coal(struct hns3_nic_priv *priv) -{ - u16 vector_num = priv->vector_num; - int i; - - for (i = 0; i < vector_num; i++) { - memcpy(&priv->tqp_vector[i].tx_group.coal, &priv->tx_coal, - sizeof(struct hns3_enet_coalesce)); - memcpy(&priv->tqp_vector[i].rx_group.coal, &priv->rx_coal, - sizeof(struct hns3_enet_coalesce)); - } -} - static int hns3_reset_notify_down_enet(struct hnae3_handle *handle) { struct hnae3_knic_private_info *kinfo = &handle->kinfo; @@ -4654,8 +4650,6 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle) if (ret) goto err_put_ring; - hns3_restore_coal(priv); - ret = hns3_nic_init_vector_data(priv); if (ret) goto err_dealloc_vector; @@ -4721,8 +4715,6 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle) hns3_nic_uninit_vector_data(priv); - hns3_store_coal(priv); - hns3_nic_dealloc_vector_data(priv); hns3_uninit_all_ring(priv); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index b48faf769b1c..c1ea403d2b56 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -1134,50 +1134,32 @@ static void hns3_get_channels(struct net_device *netdev, h->ae_algo->ops->get_channels(h, ch); } -static int hns3_get_coalesce_per_queue(struct net_device *netdev, u32 queue, - struct ethtool_coalesce *cmd) +static int hns3_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *cmd) { - struct hns3_enet_tqp_vector *tx_vector, *rx_vector; struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hns3_enet_coalesce *tx_coal = &priv->tx_coal; + struct hns3_enet_coalesce *rx_coal = &priv->rx_coal; struct hnae3_handle *h = priv->ae_handle; - u16 queue_num = h->kinfo.num_tqps; if (hns3_nic_resetting(netdev)) return -EBUSY; - if (queue >= queue_num) { - netdev_err(netdev, - "Invalid queue value %u! Queue max id=%u\n", - queue, queue_num - 1); - return -EINVAL; - } - - tx_vector = priv->ring[queue].tqp_vector; - rx_vector = priv->ring[queue_num + queue].tqp_vector; + cmd->use_adaptive_tx_coalesce = tx_coal->adapt_enable; + cmd->use_adaptive_rx_coalesce = rx_coal->adapt_enable; - cmd->use_adaptive_tx_coalesce = - tx_vector->tx_group.coal.adapt_enable; - cmd->use_adaptive_rx_coalesce = - rx_vector->rx_group.coal.adapt_enable; - - cmd->tx_coalesce_usecs = tx_vector->tx_group.coal.int_gl; - cmd->rx_coalesce_usecs = rx_vector->rx_group.coal.int_gl; + cmd->tx_coalesce_usecs = tx_coal->int_gl; + cmd->rx_coalesce_usecs = rx_coal->int_gl; cmd->tx_coalesce_usecs_high = h->kinfo.int_rl_setting; cmd->rx_coalesce_usecs_high = h->kinfo.int_rl_setting; - cmd->tx_max_coalesced_frames = tx_vector->tx_group.coal.int_ql; - cmd->rx_max_coalesced_frames = rx_vector->rx_group.coal.int_ql; + cmd->tx_max_coalesced_frames = tx_coal->int_ql; + cmd->rx_max_coalesced_frames = rx_coal->int_ql; return 0; } -static int hns3_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *cmd) -{ - return hns3_get_coalesce_per_queue(netdev, 0, cmd); -} - static int hns3_check_gl_coalesce_para(struct net_device *netdev, struct ethtool_coalesce *cmd) { @@ -1292,19 +1274,7 @@ static int hns3_check_coalesce_para(struct net_device *netdev, return ret; } - ret = hns3_check_ql_coalesce_param(netdev, cmd); - if (ret) - return ret; - - if (cmd->use_adaptive_tx_coalesce == 1 || - cmd->use_adaptive_rx_coalesce == 1) { - netdev_info(netdev, - "adaptive-tx=%u and adaptive-rx=%u, tx_usecs or rx_usecs will changed dynamically.\n", - cmd->use_adaptive_tx_coalesce, - cmd->use_adaptive_rx_coalesce); - } - - return 0; + return hns3_check_ql_coalesce_param(netdev, cmd); } static void hns3_set_coalesce_per_queue(struct net_device *netdev, @@ -1350,6 +1320,9 @@ static int hns3_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *cmd) { struct hnae3_handle *h = hns3_get_handle(netdev); + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hns3_enet_coalesce *tx_coal = &priv->tx_coal; + struct hns3_enet_coalesce *rx_coal = &priv->rx_coal; u16 queue_num = h->kinfo.num_tqps; int ret; int i; @@ -1364,6 +1337,15 @@ static int hns3_set_coalesce(struct net_device *netdev, h->kinfo.int_rl_setting = hns3_rl_round_down(cmd->rx_coalesce_usecs_high); + tx_coal->adapt_enable = cmd->use_adaptive_tx_coalesce; + rx_coal->adapt_enable = cmd->use_adaptive_rx_coalesce; + + tx_coal->int_gl = cmd->tx_coalesce_usecs; + rx_coal->int_gl = cmd->rx_coalesce_usecs; + + tx_coal->int_ql = cmd->tx_max_coalesced_frames; + rx_coal->int_ql = cmd->rx_max_coalesced_frames; + for (i = 0; i < queue_num; i++) hns3_set_coalesce_per_queue(netdev, cmd, i); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 8e5f9dc8791d..f1c9f4ada348 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -710,7 +710,6 @@ void hclge_mbx_handler(struct hclge_dev *hdev) unsigned int flag; int ret = 0; - memset(&resp_msg, 0, sizeof(resp_msg)); /* handle all the mailbox requests in the queue */ while (!hclge_cmd_crq_empty(&hdev->hw)) { if (test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) { @@ -738,6 +737,9 @@ void hclge_mbx_handler(struct hclge_dev *hdev) trace_hclge_pf_mbx_get(hdev, req); + /* clear the resp_msg before processing every mailbox message */ + memset(&resp_msg, 0, sizeof(resp_msg)); + switch (req->msg.code) { case HCLGE_MBX_MAP_RING_TO_VECTOR: ret = hclge_map_unmap_ring_to_vf_vector(vport, true, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 988db46bff0e..214a38de3f41 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -467,12 +467,16 @@ static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid, return err; } -static s32 ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) +static int ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 max_frame, u32 vf) { struct ixgbe_hw *hw = &adapter->hw; - int max_frame = msgbuf[1]; u32 max_frs; + if (max_frame < ETH_MIN_MTU || max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE) { + e_err(drv, "VF max_frame %d out of range\n", max_frame); + return -EINVAL; + } + /* * For 82599EB we have to keep all PFs and VFs operating with * the same max_frame value in order to avoid sending an oversize @@ -533,12 +537,6 @@ static s32 ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) } } - /* MTU < 68 is an error and causes problems on some kernels */ - if (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE) { - e_err(drv, "VF max_frame %d out of range\n", max_frame); - return -EINVAL; - } - /* pull current max frame size from hardware */ max_frs = IXGBE_READ_REG(hw, IXGBE_MAXFRS); max_frs &= IXGBE_MHADD_MFS_MASK; @@ -1249,7 +1247,7 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) retval = ixgbe_set_vf_vlan_msg(adapter, msgbuf, vf); break; case IXGBE_VF_SET_LPE: - retval = ixgbe_set_vf_lpe(adapter, msgbuf, vf); + retval = ixgbe_set_vf_lpe(adapter, msgbuf[1], vf); break; case IXGBE_VF_SET_MACVLAN: retval = ixgbe_set_vf_macvlan_msg(adapter, msgbuf, vf); diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c index 6f987a7ffcb3..b30a45725374 100644 --- a/drivers/net/ethernet/korina.c +++ b/drivers/net/ethernet/korina.c @@ -1315,23 +1315,23 @@ static int korina_probe(struct platform_device *pdev) lp->tx_irq = platform_get_irq_byname(pdev, "tx"); p = devm_platform_ioremap_resource_byname(pdev, "emac"); - if (!p) { + if (IS_ERR(p)) { printk(KERN_ERR DRV_NAME ": cannot remap registers\n"); - return -ENOMEM; + return PTR_ERR(p); } lp->eth_regs = p; p = devm_platform_ioremap_resource_byname(pdev, "dma_rx"); - if (!p) { + if (IS_ERR(p)) { printk(KERN_ERR DRV_NAME ": cannot remap Rx DMA registers\n"); - return -ENOMEM; + return PTR_ERR(p); } lp->rx_dma_regs = p; p = devm_platform_ioremap_resource_byname(pdev, "dma_tx"); - if (!p) { + if (IS_ERR(p)) { printk(KERN_ERR DRV_NAME ": cannot remap Tx DMA registers\n"); - return -ENOMEM; + return PTR_ERR(p); } lp->tx_dma_regs = p; diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index 41c2ad210bc9..36dc3e5f6218 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -154,6 +154,7 @@ static int xrx200_close(struct net_device *net_dev) static int xrx200_alloc_skb(struct xrx200_chan *ch) { + dma_addr_t mapping; int ret = 0; ch->skb[ch->dma.desc] = netdev_alloc_skb_ip_align(ch->priv->net_dev, @@ -163,16 +164,17 @@ static int xrx200_alloc_skb(struct xrx200_chan *ch) goto skip; } - ch->dma.desc_base[ch->dma.desc].addr = dma_map_single(ch->priv->dev, - ch->skb[ch->dma.desc]->data, XRX200_DMA_DATA_LEN, - DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(ch->priv->dev, - ch->dma.desc_base[ch->dma.desc].addr))) { + mapping = dma_map_single(ch->priv->dev, ch->skb[ch->dma.desc]->data, + XRX200_DMA_DATA_LEN, DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(ch->priv->dev, mapping))) { dev_kfree_skb_any(ch->skb[ch->dma.desc]); ret = -ENOMEM; goto skip; } + ch->dma.desc_base[ch->dma.desc].addr = mapping; + /* Make sure the address is written before we give it to HW */ + wmb(); skip: ch->dma.desc_base[ch->dma.desc].ctl = LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) | @@ -196,6 +198,8 @@ static int xrx200_hw_receive(struct xrx200_chan *ch) ch->dma.desc %= LTQ_DESC_NUM; if (ret) { + ch->skb[ch->dma.desc] = skb; + net_dev->stats.rx_dropped++; netdev_err(net_dev, "failed to allocate new rx buffer\n"); return ret; } diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index 8edba5ea90f0..4a61c90003b5 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -993,6 +993,14 @@ enum mvpp22_ptp_packet_format { #define MVPP2_DESC_DMA_MASK DMA_BIT_MASK(40) +/* Buffer header info bits */ +#define MVPP2_B_HDR_INFO_MC_ID_MASK 0xfff +#define MVPP2_B_HDR_INFO_MC_ID(info) ((info) & MVPP2_B_HDR_INFO_MC_ID_MASK) +#define MVPP2_B_HDR_INFO_LAST_OFFS 12 +#define MVPP2_B_HDR_INFO_LAST_MASK BIT(12) +#define MVPP2_B_HDR_INFO_IS_LAST(info) \ + (((info) & MVPP2_B_HDR_INFO_LAST_MASK) >> MVPP2_B_HDR_INFO_LAST_OFFS) + struct mvpp2_tai; /* Definitions */ @@ -1002,6 +1010,20 @@ struct mvpp2_rss_table { u32 indir[MVPP22_RSS_TABLE_ENTRIES]; }; +struct mvpp2_buff_hdr { + __le32 next_phys_addr; + __le32 next_dma_addr; + __le16 byte_count; + __le16 info; + __le16 reserved1; /* bm_qset (for future use, BM) */ + u8 next_phys_addr_high; + u8 next_dma_addr_high; + __le16 reserved2; + __le16 reserved3; + __le16 reserved4; + __le16 reserved5; +}; + /* Shared Packet Processor resources */ struct mvpp2 { /* Shared registers' base addresses */ diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index ec706d614cac..d39c7639cdba 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -3839,6 +3839,35 @@ mvpp2_run_xdp(struct mvpp2_port *port, struct mvpp2_rx_queue *rxq, return ret; } +static void mvpp2_buff_hdr_pool_put(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc, + int pool, u32 rx_status) +{ + phys_addr_t phys_addr, phys_addr_next; + dma_addr_t dma_addr, dma_addr_next; + struct mvpp2_buff_hdr *buff_hdr; + + phys_addr = mvpp2_rxdesc_dma_addr_get(port, rx_desc); + dma_addr = mvpp2_rxdesc_cookie_get(port, rx_desc); + + do { + buff_hdr = (struct mvpp2_buff_hdr *)phys_to_virt(phys_addr); + + phys_addr_next = le32_to_cpu(buff_hdr->next_phys_addr); + dma_addr_next = le32_to_cpu(buff_hdr->next_dma_addr); + + if (port->priv->hw_version >= MVPP22) { + phys_addr_next |= ((u64)buff_hdr->next_phys_addr_high << 32); + dma_addr_next |= ((u64)buff_hdr->next_dma_addr_high << 32); + } + + mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr); + + phys_addr = phys_addr_next; + dma_addr = dma_addr_next; + + } while (!MVPP2_B_HDR_INFO_IS_LAST(le16_to_cpu(buff_hdr->info))); +} + /* Main rx processing */ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, int rx_todo, struct mvpp2_rx_queue *rxq) @@ -3885,14 +3914,6 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, MVPP2_RXD_BM_POOL_ID_OFFS; bm_pool = &port->priv->bm_pools[pool]; - /* In case of an error, release the requested buffer pointer - * to the Buffer Manager. This request process is controlled - * by the hardware, and the information about the buffer is - * comprised by the RX descriptor. - */ - if (rx_status & MVPP2_RXD_ERR_SUMMARY) - goto err_drop_frame; - if (port->priv->percpu_pools) { pp = port->priv->page_pool[pool]; dma_dir = page_pool_get_dma_dir(pp); @@ -3904,6 +3925,18 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, rx_bytes + MVPP2_MH_SIZE, dma_dir); + /* Buffer header not supported */ + if (rx_status & MVPP2_RXD_BUF_HDR) + goto err_drop_frame; + + /* In case of an error, release the requested buffer pointer + * to the Buffer Manager. This request process is controlled + * by the hardware, and the information about the buffer is + * comprised by the RX descriptor. + */ + if (rx_status & MVPP2_RXD_ERR_SUMMARY) + goto err_drop_frame; + /* Prefetch header */ prefetch(data); @@ -3985,7 +4018,10 @@ err_drop_frame: dev->stats.rx_errors++; mvpp2_rx_error(port, rx_desc); /* Return the buffer to the pool */ - mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr); + if (rx_status & MVPP2_RXD_BUF_HDR) + mvpp2_buff_hdr_pool_put(port, rx_desc, pool, rx_status); + else + mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr); } rcu_read_unlock(); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index f4962a97a075..9d9a2e438acf 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -786,6 +786,10 @@ static int otx2_set_rxfh_context(struct net_device *dev, const u32 *indir, if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) return -EOPNOTSUPP; + if (*rss_context != ETH_RXFH_CONTEXT_ALLOC && + *rss_context >= MAX_RSS_GROUPS) + return -EINVAL; + rss = &pfvf->hw.rss_info; if (!rss->enable) { diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index ed4eacef17ce..64adfd24e134 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -681,32 +681,53 @@ static int mtk_set_mac_address(struct net_device *dev, void *p) void mtk_stats_update_mac(struct mtk_mac *mac) { struct mtk_hw_stats *hw_stats = mac->hw_stats; - unsigned int base = MTK_GDM1_TX_GBCNT; - u64 stats; - - base += hw_stats->reg_offset; + struct mtk_eth *eth = mac->hw; u64_stats_update_begin(&hw_stats->syncp); - hw_stats->rx_bytes += mtk_r32(mac->hw, base); - stats = mtk_r32(mac->hw, base + 0x04); - if (stats) - hw_stats->rx_bytes += (stats << 32); - hw_stats->rx_packets += mtk_r32(mac->hw, base + 0x08); - hw_stats->rx_overflow += mtk_r32(mac->hw, base + 0x10); - hw_stats->rx_fcs_errors += mtk_r32(mac->hw, base + 0x14); - hw_stats->rx_short_errors += mtk_r32(mac->hw, base + 0x18); - hw_stats->rx_long_errors += mtk_r32(mac->hw, base + 0x1c); - hw_stats->rx_checksum_errors += mtk_r32(mac->hw, base + 0x20); - hw_stats->rx_flow_control_packets += - mtk_r32(mac->hw, base + 0x24); - hw_stats->tx_skip += mtk_r32(mac->hw, base + 0x28); - hw_stats->tx_collisions += mtk_r32(mac->hw, base + 0x2c); - hw_stats->tx_bytes += mtk_r32(mac->hw, base + 0x30); - stats = mtk_r32(mac->hw, base + 0x34); - if (stats) - hw_stats->tx_bytes += (stats << 32); - hw_stats->tx_packets += mtk_r32(mac->hw, base + 0x38); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { + hw_stats->tx_packets += mtk_r32(mac->hw, MT7628_SDM_TPCNT); + hw_stats->tx_bytes += mtk_r32(mac->hw, MT7628_SDM_TBCNT); + hw_stats->rx_packets += mtk_r32(mac->hw, MT7628_SDM_RPCNT); + hw_stats->rx_bytes += mtk_r32(mac->hw, MT7628_SDM_RBCNT); + hw_stats->rx_checksum_errors += + mtk_r32(mac->hw, MT7628_SDM_CS_ERR); + } else { + unsigned int offs = hw_stats->reg_offset; + u64 stats; + + hw_stats->rx_bytes += mtk_r32(mac->hw, + MTK_GDM1_RX_GBCNT_L + offs); + stats = mtk_r32(mac->hw, MTK_GDM1_RX_GBCNT_H + offs); + if (stats) + hw_stats->rx_bytes += (stats << 32); + hw_stats->rx_packets += + mtk_r32(mac->hw, MTK_GDM1_RX_GPCNT + offs); + hw_stats->rx_overflow += + mtk_r32(mac->hw, MTK_GDM1_RX_OERCNT + offs); + hw_stats->rx_fcs_errors += + mtk_r32(mac->hw, MTK_GDM1_RX_FERCNT + offs); + hw_stats->rx_short_errors += + mtk_r32(mac->hw, MTK_GDM1_RX_SERCNT + offs); + hw_stats->rx_long_errors += + mtk_r32(mac->hw, MTK_GDM1_RX_LENCNT + offs); + hw_stats->rx_checksum_errors += + mtk_r32(mac->hw, MTK_GDM1_RX_CERCNT + offs); + hw_stats->rx_flow_control_packets += + mtk_r32(mac->hw, MTK_GDM1_RX_FCCNT + offs); + hw_stats->tx_skip += + mtk_r32(mac->hw, MTK_GDM1_TX_SKIPCNT + offs); + hw_stats->tx_collisions += + mtk_r32(mac->hw, MTK_GDM1_TX_COLCNT + offs); + hw_stats->tx_bytes += + mtk_r32(mac->hw, MTK_GDM1_TX_GBCNT_L + offs); + stats = mtk_r32(mac->hw, MTK_GDM1_TX_GBCNT_H + offs); + if (stats) + hw_stats->tx_bytes += (stats << 32); + hw_stats->tx_packets += + mtk_r32(mac->hw, MTK_GDM1_TX_GPCNT + offs); + } + u64_stats_update_end(&hw_stats->syncp); } @@ -2423,7 +2444,8 @@ static void mtk_dim_rx(struct work_struct *work) val |= cur << MTK_PDMA_DELAY_RX_PINT_SHIFT; mtk_w32(eth, val, MTK_PDMA_DELAY_INT); - mtk_w32(eth, val, MTK_QDMA_DELAY_INT); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + mtk_w32(eth, val, MTK_QDMA_DELAY_INT); spin_unlock_bh(ð->dim_lock); @@ -2452,7 +2474,8 @@ static void mtk_dim_tx(struct work_struct *work) val |= cur << MTK_PDMA_DELAY_TX_PINT_SHIFT; mtk_w32(eth, val, MTK_PDMA_DELAY_INT); - mtk_w32(eth, val, MTK_QDMA_DELAY_INT); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + mtk_w32(eth, val, MTK_QDMA_DELAY_INT); spin_unlock_bh(ð->dim_lock); @@ -2480,6 +2503,10 @@ static int mtk_hw_init(struct mtk_eth *eth) goto err_disable_pm; } + /* set interrupt delays based on current Net DIM sample */ + mtk_dim_rx(ð->rx_dim.work); + mtk_dim_tx(ð->tx_dim.work); + /* disable delay and normal interrupt */ mtk_tx_irq_disable(eth, ~0); mtk_rx_irq_disable(eth, ~0); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 11331b44ba07..5ef70dd8b49c 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -278,8 +278,21 @@ /* QDMA FQ Free Page Buffer Length Register */ #define MTK_QDMA_FQ_BLEN 0x1B2C -/* GMA1 Received Good Byte Count Register */ -#define MTK_GDM1_TX_GBCNT 0x2400 +/* GMA1 counter / statics register */ +#define MTK_GDM1_RX_GBCNT_L 0x2400 +#define MTK_GDM1_RX_GBCNT_H 0x2404 +#define MTK_GDM1_RX_GPCNT 0x2408 +#define MTK_GDM1_RX_OERCNT 0x2410 +#define MTK_GDM1_RX_FERCNT 0x2414 +#define MTK_GDM1_RX_SERCNT 0x2418 +#define MTK_GDM1_RX_LENCNT 0x241c +#define MTK_GDM1_RX_CERCNT 0x2420 +#define MTK_GDM1_RX_FCCNT 0x2424 +#define MTK_GDM1_TX_SKIPCNT 0x2428 +#define MTK_GDM1_TX_COLCNT 0x242c +#define MTK_GDM1_TX_GBCNT_L 0x2430 +#define MTK_GDM1_TX_GBCNT_H 0x2434 +#define MTK_GDM1_TX_GPCNT 0x2438 #define MTK_STAT_OFFSET 0x40 /* QDMA descriptor txd4 */ @@ -502,6 +515,13 @@ #define MT7628_SDM_MAC_ADRL (MT7628_SDM_OFFSET + 0x0c) #define MT7628_SDM_MAC_ADRH (MT7628_SDM_OFFSET + 0x10) +/* Counter / stat register */ +#define MT7628_SDM_TPCNT (MT7628_SDM_OFFSET + 0x100) +#define MT7628_SDM_TBCNT (MT7628_SDM_OFFSET + 0x104) +#define MT7628_SDM_RPCNT (MT7628_SDM_OFFSET + 0x108) +#define MT7628_SDM_RBCNT (MT7628_SDM_OFFSET + 0x10c) +#define MT7628_SDM_CS_ERR (MT7628_SDM_OFFSET + 0x110) + struct mtk_rx_dma { unsigned int rxd1; unsigned int rxd2; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 1434df66fcf2..3616b77caa0a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -2027,8 +2027,6 @@ static int mlx4_en_set_tunable(struct net_device *dev, return ret; } -#define MLX4_EEPROM_PAGE_LEN 256 - static int mlx4_en_get_module_info(struct net_device *dev, struct ethtool_modinfo *modinfo) { @@ -2063,7 +2061,7 @@ static int mlx4_en_get_module_info(struct net_device *dev, break; case MLX4_MODULE_ID_SFP: modinfo->type = ETH_MODULE_SFF_8472; - modinfo->eeprom_len = MLX4_EEPROM_PAGE_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; break; default: return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index ba6ac31a339d..256a06b3c096 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -1973,6 +1973,7 @@ EXPORT_SYMBOL(mlx4_get_roce_gid_from_slave); #define I2C_ADDR_LOW 0x50 #define I2C_ADDR_HIGH 0x51 #define I2C_PAGE_SIZE 256 +#define I2C_HIGH_PAGE_SIZE 128 /* Module Info Data */ struct mlx4_cable_info { @@ -2026,6 +2027,88 @@ static inline const char *cable_info_mad_err_str(u16 mad_status) return "Unknown Error"; } +static int mlx4_get_module_id(struct mlx4_dev *dev, u8 port, u8 *module_id) +{ + struct mlx4_cmd_mailbox *inbox, *outbox; + struct mlx4_mad_ifc *inmad, *outmad; + struct mlx4_cable_info *cable_info; + int ret; + + inbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(inbox)) + return PTR_ERR(inbox); + + outbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(outbox)) { + mlx4_free_cmd_mailbox(dev, inbox); + return PTR_ERR(outbox); + } + + inmad = (struct mlx4_mad_ifc *)(inbox->buf); + outmad = (struct mlx4_mad_ifc *)(outbox->buf); + + inmad->method = 0x1; /* Get */ + inmad->class_version = 0x1; + inmad->mgmt_class = 0x1; + inmad->base_version = 0x1; + inmad->attr_id = cpu_to_be16(0xFF60); /* Module Info */ + + cable_info = (struct mlx4_cable_info *)inmad->data; + cable_info->dev_mem_address = 0; + cable_info->page_num = 0; + cable_info->i2c_addr = I2C_ADDR_LOW; + cable_info->size = cpu_to_be16(1); + + ret = mlx4_cmd_box(dev, inbox->dma, outbox->dma, port, 3, + MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C, + MLX4_CMD_NATIVE); + if (ret) + goto out; + + if (be16_to_cpu(outmad->status)) { + /* Mad returned with bad status */ + ret = be16_to_cpu(outmad->status); + mlx4_warn(dev, + "MLX4_CMD_MAD_IFC Get Module ID attr(%x) port(%d) i2c_addr(%x) offset(%d) size(%d): Response Mad Status(%x) - %s\n", + 0xFF60, port, I2C_ADDR_LOW, 0, 1, ret, + cable_info_mad_err_str(ret)); + ret = -ret; + goto out; + } + cable_info = (struct mlx4_cable_info *)outmad->data; + *module_id = cable_info->data[0]; +out: + mlx4_free_cmd_mailbox(dev, inbox); + mlx4_free_cmd_mailbox(dev, outbox); + return ret; +} + +static void mlx4_sfp_eeprom_params_set(u8 *i2c_addr, u8 *page_num, u16 *offset) +{ + *i2c_addr = I2C_ADDR_LOW; + *page_num = 0; + + if (*offset < I2C_PAGE_SIZE) + return; + + *i2c_addr = I2C_ADDR_HIGH; + *offset -= I2C_PAGE_SIZE; +} + +static void mlx4_qsfp_eeprom_params_set(u8 *i2c_addr, u8 *page_num, u16 *offset) +{ + /* Offsets 0-255 belong to page 0. + * Offsets 256-639 belong to pages 01, 02, 03. + * For example, offset 400 is page 02: 1 + (400 - 256) / 128 = 2 + */ + if (*offset < I2C_PAGE_SIZE) + *page_num = 0; + else + *page_num = 1 + (*offset - I2C_PAGE_SIZE) / I2C_HIGH_PAGE_SIZE; + *i2c_addr = I2C_ADDR_LOW; + *offset -= *page_num * I2C_HIGH_PAGE_SIZE; +} + /** * mlx4_get_module_info - Read cable module eeprom data * @dev: mlx4_dev. @@ -2045,12 +2128,30 @@ int mlx4_get_module_info(struct mlx4_dev *dev, u8 port, struct mlx4_cmd_mailbox *inbox, *outbox; struct mlx4_mad_ifc *inmad, *outmad; struct mlx4_cable_info *cable_info; - u16 i2c_addr; + u8 module_id, i2c_addr, page_num; int ret; if (size > MODULE_INFO_MAX_READ) size = MODULE_INFO_MAX_READ; + ret = mlx4_get_module_id(dev, port, &module_id); + if (ret) + return ret; + + switch (module_id) { + case MLX4_MODULE_ID_SFP: + mlx4_sfp_eeprom_params_set(&i2c_addr, &page_num, &offset); + break; + case MLX4_MODULE_ID_QSFP: + case MLX4_MODULE_ID_QSFP_PLUS: + case MLX4_MODULE_ID_QSFP28: + mlx4_qsfp_eeprom_params_set(&i2c_addr, &page_num, &offset); + break; + default: + mlx4_err(dev, "Module ID not recognized: %#x\n", module_id); + return -EINVAL; + } + inbox = mlx4_alloc_cmd_mailbox(dev); if (IS_ERR(inbox)) return PTR_ERR(inbox); @@ -2076,11 +2177,9 @@ int mlx4_get_module_info(struct mlx4_dev *dev, u8 port, */ size -= offset + size - I2C_PAGE_SIZE; - i2c_addr = I2C_ADDR_LOW; - cable_info = (struct mlx4_cable_info *)inmad->data; cable_info->dev_mem_address = cpu_to_be16(offset); - cable_info->page_num = 0; + cable_info->page_num = page_num; cable_info->i2c_addr = i2c_addr; cable_info->size = cpu_to_be16(size); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c index 95f2b26a3ee3..9c076aa20306 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c @@ -223,6 +223,8 @@ static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *pt rpriv = priv->ppriv; fwd_vport_num = rpriv->rep->vport; lag_dev = netdev_master_upper_dev_get(netdev); + if (!lag_dev) + return; netdev_dbg(netdev, "lag_dev(%s)'s slave vport(%d) is txable(%d)\n", lag_dev->name, fwd_vport_num, net_lag_port_dev_txable(netdev)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index 6cdc52d50a48..311382261840 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -626,7 +626,7 @@ static bool mlx5e_restore_skb(struct sk_buff *skb, u32 chain, u32 reg_c1, struct mlx5_eswitch *esw; u32 zone_restore_id; - tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT); + tc_skb_ext = tc_skb_ext_alloc(skb); if (!tc_skb_ext) { WARN_ON(1); return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 593503bc4d07..f1fb11680d20 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -1505,7 +1505,7 @@ mlx5e_init_fib_work_ipv4(struct mlx5e_priv *priv, fen_info = container_of(info, struct fib_entry_notifier_info, info); fib_dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev; - if (fib_dev->netdev_ops != &mlx5e_netdev_ops || + if (!fib_dev || fib_dev->netdev_ops != &mlx5e_netdev_ops || fen_info->dst_len != 32) return NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 0d571a0c76d9..0b75fab41ae8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -35,6 +35,7 @@ #include <linux/ipv6.h> #include <linux/tcp.h> #include <linux/mlx5/fs.h> +#include <linux/mlx5/mpfs.h> #include "en.h" #include "en_rep.h" #include "lib/mpfs.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index bca832cdc4cb..ad0f69480b9c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -889,10 +889,13 @@ err_free_rq: void mlx5e_activate_rq(struct mlx5e_rq *rq) { set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); - if (rq->icosq) + if (rq->icosq) { mlx5e_trigger_irq(rq->icosq); - else + } else { + local_bh_disable(); napi_schedule(rq->cq.napi); + local_bh_enable(); + } } void mlx5e_deactivate_rq(struct mlx5e_rq *rq) @@ -2697,7 +2700,7 @@ static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv) int err; old_num_txqs = netdev->real_num_tx_queues; - old_ntc = netdev->num_tc; + old_ntc = netdev->num_tc ? : 1; nch = priv->channels.params.num_channels; ntc = priv->channels.params.num_tc; @@ -5229,6 +5232,11 @@ static void mlx5e_update_features(struct net_device *netdev) rtnl_unlock(); } +static void mlx5e_reset_channels(struct net_device *netdev) +{ + netdev_reset_tc(netdev); +} + int mlx5e_attach_netdev(struct mlx5e_priv *priv) { const bool take_rtnl = priv->netdev->reg_state == NETREG_REGISTERED; @@ -5283,6 +5291,7 @@ err_cleanup_tx: profile->cleanup_tx(priv); out: + mlx5e_reset_channels(priv->netdev); set_bit(MLX5E_STATE_DESTROYING, &priv->state); cancel_work_sync(&priv->update_stats_work); return err; @@ -5300,6 +5309,7 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv) profile->cleanup_rx(priv); profile->cleanup_tx(priv); + mlx5e_reset_channels(priv->netdev); cancel_work_sync(&priv->update_stats_work); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 47a9c49b25fd..2c776e7a7692 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1322,10 +1322,10 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct net_device *out_dev, *encap_dev = NULL; struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; bool vf_tun = false, encap_valid = true; + struct net_device *encap_dev = NULL; struct mlx5_esw_flow_attr *esw_attr; struct mlx5_fc *counter = NULL; struct mlx5e_rep_priv *rpriv; @@ -1371,16 +1371,22 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, esw_attr = attr->esw_attr; for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { + struct net_device *out_dev; int mirred_ifindex; if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) continue; mirred_ifindex = parse_attr->mirred_ifindex[out_index]; - out_dev = __dev_get_by_index(dev_net(priv->netdev), - mirred_ifindex); + out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex); + if (!out_dev) { + NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found"); + err = -ENODEV; + goto err_out; + } err = mlx5e_attach_encap(priv, flow, out_dev, out_index, extack, &encap_dev, &encap_valid); + dev_put(out_dev); if (err) goto err_out; @@ -1393,6 +1399,12 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, esw_attr->dests[out_index].mdev = out_priv->mdev; } + if (vf_tun && esw_attr->out_count > 1) { + NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported"); + err = -EOPNOTSUPP; + goto err_out; + } + err = mlx5_eswitch_add_vlan_action(esw, attr); if (err) goto err_out; @@ -3526,8 +3538,12 @@ static int add_vlan_push_action(struct mlx5e_priv *priv, if (err) return err; - *out_dev = dev_get_by_index_rcu(dev_net(vlan_dev), - dev_get_iflink(vlan_dev)); + rcu_read_lock(); + *out_dev = dev_get_by_index_rcu(dev_net(vlan_dev), dev_get_iflink(vlan_dev)); + rcu_read_unlock(); + if (!*out_dev) + return -ENODEV; + if (is_vlan_dev(*out_dev)) err = add_vlan_push_action(priv, attr, out_dev, action); @@ -5074,7 +5090,7 @@ bool mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe, if (mapped_obj.type == MLX5_MAPPED_OBJ_CHAIN) { chain = mapped_obj.chain; - tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT); + tc_skb_ext = tc_skb_ext_alloc(skb); if (WARN_ON(!tc_skb_ext)) return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 570f2280823c..b88705a3a1a8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -35,6 +35,7 @@ #include <linux/mlx5/mlx5_ifc.h> #include <linux/mlx5/vport.h> #include <linux/mlx5/fs.h> +#include <linux/mlx5/mpfs.h> #include "esw/acl/lgcy.h" #include "esw/legacy.h" #include "mlx5_core.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index a81ece94f599..b45954905845 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -65,7 +65,7 @@ mlx5_eswitch_termtbl_create(struct mlx5_core_dev *dev, { struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_flow_namespace *root_ns; - int err; + int err, err2; root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); if (!root_ns) { @@ -76,33 +76,34 @@ mlx5_eswitch_termtbl_create(struct mlx5_core_dev *dev, /* As this is the terminating action then the termination table is the * same prio as the slow path */ - ft_attr.flags = MLX5_FLOW_TABLE_TERMINATION | + ft_attr.flags = MLX5_FLOW_TABLE_TERMINATION | MLX5_FLOW_TABLE_UNMANAGED | MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT; - ft_attr.prio = FDB_SLOW_PATH; + ft_attr.prio = FDB_TC_OFFLOAD; ft_attr.max_fte = 1; + ft_attr.level = 1; ft_attr.autogroup.max_num_groups = 1; tt->termtbl = mlx5_create_auto_grouped_flow_table(root_ns, &ft_attr); if (IS_ERR(tt->termtbl)) { - esw_warn(dev, "Failed to create termination table (error %d)\n", - IS_ERR(tt->termtbl)); - return -EOPNOTSUPP; + err = PTR_ERR(tt->termtbl); + esw_warn(dev, "Failed to create termination table, err %pe\n", tt->termtbl); + return err; } tt->rule = mlx5_add_flow_rules(tt->termtbl, NULL, flow_act, &tt->dest, 1); if (IS_ERR(tt->rule)) { - esw_warn(dev, "Failed to create termination table rule (error %d)\n", - IS_ERR(tt->rule)); + err = PTR_ERR(tt->rule); + esw_warn(dev, "Failed to create termination table rule, err %pe\n", tt->rule); goto add_flow_err; } return 0; add_flow_err: - err = mlx5_destroy_flow_table(tt->termtbl); - if (err) - esw_warn(dev, "Failed to destroy termination table\n"); + err2 = mlx5_destroy_flow_table(tt->termtbl); + if (err2) + esw_warn(dev, "Failed to destroy termination table, err %d\n", err2); - return -EOPNOTSUPP; + return err; } static struct mlx5_termtbl_handle * @@ -172,19 +173,6 @@ mlx5_eswitch_termtbl_put(struct mlx5_eswitch *esw, } } -static bool mlx5_eswitch_termtbl_is_encap_reformat(struct mlx5_pkt_reformat *rt) -{ - switch (rt->reformat_type) { - case MLX5_REFORMAT_TYPE_L2_TO_VXLAN: - case MLX5_REFORMAT_TYPE_L2_TO_NVGRE: - case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL: - case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL: - return true; - default: - return false; - } -} - static void mlx5_eswitch_termtbl_actions_move(struct mlx5_flow_act *src, struct mlx5_flow_act *dst) @@ -202,14 +190,6 @@ mlx5_eswitch_termtbl_actions_move(struct mlx5_flow_act *src, memset(&src->vlan[1], 0, sizeof(src->vlan[1])); } } - - if (src->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT && - mlx5_eswitch_termtbl_is_encap_reformat(src->pkt_reformat)) { - src->action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; - dst->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; - dst->pkt_reformat = src->pkt_reformat; - src->pkt_reformat = NULL; - } } static bool mlx5_eswitch_offload_is_uplink_port(const struct mlx5_eswitch *esw, @@ -238,6 +218,7 @@ mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw, int i; if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, termination_table) || + !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level) || attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH || !mlx5_eswitch_offload_is_uplink_port(esw, spec)) return false; @@ -279,12 +260,19 @@ mlx5_eswitch_add_termtbl_rule(struct mlx5_eswitch *esw, if (dest[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT) continue; + if (attr->dests[num_vport_dests].flags & MLX5_ESW_DEST_ENCAP) { + term_tbl_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + term_tbl_act.pkt_reformat = attr->dests[num_vport_dests].pkt_reformat; + } else { + term_tbl_act.action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + term_tbl_act.pkt_reformat = NULL; + } + /* get the terminating table for the action list */ tt = mlx5_eswitch_termtbl_get_create(esw, &term_tbl_act, &dest[i], attr); if (IS_ERR(tt)) { - esw_warn(esw->dev, "Failed to get termination table (error %d)\n", - IS_ERR(tt)); + esw_warn(esw->dev, "Failed to get termination table, err %pe\n", tt); goto revert_changes; } attr->dests[num_vport_dests].termtbl = tt; @@ -301,6 +289,9 @@ mlx5_eswitch_add_termtbl_rule(struct mlx5_eswitch *esw, goto revert_changes; /* create the FTE */ + flow_act->action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + flow_act->pkt_reformat = NULL; + flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; rule = mlx5_add_flow_rules(fdb, spec, flow_act, dest, num_dest); if (IS_ERR(rule)) goto revert_changes; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c index 2c41a6920264..fd6196b5e163 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c @@ -307,6 +307,11 @@ int mlx5_lag_mp_init(struct mlx5_lag *ldev) struct lag_mp *mp = &ldev->lag_mp; int err; + /* always clear mfi, as it might become stale when a route delete event + * has been missed + */ + mp->mfi = NULL; + if (mp->fib_nb.notifier_call) return 0; @@ -335,4 +340,5 @@ void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev) unregister_fib_notifier(&init_net, &mp->fib_nb); destroy_workqueue(mp->wq); mp->fib_nb.notifier_call = NULL; + mp->mfi = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c index fd8449ff9e17..839a01da110f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c @@ -33,6 +33,7 @@ #include <linux/etherdevice.h> #include <linux/mlx5/driver.h> #include <linux/mlx5/mlx5_ifc.h> +#include <linux/mlx5/mpfs.h> #include <linux/mlx5/eswitch.h> #include "mlx5_core.h" #include "lib/mpfs.h" @@ -175,6 +176,7 @@ out: mutex_unlock(&mpfs->lock); return err; } +EXPORT_SYMBOL(mlx5_mpfs_add_mac); int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { @@ -206,3 +208,4 @@ unlock: mutex_unlock(&mpfs->lock); return err; } +EXPORT_SYMBOL(mlx5_mpfs_del_mac); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h index 4a7b2c3203a7..4a293542a7aa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h @@ -84,12 +84,9 @@ struct l2addr_node { #ifdef CONFIG_MLX5_MPFS int mlx5_mpfs_init(struct mlx5_core_dev *dev); void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev); -int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac); -int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac); #else /* #ifndef CONFIG_MLX5_MPFS */ static inline int mlx5_mpfs_init(struct mlx5_core_dev *dev) { return 0; } static inline void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev) {} -static inline int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } -static inline int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } #endif + #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index c114365eb126..a1d67bd7fb43 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -503,7 +503,7 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx) static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) { - struct mlx5_profile *prof = dev->profile; + struct mlx5_profile *prof = &dev->profile; void *set_hca_cap; int err; @@ -524,11 +524,11 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) to_fw_pkey_sz(dev, 128)); /* Check log_max_qp from HCA caps to set in current profile */ - if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < profile[prof_sel].log_max_qp) { + if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < prof->log_max_qp) { mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n", - profile[prof_sel].log_max_qp, + prof->log_max_qp, MLX5_CAP_GEN_MAX(dev, log_max_qp)); - profile[prof_sel].log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp); + prof->log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp); } if (prof->mask & MLX5_PROF_MASK_QP_SIZE) MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_qp, @@ -1381,8 +1381,7 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) struct mlx5_priv *priv = &dev->priv; int err; - dev->profile = &profile[profile_idx]; - + memcpy(&dev->profile, &profile[profile_idx], sizeof(dev->profile)); INIT_LIST_HEAD(&priv->ctx_list); spin_lock_init(&priv->ctx_lock); mutex_init(&dev->intf_state_mutex); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 1f907df5b3a2..c3373fb1cd7f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -95,9 +95,10 @@ int mlx5_get_default_msix_vec_count(struct mlx5_core_dev *dev, int num_vfs) int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id, int msix_vec_count) { - int sz = MLX5_ST_SZ_BYTES(set_hca_cap_in); + int query_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out); + int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in); + void *hca_cap = NULL, *query_cap = NULL, *cap; int num_vf_msix, min_msix, max_msix; - void *hca_cap, *cap; int ret; num_vf_msix = MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix); @@ -116,11 +117,20 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id, if (msix_vec_count > max_msix) return -EOVERFLOW; - hca_cap = kzalloc(sz, GFP_KERNEL); - if (!hca_cap) - return -ENOMEM; + query_cap = kzalloc(query_sz, GFP_KERNEL); + hca_cap = kzalloc(set_sz, GFP_KERNEL); + if (!hca_cap || !query_cap) { + ret = -ENOMEM; + goto out; + } + + ret = mlx5_vport_get_other_func_cap(dev, function_id, query_cap); + if (ret) + goto out; cap = MLX5_ADDR_OF(set_hca_cap_in, hca_cap, capability); + memcpy(cap, MLX5_ADDR_OF(query_hca_cap_out, query_cap, capability), + MLX5_UN_SZ_BYTES(hca_cap_union)); MLX5_SET(cmd_hca_cap, cap, dynamic_msix_table_size, msix_vec_count); MLX5_SET(set_hca_cap_in, hca_cap, opcode, MLX5_CMD_OP_SET_HCA_CAP); @@ -130,7 +140,9 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id, MLX5_SET(set_hca_cap_in, hca_cap, op_mod, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE << 1); ret = mlx5_cmd_exec_in(dev, set_hca_cap, hca_cap); +out: kfree(hca_cap); + kfree(query_cap); return ret; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c index a8e73c9ed1ea..1be048769309 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c @@ -136,10 +136,10 @@ static enum devlink_port_fn_state mlx5_sf_to_devlink_state(u8 hw_state) switch (hw_state) { case MLX5_VHCA_STATE_ACTIVE: case MLX5_VHCA_STATE_IN_USE: - case MLX5_VHCA_STATE_TEARDOWN_REQUEST: return DEVLINK_PORT_FN_STATE_ACTIVE; case MLX5_VHCA_STATE_INVALID: case MLX5_VHCA_STATE_ALLOCATED: + case MLX5_VHCA_STATE_TEARDOWN_REQUEST: default: return DEVLINK_PORT_FN_STATE_INACTIVE; } @@ -192,14 +192,17 @@ sf_err: return err; } -static int mlx5_sf_activate(struct mlx5_core_dev *dev, struct mlx5_sf *sf) +static int mlx5_sf_activate(struct mlx5_core_dev *dev, struct mlx5_sf *sf, + struct netlink_ext_ack *extack) { int err; if (mlx5_sf_is_active(sf)) return 0; - if (sf->hw_state != MLX5_VHCA_STATE_ALLOCATED) - return -EINVAL; + if (sf->hw_state != MLX5_VHCA_STATE_ALLOCATED) { + NL_SET_ERR_MSG_MOD(extack, "SF is inactivated but it is still attached"); + return -EBUSY; + } err = mlx5_cmd_sf_enable_hca(dev, sf->hw_fn_id); if (err) @@ -226,7 +229,8 @@ static int mlx5_sf_deactivate(struct mlx5_core_dev *dev, struct mlx5_sf *sf) static int mlx5_sf_state_set(struct mlx5_core_dev *dev, struct mlx5_sf_table *table, struct mlx5_sf *sf, - enum devlink_port_fn_state state) + enum devlink_port_fn_state state, + struct netlink_ext_ack *extack) { int err = 0; @@ -234,7 +238,7 @@ static int mlx5_sf_state_set(struct mlx5_core_dev *dev, struct mlx5_sf_table *ta if (state == mlx5_sf_to_devlink_state(sf->hw_state)) goto out; if (state == DEVLINK_PORT_FN_STATE_ACTIVE) - err = mlx5_sf_activate(dev, sf); + err = mlx5_sf_activate(dev, sf, extack); else if (state == DEVLINK_PORT_FN_STATE_INACTIVE) err = mlx5_sf_deactivate(dev, sf); else @@ -265,7 +269,7 @@ int mlx5_devlink_sf_port_fn_state_set(struct devlink *devlink, struct devlink_po goto out; } - err = mlx5_sf_state_set(dev, table, sf, state); + err = mlx5_sf_state_set(dev, table, sf, state, extack); out: mlx5_sf_table_put(table); return err; diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c index 3658c4ae3c37..ee921a99e439 100644 --- a/drivers/net/ethernet/microchip/encx24j600.c +++ b/drivers/net/ethernet/microchip/encx24j600.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later -/** +/* * Microchip ENCX24J600 ethernet driver * * Copyright (C) 2015 Gridpoint diff --git a/drivers/net/ethernet/microchip/encx24j600_hw.h b/drivers/net/ethernet/microchip/encx24j600_hw.h index f604a260ede7..fac61a8fbd02 100644 --- a/drivers/net/ethernet/microchip/encx24j600_hw.h +++ b/drivers/net/ethernet/microchip/encx24j600_hw.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/** +/* * encx24j600_hw.h: Register definitions * */ diff --git a/drivers/net/ethernet/pensando/Kconfig b/drivers/net/ethernet/pensando/Kconfig index 5f8b0bb3af6e..202973a82712 100644 --- a/drivers/net/ethernet/pensando/Kconfig +++ b/drivers/net/ethernet/pensando/Kconfig @@ -20,6 +20,7 @@ if NET_VENDOR_PENSANDO config IONIC tristate "Pensando Ethernet IONIC Support" depends on 64BIT && PCI + depends on PTP_1588_CLOCK || !PTP_1588_CLOCK select NET_DEVLINK select DIMLIB help diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 214e347097a7..2376b2729633 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -114,7 +114,7 @@ static int ql_sem_spinlock(struct ql3_adapter *qdev, value = readl(&port_regs->CommonRegs.semaphoreReg); if ((value & (sem_mask >> 16)) == sem_bits) return 0; - ssleep(1); + mdelay(1000); } while (--seconds); return -1; } diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c index d1e908846f5d..22fbb0ae77fb 100644 --- a/drivers/net/ethernet/sfc/nic.c +++ b/drivers/net/ethernet/sfc/nic.c @@ -90,6 +90,7 @@ int efx_nic_init_interrupt(struct efx_nic *efx) efx->pci_dev->irq); goto fail1; } + efx->irqs_hooked = true; return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 345b4c6d1fd4..5d956a553434 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1196,7 +1196,6 @@ static void stmmac_check_pcs_mode(struct stmmac_priv *priv) */ static int stmmac_init_phy(struct net_device *dev) { - struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; struct stmmac_priv *priv = netdev_priv(dev); struct device_node *node; int ret; @@ -1222,8 +1221,12 @@ static int stmmac_init_phy(struct net_device *dev) ret = phylink_connect_phy(priv->phylink, phydev); } - phylink_ethtool_get_wol(priv->phylink, &wol); - device_set_wakeup_capable(priv->device, !!wol.supported); + if (!priv->plat->pmt) { + struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; + + phylink_ethtool_get_wol(priv->phylink, &wol); + device_set_wakeup_capable(priv->device, !!wol.supported); + } return ret; } @@ -5888,12 +5891,21 @@ static int stmmac_set_mac_address(struct net_device *ndev, void *addr) struct stmmac_priv *priv = netdev_priv(ndev); int ret = 0; + ret = pm_runtime_get_sync(priv->device); + if (ret < 0) { + pm_runtime_put_noidle(priv->device); + return ret; + } + ret = eth_mac_addr(ndev, addr); if (ret) - return ret; + goto set_mac_error; stmmac_set_umac_addr(priv, priv->hw, ndev->dev_addr, 0); +set_mac_error: + pm_runtime_put(priv->device); + return ret; } @@ -6188,12 +6200,6 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid bool is_double = false; int ret; - ret = pm_runtime_get_sync(priv->device); - if (ret < 0) { - pm_runtime_put_noidle(priv->device); - return ret; - } - if (be16_to_cpu(proto) == ETH_P_8021AD) is_double = true; @@ -6219,6 +6225,12 @@ static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vi bool is_double = false; int ret; + ret = pm_runtime_get_sync(priv->device); + if (ret < 0) { + pm_runtime_put_noidle(priv->device); + return ret; + } + if (be16_to_cpu(proto) == ETH_P_8021AD) is_double = true; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 9030e619e543..97942b0e3897 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1350,8 +1350,8 @@ int netcp_txpipe_open(struct netcp_tx_pipe *tx_pipe) tx_pipe->dma_queue = knav_queue_open(name, tx_pipe->dma_queue_id, KNAV_QUEUE_SHARED); if (IS_ERR(tx_pipe->dma_queue)) { - dev_err(dev, "Could not open DMA queue for channel \"%s\": %d\n", - name, ret); + dev_err(dev, "Could not open DMA queue for channel \"%s\": %pe\n", + name, tx_pipe->dma_queue); ret = PTR_ERR(tx_pipe->dma_queue); goto err; } diff --git a/drivers/net/ipa/ipa.h b/drivers/net/ipa/ipa.h index e7ff376cb5b7..744406832a77 100644 --- a/drivers/net/ipa/ipa.h +++ b/drivers/net/ipa/ipa.h @@ -58,6 +58,7 @@ enum ipa_flag { * @mem_virt: Virtual address of IPA-local memory space * @mem_offset: Offset from @mem_virt used for access to IPA memory * @mem_size: Total size (bytes) of memory at @mem_virt + * @mem_count: Number of entries in the mem array * @mem: Array of IPA-local memory region descriptors * @imem_iova: I/O virtual address of IPA region in IMEM * @imem_size: Size of IMEM region @@ -103,6 +104,7 @@ struct ipa { void *mem_virt; u32 mem_offset; u32 mem_size; + u32 mem_count; const struct ipa_mem *mem; unsigned long imem_iova; diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c index c5c3b1b7e67d..1624125e7459 100644 --- a/drivers/net/ipa/ipa_mem.c +++ b/drivers/net/ipa/ipa_mem.c @@ -180,7 +180,7 @@ int ipa_mem_config(struct ipa *ipa) * for the region, write "canary" values in the space prior to * the region's base address. */ - for (mem_id = 0; mem_id < IPA_MEM_COUNT; mem_id++) { + for (mem_id = 0; mem_id < ipa->mem_count; mem_id++) { const struct ipa_mem *mem = &ipa->mem[mem_id]; u16 canary_count; __le32 *canary; @@ -487,6 +487,7 @@ int ipa_mem_init(struct ipa *ipa, const struct ipa_mem_data *mem_data) ipa->mem_size = resource_size(res); /* The ipa->mem[] array is indexed by enum ipa_mem_id values */ + ipa->mem_count = mem_data->local_count; ipa->mem = mem_data->local; ret = ipa_imem_init(ipa, mem_data->imem_addr, mem_data->imem_size); diff --git a/drivers/net/mdio/mdio-octeon.c b/drivers/net/mdio/mdio-octeon.c index 8ce99c4888e1..e096e68ac667 100644 --- a/drivers/net/mdio/mdio-octeon.c +++ b/drivers/net/mdio/mdio-octeon.c @@ -71,7 +71,6 @@ static int octeon_mdiobus_probe(struct platform_device *pdev) return 0; fail_register: - mdiobus_free(bus->mii_bus); smi_en.u64 = 0; oct_mdio_writeq(smi_en.u64, bus->register_base + SMI_EN); return err; @@ -85,7 +84,6 @@ static int octeon_mdiobus_remove(struct platform_device *pdev) bus = platform_get_drvdata(pdev); mdiobus_unregister(bus->mii_bus); - mdiobus_free(bus->mii_bus); smi_en.u64 = 0; oct_mdio_writeq(smi_en.u64, bus->register_base + SMI_EN); return 0; diff --git a/drivers/net/mdio/mdio-thunder.c b/drivers/net/mdio/mdio-thunder.c index cb1761693b69..822d2cdd2f35 100644 --- a/drivers/net/mdio/mdio-thunder.c +++ b/drivers/net/mdio/mdio-thunder.c @@ -126,7 +126,6 @@ static void thunder_mdiobus_pci_remove(struct pci_dev *pdev) continue; mdiobus_unregister(bus->mii_bus); - mdiobus_free(bus->mii_bus); oct_mdio_writeq(0, bus->register_base + SMI_EN); } pci_release_regions(pdev); diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index dadf75ff3ab9..6045ad3def12 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -607,7 +607,8 @@ void mdiobus_unregister(struct mii_bus *bus) struct mdio_device *mdiodev; int i; - BUG_ON(bus->state != MDIOBUS_REGISTERED); + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) + return; bus->state = MDIOBUS_UNREGISTERED; for (i = 0; i < PHY_MAX_ADDR; i++) { diff --git a/drivers/net/usb/cdc_eem.c b/drivers/net/usb/cdc_eem.c index 0eeec80bec31..2e60bc1b9a6b 100644 --- a/drivers/net/usb/cdc_eem.c +++ b/drivers/net/usb/cdc_eem.c @@ -26,7 +26,7 @@ * for transport over USB using a simpler USB device model than the * previous CDC "Ethernet Control Model" (ECM, or "CDC Ethernet"). * - * For details, see www.usb.org/developers/devclass_docs/CDC_EEM10.pdf + * For details, see https://usb.org/sites/default/files/CDC_EEM10.pdf * * This version has been tested with GIGAntIC WuaoW SIM Smart Card on 2.6.24, * 2.6.27 and 2.6.30rc2 kernel. diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 3ef4b2841402..5c779cc0ea11 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -1689,7 +1689,7 @@ static int hso_serial_tiocmset(struct tty_struct *tty, spin_unlock_irqrestore(&serial->serial_lock, flags); return usb_control_msg(serial->parent->usb, - usb_rcvctrlpipe(serial->parent->usb, 0), 0x22, + usb_sndctrlpipe(serial->parent->usb, 0), 0x22, 0x21, val, if_num, NULL, 0, USB_CTRL_SET_TIMEOUT); } @@ -2436,7 +2436,7 @@ static int hso_rfkill_set_block(void *data, bool blocked) if (hso_dev->usb_gone) rv = 0; else - rv = usb_control_msg(hso_dev->usb, usb_rcvctrlpipe(hso_dev->usb, 0), + rv = usb_control_msg(hso_dev->usb, usb_sndctrlpipe(hso_dev->usb, 0), enabled ? 0x82 : 0x81, 0x40, 0, 0, NULL, 0, USB_CTRL_SET_TIMEOUT); mutex_unlock(&hso_dev->mutex); @@ -2618,32 +2618,31 @@ static struct hso_device *hso_create_bulk_serial_device( num_urbs = 2; serial->tiocmget = kzalloc(sizeof(struct hso_tiocmget), GFP_KERNEL); + if (!serial->tiocmget) + goto exit; serial->tiocmget->serial_state_notification = kzalloc(sizeof(struct hso_serial_state_notification), GFP_KERNEL); - /* it isn't going to break our heart if serial->tiocmget - * allocation fails don't bother checking this. - */ - if (serial->tiocmget && serial->tiocmget->serial_state_notification) { - tiocmget = serial->tiocmget; - tiocmget->endp = hso_get_ep(interface, - USB_ENDPOINT_XFER_INT, - USB_DIR_IN); - if (!tiocmget->endp) { - dev_err(&interface->dev, "Failed to find INT IN ep\n"); - goto exit; - } - - tiocmget->urb = usb_alloc_urb(0, GFP_KERNEL); - if (tiocmget->urb) { - mutex_init(&tiocmget->mutex); - init_waitqueue_head(&tiocmget->waitq); - } else - hso_free_tiomget(serial); + if (!serial->tiocmget->serial_state_notification) + goto exit; + tiocmget = serial->tiocmget; + tiocmget->endp = hso_get_ep(interface, + USB_ENDPOINT_XFER_INT, + USB_DIR_IN); + if (!tiocmget->endp) { + dev_err(&interface->dev, "Failed to find INT IN ep\n"); + goto exit; } - } - else + + tiocmget->urb = usb_alloc_urb(0, GFP_KERNEL); + if (!tiocmget->urb) + goto exit; + + mutex_init(&tiocmget->mutex); + init_waitqueue_head(&tiocmget->waitq); + } else { num_urbs = 1; + } if (hso_serial_common_create(serial, num_urbs, BULK_URB_RX_SIZE, BULK_URB_TX_SIZE)) diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 6acc5e904518..02bce40a67e5 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1645,6 +1645,7 @@ static const struct ethtool_ops lan78xx_ethtool_ops = { .get_strings = lan78xx_get_strings, .get_wol = lan78xx_get_wol, .set_wol = lan78xx_set_wol, + .get_ts_info = ethtool_op_get_ts_info, .get_eee = lan78xx_get_eee, .set_eee = lan78xx_set_eee, .get_pauseparam = lan78xx_get_pause, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 136ea06540ff..f6abb2fbf972 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -8107,6 +8107,37 @@ static void r8156b_init(struct r8152 *tp) tp->coalesce = 15000; /* 15 us */ } +static bool rtl_check_vendor_ok(struct usb_interface *intf) +{ + struct usb_host_interface *alt = intf->cur_altsetting; + struct usb_endpoint_descriptor *in, *out, *intr; + + if (usb_find_common_endpoints(alt, &in, &out, &intr, NULL) < 0) { + dev_err(&intf->dev, "Expected endpoints are not found\n"); + return false; + } + + /* Check Rx endpoint address */ + if (usb_endpoint_num(in) != 1) { + dev_err(&intf->dev, "Invalid Rx endpoint address\n"); + return false; + } + + /* Check Tx endpoint address */ + if (usb_endpoint_num(out) != 2) { + dev_err(&intf->dev, "Invalid Tx endpoint address\n"); + return false; + } + + /* Check interrupt endpoint address */ + if (usb_endpoint_num(intr) != 3) { + dev_err(&intf->dev, "Invalid interrupt endpoint address\n"); + return false; + } + + return true; +} + static bool rtl_vendor_mode(struct usb_interface *intf) { struct usb_host_interface *alt = intf->cur_altsetting; @@ -8115,12 +8146,15 @@ static bool rtl_vendor_mode(struct usb_interface *intf) int i, num_configs; if (alt->desc.bInterfaceClass == USB_CLASS_VENDOR_SPEC) - return true; + return rtl_check_vendor_ok(intf); /* The vendor mode is not always config #1, so to find it out. */ udev = interface_to_usbdev(intf); c = udev->config; num_configs = udev->descriptor.bNumConfigurations; + if (num_configs < 2) + return false; + for (i = 0; i < num_configs; (i++, c++)) { struct usb_interface_descriptor *desc = NULL; @@ -8135,7 +8169,8 @@ static bool rtl_vendor_mode(struct usb_interface *intf) } } - WARN_ON_ONCE(i == num_configs); + if (i == num_configs) + dev_err(&intf->dev, "Unexpected Device\n"); return false; } @@ -9381,9 +9416,6 @@ static int rtl8152_probe(struct usb_interface *intf, if (!rtl_vendor_mode(intf)) return -ENODEV; - if (intf->cur_altsetting->desc.bNumEndpoints < 3) - return -ENODEV; - usb_reset_device(udev); netdev = alloc_etherdev(sizeof(struct r8152)); if (!netdev) { diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index f8cdabb9ef5a..b286993da67c 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -1483,7 +1483,7 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf) ret = smsc75xx_wait_ready(dev, 0); if (ret < 0) { netdev_warn(dev->net, "device not ready in smsc75xx_bind\n"); - return ret; + goto err; } smsc75xx_init_mac_address(dev); @@ -1492,7 +1492,7 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf) ret = smsc75xx_reset(dev); if (ret < 0) { netdev_warn(dev->net, "smsc75xx_reset error %d\n", ret); - return ret; + goto err; } dev->net->netdev_ops = &smsc75xx_netdev_ops; @@ -1502,6 +1502,10 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf) dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; dev->net->max_mtu = MAX_SINGLE_PACKET_SIZE; return 0; + +err: + kfree(pdata); + return ret; } static void smsc75xx_unbind(struct usbnet *dev, struct usb_interface *intf) diff --git a/drivers/net/wireless/ath/ath10k/htt.h b/drivers/net/wireless/ath/ath10k/htt.h index 956157946106..dbc8aef82a65 100644 --- a/drivers/net/wireless/ath/ath10k/htt.h +++ b/drivers/net/wireless/ath/ath10k/htt.h @@ -845,6 +845,7 @@ enum htt_security_types { #define ATH10K_HTT_TXRX_PEER_SECURITY_MAX 2 #define ATH10K_TXRX_NUM_EXT_TIDS 19 +#define ATH10K_TXRX_NON_QOS_TID 16 enum htt_security_flags { #define HTT_SECURITY_TYPE_MASK 0x7F diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c index 1a08156d5011..7ffb5d5b2a70 100644 --- a/drivers/net/wireless/ath/ath10k/htt_rx.c +++ b/drivers/net/wireless/ath/ath10k/htt_rx.c @@ -1746,16 +1746,97 @@ static void ath10k_htt_rx_h_csum_offload(struct sk_buff *msdu) msdu->ip_summed = ath10k_htt_rx_get_csum_state(msdu); } +static u64 ath10k_htt_rx_h_get_pn(struct ath10k *ar, struct sk_buff *skb, + u16 offset, + enum htt_rx_mpdu_encrypt_type enctype) +{ + struct ieee80211_hdr *hdr; + u64 pn = 0; + u8 *ehdr; + + hdr = (struct ieee80211_hdr *)(skb->data + offset); + ehdr = skb->data + offset + ieee80211_hdrlen(hdr->frame_control); + + if (enctype == HTT_RX_MPDU_ENCRYPT_AES_CCM_WPA2) { + pn = ehdr[0]; + pn |= (u64)ehdr[1] << 8; + pn |= (u64)ehdr[4] << 16; + pn |= (u64)ehdr[5] << 24; + pn |= (u64)ehdr[6] << 32; + pn |= (u64)ehdr[7] << 40; + } + return pn; +} + +static bool ath10k_htt_rx_h_frag_multicast_check(struct ath10k *ar, + struct sk_buff *skb, + u16 offset) +{ + struct ieee80211_hdr *hdr; + + hdr = (struct ieee80211_hdr *)(skb->data + offset); + return !is_multicast_ether_addr(hdr->addr1); +} + +static bool ath10k_htt_rx_h_frag_pn_check(struct ath10k *ar, + struct sk_buff *skb, + u16 peer_id, + u16 offset, + enum htt_rx_mpdu_encrypt_type enctype) +{ + struct ath10k_peer *peer; + union htt_rx_pn_t *last_pn, new_pn = {0}; + struct ieee80211_hdr *hdr; + bool more_frags; + u8 tid, frag_number; + u32 seq; + + peer = ath10k_peer_find_by_id(ar, peer_id); + if (!peer) { + ath10k_dbg(ar, ATH10K_DBG_HTT, "invalid peer for frag pn check\n"); + return false; + } + + hdr = (struct ieee80211_hdr *)(skb->data + offset); + if (ieee80211_is_data_qos(hdr->frame_control)) + tid = ieee80211_get_tid(hdr); + else + tid = ATH10K_TXRX_NON_QOS_TID; + + last_pn = &peer->frag_tids_last_pn[tid]; + new_pn.pn48 = ath10k_htt_rx_h_get_pn(ar, skb, offset, enctype); + more_frags = ieee80211_has_morefrags(hdr->frame_control); + frag_number = le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_FRAG; + seq = (__le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_SEQ) >> 4; + + if (frag_number == 0) { + last_pn->pn48 = new_pn.pn48; + peer->frag_tids_seq[tid] = seq; + } else { + if (seq != peer->frag_tids_seq[tid]) + return false; + + if (new_pn.pn48 != last_pn->pn48 + 1) + return false; + + last_pn->pn48 = new_pn.pn48; + } + + return true; +} + static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, struct sk_buff_head *amsdu, struct ieee80211_rx_status *status, bool fill_crypt_header, u8 *rx_hdr, - enum ath10k_pkt_rx_err *err) + enum ath10k_pkt_rx_err *err, + u16 peer_id, + bool frag) { struct sk_buff *first; struct sk_buff *last; - struct sk_buff *msdu; + struct sk_buff *msdu, *temp; struct htt_rx_desc *rxd; struct ieee80211_hdr *hdr; enum htt_rx_mpdu_encrypt_type enctype; @@ -1768,6 +1849,7 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, bool is_decrypted; bool is_mgmt; u32 attention; + bool frag_pn_check = true, multicast_check = true; if (skb_queue_empty(amsdu)) return; @@ -1866,7 +1948,37 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, } skb_queue_walk(amsdu, msdu) { + if (frag && !fill_crypt_header && is_decrypted && + enctype == HTT_RX_MPDU_ENCRYPT_AES_CCM_WPA2) + frag_pn_check = ath10k_htt_rx_h_frag_pn_check(ar, + msdu, + peer_id, + 0, + enctype); + + if (frag) + multicast_check = ath10k_htt_rx_h_frag_multicast_check(ar, + msdu, + 0); + + if (!frag_pn_check || !multicast_check) { + /* Discard the fragment with invalid PN or multicast DA + */ + temp = msdu->prev; + __skb_unlink(msdu, amsdu); + dev_kfree_skb_any(msdu); + msdu = temp; + frag_pn_check = true; + multicast_check = true; + continue; + } + ath10k_htt_rx_h_csum_offload(msdu); + + if (frag && !fill_crypt_header && + enctype == HTT_RX_MPDU_ENCRYPT_TKIP_WPA) + status->flag &= ~RX_FLAG_MMIC_STRIPPED; + ath10k_htt_rx_h_undecap(ar, msdu, status, first_hdr, enctype, is_decrypted); @@ -1884,6 +1996,11 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, hdr = (void *)msdu->data; hdr->frame_control &= ~__cpu_to_le16(IEEE80211_FCTL_PROTECTED); + + if (frag && !fill_crypt_header && + enctype == HTT_RX_MPDU_ENCRYPT_TKIP_WPA) + status->flag &= ~RX_FLAG_IV_STRIPPED & + ~RX_FLAG_MMIC_STRIPPED; } } @@ -1991,14 +2108,62 @@ static void ath10k_htt_rx_h_unchain(struct ath10k *ar, ath10k_unchain_msdu(amsdu, unchain_cnt); } +static bool ath10k_htt_rx_validate_amsdu(struct ath10k *ar, + struct sk_buff_head *amsdu) +{ + u8 *subframe_hdr; + struct sk_buff *first; + bool is_first, is_last; + struct htt_rx_desc *rxd; + struct ieee80211_hdr *hdr; + size_t hdr_len, crypto_len; + enum htt_rx_mpdu_encrypt_type enctype; + int bytes_aligned = ar->hw_params.decap_align_bytes; + + first = skb_peek(amsdu); + + rxd = (void *)first->data - sizeof(*rxd); + hdr = (void *)rxd->rx_hdr_status; + + is_first = !!(rxd->msdu_end.common.info0 & + __cpu_to_le32(RX_MSDU_END_INFO0_FIRST_MSDU)); + is_last = !!(rxd->msdu_end.common.info0 & + __cpu_to_le32(RX_MSDU_END_INFO0_LAST_MSDU)); + + /* Return in case of non-aggregated msdu */ + if (is_first && is_last) + return true; + + /* First msdu flag is not set for the first msdu of the list */ + if (!is_first) + return false; + + enctype = MS(__le32_to_cpu(rxd->mpdu_start.info0), + RX_MPDU_START_INFO0_ENCRYPT_TYPE); + + hdr_len = ieee80211_hdrlen(hdr->frame_control); + crypto_len = ath10k_htt_rx_crypto_param_len(ar, enctype); + + subframe_hdr = (u8 *)hdr + round_up(hdr_len, bytes_aligned) + + crypto_len; + + /* Validate if the amsdu has a proper first subframe. + * There are chances a single msdu can be received as amsdu when + * the unauthenticated amsdu flag of a QoS header + * gets flipped in non-SPP AMSDU's, in such cases the first + * subframe has llc/snap header in place of a valid da. + * return false if the da matches rfc1042 pattern + */ + if (ether_addr_equal(subframe_hdr, rfc1042_header)) + return false; + + return true; +} + static bool ath10k_htt_rx_amsdu_allowed(struct ath10k *ar, struct sk_buff_head *amsdu, struct ieee80211_rx_status *rx_status) { - /* FIXME: It might be a good idea to do some fuzzy-testing to drop - * invalid/dangerous frames. - */ - if (!rx_status->freq) { ath10k_dbg(ar, ATH10K_DBG_HTT, "no channel configured; ignoring frame(s)!\n"); return false; @@ -2009,6 +2174,11 @@ static bool ath10k_htt_rx_amsdu_allowed(struct ath10k *ar, return false; } + if (!ath10k_htt_rx_validate_amsdu(ar, amsdu)) { + ath10k_dbg(ar, ATH10K_DBG_HTT, "invalid amsdu received\n"); + return false; + } + return true; } @@ -2071,7 +2241,8 @@ static int ath10k_htt_rx_handle_amsdu(struct ath10k_htt *htt) ath10k_htt_rx_h_unchain(ar, &amsdu, &drop_cnt, &unchain_cnt); ath10k_htt_rx_h_filter(ar, &amsdu, rx_status, &drop_cnt_filter); - ath10k_htt_rx_h_mpdu(ar, &amsdu, rx_status, true, first_hdr, &err); + ath10k_htt_rx_h_mpdu(ar, &amsdu, rx_status, true, first_hdr, &err, 0, + false); msdus_to_queue = skb_queue_len(&amsdu); ath10k_htt_rx_h_enqueue(ar, &amsdu, rx_status); @@ -2204,6 +2375,11 @@ static bool ath10k_htt_rx_proc_rx_ind_hl(struct ath10k_htt *htt, fw_desc = &rx->fw_desc; rx_desc_len = fw_desc->len; + if (fw_desc->u.bits.discard) { + ath10k_dbg(ar, ATH10K_DBG_HTT, "htt discard mpdu\n"); + goto err; + } + /* I have not yet seen any case where num_mpdu_ranges > 1. * qcacld does not seem handle that case either, so we introduce the * same limitiation here as well. @@ -2509,6 +2685,13 @@ static bool ath10k_htt_rx_proc_rx_frag_ind_hl(struct ath10k_htt *htt, rx_desc = (struct htt_hl_rx_desc *)(skb->data + tot_hdr_len); rx_desc_info = __le32_to_cpu(rx_desc->info); + hdr = (struct ieee80211_hdr *)((u8 *)rx_desc + rx_hl->fw_desc.len); + + if (is_multicast_ether_addr(hdr->addr1)) { + /* Discard the fragment with multicast DA */ + goto err; + } + if (!MS(rx_desc_info, HTT_RX_DESC_HL_INFO_ENCRYPTED)) { spin_unlock_bh(&ar->data_lock); return ath10k_htt_rx_proc_rx_ind_hl(htt, &resp->rx_ind_hl, skb, @@ -2516,8 +2699,6 @@ static bool ath10k_htt_rx_proc_rx_frag_ind_hl(struct ath10k_htt *htt, HTT_RX_NON_TKIP_MIC); } - hdr = (struct ieee80211_hdr *)((u8 *)rx_desc + rx_hl->fw_desc.len); - if (ieee80211_has_retry(hdr->frame_control)) goto err; @@ -3027,7 +3208,7 @@ static int ath10k_htt_rx_in_ord_ind(struct ath10k *ar, struct sk_buff *skb) ath10k_htt_rx_h_ppdu(ar, &amsdu, status, vdev_id); ath10k_htt_rx_h_filter(ar, &amsdu, status, NULL); ath10k_htt_rx_h_mpdu(ar, &amsdu, status, false, NULL, - NULL); + NULL, peer_id, frag); ath10k_htt_rx_h_enqueue(ar, &amsdu, status); break; case -EAGAIN: diff --git a/drivers/net/wireless/ath/ath10k/rx_desc.h b/drivers/net/wireless/ath/ath10k/rx_desc.h index f2b6bf8f0d60..705b6295e466 100644 --- a/drivers/net/wireless/ath/ath10k/rx_desc.h +++ b/drivers/net/wireless/ath/ath10k/rx_desc.h @@ -1282,7 +1282,19 @@ struct fw_rx_desc_base { #define FW_RX_DESC_UDP (1 << 6) struct fw_rx_desc_hl { - u8 info0; + union { + struct { + u8 discard:1, + forward:1, + any_err:1, + dup_err:1, + reserved:1, + inspect:1, + extension:2; + } bits; + u8 info0; + } u; + u8 version; u8 len; u8 flags; diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c index 1d9aa1bb6b6e..603d2f93ac18 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.c +++ b/drivers/net/wireless/ath/ath11k/dp_rx.c @@ -260,6 +260,16 @@ static void ath11k_dp_rxdesc_set_msdu_len(struct ath11k_base *ab, ab->hw_params.hw_ops->rx_desc_set_msdu_len(desc, len); } +static bool ath11k_dp_rx_h_attn_is_mcbc(struct ath11k_base *ab, + struct hal_rx_desc *desc) +{ + struct rx_attention *attn = ath11k_dp_rx_get_attention(ab, desc); + + return ath11k_dp_rx_h_msdu_end_first_msdu(ab, desc) && + (!!FIELD_GET(RX_ATTENTION_INFO1_MCAST_BCAST, + __le32_to_cpu(attn->info1))); +} + static void ath11k_dp_service_mon_ring(struct timer_list *t) { struct ath11k_base *ab = from_timer(ab, t, mon_reap_timer); @@ -852,6 +862,24 @@ static void ath11k_dp_rx_frags_cleanup(struct dp_rx_tid *rx_tid, bool rel_link_d __skb_queue_purge(&rx_tid->rx_frags); } +void ath11k_peer_frags_flush(struct ath11k *ar, struct ath11k_peer *peer) +{ + struct dp_rx_tid *rx_tid; + int i; + + lockdep_assert_held(&ar->ab->base_lock); + + for (i = 0; i <= IEEE80211_NUM_TIDS; i++) { + rx_tid = &peer->rx_tid[i]; + + spin_unlock_bh(&ar->ab->base_lock); + del_timer_sync(&rx_tid->frag_timer); + spin_lock_bh(&ar->ab->base_lock); + + ath11k_dp_rx_frags_cleanup(rx_tid, true); + } +} + void ath11k_peer_rx_tid_cleanup(struct ath11k *ar, struct ath11k_peer *peer) { struct dp_rx_tid *rx_tid; @@ -3450,6 +3478,7 @@ static int ath11k_dp_rx_frag_h_mpdu(struct ath11k *ar, u8 tid; int ret = 0; bool more_frags; + bool is_mcbc; rx_desc = (struct hal_rx_desc *)msdu->data; peer_id = ath11k_dp_rx_h_mpdu_start_peer_id(ar->ab, rx_desc); @@ -3457,6 +3486,11 @@ static int ath11k_dp_rx_frag_h_mpdu(struct ath11k *ar, seqno = ath11k_dp_rx_h_mpdu_start_seq_no(ar->ab, rx_desc); frag_no = ath11k_dp_rx_h_mpdu_start_frag_no(ar->ab, msdu); more_frags = ath11k_dp_rx_h_mpdu_start_more_frags(ar->ab, msdu); + is_mcbc = ath11k_dp_rx_h_attn_is_mcbc(ar->ab, rx_desc); + + /* Multicast/Broadcast fragments are not expected */ + if (is_mcbc) + return -EINVAL; if (!ath11k_dp_rx_h_mpdu_start_seq_ctrl_valid(ar->ab, rx_desc) || !ath11k_dp_rx_h_mpdu_start_fc_valid(ar->ab, rx_desc) || diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.h b/drivers/net/wireless/ath/ath11k/dp_rx.h index bf399312b5ff..623da3bf9dc8 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.h +++ b/drivers/net/wireless/ath/ath11k/dp_rx.h @@ -49,6 +49,7 @@ int ath11k_dp_peer_rx_pn_replay_config(struct ath11k_vif *arvif, const u8 *peer_addr, enum set_key_cmd key_cmd, struct ieee80211_key_conf *key); +void ath11k_peer_frags_flush(struct ath11k *ar, struct ath11k_peer *peer); void ath11k_peer_rx_tid_cleanup(struct ath11k *ar, struct ath11k_peer *peer); void ath11k_peer_rx_tid_delete(struct ath11k *ar, struct ath11k_peer *peer, u8 tid); diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 4df425dd31a2..9d0ff150ec30 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -2779,6 +2779,12 @@ static int ath11k_mac_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, */ spin_lock_bh(&ab->base_lock); peer = ath11k_peer_find(ab, arvif->vdev_id, peer_addr); + + /* flush the fragments cache during key (re)install to + * ensure all frags in the new frag list belong to the same key. + */ + if (peer && cmd == SET_KEY) + ath11k_peer_frags_flush(ar, peer); spin_unlock_bh(&ab->base_lock); if (!peer) { diff --git a/drivers/nfc/nfcmrvl/fw_dnld.h b/drivers/nfc/nfcmrvl/fw_dnld.h index ee4a339c05fd..058ce77b3cbc 100644 --- a/drivers/nfc/nfcmrvl/fw_dnld.h +++ b/drivers/nfc/nfcmrvl/fw_dnld.h @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC driver: Firmware downloader * * Copyright (C) 2015, Marvell International Ltd. diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c index 18cd96284b77..c5420616b7bc 100644 --- a/drivers/nfc/nfcmrvl/i2c.c +++ b/drivers/nfc/nfcmrvl/i2c.c @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC-over-I2C driver: I2C interface related functions * * Copyright (C) 2015, Marvell International Ltd. diff --git a/drivers/nfc/nfcmrvl/nfcmrvl.h b/drivers/nfc/nfcmrvl/nfcmrvl.h index de68ff45e49a..e84ee18c73ae 100644 --- a/drivers/nfc/nfcmrvl/nfcmrvl.h +++ b/drivers/nfc/nfcmrvl/nfcmrvl.h @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC driver * * Copyright (C) 2014-2015, Marvell International Ltd. diff --git a/drivers/nfc/nfcmrvl/spi.c b/drivers/nfc/nfcmrvl/spi.c index 8e0ddb434770..dec0d3eb3648 100644 --- a/drivers/nfc/nfcmrvl/spi.c +++ b/drivers/nfc/nfcmrvl/spi.c @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC-over-SPI driver: SPI interface related functions * * Copyright (C) 2015, Marvell International Ltd. diff --git a/drivers/nfc/nfcmrvl/uart.c b/drivers/nfc/nfcmrvl/uart.c index e5a622ce4b95..7194dd7ef0f1 100644 --- a/drivers/nfc/nfcmrvl/uart.c +++ b/drivers/nfc/nfcmrvl/uart.c @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC-over-UART driver * * Copyright (C) 2015, Marvell International Ltd. diff --git a/drivers/nfc/nfcmrvl/usb.c b/drivers/nfc/nfcmrvl/usb.c index 888e298f610b..bcd563cb556c 100644 --- a/drivers/nfc/nfcmrvl/usb.c +++ b/drivers/nfc/nfcmrvl/usb.c @@ -1,4 +1,4 @@ -/** +/* * Marvell NFC-over-USB driver: USB interface related functions * * Copyright (C) 2014, Marvell International Ltd. diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index a44d49d63968..494675aeaaad 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -71,7 +71,8 @@ config NVME_FC config NVME_TCP tristate "NVM Express over Fabrics TCP host driver" depends on INET - depends on BLK_DEV_NVME + depends on BLOCK + select NVME_CORE select NVME_FABRICS select CRYPTO select CRYPTO_CRC32C diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 762125f2905f..66973bb56305 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3485,8 +3485,10 @@ int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device, cdev_init(cdev, fops); cdev->owner = owner; ret = cdev_device_add(cdev, cdev_device); - if (ret) + if (ret) { + put_device(cdev_device); ida_simple_remove(&nvme_ns_chr_minor_ida, minor); + } return ret; } diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index a2bb7fc63a73..34a84d2086c7 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -336,6 +336,11 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl, cmd->connect.recfmt); break; + case NVME_SC_HOST_PATH_ERROR: + dev_err(ctrl->device, + "Connect command failed: host path error\n"); + break; + default: dev_err(ctrl->device, "Connect command failed, error wo/DNR bit: %d\n", diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 256e87721a01..f183f9fa03d0 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3107,6 +3107,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) if (ctrl->ctrl.icdoff) { dev_err(ctrl->ctrl.device, "icdoff %d is not supported!\n", ctrl->ctrl.icdoff); + ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR; goto out_disconnect_admin_queue; } @@ -3114,6 +3115,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) if (!(ctrl->ctrl.sgls & ((1 << 0) | (1 << 1)))) { dev_err(ctrl->ctrl.device, "Mandatory sgls are not supported!\n"); + ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR; goto out_disconnect_admin_queue; } @@ -3280,11 +3282,13 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) return; - if (portptr->port_state == FC_OBJSTATE_ONLINE) + if (portptr->port_state == FC_OBJSTATE_ONLINE) { dev_info(ctrl->ctrl.device, "NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n", ctrl->cnum, status); - else if (time_after_eq(jiffies, rport->dev_loss_end)) + if (status > 0 && (status & NVME_SC_DNR)) + recon = false; + } else if (time_after_eq(jiffies, rport->dev_loss_end)) recon = false; if (recon && nvmf_should_reconnect(&ctrl->ctrl)) { @@ -3298,12 +3302,17 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) queue_delayed_work(nvme_wq, &ctrl->connect_work, recon_delay); } else { - if (portptr->port_state == FC_OBJSTATE_ONLINE) - dev_warn(ctrl->ctrl.device, - "NVME-FC{%d}: Max reconnect attempts (%d) " - "reached.\n", - ctrl->cnum, ctrl->ctrl.nr_reconnects); - else + if (portptr->port_state == FC_OBJSTATE_ONLINE) { + if (status > 0 && (status & NVME_SC_DNR)) + dev_warn(ctrl->ctrl.device, + "NVME-FC{%d}: reconnect failure\n", + ctrl->cnum); + else + dev_warn(ctrl->ctrl.device, + "NVME-FC{%d}: Max reconnect attempts " + "(%d) reached.\n", + ctrl->cnum, ctrl->ctrl.nr_reconnects); + } else dev_warn(ctrl->ctrl.device, "NVME-FC{%d}: dev_loss_tmo (%d) expired " "while waiting for remoteport connectivity.\n", diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 1853db38b682..4b29a5bac896 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -388,10 +388,10 @@ static void nvmet_keep_alive_timer(struct work_struct *work) { struct nvmet_ctrl *ctrl = container_of(to_delayed_work(work), struct nvmet_ctrl, ka_work); - bool cmd_seen = ctrl->cmd_seen; + bool reset_tbkas = ctrl->reset_tbkas; - ctrl->cmd_seen = false; - if (cmd_seen) { + ctrl->reset_tbkas = false; + if (reset_tbkas) { pr_debug("ctrl %d reschedule traffic based keep-alive timer\n", ctrl->cntlid); schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); @@ -804,6 +804,13 @@ void nvmet_sq_destroy(struct nvmet_sq *sq) percpu_ref_exit(&sq->ref); if (ctrl) { + /* + * The teardown flow may take some time, and the host may not + * send us keep-alive during this period, hence reset the + * traffic based keep-alive timer so we don't trigger a + * controller teardown as a result of a keep-alive expiration. + */ + ctrl->reset_tbkas = true; nvmet_ctrl_put(ctrl); sq->ctrl = NULL; /* allows reusing the queue later */ } @@ -952,7 +959,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, } if (sq->ctrl) - sq->ctrl->cmd_seen = true; + sq->ctrl->reset_tbkas = true; return true; diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index d69a409515d6..53aea9a8056e 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -167,7 +167,7 @@ struct nvmet_ctrl { struct nvmet_subsys *subsys; struct nvmet_sq **sqs; - bool cmd_seen; + bool reset_tbkas; struct mutex lock; u64 cap; diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index f9f34f6caf5e..d8aceef83284 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -550,7 +550,7 @@ static void nvmet_tcp_queue_response(struct nvmet_req *req) * nvmet_req_init is completed. */ if (queue->rcv_state == NVMET_TCP_RECV_PDU && - len && len < cmd->req.port->inline_data_size && + len && len <= cmd->req.port->inline_data_size && nvme_is_write(cmd->req.cmd)) return; } diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 530e5f90095e..0d1034e3ed0f 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -324,7 +324,7 @@ ptp_ocp_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (!bp->base) { dev_err(&pdev->dev, "io_remap bar0\n"); err = -ENOMEM; - goto out; + goto out_release_regions; } bp->reg = bp->base + OCP_REGISTER_OFFSET; bp->tod = bp->base + TOD_REGISTER_OFFSET; @@ -347,6 +347,8 @@ ptp_ocp_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; out: + pci_iounmap(pdev, bp->base); +out_release_regions: pci_release_regions(pdev); out_disable: pci_disable_device(pdev); diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c index 1b9e1442e6a5..fd42a5fffaed 100644 --- a/drivers/s390/block/dasd_diag.c +++ b/drivers/s390/block/dasd_diag.c @@ -642,12 +642,18 @@ static void dasd_diag_setup_blk_queue(struct dasd_block *block) blk_queue_segment_boundary(q, PAGE_SIZE - 1); } +static int dasd_diag_pe_handler(struct dasd_device *device, + __u8 tbvpm, __u8 fcsecpm) +{ + return dasd_generic_verify_path(device, tbvpm); +} + static struct dasd_discipline dasd_diag_discipline = { .owner = THIS_MODULE, .name = "DIAG", .ebcname = "DIAG", .check_device = dasd_diag_check_device, - .verify_path = dasd_generic_verify_path, + .pe_handler = dasd_diag_pe_handler, .fill_geometry = dasd_diag_fill_geometry, .setup_blk_queue = dasd_diag_setup_blk_queue, .start_IO = dasd_start_diag, diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c index 4789410885e4..3ad319aee51e 100644 --- a/drivers/s390/block/dasd_fba.c +++ b/drivers/s390/block/dasd_fba.c @@ -794,13 +794,19 @@ static void dasd_fba_setup_blk_queue(struct dasd_block *block) blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } +static int dasd_fba_pe_handler(struct dasd_device *device, + __u8 tbvpm, __u8 fcsecpm) +{ + return dasd_generic_verify_path(device, tbvpm); +} + static struct dasd_discipline dasd_fba_discipline = { .owner = THIS_MODULE, .name = "FBA ", .ebcname = "FBA ", .check_device = dasd_fba_check_characteristics, .do_analysis = dasd_fba_do_analysis, - .verify_path = dasd_generic_verify_path, + .pe_handler = dasd_fba_pe_handler, .setup_blk_queue = dasd_fba_setup_blk_queue, .fill_geometry = dasd_fba_fill_geometry, .start_IO = dasd_start_IO, diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 1c59b0e86a9f..155428bfed8a 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -297,7 +297,6 @@ struct dasd_discipline { * e.g. verify that new path is compatible with the current * configuration. */ - int (*verify_path)(struct dasd_device *, __u8); int (*pe_handler)(struct dasd_device *, __u8, __u8); /* diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index b9febc581b1f..8d1b2771c1aa 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -638,6 +638,10 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb) static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 1); int ret; + /* this is an error in the caller */ + if (cp->initialized) + return -EBUSY; + /* * We only support prefetching the channel program. We assume all channel * programs executed by supported guests likewise support prefetching. diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index 8c625b530035..9b61e9b131ad 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -86,6 +86,7 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work) struct vfio_ccw_private *private; struct irb *irb; bool is_final; + bool cp_is_finished = false; private = container_of(work, struct vfio_ccw_private, io_work); irb = &private->irb; @@ -94,14 +95,21 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work) (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT)); if (scsw_is_solicited(&irb->scsw)) { cp_update_scsw(&private->cp, &irb->scsw); - if (is_final && private->state == VFIO_CCW_STATE_CP_PENDING) + if (is_final && private->state == VFIO_CCW_STATE_CP_PENDING) { cp_free(&private->cp); + cp_is_finished = true; + } } mutex_lock(&private->io_mutex); memcpy(private->io_region->irb_area, irb, sizeof(*irb)); mutex_unlock(&private->io_mutex); - if (private->mdev && is_final) + /* + * Reset to IDLE only if processing of a channel program + * has finished. Do not overwrite a possible processing + * state if the final interrupt was for HSCH or CSCH. + */ + if (private->mdev && cp_is_finished) private->state = VFIO_CCW_STATE_IDLE; if (private->io_trigger) diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c index 23e61aa638e4..e435a9cd92da 100644 --- a/drivers/s390/cio/vfio_ccw_fsm.c +++ b/drivers/s390/cio/vfio_ccw_fsm.c @@ -318,6 +318,7 @@ static void fsm_io_request(struct vfio_ccw_private *private, } err_out: + private->state = VFIO_CCW_STATE_IDLE; trace_vfio_ccw_fsm_io_request(scsw->cmd.fctl, schid, io_region->ret_code, errstr); } diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c index 491a64c61fff..c57d2a7f0919 100644 --- a/drivers/s390/cio/vfio_ccw_ops.c +++ b/drivers/s390/cio/vfio_ccw_ops.c @@ -279,8 +279,6 @@ static ssize_t vfio_ccw_mdev_write_io_region(struct vfio_ccw_private *private, } vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_IO_REQ); - if (region->ret_code != 0) - private->state = VFIO_CCW_STATE_IDLE; ret = (region->ret_code != 0) ? region->ret_code : count; out_unlock: diff --git a/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y b/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y index 924d55a8acbf..65182ad9cdf8 100644 --- a/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y +++ b/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y @@ -58,7 +58,6 @@ #include "aicasm_symbol.h" #include "aicasm_insformat.h" -int yylineno; char *yyfilename; char stock_prefix[] = "aic_"; char *prefix = stock_prefix; diff --git a/drivers/scsi/aic7xxx/aicasm/aicasm_symbol.h b/drivers/scsi/aic7xxx/aicasm/aicasm_symbol.h index 7bf7fd5953ac..ed3bdd43c297 100644 --- a/drivers/scsi/aic7xxx/aicasm/aicasm_symbol.h +++ b/drivers/scsi/aic7xxx/aicasm/aicasm_symbol.h @@ -108,7 +108,7 @@ struct macro_arg { regex_t arg_regex; char *replacement_text; }; -STAILQ_HEAD(macro_arg_list, macro_arg) args; +STAILQ_HEAD(macro_arg_list, macro_arg); struct macro_info { struct macro_arg_list args; diff --git a/drivers/scsi/aic7xxx/scsi_message.h b/drivers/scsi/aic7xxx/scsi_message.h index a7515c3039ed..53343a6d8ae1 100644 --- a/drivers/scsi/aic7xxx/scsi_message.h +++ b/drivers/scsi/aic7xxx/scsi_message.h @@ -3,6 +3,17 @@ * $FreeBSD: src/sys/cam/scsi/scsi_message.h,v 1.2 2000/05/01 20:21:29 peter Exp $ */ +/* Messages (1 byte) */ /* I/T (M)andatory or (O)ptional */ +#define MSG_SAVEDATAPOINTER 0x02 /* O/O */ +#define MSG_RESTOREPOINTERS 0x03 /* O/O */ +#define MSG_DISCONNECT 0x04 /* O/O */ +#define MSG_MESSAGE_REJECT 0x07 /* M/M */ +#define MSG_NOOP 0x08 /* M/M */ + +/* Messages (2 byte) */ +#define MSG_SIMPLE_Q_TAG 0x20 /* O/O */ +#define MSG_IGN_WIDE_RESIDUE 0x23 /* O/O */ + /* Identify message */ /* M/M */ #define MSG_IDENTIFYFLAG 0x80 #define MSG_IDENTIFY_DISCFLAG 0x40 diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c index 1a0dc18d6915..ed300a279a38 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_io.c +++ b/drivers/scsi/bnx2fc/bnx2fc_io.c @@ -1220,6 +1220,7 @@ int bnx2fc_eh_abort(struct scsi_cmnd *sc_cmd) was a result from the ABTS request rather than the CLEANUP request */ set_bit(BNX2FC_FLAG_IO_CLEANUP, &io_req->req_flags); + rc = FAILED; goto done; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 499c770d405c..e95408314078 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -4811,14 +4811,14 @@ hisi_sas_v3_destroy_irqs(struct pci_dev *pdev, struct hisi_hba *hisi_hba) { int i; - free_irq(pci_irq_vector(pdev, 1), hisi_hba); - free_irq(pci_irq_vector(pdev, 2), hisi_hba); - free_irq(pci_irq_vector(pdev, 11), hisi_hba); + devm_free_irq(&pdev->dev, pci_irq_vector(pdev, 1), hisi_hba); + devm_free_irq(&pdev->dev, pci_irq_vector(pdev, 2), hisi_hba); + devm_free_irq(&pdev->dev, pci_irq_vector(pdev, 11), hisi_hba); for (i = 0; i < hisi_hba->cq_nvecs; i++) { struct hisi_sas_cq *cq = &hisi_hba->cq[i]; int nr = hisi_sas_intr_conv ? 16 : 16 + i; - free_irq(pci_irq_vector(pdev, nr), cq); + devm_free_irq(&pdev->dev, pci_irq_vector(pdev, nr), cq); } pci_free_irq_vectors(pdev); } diff --git a/drivers/scsi/libsas/sas_port.c b/drivers/scsi/libsas/sas_port.c index 19cf418928fa..e3d03d744713 100644 --- a/drivers/scsi/libsas/sas_port.c +++ b/drivers/scsi/libsas/sas_port.c @@ -25,7 +25,7 @@ static bool phy_is_wideport_member(struct asd_sas_port *port, struct asd_sas_phy static void sas_resume_port(struct asd_sas_phy *phy) { - struct domain_device *dev; + struct domain_device *dev, *n; struct asd_sas_port *port = phy->port; struct sas_ha_struct *sas_ha = phy->ha; struct sas_internal *si = to_sas_internal(sas_ha->core.shost->transportt); @@ -44,7 +44,7 @@ static void sas_resume_port(struct asd_sas_phy *phy) * 1/ presume every device came back * 2/ force the next revalidation to check all expander phys */ - list_for_each_entry(dev, &port->dev_list, dev_list_node) { + list_for_each_entry_safe(dev, n, &port->dev_list, dev_list_node) { int i, rc; rc = sas_notify_lldd_dev_found(dev); diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index b2008fb1dd38..12a6848ade43 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1563,10 +1563,12 @@ void qlt_stop_phase2(struct qla_tgt *tgt) return; } + mutex_lock(&tgt->ha->optrom_mutex); mutex_lock(&vha->vha_tgt.tgt_mutex); tgt->tgt_stop = 0; tgt->tgt_stopped = 1; mutex_unlock(&vha->vha_tgt.tgt_mutex); + mutex_unlock(&tgt->ha->optrom_mutex); ql_dbg(ql_dbg_tgt_mgt, vha, 0xf00c, "Stop of tgt %p finished\n", tgt); diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c index 8a79605d9652..b9969fce6b4d 100644 --- a/drivers/scsi/vmw_pvscsi.c +++ b/drivers/scsi/vmw_pvscsi.c @@ -585,7 +585,13 @@ static void pvscsi_complete_request(struct pvscsi_adapter *adapter, case BTSTAT_SUCCESS: case BTSTAT_LINKED_COMMAND_COMPLETED: case BTSTAT_LINKED_COMMAND_COMPLETED_WITH_FLAG: - /* If everything went fine, let's move on.. */ + /* + * Commands like INQUIRY may transfer less data than + * requested by the initiator via bufflen. Set residual + * count to make upper layer aware of the actual amount + * of data returned. + */ + scsi_set_resid(cmd, scsi_bufflen(cmd) - e->dataLen); cmd->result = (DID_OK << 16); break; diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c index 2827085a323b..0ef79d60e88e 100644 --- a/drivers/soundwire/qcom.c +++ b/drivers/soundwire/qcom.c @@ -1150,8 +1150,16 @@ static int qcom_swrm_get_port_config(struct qcom_swrm_ctrl *ctrl) ret = of_property_read_u8_array(np, "qcom,ports-block-pack-mode", bp_mode, nports); - if (ret) - return ret; + if (ret) { + u32 version; + + ctrl->reg_read(ctrl, SWRM_COMP_HW_VERSION, &version); + + if (version <= 0x01030000) + memset(bp_mode, SWR_INVALID_PARAM, QCOM_SDW_MAX_PORTS); + else + return ret; + } memset(hstart, SWR_INVALID_PARAM, QCOM_SDW_MAX_PORTS); of_property_read_u8_array(np, "qcom,ports-hstart", hstart, nports); diff --git a/drivers/staging/emxx_udc/emxx_udc.c b/drivers/staging/emxx_udc/emxx_udc.c index 741147a4f0fe..ecc5c9da9027 100644 --- a/drivers/staging/emxx_udc/emxx_udc.c +++ b/drivers/staging/emxx_udc/emxx_udc.c @@ -2064,7 +2064,7 @@ static int _nbu2ss_nuke(struct nbu2ss_udc *udc, struct nbu2ss_ep *ep, int status) { - struct nbu2ss_req *req; + struct nbu2ss_req *req, *n; /* Endpoint Disable */ _nbu2ss_epn_exit(udc, ep); @@ -2076,7 +2076,7 @@ static int _nbu2ss_nuke(struct nbu2ss_udc *udc, return 0; /* called with irqs blocked */ - list_for_each_entry(req, &ep->queue, queue) { + list_for_each_entry_safe(req, n, &ep->queue, queue) { _nbu2ss_ep_done(ep, req, status); } diff --git a/drivers/staging/iio/cdc/ad7746.c b/drivers/staging/iio/cdc/ad7746.c index dfd71e99e872..eab534dc4bcc 100644 --- a/drivers/staging/iio/cdc/ad7746.c +++ b/drivers/staging/iio/cdc/ad7746.c @@ -700,7 +700,6 @@ static int ad7746_probe(struct i2c_client *client, indio_dev->num_channels = ARRAY_SIZE(ad7746_channels); else indio_dev->num_channels = ARRAY_SIZE(ad7746_channels) - 2; - indio_dev->num_channels = ARRAY_SIZE(ad7746_channels); indio_dev->modes = INDIO_DIRECT_MODE; if (pdata) { diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index d6fdd1c61f90..a526f9678c34 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -204,11 +204,11 @@ static struct se_dev_plug *iblock_plug_device(struct se_device *se_dev) struct iblock_dev_plug *ib_dev_plug; /* - * Each se_device has a per cpu work this can be run from. Wwe + * Each se_device has a per cpu work this can be run from. We * shouldn't have multiple threads on the same cpu calling this * at the same time. */ - ib_dev_plug = &ib_dev->ibd_plug[smp_processor_id()]; + ib_dev_plug = &ib_dev->ibd_plug[raw_smp_processor_id()]; if (test_and_set_bit(IBD_PLUGF_PLUGGED, &ib_dev_plug->flags)) return NULL; diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 8fbfe75c5744..05d7ffd59df6 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1416,7 +1416,7 @@ void __target_init_cmd( cmd->orig_fe_lun = unpacked_lun; if (!(cmd->se_cmd_flags & SCF_USE_CPUID)) - cmd->cpuid = smp_processor_id(); + cmd->cpuid = raw_smp_processor_id(); cmd->state_active = false; } diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 198d25ae482a..4bba10e7755a 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -516,8 +516,10 @@ static inline int tcmu_get_empty_block(struct tcmu_dev *udev, dpi = dbi * udev->data_pages_per_blk; /* Count the number of already allocated pages */ xas_set(&xas, dpi); + rcu_read_lock(); for (cnt = 0; xas_next(&xas) && cnt < page_cnt;) cnt++; + rcu_read_unlock(); for (i = cnt; i < page_cnt; i++) { /* try to get new page from the mm */ @@ -699,11 +701,10 @@ static inline void tcmu_copy_data(struct tcmu_dev *udev, struct scatterlist *sg, unsigned int sg_nents, struct iovec **iov, size_t data_len) { - XA_STATE(xas, &udev->data_pages, 0); /* start value of dbi + 1 must not be a valid dbi */ int dbi = -2; size_t page_remaining, cp_len; - int page_cnt, page_inx; + int page_cnt, page_inx, dpi; struct sg_mapping_iter sg_iter; unsigned int sg_flags; struct page *page; @@ -726,9 +727,10 @@ static inline void tcmu_copy_data(struct tcmu_dev *udev, if (page_cnt > udev->data_pages_per_blk) page_cnt = udev->data_pages_per_blk; - xas_set(&xas, dbi * udev->data_pages_per_blk); - for (page_inx = 0; page_inx < page_cnt && data_len; page_inx++) { - page = xas_next(&xas); + dpi = dbi * udev->data_pages_per_blk; + for (page_inx = 0; page_inx < page_cnt && data_len; + page_inx++, dpi++) { + page = xa_load(&udev->data_pages, dpi); if (direction == TCMU_DATA_AREA_TO_SG) flush_dcache_page(page); diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c index d1248ba943a4..62c0aa5d0783 100644 --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c @@ -237,6 +237,8 @@ struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev, if (ACPI_FAILURE(status)) trip_cnt = 0; else { + int i; + int34x_thermal_zone->aux_trips = kcalloc(trip_cnt, sizeof(*int34x_thermal_zone->aux_trips), @@ -247,6 +249,8 @@ struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev, } trip_mask = BIT(trip_cnt) - 1; int34x_thermal_zone->aux_trip_nr = trip_cnt; + for (i = 0; i < trip_cnt; ++i) + int34x_thermal_zone->aux_trips[i] = THERMAL_TEMP_INVALID; } trip_cnt = int340x_thermal_read_trips(int34x_thermal_zone); diff --git a/drivers/thermal/intel/x86_pkg_temp_thermal.c b/drivers/thermal/intel/x86_pkg_temp_thermal.c index 295742e83960..4d8edc61a78b 100644 --- a/drivers/thermal/intel/x86_pkg_temp_thermal.c +++ b/drivers/thermal/intel/x86_pkg_temp_thermal.c @@ -166,7 +166,7 @@ static int sys_get_trip_temp(struct thermal_zone_device *tzd, if (thres_reg_value) *temp = zonedev->tj_max - thres_reg_value * 1000; else - *temp = 0; + *temp = THERMAL_TEMP_INVALID; pr_debug("sys_get_trip_temp %d\n", *temp); return 0; diff --git a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c index b460b56e981c..232fd0b33325 100644 --- a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c +++ b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c @@ -441,7 +441,7 @@ static int adc_tm5_get_dt_channel_data(struct adc_tm5_chip *adc_tm, if (args.args_count != 1 || args.args[0] >= ADC5_MAX_CHANNEL) { dev_err(dev, "%s: invalid ADC channel number %d\n", name, chan); - return ret; + return -EINVAL; } channel->adc_channel = args.args[0]; diff --git a/drivers/thermal/ti-soc-thermal/ti-bandgap.c b/drivers/thermal/ti-soc-thermal/ti-bandgap.c index ebe7cb70bfb6..ea0603b59309 100644 --- a/drivers/thermal/ti-soc-thermal/ti-bandgap.c +++ b/drivers/thermal/ti-soc-thermal/ti-bandgap.c @@ -770,7 +770,7 @@ static int ti_bandgap_tshut_init(struct ti_bandgap *bgp, } /** - * ti_bandgap_alert_init() - setup and initialize talert handling + * ti_bandgap_talert_init() - setup and initialize talert handling * @bgp: pointer to struct ti_bandgap * @pdev: pointer to device struct platform_device * diff --git a/drivers/thunderbolt/dma_port.c b/drivers/thunderbolt/dma_port.c index 7288aaf01ae6..5631319f7b20 100644 --- a/drivers/thunderbolt/dma_port.c +++ b/drivers/thunderbolt/dma_port.c @@ -366,15 +366,15 @@ int dma_port_flash_read(struct tb_dma_port *dma, unsigned int address, void *buf, size_t size) { unsigned int retries = DMA_PORT_RETRIES; - unsigned int offset; - - offset = address & 3; - address = address & ~3; do { - u32 nbytes = min_t(u32, size, MAIL_DATA_DWORDS * 4); + unsigned int offset; + size_t nbytes; int ret; + offset = address & 3; + nbytes = min_t(size_t, size + offset, MAIL_DATA_DWORDS * 4); + ret = dma_port_flash_read_block(dma, address, dma->buf, ALIGN(nbytes, 4)); if (ret) { @@ -386,6 +386,7 @@ int dma_port_flash_read(struct tb_dma_port *dma, unsigned int address, return ret; } + nbytes -= offset; memcpy(buf, dma->buf + offset, nbytes); size -= nbytes; diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 680bc738dd66..671d72af8ba1 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -68,15 +68,15 @@ static int usb4_do_read_data(u16 address, void *buf, size_t size, unsigned int retries = USB4_DATA_RETRIES; unsigned int offset; - offset = address & 3; - address = address & ~3; - do { - size_t nbytes = min_t(size_t, size, USB4_DATA_DWORDS * 4); unsigned int dwaddress, dwords; u8 data[USB4_DATA_DWORDS * 4]; + size_t nbytes; int ret; + offset = address & 3; + nbytes = min_t(size_t, size + offset, USB4_DATA_DWORDS * 4); + dwaddress = address / 4; dwords = ALIGN(nbytes, 4) / 4; @@ -87,6 +87,7 @@ static int usb4_do_read_data(u16 address, void *buf, size_t size, return ret; } + nbytes -= offset; memcpy(buf, data + offset, nbytes); size -= nbytes; diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h index 52bb21205bb6..6473361525d1 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -7,6 +7,7 @@ * Copyright (C) 2001 Russell King. */ +#include <linux/bits.h> #include <linux/serial_8250.h> #include <linux/serial_reg.h> #include <linux/dmaengine.h> @@ -70,24 +71,25 @@ struct serial8250_config { unsigned int flags; }; -#define UART_CAP_FIFO (1 << 8) /* UART has FIFO */ -#define UART_CAP_EFR (1 << 9) /* UART has EFR */ -#define UART_CAP_SLEEP (1 << 10) /* UART has IER sleep */ -#define UART_CAP_AFE (1 << 11) /* MCR-based hw flow control */ -#define UART_CAP_UUE (1 << 12) /* UART needs IER bit 6 set (Xscale) */ -#define UART_CAP_RTOIE (1 << 13) /* UART needs IER bit 4 set (Xscale, Tegra) */ -#define UART_CAP_HFIFO (1 << 14) /* UART has a "hidden" FIFO */ -#define UART_CAP_RPM (1 << 15) /* Runtime PM is active while idle */ -#define UART_CAP_IRDA (1 << 16) /* UART supports IrDA line discipline */ -#define UART_CAP_MINI (1 << 17) /* Mini UART on BCM283X family lacks: +#define UART_CAP_FIFO BIT(8) /* UART has FIFO */ +#define UART_CAP_EFR BIT(9) /* UART has EFR */ +#define UART_CAP_SLEEP BIT(10) /* UART has IER sleep */ +#define UART_CAP_AFE BIT(11) /* MCR-based hw flow control */ +#define UART_CAP_UUE BIT(12) /* UART needs IER bit 6 set (Xscale) */ +#define UART_CAP_RTOIE BIT(13) /* UART needs IER bit 4 set (Xscale, Tegra) */ +#define UART_CAP_HFIFO BIT(14) /* UART has a "hidden" FIFO */ +#define UART_CAP_RPM BIT(15) /* Runtime PM is active while idle */ +#define UART_CAP_IRDA BIT(16) /* UART supports IrDA line discipline */ +#define UART_CAP_MINI BIT(17) /* Mini UART on BCM283X family lacks: * STOP PARITY EPAR SPAR WLEN5 WLEN6 */ -#define UART_BUG_QUOT (1 << 0) /* UART has buggy quot LSB */ -#define UART_BUG_TXEN (1 << 1) /* UART has buggy TX IIR status */ -#define UART_BUG_NOMSR (1 << 2) /* UART has buggy MSR status bits (Au1x00) */ -#define UART_BUG_THRE (1 << 3) /* UART has buggy THRE reassertion */ -#define UART_BUG_PARITY (1 << 4) /* UART mishandles parity if FIFO enabled */ +#define UART_BUG_QUOT BIT(0) /* UART has buggy quot LSB */ +#define UART_BUG_TXEN BIT(1) /* UART has buggy TX IIR status */ +#define UART_BUG_NOMSR BIT(2) /* UART has buggy MSR status bits (Au1x00) */ +#define UART_BUG_THRE BIT(3) /* UART has buggy THRE reassertion */ +#define UART_BUG_PARITY BIT(4) /* UART mishandles parity if FIFO enabled */ +#define UART_BUG_TXRACE BIT(5) /* UART Tx fails to set remote DR */ #ifdef CONFIG_SERIAL_8250_SHARE_IRQ diff --git a/drivers/tty/serial/8250/8250_aspeed_vuart.c b/drivers/tty/serial/8250/8250_aspeed_vuart.c index 61550f24a2d3..d035d08cb987 100644 --- a/drivers/tty/serial/8250/8250_aspeed_vuart.c +++ b/drivers/tty/serial/8250/8250_aspeed_vuart.c @@ -437,6 +437,7 @@ static int aspeed_vuart_probe(struct platform_device *pdev) port.port.status = UPSTAT_SYNC_FIFO; port.port.dev = &pdev->dev; port.port.has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE); + port.bugs |= UART_BUG_TXRACE; rc = sysfs_create_group(&vuart->dev->kobj, &aspeed_vuart_attr_group); if (rc < 0) diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c index 9e204f9b799a..a3a0154da567 100644 --- a/drivers/tty/serial/8250/8250_dw.c +++ b/drivers/tty/serial/8250/8250_dw.c @@ -714,6 +714,7 @@ static const struct acpi_device_id dw8250_acpi_match[] = { { "APMC0D08", 0}, { "AMD0020", 0 }, { "AMDI0020", 0 }, + { "AMDI0022", 0 }, { "BRCM2032", 0 }, { "HISI0031", 0 }, { }, diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 689d8227f95f..780cc99732b6 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -56,6 +56,8 @@ struct serial_private { int line[]; }; +#define PCI_DEVICE_ID_HPE_PCI_SERIAL 0x37e + static const struct pci_device_id pci_use_msi[] = { { PCI_DEVICE_SUB(PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9900, 0xA000, 0x1000) }, @@ -63,6 +65,8 @@ static const struct pci_device_id pci_use_msi[] = { 0xA000, 0x1000) }, { PCI_DEVICE_SUB(PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9922, 0xA000, 0x1000) }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_HP_3PAR, PCI_DEVICE_ID_HPE_PCI_SERIAL, + PCI_ANY_ID, PCI_ANY_ID) }, { } }; @@ -1998,6 +2002,16 @@ static struct pci_serial_quirk pci_serial_quirks[] = { .setup = pci_hp_diva_setup, }, /* + * HPE PCI serial device + */ + { + .vendor = PCI_VENDOR_ID_HP_3PAR, + .device = PCI_DEVICE_ID_HPE_PCI_SERIAL, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = pci_hp_diva_setup, + }, + /* * Intel */ { @@ -3944,21 +3958,26 @@ pciserial_init_ports(struct pci_dev *dev, const struct pciserial_board *board) uart.port.flags = UPF_SKIP_TEST | UPF_BOOT_AUTOCONF | UPF_SHARE_IRQ; uart.port.uartclk = board->base_baud * 16; - if (pci_match_id(pci_use_msi, dev)) { - dev_dbg(&dev->dev, "Using MSI(-X) interrupts\n"); - pci_set_master(dev); - rc = pci_alloc_irq_vectors(dev, 1, 1, PCI_IRQ_ALL_TYPES); + if (board->flags & FL_NOIRQ) { + uart.port.irq = 0; } else { - dev_dbg(&dev->dev, "Using legacy interrupts\n"); - rc = pci_alloc_irq_vectors(dev, 1, 1, PCI_IRQ_LEGACY); - } - if (rc < 0) { - kfree(priv); - priv = ERR_PTR(rc); - goto err_deinit; + if (pci_match_id(pci_use_msi, dev)) { + dev_dbg(&dev->dev, "Using MSI(-X) interrupts\n"); + pci_set_master(dev); + rc = pci_alloc_irq_vectors(dev, 1, 1, PCI_IRQ_ALL_TYPES); + } else { + dev_dbg(&dev->dev, "Using legacy interrupts\n"); + rc = pci_alloc_irq_vectors(dev, 1, 1, PCI_IRQ_LEGACY); + } + if (rc < 0) { + kfree(priv); + priv = ERR_PTR(rc); + goto err_deinit; + } + + uart.port.irq = pci_irq_vector(dev, 0); } - uart.port.irq = pci_irq_vector(dev, 0); uart.port.dev = &dev->dev; for (i = 0; i < nr_ports; i++) { @@ -4973,6 +4992,10 @@ static const struct pci_device_id serial_pci_tbl[] = { { PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_DIVA_AUX, PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_b2_1_115200 }, + /* HPE PCI serial device */ + { PCI_VENDOR_ID_HP_3PAR, PCI_DEVICE_ID_HPE_PCI_SERIAL, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_b1_1_115200 }, { PCI_VENDOR_ID_DCI, PCI_DEVICE_ID_DCI_PCCOM2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index d45dab1ab316..fc5ab2032282 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1809,6 +1809,18 @@ void serial8250_tx_chars(struct uart_8250_port *up) count = up->tx_loadsz; do { serial_out(up, UART_TX, xmit->buf[xmit->tail]); + if (up->bugs & UART_BUG_TXRACE) { + /* + * The Aspeed BMC virtual UARTs have a bug where data + * may get stuck in the BMC's Tx FIFO from bursts of + * writes on the APB interface. + * + * Delay back-to-back writes by a read cycle to avoid + * stalling the VUART. Read a register that won't have + * side-effects and discard the result. + */ + serial_in(up, UART_SCR); + } xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1); port->icount.tx++; if (uart_circ_empty(xmit)) diff --git a/drivers/tty/serial/rp2.c b/drivers/tty/serial/rp2.c index d60abffab70e..6689d8add8f7 100644 --- a/drivers/tty/serial/rp2.c +++ b/drivers/tty/serial/rp2.c @@ -195,7 +195,6 @@ struct rp2_card { void __iomem *bar0; void __iomem *bar1; spinlock_t card_lock; - struct completion fw_loaded; }; #define RP_ID(prod) PCI_VDEVICE(RP, (prod)) @@ -662,17 +661,10 @@ static void rp2_remove_ports(struct rp2_card *card) card->initialized_ports = 0; } -static void rp2_fw_cb(const struct firmware *fw, void *context) +static int rp2_load_firmware(struct rp2_card *card, const struct firmware *fw) { - struct rp2_card *card = context; resource_size_t phys_base; - int i, rc = -ENOENT; - - if (!fw) { - dev_err(&card->pdev->dev, "cannot find '%s' firmware image\n", - RP2_FW_NAME); - goto no_fw; - } + int i, rc = 0; phys_base = pci_resource_start(card->pdev, 1); @@ -718,23 +710,13 @@ static void rp2_fw_cb(const struct firmware *fw, void *context) card->initialized_ports++; } - release_firmware(fw); -no_fw: - /* - * rp2_fw_cb() is called from a workqueue long after rp2_probe() - * has already returned success. So if something failed here, - * we'll just leave the now-dormant device in place until somebody - * unbinds it. - */ - if (rc) - dev_warn(&card->pdev->dev, "driver initialization failed\n"); - - complete(&card->fw_loaded); + return rc; } static int rp2_probe(struct pci_dev *pdev, const struct pci_device_id *id) { + const struct firmware *fw; struct rp2_card *card; struct rp2_uart_port *ports; void __iomem * const *bars; @@ -745,7 +727,6 @@ static int rp2_probe(struct pci_dev *pdev, return -ENOMEM; pci_set_drvdata(pdev, card); spin_lock_init(&card->card_lock); - init_completion(&card->fw_loaded); rc = pcim_enable_device(pdev); if (rc) @@ -778,21 +759,23 @@ static int rp2_probe(struct pci_dev *pdev, return -ENOMEM; card->ports = ports; - rc = devm_request_irq(&pdev->dev, pdev->irq, rp2_uart_interrupt, - IRQF_SHARED, DRV_NAME, card); - if (rc) + rc = request_firmware(&fw, RP2_FW_NAME, &pdev->dev); + if (rc < 0) { + dev_err(&pdev->dev, "cannot find '%s' firmware image\n", + RP2_FW_NAME); return rc; + } - /* - * Only catastrophic errors (e.g. ENOMEM) are reported here. - * If the FW image is missing, we'll find out in rp2_fw_cb() - * and print an error message. - */ - rc = request_firmware_nowait(THIS_MODULE, 1, RP2_FW_NAME, &pdev->dev, - GFP_KERNEL, card, rp2_fw_cb); + rc = rp2_load_firmware(card, fw); + + release_firmware(fw); + if (rc < 0) + return rc; + + rc = devm_request_irq(&pdev->dev, pdev->irq, rp2_uart_interrupt, + IRQF_SHARED, DRV_NAME, card); if (rc) return rc; - dev_dbg(&pdev->dev, "waiting for firmware blob...\n"); return 0; } @@ -801,7 +784,6 @@ static void rp2_remove(struct pci_dev *pdev) { struct rp2_card *card = pci_get_drvdata(pdev); - wait_for_completion(&card->fw_loaded); rp2_remove_ports(card); } diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c index bbae072a125d..222032792d6c 100644 --- a/drivers/tty/serial/serial-tegra.c +++ b/drivers/tty/serial/serial-tegra.c @@ -338,7 +338,7 @@ static void tegra_uart_fifo_reset(struct tegra_uart_port *tup, u8 fcr_bits) do { lsr = tegra_uart_read(tup, UART_LSR); - if ((lsr | UART_LSR_TEMT) && !(lsr & UART_LSR_DR)) + if ((lsr & UART_LSR_TEMT) && !(lsr & UART_LSR_DR)) break; udelay(1); } while (--tmout); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 87f7127b57e6..18ff85a83f80 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -863,9 +863,11 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port, goto check_and_exit; } - retval = security_locked_down(LOCKDOWN_TIOCSSERIAL); - if (retval && (change_irq || change_port)) - goto exit; + if (change_irq || change_port) { + retval = security_locked_down(LOCKDOWN_TIOCSSERIAL); + if (retval) + goto exit; + } /* * Ask the low level driver to verify the settings. diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index ef37fdf37612..4baf1316ea72 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1023,10 +1023,10 @@ static int scif_set_rtrg(struct uart_port *port, int rx_trig) { unsigned int bits; + if (rx_trig >= port->fifosize) + rx_trig = port->fifosize - 1; if (rx_trig < 1) rx_trig = 1; - if (rx_trig >= port->fifosize) - rx_trig = port->fifosize; /* HSCIF can be set to an arbitrary level. */ if (sci_getreg(port, HSRTRGR)->size) { diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c index 9b1bd417cec0..a8b7b50abf64 100644 --- a/drivers/usb/cdns3/cdns3-gadget.c +++ b/drivers/usb/cdns3/cdns3-gadget.c @@ -3268,8 +3268,10 @@ static int __cdns3_gadget_init(struct cdns *cdns) pm_runtime_get_sync(cdns->dev); ret = cdns3_gadget_start(cdns); - if (ret) + if (ret) { + pm_runtime_put_sync(cdns->dev); return ret; + } /* * Because interrupt line can be shared with other components in diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c index 56707b6b0f57..c083985e387b 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.c +++ b/drivers/usb/cdns3/cdnsp-gadget.c @@ -422,17 +422,17 @@ unmap: int cdnsp_ep_dequeue(struct cdnsp_ep *pep, struct cdnsp_request *preq) { struct cdnsp_device *pdev = pep->pdev; - int ret; + int ret_stop = 0; + int ret_rem; trace_cdnsp_request_dequeue(preq); - if (GET_EP_CTX_STATE(pep->out_ctx) == EP_STATE_RUNNING) { - ret = cdnsp_cmd_stop_ep(pdev, pep); - if (ret) - return ret; - } + if (GET_EP_CTX_STATE(pep->out_ctx) == EP_STATE_RUNNING) + ret_stop = cdnsp_cmd_stop_ep(pdev, pep); + + ret_rem = cdnsp_remove_request(pdev, preq, pep); - return cdnsp_remove_request(pdev, preq, pep); + return ret_rem ? ret_rem : ret_stop; } static void cdnsp_zero_in_ctx(struct cdnsp_device *pdev) diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c index c16d900cdaee..393f216b9161 100644 --- a/drivers/usb/chipidea/udc.c +++ b/drivers/usb/chipidea/udc.c @@ -2061,6 +2061,7 @@ static int udc_start(struct ci_hdrc *ci) ci->gadget.name = ci->platdata->name; ci->gadget.otg_caps = otg_caps; ci->gadget.sg_supported = 1; + ci->gadget.irq = ci->irq; if (ci->platdata->flags & CI_HDRC_REQUIRES_ALIGNED_DMA) ci->gadget.quirk_avoids_skb_reserve = 1; diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 533236366a03..2218941d35a3 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -1218,7 +1218,12 @@ static int do_proc_bulk(struct usb_dev_state *ps, ret = usbfs_increase_memory_usage(len1 + sizeof(struct urb)); if (ret) return ret; - tbuf = kmalloc(len1, GFP_KERNEL); + + /* + * len1 can be almost arbitrarily large. Don't WARN if it's + * too big, just fail the request. + */ + tbuf = kmalloc(len1, GFP_KERNEL | __GFP_NOWARN); if (!tbuf) { ret = -ENOMEM; goto done; @@ -1696,7 +1701,7 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb if (num_sgs) { as->urb->sg = kmalloc_array(num_sgs, sizeof(struct scatterlist), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (!as->urb->sg) { ret = -ENOMEM; goto error; @@ -1731,7 +1736,7 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb (uurb_start - as->usbm->vm_start); } else { as->urb->transfer_buffer = kmalloc(uurb->buffer_length, - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (!as->urb->transfer_buffer) { ret = -ENOMEM; goto error; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 49ca5da5e279..612825a39f82 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1244,6 +1244,7 @@ static int dwc3_prepare_trbs_sg(struct dwc3_ep *dep, req->start_sg = sg_next(s); req->num_queued_sgs++; + req->num_pending_sgs--; /* * The number of pending SG entries may not correspond to the @@ -1251,7 +1252,7 @@ static int dwc3_prepare_trbs_sg(struct dwc3_ep *dep, * don't include unused SG entries. */ if (length == 0) { - req->num_pending_sgs -= req->request.num_mapped_sgs - req->num_queued_sgs; + req->num_pending_sgs = 0; break; } @@ -2873,15 +2874,15 @@ static int dwc3_gadget_ep_reclaim_trb_sg(struct dwc3_ep *dep, struct dwc3_trb *trb = &dep->trb_pool[dep->trb_dequeue]; struct scatterlist *sg = req->sg; struct scatterlist *s; - unsigned int pending = req->num_pending_sgs; + unsigned int num_queued = req->num_queued_sgs; unsigned int i; int ret = 0; - for_each_sg(sg, s, pending, i) { + for_each_sg(sg, s, num_queued, i) { trb = &dep->trb_pool[dep->trb_dequeue]; req->sg = sg_next(s); - req->num_pending_sgs--; + req->num_queued_sgs--; ret = dwc3_gadget_ep_reclaim_completed_trb(dep, req, trb, event, status, true); @@ -2904,7 +2905,7 @@ static int dwc3_gadget_ep_reclaim_trb_linear(struct dwc3_ep *dep, static bool dwc3_gadget_ep_request_completed(struct dwc3_request *req) { - return req->num_pending_sgs == 0; + return req->num_pending_sgs == 0 && req->num_queued_sgs == 0; } static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep, @@ -2913,7 +2914,7 @@ static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep, { int ret; - if (req->num_pending_sgs) + if (req->request.num_mapped_sgs) ret = dwc3_gadget_ep_reclaim_trb_sg(dep, req, event, status); else diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index 0c418ce50ba0..f1b35a39d1ba 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -1488,7 +1488,7 @@ static void usb3_start_pipen(struct renesas_usb3_ep *usb3_ep, struct renesas_usb3_request *usb3_req) { struct renesas_usb3 *usb3 = usb3_ep_to_usb3(usb3_ep); - struct renesas_usb3_request *usb3_req_first = usb3_get_request(usb3_ep); + struct renesas_usb3_request *usb3_req_first; unsigned long flags; int ret = -EAGAIN; u32 enable_bits = 0; @@ -1496,7 +1496,8 @@ static void usb3_start_pipen(struct renesas_usb3_ep *usb3_ep, spin_lock_irqsave(&usb3->lock, flags); if (usb3_ep->halt || usb3_ep->started) goto out; - if (usb3_req != usb3_req_first) + usb3_req_first = __usb3_get_request(usb3_ep); + if (!usb3_req_first || usb3_req != usb3_req_first) goto out; if (usb3_pn_change(usb3, usb3_ep->num) < 0) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index a8e4189277da..6acd2329e08d 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -828,14 +828,10 @@ static void xhci_giveback_invalidated_tds(struct xhci_virt_ep *ep) list_for_each_entry_safe(td, tmp_td, &ep->cancelled_td_list, cancelled_td_list) { - /* - * Doesn't matter what we pass for status, since the core will - * just overwrite it (because the URB has been unlinked). - */ ring = xhci_urb_to_transfer_ring(ep->xhci, td->urb); if (td->cancel_status == TD_CLEARED) - xhci_td_cleanup(ep->xhci, td, ring, 0); + xhci_td_cleanup(ep->xhci, td, ring, td->status); if (ep->xhci->xhc_state & XHCI_STATE_DYING) return; @@ -937,14 +933,18 @@ static int xhci_invalidate_cancelled_tds(struct xhci_virt_ep *ep) continue; } /* - * If ring stopped on the TD we need to cancel, then we have to + * If a ring stopped on the TD we need to cancel then we have to * move the xHC endpoint ring dequeue pointer past this TD. + * Rings halted due to STALL may show hw_deq is past the stalled + * TD, but still require a set TR Deq command to flush xHC cache. */ hw_deq = xhci_get_hw_deq(xhci, ep->vdev, ep->ep_index, td->urb->stream_id); hw_deq &= ~0xf; - if (trb_in_td(xhci, td->start_seg, td->first_trb, + if (td->cancel_status == TD_HALTED) { + cached_td = td; + } else if (trb_in_td(xhci, td->start_seg, td->first_trb, td->last_trb, hw_deq, false)) { switch (td->cancel_status) { case TD_CLEARED: /* TD is already no-op */ diff --git a/drivers/usb/misc/trancevibrator.c b/drivers/usb/misc/trancevibrator.c index a3dfc77578ea..26baba3ab7d7 100644 --- a/drivers/usb/misc/trancevibrator.c +++ b/drivers/usb/misc/trancevibrator.c @@ -61,9 +61,9 @@ static ssize_t speed_store(struct device *dev, struct device_attribute *attr, /* Set speed */ retval = usb_control_msg(tv->udev, usb_sndctrlpipe(tv->udev, 0), 0x01, /* vendor request: set speed */ - USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_OTHER, + USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_OTHER, tv->speed, /* speed value */ - 0, NULL, 0, USB_CTRL_GET_TIMEOUT); + 0, NULL, 0, USB_CTRL_SET_TIMEOUT); if (retval) { tv->speed = old; dev_dbg(&tv->udev->dev, "retval = %d\n", retval); diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c index b5d661644263..748139d26263 100644 --- a/drivers/usb/misc/uss720.c +++ b/drivers/usb/misc/uss720.c @@ -736,6 +736,7 @@ static int uss720_probe(struct usb_interface *intf, parport_announce_port(pp); usb_set_intfdata(intf, pp); + usb_put_dev(usbdev); return 0; probe_abort: diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 6f2659e59b2e..369ef140df78 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1034,6 +1034,9 @@ static const struct usb_device_id id_table_combined[] = { /* Sienna devices */ { USB_DEVICE(FTDI_VID, FTDI_SIENNA_PID) }, { USB_DEVICE(ECHELON_VID, ECHELON_U20_PID) }, + /* IDS GmbH devices */ + { USB_DEVICE(IDS_VID, IDS_SI31A_PID) }, + { USB_DEVICE(IDS_VID, IDS_CM31A_PID) }, /* U-Blox devices */ { USB_DEVICE(UBLOX_VID, UBLOX_C099F9P_ZED_PID) }, { USB_DEVICE(UBLOX_VID, UBLOX_C099F9P_ODIN_PID) }, diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 3d47c6d72256..d854e04a4286 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -1568,6 +1568,13 @@ #define UNJO_ISODEBUG_V1_PID 0x150D /* + * IDS GmbH + */ +#define IDS_VID 0x2CAF +#define IDS_SI31A_PID 0x13A2 +#define IDS_CM31A_PID 0x13A3 + +/* * U-Blox products (http://www.u-blox.com). */ #define UBLOX_VID 0x1546 diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 3e79a543d3e7..7608584ef4fe 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1240,6 +1240,10 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1901, 0xff), /* Telit LN940 (MBIM) */ .driver_info = NCTRL(0) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x7010, 0xff), /* Telit LE910-S1 (RNDIS) */ + .driver_info = NCTRL(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x7011, 0xff), /* Telit LE910-S1 (ECM) */ + .driver_info = NCTRL(2) }, { USB_DEVICE(TELIT_VENDOR_ID, 0x9010), /* Telit SBL FN980 flashing device */ .driver_info = NCTRL(0) | ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */ diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index fd773d252691..940050c31482 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -113,6 +113,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(SONY_VENDOR_ID, SONY_QN3USB_PRODUCT_ID) }, { USB_DEVICE(SANWA_VENDOR_ID, SANWA_PRODUCT_ID) }, { USB_DEVICE(ADLINK_VENDOR_ID, ADLINK_ND6530_PRODUCT_ID) }, + { USB_DEVICE(ADLINK_VENDOR_ID, ADLINK_ND6530GC_PRODUCT_ID) }, { USB_DEVICE(SMART_VENDOR_ID, SMART_PRODUCT_ID) }, { USB_DEVICE(AT_VENDOR_ID, AT_VTKIT3_PRODUCT_ID) }, { } /* Terminating entry */ diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h index 0f681ddbfd28..6097ee8fccb2 100644 --- a/drivers/usb/serial/pl2303.h +++ b/drivers/usb/serial/pl2303.h @@ -158,6 +158,7 @@ /* ADLINK ND-6530 RS232,RS485 and RS422 adapter */ #define ADLINK_VENDOR_ID 0x0b63 #define ADLINK_ND6530_PRODUCT_ID 0x6530 +#define ADLINK_ND6530GC_PRODUCT_ID 0x653a /* SMART USB Serial Adapter */ #define SMART_VENDOR_ID 0x0b8c diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c index caa46ac23db9..310db5abea9d 100644 --- a/drivers/usb/serial/ti_usb_3410_5052.c +++ b/drivers/usb/serial/ti_usb_3410_5052.c @@ -37,6 +37,7 @@ /* Vendor and product ids */ #define TI_VENDOR_ID 0x0451 #define IBM_VENDOR_ID 0x04b3 +#define STARTECH_VENDOR_ID 0x14b0 #define TI_3410_PRODUCT_ID 0x3410 #define IBM_4543_PRODUCT_ID 0x4543 #define IBM_454B_PRODUCT_ID 0x454b @@ -370,6 +371,7 @@ static const struct usb_device_id ti_id_table_3410[] = { { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1131_PRODUCT_ID) }, { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1150_PRODUCT_ID) }, { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1151_PRODUCT_ID) }, + { USB_DEVICE(STARTECH_VENDOR_ID, TI_3410_PRODUCT_ID) }, { } /* terminator */ }; @@ -408,6 +410,7 @@ static const struct usb_device_id ti_id_table_combined[] = { { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1131_PRODUCT_ID) }, { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1150_PRODUCT_ID) }, { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1151_PRODUCT_ID) }, + { USB_DEVICE(STARTECH_VENDOR_ID, TI_3410_PRODUCT_ID) }, { } /* terminator */ }; diff --git a/drivers/usb/typec/mux.c b/drivers/usb/typec/mux.c index 9da22ae3006c..8514bec7e1b8 100644 --- a/drivers/usb/typec/mux.c +++ b/drivers/usb/typec/mux.c @@ -191,6 +191,7 @@ static void *typec_mux_match(struct fwnode_handle *fwnode, const char *id, bool match; int nval; u16 *val; + int ret; int i; /* @@ -218,10 +219,10 @@ static void *typec_mux_match(struct fwnode_handle *fwnode, const char *id, if (!val) return ERR_PTR(-ENOMEM); - nval = fwnode_property_read_u16_array(fwnode, "svid", val, nval); - if (nval < 0) { + ret = fwnode_property_read_u16_array(fwnode, "svid", val, nval); + if (ret < 0) { kfree(val); - return ERR_PTR(nval); + return ERR_PTR(ret); } for (i = 0; i < nval; i++) { diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 64133e586c64..9ce8c9af4da5 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -1550,6 +1550,8 @@ static int tcpm_pd_svdm(struct tcpm_port *port, struct typec_altmode *adev, if (PD_VDO_SVDM_VER(p[0]) < svdm_version) typec_partner_set_svdm_version(port->partner, PD_VDO_SVDM_VER(p[0])); + + tcpm_ams_start(port, DISCOVER_IDENTITY); /* 6.4.4.3.1: Only respond as UFP (device) */ if (port->data_role == TYPEC_DEVICE && port->nr_snk_vdo) { @@ -1568,14 +1570,19 @@ static int tcpm_pd_svdm(struct tcpm_port *port, struct typec_altmode *adev, } break; case CMD_DISCOVER_SVID: + tcpm_ams_start(port, DISCOVER_SVIDS); break; case CMD_DISCOVER_MODES: + tcpm_ams_start(port, DISCOVER_MODES); break; case CMD_ENTER_MODE: + tcpm_ams_start(port, DFP_TO_UFP_ENTER_MODE); break; case CMD_EXIT_MODE: + tcpm_ams_start(port, DFP_TO_UFP_EXIT_MODE); break; case CMD_ATTENTION: + tcpm_ams_start(port, ATTENTION); /* Attention command does not have response */ *adev_action = ADEV_ATTENTION; return 0; @@ -2287,6 +2294,12 @@ static void tcpm_pd_data_request(struct tcpm_port *port, bool frs_enable; int ret; + if (tcpm_vdm_ams(port) && type != PD_DATA_VENDOR_DEF) { + port->vdm_state = VDM_STATE_ERR_BUSY; + tcpm_ams_finish(port); + mod_vdm_delayed_work(port, 0); + } + switch (type) { case PD_DATA_SOURCE_CAP: for (i = 0; i < cnt; i++) @@ -2417,7 +2430,10 @@ static void tcpm_pd_data_request(struct tcpm_port *port, NONE_AMS); break; case PD_DATA_VENDOR_DEF: - tcpm_handle_vdm_request(port, msg->payload, cnt); + if (tcpm_vdm_ams(port) || port->nr_snk_vdo) + tcpm_handle_vdm_request(port, msg->payload, cnt); + else if (port->negotiated_rev > PD_REV20) + tcpm_pd_handle_msg(port, PD_MSG_CTRL_NOT_SUPP, NONE_AMS); break; case PD_DATA_BIST: port->bist_request = le32_to_cpu(msg->payload[0]); @@ -2459,6 +2475,16 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port, enum pd_ctrl_msg_type type = pd_header_type_le(msg->header); enum tcpm_state next_state; + /* + * Stop VDM state machine if interrupted by other Messages while NOT_SUPP is allowed in + * VDM AMS if waiting for VDM responses and will be handled later. + */ + if (tcpm_vdm_ams(port) && type != PD_CTRL_NOT_SUPP && type != PD_CTRL_GOOD_CRC) { + port->vdm_state = VDM_STATE_ERR_BUSY; + tcpm_ams_finish(port); + mod_vdm_delayed_work(port, 0); + } + switch (type) { case PD_CTRL_GOOD_CRC: case PD_CTRL_PING: @@ -2717,7 +2743,14 @@ static void tcpm_pd_ext_msg_request(struct tcpm_port *port, enum pd_ext_msg_type type = pd_header_type_le(msg->header); unsigned int data_size = pd_ext_header_data_size_le(msg->ext_msg.header); - if (!(msg->ext_msg.header & PD_EXT_HDR_CHUNKED)) { + /* stopping VDM state machine if interrupted by other Messages */ + if (tcpm_vdm_ams(port)) { + port->vdm_state = VDM_STATE_ERR_BUSY; + tcpm_ams_finish(port); + mod_vdm_delayed_work(port, 0); + } + + if (!(le16_to_cpu(msg->ext_msg.header) & PD_EXT_HDR_CHUNKED)) { tcpm_pd_handle_msg(port, PD_MSG_CTRL_NOT_SUPP, NONE_AMS); tcpm_log(port, "Unchunked extended messages unsupported"); return; @@ -2811,7 +2844,7 @@ static void tcpm_pd_rx_handler(struct kthread_work *work) "Data role mismatch, initiating error recovery"); tcpm_set_state(port, ERROR_RECOVERY, 0); } else { - if (msg->header & PD_HEADER_EXT_HDR) + if (le16_to_cpu(msg->header) & PD_HEADER_EXT_HDR) tcpm_pd_ext_msg_request(port, msg); else if (cnt) tcpm_pd_data_request(port, msg); diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 1d8b7df59ff4..b433169ef6fa 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -717,8 +717,8 @@ static void ucsi_handle_connector_change(struct work_struct *work) ucsi_send_command(con->ucsi, command, NULL, 0); /* 3. ACK connector change */ - clear_bit(EVENT_PENDING, &ucsi->flags); ret = ucsi_acknowledge_connector_change(ucsi); + clear_bit(EVENT_PENDING, &ucsi->flags); if (ret) { dev_err(ucsi->dev, "%s: ACK failed (%d)", __func__, ret); goto out_unlock; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 189e4385df40..dda5dc6f7737 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -15,6 +15,7 @@ #include <linux/mlx5/vport.h> #include <linux/mlx5/fs.h> #include <linux/mlx5/mlx5_ifc_vdpa.h> +#include <linux/mlx5/mpfs.h> #include "mlx5_vdpa.h" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); @@ -1859,11 +1860,16 @@ static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb static void mlx5_vdpa_free(struct vdpa_device *vdev) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_core_dev *pfmdev; struct mlx5_vdpa_net *ndev; ndev = to_mlx5_vdpa_ndev(mvdev); free_resources(ndev); + if (!is_zero_ether_addr(ndev->config.mac)) { + pfmdev = pci_get_drvdata(pci_physfn(mvdev->mdev->pdev)); + mlx5_mpfs_del_mac(pfmdev, ndev->config.mac); + } mlx5_vdpa_free_resources(&ndev->mvdev); mutex_destroy(&ndev->reslock); } @@ -1990,6 +1996,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name) { struct mlx5_vdpa_mgmtdev *mgtdev = container_of(v_mdev, struct mlx5_vdpa_mgmtdev, mgtdev); struct virtio_net_config *config; + struct mlx5_core_dev *pfmdev; struct mlx5_vdpa_dev *mvdev; struct mlx5_vdpa_net *ndev; struct mlx5_core_dev *mdev; @@ -2023,10 +2030,17 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name) if (err) goto err_mtu; + if (!is_zero_ether_addr(config->mac)) { + pfmdev = pci_get_drvdata(pci_physfn(mdev->pdev)); + err = mlx5_mpfs_add_mac(pfmdev, config->mac); + if (err) + goto err_mtu; + } + mvdev->vdev.dma_dev = mdev->device; err = mlx5_vdpa_alloc_resources(&ndev->mvdev); if (err) - goto err_mtu; + goto err_mpfs; err = alloc_resources(ndev); if (err) @@ -2044,6 +2058,9 @@ err_reg: free_resources(ndev); err_res: mlx5_vdpa_free_resources(&ndev->mvdev); +err_mpfs: + if (!is_zero_ether_addr(config->mac)) + mlx5_mpfs_del_mac(pfmdev, config->mac); err_mtu: mutex_destroy(&ndev->reslock); put_device(&mvdev->vdev.dev); diff --git a/drivers/video/fbdev/hgafb.c b/drivers/video/fbdev/hgafb.c index cc8e62ae93f6..bd3d07aa4f0e 100644 --- a/drivers/video/fbdev/hgafb.c +++ b/drivers/video/fbdev/hgafb.c @@ -558,7 +558,7 @@ static int hgafb_probe(struct platform_device *pdev) int ret; ret = hga_card_detect(); - if (!ret) + if (ret) return ret; printk(KERN_INFO "hgafb: %s with %ldK of memory detected.\n", diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index a4e9e6e07e93..d3c6bb22c5f4 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -322,6 +322,8 @@ static int afs_deliver_cb_callback(struct afs_call *call) return ret; call->unmarshall++; + fallthrough; + case 5: break; } @@ -418,6 +420,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) r->node[loop] = ntohl(b[loop + 5]); call->unmarshall++; + fallthrough; case 2: break; @@ -530,6 +533,7 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call) r->node[loop] = ntohl(b[loop + 5]); call->unmarshall++; + fallthrough; case 2: break; @@ -663,6 +667,7 @@ static int afs_deliver_yfs_cb_callback(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; + fallthrough; case 3: break; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 9fbe5a5ec9bd..78719f2f567e 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1919,7 +1919,9 @@ static void afs_rename_edit_dir(struct afs_operation *op) new_inode = d_inode(new_dentry); if (new_inode) { spin_lock(&new_inode->i_lock); - if (new_inode->i_nlink > 0) + if (S_ISDIR(new_inode->i_mode)) + clear_nlink(new_inode); + else if (new_inode->i_nlink > 0) drop_nlink(new_inode); spin_unlock(&new_inode->i_lock); } diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 2f695a260442..dd3f45d906d2 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -388,6 +388,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) req->file_size = vp->scb.status.size; call->unmarshall++; + fallthrough; case 5: break; @@ -1408,6 +1409,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) _debug("motd '%s'", p); call->unmarshall++; + fallthrough; case 8: break; @@ -1845,6 +1847,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) xdr_decode_AFSVolSync(&bp, &op->volsync); call->unmarshall++; + fallthrough; case 6: break; @@ -1979,6 +1982,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) xdr_decode_AFSVolSync(&bp, &op->volsync); call->unmarshall++; + fallthrough; case 4: break; diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index dc9327332f06..00fca3c66ba6 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -593,6 +593,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) if (ret < 0) return ret; call->unmarshall = 6; + fallthrough; case 6: break; diff --git a/fs/cifs/cifs_ioctl.h b/fs/cifs/cifs_ioctl.h index 4a97fe12006b..37fc7d6ac457 100644 --- a/fs/cifs/cifs_ioctl.h +++ b/fs/cifs/cifs_ioctl.h @@ -72,15 +72,28 @@ struct smb3_key_debug_info { } __packed; /* - * Dump full key (32 byte encrypt/decrypt keys instead of 16 bytes) - * is needed if GCM256 (stronger encryption) negotiated + * Dump variable-sized keys */ struct smb3_full_key_debug_info { - __u64 Suid; + /* INPUT: size of userspace buffer */ + __u32 in_size; + + /* + * INPUT: 0 for current user, otherwise session to dump + * OUTPUT: session id that was dumped + */ + __u64 session_id; __u16 cipher_type; - __u8 auth_key[16]; /* SMB2_NTLMV2_SESSKEY_SIZE */ - __u8 smb3encryptionkey[32]; /* SMB3_ENC_DEC_KEY_SIZE */ - __u8 smb3decryptionkey[32]; /* SMB3_ENC_DEC_KEY_SIZE */ + __u8 session_key_length; + __u8 server_in_key_length; + __u8 server_out_key_length; + __u8 data[]; + /* + * return this struct with the keys appended at the end: + * __u8 session_key[session_key_length]; + * __u8 server_in_key[server_in_key_length]; + * __u8 server_out_key[server_out_key_length]; + */ } __packed; struct smb3_notify { diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index b53a87db282f..554d64fe171e 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -148,7 +148,8 @@ #define SMB3_SIGN_KEY_SIZE (16) /* - * Size of the smb3 encryption/decryption keys + * Size of the smb3 encryption/decryption key storage. + * This size is big enough to store any cipher key types. */ #define SMB3_ENC_DEC_KEY_SIZE (32) diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 28ec8d7c521a..d67d281ab863 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -33,6 +33,7 @@ #include "cifsfs.h" #include "cifs_ioctl.h" #include "smb2proto.h" +#include "smb2glob.h" #include <linux/btrfs.h> static long cifs_ioctl_query_info(unsigned int xid, struct file *filep, @@ -214,48 +215,112 @@ static int cifs_shutdown(struct super_block *sb, unsigned long arg) return 0; } -static int cifs_dump_full_key(struct cifs_tcon *tcon, unsigned long arg) +static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug_info __user *in) { - struct smb3_full_key_debug_info pfull_key_inf; - __u64 suid; - struct list_head *tmp; + struct smb3_full_key_debug_info out; struct cifs_ses *ses; + int rc = 0; bool found = false; + u8 __user *end; - if (!smb3_encryption_required(tcon)) - return -EOPNOTSUPP; + if (!smb3_encryption_required(tcon)) { + rc = -EOPNOTSUPP; + goto out; + } + + /* copy user input into our output buffer */ + if (copy_from_user(&out, in, sizeof(out))) { + rc = -EINVAL; + goto out; + } + + if (!out.session_id) { + /* if ses id is 0, use current user session */ + ses = tcon->ses; + } else { + /* otherwise if a session id is given, look for it in all our sessions */ + struct cifs_ses *ses_it = NULL; + struct TCP_Server_Info *server_it = NULL; - ses = tcon->ses; /* default to user id for current user */ - if (get_user(suid, (__u64 __user *)arg)) - suid = 0; - if (suid) { - /* search to see if there is a session with a matching SMB UID */ spin_lock(&cifs_tcp_ses_lock); - list_for_each(tmp, &tcon->ses->server->smb_ses_list) { - ses = list_entry(tmp, struct cifs_ses, smb_ses_list); - if (ses->Suid == suid) { - found = true; - break; + list_for_each_entry(server_it, &cifs_tcp_ses_list, tcp_ses_list) { + list_for_each_entry(ses_it, &server_it->smb_ses_list, smb_ses_list) { + if (ses_it->Suid == out.session_id) { + ses = ses_it; + /* + * since we are using the session outside the crit + * section, we need to make sure it won't be released + * so increment its refcount + */ + ses->ses_count++; + found = true; + goto search_end; + } } } +search_end: spin_unlock(&cifs_tcp_ses_lock); - if (found == false) - return -EINVAL; - } /* else uses default user's SMB UID (ie current user) */ - - pfull_key_inf.cipher_type = le16_to_cpu(ses->server->cipher_type); - pfull_key_inf.Suid = ses->Suid; - memcpy(pfull_key_inf.auth_key, ses->auth_key.response, - 16 /* SMB2_NTLMV2_SESSKEY_SIZE */); - memcpy(pfull_key_inf.smb3decryptionkey, ses->smb3decryptionkey, - 32 /* SMB3_ENC_DEC_KEY_SIZE */); - memcpy(pfull_key_inf.smb3encryptionkey, - ses->smb3encryptionkey, 32 /* SMB3_ENC_DEC_KEY_SIZE */); - if (copy_to_user((void __user *)arg, &pfull_key_inf, - sizeof(struct smb3_full_key_debug_info))) - return -EFAULT; + if (!found) { + rc = -ENOENT; + goto out; + } + } - return 0; + switch (ses->server->cipher_type) { + case SMB2_ENCRYPTION_AES128_CCM: + case SMB2_ENCRYPTION_AES128_GCM: + out.session_key_length = CIFS_SESS_KEY_SIZE; + out.server_in_key_length = out.server_out_key_length = SMB3_GCM128_CRYPTKEY_SIZE; + break; + case SMB2_ENCRYPTION_AES256_CCM: + case SMB2_ENCRYPTION_AES256_GCM: + out.session_key_length = CIFS_SESS_KEY_SIZE; + out.server_in_key_length = out.server_out_key_length = SMB3_GCM256_CRYPTKEY_SIZE; + break; + default: + rc = -EOPNOTSUPP; + goto out; + } + + /* check if user buffer is big enough to store all the keys */ + if (out.in_size < sizeof(out) + out.session_key_length + out.server_in_key_length + + out.server_out_key_length) { + rc = -ENOBUFS; + goto out; + } + + out.session_id = ses->Suid; + out.cipher_type = le16_to_cpu(ses->server->cipher_type); + + /* overwrite user input with our output */ + if (copy_to_user(in, &out, sizeof(out))) { + rc = -EINVAL; + goto out; + } + + /* append all the keys at the end of the user buffer */ + end = in->data; + if (copy_to_user(end, ses->auth_key.response, out.session_key_length)) { + rc = -EINVAL; + goto out; + } + end += out.session_key_length; + + if (copy_to_user(end, ses->smb3encryptionkey, out.server_in_key_length)) { + rc = -EINVAL; + goto out; + } + end += out.server_in_key_length; + + if (copy_to_user(end, ses->smb3decryptionkey, out.server_out_key_length)) { + rc = -EINVAL; + goto out; + } + +out: + if (found) + cifs_put_smb_ses(ses); + return rc; } long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) @@ -371,6 +436,10 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) rc = -EOPNOTSUPP; break; case CIFS_DUMP_KEY: + /* + * Dump encryption keys. This is an old ioctl that only + * handles AES-128-{CCM,GCM}. + */ if (pSMBFile == NULL) break; if (!capable(CAP_SYS_ADMIN)) { @@ -398,11 +467,10 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) else rc = 0; break; - /* - * Dump full key (32 bytes instead of 16 bytes) is - * needed if GCM256 (stronger encryption) negotiated - */ case CIFS_DUMP_FULL_KEY: + /* + * Dump encryption keys (handles any key sizes) + */ if (pSMBFile == NULL) break; if (!capable(CAP_SYS_ADMIN)) { @@ -410,8 +478,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) break; } tcon = tlink_tcon(pSMBFile->tlink); - rc = cifs_dump_full_key(tcon, arg); - + rc = cifs_dump_full_key(tcon, (void __user *)arg); break; case CIFS_IOC_NOTIFY: if (!S_ISDIR(inode->i_mode)) { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 9f24eb88297a..c205f93e0a10 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -958,6 +958,13 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) /* Internal types */ server->capabilities |= SMB2_NT_FIND | SMB2_LARGE_FILES; + /* + * SMB3.0 supports only 1 cipher and doesn't have a encryption neg context + * Set the cipher type manually. + */ + if (server->dialect == SMB30_PROT_ID && (server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION)) + server->cipher_type = SMB2_ENCRYPTION_AES128_CCM; + security_blob = smb2_get_data_area_len(&blob_offset, &blob_length, (struct smb2_sync_hdr *)rsp); /* diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h index d6df908dccad..dafcb6ab050d 100644 --- a/fs/cifs/trace.h +++ b/fs/cifs/trace.h @@ -12,6 +12,11 @@ #include <linux/tracepoint.h> +/* + * Please use this 3-part article as a reference for writing new tracepoints: + * https://lwn.net/Articles/379903/ + */ + /* For logging errors in read or write */ DECLARE_EVENT_CLASS(smb3_rw_err_class, TP_PROTO(unsigned int xid, @@ -529,16 +534,16 @@ DECLARE_EVENT_CLASS(smb3_exit_err_class, TP_ARGS(xid, func_name, rc), TP_STRUCT__entry( __field(unsigned int, xid) - __field(const char *, func_name) + __string(func_name, func_name) __field(int, rc) ), TP_fast_assign( __entry->xid = xid; - __entry->func_name = func_name; + __assign_str(func_name, func_name); __entry->rc = rc; ), TP_printk("\t%s: xid=%u rc=%d", - __entry->func_name, __entry->xid, __entry->rc) + __get_str(func_name), __entry->xid, __entry->rc) ) #define DEFINE_SMB3_EXIT_ERR_EVENT(name) \ @@ -583,14 +588,14 @@ DECLARE_EVENT_CLASS(smb3_enter_exit_class, TP_ARGS(xid, func_name), TP_STRUCT__entry( __field(unsigned int, xid) - __field(const char *, func_name) + __string(func_name, func_name) ), TP_fast_assign( __entry->xid = xid; - __entry->func_name = func_name; + __assign_str(func_name, func_name); ), TP_printk("\t%s: xid=%u", - __entry->func_name, __entry->xid) + __get_str(func_name), __entry->xid) ) #define DEFINE_SMB3_ENTER_EXIT_EVENT(name) \ @@ -857,16 +862,16 @@ DECLARE_EVENT_CLASS(smb3_reconnect_class, TP_STRUCT__entry( __field(__u64, currmid) __field(__u64, conn_id) - __field(char *, hostname) + __string(hostname, hostname) ), TP_fast_assign( __entry->currmid = currmid; __entry->conn_id = conn_id; - __entry->hostname = hostname; + __assign_str(hostname, hostname); ), TP_printk("conn_id=0x%llx server=%s current_mid=%llu", __entry->conn_id, - __entry->hostname, + __get_str(hostname), __entry->currmid) ) @@ -891,7 +896,7 @@ DECLARE_EVENT_CLASS(smb3_credit_class, TP_STRUCT__entry( __field(__u64, currmid) __field(__u64, conn_id) - __field(char *, hostname) + __string(hostname, hostname) __field(int, credits) __field(int, credits_to_add) __field(int, in_flight) @@ -899,7 +904,7 @@ DECLARE_EVENT_CLASS(smb3_credit_class, TP_fast_assign( __entry->currmid = currmid; __entry->conn_id = conn_id; - __entry->hostname = hostname; + __assign_str(hostname, hostname); __entry->credits = credits; __entry->credits_to_add = credits_to_add; __entry->in_flight = in_flight; @@ -907,7 +912,7 @@ DECLARE_EVENT_CLASS(smb3_credit_class, TP_printk("conn_id=0x%llx server=%s current_mid=%llu " "credits=%d credit_change=%d in_flight=%d", __entry->conn_id, - __entry->hostname, + __get_str(hostname), __entry->currmid, __entry->credits, __entry->credits_to_add, diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 1d252164d97b..8129a430d789 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -45,10 +45,13 @@ static unsigned int debugfs_allow __ro_after_init = DEFAULT_DEBUGFS_ALLOW_BITS; static int debugfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *ia) { - int ret = security_locked_down(LOCKDOWN_DEBUGFS); + int ret; - if (ret && (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))) - return ret; + if (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) { + ret = security_locked_down(LOCKDOWN_DEBUGFS); + if (ret) + return ret; + } return simple_setattr(&init_user_ns, dentry, ia); } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index a0b542d84cd9..8a35a0196b6d 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -540,9 +540,11 @@ static vm_fault_t gfs2_fault(struct vm_fault *vmf) struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_holder gh; vm_fault_t ret; + u16 state; int err; - gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh); + state = (vmf->flags & FAULT_FLAG_WRITE) ? LM_ST_EXCLUSIVE : LM_ST_SHARED; + gfs2_holder_init(ip->i_gl, state, 0, &gh); err = gfs2_glock_nq(&gh); if (err) { ret = block_page_mkwrite_return(err); @@ -911,8 +913,11 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from) current->backing_dev_info = inode_to_bdi(inode); buffered = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops); current->backing_dev_info = NULL; - if (unlikely(buffered <= 0)) + if (unlikely(buffered <= 0)) { + if (!ret) + ret = buffered; goto out_unlock; + } /* * We need to ensure that the page cache pages are written to diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index ea7fc5c641c7..d9cb261f55b0 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -582,6 +582,16 @@ out_locked: spin_unlock(&gl->gl_lockref.lock); } +static bool is_system_glock(struct gfs2_glock *gl) +{ + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode); + + if (gl == m_ip->i_gl) + return true; + return false; +} + /** * do_xmote - Calls the DLM to change the state of a lock * @gl: The lock state @@ -671,17 +681,25 @@ skip_inval: * to see sd_log_error and withdraw, and in the meantime, requeue the * work for later. * + * We make a special exception for some system glocks, such as the + * system statfs inode glock, which needs to be granted before the + * gfs2_quotad daemon can exit, and that exit needs to finish before + * we can unmount the withdrawn file system. + * * However, if we're just unlocking the lock (say, for unmount, when * gfs2_gl_hash_clear calls clear_glock) and recovery is complete * then it's okay to tell dlm to unlock it. */ if (unlikely(sdp->sd_log_error && !gfs2_withdrawn(sdp))) gfs2_withdraw_delayed(sdp); - if (glock_blocked_by_withdraw(gl)) { - if (target != LM_ST_UNLOCKED || - test_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags)) { + if (glock_blocked_by_withdraw(gl) && + (target != LM_ST_UNLOCKED || + test_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags))) { + if (!is_system_glock(gl)) { gfs2_glock_queue_work(gl, GL_GLOCK_DFT_HOLD); goto out; + } else { + clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags); } } @@ -1466,9 +1484,11 @@ void gfs2_glock_dq(struct gfs2_holder *gh) glock_blocked_by_withdraw(gl) && gh->gh_gl != sdp->sd_jinode_gl) { sdp->sd_glock_dqs_held++; + spin_unlock(&gl->gl_lockref.lock); might_sleep(); wait_on_bit(&sdp->sd_flags, SDF_WITHDRAW_RECOVERY, TASK_UNINTERRUPTIBLE); + spin_lock(&gl->gl_lockref.lock); } if (gh->gh_flags & GL_NOCACHE) handle_callback(gl, LM_ST_UNLOCKED, 0, false); @@ -1775,6 +1795,7 @@ __acquires(&lru_lock) while(!list_empty(list)) { gl = list_first_entry(list, struct gfs2_glock, gl_lru); list_del_init(&gl->gl_lru); + clear_bit(GLF_LRU, &gl->gl_flags); if (!spin_trylock(&gl->gl_lockref.lock)) { add_back_to_lru: list_add(&gl->gl_lru, &lru_list); @@ -1820,7 +1841,6 @@ static long gfs2_scan_glock_lru(int nr) if (!test_bit(GLF_LOCK, &gl->gl_flags)) { list_move(&gl->gl_lru, &dispose); atomic_dec(&lru_count); - clear_bit(GLF_LRU, &gl->gl_flags); freed++; continue; } diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 454095e9fedf..54d3fbeb3002 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -396,7 +396,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) struct timespec64 atime; u16 height, depth; umode_t mode = be32_to_cpu(str->di_mode); - bool is_new = ip->i_inode.i_flags & I_NEW; + bool is_new = ip->i_inode.i_state & I_NEW; if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr))) goto corrupt; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 97d54e581a7b..42c15cfc0821 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -926,10 +926,10 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags) } /** - * ail_drain - drain the ail lists after a withdraw + * gfs2_ail_drain - drain the ail lists after a withdraw * @sdp: Pointer to GFS2 superblock */ -static void ail_drain(struct gfs2_sbd *sdp) +void gfs2_ail_drain(struct gfs2_sbd *sdp) { struct gfs2_trans *tr; @@ -956,6 +956,7 @@ static void ail_drain(struct gfs2_sbd *sdp) list_del(&tr->tr_list); gfs2_trans_free(sdp, tr); } + gfs2_drain_revokes(sdp); spin_unlock(&sdp->sd_ail_lock); } @@ -1162,7 +1163,6 @@ out_withdraw: if (tr && list_empty(&tr->tr_list)) list_add(&tr->tr_list, &sdp->sd_ail1_list); spin_unlock(&sdp->sd_ail_lock); - ail_drain(sdp); /* frees all transactions */ tr = NULL; goto out_end; } diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h index eea58015710e..fc905c2af53c 100644 --- a/fs/gfs2/log.h +++ b/fs/gfs2/log.h @@ -93,5 +93,6 @@ extern int gfs2_logd(void *data); extern void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd); extern void gfs2_glock_remove_revoke(struct gfs2_glock *gl); extern void gfs2_flush_revokes(struct gfs2_sbd *sdp); +extern void gfs2_ail_drain(struct gfs2_sbd *sdp); #endif /* __LOG_DOT_H__ */ diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 221e7118cc3b..8ee05d25dfa6 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -885,7 +885,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) gfs2_log_write_page(sdp, page); } -static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) +void gfs2_drain_revokes(struct gfs2_sbd *sdp) { struct list_head *head = &sdp->sd_log_revokes; struct gfs2_bufdata *bd; @@ -900,6 +900,11 @@ static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) } } +static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) +{ + gfs2_drain_revokes(sdp); +} + static void revoke_lo_before_scan(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, int pass) { diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h index 31b6dd0d2e5d..f707601597dc 100644 --- a/fs/gfs2/lops.h +++ b/fs/gfs2/lops.h @@ -20,6 +20,7 @@ extern void gfs2_log_submit_bio(struct bio **biop, int opf); extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh); extern int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, bool keep_cache); +extern void gfs2_drain_revokes(struct gfs2_sbd *sdp); static inline unsigned int buf_limit(struct gfs2_sbd *sdp) { return sdp->sd_ldptrs; diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c index 3e08027a6c81..f4325b44956d 100644 --- a/fs/gfs2/util.c +++ b/fs/gfs2/util.c @@ -131,6 +131,7 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp) if (test_bit(SDF_NORECOVERY, &sdp->sd_flags) || !sdp->sd_jdesc) return; + gfs2_ail_drain(sdp); /* frees all transactions */ inode = sdp->sd_jdesc->jd_inode; ip = GFS2_I(inode); i_gl = ip->i_gl; diff --git a/fs/io-wq.c b/fs/io-wq.c index 5361a9b4b47b..b3e8624a37d0 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -979,13 +979,16 @@ static bool io_task_work_match(struct callback_head *cb, void *data) return cwd->wqe->wq == data; } +void io_wq_exit_start(struct io_wq *wq) +{ + set_bit(IO_WQ_BIT_EXIT, &wq->state); +} + static void io_wq_exit_workers(struct io_wq *wq) { struct callback_head *cb; int node; - set_bit(IO_WQ_BIT_EXIT, &wq->state); - if (!wq->task) return; @@ -1003,13 +1006,16 @@ static void io_wq_exit_workers(struct io_wq *wq) struct io_wqe *wqe = wq->wqes[node]; io_wq_for_each_worker(wqe, io_wq_worker_wake, NULL); - spin_lock_irq(&wq->hash->wait.lock); - list_del_init(&wq->wqes[node]->wait.entry); - spin_unlock_irq(&wq->hash->wait.lock); } rcu_read_unlock(); io_worker_ref_put(wq); wait_for_completion(&wq->worker_done); + + for_each_node(node) { + spin_lock_irq(&wq->hash->wait.lock); + list_del_init(&wq->wqes[node]->wait.entry); + spin_unlock_irq(&wq->hash->wait.lock); + } put_task_struct(wq->task); wq->task = NULL; } @@ -1020,8 +1026,6 @@ static void io_wq_destroy(struct io_wq *wq) cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node); - io_wq_exit_workers(wq); - for_each_node(node) { struct io_wqe *wqe = wq->wqes[node]; struct io_cb_cancel_data match = { @@ -1036,16 +1040,13 @@ static void io_wq_destroy(struct io_wq *wq) kfree(wq); } -void io_wq_put(struct io_wq *wq) -{ - if (refcount_dec_and_test(&wq->refs)) - io_wq_destroy(wq); -} - void io_wq_put_and_exit(struct io_wq *wq) { + WARN_ON_ONCE(!test_bit(IO_WQ_BIT_EXIT, &wq->state)); + io_wq_exit_workers(wq); - io_wq_put(wq); + if (refcount_dec_and_test(&wq->refs)) + io_wq_destroy(wq); } static bool io_wq_worker_affinity(struct io_worker *worker, void *data) diff --git a/fs/io-wq.h b/fs/io-wq.h index 0e6d310999e8..af2df0680ee2 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -122,7 +122,7 @@ struct io_wq_data { }; struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data); -void io_wq_put(struct io_wq *wq); +void io_wq_exit_start(struct io_wq *wq); void io_wq_put_and_exit(struct io_wq *wq); void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work); diff --git a/fs/io_uring.c b/fs/io_uring.c index 5f82954004f6..903458afd56c 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -9039,11 +9039,16 @@ static void io_uring_clean_tctx(struct io_uring_task *tctx) struct io_tctx_node *node; unsigned long index; - tctx->io_wq = NULL; xa_for_each(&tctx->xa, index, node) io_uring_del_task_file(index); - if (wq) + if (wq) { + /* + * Must be after io_uring_del_task_file() (removes nodes under + * uring_lock) to avoid race with io_uring_try_cancel_iowq(). + */ + tctx->io_wq = NULL; io_wq_put_and_exit(wq); + } } static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) @@ -9078,6 +9083,9 @@ static void io_uring_cancel_sqpoll(struct io_sq_data *sqd) if (!current->io_uring) return; + if (tctx->io_wq) + io_wq_exit_start(tctx->io_wq); + WARN_ON_ONCE(!sqd || sqd->thread != current); atomic_inc(&tctx->in_idle); @@ -9112,6 +9120,9 @@ void __io_uring_cancel(struct files_struct *files) DEFINE_WAIT(wait); s64 inflight; + if (tctx->io_wq) + io_wq_exit_start(tctx->io_wq); + /* make sure overflow events are dropped */ atomic_inc(&tctx->in_idle); do { diff --git a/fs/netfs/Kconfig b/fs/netfs/Kconfig index 578112713703..b4db21022cb4 100644 --- a/fs/netfs/Kconfig +++ b/fs/netfs/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config NETFS_SUPPORT - tristate "Support for network filesystem high-level I/O" + tristate help This option enables support for network filesystems, including helpers for high-level buffered I/O, abstracting out read diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index 193841d03de0..725614625ed4 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -1068,7 +1068,7 @@ int netfs_write_begin(struct file *file, struct address_space *mapping, DEFINE_READAHEAD(ractl, file, NULL, mapping, index); retry: - page = grab_cache_page_write_begin(mapping, index, 0); + page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index d158a500c25c..d2103852475f 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -718,7 +718,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, if (unlikely(!p)) goto out_err; fl->fh_array[i]->size = be32_to_cpup(p++); - if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) { + if (fl->fh_array[i]->size > NFS_MAXFHSIZE) { printk(KERN_ERR "NFS: Too big fh %d received %d\n", i, fl->fh_array[i]->size); goto out_err; diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 93e60e921f92..bc0c698f3350 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -362,7 +362,7 @@ static const struct kernel_param_ops param_ops_nfs_timeout = { .set = param_set_nfs_timeout, .get = param_get_nfs_timeout, }; -#define param_check_nfs_timeout(name, p) __param_check(name, p, int); +#define param_check_nfs_timeout(name, p) __param_check(name, p, int) module_param(nfs_mountpoint_expiry_timeout, nfs_timeout, 0644); MODULE_PARM_DESC(nfs_mountpoint_expiry_timeout, diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 57b3821d975a..a1e5c6b85ded 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -211,7 +211,7 @@ static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence) case SEEK_HOLE: case SEEK_DATA: ret = nfs42_proc_llseek(filep, offset, whence); - if (ret != -ENOTSUPP) + if (ret != -EOPNOTSUPP) return ret; fallthrough; default: diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 87d04f2c9385..0cd965882232 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1706,7 +1706,7 @@ static void nfs_set_open_stateid_locked(struct nfs4_state *state, rcu_read_unlock(); trace_nfs4_open_stateid_update_wait(state->inode, stateid, 0); - if (!signal_pending(current)) { + if (!fatal_signal_pending(current)) { if (schedule_timeout(5*HZ) == 0) status = -EAGAIN; else @@ -3487,7 +3487,7 @@ static bool nfs4_refresh_open_old_stateid(nfs4_stateid *dst, write_sequnlock(&state->seqlock); trace_nfs4_close_stateid_update_wait(state->inode, dst, 0); - if (signal_pending(current)) + if (fatal_signal_pending(current)) status = -EINTR; else if (schedule_timeout(5*HZ) != 0) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 6c20b28d9d7c..cf9cc62ec48e 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -1094,15 +1094,16 @@ nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc, struct nfs_page *prev = NULL; unsigned int size; - if (mirror->pg_count != 0) { - prev = nfs_list_entry(mirror->pg_list.prev); - } else { + if (list_empty(&mirror->pg_list)) { if (desc->pg_ops->pg_init) desc->pg_ops->pg_init(desc, req); if (desc->pg_error < 0) return 0; mirror->pg_base = req->wb_pgbase; - } + mirror->pg_count = 0; + mirror->pg_recoalesce = 0; + } else + prev = nfs_list_entry(mirror->pg_list.prev); if (desc->pg_maxretrans && req->wb_nio > desc->pg_maxretrans) { if (NFS_SERVER(desc->pg_inode)->flags & NFS_MOUNT_SOFTERR) @@ -1127,18 +1128,13 @@ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc) { struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); - if (!list_empty(&mirror->pg_list)) { int error = desc->pg_ops->pg_doio(desc); if (error < 0) desc->pg_error = error; - else + if (list_empty(&mirror->pg_list)) mirror->pg_bytes_written += mirror->pg_count; } - if (list_empty(&mirror->pg_list)) { - mirror->pg_count = 0; - mirror->pg_base = 0; - } } static void @@ -1227,10 +1223,6 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) do { list_splice_init(&mirror->pg_list, &head); - mirror->pg_bytes_written -= mirror->pg_count; - mirror->pg_count = 0; - mirror->pg_base = 0; - mirror->pg_recoalesce = 0; while (!list_empty(&head)) { struct nfs_page *req; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 03e0b34c4a64..2c01ee805306 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1317,6 +1317,11 @@ _pnfs_return_layout(struct inode *ino) { struct pnfs_layout_hdr *lo = NULL; struct nfs_inode *nfsi = NFS_I(ino); + struct pnfs_layout_range range = { + .iomode = IOMODE_ANY, + .offset = 0, + .length = NFS4_MAX_UINT64, + }; LIST_HEAD(tmp_list); const struct cred *cred; nfs4_stateid stateid; @@ -1344,16 +1349,10 @@ _pnfs_return_layout(struct inode *ino) } valid_layout = pnfs_layout_is_valid(lo); pnfs_clear_layoutcommit(ino, &tmp_list); - pnfs_mark_matching_lsegs_return(lo, &tmp_list, NULL, 0); + pnfs_mark_matching_lsegs_return(lo, &tmp_list, &range, 0); - if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) { - struct pnfs_layout_range range = { - .iomode = IOMODE_ANY, - .offset = 0, - .length = NFS4_MAX_UINT64, - }; + if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo, &range); - } /* Don't send a LAYOUTRETURN if list was initially empty */ if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags) || @@ -2678,7 +2677,7 @@ EXPORT_SYMBOL_GPL(pnfs_generic_pg_check_range); void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { - u64 rd_size = req->wb_bytes; + u64 rd_size; pnfs_generic_pg_check_layout(pgio); pnfs_generic_pg_check_range(pgio, req); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 19a212f9725d..fe58525cfed4 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1379,7 +1379,7 @@ static const struct kernel_param_ops param_ops_portnr = { .set = param_set_portnr, .get = param_get_uint, }; -#define param_check_portnr(name, p) __param_check(name, p, unsigned int); +#define param_check_portnr(name, p) __param_check(name, p, unsigned int) module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644); module_param_named(callback_nr_threads, nfs_callback_nr_threads, ushort, 0644); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 71fefb30e015..be5b6d2c01e7 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -424,11 +424,18 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, * events generated by the listener process itself, without disclosing * the pids of other processes. */ - if (!capable(CAP_SYS_ADMIN) && + if (FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) && task_tgid(current) != event->pid) metadata.pid = 0; - if (path && path->mnt && path->dentry) { + /* + * For now, fid mode is required for an unprivileged listener and + * fid mode does not report fd in events. Keep this check anyway + * for safety in case fid mode requirement is relaxed in the future + * to allow unprivileged listener to get events with no fd and no fid. + */ + if (!FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) && + path && path->mnt && path->dentry) { fd = create_fd(group, path, &f); if (fd < 0) return fd; @@ -1040,6 +1047,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) int f_flags, fd; unsigned int fid_mode = flags & FANOTIFY_FID_BITS; unsigned int class = flags & FANOTIFY_CLASS_BITS; + unsigned int internal_flags = 0; pr_debug("%s: flags=%x event_f_flags=%x\n", __func__, flags, event_f_flags); @@ -1053,6 +1061,13 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) */ if ((flags & FANOTIFY_ADMIN_INIT_FLAGS) || !fid_mode) return -EPERM; + + /* + * Setting the internal flag FANOTIFY_UNPRIV on the group + * prevents setting mount/filesystem marks on this group and + * prevents reporting pid and open fd in events. + */ + internal_flags |= FANOTIFY_UNPRIV; } #ifdef CONFIG_AUDITSYSCALL @@ -1105,7 +1120,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) goto out_destroy_group; } - group->fanotify_data.flags = flags; + group->fanotify_data.flags = flags | internal_flags; group->memcg = get_mem_cgroup_from_mm(current->mm); group->fanotify_data.merge_hash = fanotify_alloc_merge_hash(); @@ -1305,11 +1320,13 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, group = f.file->private_data; /* - * An unprivileged user is not allowed to watch a mount point nor - * a filesystem. + * An unprivileged user is not allowed to setup mount nor filesystem + * marks. This also includes setting up such marks by a group that + * was initialized by an unprivileged user. */ ret = -EPERM; - if (!capable(CAP_SYS_ADMIN) && + if ((!capable(CAP_SYS_ADMIN) || + FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV)) && mark_type != FAN_MARK_INODE) goto fput_and_out; @@ -1460,6 +1477,7 @@ static int __init fanotify_user_setup(void) max_marks = clamp(max_marks, FANOTIFY_OLD_DEFAULT_MAX_MARKS, FANOTIFY_DEFAULT_MAX_USER_MARKS); + BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS); BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 10); BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9); diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index a712b2aaa9ac..57f0d5d9f934 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -144,7 +144,7 @@ void fanotify_show_fdinfo(struct seq_file *m, struct file *f) struct fsnotify_group *group = f->private_data; seq_printf(m, "fanotify flags:%x event-flags:%x\n", - group->fanotify_data.flags, + group->fanotify_data.flags & FANOTIFY_INIT_FLAGS, group->fanotify_data.f_flags); show_fdinfo(m, f, fanotify_fdinfo); diff --git a/fs/proc/base.c b/fs/proc/base.c index 3851bfcdba56..58bbf334265b 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2703,6 +2703,10 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, void *page; int rv; + /* A task may only write when it was the opener. */ + if (file->f_cred != current_real_cred()) + return -EPERM; + rcu_read_lock(); task = pid_task(proc_pid(inode), PIDTYPE_PID); if (!task) { diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index e32a1833d523..bbfea8022a3b 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -325,10 +325,22 @@ out: error2 = xfs_alloc_pagf_init(mp, tp, pag->pag_agno, 0); if (error2) return error2; - ASSERT(xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved + - xfs_perag_resv(pag, XFS_AG_RESV_RMAPBT)->ar_reserved <= - pag->pagf_freeblks + pag->pagf_flcount); + + /* + * If there isn't enough space in the AG to satisfy the + * reservation, let the caller know that there wasn't enough + * space. Callers are responsible for deciding what to do + * next, since (in theory) we can stumble along with + * insufficient reservation if data blocks are being freed to + * replenish the AG's free space. + */ + if (!error && + xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved + + xfs_perag_resv(pag, XFS_AG_RESV_RMAPBT)->ar_reserved > + pag->pagf_freeblks + pag->pagf_flcount) + error = -ENOSPC; } + return error; } diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 7e3b9b01431e..a3e0e6f672d6 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -605,7 +605,6 @@ xfs_bmap_btree_to_extents( ASSERT(cur); ASSERT(whichfork != XFS_COW_FORK); - ASSERT(!xfs_need_iread_extents(ifp)); ASSERT(ifp->if_format == XFS_DINODE_FMT_BTREE); ASSERT(be16_to_cpu(rblock->bb_level) == 1); ASSERT(be16_to_cpu(rblock->bb_numrecs) == 1); @@ -5350,7 +5349,6 @@ __xfs_bunmapi( xfs_fsblock_t sum; xfs_filblks_t len = *rlen; /* length to unmap in file */ xfs_fileoff_t max_len; - xfs_agnumber_t prev_agno = NULLAGNUMBER, agno; xfs_fileoff_t end; struct xfs_iext_cursor icur; bool done = false; @@ -5442,16 +5440,6 @@ __xfs_bunmapi( del = got; wasdel = isnullstartblock(del.br_startblock); - /* - * Make sure we don't touch multiple AGF headers out of order - * in a single transaction, as that could cause AB-BA deadlocks. - */ - if (!wasdel && !isrt) { - agno = XFS_FSB_TO_AGNO(mp, del.br_startblock); - if (prev_agno != NULLAGNUMBER && prev_agno > agno) - break; - prev_agno = agno; - } if (got.br_startoff < start) { del.br_startoff = start; del.br_blockcount -= start - got.br_startoff; diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 5c9a7440d9e4..f3254a4f4cb4 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -559,8 +559,17 @@ xfs_dinode_calc_crc( /* * Validate di_extsize hint. * - * The rules are documented at xfs_ioctl_setattr_check_extsize(). - * These functions must be kept in sync with each other. + * 1. Extent size hint is only valid for directories and regular files. + * 2. FS_XFLAG_EXTSIZE is only valid for regular files. + * 3. FS_XFLAG_EXTSZINHERIT is only valid for directories. + * 4. Hint cannot be larger than MAXTEXTLEN. + * 5. Can be changed on directories at any time. + * 6. Hint value of 0 turns off hints, clears inode flags. + * 7. Extent size must be a multiple of the appropriate block size. + * For realtime files, this is the rt extent size. + * 8. For non-realtime files, the extent size hint must be limited + * to half the AG size to avoid alignment extending the extent beyond the + * limits of the AG. */ xfs_failaddr_t xfs_inode_validate_extsize( @@ -580,6 +589,28 @@ xfs_inode_validate_extsize( inherit_flag = (flags & XFS_DIFLAG_EXTSZINHERIT); extsize_bytes = XFS_FSB_TO_B(mp, extsize); + /* + * This comment describes a historic gap in this verifier function. + * + * On older kernels, the extent size hint verifier doesn't check that + * the extent size hint is an integer multiple of the realtime extent + * size on a directory with both RTINHERIT and EXTSZINHERIT flags set. + * The verifier has always enforced the alignment rule for regular + * files with the REALTIME flag set. + * + * If a directory with a misaligned extent size hint is allowed to + * propagate that hint into a new regular realtime file, the result + * is that the inode cluster buffer verifier will trigger a corruption + * shutdown the next time it is run. + * + * Unfortunately, there could be filesystems with these misconfigured + * directories in the wild, so we cannot add a check to this verifier + * at this time because that will result a new source of directory + * corruption errors when reading an existing filesystem. Instead, we + * permit the misconfiguration to pass through the verifiers so that + * callers of this function can correct and mitigate externally. + */ + if (rt_flag) blocksize_bytes = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog; else @@ -616,8 +647,15 @@ xfs_inode_validate_extsize( /* * Validate di_cowextsize hint. * - * The rules are documented at xfs_ioctl_setattr_check_cowextsize(). - * These functions must be kept in sync with each other. + * 1. CoW extent size hint can only be set if reflink is enabled on the fs. + * The inode does not have to have any shared blocks, but it must be a v3. + * 2. FS_XFLAG_COWEXTSIZE is only valid for directories and regular files; + * for a directory, the hint is propagated to new files. + * 3. Can be changed on files & directories at any time. + * 4. Hint value of 0 turns off hints, clears inode flags. + * 5. Extent size must be a multiple of the appropriate block size. + * 6. The extent size hint must be limited to half the AG size to avoid + * alignment extending the extent beyond the limits of the AG. */ xfs_failaddr_t xfs_inode_validate_cowextsize( diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c index 78324e043e25..8d595a5c4abd 100644 --- a/fs/xfs/libxfs/xfs_trans_inode.c +++ b/fs/xfs/libxfs/xfs_trans_inode.c @@ -143,6 +143,23 @@ xfs_trans_log_inode( } /* + * Inode verifiers on older kernels don't check that the extent size + * hint is an integer multiple of the rt extent size on a directory + * with both rtinherit and extszinherit flags set. If we're logging a + * directory that is misconfigured in this way, clear the hint. + */ + if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && + (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) && + (ip->i_extsize % ip->i_mount->m_sb.sb_rextsize) > 0) { + xfs_info_once(ip->i_mount, + "Correcting misaligned extent size hint in inode 0x%llx.", ip->i_ino); + ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE | + XFS_DIFLAG_EXTSZINHERIT); + ip->i_extsize = 0; + flags |= XFS_ILOG_CORE; + } + + /* * Record the specific change for fdatasync optimisation. This allows * fdatasync to skip log forces for inodes that are only timestamp * dirty. diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 0369eb22c1bb..e4c2da4566f1 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -690,6 +690,7 @@ xfs_inode_inherit_flags( const struct xfs_inode *pip) { unsigned int di_flags = 0; + xfs_failaddr_t failaddr; umode_t mode = VFS_I(ip)->i_mode; if (S_ISDIR(mode)) { @@ -729,6 +730,24 @@ xfs_inode_inherit_flags( di_flags |= XFS_DIFLAG_FILESTREAM; ip->i_diflags |= di_flags; + + /* + * Inode verifiers on older kernels only check that the extent size + * hint is an integer multiple of the rt extent size on realtime files. + * They did not check the hint alignment on a directory with both + * rtinherit and extszinherit flags set. If the misaligned hint is + * propagated from a directory into a new realtime file, new file + * allocations will fail due to math errors in the rt allocator and/or + * trip the verifiers. Validate the hint settings in the new file so + * that we don't let broken hints propagate. + */ + failaddr = xfs_inode_validate_extsize(ip->i_mount, ip->i_extsize, + VFS_I(ip)->i_mode, ip->i_diflags); + if (failaddr) { + ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE | + XFS_DIFLAG_EXTSZINHERIT); + ip->i_extsize = 0; + } } /* Propagate di_flags2 from a parent inode to a child inode. */ @@ -737,12 +756,22 @@ xfs_inode_inherit_flags2( struct xfs_inode *ip, const struct xfs_inode *pip) { + xfs_failaddr_t failaddr; + if (pip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) { ip->i_diflags2 |= XFS_DIFLAG2_COWEXTSIZE; ip->i_cowextsize = pip->i_cowextsize; } if (pip->i_diflags2 & XFS_DIFLAG2_DAX) ip->i_diflags2 |= XFS_DIFLAG2_DAX; + + /* Don't let invalid cowextsize hints propagate. */ + failaddr = xfs_inode_validate_cowextsize(ip->i_mount, ip->i_cowextsize, + VFS_I(ip)->i_mode, ip->i_diflags, ip->i_diflags2); + if (failaddr) { + ip->i_diflags2 &= ~XFS_DIFLAG2_COWEXTSIZE; + ip->i_cowextsize = 0; + } } /* diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 3925bfcb2365..1fe4c1fc0aea 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1267,20 +1267,8 @@ out_error: } /* - * extent size hint validation is somewhat cumbersome. Rules are: - * - * 1. extent size hint is only valid for directories and regular files - * 2. FS_XFLAG_EXTSIZE is only valid for regular files - * 3. FS_XFLAG_EXTSZINHERIT is only valid for directories. - * 4. can only be changed on regular files if no extents are allocated - * 5. can be changed on directories at any time - * 6. extsize hint of 0 turns off hints, clears inode flags. - * 7. Extent size must be a multiple of the appropriate block size. - * 8. for non-realtime files, the extent size hint must be limited - * to half the AG size to avoid alignment extending the extent beyond the - * limits of the AG. - * - * Please keep this function in sync with xfs_scrub_inode_extsize. + * Validate a proposed extent size hint. For regular files, the hint can only + * be changed if no extents are allocated. */ static int xfs_ioctl_setattr_check_extsize( @@ -1288,86 +1276,65 @@ xfs_ioctl_setattr_check_extsize( struct fileattr *fa) { struct xfs_mount *mp = ip->i_mount; - xfs_extlen_t size; - xfs_fsblock_t extsize_fsb; + xfs_failaddr_t failaddr; + uint16_t new_diflags; if (!fa->fsx_valid) return 0; if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_df.if_nextents && - ((ip->i_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize)) + XFS_FSB_TO_B(mp, ip->i_extsize) != fa->fsx_extsize) return -EINVAL; - if (fa->fsx_extsize == 0) - return 0; - - extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize); - if (extsize_fsb > MAXEXTLEN) + if (fa->fsx_extsize & mp->m_blockmask) return -EINVAL; - if (XFS_IS_REALTIME_INODE(ip) || - (fa->fsx_xflags & FS_XFLAG_REALTIME)) { - size = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog; - } else { - size = mp->m_sb.sb_blocksize; - if (extsize_fsb > mp->m_sb.sb_agblocks / 2) + new_diflags = xfs_flags2diflags(ip, fa->fsx_xflags); + + /* + * Inode verifiers on older kernels don't check that the extent size + * hint is an integer multiple of the rt extent size on a directory + * with both rtinherit and extszinherit flags set. Don't let sysadmins + * misconfigure directories. + */ + if ((new_diflags & XFS_DIFLAG_RTINHERIT) && + (new_diflags & XFS_DIFLAG_EXTSZINHERIT)) { + unsigned int rtextsize_bytes; + + rtextsize_bytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize); + if (fa->fsx_extsize % rtextsize_bytes) return -EINVAL; } - if (fa->fsx_extsize % size) - return -EINVAL; - - return 0; + failaddr = xfs_inode_validate_extsize(ip->i_mount, + XFS_B_TO_FSB(mp, fa->fsx_extsize), + VFS_I(ip)->i_mode, new_diflags); + return failaddr != NULL ? -EINVAL : 0; } -/* - * CoW extent size hint validation rules are: - * - * 1. CoW extent size hint can only be set if reflink is enabled on the fs. - * The inode does not have to have any shared blocks, but it must be a v3. - * 2. FS_XFLAG_COWEXTSIZE is only valid for directories and regular files; - * for a directory, the hint is propagated to new files. - * 3. Can be changed on files & directories at any time. - * 4. CoW extsize hint of 0 turns off hints, clears inode flags. - * 5. Extent size must be a multiple of the appropriate block size. - * 6. The extent size hint must be limited to half the AG size to avoid - * alignment extending the extent beyond the limits of the AG. - * - * Please keep this function in sync with xfs_scrub_inode_cowextsize. - */ static int xfs_ioctl_setattr_check_cowextsize( struct xfs_inode *ip, struct fileattr *fa) { struct xfs_mount *mp = ip->i_mount; - xfs_extlen_t size; - xfs_fsblock_t cowextsize_fsb; + xfs_failaddr_t failaddr; + uint64_t new_diflags2; + uint16_t new_diflags; if (!fa->fsx_valid) return 0; - if (!(fa->fsx_xflags & FS_XFLAG_COWEXTSIZE)) - return 0; - - if (!xfs_sb_version_hasreflink(&ip->i_mount->m_sb)) + if (fa->fsx_cowextsize & mp->m_blockmask) return -EINVAL; - if (fa->fsx_cowextsize == 0) - return 0; + new_diflags = xfs_flags2diflags(ip, fa->fsx_xflags); + new_diflags2 = xfs_flags2diflags2(ip, fa->fsx_xflags); - cowextsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_cowextsize); - if (cowextsize_fsb > MAXEXTLEN) - return -EINVAL; - - size = mp->m_sb.sb_blocksize; - if (cowextsize_fsb > mp->m_sb.sb_agblocks / 2) - return -EINVAL; - - if (fa->fsx_cowextsize % size) - return -EINVAL; - - return 0; + failaddr = xfs_inode_validate_cowextsize(ip->i_mount, + XFS_B_TO_FSB(mp, fa->fsx_cowextsize), + VFS_I(ip)->i_mode, new_diflags, new_diflags2); + return failaddr != NULL ? -EINVAL : 0; } static int diff --git a/fs/xfs/xfs_message.h b/fs/xfs/xfs_message.h index 3c392b1512ac..7ec1a9207517 100644 --- a/fs/xfs/xfs_message.h +++ b/fs/xfs/xfs_message.h @@ -73,6 +73,8 @@ do { \ xfs_printk_once(xfs_warn, dev, fmt, ##__VA_ARGS__) #define xfs_notice_once(dev, fmt, ...) \ xfs_printk_once(xfs_notice, dev, fmt, ##__VA_ARGS__) +#define xfs_info_once(dev, fmt, ...) \ + xfs_printk_once(xfs_info, dev, fmt, ##__VA_ARGS__) void assfail(struct xfs_mount *mp, char *expr, char *f, int l); void asswarn(struct xfs_mount *mp, char *expr, char *f, int l); diff --git a/include/linux/device.h b/include/linux/device.h index 38a2071cf776..f1a00040fa53 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -570,7 +570,7 @@ struct device { * @flags: Link flags. * @rpm_active: Whether or not the consumer device is runtime-PM-active. * @kref: Count repeated addition of the same link. - * @rcu_head: An RCU head to use for deferred execution of SRCU callbacks. + * @rm_work: Work structure used for removing the link. * @supplier_preactivated: Supplier has been made active before consumer probe. */ struct device_link { @@ -583,9 +583,7 @@ struct device_link { u32 flags; refcount_t rpm_active; struct kref kref; -#ifdef CONFIG_SRCU - struct rcu_head rcu_head; -#endif + struct work_struct rm_work; bool supplier_preactivated; /* Owned by consumer probe. */ }; diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index bad41bcb25df..a16dbeced152 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -51,6 +51,10 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ #define FANOTIFY_INIT_FLAGS (FANOTIFY_ADMIN_INIT_FLAGS | \ FANOTIFY_USER_INIT_FLAGS) +/* Internal group flags */ +#define FANOTIFY_UNPRIV 0x80000000 +#define FANOTIFY_INTERNAL_GROUP_FLAGS (FANOTIFY_UNPRIV) + #define FANOTIFY_MARK_TYPE_BITS (FAN_MARK_INODE | FAN_MARK_MOUNT | \ FAN_MARK_FILESYSTEM) diff --git a/include/linux/init.h b/include/linux/init.h index 045ad1650ed1..d82b4b2e1d25 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -242,7 +242,8 @@ extern bool initcall_debug; asm(".section \"" __sec "\", \"a\" \n" \ __stringify(__name) ": \n" \ ".long " __stringify(__stub) " - . \n" \ - ".previous \n"); + ".previous \n"); \ + static_assert(__same_type(initcall_t, &fn)); #else #define ____define_initcall(fn, __unused, __name, __sec) \ static initcall_t __name __used \ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2f34487e21f2..76102efbf079 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -10,6 +10,7 @@ #include <linux/spinlock.h> #include <linux/signal.h> #include <linux/sched.h> +#include <linux/sched/stat.h> #include <linux/bug.h> #include <linux/minmax.h> #include <linux/mm.h> @@ -146,7 +147,7 @@ static inline bool is_error_page(struct page *page) */ #define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_PENDING_TIMER 2 +#define KVM_REQ_UNBLOCK 2 #define KVM_REQ_UNHALT 3 #define KVM_REQUEST_ARCH_BASE 8 @@ -265,6 +266,11 @@ static inline bool kvm_vcpu_mapped(struct kvm_host_map *map) return !!map->hva; } +static inline bool kvm_vcpu_can_poll(ktime_t cur, ktime_t stop) +{ + return single_task_running() && !need_resched() && ktime_before(cur, stop); +} + /* * Sometimes a large or cross-page mmio needs to be broken up into separate * exits for userspace servicing. diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f8e8d7e90616..020a8f7fdbdd 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -703,6 +703,27 @@ struct mlx5_hv_vhca; #define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity)) #define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)) +enum { + MLX5_PROF_MASK_QP_SIZE = (u64)1 << 0, + MLX5_PROF_MASK_MR_CACHE = (u64)1 << 1, +}; + +enum { + MR_CACHE_LAST_STD_ENTRY = 20, + MLX5_IMR_MTT_CACHE_ENTRY, + MLX5_IMR_KSM_CACHE_ENTRY, + MAX_MR_CACHE_ENTRIES +}; + +struct mlx5_profile { + u64 mask; + u8 log_max_qp; + struct { + int size; + int limit; + } mr_cache[MAX_MR_CACHE_ENTRIES]; +}; + struct mlx5_core_dev { struct device *device; enum mlx5_coredev_type coredev_type; @@ -731,7 +752,7 @@ struct mlx5_core_dev { struct mutex intf_state_mutex; unsigned long intf_state; struct mlx5_priv priv; - struct mlx5_profile *profile; + struct mlx5_profile profile; u32 issi; struct mlx5e_resources mlx5e_res; struct mlx5_dm *dm; @@ -1083,18 +1104,6 @@ static inline u8 mlx5_mkey_variant(u32 mkey) return mkey & 0xff; } -enum { - MLX5_PROF_MASK_QP_SIZE = (u64)1 << 0, - MLX5_PROF_MASK_MR_CACHE = (u64)1 << 1, -}; - -enum { - MR_CACHE_LAST_STD_ENTRY = 20, - MLX5_IMR_MTT_CACHE_ENTRY, - MLX5_IMR_KSM_CACHE_ENTRY, - MAX_MR_CACHE_ENTRIES -}; - /* Async-atomic event notifier used by mlx5 core to forward FW * evetns recived from event queue to mlx5 consumers. * Optimise event queue dipatching. @@ -1148,15 +1157,6 @@ int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev, struct ib_device *device, struct rdma_netdev_alloc_params *params); -struct mlx5_profile { - u64 mask; - u8 log_max_qp; - struct { - int size; - int limit; - } mr_cache[MAX_MR_CACHE_ENTRIES]; -}; - enum { MLX5_PCI_DEV_IS_VF = 1 << 0, }; diff --git a/include/linux/mlx5/mpfs.h b/include/linux/mlx5/mpfs.h new file mode 100644 index 000000000000..bf700c8d5516 --- /dev/null +++ b/include/linux/mlx5/mpfs.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB + * Copyright (c) 2021 Mellanox Technologies Ltd. + */ + +#ifndef _MLX5_MPFS_ +#define _MLX5_MPFS_ + +struct mlx5_core_dev; + +#ifdef CONFIG_MLX5_MPFS +int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac); +int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac); +#else /* #ifndef CONFIG_MLX5_MPFS */ +static inline int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } +static inline int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } +#endif + +#endif diff --git a/include/linux/phy.h b/include/linux/phy.h index 60d2b26026a2..852743f07e3e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -496,6 +496,11 @@ struct macsec_ops; * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY * @state: State of the PHY for management purposes * @dev_flags: Device-specific flags used by the PHY driver. + * Bits [15:0] are free to use by the PHY driver to communicate + * driver specific behavior. + * Bits [23:16] are currently reserved for future use. + * Bits [31:24] are reserved for defining generic + * PHY driver behavior. * @irq: IRQ number of the PHY's interrupt (-1 if none) * @phy_timer: The timer for handling the state machine * @phylink: Pointer to phylink instance for this PHY diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index d81fe8b364d0..61b622e334ee 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -368,6 +368,8 @@ struct rpc_xprt * xprt_alloc(struct net *net, size_t size, unsigned int num_prealloc, unsigned int max_req); void xprt_free(struct rpc_xprt *); +void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task); +bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req); static inline int xprt_enable_swap(struct rpc_xprt *xprt) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5224f885a99a..58c2cd417e89 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5760,7 +5760,7 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr); */ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, const u8 *addr, enum nl80211_iftype iftype, - u8 data_offset); + u8 data_offset, bool is_amsdu); /** * ieee80211_data_to_8023 - convert an 802.11 data frame to 802.3 @@ -5772,7 +5772,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, enum nl80211_iftype iftype) { - return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype, 0); + return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype, 0, false); } /** diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 51d8eb99764d..48ef7460ff30 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -157,7 +157,6 @@ enum nf_flow_flags { NF_FLOW_HW, NF_FLOW_HW_DYING, NF_FLOW_HW_DEAD, - NF_FLOW_HW_REFRESH, NF_FLOW_HW_PENDING, }; diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index bd76e8e082c0..1df0f8074c9d 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -298,6 +298,7 @@ int nci_nfcc_loopback(struct nci_dev *ndev, void *data, size_t data_len, struct sk_buff **resp); struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev); +void nci_hci_deallocate(struct nci_dev *ndev); int nci_hci_send_event(struct nci_dev *ndev, u8 gate, u8 event, const u8 *param, size_t param_len); int nci_hci_send_cmd(struct nci_dev *ndev, u8 gate, diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 255e4f4b521f..ec7823921bd2 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -709,6 +709,17 @@ tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common, cls_common->extack = extack; } +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) +static inline struct tc_skb_ext *tc_skb_ext_alloc(struct sk_buff *skb) +{ + struct tc_skb_ext *tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT); + + if (tc_skb_ext) + memset(tc_skb_ext, 0, sizeof(*tc_skb_ext)); + return tc_skb_ext; +} +#endif + enum tc_matchall_command { TC_CLSMATCHALL_REPLACE, TC_CLSMATCHALL_DESTROY, diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index f5c1bee0cd6a..6d7b12cba015 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -128,12 +128,7 @@ void __qdisc_run(struct Qdisc *q); static inline void qdisc_run(struct Qdisc *q) { if (qdisc_run_begin(q)) { - /* NOLOCK qdisc must check 'state' under the qdisc seqlock - * to avoid racing with dev_qdisc_reset() - */ - if (!(q->flags & TCQ_F_NOLOCK) || - likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) - __qdisc_run(q); + __qdisc_run(q); qdisc_run_end(q); } } diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index f7a6e14491fb..1e625519ae96 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -36,6 +36,7 @@ struct qdisc_rate_table { enum qdisc_state_t { __QDISC_STATE_SCHED, __QDISC_STATE_DEACTIVATED, + __QDISC_STATE_MISSED, }; struct qdisc_size_table { @@ -159,8 +160,33 @@ static inline bool qdisc_is_empty(const struct Qdisc *qdisc) static inline bool qdisc_run_begin(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) { + if (spin_trylock(&qdisc->seqlock)) + goto nolock_empty; + + /* If the MISSED flag is set, it means other thread has + * set the MISSED flag before second spin_trylock(), so + * we can return false here to avoid multi cpus doing + * the set_bit() and second spin_trylock() concurrently. + */ + if (test_bit(__QDISC_STATE_MISSED, &qdisc->state)) + return false; + + /* Set the MISSED flag before the second spin_trylock(), + * if the second spin_trylock() return false, it means + * other cpu holding the lock will do dequeuing for us + * or it will see the MISSED flag set after releasing + * lock and reschedule the net_tx_action() to do the + * dequeuing. + */ + set_bit(__QDISC_STATE_MISSED, &qdisc->state); + + /* Retry again in case other CPU may not see the new flag + * after it releases the lock at the end of qdisc_run_end(). + */ if (!spin_trylock(&qdisc->seqlock)) return false; + +nolock_empty: WRITE_ONCE(qdisc->empty, false); } else if (qdisc_is_running(qdisc)) { return false; @@ -176,8 +202,15 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) static inline void qdisc_run_end(struct Qdisc *qdisc) { write_seqcount_end(&qdisc->running); - if (qdisc->flags & TCQ_F_NOLOCK) + if (qdisc->flags & TCQ_F_NOLOCK) { spin_unlock(&qdisc->seqlock); + + if (unlikely(test_bit(__QDISC_STATE_MISSED, + &qdisc->state))) { + clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + __netif_schedule(qdisc); + } + } } static inline bool qdisc_may_bulk(const struct Qdisc *qdisc) diff --git a/include/net/sock.h b/include/net/sock.h index 42bc5e1a627f..0e962d8bc73b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2231,13 +2231,15 @@ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk) sk_mem_charge(sk, skb->truesize); } -static inline void skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk) +static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk) { if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) { skb_orphan(skb); skb->destructor = sock_efree; skb->sk = sk; + return true; } + return false; } void sk_reset_timer(struct sock *sk, struct timer_list *timer, diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h index 1358a0ceb4d0..0bc29c4516e7 100644 --- a/include/sound/soc-dai.h +++ b/include/sound/soc-dai.h @@ -81,7 +81,7 @@ struct snd_compr_stream; #define SND_SOC_DAIFMT_CBP_CFP (1 << 12) /* codec clk provider & frame provider */ #define SND_SOC_DAIFMT_CBC_CFP (2 << 12) /* codec clk consumer & frame provider */ #define SND_SOC_DAIFMT_CBP_CFC (3 << 12) /* codec clk provider & frame consumer */ -#define SND_SOC_DAIFMT_CBC_CFC (4 << 12) /* codec clk consumer & frame follower */ +#define SND_SOC_DAIFMT_CBC_CFC (4 << 12) /* codec clk consumer & frame consumer */ /* previous definitions kept for backwards-compatibility, do not use in new contributions */ #define SND_SOC_DAIFMT_CBM_CFM SND_SOC_DAIFMT_CBP_CFP diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 3fd9a7e9d90c..79d9c44d1ad7 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -8,6 +8,7 @@ * Note: you must update KVM_API_VERSION if you change this interface. */ +#include <linux/const.h> #include <linux/types.h> #include <linux/compiler.h> #include <linux/ioctl.h> @@ -1879,8 +1880,8 @@ struct kvm_hyperv_eventfd { * conversion after harvesting an entry. Also, it must not skip any * dirty bits, so that dirty bits are always harvested in sequence. */ -#define KVM_DIRTY_GFN_F_DIRTY BIT(0) -#define KVM_DIRTY_GFN_F_RESET BIT(1) +#define KVM_DIRTY_GFN_F_DIRTY _BITUL(0) +#define KVM_DIRTY_GFN_F_RESET _BITUL(1) #define KVM_DIRTY_GFN_F_MASK 0x3 /* diff --git a/init/Kconfig b/init/Kconfig index 1ea12c64e4c9..a61c92066c2e 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -442,6 +442,7 @@ config AUDITSYSCALL source "kernel/irq/Kconfig" source "kernel/time/Kconfig" +source "kernel/bpf/Kconfig" source "kernel/Kconfig.preempt" menu "CPU/Task time and stats accounting" @@ -1713,46 +1714,6 @@ config KALLSYMS_BASE_RELATIVE # syscall, maps, verifier -config BPF_LSM - bool "LSM Instrumentation with BPF" - depends on BPF_EVENTS - depends on BPF_SYSCALL - depends on SECURITY - depends on BPF_JIT - help - Enables instrumentation of the security hooks with eBPF programs for - implementing dynamic MAC and Audit Policies. - - If you are unsure how to answer this question, answer N. - -config BPF_SYSCALL - bool "Enable bpf() system call" - select BPF - select IRQ_WORK - select TASKS_TRACE_RCU - select BINARY_PRINTF - select NET_SOCK_MSG if INET - default n - help - Enable the bpf() system call that allows to manipulate eBPF - programs and maps via file descriptors. - -config ARCH_WANT_DEFAULT_BPF_JIT - bool - -config BPF_JIT_ALWAYS_ON - bool "Permanently enable BPF JIT and remove BPF interpreter" - depends on BPF_SYSCALL && HAVE_EBPF_JIT && BPF_JIT - help - Enables BPF JIT and removes BPF interpreter to avoid - speculative execution of BPF instructions by the interpreter - -config BPF_JIT_DEFAULT_ON - def_bool ARCH_WANT_DEFAULT_BPF_JIT || BPF_JIT_ALWAYS_ON - depends on HAVE_EBPF_JIT && BPF_JIT - -source "kernel/bpf/preload/Kconfig" - config USERFAULTFD bool "Enable userfaultfd() system call" depends on MMU diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig new file mode 100644 index 000000000000..bd04f4a44c01 --- /dev/null +++ b/kernel/bpf/Kconfig @@ -0,0 +1,89 @@ +# SPDX-License-Identifier: GPL-2.0-only + +# BPF interpreter that, for example, classic socket filters depend on. +config BPF + bool + +# Used by archs to tell that they support BPF JIT compiler plus which +# flavour. Only one of the two can be selected for a specific arch since +# eBPF JIT supersedes the cBPF JIT. + +# Classic BPF JIT (cBPF) +config HAVE_CBPF_JIT + bool + +# Extended BPF JIT (eBPF) +config HAVE_EBPF_JIT + bool + +# Used by archs to tell that they want the BPF JIT compiler enabled by +# default for kernels that were compiled with BPF JIT support. +config ARCH_WANT_DEFAULT_BPF_JIT + bool + +menu "BPF subsystem" + +config BPF_SYSCALL + bool "Enable bpf() system call" + select BPF + select IRQ_WORK + select TASKS_TRACE_RCU + select BINARY_PRINTF + select NET_SOCK_MSG if INET + default n + help + Enable the bpf() system call that allows to manipulate BPF programs + and maps via file descriptors. + +config BPF_JIT + bool "Enable BPF Just In Time compiler" + depends on BPF + depends on HAVE_CBPF_JIT || HAVE_EBPF_JIT + depends on MODULES + help + BPF programs are normally handled by a BPF interpreter. This option + allows the kernel to generate native code when a program is loaded + into the kernel. This will significantly speed-up processing of BPF + programs. + + Note, an admin should enable this feature changing: + /proc/sys/net/core/bpf_jit_enable + /proc/sys/net/core/bpf_jit_harden (optional) + /proc/sys/net/core/bpf_jit_kallsyms (optional) + +config BPF_JIT_ALWAYS_ON + bool "Permanently enable BPF JIT and remove BPF interpreter" + depends on BPF_SYSCALL && HAVE_EBPF_JIT && BPF_JIT + help + Enables BPF JIT and removes BPF interpreter to avoid speculative + execution of BPF instructions by the interpreter. + +config BPF_JIT_DEFAULT_ON + def_bool ARCH_WANT_DEFAULT_BPF_JIT || BPF_JIT_ALWAYS_ON + depends on HAVE_EBPF_JIT && BPF_JIT + +config BPF_UNPRIV_DEFAULT_OFF + bool "Disable unprivileged BPF by default" + depends on BPF_SYSCALL + help + Disables unprivileged BPF by default by setting the corresponding + /proc/sys/kernel/unprivileged_bpf_disabled knob to 2. An admin can + still reenable it by setting it to 0 later on, or permanently + disable it by setting it to 1 (from which no other transition to + 0 is possible anymore). + +source "kernel/bpf/preload/Kconfig" + +config BPF_LSM + bool "Enable BPF LSM Instrumentation" + depends on BPF_EVENTS + depends on BPF_SYSCALL + depends on SECURITY + depends on BPF_JIT + help + Enables instrumentation of the security hooks with BPF programs for + implementing dynamic MAC and Audit Policies. + + If you are unsure how to answer this question, answer N. + +endmenu # "BPF subsystem" diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 5efb2b24012c..da471bf01b97 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -107,10 +107,12 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_inode_storage_get_proto; case BPF_FUNC_inode_storage_delete: return &bpf_inode_storage_delete_proto; +#ifdef CONFIG_NET case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; +#endif /* CONFIG_NET */ case BPF_FUNC_spin_lock: return &bpf_spin_lock_proto; case BPF_FUNC_spin_unlock: diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 0600ed325fa0..f982a9f0dbc4 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5206,6 +5206,12 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, m->ret_size = ret; for (i = 0; i < nargs; i++) { + if (i == nargs - 1 && args[i].type == 0) { + bpf_log(log, + "The function %s with variable args is unsupported.\n", + tname); + return -EINVAL; + } ret = __get_type_size(btf, args[i].type, &t); if (ret < 0) { bpf_log(log, @@ -5213,6 +5219,12 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, tname, i, btf_kind_str[BTF_INFO_KIND(t->info)]); return -EINVAL; } + if (ret == 0) { + bpf_log(log, + "The function %s has malformed void argument.\n", + tname); + return -EINVAL; + } m->arg_size[i] = ret; } m->nr_args = nargs; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 544773970dbc..73443498d88f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -692,38 +692,41 @@ static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype, return -EINVAL; } -/* Per-cpu temp buffers which can be used by printf-like helpers for %s or %p +/* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary + * arguments representation. */ -#define MAX_PRINTF_BUF_LEN 512 +#define MAX_BPRINTF_BUF_LEN 512 -struct bpf_printf_buf { - char tmp_buf[MAX_PRINTF_BUF_LEN]; +/* Support executing three nested bprintf helper calls on a given CPU */ +#define MAX_BPRINTF_NEST_LEVEL 3 +struct bpf_bprintf_buffers { + char tmp_bufs[MAX_BPRINTF_NEST_LEVEL][MAX_BPRINTF_BUF_LEN]; }; -static DEFINE_PER_CPU(struct bpf_printf_buf, bpf_printf_buf); -static DEFINE_PER_CPU(int, bpf_printf_buf_used); +static DEFINE_PER_CPU(struct bpf_bprintf_buffers, bpf_bprintf_bufs); +static DEFINE_PER_CPU(int, bpf_bprintf_nest_level); static int try_get_fmt_tmp_buf(char **tmp_buf) { - struct bpf_printf_buf *bufs; - int used; + struct bpf_bprintf_buffers *bufs; + int nest_level; preempt_disable(); - used = this_cpu_inc_return(bpf_printf_buf_used); - if (WARN_ON_ONCE(used > 1)) { - this_cpu_dec(bpf_printf_buf_used); + nest_level = this_cpu_inc_return(bpf_bprintf_nest_level); + if (WARN_ON_ONCE(nest_level > MAX_BPRINTF_NEST_LEVEL)) { + this_cpu_dec(bpf_bprintf_nest_level); preempt_enable(); return -EBUSY; } - bufs = this_cpu_ptr(&bpf_printf_buf); - *tmp_buf = bufs->tmp_buf; + bufs = this_cpu_ptr(&bpf_bprintf_bufs); + *tmp_buf = bufs->tmp_bufs[nest_level - 1]; return 0; } void bpf_bprintf_cleanup(void) { - if (this_cpu_read(bpf_printf_buf_used)) { - this_cpu_dec(bpf_printf_buf_used); + if (this_cpu_read(bpf_bprintf_nest_level)) { + this_cpu_dec(bpf_bprintf_nest_level); preempt_enable(); } } @@ -760,7 +763,7 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, if (num_args && try_get_fmt_tmp_buf(&tmp_buf)) return -EBUSY; - tmp_buf_end = tmp_buf + MAX_PRINTF_BUF_LEN; + tmp_buf_end = tmp_buf + MAX_BPRINTF_BUF_LEN; *bin_args = (u32 *)tmp_buf; } diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index f25b719ac786..84b3b35fc0d0 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -221,25 +221,20 @@ static int ringbuf_map_get_next_key(struct bpf_map *map, void *key, return -ENOTSUPP; } -static size_t bpf_ringbuf_mmap_page_cnt(const struct bpf_ringbuf *rb) -{ - size_t data_pages = (rb->mask + 1) >> PAGE_SHIFT; - - /* consumer page + producer page + 2 x data pages */ - return RINGBUF_POS_PAGES + 2 * data_pages; -} - static int ringbuf_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) { struct bpf_ringbuf_map *rb_map; - size_t mmap_sz; rb_map = container_of(map, struct bpf_ringbuf_map, map); - mmap_sz = bpf_ringbuf_mmap_page_cnt(rb_map->rb) << PAGE_SHIFT; - - if (vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) > mmap_sz) - return -EINVAL; + if (vma->vm_flags & VM_WRITE) { + /* allow writable mapping for the consumer_pos only */ + if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE) + return -EPERM; + } else { + vma->vm_flags &= ~VM_MAYWRITE; + } + /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF); } @@ -315,6 +310,9 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) return NULL; len = round_up(size + BPF_RINGBUF_HDR_SZ, 8); + if (len > rb->mask + 1) + return NULL; + cons_pos = smp_load_acquire(&rb->consumer_pos); if (in_nmi()) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 941ca06d9dfa..ea04b0deb5ce 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -50,7 +50,8 @@ static DEFINE_SPINLOCK(map_idr_lock); static DEFINE_IDR(link_idr); static DEFINE_SPINLOCK(link_idr_lock); -int sysctl_unprivileged_bpf_disabled __read_mostly; +int sysctl_unprivileged_bpf_disabled __read_mostly = + IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0; static const struct bpf_map_ops * const bpf_map_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 757476c91c98..94ba5163d4c5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6409,18 +6409,10 @@ enum { }; static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg, - const struct bpf_reg_state *off_reg, - u32 *alu_limit, u8 opcode) + u32 *alu_limit, bool mask_to_left) { - bool off_is_neg = off_reg->smin_value < 0; - bool mask_to_left = (opcode == BPF_ADD && off_is_neg) || - (opcode == BPF_SUB && !off_is_neg); u32 max = 0, ptr_limit = 0; - if (!tnum_is_const(off_reg->var_off) && - (off_reg->smin_value < 0) != (off_reg->smax_value < 0)) - return REASON_BOUNDS; - switch (ptr_reg->type) { case PTR_TO_STACK: /* Offset 0 is out-of-bounds, but acceptable start for the @@ -6486,15 +6478,20 @@ static bool sanitize_needed(u8 opcode) return opcode == BPF_ADD || opcode == BPF_SUB; } +struct bpf_sanitize_info { + struct bpf_insn_aux_data aux; + bool mask_to_left; +}; + static int sanitize_ptr_alu(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, const struct bpf_reg_state *off_reg, struct bpf_reg_state *dst_reg, - struct bpf_insn_aux_data *tmp_aux, + struct bpf_sanitize_info *info, const bool commit_window) { - struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : tmp_aux; + struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : &info->aux; struct bpf_verifier_state *vstate = env->cur_state; bool off_is_imm = tnum_is_const(off_reg->var_off); bool off_is_neg = off_reg->smin_value < 0; @@ -6515,7 +6512,16 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, if (vstate->speculative) goto do_sim; - err = retrieve_ptr_limit(ptr_reg, off_reg, &alu_limit, opcode); + if (!commit_window) { + if (!tnum_is_const(off_reg->var_off) && + (off_reg->smin_value < 0) != (off_reg->smax_value < 0)) + return REASON_BOUNDS; + + info->mask_to_left = (opcode == BPF_ADD && off_is_neg) || + (opcode == BPF_SUB && !off_is_neg); + } + + err = retrieve_ptr_limit(ptr_reg, &alu_limit, info->mask_to_left); if (err < 0) return err; @@ -6523,8 +6529,8 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, /* In commit phase we narrow the masking window based on * the observed pointer move after the simulated operation. */ - alu_state = tmp_aux->alu_state; - alu_limit = abs(tmp_aux->alu_limit - alu_limit); + alu_state = info->aux.alu_state; + alu_limit = abs(info->aux.alu_limit - alu_limit); } else { alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0; alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0; @@ -6539,8 +6545,12 @@ do_sim: /* If we're in commit phase, we're done here given we already * pushed the truncated dst_reg into the speculative verification * stack. + * + * Also, when register is a known constant, we rewrite register-based + * operation to immediate-based, and thus do not need masking (and as + * a consequence, do not need to simulate the zero-truncation either). */ - if (commit_window) + if (commit_window || off_is_imm) return 0; /* Simulate and find potential out-of-bounds access under @@ -6685,7 +6695,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value; u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value, umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value; - struct bpf_insn_aux_data tmp_aux = {}; + struct bpf_sanitize_info info = {}; u8 opcode = BPF_OP(insn->code); u32 dst = insn->dst_reg; int ret; @@ -6754,7 +6764,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg, - &tmp_aux, false); + &info, false); if (ret < 0) return sanitize_err(env, insn, ret, off_reg, dst_reg); } @@ -6895,7 +6905,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return -EACCES; if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg, - &tmp_aux, true); + &info, true); if (ret < 0) return sanitize_err(env, insn, ret, off_reg, dst_reg); } @@ -7084,11 +7094,10 @@ static void scalar32_min_max_and(struct bpf_reg_state *dst_reg, s32 smin_val = src_reg->s32_min_value; u32 umax_val = src_reg->u32_max_value; - /* Assuming scalar64_min_max_and will be called so its safe - * to skip updating register for known 32-bit case. - */ - if (src_known && dst_known) + if (src_known && dst_known) { + __mark_reg32_known(dst_reg, var32_off.value); return; + } /* We get our minimum from the var_off, since that's inherently * bitwise. Our maximum is the minimum of the operands' maxima. @@ -7108,7 +7117,6 @@ static void scalar32_min_max_and(struct bpf_reg_state *dst_reg, dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } - } static void scalar_min_max_and(struct bpf_reg_state *dst_reg, @@ -7155,11 +7163,10 @@ static void scalar32_min_max_or(struct bpf_reg_state *dst_reg, s32 smin_val = src_reg->s32_min_value; u32 umin_val = src_reg->u32_min_value; - /* Assuming scalar64_min_max_or will be called so it is safe - * to skip updating register for known case. - */ - if (src_known && dst_known) + if (src_known && dst_known) { + __mark_reg32_known(dst_reg, var32_off.value); return; + } /* We get our maximum from the var_off, and our minimum is the * maximum of the operands' minima @@ -7224,11 +7231,10 @@ static void scalar32_min_max_xor(struct bpf_reg_state *dst_reg, struct tnum var32_off = tnum_subreg(dst_reg->var_off); s32 smin_val = src_reg->s32_min_value; - /* Assuming scalar64_min_max_xor will be called so it is safe - * to skip updating register for known case. - */ - if (src_known && dst_known) + if (src_known && dst_known) { + __mark_reg32_known(dst_reg, var32_off.value); return; + } /* We get both minimum and maximum from the var32_off. */ dst_reg->u32_min_value = var32_off.value; @@ -13200,6 +13206,17 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, return 0; } +BTF_SET_START(btf_id_deny) +BTF_ID_UNUSED +#ifdef CONFIG_SMP +BTF_ID(func, migrate_disable) +BTF_ID(func, migrate_enable) +#endif +#if !defined CONFIG_PREEMPT_RCU && !defined CONFIG_TINY_RCU +BTF_ID(func, rcu_read_unlock_strict) +#endif +BTF_SET_END(btf_id_deny) + static int check_attach_btf_id(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; @@ -13259,6 +13276,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) ret = bpf_lsm_verify_prog(&env->log, prog); if (ret < 0) return ret; + } else if (prog->type == BPF_PROG_TYPE_TRACING && + btf_id_set_contains(&btf_id_deny, btf_id)) { + return -EINVAL; } key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id); @@ -13358,12 +13378,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; - if (bpf_prog_is_dev_bound(env->prog->aux)) { - ret = bpf_prog_offload_verifier_prep(env->prog); - if (ret) - goto skip_full_check; - } - env->explored_states = kvcalloc(state_htab_size(env), sizeof(struct bpf_verifier_state_list *), GFP_USER); @@ -13391,6 +13405,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, if (ret < 0) goto skip_full_check; + if (bpf_prog_is_dev_bound(env->prog->aux)) { + ret = bpf_prog_offload_verifier_prep(env->prog); + if (ret) + goto skip_full_check; + } + ret = check_cfg(env); if (ret < 0) goto skip_full_check; diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 6ecd3f3a52b5..9f58049ac16d 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -1105,28 +1105,30 @@ static int seccomp_do_user_notification(int this_syscall, up(&match->notif->request); wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM); - mutex_unlock(&match->notify_lock); /* * This is where we wait for a reply from userspace. */ -wait: - err = wait_for_completion_interruptible(&n.ready); - mutex_lock(&match->notify_lock); - if (err == 0) { - /* Check if we were woken up by a addfd message */ + do { + mutex_unlock(&match->notify_lock); + err = wait_for_completion_interruptible(&n.ready); + mutex_lock(&match->notify_lock); + if (err != 0) + goto interrupted; + addfd = list_first_entry_or_null(&n.addfd, struct seccomp_kaddfd, list); - if (addfd && n.state != SECCOMP_NOTIFY_REPLIED) { + /* Check if we were woken up by a addfd message */ + if (addfd) seccomp_handle_addfd(addfd); - mutex_unlock(&match->notify_lock); - goto wait; - } - ret = n.val; - err = n.error; - flags = n.flags; - } + } while (n.state != SECCOMP_NOTIFY_REPLIED); + + ret = n.val; + err = n.error; + flags = n.flags; + +interrupted: /* If there were any pending addfd calls, clear them out */ list_for_each_entry_safe(addfd, tmp, &n.addfd, list) { /* The process went away before we got a chance to handle it */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 14edf84cc571..d4a78e08f6d8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -225,7 +225,27 @@ static int bpf_stats_handler(struct ctl_table *table, int write, mutex_unlock(&bpf_stats_enabled_mutex); return ret; } -#endif + +static int bpf_unpriv_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret, unpriv_enable = *(int *)table->data; + bool locked_state = unpriv_enable == 1; + struct ctl_table tmp = *table; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + tmp.data = &unpriv_enable; + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + if (write && !ret) { + if (locked_state && unpriv_enable != 1) + return -EPERM; + *(int *)table->data = unpriv_enable; + } + return ret; +} +#endif /* CONFIG_BPF_SYSCALL && CONFIG_SYSCTL */ /* * /proc/sys support @@ -2600,10 +2620,9 @@ static struct ctl_table kern_table[] = { .data = &sysctl_unprivileged_bpf_disabled, .maxlen = sizeof(sysctl_unprivileged_bpf_disabled), .mode = 0644, - /* only handle a transition from default "0" to "1" */ - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ONE, - .extra2 = SYSCTL_ONE, + .proc_handler = bpf_unpriv_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = &two, }, { .procname = "bpf_stats_enabled", diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c index a1071cdefb5a..af9302141bcf 100644 --- a/lib/percpu-refcount.c +++ b/lib/percpu-refcount.c @@ -275,7 +275,7 @@ static void __percpu_ref_switch_mode(struct percpu_ref *ref, wait_event_lock_irq(percpu_ref_switch_waitq, !data->confirm_switch, percpu_ref_switch_lock); - if (data->force_atomic || (ref->percpu_count_ptr & __PERCPU_REF_DEAD)) + if (data->force_atomic || percpu_ref_is_dying(ref)) __percpu_ref_switch_to_atomic(ref, confirm_switch); else __percpu_ref_switch_to_percpu(ref); @@ -385,7 +385,7 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref, spin_lock_irqsave(&percpu_ref_switch_lock, flags); - WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_DEAD, + WARN_ONCE(percpu_ref_is_dying(ref), "%s called more than once on %ps!", __func__, ref->data->release); @@ -465,7 +465,7 @@ void percpu_ref_resurrect(struct percpu_ref *ref) spin_lock_irqsave(&percpu_ref_switch_lock, flags); - WARN_ON_ONCE(!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)); + WARN_ON_ONCE(!percpu_ref_is_dying(ref)); WARN_ON_ONCE(__ref_is_percpu(ref, &percpu_count)); ref->percpu_count_ptr &= ~__PERCPU_REF_DEAD; diff --git a/net/Kconfig b/net/Kconfig index f5ee7c65e6b4..c7392c449b25 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -302,21 +302,6 @@ config BQL select DQL default y -config BPF_JIT - bool "enable BPF Just In Time compiler" - depends on HAVE_CBPF_JIT || HAVE_EBPF_JIT - depends on MODULES - help - Berkeley Packet Filter filtering capabilities are normally handled - by an interpreter. This option allows kernel to generate a native - code when filter is loaded in memory. This should speedup - packet sniffing (libpcap/tcpdump). - - Note, admin should enable this feature changing: - /proc/sys/net/core/bpf_jit_enable - /proc/sys/net/core/bpf_jit_harden (optional) - /proc/sys/net/core/bpf_jit_kallsyms (optional) - config BPF_STREAM_PARSER bool "enable BPF STREAM_PARSER" depends on INET @@ -470,15 +455,3 @@ config ETHTOOL_NETLINK e.g. notification messages. endif # if NET - -# Used by archs to tell that they support BPF JIT compiler plus which flavour. -# Only one of the two can be selected for a specific arch since eBPF JIT supersedes -# the cBPF JIT. - -# Classic BPF JIT (cBPF) -config HAVE_CBPF_JIT - bool - -# Extended BPF JIT (eBPF) -config HAVE_EBPF_JIT - bool diff --git a/net/can/isotp.c b/net/can/isotp.c index 9f94ad3caee9..253b24417c8e 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1062,27 +1062,31 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (len < ISOTP_MIN_NAMELEN) return -EINVAL; + if (addr->can_addr.tp.tx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG)) + return -EADDRNOTAVAIL; + + if (!addr->can_ifindex) + return -ENODEV; + + lock_sock(sk); + /* do not register frame reception for functional addressing */ if (so->opt.flags & CAN_ISOTP_SF_BROADCAST) do_rx_reg = 0; /* do not validate rx address for functional addressing */ if (do_rx_reg) { - if (addr->can_addr.tp.rx_id == addr->can_addr.tp.tx_id) - return -EADDRNOTAVAIL; + if (addr->can_addr.tp.rx_id == addr->can_addr.tp.tx_id) { + err = -EADDRNOTAVAIL; + goto out; + } - if (addr->can_addr.tp.rx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG)) - return -EADDRNOTAVAIL; + if (addr->can_addr.tp.rx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG)) { + err = -EADDRNOTAVAIL; + goto out; + } } - if (addr->can_addr.tp.tx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG)) - return -EADDRNOTAVAIL; - - if (!addr->can_ifindex) - return -ENODEV; - - lock_sock(sk); - if (so->bound && addr->can_ifindex == so->ifindex && addr->can_addr.tp.rx_id == so->rxid && addr->can_addr.tp.tx_id == so->txid) @@ -1164,16 +1168,13 @@ static int isotp_getname(struct socket *sock, struct sockaddr *uaddr, int peer) return ISOTP_MIN_NAMELEN; } -static int isotp_setsockopt(struct socket *sock, int level, int optname, +static int isotp_setsockopt_locked(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); int ret = 0; - if (level != SOL_CAN_ISOTP) - return -EINVAL; - if (so->bound) return -EISCONN; @@ -1248,6 +1249,22 @@ static int isotp_setsockopt(struct socket *sock, int level, int optname, return ret; } +static int isotp_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen) + +{ + struct sock *sk = sock->sk; + int ret; + + if (level != SOL_CAN_ISOTP) + return -EINVAL; + + lock_sock(sk); + ret = isotp_setsockopt_locked(sock, level, optname, optval, optlen); + release_sock(sk); + return ret; +} + static int isotp_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { diff --git a/net/core/dev.c b/net/core/dev.c index 222b1d322c96..ef8cf7619baf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3853,7 +3853,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, if (q->flags & TCQ_F_NOLOCK) { rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; - qdisc_run(q); + if (likely(!netif_xmit_frozen_or_stopped(txq))) + qdisc_run(q); if (unlikely(to_free)) kfree_skb_list(to_free); @@ -5025,25 +5026,43 @@ static __latent_entropy void net_tx_action(struct softirq_action *h) sd->output_queue_tailp = &sd->output_queue; local_irq_enable(); + rcu_read_lock(); + while (head) { struct Qdisc *q = head; spinlock_t *root_lock = NULL; head = head->next_sched; - if (!(q->flags & TCQ_F_NOLOCK)) { - root_lock = qdisc_lock(q); - spin_lock(root_lock); - } /* We need to make sure head->next_sched is read * before clearing __QDISC_STATE_SCHED */ smp_mb__before_atomic(); + + if (!(q->flags & TCQ_F_NOLOCK)) { + root_lock = qdisc_lock(q); + spin_lock(root_lock); + } else if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, + &q->state))) { + /* There is a synchronize_net() between + * STATE_DEACTIVATED flag being set and + * qdisc_reset()/some_qdisc_is_busy() in + * dev_deactivate(), so we can safely bail out + * early here to avoid data race between + * qdisc_deactivate() and some_qdisc_is_busy() + * for lockless qdisc. + */ + clear_bit(__QDISC_STATE_SCHED, &q->state); + continue; + } + clear_bit(__QDISC_STATE_SCHED, &q->state); qdisc_run(q); if (root_lock) spin_unlock(root_lock); } + + rcu_read_unlock(); } xfrm_dev_backlog(sd); diff --git a/net/core/filter.c b/net/core/filter.c index cae56d08a670..65ab4e21c087 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3784,6 +3784,7 @@ static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, __skb_push(skb, head_room); memset(skb->data, 0, head_room); skb_reset_mac_header(skb); + skb_reset_mac_len(skb); } return ret; diff --git a/net/core/sock.c b/net/core/sock.c index c761c4a0b66b..958614ea16ed 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2132,10 +2132,10 @@ void skb_orphan_partial(struct sk_buff *skb) if (skb_is_tcp_pure_ack(skb)) return; - if (can_skb_orphan_partial(skb)) - skb_set_owner_sk_safe(skb, skb->sk); - else - skb_orphan(skb); + if (can_skb_orphan_partial(skb) && skb_set_owner_sk_safe(skb, skb->sk)) + return; + + skb_orphan(skb); } EXPORT_SYMBOL(skb_orphan_partial); diff --git a/net/dsa/master.c b/net/dsa/master.c index 052a977914a6..63adbc21a735 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -147,8 +147,7 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, struct dsa_switch *ds = cpu_dp->ds; int port = cpu_dp->index; int len = ETH_GSTRING_LEN; - int mcount = 0, count; - unsigned int i; + int mcount = 0, count, i; uint8_t pfx[4]; uint8_t *ndata; @@ -178,6 +177,8 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, */ ds->ops->get_strings(ds, port, stringset, ndata); count = ds->ops->get_sset_count(ds, port, stringset); + if (count < 0) + return; for (i = 0; i < count; i++) { memmove(ndata + (i * len + sizeof(pfx)), ndata + i * len, len - sizeof(pfx)); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 8c0f3c6ab365..d4756b920108 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -776,13 +776,15 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset) struct dsa_switch *ds = dp->ds; if (sset == ETH_SS_STATS) { - int count; + int count = 0; - count = 4; - if (ds->ops->get_sset_count) - count += ds->ops->get_sset_count(ds, dp->index, sset); + if (ds->ops->get_sset_count) { + count = ds->ops->get_sset_count(ds, dp->index, sset); + if (count < 0) + return count; + } - return count; + return count + 4; } else if (sset == ETH_SS_TEST) { return net_selftest_get_count(); } diff --git a/net/ethtool/stats.c b/net/ethtool/stats.c index b7642dc96d50..ec07f5765e03 100644 --- a/net/ethtool/stats.c +++ b/net/ethtool/stats.c @@ -119,7 +119,7 @@ static int stats_prepare_data(const struct ethnl_req_info *req_base, */ memset(&data->phy_stats, 0xff, sizeof(data->phy_stats)); memset(&data->mac_stats, 0xff, sizeof(data->mac_stats)); - memset(&data->ctrl_stats, 0xff, sizeof(data->mac_stats)); + memset(&data->ctrl_stats, 0xff, sizeof(data->ctrl_stats)); memset(&data->rmon_stats, 0xff, sizeof(data->rmon_stats)); if (test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask) && diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index bfcdc75fc01e..26c32407f029 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -218,6 +218,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) if (master) { skb->dev = master->dev; skb_reset_mac_header(skb); + skb_reset_mac_len(skb); hsr_forward_skb(skb, master); } else { atomic_long_inc(&dev->tx_dropped); @@ -259,6 +260,7 @@ static struct sk_buff *hsr_init_skb(struct hsr_port *master) goto out; skb_reset_mac_header(skb); + skb_reset_mac_len(skb); skb_reset_network_header(skb); skb_reset_transport_header(skb); diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 6852e9bccf5b..ceb8afb2a62f 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -474,8 +474,8 @@ static void handle_std_frame(struct sk_buff *skb, } } -void hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, - struct hsr_frame_info *frame) +int hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame) { struct hsr_port *port = frame->port_rcv; struct hsr_priv *hsr = port->hsr; @@ -483,20 +483,26 @@ void hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, /* HSRv0 supervisory frames double as a tag so treat them as tagged. */ if ((!hsr->prot_version && proto == htons(ETH_P_PRP)) || proto == htons(ETH_P_HSR)) { + /* Check if skb contains hsr_ethhdr */ + if (skb->mac_len < sizeof(struct hsr_ethhdr)) + return -EINVAL; + /* HSR tagged frame :- Data or Supervision */ frame->skb_std = NULL; frame->skb_prp = NULL; frame->skb_hsr = skb; frame->sequence_nr = hsr_get_skb_sequence_nr(skb); - return; + return 0; } /* Standard frame or PRP from master port */ handle_std_frame(skb, frame); + + return 0; } -void prp_fill_frame_info(__be16 proto, struct sk_buff *skb, - struct hsr_frame_info *frame) +int prp_fill_frame_info(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame) { /* Supervision frame */ struct prp_rct *rct = skb_get_PRP_rct(skb); @@ -507,9 +513,11 @@ void prp_fill_frame_info(__be16 proto, struct sk_buff *skb, frame->skb_std = NULL; frame->skb_prp = skb; frame->sequence_nr = prp_get_skb_sequence_nr(rct); - return; + return 0; } handle_std_frame(skb, frame); + + return 0; } static int fill_frame_info(struct hsr_frame_info *frame, @@ -519,9 +527,10 @@ static int fill_frame_info(struct hsr_frame_info *frame, struct hsr_vlan_ethhdr *vlan_hdr; struct ethhdr *ethhdr; __be16 proto; + int ret; - /* Check if skb contains hsr_ethhdr */ - if (skb->mac_len < sizeof(struct hsr_ethhdr)) + /* Check if skb contains ethhdr */ + if (skb->mac_len < sizeof(struct ethhdr)) return -EINVAL; memset(frame, 0, sizeof(*frame)); @@ -548,7 +557,10 @@ static int fill_frame_info(struct hsr_frame_info *frame, frame->is_from_san = false; frame->port_rcv = port; - hsr->proto_ops->fill_frame_info(proto, skb, frame); + ret = hsr->proto_ops->fill_frame_info(proto, skb, frame); + if (ret) + return ret; + check_local_dest(port->hsr, skb, frame); return 0; diff --git a/net/hsr/hsr_forward.h b/net/hsr/hsr_forward.h index b6acaafa83fc..206636750b30 100644 --- a/net/hsr/hsr_forward.h +++ b/net/hsr/hsr_forward.h @@ -24,8 +24,8 @@ struct sk_buff *prp_get_untagged_frame(struct hsr_frame_info *frame, struct hsr_port *port); bool prp_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port); bool hsr_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port); -void prp_fill_frame_info(__be16 proto, struct sk_buff *skb, - struct hsr_frame_info *frame); -void hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, - struct hsr_frame_info *frame); +int prp_fill_frame_info(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame); +int hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame); #endif /* __HSR_FORWARD_H */ diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 8f264672b70b..53d1f7a82463 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -186,8 +186,8 @@ struct hsr_proto_ops { struct hsr_port *port); struct sk_buff * (*create_tagged_frame)(struct hsr_frame_info *frame, struct hsr_port *port); - void (*fill_frame_info)(__be16 proto, struct sk_buff *skb, - struct hsr_frame_info *frame); + int (*fill_frame_info)(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame); bool (*invalid_dan_ingress_frame)(__be16 protocol); void (*update_san_info)(struct hsr_node *node, bool is_sup); }; diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index c5227d42faf5..b70e6bbf6021 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -60,12 +60,11 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) goto finish_pass; skb_push(skb, ETH_HLEN); - - if (skb_mac_header(skb) != skb->data) { - WARN_ONCE(1, "%s:%d: Malformed frame at source port %s)\n", - __func__, __LINE__, port->dev->name); - goto finish_consume; - } + skb_reset_mac_header(skb); + if ((!hsr->prot_version && protocol == htons(ETH_P_PRP)) || + protocol == htons(ETH_P_HSR)) + skb_set_network_header(skb, ETH_HLEN + HSR_HLEN); + skb_reset_mac_len(skb); hsr_forward_skb(skb, port); diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index dff4f0eb96b0..9e41eff4a685 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -185,6 +185,7 @@ BTF_ID(func, tcp_reno_cong_avoid) BTF_ID(func, tcp_reno_undo_cwnd) BTF_ID(func, tcp_slow_start) BTF_ID(func, tcp_cong_avoid_ai) +#ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE #if IS_BUILTIN(CONFIG_TCP_CONG_CUBIC) BTF_ID(func, cubictcp_init) @@ -213,6 +214,7 @@ BTF_ID(func, bbr_min_tso_segs) BTF_ID(func, bbr_set_state) #endif #endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_X86 */ BTF_SET_END(bpf_tcp_ca_kfunc_ids) static bool bpf_tcp_ca_check_kfunc_call(u32 kfunc_btf_id) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 0d59efb6b49e..d36ef9d25e73 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1745,10 +1745,7 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) IPV6_TLV_PADN, 0 }; /* we assume size > sizeof(ra) here */ - /* limit our allocations to order-0 page */ - size = min_t(int, size, SKB_MAX_ORDER(0, 0)); skb = sock_alloc_send_skb(sk, size, 1, &err); - if (!skb) return NULL; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 47a0dc46cbdb..28e44782c94d 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -343,7 +343,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb); - if (!(fhdr->frag_off & htons(0xFFF9))) { + if (!(fhdr->frag_off & htons(IP6_OFFSET | IP6_MF))) { /* It is not a fragmented frame */ skb->transport_header += sizeof(struct frag_hdr); __IP6_INC_STATS(net, @@ -351,6 +351,8 @@ static int ipv6_frag_rcv(struct sk_buff *skb) IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb); IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; + IP6CB(skb)->frag_max_size = ntohs(hdr->payload_len) + + sizeof(struct ipv6hdr); return 1; } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 8fcbaa1eedf3..214404a558fb 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -50,12 +50,6 @@ struct ieee80211_local; #define IEEE80211_ENCRYPT_HEADROOM 8 #define IEEE80211_ENCRYPT_TAILROOM 18 -/* IEEE 802.11 (Ch. 9.5 Defragmentation) requires support for concurrent - * reception of at least three fragmented frames. This limit can be increased - * by changing this define, at the cost of slower frame reassembly and - * increased memory use (about 2 kB of RAM per entry). */ -#define IEEE80211_FRAGMENT_MAX 4 - /* power level hasn't been configured (or set to automatic) */ #define IEEE80211_UNSET_POWER_LEVEL INT_MIN @@ -88,18 +82,6 @@ extern const u8 ieee80211_ac_to_qos_mask[IEEE80211_NUM_ACS]; #define IEEE80211_MAX_NAN_INSTANCE_ID 255 -struct ieee80211_fragment_entry { - struct sk_buff_head skb_list; - unsigned long first_frag_time; - u16 seq; - u16 extra_len; - u16 last_frag; - u8 rx_queue; - bool check_sequential_pn; /* needed for CCMP/GCMP */ - u8 last_pn[6]; /* PN of the last fragment if CCMP was used */ -}; - - struct ieee80211_bss { u32 device_ts_beacon, device_ts_presp; @@ -241,8 +223,15 @@ struct ieee80211_rx_data { */ int security_idx; - u32 tkip_iv32; - u16 tkip_iv16; + union { + struct { + u32 iv32; + u16 iv16; + } tkip; + struct { + u8 pn[IEEE80211_CCMP_PN_LEN]; + } ccm_gcm; + }; }; struct ieee80211_csa_settings { @@ -902,9 +891,7 @@ struct ieee80211_sub_if_data { char name[IFNAMSIZ]; - /* Fragment table for host-based reassembly */ - struct ieee80211_fragment_entry fragments[IEEE80211_FRAGMENT_MAX]; - unsigned int fragment_next; + struct ieee80211_fragment_cache frags; /* TID bitmap for NoAck policy */ u16 noack_map; @@ -2320,4 +2307,7 @@ u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw, #define debug_noinline #endif +void ieee80211_init_frag_cache(struct ieee80211_fragment_cache *cache); +void ieee80211_destroy_frag_cache(struct ieee80211_fragment_cache *cache); + #endif /* IEEE80211_I_H */ diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 7032a2b59249..2e2f73a4aa73 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -8,7 +8,7 @@ * Copyright 2008, Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (c) 2016 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include <linux/slab.h> #include <linux/kernel.h> @@ -677,16 +677,12 @@ static void ieee80211_set_multicast_list(struct net_device *dev) */ static void ieee80211_teardown_sdata(struct ieee80211_sub_if_data *sdata) { - int i; - /* free extra data */ ieee80211_free_keys(sdata, false); ieee80211_debugfs_remove_netdev(sdata); - for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) - __skb_queue_purge(&sdata->fragments[i].skb_list); - sdata->fragment_next = 0; + ieee80211_destroy_frag_cache(&sdata->frags); if (ieee80211_vif_is_mesh(&sdata->vif)) ieee80211_mesh_teardown_sdata(sdata); @@ -1930,8 +1926,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, sdata->wdev.wiphy = local->hw.wiphy; sdata->local = local; - for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) - skb_queue_head_init(&sdata->fragments[i].skb_list); + ieee80211_init_frag_cache(&sdata->frags); INIT_LIST_HEAD(&sdata->key_list); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 56c068cb49c4..f695fc80088b 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -799,6 +799,7 @@ int ieee80211_key_link(struct ieee80211_key *key, struct ieee80211_sub_if_data *sdata, struct sta_info *sta) { + static atomic_t key_color = ATOMIC_INIT(0); struct ieee80211_key *old_key; int idx = key->conf.keyidx; bool pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE; @@ -850,6 +851,12 @@ int ieee80211_key_link(struct ieee80211_key *key, key->sdata = sdata; key->sta = sta; + /* + * Assign a unique ID to every key so we can easily prevent mixed + * key and fragment cache attacks. + */ + key->color = atomic_inc_return(&key_color); + increment_tailroom_need_count(sdata); ret = ieee80211_key_replace(sdata, sta, pairwise, old_key, key); diff --git a/net/mac80211/key.h b/net/mac80211/key.h index 7ad72e9b4991..1e326c89d721 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -128,6 +128,8 @@ struct ieee80211_key { } debugfs; #endif + unsigned int color; + /* * key config, must be last because it contains key * material as variable length member diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 62047e93e217..1bb43edd47b6 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -6,7 +6,7 @@ * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include <linux/jiffies.h> @@ -2123,19 +2123,34 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) return result; } +void ieee80211_init_frag_cache(struct ieee80211_fragment_cache *cache) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cache->entries); i++) + skb_queue_head_init(&cache->entries[i].skb_list); +} + +void ieee80211_destroy_frag_cache(struct ieee80211_fragment_cache *cache) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cache->entries); i++) + __skb_queue_purge(&cache->entries[i].skb_list); +} + static inline struct ieee80211_fragment_entry * -ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata, +ieee80211_reassemble_add(struct ieee80211_fragment_cache *cache, unsigned int frag, unsigned int seq, int rx_queue, struct sk_buff **skb) { struct ieee80211_fragment_entry *entry; - entry = &sdata->fragments[sdata->fragment_next++]; - if (sdata->fragment_next >= IEEE80211_FRAGMENT_MAX) - sdata->fragment_next = 0; + entry = &cache->entries[cache->next++]; + if (cache->next >= IEEE80211_FRAGMENT_MAX) + cache->next = 0; - if (!skb_queue_empty(&entry->skb_list)) - __skb_queue_purge(&entry->skb_list); + __skb_queue_purge(&entry->skb_list); __skb_queue_tail(&entry->skb_list, *skb); /* no need for locking */ *skb = NULL; @@ -2150,14 +2165,14 @@ ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata, } static inline struct ieee80211_fragment_entry * -ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, +ieee80211_reassemble_find(struct ieee80211_fragment_cache *cache, unsigned int frag, unsigned int seq, int rx_queue, struct ieee80211_hdr *hdr) { struct ieee80211_fragment_entry *entry; int i, idx; - idx = sdata->fragment_next; + idx = cache->next; for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) { struct ieee80211_hdr *f_hdr; struct sk_buff *f_skb; @@ -2166,7 +2181,7 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, if (idx < 0) idx = IEEE80211_FRAGMENT_MAX - 1; - entry = &sdata->fragments[idx]; + entry = &cache->entries[idx]; if (skb_queue_empty(&entry->skb_list) || entry->seq != seq || entry->rx_queue != rx_queue || entry->last_frag + 1 != frag) @@ -2194,15 +2209,27 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, return NULL; } +static bool requires_sequential_pn(struct ieee80211_rx_data *rx, __le16 fc) +{ + return rx->key && + (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) && + ieee80211_has_protected(fc); +} + static ieee80211_rx_result debug_noinline ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) { + struct ieee80211_fragment_cache *cache = &rx->sdata->frags; struct ieee80211_hdr *hdr; u16 sc; __le16 fc; unsigned int frag, seq; struct ieee80211_fragment_entry *entry; struct sk_buff *skb; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); hdr = (struct ieee80211_hdr *)rx->skb->data; fc = hdr->frame_control; @@ -2218,6 +2245,9 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) goto out_no_led; } + if (rx->sta) + cache = &rx->sta->frags; + if (likely(!ieee80211_has_morefrags(fc) && frag == 0)) goto out; @@ -2236,20 +2266,17 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) if (frag == 0) { /* This is the first fragment of a new frame. */ - entry = ieee80211_reassemble_add(rx->sdata, frag, seq, + entry = ieee80211_reassemble_add(cache, frag, seq, rx->seqno_idx, &(rx->skb)); - if (rx->key && - (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) && - ieee80211_has_protected(fc)) { + if (requires_sequential_pn(rx, fc)) { int queue = rx->security_idx; /* Store CCMP/GCMP PN so that we can verify that the * next fragment has a sequential PN value. */ entry->check_sequential_pn = true; + entry->is_protected = true; + entry->key_color = rx->key->color; memcpy(entry->last_pn, rx->key->u.ccmp.rx_pn[queue], IEEE80211_CCMP_PN_LEN); @@ -2261,6 +2288,11 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) sizeof(rx->key->u.gcmp.rx_pn[queue])); BUILD_BUG_ON(IEEE80211_CCMP_PN_LEN != IEEE80211_GCMP_PN_LEN); + } else if (rx->key && + (ieee80211_has_protected(fc) || + (status->flag & RX_FLAG_DECRYPTED))) { + entry->is_protected = true; + entry->key_color = rx->key->color; } return RX_QUEUED; } @@ -2268,7 +2300,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) /* This is a fragment for a frame that should already be pending in * fragment cache. Add this fragment to the end of the pending entry. */ - entry = ieee80211_reassemble_find(rx->sdata, frag, seq, + entry = ieee80211_reassemble_find(cache, frag, seq, rx->seqno_idx, hdr); if (!entry) { I802_DEBUG_INC(rx->local->rx_handlers_drop_defrag); @@ -2283,25 +2315,39 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) if (entry->check_sequential_pn) { int i; u8 pn[IEEE80211_CCMP_PN_LEN], *rpn; - int queue; - if (!rx->key || - (rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256 && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP_256)) + if (!requires_sequential_pn(rx, fc)) + return RX_DROP_UNUSABLE; + + /* Prevent mixed key and fragment cache attacks */ + if (entry->key_color != rx->key->color) return RX_DROP_UNUSABLE; + memcpy(pn, entry->last_pn, IEEE80211_CCMP_PN_LEN); for (i = IEEE80211_CCMP_PN_LEN - 1; i >= 0; i--) { pn[i]++; if (pn[i]) break; } - queue = rx->security_idx; - rpn = rx->key->u.ccmp.rx_pn[queue]; + + rpn = rx->ccm_gcm.pn; if (memcmp(pn, rpn, IEEE80211_CCMP_PN_LEN)) return RX_DROP_UNUSABLE; memcpy(entry->last_pn, pn, IEEE80211_CCMP_PN_LEN); + } else if (entry->is_protected && + (!rx->key || + (!ieee80211_has_protected(fc) && + !(status->flag & RX_FLAG_DECRYPTED)) || + rx->key->color != entry->key_color)) { + /* Drop this as a mixed key or fragment cache attack, even + * if for TKIP Michael MIC should protect us, and WEP is a + * lost cause anyway. + */ + return RX_DROP_UNUSABLE; + } else if (entry->is_protected && rx->key && + entry->key_color != rx->key->color && + (status->flag & RX_FLAG_DECRYPTED)) { + return RX_DROP_UNUSABLE; } skb_pull(rx->skb, ieee80211_hdrlen(fc)); @@ -2494,13 +2540,13 @@ static bool ieee80211_frame_allowed(struct ieee80211_rx_data *rx, __le16 fc) struct ethhdr *ehdr = (struct ethhdr *) rx->skb->data; /* - * Allow EAPOL frames to us/the PAE group address regardless - * of whether the frame was encrypted or not. + * Allow EAPOL frames to us/the PAE group address regardless of + * whether the frame was encrypted or not, and always disallow + * all other destination addresses for them. */ - if (ehdr->h_proto == rx->sdata->control_port_protocol && - (ether_addr_equal(ehdr->h_dest, rx->sdata->vif.addr) || - ether_addr_equal(ehdr->h_dest, pae_group_addr))) - return true; + if (unlikely(ehdr->h_proto == rx->sdata->control_port_protocol)) + return ether_addr_equal(ehdr->h_dest, rx->sdata->vif.addr) || + ether_addr_equal(ehdr->h_dest, pae_group_addr); if (ieee80211_802_1x_port_control(rx) || ieee80211_drop_unencrypted(rx, fc)) @@ -2525,8 +2571,28 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb, cfg80211_rx_control_port(dev, skb, noencrypt); dev_kfree_skb(skb); } else { + struct ethhdr *ehdr = (void *)skb_mac_header(skb); + memset(skb->cb, 0, sizeof(skb->cb)); + /* + * 802.1X over 802.11 requires that the authenticator address + * be used for EAPOL frames. However, 802.1X allows the use of + * the PAE group address instead. If the interface is part of + * a bridge and we pass the frame with the PAE group address, + * then the bridge will forward it to the network (even if the + * client was not associated yet), which isn't supposed to + * happen. + * To avoid that, rewrite the destination address to our own + * address, so that the authenticator (e.g. hostapd) will see + * the frame, but bridge won't forward it anywhere else. Note + * that due to earlier filtering, the only other address can + * be the PAE group address. + */ + if (unlikely(skb->protocol == sdata->control_port_protocol && + !ether_addr_equal(ehdr->h_dest, sdata->vif.addr))) + ether_addr_copy(ehdr->h_dest, sdata->vif.addr); + /* deliver to local stack */ if (rx->list) list_add_tail(&skb->list, rx->list); @@ -2566,6 +2632,7 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) if ((sdata->vif.type == NL80211_IFTYPE_AP || sdata->vif.type == NL80211_IFTYPE_AP_VLAN) && !(sdata->flags & IEEE80211_SDATA_DONT_BRIDGE_PACKETS) && + ehdr->h_proto != rx->sdata->control_port_protocol && (sdata->vif.type != NL80211_IFTYPE_AP_VLAN || !sdata->u.vlan.sta)) { if (is_multicast_ether_addr(ehdr->h_dest) && ieee80211_vif_get_num_mcast_if(sdata) != 0) { @@ -2675,7 +2742,7 @@ __ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx, u8 data_offset) if (ieee80211_data_to_8023_exthdr(skb, ðhdr, rx->sdata->vif.addr, rx->sdata->vif.type, - data_offset)) + data_offset, true)) return RX_DROP_UNUSABLE; ieee80211_amsdu_to_8023s(skb, &frame_list, dev->dev_addr, @@ -2732,6 +2799,23 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) if (is_multicast_ether_addr(hdr->addr1)) return RX_DROP_UNUSABLE; + if (rx->key) { + /* + * We should not receive A-MSDUs on pre-HT connections, + * and HT connections cannot use old ciphers. Thus drop + * them, as in those cases we couldn't even have SPP + * A-MSDUs or such. + */ + switch (rx->key->conf.cipher) { + case WLAN_CIPHER_SUITE_WEP40: + case WLAN_CIPHER_SUITE_WEP104: + case WLAN_CIPHER_SUITE_TKIP: + return RX_DROP_UNUSABLE; + default: + break; + } + } + return __ieee80211_rx_h_amsdu(rx, 0); } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index ec6973ee88ef..f2fb69da9b6e 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -4,7 +4,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include <linux/module.h> @@ -392,6 +392,8 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, u64_stats_init(&sta->rx_stats.syncp); + ieee80211_init_frag_cache(&sta->frags); + sta->sta_state = IEEE80211_STA_NONE; /* Mark TID as unreserved */ @@ -1102,6 +1104,8 @@ static void __sta_info_destroy_part2(struct sta_info *sta) ieee80211_sta_debugfs_remove(sta); + ieee80211_destroy_frag_cache(&sta->frags); + cleanup_single_sta(sta); } diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 78b9d0c7cc58..0333072ebd98 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -3,7 +3,7 @@ * Copyright 2002-2005, Devicescape Software, Inc. * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright(c) 2020 Intel Corporation + * Copyright(c) 2020-2021 Intel Corporation */ #ifndef STA_INFO_H @@ -439,6 +439,34 @@ struct ieee80211_sta_rx_stats { }; /* + * IEEE 802.11-2016 (10.6 "Defragmentation") recommends support for "concurrent + * reception of at least one MSDU per access category per associated STA" + * on APs, or "at least one MSDU per access category" on other interface types. + * + * This limit can be increased by changing this define, at the cost of slower + * frame reassembly and increased memory use while fragments are pending. + */ +#define IEEE80211_FRAGMENT_MAX 4 + +struct ieee80211_fragment_entry { + struct sk_buff_head skb_list; + unsigned long first_frag_time; + u16 seq; + u16 extra_len; + u16 last_frag; + u8 rx_queue; + u8 check_sequential_pn:1, /* needed for CCMP/GCMP */ + is_protected:1; + u8 last_pn[6]; /* PN of the last fragment if CCMP was used */ + unsigned int key_color; +}; + +struct ieee80211_fragment_cache { + struct ieee80211_fragment_entry entries[IEEE80211_FRAGMENT_MAX]; + unsigned int next; +}; + +/* * The bandwidth threshold below which the per-station CoDel parameters will be * scaled to be more lenient (to prevent starvation of slow stations). This * value will be scaled by the number of active stations when it is being @@ -531,6 +559,7 @@ struct ieee80211_sta_rx_stats { * @status_stats.last_ack_signal: last ACK signal * @status_stats.ack_signal_filled: last ACK signal validity * @status_stats.avg_ack_signal: average ACK signal + * @frags: fragment cache */ struct sta_info { /* General information, mostly static */ @@ -639,6 +668,8 @@ struct sta_info { struct cfg80211_chan_def tdls_chandef; + struct ieee80211_fragment_cache frags; + /* keep last! */ struct ieee80211_sta sta; }; diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 91bf32af55e9..bca47fad5a16 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -3,6 +3,7 @@ * Copyright 2002-2004, Instant802 Networks, Inc. * Copyright 2008, Jouni Malinen <j@w1.fi> * Copyright (C) 2016-2017 Intel Deutschland GmbH + * Copyright (C) 2020-2021 Intel Corporation */ #include <linux/netdevice.h> @@ -167,8 +168,8 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) update_iv: /* update IV in key information to be able to detect replays */ - rx->key->u.tkip.rx[rx->security_idx].iv32 = rx->tkip_iv32; - rx->key->u.tkip.rx[rx->security_idx].iv16 = rx->tkip_iv16; + rx->key->u.tkip.rx[rx->security_idx].iv32 = rx->tkip.iv32; + rx->key->u.tkip.rx[rx->security_idx].iv16 = rx->tkip.iv16; return RX_CONTINUE; @@ -294,8 +295,8 @@ ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx) key, skb->data + hdrlen, skb->len - hdrlen, rx->sta->sta.addr, hdr->addr1, hwaccel, rx->security_idx, - &rx->tkip_iv32, - &rx->tkip_iv16); + &rx->tkip.iv32, + &rx->tkip.iv16); if (res != TKIP_DECRYPT_OK) return RX_DROP_UNUSABLE; @@ -553,6 +554,8 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, } memcpy(key->u.ccmp.rx_pn[queue], pn, IEEE80211_CCMP_PN_LEN); + if (unlikely(ieee80211_is_frag(hdr))) + memcpy(rx->ccm_gcm.pn, pn, IEEE80211_CCMP_PN_LEN); } /* Remove CCMP header and MIC */ @@ -781,6 +784,8 @@ ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx) } memcpy(key->u.gcmp.rx_pn[queue], pn, IEEE80211_GCMP_PN_LEN); + if (unlikely(ieee80211_is_frag(hdr))) + memcpy(rx->ccm_gcm.pn, pn, IEEE80211_CCMP_PN_LEN); } /* Remove GCMP header and MIC */ diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 99fc21406168..6b825fb3fa83 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -130,7 +130,6 @@ static void mptcp_parse_option(const struct sk_buff *skb, memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN); pr_debug("MP_JOIN hmac"); } else { - pr_warn("MP_JOIN bad option size"); mp_opt->mp_join = 0; } break; @@ -1024,7 +1023,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR); } else { mptcp_pm_add_addr_echoed(msk, &mp_opt.addr); - mptcp_pm_del_add_timer(msk, &mp_opt.addr); + mptcp_pm_del_add_timer(msk, &mp_opt.addr, true); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD); } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 6ba040897738..2469e06a3a9d 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -346,18 +346,18 @@ out: struct mptcp_pm_add_entry * mptcp_pm_del_add_timer(struct mptcp_sock *msk, - struct mptcp_addr_info *addr) + struct mptcp_addr_info *addr, bool check_id) { struct mptcp_pm_add_entry *entry; struct sock *sk = (struct sock *)msk; spin_lock_bh(&msk->pm.lock); entry = mptcp_lookup_anno_list_by_saddr(msk, addr); - if (entry) + if (entry && (!check_id || entry->addr.id == addr->id)) entry->retrans_times = ADD_ADDR_RETRANS_MAX; spin_unlock_bh(&msk->pm.lock); - if (entry) + if (entry && (!check_id || entry->addr.id == addr->id)) sk_stop_timer_sync(sk, &entry->add_timer); return entry; @@ -1064,7 +1064,7 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, { struct mptcp_pm_add_entry *entry; - entry = mptcp_pm_del_add_timer(msk, addr); + entry = mptcp_pm_del_add_timer(msk, addr, false); if (entry) { list_del(&entry->list); kfree(entry); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 29a2d690d8d5..2bc199549a88 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -879,12 +879,18 @@ static bool mptcp_skb_can_collapse_to(u64 write_seq, !mpext->frozen; } +/* we can append data to the given data frag if: + * - there is space available in the backing page_frag + * - the data frag tail matches the current page_frag free offset + * - the data frag end sequence number matches the current write seq + */ static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk, const struct page_frag *pfrag, const struct mptcp_data_frag *df) { return df && pfrag->page == df->page && pfrag->size - pfrag->offset > 0 && + pfrag->offset == (df->offset + df->data_len) && df->data_seq + df->data_len == msk->write_seq; } @@ -2418,13 +2424,12 @@ static int __mptcp_init_sock(struct sock *sk) timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0); timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0); - tcp_assign_congestion_control(sk); - return 0; } static int mptcp_init_sock(struct sock *sk) { + struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); int ret; @@ -2442,6 +2447,16 @@ static int mptcp_init_sock(struct sock *sk) if (ret) return ret; + /* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will + * propagate the correct value + */ + tcp_assign_congestion_control(sk); + strcpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name); + + /* no need to keep a reference to the ops, the name will suffice */ + tcp_cleanup_congestion_control(sk); + icsk->icsk_ca_ops = NULL; + sk_sockets_allocated_inc(sk); sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1]; @@ -2616,7 +2631,6 @@ static void __mptcp_destroy_sock(struct sock *sk) sk_stream_kill_queues(sk); xfrm_sk_free_policy(sk); - tcp_cleanup_congestion_control(sk); sk_refcnt_debug_release(sk); mptcp_dispose_initial_subflow(msk); sock_put(sk); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index edc0128730df..0c6f99c67345 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -258,6 +258,7 @@ struct mptcp_sock { } rcvq_space; u32 setsockopt_seq; + char ca_name[TCP_CA_NAME_MAX]; }; #define mptcp_lock_sock(___sk, cb) do { \ @@ -671,7 +672,7 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk); bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk); struct mptcp_pm_add_entry * mptcp_pm_del_add_timer(struct mptcp_sock *msk, - struct mptcp_addr_info *addr); + struct mptcp_addr_info *addr, bool check_id); struct mptcp_pm_add_entry * mptcp_lookup_anno_list_by_saddr(struct mptcp_sock *msk, struct mptcp_addr_info *addr); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 00d941b66c1e..a79798189599 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -547,7 +547,7 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t } if (ret == 0) - tcp_set_congestion_control(sk, name, false, cap_net_admin); + strcpy(msk->ca_name, name); release_sock(sk); return ret; @@ -705,7 +705,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) sock_valbool_flag(ssk, SOCK_DBG, sock_flag(sk, SOCK_DBG)); if (inet_csk(sk)->icsk_ca_ops != inet_csk(ssk)->icsk_ca_ops) - tcp_set_congestion_control(ssk, inet_csk(sk)->icsk_ca_ops->name, false, true); + tcp_set_congestion_control(ssk, msk->ca_name, false, true); } static void __mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index a5ede357cfbc..bde6be77ea73 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -867,7 +867,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk, data_len = mpext->data_len; if (data_len == 0) { - pr_err("Infinite mapping not handled"); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX); return MAPPING_INVALID; } diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 39c02d1aeedf..1d02650dd715 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -306,8 +306,7 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, { flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT; - if (likely(!nf_flowtable_hw_offload(flow_table) || - !test_and_clear_bit(NF_FLOW_HW_REFRESH, &flow->flags))) + if (likely(!nf_flowtable_hw_offload(flow_table))) return; nf_flow_offload_add(flow_table, flow); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 2af7bdb38407..528b2f172684 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -902,10 +902,11 @@ static void flow_offload_work_add(struct flow_offload_work *offload) err = flow_offload_rule_add(offload, flow_rule); if (err < 0) - set_bit(NF_FLOW_HW_REFRESH, &offload->flow->flags); - else - set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status); + goto out; + + set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status); +out: nf_flow_offload_destroy(flow_rule); } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 528a2d7ca991..dce866d93fee 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -408,8 +408,8 @@ int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, * * Return: true on match, false otherwise. */ -static bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { struct nft_pipapo *priv = nft_set_priv(set); unsigned long *res_map, *fill_map; diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index 25a75591583e..d84afb8fa79a 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -178,6 +178,8 @@ struct nft_pipapo_elem { int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, union nft_pipapo_map_bucket *mt, bool match_only); +bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); /** * pipapo_and_field_buckets_4bit() - Intersect 4-bit buckets diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index d65ae0e23028..eabdb8d552ee 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -1131,6 +1131,9 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, bool map_index; int i, ret = 0; + if (unlikely(!irq_fpu_usable())) + return nft_pipapo_lookup(net, set, key, ext); + m = rcu_dereference(priv->match); /* This also protects access to all data related to scratch maps */ diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 3a62f97acf39..6133e412b948 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -461,11 +461,13 @@ void netlink_table_ungrab(void) static inline void netlink_lock_table(void) { + unsigned long flags; + /* read_lock() synchronizes us to netlink_table_grab */ - read_lock(&nl_table_lock); + read_lock_irqsave(&nl_table_lock, flags); atomic_inc(&nl_table_users); - read_unlock(&nl_table_lock); + read_unlock_irqrestore(&nl_table_lock, flags); } static inline void diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 9a585332ea84..da7fe9db1b00 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1191,6 +1191,7 @@ EXPORT_SYMBOL(nci_allocate_device); void nci_free_device(struct nci_dev *ndev) { nfc_free_device(ndev->nfc_dev); + nci_hci_deallocate(ndev); kfree(ndev); } EXPORT_SYMBOL(nci_free_device); diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index 6b275a387a92..96865142104f 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -792,3 +792,8 @@ struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev) return hdev; } + +void nci_hci_deallocate(struct nci_dev *ndev) +{ + kfree(ndev->hci_dev); +} diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 9c7eb8455ba8..5f1d438a0a23 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -329,7 +329,7 @@ static int rawsock_create(struct net *net, struct socket *sock, return -ESOCKTNOSUPPORT; if (sock->type == SOCK_RAW) { - if (!capable(CAP_NET_RAW)) + if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; sock->ops = &rawsock_raw_ops; } else { diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 96b524ceabca..896b8f5bc885 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -611,6 +611,14 @@ bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb, spin_lock(&meter->lock); long_delta_ms = (now_ms - meter->used); /* ms */ + if (long_delta_ms < 0) { + /* This condition means that we have several threads fighting + * for a meter lock, and the one who received the packets a + * bit later wins. Assuming that all racing threads received + * packets at the same time to avoid overflow. + */ + long_delta_ms = 0; + } /* Make sure delta_ms will not be too large, so that bucket will not * wrap around below. diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ba96db1880ea..ae906eb4b269 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -422,7 +422,8 @@ static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec64 *ts, ktime_to_timespec64_cond(shhwtstamps->hwtstamp, ts)) return TP_STATUS_TS_RAW_HARDWARE; - if (ktime_to_timespec64_cond(skb->tstamp, ts)) + if ((flags & SOF_TIMESTAMPING_SOFTWARE) && + ktime_to_timespec64_cond(skb->tstamp, ts)) return TP_STATUS_TS_SOFTWARE; return 0; @@ -2340,7 +2341,12 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, skb_copy_bits(skb, 0, h.raw + macoff, snaplen); - if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp))) + /* Always timestamp; prefer an existing software timestamp taken + * closer to the time of capture. + */ + ts_status = tpacket_get_timestamp(skb, &ts, + po->tp_tstamp | SOF_TIMESTAMPING_SOFTWARE); + if (!ts_status) ktime_get_real_ts64(&ts); status |= ts_status; diff --git a/net/rds/connection.c b/net/rds/connection.c index f2fcab182095..a3bc4b54d491 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -240,12 +240,23 @@ static struct rds_connection *__rds_conn_create(struct net *net, if (loop_trans) { rds_trans_put(loop_trans); conn->c_loopback = 1; - if (is_outgoing && trans->t_prefer_loopback) { - /* "outgoing" connection - and the transport - * says it wants the connection handled by the - * loopback transport. This is what TCP does. - */ - trans = &rds_loop_transport; + if (trans->t_prefer_loopback) { + if (likely(is_outgoing)) { + /* "outgoing" connection to local address. + * Protocol says it wants the connection + * handled by the loopback transport. + * This is what TCP does. + */ + trans = &rds_loop_transport; + } else { + /* No transport currently in use + * should end up here, but if it + * does, reset/destroy the connection. + */ + kmem_cache_free(rds_conn_slab, conn); + conn = ERR_PTR(-EOPNOTSUPP); + goto out; + } } } diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 43db0eca911f..abf19c0e3ba0 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -313,8 +313,8 @@ out: } #endif -static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, - __u32 scope_id) +int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, + __u32 scope_id) { struct net_device *dev = NULL; #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/rds/tcp.h b/net/rds/tcp.h index bad9cf49d565..dc8d745d6857 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -59,7 +59,8 @@ u32 rds_tcp_snd_una(struct rds_tcp_connection *tc); u64 rds_tcp_map_seq(struct rds_tcp_connection *tc, u32 seq); extern struct rds_transport rds_tcp_transport; void rds_tcp_accept_work(struct sock *sk); - +int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, + __u32 scope_id); /* tcp_connect.c */ int rds_tcp_conn_path_connect(struct rds_conn_path *cp); void rds_tcp_conn_path_shutdown(struct rds_conn_path *conn); diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 101cf14215a0..09cadd556d1e 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -167,6 +167,12 @@ int rds_tcp_accept_one(struct socket *sock) } #endif + if (!rds_tcp_laddr_check(sock_net(sock->sk), peer_addr, dev_if)) { + /* local address connection is only allowed via loopback */ + ret = -EOPNOTSUPP; + goto out; + } + conn = rds_conn_create(sock_net(sock->sk), my_addr, peer_addr, &rds_tcp_transport, 0, GFP_KERNEL, dev_if); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 40fbea626dfd..279f9e2a2319 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1624,7 +1624,7 @@ int tcf_classify_ingress(struct sk_buff *skb, /* If we missed on some chain */ if (ret == TC_ACT_UNSPEC && last_executed_chain) { - ext = skb_ext_add(skb, TC_SKB_EXT); + ext = tc_skb_ext_alloc(skb); if (WARN_ON_ONCE(!ext)) return TC_ACT_SHOT; ext->chain = last_executed_chain; diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index cd2748e2d4a2..d320bcfb2da2 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -407,7 +407,8 @@ static void dsmark_reset(struct Qdisc *sch) struct dsmark_qdisc_data *p = qdisc_priv(sch); pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - qdisc_reset(p->q); + if (p->q) + qdisc_reset(p->q); sch->qstats.backlog = 0; sch->q.qlen = 0; } diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 949163fe68af..cac684952edc 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -138,8 +138,15 @@ static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* Classifies packet into corresponding flow */ idx = fq_pie_classify(skb, sch, &ret); - sel_flow = &q->flows[idx]; + if (idx == 0) { + if (ret & __NET_XMIT_BYPASS) + qdisc_qstats_drop(sch); + __qdisc_drop(skb, to_free); + return ret; + } + idx--; + sel_flow = &q->flows[idx]; /* Checks whether adding a new packet would exceed memory limit */ get_pie_cb(skb)->mem_usage = skb->truesize; memory_limited = q->memory_usage > q->memory_limit + skb->truesize; @@ -297,9 +304,9 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, goto flow_error; } q->flows_cnt = nla_get_u32(tb[TCA_FQ_PIE_FLOWS]); - if (!q->flows_cnt || q->flows_cnt >= 65536) { + if (!q->flows_cnt || q->flows_cnt > 65536) { NL_SET_ERR_MSG_MOD(extack, - "Number of flows must range in [1..65535]"); + "Number of flows must range in [1..65536]"); goto flow_error; } } @@ -367,7 +374,7 @@ static void fq_pie_timer(struct timer_list *t) struct fq_pie_sched_data *q = from_timer(q, t, adapt_timer); struct Qdisc *sch = q->sch; spinlock_t *root_lock; /* to lock qdisc for probability calculations */ - u16 idx; + u32 idx; root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -388,7 +395,7 @@ static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt, { struct fq_pie_sched_data *q = qdisc_priv(sch); int err; - u16 idx; + u32 idx; pie_params_init(&q->p_params); sch->limit = 10 * 1024; @@ -500,7 +507,7 @@ static int fq_pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) static void fq_pie_reset(struct Qdisc *sch) { struct fq_pie_sched_data *q = qdisc_priv(sch); - u16 idx; + u32 idx; INIT_LIST_HEAD(&q->new_flows); INIT_LIST_HEAD(&q->old_flows); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 44991ea726fc..fc8b56bcabf3 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -35,6 +35,25 @@ const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops; EXPORT_SYMBOL(default_qdisc_ops); +static void qdisc_maybe_clear_missed(struct Qdisc *q, + const struct netdev_queue *txq) +{ + clear_bit(__QDISC_STATE_MISSED, &q->state); + + /* Make sure the below netif_xmit_frozen_or_stopped() + * checking happens after clearing STATE_MISSED. + */ + smp_mb__after_atomic(); + + /* Checking netif_xmit_frozen_or_stopped() again to + * make sure STATE_MISSED is set if the STATE_MISSED + * set by netif_tx_wake_queue()'s rescheduling of + * net_tx_action() is cleared by the above clear_bit(). + */ + if (!netif_xmit_frozen_or_stopped(txq)) + set_bit(__QDISC_STATE_MISSED, &q->state); +} + /* Main transmission queue. */ /* Modifications to data participating in scheduling must be protected with @@ -74,6 +93,7 @@ static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q) } } else { skb = SKB_XOFF_MAGIC; + qdisc_maybe_clear_missed(q, txq); } } @@ -242,6 +262,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, } } else { skb = NULL; + qdisc_maybe_clear_missed(q, txq); } if (lock) spin_unlock(lock); @@ -251,8 +272,10 @@ validate: *validate = true; if ((q->flags & TCQ_F_ONETXQUEUE) && - netif_xmit_frozen_or_stopped(txq)) + netif_xmit_frozen_or_stopped(txq)) { + qdisc_maybe_clear_missed(q, txq); return skb; + } skb = qdisc_dequeue_skb_bad_txq(q); if (unlikely(skb)) { @@ -311,6 +334,8 @@ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_stopped(txq)) skb = dev_hard_start_xmit(skb, dev, txq, &ret); + else + qdisc_maybe_clear_missed(q, txq); HARD_TX_UNLOCK(dev, txq); } else { @@ -640,8 +665,10 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); struct sk_buff *skb = NULL; + bool need_retry = true; int band; +retry: for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) { struct skb_array *q = band2list(priv, band); @@ -652,6 +679,23 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) } if (likely(skb)) { qdisc_update_stats_at_dequeue(qdisc, skb); + } else if (need_retry && + test_bit(__QDISC_STATE_MISSED, &qdisc->state)) { + /* Delay clearing the STATE_MISSED here to reduce + * the overhead of the second spin_trylock() in + * qdisc_run_begin() and __netif_schedule() calling + * in qdisc_run_end(). + */ + clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + + /* Make sure dequeuing happens after clearing + * STATE_MISSED. + */ + smp_mb__after_atomic(); + + need_retry = false; + + goto retry; } else { WRITE_ONCE(qdisc->empty, true); } @@ -1158,8 +1202,10 @@ static void dev_reset_queue(struct net_device *dev, qdisc_reset(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); - if (nolock) + if (nolock) { + clear_bit(__QDISC_STATE_MISSED, &qdisc->state); spin_unlock_bh(&qdisc->seqlock); + } } static bool some_qdisc_is_busy(struct net_device *dev) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 40f9f6c4a0a1..a79d193ff872 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4473,6 +4473,7 @@ static int sctp_setsockopt_encap_port(struct sock *sk, transports) t->encap_port = encap_port; + asoc->encap_port = encap_port; return 0; } diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index e92df779af73..55871b277f47 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -307,7 +307,7 @@ static struct ctl_table sctp_net_table[] = { .data = &init_net.sctp.encap_port, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &udp_port_max, }, diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index 94b31f2551bc..967712ba52a0 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -429,6 +429,8 @@ EXPORT_SYMBOL_GPL(smcd_alloc_dev); int smcd_register_dev(struct smcd_dev *smcd) { + int rc; + mutex_lock(&smcd_dev_list.mutex); if (list_empty(&smcd_dev_list.list)) { u8 *system_eid = NULL; @@ -448,7 +450,14 @@ int smcd_register_dev(struct smcd_dev *smcd) dev_name(&smcd->dev), smcd->pnetid, smcd->pnetid_by_user ? " (user defined)" : ""); - return device_add(&smcd->dev); + rc = device_add(&smcd->dev); + if (rc) { + mutex_lock(&smcd_dev_list.mutex); + list_del(&smcd->list); + mutex_unlock(&smcd_dev_list.mutex); + } + + return rc; } EXPORT_SYMBOL_GPL(smcd_register_dev); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index f555d335e910..42623d6b8f0e 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1677,13 +1677,6 @@ call_reserveresult(struct rpc_task *task) return; } - /* - * Even though there was an error, we may have acquired - * a request slot somehow. Make sure not to leak it. - */ - if (task->tk_rqstp) - xprt_release(task); - switch (status) { case -ENOMEM: rpc_delay(task, HZ >> 2); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index e5b5a960a69b..3509a7f139b9 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -70,6 +70,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net); static __be32 xprt_alloc_xid(struct rpc_xprt *xprt); static void xprt_destroy(struct rpc_xprt *xprt); +static void xprt_request_init(struct rpc_task *task); static DEFINE_SPINLOCK(xprt_list_lock); static LIST_HEAD(xprt_list); @@ -1606,17 +1607,40 @@ xprt_transmit(struct rpc_task *task) spin_unlock(&xprt->queue_lock); } -static void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task) +static void xprt_complete_request_init(struct rpc_task *task) +{ + if (task->tk_rqstp) + xprt_request_init(task); +} + +void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task) { set_bit(XPRT_CONGESTED, &xprt->state); - rpc_sleep_on(&xprt->backlog, task, NULL); + rpc_sleep_on(&xprt->backlog, task, xprt_complete_request_init); +} +EXPORT_SYMBOL_GPL(xprt_add_backlog); + +static bool __xprt_set_rq(struct rpc_task *task, void *data) +{ + struct rpc_rqst *req = data; + + if (task->tk_rqstp == NULL) { + memset(req, 0, sizeof(*req)); /* mark unused */ + task->tk_rqstp = req; + return true; + } + return false; } -static void xprt_wake_up_backlog(struct rpc_xprt *xprt) +bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req) { - if (rpc_wake_up_next(&xprt->backlog) == NULL) + if (rpc_wake_up_first(&xprt->backlog, __xprt_set_rq, req) == NULL) { clear_bit(XPRT_CONGESTED, &xprt->state); + return false; + } + return true; } +EXPORT_SYMBOL_GPL(xprt_wake_up_backlog); static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task) { @@ -1626,7 +1650,7 @@ static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task goto out; spin_lock(&xprt->reserve_lock); if (test_bit(XPRT_CONGESTED, &xprt->state)) { - rpc_sleep_on(&xprt->backlog, task, NULL); + xprt_add_backlog(xprt, task); ret = true; } spin_unlock(&xprt->reserve_lock); @@ -1703,11 +1727,11 @@ EXPORT_SYMBOL_GPL(xprt_alloc_slot); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req) { spin_lock(&xprt->reserve_lock); - if (!xprt_dynamic_free_slot(xprt, req)) { + if (!xprt_wake_up_backlog(xprt, req) && + !xprt_dynamic_free_slot(xprt, req)) { memset(req, 0, sizeof(*req)); /* mark unused */ list_add(&req->rq_list, &xprt->free); } - xprt_wake_up_backlog(xprt); spin_unlock(&xprt->reserve_lock); } EXPORT_SYMBOL_GPL(xprt_free_slot); @@ -1894,10 +1918,10 @@ void xprt_release(struct rpc_task *task) xdr_free_bvec(&req->rq_snd_buf); if (req->rq_cred != NULL) put_rpccred(req->rq_cred); - task->tk_rqstp = NULL; if (req->rq_release_snd_buf) req->rq_release_snd_buf(req); + task->tk_rqstp = NULL; if (likely(!bc_prealloc(req))) xprt->ops->free_slot(xprt, req); else diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 649f7d8b9733..c335c1361564 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -628,8 +628,9 @@ out_mapping_err: return false; } -/* The tail iovec might not reside in the same page as the - * head iovec. +/* The tail iovec may include an XDR pad for the page list, + * as well as additional content, and may not reside in the + * same page as the head iovec. */ static bool rpcrdma_prepare_tail_iov(struct rpcrdma_req *req, struct xdr_buf *xdr, @@ -747,19 +748,27 @@ static bool rpcrdma_prepare_readch(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, struct xdr_buf *xdr) { - struct kvec *tail = &xdr->tail[0]; - if (!rpcrdma_prepare_head_iov(r_xprt, req, xdr->head[0].iov_len)) return false; - /* If there is a Read chunk, the page list is handled + /* If there is a Read chunk, the page list is being handled * via explicit RDMA, and thus is skipped here. */ - if (tail->iov_len) { - if (!rpcrdma_prepare_tail_iov(req, xdr, - offset_in_page(tail->iov_base), - tail->iov_len)) + /* Do not include the tail if it is only an XDR pad */ + if (xdr->tail[0].iov_len > 3) { + unsigned int page_base, len; + + /* If the content in the page list is an odd length, + * xdr_write_pages() adds a pad at the beginning of + * the tail iovec. Force the tail's non-pad content to + * land at the next XDR position in the Send message. + */ + page_base = offset_in_page(xdr->tail[0].iov_base); + len = xdr->tail[0].iov_len; + page_base += len & 3; + len -= len & 3; + if (!rpcrdma_prepare_tail_iov(req, xdr, page_base, len)) return false; kref_get(&req->rl_kref); } diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 09953597d055..19a49d26b1e4 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -520,9 +520,8 @@ xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task) return; out_sleep: - set_bit(XPRT_CONGESTED, &xprt->state); - rpc_sleep_on(&xprt->backlog, task, NULL); task->tk_status = -EAGAIN; + xprt_add_backlog(xprt, task); } /** @@ -537,10 +536,11 @@ xprt_rdma_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *rqst) struct rpcrdma_xprt *r_xprt = container_of(xprt, struct rpcrdma_xprt, rx_xprt); - memset(rqst, 0, sizeof(*rqst)); - rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst)); - if (unlikely(!rpc_wake_up_next(&xprt->backlog))) - clear_bit(XPRT_CONGESTED, &xprt->state); + rpcrdma_reply_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst)); + if (!xprt_wake_up_backlog(xprt, rqst)) { + memset(rqst, 0, sizeof(*rqst)); + rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst)); + } } static bool rpcrdma_check_regbuf(struct rpcrdma_xprt *r_xprt, diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 1e965a380896..649c23518ec0 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1201,6 +1201,20 @@ rpcrdma_mr_get(struct rpcrdma_xprt *r_xprt) } /** + * rpcrdma_reply_put - Put reply buffers back into pool + * @buffers: buffer pool + * @req: object to return + * + */ +void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req) +{ + if (req->rl_reply) { + rpcrdma_rep_put(buffers, req->rl_reply); + req->rl_reply = NULL; + } +} + +/** * rpcrdma_buffer_get - Get a request buffer * @buffers: Buffer pool from which to obtain a buffer * @@ -1228,9 +1242,7 @@ rpcrdma_buffer_get(struct rpcrdma_buffer *buffers) */ void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req) { - if (req->rl_reply) - rpcrdma_rep_put(buffers, req->rl_reply); - req->rl_reply = NULL; + rpcrdma_reply_put(buffers, req); spin_lock(&buffers->rb_lock); list_add(&req->rl_list, &buffers->rb_send_bufs); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 436ad7312614..5d231d94e944 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -479,6 +479,7 @@ struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *); void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req); void rpcrdma_rep_put(struct rpcrdma_buffer *buf, struct rpcrdma_rep *rep); +void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req); bool rpcrdma_regbuf_realloc(struct rpcrdma_regbuf *rb, size_t size, gfp_t flags); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 47aa47a2b07c..316d04945587 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1010,6 +1010,8 @@ static int xs_tcp_send_request(struct rpc_rqst *req) kernel_sock_shutdown(transport->sock, SHUT_RDWR); return -ENOTCONN; } + if (!transport->inet) + return -ENOTCONN; xs_pktdump("packet data:", req->rq_svec->iov_base, diff --git a/net/tipc/core.c b/net/tipc/core.c index 5cc1f0307215..3f4542e0f065 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -60,7 +60,7 @@ static int __net_init tipc_init_net(struct net *net) tn->trial_addr = 0; tn->addr_trial_end = 0; tn->capabilities = TIPC_NODE_CAPABILITIES; - INIT_WORK(&tn->final_work.work, tipc_net_finalize_work); + INIT_WORK(&tn->work, tipc_net_finalize_work); memset(tn->node_id, 0, sizeof(tn->node_id)); memset(tn->node_id_string, 0, sizeof(tn->node_id_string)); tn->mon_threshold = TIPC_DEF_MON_THRESHOLD; @@ -110,7 +110,7 @@ static void __net_exit tipc_exit_net(struct net *net) tipc_detach_loopback(net); /* Make sure the tipc_net_finalize_work() finished */ - cancel_work_sync(&tn->final_work.work); + cancel_work_sync(&tn->work); tipc_net_stop(net); tipc_bcast_stop(net); @@ -119,6 +119,8 @@ static void __net_exit tipc_exit_net(struct net *net) #ifdef CONFIG_TIPC_CRYPTO tipc_crypto_stop(&tipc_net(net)->crypto_tx); #endif + while (atomic_read(&tn->wq_count)) + cond_resched(); } static void __net_exit tipc_pernet_pre_exit(struct net *net) diff --git a/net/tipc/core.h b/net/tipc/core.h index 03de7b213f55..0a3f7a70a50a 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -91,12 +91,6 @@ extern unsigned int tipc_net_id __read_mostly; extern int sysctl_tipc_rmem[3] __read_mostly; extern int sysctl_tipc_named_timeout __read_mostly; -struct tipc_net_work { - struct work_struct work; - struct net *net; - u32 addr; -}; - struct tipc_net { u8 node_id[NODE_ID_LEN]; u32 node_addr; @@ -148,7 +142,9 @@ struct tipc_net { struct tipc_crypto *crypto_tx; #endif /* Work item for net finalize */ - struct tipc_net_work final_work; + struct work_struct work; + /* The numbers of work queues in schedule */ + atomic_t wq_count; }; static inline struct tipc_net *tipc_net(struct net *net) diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 5380f605b851..da69e1abf68f 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -168,7 +168,7 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, /* Apply trial address if we just left trial period */ if (!trial && !self) { - tipc_sched_net_finalize(net, tn->trial_addr); + schedule_work(&tn->work); msg_set_prevnode(buf_msg(d->skb), tn->trial_addr); msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); } @@ -308,7 +308,7 @@ static void tipc_disc_timeout(struct timer_list *t) if (!time_before(jiffies, tn->addr_trial_end) && !tipc_own_addr(net)) { mod_timer(&d->timer, jiffies + TIPC_DISC_INIT); spin_unlock_bh(&d->lock); - tipc_sched_net_finalize(net, tn->trial_addr); + schedule_work(&tn->work); return; } diff --git a/net/tipc/link.c b/net/tipc/link.c index 115109259430..c44b4bfaaee6 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -372,6 +372,11 @@ char tipc_link_plane(struct tipc_link *l) return l->net_plane; } +struct net *tipc_link_net(struct tipc_link *l) +{ + return l->net; +} + void tipc_link_update_caps(struct tipc_link *l, u16 capabilities) { l->peer_caps = capabilities; diff --git a/net/tipc/link.h b/net/tipc/link.h index fc07232c9a12..a16f401fdabd 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -156,4 +156,5 @@ int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq); bool tipc_link_too_silent(struct tipc_link *l); +struct net *tipc_link_net(struct tipc_link *l); #endif diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 3f0a25345a7c..ce6ab54822d8 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -149,18 +149,13 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (unlikely(head)) goto err; *buf = NULL; + if (skb_has_frag_list(frag) && __skb_linearize(frag)) + goto err; frag = skb_unshare(frag, GFP_ATOMIC); if (unlikely(!frag)) goto err; head = *headbuf = frag; TIPC_SKB_CB(head)->tail = NULL; - if (skb_is_nonlinear(head)) { - skb_walk_frags(head, tail) { - TIPC_SKB_CB(head)->tail = tail; - } - } else { - skb_frag_list_init(head); - } return 0; } diff --git a/net/tipc/net.c b/net/tipc/net.c index a130195af188..0e95572e56b4 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -41,6 +41,7 @@ #include "socket.h" #include "node.h" #include "bcast.h" +#include "link.h" #include "netlink.h" #include "monitor.h" @@ -142,19 +143,9 @@ static void tipc_net_finalize(struct net *net, u32 addr) void tipc_net_finalize_work(struct work_struct *work) { - struct tipc_net_work *fwork; + struct tipc_net *tn = container_of(work, struct tipc_net, work); - fwork = container_of(work, struct tipc_net_work, work); - tipc_net_finalize(fwork->net, fwork->addr); -} - -void tipc_sched_net_finalize(struct net *net, u32 addr) -{ - struct tipc_net *tn = tipc_net(net); - - tn->final_work.net = net; - tn->final_work.addr = addr; - schedule_work(&tn->final_work.work); + tipc_net_finalize(tipc_link_net(tn->bcl), tn->trial_addr); } void tipc_net_stop(struct net *net) diff --git a/net/tipc/node.c b/net/tipc/node.c index 8217905348f4..81af92954c6c 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -423,18 +423,18 @@ static void tipc_node_write_unlock(struct tipc_node *n) write_unlock_bh(&n->lock); if (flags & TIPC_NOTIFY_NODE_DOWN) - tipc_publ_notify(net, publ_list, n->addr, n->capabilities); + tipc_publ_notify(net, publ_list, sk.node, n->capabilities); if (flags & TIPC_NOTIFY_NODE_UP) - tipc_named_node_up(net, n->addr, n->capabilities); + tipc_named_node_up(net, sk.node, n->capabilities); if (flags & TIPC_NOTIFY_LINK_UP) { - tipc_mon_peer_up(net, n->addr, bearer_id); - tipc_nametbl_publish(net, &ua, &sk, n->link_id); + tipc_mon_peer_up(net, sk.node, bearer_id); + tipc_nametbl_publish(net, &ua, &sk, sk.ref); } if (flags & TIPC_NOTIFY_LINK_DOWN) { - tipc_mon_peer_down(net, n->addr, bearer_id); - tipc_nametbl_withdraw(net, &ua, &sk, n->link_id); + tipc_mon_peer_down(net, sk.node, bearer_id); + tipc_nametbl_withdraw(net, &ua, &sk, sk.ref); } } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 58935cd0d068..53af72824c9c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1262,7 +1262,10 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, spin_lock_bh(&inputq->lock); if (skb_peek(arrvq) == skb) { skb_queue_splice_tail_init(&tmpq, inputq); - __skb_dequeue(arrvq); + /* Decrease the skb's refcnt as increasing in the + * function tipc_skb_peek + */ + kfree_skb(__skb_dequeue(arrvq)); } spin_unlock_bh(&inputq->lock); __skb_queue_purge(&tmpq); diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index e556d2cdc064..c2bb818704c8 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -814,6 +814,7 @@ static void cleanup_bearer(struct work_struct *work) kfree_rcu(rcast, rcu); } + atomic_dec(&tipc_net(sock_net(ub->ubsock->sk))->wq_count); dst_cache_destroy(&ub->rcast.dst_cache); udp_tunnel_sock_release(ub->ubsock); synchronize_net(); @@ -834,6 +835,7 @@ static void tipc_udp_disable(struct tipc_bearer *b) RCU_INIT_POINTER(ub->bearer, NULL); /* sock_release need to be done outside of rtnl lock */ + atomic_inc(&tipc_net(sock_net(ub->ubsock->sk))->wq_count); INIT_WORK(&ub->work, cleanup_bearer); schedule_work(&ub->work); } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 1dcb34dfd56b..694de024d0ee 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -37,6 +37,7 @@ #include <linux/sched/signal.h> #include <linux/module.h> +#include <linux/splice.h> #include <crypto/aead.h> #include <net/strparser.h> @@ -1281,7 +1282,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, } static struct sk_buff *tls_wait_data(struct sock *sk, struct sk_psock *psock, - int flags, long timeo, int *err) + bool nonblock, long timeo, int *err) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); @@ -1306,7 +1307,7 @@ static struct sk_buff *tls_wait_data(struct sock *sk, struct sk_psock *psock, if (sock_flag(sk, SOCK_DONE)) return NULL; - if ((flags & MSG_DONTWAIT) || !timeo) { + if (nonblock || !timeo) { *err = -EAGAIN; return NULL; } @@ -1786,7 +1787,7 @@ int tls_sw_recvmsg(struct sock *sk, bool async_capable; bool async = false; - skb = tls_wait_data(sk, psock, flags, timeo, &err); + skb = tls_wait_data(sk, psock, flags & MSG_DONTWAIT, timeo, &err); if (!skb) { if (psock) { int ret = sk_msg_recvmsg(sk, psock, msg, len, @@ -1990,9 +1991,9 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, lock_sock(sk); - timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + timeo = sock_rcvtimeo(sk, flags & SPLICE_F_NONBLOCK); - skb = tls_wait_data(sk, NULL, flags, timeo, &err); + skb = tls_wait_data(sk, NULL, flags & SPLICE_F_NONBLOCK, timeo, &err); if (!skb) goto splice_read_end; diff --git a/net/wireless/util.c b/net/wireless/util.c index 382c5262d997..7ec021a610ae 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -542,7 +542,7 @@ EXPORT_SYMBOL(ieee80211_get_mesh_hdrlen); int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, const u8 *addr, enum nl80211_iftype iftype, - u8 data_offset) + u8 data_offset, bool is_amsdu) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct { @@ -629,7 +629,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, skb_copy_bits(skb, hdrlen, &payload, sizeof(payload)); tmp.h_proto = payload.proto; - if (likely((ether_addr_equal(payload.hdr, rfc1042_header) && + if (likely((!is_amsdu && ether_addr_equal(payload.hdr, rfc1042_header) && tmp.h_proto != htons(ETH_P_AARP) && tmp.h_proto != htons(ETH_P_IPX)) || ether_addr_equal(payload.hdr, bridge_tunnel_header))) @@ -771,6 +771,9 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, remaining = skb->len - offset; if (subframe_len > remaining) goto purge; + /* mitigate A-MSDU aggregation injection attacks */ + if (ether_addr_equal(eth.h_dest, rfc1042_header)) + goto purge; offset += sizeof(struct ethhdr); last = remaining <= subframe_len + padding; diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index aa696854be78..53e300f860bb 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -1255,7 +1255,7 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size) for (i = 0; i < batch_size; i++) { struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i); - tx_desc->addr = (*frame_nb + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT; + tx_desc->addr = (*frame_nb + i) * opt_xsk_frame_size; tx_desc->len = PKT_SIZE; } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 552e2cb73291..61a60c420f6f 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2603,6 +2603,28 @@ static const struct hda_model_fixup alc882_fixup_models[] = { {} }; +static const struct snd_hda_pin_quirk alc882_pin_fixup_tbl[] = { + SND_HDA_PIN_QUIRK(0x10ec1220, 0x1043, "ASUS", ALC1220_FIXUP_CLEVO_P950, + {0x14, 0x01014010}, + {0x15, 0x01011012}, + {0x16, 0x01016011}, + {0x18, 0x01a19040}, + {0x19, 0x02a19050}, + {0x1a, 0x0181304f}, + {0x1b, 0x0221401f}, + {0x1e, 0x01456130}), + SND_HDA_PIN_QUIRK(0x10ec1220, 0x1462, "MS-7C35", ALC1220_FIXUP_CLEVO_P950, + {0x14, 0x01015010}, + {0x15, 0x01011012}, + {0x16, 0x01011011}, + {0x18, 0x01a11040}, + {0x19, 0x02a19050}, + {0x1a, 0x0181104f}, + {0x1b, 0x0221401f}, + {0x1e, 0x01451130}), + {} +}; + /* * BIOS auto configuration */ @@ -2644,6 +2666,7 @@ static int patch_alc882(struct hda_codec *codec) snd_hda_pick_fixup(codec, alc882_fixup_models, alc882_fixup_tbl, alc882_fixups); + snd_hda_pick_pin_fixup(codec, alc882_pin_fixup_tbl, alc882_fixups, true); snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE); alc_auto_parse_customize_define(codec); @@ -6543,6 +6566,8 @@ enum { ALC295_FIXUP_ASUS_DACS, ALC295_FIXUP_HP_OMEN, ALC285_FIXUP_HP_SPECTRE_X360, + ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP, + ALC623_FIXUP_LENOVO_THINKSTATION_P340, }; static const struct hda_fixup alc269_fixups[] = { @@ -8109,6 +8134,18 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC285_FIXUP_SPEAKER2_TO_DAC1, }, + [ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_ideapad_s740_coef, + .chained = true, + .chain_id = ALC285_FIXUP_THINKPAD_HEADSET_JACK, + }, + [ALC623_FIXUP_LENOVO_THINKSTATION_P340] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_no_shutup, + .chained = true, + .chain_id = ALC283_FIXUP_HEADSET_MIC, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -8291,6 +8328,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP), SND_PCI_QUIRK(0x103c, 0x8846, "HP EliteBook 850 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x884c, "HP EliteBook 840 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x886d, "HP ZBook Fury 17.3 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), + SND_PCI_QUIRK(0x103c, 0x8870, "HP ZBook Fury 15.6 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), + SND_PCI_QUIRK(0x103c, 0x8873, "HP ZBook Studio 15.6 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), + SND_PCI_QUIRK(0x103c, 0x8896, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), @@ -8427,7 +8468,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0xc019, "Clevo NH77D[BE]Q", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0xc022, "Clevo NH77[DC][QW]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS), - SND_PCI_QUIRK(0x17aa, 0x1048, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x17aa, 0x1048, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE), @@ -8477,6 +8518,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940", ALC298_FIXUP_LENOVO_SPK_VOLUME), SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF), + SND_PCI_QUIRK(0x17aa, 0x3843, "Yoga 9i", ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI), @@ -8692,6 +8734,8 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC245_FIXUP_HP_X360_AMP, .name = "alc245-hp-x360-amp"}, {.id = ALC295_FIXUP_HP_OMEN, .name = "alc295-hp-omen"}, {.id = ALC285_FIXUP_HP_SPECTRE_X360, .name = "alc285-hp-spectre-x360"}, + {.id = ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP, .name = "alc287-ideapad-bass-spk-amp"}, + {.id = ALC623_FIXUP_LENOVO_THINKSTATION_P340, .name = "alc623-lenovo-thinkstation-p340"}, {} }; #define ALC225_STANDARD_PINS \ diff --git a/sound/soc/amd/raven/acp3x-pcm-dma.c b/sound/soc/amd/raven/acp3x-pcm-dma.c index f22bb2bdf527..8148b0d22e88 100644 --- a/sound/soc/amd/raven/acp3x-pcm-dma.c +++ b/sound/soc/amd/raven/acp3x-pcm-dma.c @@ -235,10 +235,6 @@ static int acp3x_dma_open(struct snd_soc_component *component, return ret; } - if (!adata->play_stream && !adata->capture_stream && - !adata->i2ssp_play_stream && !adata->i2ssp_capture_stream) - rv_writel(1, adata->acp3x_base + mmACP_EXTERNAL_INTR_ENB); - i2s_data->acp3x_base = adata->acp3x_base; runtime->private_data = i2s_data; return ret; @@ -365,12 +361,6 @@ static int acp3x_dma_close(struct snd_soc_component *component, } } - /* Disable ACP irq, when the current stream is being closed and - * another stream is also not active. - */ - if (!adata->play_stream && !adata->capture_stream && - !adata->i2ssp_play_stream && !adata->i2ssp_capture_stream) - rv_writel(0, adata->acp3x_base + mmACP_EXTERNAL_INTR_ENB); return 0; } diff --git a/sound/soc/amd/raven/acp3x.h b/sound/soc/amd/raven/acp3x.h index 03fe93913e12..c3f0c8b7545d 100644 --- a/sound/soc/amd/raven/acp3x.h +++ b/sound/soc/amd/raven/acp3x.h @@ -77,6 +77,7 @@ #define ACP_POWER_OFF_IN_PROGRESS 0x03 #define ACP3x_ITER_IRER_SAMP_LEN_MASK 0x38 +#define ACP_EXT_INTR_STAT_CLEAR_MASK 0xFFFFFFFF struct acp3x_platform_info { u16 play_i2s_instance; diff --git a/sound/soc/amd/raven/pci-acp3x.c b/sound/soc/amd/raven/pci-acp3x.c index d3536fd6a124..a013a607b3d4 100644 --- a/sound/soc/amd/raven/pci-acp3x.c +++ b/sound/soc/amd/raven/pci-acp3x.c @@ -76,6 +76,19 @@ static int acp3x_reset(void __iomem *acp3x_base) return -ETIMEDOUT; } +static void acp3x_enable_interrupts(void __iomem *acp_base) +{ + rv_writel(0x01, acp_base + mmACP_EXTERNAL_INTR_ENB); +} + +static void acp3x_disable_interrupts(void __iomem *acp_base) +{ + rv_writel(ACP_EXT_INTR_STAT_CLEAR_MASK, acp_base + + mmACP_EXTERNAL_INTR_STAT); + rv_writel(0x00, acp_base + mmACP_EXTERNAL_INTR_CNTL); + rv_writel(0x00, acp_base + mmACP_EXTERNAL_INTR_ENB); +} + static int acp3x_init(struct acp3x_dev_data *adata) { void __iomem *acp3x_base = adata->acp3x_base; @@ -93,6 +106,7 @@ static int acp3x_init(struct acp3x_dev_data *adata) pr_err("ACP3x reset failed\n"); return ret; } + acp3x_enable_interrupts(acp3x_base); return 0; } @@ -100,6 +114,7 @@ static int acp3x_deinit(void __iomem *acp3x_base) { int ret; + acp3x_disable_interrupts(acp3x_base); /* Reset */ ret = acp3x_reset(acp3x_base); if (ret) { diff --git a/sound/soc/codecs/ak5558.c b/sound/soc/codecs/ak5558.c index 34aed80db0eb..37d4600b6f2c 100644 --- a/sound/soc/codecs/ak5558.c +++ b/sound/soc/codecs/ak5558.c @@ -307,7 +307,7 @@ static struct snd_soc_dai_driver ak5558_dai = { }; static struct snd_soc_dai_driver ak5552_dai = { - .name = "ak5558-aif", + .name = "ak5552-aif", .capture = { .stream_name = "Capture", .channels_min = 1, diff --git a/sound/soc/codecs/cs35l32.c b/sound/soc/codecs/cs35l32.c index f4067230ac42..88e79b9f52ed 100644 --- a/sound/soc/codecs/cs35l32.c +++ b/sound/soc/codecs/cs35l32.c @@ -261,6 +261,9 @@ static const struct regmap_config cs35l32_regmap = { .readable_reg = cs35l32_readable_register, .precious_reg = cs35l32_precious_register, .cache_type = REGCACHE_RBTREE, + + .use_single_read = true, + .use_single_write = true, }; static int cs35l32_handle_of_data(struct i2c_client *i2c_client, diff --git a/sound/soc/codecs/cs35l33.c b/sound/soc/codecs/cs35l33.c index 7ad7b733af9b..e8f3dcfd144d 100644 --- a/sound/soc/codecs/cs35l33.c +++ b/sound/soc/codecs/cs35l33.c @@ -1201,6 +1201,7 @@ static int cs35l33_i2c_probe(struct i2c_client *i2c_client, dev_err(&i2c_client->dev, "CS35L33 Device ID (%X). Expected ID %X\n", devid, CS35L33_CHIP_ID); + ret = -EINVAL; goto err_enable; } diff --git a/sound/soc/codecs/cs35l34.c b/sound/soc/codecs/cs35l34.c index 110ee2d06358..3d3c3c34dfe2 100644 --- a/sound/soc/codecs/cs35l34.c +++ b/sound/soc/codecs/cs35l34.c @@ -800,6 +800,9 @@ static struct regmap_config cs35l34_regmap = { .readable_reg = cs35l34_readable_register, .precious_reg = cs35l34_precious_register, .cache_type = REGCACHE_RBTREE, + + .use_single_read = true, + .use_single_write = true, }; static int cs35l34_handle_of_data(struct i2c_client *i2c_client, diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index bf982e145e94..77473c226f9e 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -399,6 +399,9 @@ static const struct regmap_config cs42l42_regmap = { .reg_defaults = cs42l42_reg_defaults, .num_reg_defaults = ARRAY_SIZE(cs42l42_reg_defaults), .cache_type = REGCACHE_RBTREE, + + .use_single_read = true, + .use_single_write = true, }; static DECLARE_TLV_DB_SCALE(adc_tlv, -9600, 100, false); diff --git a/sound/soc/codecs/cs42l56.c b/sound/soc/codecs/cs42l56.c index c44a5cdb796e..7cdffdf6b8cf 100644 --- a/sound/soc/codecs/cs42l56.c +++ b/sound/soc/codecs/cs42l56.c @@ -1175,7 +1175,7 @@ static int cs42l56_i2c_probe(struct i2c_client *i2c_client, struct cs42l56_platform_data *pdata = dev_get_platdata(&i2c_client->dev); int ret, i; - unsigned int devid = 0; + unsigned int devid; unsigned int alpha_rev, metal_rev; unsigned int reg; @@ -1245,6 +1245,11 @@ static int cs42l56_i2c_probe(struct i2c_client *i2c_client, } ret = regmap_read(cs42l56->regmap, CS42L56_CHIP_ID_1, ®); + if (ret) { + dev_err(&i2c_client->dev, "Failed to read chip ID: %d\n", ret); + return ret; + } + devid = reg & CS42L56_CHIP_ID_MASK; if (devid != CS42L56_DEVID) { dev_err(&i2c_client->dev, diff --git a/sound/soc/codecs/cs42l73.c b/sound/soc/codecs/cs42l73.c index c3f974ec78e5..e92bacaab53f 100644 --- a/sound/soc/codecs/cs42l73.c +++ b/sound/soc/codecs/cs42l73.c @@ -1268,6 +1268,9 @@ static const struct regmap_config cs42l73_regmap = { .volatile_reg = cs42l73_volatile_register, .readable_reg = cs42l73_readable_register, .cache_type = REGCACHE_RBTREE, + + .use_single_read = true, + .use_single_write = true, }; static int cs42l73_i2c_probe(struct i2c_client *i2c_client, diff --git a/sound/soc/codecs/cs53l30.c b/sound/soc/codecs/cs53l30.c index 3d67cbf9eaaa..abe0cc0bc03a 100644 --- a/sound/soc/codecs/cs53l30.c +++ b/sound/soc/codecs/cs53l30.c @@ -912,6 +912,9 @@ static struct regmap_config cs53l30_regmap = { .writeable_reg = cs53l30_writeable_register, .readable_reg = cs53l30_readable_register, .cache_type = REGCACHE_RBTREE, + + .use_single_read = true, + .use_single_write = true, }; static int cs53l30_i2c_probe(struct i2c_client *client, diff --git a/sound/soc/codecs/da7219.c b/sound/soc/codecs/da7219.c index bd3c523a8617..13009d08b09a 100644 --- a/sound/soc/codecs/da7219.c +++ b/sound/soc/codecs/da7219.c @@ -2181,10 +2181,7 @@ static int da7219_register_dai_clks(struct snd_soc_component *component) ret); goto err; } - - da7219->dai_clks[i] = devm_clk_hw_get_clk(dev, dai_clk_hw, NULL); - if (IS_ERR(da7219->dai_clks[i])) - return PTR_ERR(da7219->dai_clks[i]); + da7219->dai_clks[i] = dai_clk_hw->clk; /* For DT setup onecell data, otherwise create lookup */ if (np) { diff --git a/sound/soc/codecs/lpass-rx-macro.c b/sound/soc/codecs/lpass-rx-macro.c index b0ebfc8d180c..171ab7f519c0 100644 --- a/sound/soc/codecs/lpass-rx-macro.c +++ b/sound/soc/codecs/lpass-rx-macro.c @@ -3579,6 +3579,7 @@ static const struct of_device_id rx_macro_dt_match[] = { { .compatible = "qcom,sm8250-lpass-rx-macro" }, { } }; +MODULE_DEVICE_TABLE(of, rx_macro_dt_match); static struct platform_driver rx_macro_driver = { .driver = { diff --git a/sound/soc/codecs/lpass-tx-macro.c b/sound/soc/codecs/lpass-tx-macro.c index acd2fbc0ca7c..27a0d5defd27 100644 --- a/sound/soc/codecs/lpass-tx-macro.c +++ b/sound/soc/codecs/lpass-tx-macro.c @@ -1846,6 +1846,7 @@ static const struct of_device_id tx_macro_dt_match[] = { { .compatible = "qcom,sm8250-lpass-tx-macro" }, { } }; +MODULE_DEVICE_TABLE(of, tx_macro_dt_match); static struct platform_driver tx_macro_driver = { .driver = { .name = "tx_macro", diff --git a/sound/soc/codecs/max98088.c b/sound/soc/codecs/max98088.c index 4be24e7f51c8..f8e49e45ce33 100644 --- a/sound/soc/codecs/max98088.c +++ b/sound/soc/codecs/max98088.c @@ -41,6 +41,7 @@ struct max98088_priv { enum max98088_type devtype; struct max98088_pdata *pdata; struct clk *mclk; + unsigned char mclk_prescaler; unsigned int sysclk; struct max98088_cdata dai[2]; int eq_textcnt; @@ -998,13 +999,16 @@ static int max98088_dai1_hw_params(struct snd_pcm_substream *substream, /* Configure NI when operating as master */ if (snd_soc_component_read(component, M98088_REG_14_DAI1_FORMAT) & M98088_DAI_MAS) { + unsigned long pclk; + if (max98088->sysclk == 0) { dev_err(component->dev, "Invalid system clock frequency\n"); return -EINVAL; } ni = 65536ULL * (rate < 50000 ? 96ULL : 48ULL) * (unsigned long long int)rate; - do_div(ni, (unsigned long long int)max98088->sysclk); + pclk = DIV_ROUND_CLOSEST(max98088->sysclk, max98088->mclk_prescaler); + ni = DIV_ROUND_CLOSEST_ULL(ni, pclk); snd_soc_component_write(component, M98088_REG_12_DAI1_CLKCFG_HI, (ni >> 8) & 0x7F); snd_soc_component_write(component, M98088_REG_13_DAI1_CLKCFG_LO, @@ -1065,13 +1069,16 @@ static int max98088_dai2_hw_params(struct snd_pcm_substream *substream, /* Configure NI when operating as master */ if (snd_soc_component_read(component, M98088_REG_1C_DAI2_FORMAT) & M98088_DAI_MAS) { + unsigned long pclk; + if (max98088->sysclk == 0) { dev_err(component->dev, "Invalid system clock frequency\n"); return -EINVAL; } ni = 65536ULL * (rate < 50000 ? 96ULL : 48ULL) * (unsigned long long int)rate; - do_div(ni, (unsigned long long int)max98088->sysclk); + pclk = DIV_ROUND_CLOSEST(max98088->sysclk, max98088->mclk_prescaler); + ni = DIV_ROUND_CLOSEST_ULL(ni, pclk); snd_soc_component_write(component, M98088_REG_1A_DAI2_CLKCFG_HI, (ni >> 8) & 0x7F); snd_soc_component_write(component, M98088_REG_1B_DAI2_CLKCFG_LO, @@ -1113,8 +1120,10 @@ static int max98088_dai_set_sysclk(struct snd_soc_dai *dai, */ if ((freq >= 10000000) && (freq < 20000000)) { snd_soc_component_write(component, M98088_REG_10_SYS_CLK, 0x10); + max98088->mclk_prescaler = 1; } else if ((freq >= 20000000) && (freq < 30000000)) { snd_soc_component_write(component, M98088_REG_10_SYS_CLK, 0x20); + max98088->mclk_prescaler = 2; } else { dev_err(component->dev, "Invalid master clock frequency\n"); return -EINVAL; diff --git a/sound/soc/codecs/rt711-sdca.c b/sound/soc/codecs/rt711-sdca.c index cc36739f7fcf..24a084e0b48a 100644 --- a/sound/soc/codecs/rt711-sdca.c +++ b/sound/soc/codecs/rt711-sdca.c @@ -683,13 +683,13 @@ static int rt711_sdca_set_fu1e_capture_ctl(struct rt711_sdca_priv *rt711) ch_r = (rt711->fu1e_dapm_mute || rt711->fu1e_mixer_r_mute) ? 0x01 : 0x00; err = regmap_write(rt711->regmap, - SDW_SDCA_CTL(FUNC_NUM_JACK_CODEC, RT711_SDCA_ENT_USER_FU1E, + SDW_SDCA_CTL(FUNC_NUM_MIC_ARRAY, RT711_SDCA_ENT_USER_FU1E, RT711_SDCA_CTL_FU_MUTE, CH_L), ch_l); if (err < 0) return err; err = regmap_write(rt711->regmap, - SDW_SDCA_CTL(FUNC_NUM_JACK_CODEC, RT711_SDCA_ENT_USER_FU1E, + SDW_SDCA_CTL(FUNC_NUM_MIC_ARRAY, RT711_SDCA_ENT_USER_FU1E, RT711_SDCA_CTL_FU_MUTE, CH_R), ch_r); if (err < 0) return err; diff --git a/sound/soc/codecs/sti-sas.c b/sound/soc/codecs/sti-sas.c index ffdf7e559515..82a24e330065 100644 --- a/sound/soc/codecs/sti-sas.c +++ b/sound/soc/codecs/sti-sas.c @@ -408,6 +408,7 @@ static const struct of_device_id sti_sas_dev_match[] = { }, {}, }; +MODULE_DEVICE_TABLE(of, sti_sas_dev_match); static int sti_sas_driver_probe(struct platform_device *pdev) { diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig index 0917d65d6921..556c284f49dd 100644 --- a/sound/soc/fsl/Kconfig +++ b/sound/soc/fsl/Kconfig @@ -119,6 +119,7 @@ config SND_SOC_FSL_RPMSG tristate "NXP Audio Base On RPMSG support" depends on COMMON_CLK depends on RPMSG + depends on SND_IMX_SOC || SND_IMX_SOC = n select SND_SOC_IMX_RPMSG if SND_IMX_SOC != n help Say Y if you want to add rpmsg audio support for the Freescale CPUs. diff --git a/sound/soc/generic/audio-graph-card.c b/sound/soc/generic/audio-graph-card.c index 2c8a2fcb7922..5e71382467e8 100644 --- a/sound/soc/generic/audio-graph-card.c +++ b/sound/soc/generic/audio-graph-card.c @@ -209,7 +209,7 @@ static void graph_parse_mclk_fs(struct device_node *top, static int graph_parse_node(struct asoc_simple_priv *priv, struct device_node *ep, struct link_info *li, - int is_cpu) + int *cpu) { struct device *dev = simple_priv_to_dev(priv); struct device_node *top = dev->of_node; @@ -217,9 +217,9 @@ static int graph_parse_node(struct asoc_simple_priv *priv, struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); struct snd_soc_dai_link_component *dlc; struct asoc_simple_dai *dai; - int ret, single = 0; + int ret; - if (is_cpu) { + if (cpu) { dlc = asoc_link_to_cpu(dai_link, 0); dai = simple_props_to_dai_cpu(dai_props, 0); } else { @@ -229,7 +229,7 @@ static int graph_parse_node(struct asoc_simple_priv *priv, graph_parse_mclk_fs(top, ep, dai_props); - ret = asoc_simple_parse_dai(ep, dlc, &single); + ret = asoc_simple_parse_dai(ep, dlc, cpu); if (ret < 0) return ret; @@ -241,9 +241,6 @@ static int graph_parse_node(struct asoc_simple_priv *priv, if (ret < 0) return ret; - if (is_cpu) - asoc_simple_canonicalize_cpu(dlc, single); - return 0; } @@ -276,33 +273,29 @@ static int graph_dai_link_of_dpcm(struct asoc_simple_priv *priv, struct link_info *li) { struct device *dev = simple_priv_to_dev(priv); - struct snd_soc_card *card = simple_priv_to_card(priv); struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); struct device_node *top = dev->of_node; struct device_node *ep = li->cpu ? cpu_ep : codec_ep; - struct device_node *port; - struct device_node *ports; - struct snd_soc_dai_link_component *cpus = asoc_link_to_cpu(dai_link, 0); - struct snd_soc_dai_link_component *codecs = asoc_link_to_codec(dai_link, 0); char dai_name[64]; int ret; - port = of_get_parent(ep); - ports = of_get_parent(port); - dev_dbg(dev, "link_of DPCM (%pOF)\n", ep); if (li->cpu) { + struct snd_soc_card *card = simple_priv_to_card(priv); + struct snd_soc_dai_link_component *cpus = asoc_link_to_cpu(dai_link, 0); + int is_single_links = 0; + /* Codec is dummy */ /* FE settings */ dai_link->dynamic = 1; dai_link->dpcm_merged_format = 1; - ret = graph_parse_node(priv, cpu_ep, li, 1); + ret = graph_parse_node(priv, cpu_ep, li, &is_single_links); if (ret) - goto out_put_node; + return ret; snprintf(dai_name, sizeof(dai_name), "fe.%pOFP.%s", cpus->of_node, cpus->dai_name); @@ -318,8 +311,13 @@ static int graph_dai_link_of_dpcm(struct asoc_simple_priv *priv, */ if (card->component_chaining && !soc_component_is_pcm(cpus)) dai_link->no_pcm = 1; + + asoc_simple_canonicalize_cpu(cpus, is_single_links); } else { - struct snd_soc_codec_conf *cconf; + struct snd_soc_codec_conf *cconf = simple_props_to_codec_conf(dai_props, 0); + struct snd_soc_dai_link_component *codecs = asoc_link_to_codec(dai_link, 0); + struct device_node *port; + struct device_node *ports; /* CPU is dummy */ @@ -327,22 +325,25 @@ static int graph_dai_link_of_dpcm(struct asoc_simple_priv *priv, dai_link->no_pcm = 1; dai_link->be_hw_params_fixup = asoc_simple_be_hw_params_fixup; - cconf = simple_props_to_codec_conf(dai_props, 0); - - ret = graph_parse_node(priv, codec_ep, li, 0); + ret = graph_parse_node(priv, codec_ep, li, NULL); if (ret < 0) - goto out_put_node; + return ret; snprintf(dai_name, sizeof(dai_name), "be.%pOFP.%s", codecs->of_node, codecs->dai_name); /* check "prefix" from top node */ + port = of_get_parent(ep); + ports = of_get_parent(port); snd_soc_of_parse_node_prefix(top, cconf, codecs->of_node, "prefix"); if (of_node_name_eq(ports, "ports")) snd_soc_of_parse_node_prefix(ports, cconf, codecs->of_node, "prefix"); snd_soc_of_parse_node_prefix(port, cconf, codecs->of_node, "prefix"); + + of_node_put(ports); + of_node_put(port); } graph_parse_convert(dev, ep, &dai_props->adata); @@ -351,11 +352,8 @@ static int graph_dai_link_of_dpcm(struct asoc_simple_priv *priv, ret = graph_link_init(priv, cpu_ep, codec_ep, li, dai_name); -out_put_node: li->link++; - of_node_put(ports); - of_node_put(port); return ret; } @@ -369,20 +367,23 @@ static int graph_dai_link_of(struct asoc_simple_priv *priv, struct snd_soc_dai_link_component *cpus = asoc_link_to_cpu(dai_link, 0); struct snd_soc_dai_link_component *codecs = asoc_link_to_codec(dai_link, 0); char dai_name[64]; - int ret; + int ret, is_single_links = 0; dev_dbg(dev, "link_of (%pOF)\n", cpu_ep); - ret = graph_parse_node(priv, cpu_ep, li, 1); + ret = graph_parse_node(priv, cpu_ep, li, &is_single_links); if (ret < 0) return ret; - ret = graph_parse_node(priv, codec_ep, li, 0); + ret = graph_parse_node(priv, codec_ep, li, NULL); if (ret < 0) return ret; snprintf(dai_name, sizeof(dai_name), "%s-%s", cpus->dai_name, codecs->dai_name); + + asoc_simple_canonicalize_cpu(cpus, is_single_links); + ret = graph_link_init(priv, cpu_ep, codec_ep, li, dai_name); if (ret < 0) return ret; diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index a1373be4558f..0015f534d42d 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -93,12 +93,11 @@ static void simple_parse_convert(struct device *dev, } static void simple_parse_mclk_fs(struct device_node *top, - struct device_node *cpu, - struct device_node *codec, + struct device_node *np, struct simple_dai_props *props, char *prefix) { - struct device_node *node = of_get_parent(cpu); + struct device_node *node = of_get_parent(np); char prop[128]; snprintf(prop, sizeof(prop), "%smclk-fs", PREFIX); @@ -106,12 +105,71 @@ static void simple_parse_mclk_fs(struct device_node *top, snprintf(prop, sizeof(prop), "%smclk-fs", prefix); of_property_read_u32(node, prop, &props->mclk_fs); - of_property_read_u32(cpu, prop, &props->mclk_fs); - of_property_read_u32(codec, prop, &props->mclk_fs); + of_property_read_u32(np, prop, &props->mclk_fs); of_node_put(node); } +static int simple_parse_node(struct asoc_simple_priv *priv, + struct device_node *np, + struct link_info *li, + char *prefix, + int *cpu) +{ + struct device *dev = simple_priv_to_dev(priv); + struct device_node *top = dev->of_node; + struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); + struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); + struct snd_soc_dai_link_component *dlc; + struct asoc_simple_dai *dai; + int ret; + + if (cpu) { + dlc = asoc_link_to_cpu(dai_link, 0); + dai = simple_props_to_dai_cpu(dai_props, 0); + } else { + dlc = asoc_link_to_codec(dai_link, 0); + dai = simple_props_to_dai_codec(dai_props, 0); + } + + simple_parse_mclk_fs(top, np, dai_props, prefix); + + ret = asoc_simple_parse_dai(np, dlc, cpu); + if (ret) + return ret; + + ret = asoc_simple_parse_clk(dev, np, dai, dlc); + if (ret) + return ret; + + ret = asoc_simple_parse_tdm(np, dai); + if (ret) + return ret; + + return 0; +} + +static int simple_link_init(struct asoc_simple_priv *priv, + struct device_node *node, + struct device_node *codec, + struct link_info *li, + char *prefix, char *name) +{ + struct device *dev = simple_priv_to_dev(priv); + struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); + int ret; + + ret = asoc_simple_parse_daifmt(dev, node, codec, + prefix, &dai_link->dai_fmt); + if (ret < 0) + return 0; + + dai_link->init = asoc_simple_dai_init; + dai_link->ops = &simple_ops; + + return asoc_simple_set_dailink_name(dev, dai_link, name); +} + static int simple_dai_link_of_dpcm(struct asoc_simple_priv *priv, struct device_node *np, struct device_node *codec, @@ -121,24 +179,21 @@ static int simple_dai_link_of_dpcm(struct asoc_simple_priv *priv, struct device *dev = simple_priv_to_dev(priv); struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); - struct asoc_simple_dai *dai; - struct snd_soc_dai_link_component *cpus = asoc_link_to_cpu(dai_link, 0); - struct snd_soc_dai_link_component *codecs = asoc_link_to_codec(dai_link, 0); - struct snd_soc_dai_link_component *platforms = asoc_link_to_platform(dai_link, 0); struct device_node *top = dev->of_node; struct device_node *node = of_get_parent(np); char *prefix = ""; + char dai_name[64]; int ret; dev_dbg(dev, "link_of DPCM (%pOF)\n", np); - li->link++; - /* For single DAI link & old style of DT node */ if (is_top) prefix = PREFIX; if (li->cpu) { + struct snd_soc_dai_link_component *cpus = asoc_link_to_cpu(dai_link, 0); + struct snd_soc_dai_link_component *platforms = asoc_link_to_platform(dai_link, 0); int is_single_links = 0; /* Codec is dummy */ @@ -147,25 +202,16 @@ static int simple_dai_link_of_dpcm(struct asoc_simple_priv *priv, dai_link->dynamic = 1; dai_link->dpcm_merged_format = 1; - dai = simple_props_to_dai_cpu(dai_props, 0); - - ret = asoc_simple_parse_dai(np, cpus, &is_single_links); - if (ret) - goto out_put_node; - - ret = asoc_simple_parse_clk(dev, np, dai, cpus); + ret = simple_parse_node(priv, np, li, prefix, &is_single_links); if (ret < 0) goto out_put_node; - ret = asoc_simple_set_dailink_name(dev, dai_link, - "fe.%s", - cpus->dai_name); - if (ret < 0) - goto out_put_node; + snprintf(dai_name, sizeof(dai_name), "fe.%s", cpus->dai_name); asoc_simple_canonicalize_cpu(cpus, is_single_links); asoc_simple_canonicalize_platform(platforms, cpus); } else { + struct snd_soc_dai_link_component *codecs = asoc_link_to_codec(dai_link, 0); struct snd_soc_codec_conf *cconf; /* CPU is dummy */ @@ -174,22 +220,13 @@ static int simple_dai_link_of_dpcm(struct asoc_simple_priv *priv, dai_link->no_pcm = 1; dai_link->be_hw_params_fixup = asoc_simple_be_hw_params_fixup; - dai = simple_props_to_dai_codec(dai_props, 0); cconf = simple_props_to_codec_conf(dai_props, 0); - ret = asoc_simple_parse_dai(np, codecs, NULL); + ret = simple_parse_node(priv, np, li, prefix, NULL); if (ret < 0) goto out_put_node; - ret = asoc_simple_parse_clk(dev, np, dai, codecs); - if (ret < 0) - goto out_put_node; - - ret = asoc_simple_set_dailink_name(dev, dai_link, - "be.%s", - codecs->dai_name); - if (ret < 0) - goto out_put_node; + snprintf(dai_name, sizeof(dai_name), "be.%s", codecs->dai_name); /* check "prefix" from top node */ snd_soc_of_parse_node_prefix(top, cconf, codecs->of_node, @@ -201,23 +238,14 @@ static int simple_dai_link_of_dpcm(struct asoc_simple_priv *priv, } simple_parse_convert(dev, np, &dai_props->adata); - simple_parse_mclk_fs(top, np, codec, dai_props, prefix); - - ret = asoc_simple_parse_tdm(np, dai); - if (ret) - goto out_put_node; - - ret = asoc_simple_parse_daifmt(dev, node, codec, - prefix, &dai_link->dai_fmt); - if (ret < 0) - goto out_put_node; snd_soc_dai_link_set_capabilities(dai_link); - dai_link->ops = &simple_ops; - dai_link->init = asoc_simple_dai_init; + ret = simple_link_init(priv, node, codec, li, prefix, dai_name); out_put_node: + li->link++; + of_node_put(node); return ret; } @@ -230,23 +258,19 @@ static int simple_dai_link_of(struct asoc_simple_priv *priv, { struct device *dev = simple_priv_to_dev(priv); struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); - struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); - struct asoc_simple_dai *cpu_dai = simple_props_to_dai_cpu(dai_props, 0); - struct asoc_simple_dai *codec_dai = simple_props_to_dai_codec(dai_props, 0); struct snd_soc_dai_link_component *cpus = asoc_link_to_cpu(dai_link, 0); struct snd_soc_dai_link_component *codecs = asoc_link_to_codec(dai_link, 0); struct snd_soc_dai_link_component *platforms = asoc_link_to_platform(dai_link, 0); - struct device_node *top = dev->of_node; struct device_node *cpu = NULL; struct device_node *node = NULL; struct device_node *plat = NULL; + char dai_name[64]; char prop[128]; char *prefix = ""; int ret, single_cpu = 0; cpu = np; node = of_get_parent(np); - li->link++; dev_dbg(dev, "link_of (%pOF)\n", node); @@ -257,18 +281,11 @@ static int simple_dai_link_of(struct asoc_simple_priv *priv, snprintf(prop, sizeof(prop), "%splat", prefix); plat = of_get_child_by_name(node, prop); - ret = asoc_simple_parse_daifmt(dev, node, codec, - prefix, &dai_link->dai_fmt); - if (ret < 0) - goto dai_link_of_err; - - simple_parse_mclk_fs(top, cpu, codec, dai_props, prefix); - - ret = asoc_simple_parse_dai(cpu, cpus, &single_cpu); + ret = simple_parse_node(priv, cpu, li, prefix, &single_cpu); if (ret < 0) goto dai_link_of_err; - ret = asoc_simple_parse_dai(codec, codecs, NULL); + ret = simple_parse_node(priv, codec, li, prefix, NULL); if (ret < 0) goto dai_link_of_err; @@ -276,39 +293,20 @@ static int simple_dai_link_of(struct asoc_simple_priv *priv, if (ret < 0) goto dai_link_of_err; - ret = asoc_simple_parse_tdm(cpu, cpu_dai); - if (ret < 0) - goto dai_link_of_err; - - ret = asoc_simple_parse_tdm(codec, codec_dai); - if (ret < 0) - goto dai_link_of_err; - - ret = asoc_simple_parse_clk(dev, cpu, cpu_dai, cpus); - if (ret < 0) - goto dai_link_of_err; - - ret = asoc_simple_parse_clk(dev, codec, codec_dai, codecs); - if (ret < 0) - goto dai_link_of_err; - - ret = asoc_simple_set_dailink_name(dev, dai_link, - "%s-%s", - cpus->dai_name, - codecs->dai_name); - if (ret < 0) - goto dai_link_of_err; - - dai_link->ops = &simple_ops; - dai_link->init = asoc_simple_dai_init; + snprintf(dai_name, sizeof(dai_name), + "%s-%s", cpus->dai_name, codecs->dai_name); asoc_simple_canonicalize_cpu(cpus, single_cpu); asoc_simple_canonicalize_platform(platforms, cpus); + ret = simple_link_init(priv, node, codec, li, prefix, dai_name); + dai_link_of_err: of_node_put(plat); of_node_put(node); + li->link++; + return ret; } diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index df2f5d55e8ff..22dbd9d93c1e 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -574,6 +574,17 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF1 | BYT_RT5640_MCLK_EN), }, + { /* Glavey TM800A550L */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "Aptio CRB"), + /* Above strings are too generic, also match on BIOS version */ + DMI_MATCH(DMI_BIOS_VERSION, "ZY-8-BI-PX4S70VTR400-X423B-005-D"), + }, + .driver_data = (void *)(BYTCR_INPUT_DEFAULTS | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), @@ -652,6 +663,20 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_MONO_SPEAKER | BYT_RT5640_MCLK_EN), }, + { /* Lenovo Miix 3-830 */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo MIIX 3-830"), + }, + .driver_data = (void *)(BYT_RT5640_IN1_MAP | + BYT_RT5640_JD_SRC_JD2_IN4N | + BYT_RT5640_OVCD_TH_2000UA | + BYT_RT5640_OVCD_SF_0P75 | + BYT_RT5640_MONO_SPEAKER | + BYT_RT5640_DIFF_MIC | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { /* Linx Linx7 tablet */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LINX"), diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index c62d2612e8f5..28c7497344e3 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -835,18 +835,8 @@ int asoc_qcom_lpass_cpu_platform_probe(struct platform_device *pdev) if (dai_id == LPASS_DP_RX) continue; - drvdata->mi2s_osr_clk[dai_id] = devm_clk_get(dev, + drvdata->mi2s_osr_clk[dai_id] = devm_clk_get_optional(dev, variant->dai_osr_clk_names[i]); - if (IS_ERR(drvdata->mi2s_osr_clk[dai_id])) { - dev_warn(dev, - "%s() error getting optional %s: %ld\n", - __func__, - variant->dai_osr_clk_names[i], - PTR_ERR(drvdata->mi2s_osr_clk[dai_id])); - - drvdata->mi2s_osr_clk[dai_id] = NULL; - } - drvdata->mi2s_bit_clk[dai_id] = devm_clk_get(dev, variant->dai_bit_clk_names[i]); if (IS_ERR(drvdata->mi2s_bit_clk[dai_id])) { diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c index 8d7bab433fb3..c1f9f0f58464 100644 --- a/sound/soc/sof/intel/hda-dai.c +++ b/sound/soc/sof/intel/hda-dai.c @@ -421,11 +421,16 @@ static int ssp_dai_hw_params(struct snd_pcm_substream *substream, struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream); struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, SOF_AUDIO_PCM_DRV_NAME); struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component); + struct sof_ipc_fw_version *v = &sdev->fw_ready.version; struct sof_ipc_dai_config *config; struct snd_sof_dai *sof_dai; struct sof_ipc_reply reply; int ret; + /* DAI_CONFIG IPC during hw_params is not supported in older firmware */ + if (v->abi_version < SOF_ABI_VER(3, 18, 0)) + return 0; + list_for_each_entry(sof_dai, &sdev->dai_list, list) { if (!sof_dai->cpu_dai_name || !sof_dai->dai_config) continue; diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c index c1561237ee24..3aa1cf262402 100644 --- a/sound/soc/stm/stm32_sai_sub.c +++ b/sound/soc/stm/stm32_sai_sub.c @@ -484,10 +484,7 @@ static int stm32_sai_add_mclk_provider(struct stm32_sai_sub_data *sai) dev_err(dev, "mclk register returned %d\n", ret); return ret; } - - sai->sai_mclk = devm_clk_hw_get_clk(dev, hw, NULL); - if (IS_ERR(sai->sai_mclk)) - return PTR_ERR(sai->sai_mclk); + sai->sai_mclk = hw->clk; /* register mclk provider */ return devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, hw); diff --git a/sound/usb/format.c b/sound/usb/format.c index e6ff317a6785..2287f8c65315 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -436,7 +436,7 @@ static bool check_valid_altsetting_v2v3(struct snd_usb_audio *chip, int iface, if (snd_BUG_ON(altsetting >= 64 - 8)) return false; - err = snd_usb_ctl_msg(dev, usb_sndctrlpipe(dev, 0), UAC2_CS_CUR, + err = snd_usb_ctl_msg(dev, usb_rcvctrlpipe(dev, 0), UAC2_CS_CUR, USB_TYPE_CLASS | USB_RECIP_INTERFACE | USB_DIR_IN, UAC2_AS_VAL_ALT_SETTINGS << 8, iface, &raw_data, sizeof(raw_data)); diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index fda66b2dbb01..37ad77524c0b 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -3060,7 +3060,7 @@ int snd_usb_mixer_apply_create_quirk(struct usb_mixer_interface *mixer) case USB_ID(0x1235, 0x8203): /* Focusrite Scarlett 6i6 2nd Gen */ case USB_ID(0x1235, 0x8204): /* Focusrite Scarlett 18i8 2nd Gen */ case USB_ID(0x1235, 0x8201): /* Focusrite Scarlett 18i20 2nd Gen */ - err = snd_scarlett_gen2_controls_create(mixer); + err = snd_scarlett_gen2_init(mixer); break; case USB_ID(0x041e, 0x323b): /* Creative Sound Blaster E1 */ diff --git a/sound/usb/mixer_scarlett_gen2.c b/sound/usb/mixer_scarlett_gen2.c index 560c2ade829d..4caf379d5b99 100644 --- a/sound/usb/mixer_scarlett_gen2.c +++ b/sound/usb/mixer_scarlett_gen2.c @@ -635,7 +635,7 @@ static int scarlett2_usb( /* send a second message to get the response */ err = snd_usb_ctl_msg(mixer->chip->dev, - usb_sndctrlpipe(mixer->chip->dev, 0), + usb_rcvctrlpipe(mixer->chip->dev, 0), SCARLETT2_USB_VENDOR_SPECIFIC_CMD_RESP, USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_IN, 0, @@ -1997,38 +1997,11 @@ static int scarlett2_mixer_status_create(struct usb_mixer_interface *mixer) return usb_submit_urb(mixer->urb, GFP_KERNEL); } -/* Entry point */ -int snd_scarlett_gen2_controls_create(struct usb_mixer_interface *mixer) +static int snd_scarlett_gen2_controls_create(struct usb_mixer_interface *mixer, + const struct scarlett2_device_info *info) { - const struct scarlett2_device_info *info; int err; - /* only use UAC_VERSION_2 */ - if (!mixer->protocol) - return 0; - - switch (mixer->chip->usb_id) { - case USB_ID(0x1235, 0x8203): - info = &s6i6_gen2_info; - break; - case USB_ID(0x1235, 0x8204): - info = &s18i8_gen2_info; - break; - case USB_ID(0x1235, 0x8201): - info = &s18i20_gen2_info; - break; - default: /* device not (yet) supported */ - return -EINVAL; - } - - if (!(mixer->chip->setup & SCARLETT2_ENABLE)) { - usb_audio_err(mixer->chip, - "Focusrite Scarlett Gen 2 Mixer Driver disabled; " - "use options snd_usb_audio device_setup=1 " - "to enable and report any issues to g@b4.vu"); - return 0; - } - /* Initialise private data, routing, sequence number */ err = scarlett2_init_private(mixer, info); if (err < 0) @@ -2073,3 +2046,51 @@ int snd_scarlett_gen2_controls_create(struct usb_mixer_interface *mixer) return 0; } + +int snd_scarlett_gen2_init(struct usb_mixer_interface *mixer) +{ + struct snd_usb_audio *chip = mixer->chip; + const struct scarlett2_device_info *info; + int err; + + /* only use UAC_VERSION_2 */ + if (!mixer->protocol) + return 0; + + switch (chip->usb_id) { + case USB_ID(0x1235, 0x8203): + info = &s6i6_gen2_info; + break; + case USB_ID(0x1235, 0x8204): + info = &s18i8_gen2_info; + break; + case USB_ID(0x1235, 0x8201): + info = &s18i20_gen2_info; + break; + default: /* device not (yet) supported */ + return -EINVAL; + } + + if (!(chip->setup & SCARLETT2_ENABLE)) { + usb_audio_info(chip, + "Focusrite Scarlett Gen 2 Mixer Driver disabled; " + "use options snd_usb_audio vid=0x%04x pid=0x%04x " + "device_setup=1 to enable and report any issues " + "to g@b4.vu", + USB_ID_VENDOR(chip->usb_id), + USB_ID_PRODUCT(chip->usb_id)); + return 0; + } + + usb_audio_info(chip, + "Focusrite Scarlett Gen 2 Mixer Driver enabled pid=0x%04x", + USB_ID_PRODUCT(chip->usb_id)); + + err = snd_scarlett_gen2_controls_create(mixer, info); + if (err < 0) + usb_audio_err(mixer->chip, + "Error initialising Scarlett Mixer Driver: %d", + err); + + return err; +} diff --git a/sound/usb/mixer_scarlett_gen2.h b/sound/usb/mixer_scarlett_gen2.h index 52e1dad77afd..668c6b0cb50a 100644 --- a/sound/usb/mixer_scarlett_gen2.h +++ b/sound/usb/mixer_scarlett_gen2.h @@ -2,6 +2,6 @@ #ifndef __USB_MIXER_SCARLETT_GEN2_H #define __USB_MIXER_SCARLETT_GEN2_H -int snd_scarlett_gen2_controls_create(struct usb_mixer_interface *mixer); +int snd_scarlett_gen2_init(struct usb_mixer_interface *mixer); #endif /* __USB_MIXER_SCARLETT_GEN2_H */ diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 790944c35602..baee8591ac76 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -30,7 +30,8 @@ CGROUP COMMANDS | *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** | | **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** | | **getpeername4** | **getpeername6** | **getsockname4** | **getsockname6** | **sendmsg4** | -| **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** } +| **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** | +| **sock_release** } | *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION @@ -106,6 +107,7 @@ DESCRIPTION **getpeername6** call to getpeername(2) for an inet6 socket (since 5.8); **getsockname4** call to getsockname(2) for an inet4 socket (since 5.8); **getsockname6** call to getsockname(2) for an inet6 socket (since 5.8). + **sock_release** closing an userspace inet socket (since 5.9). **bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* Detach *PROG* from the cgroup *CGROUP* and attach type diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 358c7309d419..fe1b38e7e887 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -44,7 +44,7 @@ PROG COMMANDS | **cgroup/connect4** | **cgroup/connect6** | **cgroup/getpeername4** | **cgroup/getpeername6** | | **cgroup/getsockname4** | **cgroup/getsockname6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** | | **cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl** | -| **cgroup/getsockopt** | **cgroup/setsockopt** | +| **cgroup/getsockopt** | **cgroup/setsockopt** | **cgroup/sock_release** | | **struct_ops** | **fentry** | **fexit** | **freplace** | **sk_lookup** | } | *ATTACH_TYPE* := { diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index d67518bcbd44..cc33c5824a2f 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -478,7 +478,7 @@ _bpftool() cgroup/recvmsg4 cgroup/recvmsg6 \ cgroup/post_bind4 cgroup/post_bind6 \ cgroup/sysctl cgroup/getsockopt \ - cgroup/setsockopt struct_ops \ + cgroup/setsockopt cgroup/sock_release struct_ops \ fentry fexit freplace sk_lookup" -- \ "$cur" ) ) return 0 @@ -1021,7 +1021,7 @@ _bpftool() device bind4 bind6 post_bind4 post_bind6 connect4 connect6 \ getpeername4 getpeername6 getsockname4 getsockname6 \ sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl getsockopt \ - setsockopt' + setsockopt sock_release' local ATTACH_FLAGS='multi override' local PROG_TYPE='id pinned tag name' case $prev in @@ -1032,7 +1032,7 @@ _bpftool() ingress|egress|sock_create|sock_ops|device|bind4|bind6|\ post_bind4|post_bind6|connect4|connect6|getpeername4|\ getpeername6|getsockname4|getsockname6|sendmsg4|sendmsg6|\ - recvmsg4|recvmsg6|sysctl|getsockopt|setsockopt) + recvmsg4|recvmsg6|sysctl|getsockopt|setsockopt|sock_release) COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ "$cur" ) ) return 0 diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index d901cc1b904a..6e53b1d393f4 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -28,7 +28,8 @@ " connect6 | getpeername4 | getpeername6 |\n" \ " getsockname4 | getsockname6 | sendmsg4 |\n" \ " sendmsg6 | recvmsg4 | recvmsg6 |\n" \ - " sysctl | getsockopt | setsockopt }" + " sysctl | getsockopt | setsockopt |\n" \ + " sock_release }" static unsigned int query_flags; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 3f067d2d7584..da4846c9856a 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -2138,7 +2138,7 @@ static int do_help(int argc, char **argv) " cgroup/getpeername4 | cgroup/getpeername6 |\n" " cgroup/getsockname4 | cgroup/getsockname6 | cgroup/sendmsg4 |\n" " cgroup/sendmsg6 | cgroup/recvmsg4 | cgroup/recvmsg6 |\n" - " cgroup/getsockopt | cgroup/setsockopt |\n" + " cgroup/getsockopt | cgroup/setsockopt | cgroup/sock_release |\n" " struct_ops | fentry | fexit | freplace | sk_lookup }\n" " ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n" " flow_dissector }\n" diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 3fd9a7e9d90c..79d9c44d1ad7 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -8,6 +8,7 @@ * Note: you must update KVM_API_VERSION if you change this interface. */ +#include <linux/const.h> #include <linux/types.h> #include <linux/compiler.h> #include <linux/ioctl.h> @@ -1879,8 +1880,8 @@ struct kvm_hyperv_eventfd { * conversion after harvesting an entry. Also, it must not skip any * dirty bits, so that dirty bits are always harvested in sequence. */ -#define KVM_DIRTY_GFN_F_DIRTY BIT(0) -#define KVM_DIRTY_GFN_F_RESET BIT(1) +#define KVM_DIRTY_GFN_F_DIRTY _BITUL(0) +#define KVM_DIRTY_GFN_F_RESET _BITUL(1) #define KVM_DIRTY_GFN_F_MASK 0x3 /* diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index e2a3cf437814..c41d9b2b59ac 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -3216,6 +3216,9 @@ static int add_dummy_ksym_var(struct btf *btf) const struct btf_var_secinfo *vs; const struct btf_type *sec; + if (!btf) + return 0; + sec_btf_id = btf__find_by_name_kind(btf, KSYMS_SEC, BTF_KIND_DATASEC); if (sec_btf_id < 0) diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index ee426226928f..acbcf6c7bdf8 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -41,6 +41,11 @@ #define ELF_C_READ_MMAP ELF_C_READ #endif +/* Older libelf all end up in this expression, for both 32 and 64 bit */ +#ifndef GELF_ST_VISIBILITY +#define GELF_ST_VISIBILITY(o) ((o) & 0x03) +#endif + #define BTF_INFO_ENC(kind, kind_flag, vlen) \ ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) #define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type) diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 20cb91ef06ff..2f6b67189b42 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -443,6 +443,8 @@ int main(int argc, const char **argv) const char *cmd; char sbuf[STRERR_BUFSIZE]; + perf_debug_setup(); + /* libsubcmd init */ exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT); pager_init(PERF_PAGER_ENVIRONMENT); @@ -531,8 +533,6 @@ int main(int argc, const char **argv) */ pthread__block_sigwinch(); - perf_debug_setup(); - while (1) { static int done_help; diff --git a/tools/perf/pmu-events/arch/powerpc/power10/cache.json b/tools/perf/pmu-events/arch/powerpc/power10/cache.json index 616f29098c71..605be14f441c 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/cache.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/cache.json @@ -1,46 +1,56 @@ [ { - "EventCode": "1003C", + "EventCode": "0x1003C", "EventName": "PM_EXEC_STALL_DMISS_L2L3", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from either the local L2 or local L3." }, { - "EventCode": "34056", + "EventCode": "0x1E054", + "EventName": "PM_EXEC_STALL_DMISS_L21_L31", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from another core's L2 or L3 on the same chip." + }, + { + "EventCode": "0x34054", + "EventName": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, without a dispatch conflict." + }, + { + "EventCode": "0x34056", "EventName": "PM_EXEC_STALL_LOAD_FINISH", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the NTF instruction merged with another load in the LMQ." + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the NTF instruction merged with another load in the LMQ; cycles in which the NTF instruction is waiting for a data reload for a load miss, but the data comes back with a non-NTF instruction." }, { - "EventCode": "3006C", + "EventCode": "0x3006C", "EventName": "PM_RUN_CYC_SMT2_MODE", "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT2 mode." }, { - "EventCode": "300F4", + "EventCode": "0x300F4", "EventName": "PM_RUN_INST_CMPL_CONC", "BriefDescription": "PowerPC instructions completed by this thread when all threads in the core had the run-latch set." }, { - "EventCode": "4C016", + "EventCode": "0x4C016", "EventName": "PM_EXEC_STALL_DMISS_L2L3_CONFLICT", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, with a dispatch conflict." }, { - "EventCode": "4D014", + "EventCode": "0x4D014", "EventName": "PM_EXEC_STALL_LOAD", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a load instruction executing in the Load Store Unit." }, { - "EventCode": "4D016", + "EventCode": "0x4D016", "EventName": "PM_EXEC_STALL_PTESYNC", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a PTESYNC instruction executing in the Load Store Unit." }, { - "EventCode": "401EA", + "EventCode": "0x401EA", "EventName": "PM_THRESH_EXC_128", "BriefDescription": "Threshold counter exceeded a value of 128." }, { - "EventCode": "400F6", + "EventCode": "0x400F6", "EventName": "PM_BR_MPRED_CMPL", "BriefDescription": "A mispredicted branch completed. Includes direction and target." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json b/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json index 703cd431ae5b..54acb55e2c8c 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json @@ -1,6 +1,6 @@ [ { - "EventCode": "4016E", + "EventCode": "0x4016E", "EventName": "PM_THRESH_NOT_MET", "BriefDescription": "Threshold counter did not meet threshold." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json index eac8609dcc90..558f9530f54e 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json @@ -1,216 +1,246 @@ [ { - "EventCode": "10004", + "EventCode": "0x10004", "EventName": "PM_EXEC_STALL_TRANSLATION", "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss or ERAT miss and waited for it to resolve." }, { - "EventCode": "10010", + "EventCode": "0x10006", + "EventName": "PM_DISP_STALL_HELD_OTHER_CYC", + "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any other reason." + }, + { + "EventCode": "0x10010", "EventName": "PM_PMC4_OVERFLOW", "BriefDescription": "The event selected for PMC4 caused the event counter to overflow." }, { - "EventCode": "10020", + "EventCode": "0x10020", "EventName": "PM_PMC4_REWIND", "BriefDescription": "The speculative event selected for PMC4 rewinds and the counter for PMC4 is not charged." }, { - "EventCode": "10038", + "EventCode": "0x10038", "EventName": "PM_DISP_STALL_TRANSLATION", "BriefDescription": "Cycles when dispatch was stalled for this thread because the MMU was handling a translation miss." }, { - "EventCode": "1003A", + "EventCode": "0x1003A", "EventName": "PM_DISP_STALL_BR_MPRED_IC_L2", "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2 after suffering a branch mispredict." }, { - "EventCode": "1E050", + "EventCode": "0x1D05E", + "EventName": "PM_DISP_STALL_HELD_HALT_CYC", + "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of power management." + }, + { + "EventCode": "0x1E050", "EventName": "PM_DISP_STALL_HELD_STF_MAPPER_CYC", "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR." }, { - "EventCode": "1F054", + "EventCode": "0x1F054", "EventName": "PM_DTLB_HIT", "BriefDescription": "The PTE required by the instruction was resident in the TLB (data TLB access). When MMCR1[16]=0 this event counts only demand hits. When MMCR1[16]=1 this event includes demand and prefetch. Applies to both HPT and RPT." }, { - "EventCode": "101E8", + "EventCode": "0x10064", + "EventName": "PM_DISP_STALL_IC_L2", + "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2." + }, + { + "EventCode": "0x101E8", "EventName": "PM_THRESH_EXC_256", "BriefDescription": "Threshold counter exceeded a count of 256." }, { - "EventCode": "101EC", + "EventCode": "0x101EC", "EventName": "PM_THRESH_MET", "BriefDescription": "Threshold exceeded." }, { - "EventCode": "100F2", + "EventCode": "0x100F2", "EventName": "PM_1PLUS_PPC_CMPL", "BriefDescription": "Cycles in which at least one instruction is completed by this thread." }, { - "EventCode": "100F6", + "EventCode": "0x100F6", "EventName": "PM_IERAT_MISS", "BriefDescription": "IERAT Reloaded to satisfy an IERAT miss. All page sizes are counted by this event." }, { - "EventCode": "100F8", + "EventCode": "0x100F8", "EventName": "PM_DISP_STALL_CYC", "BriefDescription": "Cycles the ICT has no itags assigned to this thread (no instructions were dispatched during these cycles)." }, { - "EventCode": "20114", + "EventCode": "0x20006", + "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC", + "BriefDescription": "Cycles in which the NTC instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue." + }, + { + "EventCode": "0x20114", "EventName": "PM_MRK_L2_RC_DISP", "BriefDescription": "Marked instruction RC dispatched in L2." }, { - "EventCode": "2C010", + "EventCode": "0x2C010", "EventName": "PM_EXEC_STALL_LSU", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the Load Store Unit. This does not include simple fixed point instructions." }, { - "EventCode": "2C016", + "EventCode": "0x2C016", "EventName": "PM_DISP_STALL_IERAT_ONLY_MISS", "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction ERAT miss." }, { - "EventCode": "2C01E", + "EventCode": "0x2C01E", "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3", "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3 after suffering a branch mispredict." }, { - "EventCode": "2D01A", + "EventCode": "0x2D01A", "EventName": "PM_DISP_STALL_IC_MISS", "BriefDescription": "Cycles when dispatch was stalled for this thread due to an Icache Miss." }, { - "EventCode": "2D01C", - "EventName": "PM_CMPL_STALL_STCX", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a stcx waiting for resolution from the nest before completing." - }, - { - "EventCode": "2E018", + "EventCode": "0x2E018", "EventName": "PM_DISP_STALL_FETCH", "BriefDescription": "Cycles when dispatch was stalled for this thread because Fetch was being held." }, { - "EventCode": "2E01A", + "EventCode": "0x2E01A", "EventName": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC", "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the XVFC mapper/SRB was full." }, { - "EventCode": "2C142", + "EventCode": "0x2C142", "EventName": "PM_MRK_XFER_FROM_SRC_PMC2", "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[15:27]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "24050", + "EventCode": "0x24050", "EventName": "PM_IOPS_DISP", "BriefDescription": "Internal Operations dispatched. PM_IOPS_DISP / PM_INST_DISP will show the average number of internal operations per PowerPC instruction." }, { - "EventCode": "2405E", + "EventCode": "0x2405E", "EventName": "PM_ISSUE_CANCEL", "BriefDescription": "An instruction issued and the issue was later cancelled. Only one cancel per PowerPC instruction." }, { - "EventCode": "200FA", + "EventCode": "0x200FA", "EventName": "PM_BR_TAKEN_CMPL", "BriefDescription": "Branch Taken instruction completed." }, { - "EventCode": "30012", + "EventCode": "0x30004", + "EventName": "PM_DISP_STALL_FLUSH", + "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet NTC. PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC." + }, + { + "EventCode": "0x3000A", + "EventName": "PM_DISP_STALL_ITLB_MISS", + "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction TLB miss." + }, + { + "EventCode": "0x30012", "EventName": "PM_FLUSH_COMPLETION", "BriefDescription": "The instruction that was next to complete (oldest in the pipeline) did not complete because it suffered a flush." }, { - "EventCode": "30014", + "EventCode": "0x30014", "EventName": "PM_EXEC_STALL_STORE", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store instruction executing in the Load Store Unit." }, { - "EventCode": "30018", + "EventCode": "0x30018", "EventName": "PM_DISP_STALL_HELD_SCOREBOARD_CYC", "BriefDescription": "Cycles in which the NTC instruction is held at dispatch while waiting on the Scoreboard. This event combines VSCR and FPSCR together." }, { - "EventCode": "30026", + "EventCode": "0x30026", "EventName": "PM_EXEC_STALL_STORE_MISS", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store whose cache line was not resident in the L1 and was waiting for allocation of the missing line into the L1." }, { - "EventCode": "3012A", + "EventCode": "0x3012A", "EventName": "PM_MRK_L2_RC_DONE", "BriefDescription": "L2 RC machine completed the transaction for the marked instruction." }, { - "EventCode": "3F046", + "EventCode": "0x3F046", "EventName": "PM_ITLB_HIT_1G", "BriefDescription": "Instruction TLB hit (IERAT reload) page size 1G, which implies Radix Page Table translation is in use. When MMCR1[17]=0 this event counts only for demand misses. When MMCR1[17]=1 this event includes demand misses and prefetches." }, { - "EventCode": "34058", + "EventCode": "0x34058", "EventName": "PM_DISP_STALL_BR_MPRED_ICMISS", "BriefDescription": "Cycles when dispatch was stalled after a mispredicted branch resulted in an instruction cache miss." }, { - "EventCode": "3D05C", + "EventCode": "0x3D05C", "EventName": "PM_DISP_STALL_HELD_RENAME_CYC", "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC." }, { - "EventCode": "3E052", + "EventCode": "0x3E052", "EventName": "PM_DISP_STALL_IC_L3", "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3." }, { - "EventCode": "3E054", + "EventCode": "0x3E054", "EventName": "PM_LD_MISS_L1", "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load." }, { - "EventCode": "301EA", + "EventCode": "0x301EA", "EventName": "PM_THRESH_EXC_1024", "BriefDescription": "Threshold counter exceeded a value of 1024." }, { - "EventCode": "300FA", + "EventCode": "0x300FA", "EventName": "PM_INST_FROM_L3MISS", "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss." }, { - "EventCode": "40006", + "EventCode": "0x40006", "EventName": "PM_ISSUE_KILL", "BriefDescription": "Cycles in which an instruction or group of instructions were cancelled after being issued. This event increments once per occurrence, regardless of how many instructions are included in the issue group." }, { - "EventCode": "40116", + "EventCode": "0x40116", "EventName": "PM_MRK_LARX_FIN", "BriefDescription": "Marked load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "4C010", + "EventCode": "0x4C010", "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3MISS", "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from sources beyond the local L3 after suffering a mispredicted branch." }, { - "EventCode": "4D01E", + "EventCode": "0x4D01E", "EventName": "PM_DISP_STALL_BR_MPRED", "BriefDescription": "Cycles when dispatch was stalled for this thread due to a mispredicted branch." }, { - "EventCode": "4E010", + "EventCode": "0x4E010", "EventName": "PM_DISP_STALL_IC_L3MISS", "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from any source beyond the local L3." }, { - "EventCode": "4E01A", + "EventCode": "0x4E01A", "EventName": "PM_DISP_STALL_HELD_CYC", "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any reason." }, { - "EventCode": "44056", + "EventCode": "0x4003C", + "EventName": "PM_DISP_STALL_HELD_SYNC_CYC", + "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch." + }, + { + "EventCode": "0x44056", "EventName": "PM_VECTOR_ST_CMPL", "BriefDescription": "Vector store instructions completed." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/locks.json b/tools/perf/pmu-events/arch/powerpc/power10/locks.json index 016d8de0e14a..b5a0d6521963 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/locks.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/locks.json @@ -1,11 +1,11 @@ [ { - "EventCode": "1E058", + "EventCode": "0x1E058", "EventName": "PM_STCX_FAIL_FIN", "BriefDescription": "Conditional store instruction (STCX) failed. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "4E050", + "EventCode": "0x4E050", "EventName": "PM_STCX_PASS_FIN", "BriefDescription": "Conditional store instruction (STCX) passed. LARX and STCX are instructions used to acquire a lock." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/marked.json b/tools/perf/pmu-events/arch/powerpc/power10/marked.json index 93a5a5910648..58b5dfe3a273 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/marked.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/marked.json @@ -1,146 +1,141 @@ [ { - "EventCode": "1002C", + "EventCode": "0x1002C", "EventName": "PM_LD_PREFETCH_CACHE_LINE_MISS", "BriefDescription": "The L1 cache was reloaded with a line that fulfills a prefetch request." }, { - "EventCode": "10132", + "EventCode": "0x10132", "EventName": "PM_MRK_INST_ISSUED", "BriefDescription": "Marked instruction issued. Note that stores always get issued twice, the address gets issued to the LSU and the data gets issued to the VSU. Also, issues can sometimes get killed/cancelled and cause multiple sequential issues for the same instruction." }, { - "EventCode": "101E0", + "EventCode": "0x101E0", "EventName": "PM_MRK_INST_DISP", "BriefDescription": "The thread has dispatched a randomly sampled marked instruction." }, { - "EventCode": "101E2", + "EventCode": "0x101E2", "EventName": "PM_MRK_BR_TAKEN_CMPL", "BriefDescription": "Marked Branch Taken instruction completed." }, { - "EventCode": "20112", + "EventCode": "0x20112", "EventName": "PM_MRK_NTF_FIN", "BriefDescription": "The marked instruction became the oldest in the pipeline before it finished. It excludes instructions that finish at dispatch." }, { - "EventCode": "2C01C", + "EventCode": "0x2C01C", "EventName": "PM_EXEC_STALL_DMISS_OFF_CHIP", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a remote chip." }, { - "EventCode": "20138", + "EventCode": "0x20138", "EventName": "PM_MRK_ST_NEST", "BriefDescription": "A store has been sampled/marked and is at the point of execution where it has completed in the core and can no longer be flushed. At this point the store is sent to the L2." }, { - "EventCode": "2013A", + "EventCode": "0x2013A", "EventName": "PM_MRK_BRU_FIN", "BriefDescription": "Marked Branch instruction finished." }, { - "EventCode": "2C144", + "EventCode": "0x2C144", "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC2", "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[15:27]." }, { - "EventCode": "24156", + "EventCode": "0x24156", "EventName": "PM_MRK_STCX_FIN", "BriefDescription": "Marked conditional store instruction (STCX) finished. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "24158", + "EventCode": "0x24158", "EventName": "PM_MRK_INST", "BriefDescription": "An instruction was marked. Includes both Random Instruction Sampling (RIS) at decode time and Random Event Sampling (RES) at the time the configured event happens." }, { - "EventCode": "2415C", + "EventCode": "0x2415C", "EventName": "PM_MRK_BR_CMPL", "BriefDescription": "A marked branch completed. All branches are included." }, { - "EventCode": "200FD", + "EventCode": "0x200FD", "EventName": "PM_L1_ICACHE_MISS", "BriefDescription": "Demand iCache Miss." }, { - "EventCode": "30130", + "EventCode": "0x30130", "EventName": "PM_MRK_INST_FIN", "BriefDescription": "marked instruction finished. Excludes instructions that finish at dispatch. Note that stores always finish twice since the address gets issued to the LSU and the data gets issued to the VSU." }, { - "EventCode": "34146", + "EventCode": "0x34146", "EventName": "PM_MRK_LD_CMPL", "BriefDescription": "Marked loads completed." }, { - "EventCode": "3E158", + "EventCode": "0x3E158", "EventName": "PM_MRK_STCX_FAIL", "BriefDescription": "Marked conditional store instruction (STCX) failed. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "3E15A", + "EventCode": "0x3E15A", "EventName": "PM_MRK_ST_FIN", "BriefDescription": "The marked instruction was a store of any kind." }, { - "EventCode": "30068", + "EventCode": "0x30068", "EventName": "PM_L1_ICACHE_RELOADED_PREF", "BriefDescription": "Counts all Icache prefetch reloads ( includes demand turned into prefetch)." }, { - "EventCode": "301E4", + "EventCode": "0x301E4", "EventName": "PM_MRK_BR_MPRED_CMPL", "BriefDescription": "Marked Branch Mispredicted. Includes direction and target." }, { - "EventCode": "300F6", + "EventCode": "0x300F6", "EventName": "PM_LD_DEMAND_MISS_L1", "BriefDescription": "The L1 cache was reloaded with a line that fulfills a demand miss request. Counted at reload time, before finish." }, { - "EventCode": "300FE", + "EventCode": "0x300FE", "EventName": "PM_DATA_FROM_L3MISS", "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss." }, { - "EventCode": "40012", + "EventCode": "0x40012", "EventName": "PM_L1_ICACHE_RELOADED_ALL", "BriefDescription": "Counts all Icache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch." }, { - "EventCode": "40134", + "EventCode": "0x40134", "EventName": "PM_MRK_INST_TIMEO", "BriefDescription": "Marked instruction finish timeout (instruction was lost)." }, { - "EventCode": "4003C", - "EventName": "PM_DISP_STALL_HELD_SYNC_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch." - }, - { - "EventCode": "4505A", + "EventCode": "0x4505A", "EventName": "PM_SP_FLOP_CMPL", "BriefDescription": "Single Precision floating point instructions completed." }, { - "EventCode": "4D058", + "EventCode": "0x4D058", "EventName": "PM_VECTOR_FLOP_CMPL", "BriefDescription": "Vector floating point instructions completed." }, { - "EventCode": "4D05A", + "EventCode": "0x4D05A", "EventName": "PM_NON_MATH_FLOP_CMPL", "BriefDescription": "Non Math instructions completed." }, { - "EventCode": "401E0", + "EventCode": "0x401E0", "EventName": "PM_MRK_INST_CMPL", "BriefDescription": "marked instruction completed." }, { - "EventCode": "400FE", + "EventCode": "0x400FE", "EventName": "PM_DATA_FROM_MEMORY", "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/memory.json b/tools/perf/pmu-events/arch/powerpc/power10/memory.json index b01141eeebee..843b51f531e9 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/memory.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/memory.json @@ -1,191 +1,186 @@ [ { - "EventCode": "1000A", + "EventCode": "0x1000A", "EventName": "PM_PMC3_REWIND", "BriefDescription": "The speculative event selected for PMC3 rewinds and the counter for PMC3 is not charged." }, { - "EventCode": "1C040", + "EventCode": "0x1C040", "EventName": "PM_XFER_FROM_SRC_PMC1", "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "1C142", + "EventCode": "0x1C142", "EventName": "PM_MRK_XFER_FROM_SRC_PMC1", "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "1C144", + "EventCode": "0x1C144", "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC1", "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[0:12]." }, { - "EventCode": "1C056", + "EventCode": "0x1C056", "EventName": "PM_DERAT_MISS_4K", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 4K. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "1C058", + "EventCode": "0x1C058", "EventName": "PM_DTLB_MISS_16G", "BriefDescription": "Data TLB reload (after a miss) page size 16G. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "1C05C", + "EventCode": "0x1C05C", "EventName": "PM_DTLB_MISS_2M", "BriefDescription": "Data TLB reload (after a miss) page size 2M. Implies radix translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "1E056", + "EventCode": "0x1E056", "EventName": "PM_EXEC_STALL_STORE_PIPE", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the store unit. This does not include cycles spent handling store misses, PTESYNC instructions or TLBIE instructions." }, { - "EventCode": "1F150", + "EventCode": "0x1F150", "EventName": "PM_MRK_ST_L2_CYC", "BriefDescription": "Cycles from L2 RC dispatch to L2 RC completion." }, { - "EventCode": "10062", + "EventCode": "0x10062", "EventName": "PM_LD_L3MISS_PEND_CYC", "BriefDescription": "Cycles L3 miss was pending for this thread." }, { - "EventCode": "20010", + "EventCode": "0x20010", "EventName": "PM_PMC1_OVERFLOW", "BriefDescription": "The event selected for PMC1 caused the event counter to overflow." }, { - "EventCode": "2001A", + "EventCode": "0x2001A", "EventName": "PM_ITLB_HIT", "BriefDescription": "The PTE required to translate the instruction address was resident in the TLB (instruction TLB access/IERAT reload). Applies to both HPT and RPT. When MMCR1[17]=0 this event counts only for demand misses. When MMCR1[17]=1 this event includes demand misses and prefetches." }, { - "EventCode": "2003E", + "EventCode": "0x2003E", "EventName": "PM_PTESYNC_FIN", "BriefDescription": "Ptesync instruction finished in the store unit. Only one ptesync can finish at a time." }, { - "EventCode": "2C040", + "EventCode": "0x2C040", "EventName": "PM_XFER_FROM_SRC_PMC2", "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[15:27]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "2C054", + "EventCode": "0x2C054", "EventName": "PM_DERAT_MISS_64K", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "2C056", + "EventCode": "0x2C056", "EventName": "PM_DTLB_MISS_4K", "BriefDescription": "Data TLB reload (after a miss) page size 4K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "2D154", + "EventCode": "0x2D154", "EventName": "PM_MRK_DERAT_MISS_64K", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "200F6", + "EventCode": "0x200F6", "EventName": "PM_DERAT_MISS", "BriefDescription": "DERAT Reloaded to satisfy a DERAT miss. All page sizes are counted by this event. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "3000A", - "EventName": "PM_DISP_STALL_ITLB_MISS", - "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction TLB miss." - }, - { - "EventCode": "30016", + "EventCode": "0x30016", "EventName": "PM_EXEC_STALL_DERAT_DTLB_MISS", "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss and waited for it resolve." }, { - "EventCode": "3C040", + "EventCode": "0x3C040", "EventName": "PM_XFER_FROM_SRC_PMC3", "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "3C142", + "EventCode": "0x3C142", "EventName": "PM_MRK_XFER_FROM_SRC_PMC3", "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "3C144", + "EventCode": "0x3C144", "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC3", "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[30:42]." }, { - "EventCode": "3C054", + "EventCode": "0x3C054", "EventName": "PM_DERAT_MISS_16M", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16M. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "3C056", + "EventCode": "0x3C056", "EventName": "PM_DTLB_MISS_64K", "BriefDescription": "Data TLB reload (after a miss) page size 64K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "3C058", + "EventCode": "0x3C058", "EventName": "PM_LARX_FIN", "BriefDescription": "Load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "301E2", + "EventCode": "0x301E2", "EventName": "PM_MRK_ST_CMPL", "BriefDescription": "Marked store completed and sent to nest. Note that this count excludes cache-inhibited stores." }, { - "EventCode": "300FC", + "EventCode": "0x300FC", "EventName": "PM_DTLB_MISS", "BriefDescription": "The DPTEG required for the load/store instruction in execution was missing from the TLB. It includes pages of all sizes for demand and prefetch activity." }, { - "EventCode": "4D02C", + "EventCode": "0x4D02C", "EventName": "PM_PMC1_REWIND", "BriefDescription": "The speculative event selected for PMC1 rewinds and the counter for PMC1 is not charged." }, { - "EventCode": "4003E", + "EventCode": "0x4003E", "EventName": "PM_LD_CMPL", "BriefDescription": "Loads completed." }, { - "EventCode": "4C040", + "EventCode": "0x4C040", "EventName": "PM_XFER_FROM_SRC_PMC4", "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "4C142", + "EventCode": "0x4C142", "EventName": "PM_MRK_XFER_FROM_SRC_PMC4", "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "4C144", + "EventCode": "0x4C144", "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC4", "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[45:57]." }, { - "EventCode": "4C056", + "EventCode": "0x4C056", "EventName": "PM_DTLB_MISS_16M", "BriefDescription": "Data TLB reload (after a miss) page size 16M. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "4C05A", + "EventCode": "0x4C05A", "EventName": "PM_DTLB_MISS_1G", "BriefDescription": "Data TLB reload (after a miss) page size 1G. Implies radix translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "4C15E", + "EventCode": "0x4C15E", "EventName": "PM_MRK_DTLB_MISS_64K", "BriefDescription": "Marked Data TLB reload (after a miss) page size 64K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "4D056", + "EventCode": "0x4D056", "EventName": "PM_NON_FMA_FLOP_CMPL", "BriefDescription": "Non FMA instruction completed." }, { - "EventCode": "40164", + "EventCode": "0x40164", "EventName": "PM_MRK_DERAT_MISS_2M", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/others.json b/tools/perf/pmu-events/arch/powerpc/power10/others.json index a119e56cbf1c..7d0de1a2860b 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/others.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/others.json @@ -1,296 +1,271 @@ [ { - "EventCode": "10016", + "EventCode": "0x10016", "EventName": "PM_VSU0_ISSUE", "BriefDescription": "VSU instructions issued to VSU pipe 0." }, { - "EventCode": "1001C", + "EventCode": "0x1001C", "EventName": "PM_ULTRAVISOR_INST_CMPL", "BriefDescription": "PowerPC instructions that completed while the thread was in ultravisor state." }, { - "EventCode": "100F0", + "EventCode": "0x100F0", "EventName": "PM_CYC", "BriefDescription": "Processor cycles." }, { - "EventCode": "10134", + "EventCode": "0x10134", "EventName": "PM_MRK_ST_DONE_L2", "BriefDescription": "Marked stores completed in L2 (RC machine done)." }, { - "EventCode": "1505E", + "EventCode": "0x1505E", "EventName": "PM_LD_HIT_L1", "BriefDescription": "Loads that finished without experiencing an L1 miss." }, { - "EventCode": "1D05E", - "EventName": "PM_DISP_STALL_HELD_HALT_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of power management." - }, - { - "EventCode": "1E054", - "EventName": "PM_EXEC_STALL_DMISS_L21_L31", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from another core's L2 or L3 on the same chip." - }, - { - "EventCode": "1E05A", - "EventName": "PM_CMPL_STALL_LWSYNC", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a lwsync waiting to complete." - }, - { - "EventCode": "1F056", + "EventCode": "0x1F056", "EventName": "PM_DISP_SS0_2_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 0 dispatches either 1 or 2 instructions." }, { - "EventCode": "1F15C", + "EventCode": "0x1F15C", "EventName": "PM_MRK_STCX_L2_CYC", "BriefDescription": "Cycles spent in the nest portion of a marked Stcx instruction. It starts counting when the operation starts to drain to the L2 and it stops counting when the instruction retires from the Instruction Completion Table (ICT) in the Instruction Sequencing Unit (ISU)." }, { - "EventCode": "10066", + "EventCode": "0x10066", "EventName": "PM_ADJUNCT_CYC", "BriefDescription": "Cycles in which the thread is in Adjunct state. MSR[S HV PR] bits = 011." }, { - "EventCode": "101E4", + "EventCode": "0x101E4", "EventName": "PM_MRK_L1_ICACHE_MISS", "BriefDescription": "Marked Instruction suffered an icache Miss." }, { - "EventCode": "101EA", + "EventCode": "0x101EA", "EventName": "PM_MRK_L1_RELOAD_VALID", "BriefDescription": "Marked demand reload." }, { - "EventCode": "100F4", + "EventCode": "0x100F4", "EventName": "PM_FLOP_CMPL", "BriefDescription": "Floating Point Operations Completed. Includes any type. It counts once for each 1, 2, 4 or 8 flop instruction. Use PM_1|2|4|8_FLOP_CMPL events to count flops." }, { - "EventCode": "100FA", + "EventCode": "0x100FA", "EventName": "PM_RUN_LATCH_ANY_THREAD_CYC", "BriefDescription": "Cycles when at least one thread has the run latch set." }, { - "EventCode": "100FC", + "EventCode": "0x100FC", "EventName": "PM_LD_REF_L1", "BriefDescription": "All L1 D cache load references counted at finish, gated by reject. In P9 and earlier this event counted only cacheable loads but in P10 both cacheable and non-cacheable loads are included." }, { - "EventCode": "20006", - "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue." - }, - { - "EventCode": "2000C", + "EventCode": "0x2000C", "EventName": "PM_RUN_LATCH_ALL_THREADS_CYC", "BriefDescription": "Cycles when the run latch is set for all threads." }, { - "EventCode": "2E010", + "EventCode": "0x2E010", "EventName": "PM_ADJUNCT_INST_CMPL", "BriefDescription": "PowerPC instructions that completed while the thread is in Adjunct state." }, { - "EventCode": "2E014", + "EventCode": "0x2E014", "EventName": "PM_STCX_FIN", "BriefDescription": "Conditional store instruction (STCX) finished. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "20130", + "EventCode": "0x20130", "EventName": "PM_MRK_INST_DECODED", "BriefDescription": "An instruction was marked at decode time. Random Instruction Sampling (RIS) only." }, { - "EventCode": "20132", + "EventCode": "0x20132", "EventName": "PM_MRK_DFU_ISSUE", "BriefDescription": "The marked instruction was a decimal floating point operation issued to the VSU. Measured at issue time." }, { - "EventCode": "20134", + "EventCode": "0x20134", "EventName": "PM_MRK_FXU_ISSUE", "BriefDescription": "The marked instruction was a fixed point operation issued to the VSU. Measured at issue time." }, { - "EventCode": "2505C", + "EventCode": "0x2505C", "EventName": "PM_VSU_ISSUE", "BriefDescription": "At least one VSU instruction was issued to one of the VSU pipes. Up to 4 per cycle. Includes fixed point operations." }, { - "EventCode": "2F054", + "EventCode": "0x2F054", "EventName": "PM_DISP_SS1_2_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 1 dispatches either 1 or 2 instructions." }, { - "EventCode": "2F056", + "EventCode": "0x2F056", "EventName": "PM_DISP_SS1_4_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 1 dispatches either 3 or 4 instructions." }, { - "EventCode": "2006C", + "EventCode": "0x2006C", "EventName": "PM_RUN_CYC_SMT4_MODE", "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT4 mode." }, { - "EventCode": "201E0", + "EventCode": "0x201E0", "EventName": "PM_MRK_DATA_FROM_MEMORY", "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss for a marked load." }, { - "EventCode": "201E4", + "EventCode": "0x201E4", "EventName": "PM_MRK_DATA_FROM_L3MISS", "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked load." }, { - "EventCode": "201E8", + "EventCode": "0x201E8", "EventName": "PM_THRESH_EXC_512", "BriefDescription": "Threshold counter exceeded a value of 512." }, { - "EventCode": "200F2", + "EventCode": "0x200F2", "EventName": "PM_INST_DISP", "BriefDescription": "PowerPC instructions dispatched." }, { - "EventCode": "30132", + "EventCode": "0x30132", "EventName": "PM_MRK_VSU_FIN", "BriefDescription": "VSU marked instructions finished. Excludes simple FX instructions issued to the Store Unit." }, { - "EventCode": "30038", + "EventCode": "0x30038", "EventName": "PM_EXEC_STALL_DMISS_LMEM", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local memory, local OpenCapp cache, or local OpenCapp memory." }, { - "EventCode": "3F04A", + "EventCode": "0x3F04A", "EventName": "PM_LSU_ST5_FIN", "BriefDescription": "LSU Finished an internal operation in ST2 port." }, { - "EventCode": "34054", - "EventName": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, without a dispatch conflict." - }, - { - "EventCode": "3405A", + "EventCode": "0x3405A", "EventName": "PM_PRIVILEGED_INST_CMPL", "BriefDescription": "PowerPC Instructions that completed while the thread is in Privileged state." }, { - "EventCode": "3F150", + "EventCode": "0x3F150", "EventName": "PM_MRK_ST_DRAIN_CYC", "BriefDescription": "cycles to drain st from core to L2." }, { - "EventCode": "3F054", + "EventCode": "0x3F054", "EventName": "PM_DISP_SS0_4_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 0 dispatches either 3 or 4 instructions." }, { - "EventCode": "3F056", + "EventCode": "0x3F056", "EventName": "PM_DISP_SS0_8_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 0 dispatches either 5, 6, 7 or 8 instructions." }, { - "EventCode": "30162", + "EventCode": "0x30162", "EventName": "PM_MRK_ISSUE_DEPENDENT_LOAD", "BriefDescription": "The marked instruction was dependent on a load. It is eligible for issue kill." }, { - "EventCode": "40114", + "EventCode": "0x40114", "EventName": "PM_MRK_START_PROBE_NOP_DISP", "BriefDescription": "Marked Start probe nop dispatched. Instruction AND R0,R0,R0." }, { - "EventCode": "4001C", + "EventCode": "0x4001C", "EventName": "PM_VSU_FIN", "BriefDescription": "VSU instructions finished." }, { - "EventCode": "4C01A", + "EventCode": "0x4C01A", "EventName": "PM_EXEC_STALL_DMISS_OFF_NODE", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a distant chip." }, { - "EventCode": "4D012", + "EventCode": "0x4D012", "EventName": "PM_PMC3_SAVED", "BriefDescription": "The conditions for the speculative event selected for PMC3 are met and PMC3 is charged." }, { - "EventCode": "4D022", + "EventCode": "0x4D022", "EventName": "PM_HYPERVISOR_INST_CMPL", "BriefDescription": "PowerPC instructions that completed while the thread is in hypervisor state." }, { - "EventCode": "4D026", + "EventCode": "0x4D026", "EventName": "PM_ULTRAVISOR_CYC", "BriefDescription": "Cycles when the thread is in Ultravisor state. MSR[S HV PR]=110." }, { - "EventCode": "4D028", + "EventCode": "0x4D028", "EventName": "PM_PRIVILEGED_CYC", "BriefDescription": "Cycles when the thread is in Privileged state. MSR[S HV PR]=x00." }, { - "EventCode": "40030", + "EventCode": "0x40030", "EventName": "PM_INST_FIN", "BriefDescription": "Instructions finished." }, { - "EventCode": "44146", + "EventCode": "0x44146", "EventName": "PM_MRK_STCX_CORE_CYC", "BriefDescription": "Cycles spent in the core portion of a marked Stcx instruction. It starts counting when the instruction is decoded and stops counting when it drains into the L2." }, { - "EventCode": "44054", + "EventCode": "0x44054", "EventName": "PM_VECTOR_LD_CMPL", "BriefDescription": "Vector load instructions completed." }, { - "EventCode": "45054", + "EventCode": "0x45054", "EventName": "PM_FMA_CMPL", "BriefDescription": "Two floating point instructions completed (FMA class of instructions: fmadd, fnmadd, fmsub, fnmsub). Scalar instructions only." }, { - "EventCode": "45056", + "EventCode": "0x45056", "EventName": "PM_SCALAR_FLOP_CMPL", "BriefDescription": "Scalar floating point instructions completed." }, { - "EventCode": "4505C", + "EventCode": "0x4505C", "EventName": "PM_MATH_FLOP_CMPL", "BriefDescription": "Math floating point instructions completed." }, { - "EventCode": "4D05E", + "EventCode": "0x4D05E", "EventName": "PM_BR_CMPL", "BriefDescription": "A branch completed. All branches are included." }, { - "EventCode": "4E15E", + "EventCode": "0x4E15E", "EventName": "PM_MRK_INST_FLUSHED", "BriefDescription": "The marked instruction was flushed." }, { - "EventCode": "401E6", + "EventCode": "0x401E6", "EventName": "PM_MRK_INST_FROM_L3MISS", "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked instruction." }, { - "EventCode": "401E8", + "EventCode": "0x401E8", "EventName": "PM_MRK_DATA_FROM_L2MISS", "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss for a marked load." }, { - "EventCode": "400F0", + "EventCode": "0x400F0", "EventName": "PM_LD_DEMAND_MISS_L1_FIN", "BriefDescription": "Load Missed L1, counted at finish time." }, { - "EventCode": "400FA", + "EventCode": "0x400FA", "EventName": "PM_RUN_INST_CMPL", "BriefDescription": "Completed PowerPC instructions gated by the run latch." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json index b61b5cc157ee..b8aded6045fa 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json @@ -1,296 +1,291 @@ [ { - "EventCode": "100FE", + "EventCode": "0x100FE", "EventName": "PM_INST_CMPL", "BriefDescription": "PowerPC instructions completed." }, { - "EventCode": "10006", - "EventName": "PM_DISP_STALL_HELD_OTHER_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any other reason." - }, - { - "EventCode": "1000C", + "EventCode": "0x1000C", "EventName": "PM_LSU_LD0_FIN", "BriefDescription": "LSU Finished an internal operation in LD0 port." }, { - "EventCode": "1000E", + "EventCode": "0x1000E", "EventName": "PM_MMA_ISSUED", "BriefDescription": "MMA instructions issued." }, { - "EventCode": "10012", + "EventCode": "0x10012", "EventName": "PM_LSU_ST0_FIN", "BriefDescription": "LSU Finished an internal operation in ST0 port." }, { - "EventCode": "10014", + "EventCode": "0x10014", "EventName": "PM_LSU_ST4_FIN", "BriefDescription": "LSU Finished an internal operation in ST4 port." }, { - "EventCode": "10018", + "EventCode": "0x10018", "EventName": "PM_IC_DEMAND_CYC", "BriefDescription": "Cycles in which an instruction reload is pending to satisfy a demand miss." }, { - "EventCode": "10022", + "EventCode": "0x10022", "EventName": "PM_PMC2_SAVED", "BriefDescription": "The conditions for the speculative event selected for PMC2 are met and PMC2 is charged." }, { - "EventCode": "10024", + "EventCode": "0x10024", "EventName": "PM_PMC5_OVERFLOW", "BriefDescription": "The event selected for PMC5 caused the event counter to overflow." }, { - "EventCode": "10058", + "EventCode": "0x10058", "EventName": "PM_EXEC_STALL_FIN_AT_DISP", "BriefDescription": "Cycles in which the oldest instruction in the pipeline finished at dispatch and did not require execution in the LSU, BRU or VSU." }, { - "EventCode": "1005A", + "EventCode": "0x1005A", "EventName": "PM_FLUSH_MPRED", "BriefDescription": "A flush occurred due to a mispredicted branch. Includes target and direction." }, { - "EventCode": "1C05A", + "EventCode": "0x1C05A", "EventName": "PM_DERAT_MISS_2M", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "10064", - "EventName": "PM_DISP_STALL_IC_L2", - "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2." + "EventCode": "0x1E05A", + "EventName": "PM_CMPL_STALL_LWSYNC", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a lwsync waiting to complete." }, { - "EventCode": "10068", + "EventCode": "0x10068", "EventName": "PM_BR_FIN", "BriefDescription": "A branch instruction finished. Includes predicted/mispredicted/unconditional." }, { - "EventCode": "1006A", + "EventCode": "0x1006A", "EventName": "PM_FX_LSU_FIN", "BriefDescription": "Simple fixed point instruction issued to the store unit. Measured at finish time." }, { - "EventCode": "1006C", + "EventCode": "0x1006C", "EventName": "PM_RUN_CYC_ST_MODE", "BriefDescription": "Cycles when the run latch is set and the core is in ST mode." }, { - "EventCode": "20004", + "EventCode": "0x20004", "EventName": "PM_ISSUE_STALL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was dispatched but not issued yet." }, { - "EventCode": "2000A", + "EventCode": "0x2000A", "EventName": "PM_HYPERVISOR_CYC", "BriefDescription": "Cycles when the thread is in Hypervisor state. MSR[S HV PR]=010." }, { - "EventCode": "2000E", + "EventCode": "0x2000E", "EventName": "PM_LSU_LD1_FIN", "BriefDescription": "LSU Finished an internal operation in LD1 port." }, { - "EventCode": "2C014", + "EventCode": "0x2C014", "EventName": "PM_CMPL_STALL_SPECIAL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline required special handling before completing." }, { - "EventCode": "2C018", + "EventCode": "0x2C018", "EventName": "PM_EXEC_STALL_DMISS_L3MISS", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a source beyond the local L2 or local L3." }, { - "EventCode": "2D010", + "EventCode": "0x2D010", "EventName": "PM_LSU_ST1_FIN", "BriefDescription": "LSU Finished an internal operation in ST1 port." }, { - "EventCode": "2D012", + "EventCode": "0x2D012", "EventName": "PM_VSU1_ISSUE", "BriefDescription": "VSU instructions issued to VSU pipe 1." }, { - "EventCode": "2D018", + "EventCode": "0x2D018", "EventName": "PM_EXEC_STALL_VSU", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the VSU (includes FXU, VSU, CRU)." }, { - "EventCode": "2E01E", + "EventCode": "0x2D01C", + "EventName": "PM_CMPL_STALL_STCX", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a stcx waiting for resolution from the nest before completing." + }, + { + "EventCode": "0x2E01E", "EventName": "PM_EXEC_STALL_NTC_FLUSH", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children." + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children. This event will also count cycles when the previous NTF instruction is still completing and the new NTF instruction is stalled at dispatch." }, { - "EventCode": "2013C", + "EventCode": "0x2013C", "EventName": "PM_MRK_FX_LSU_FIN", "BriefDescription": "The marked instruction was simple fixed point that was issued to the store unit. Measured at finish time." }, { - "EventCode": "2405A", + "EventCode": "0x2405A", "EventName": "PM_NTC_FIN", "BriefDescription": "Cycles in which the oldest instruction in the pipeline (NTC) finishes. Note that instructions can finish out of order, therefore not all the instructions that finish have a Next-to-complete status." }, { - "EventCode": "201E2", + "EventCode": "0x201E2", "EventName": "PM_MRK_LD_MISS_L1", "BriefDescription": "Marked DL1 Demand Miss counted at finish time." }, { - "EventCode": "200F4", + "EventCode": "0x200F4", "EventName": "PM_RUN_CYC", "BriefDescription": "Processor cycles gated by the run latch." }, { - "EventCode": "30004", - "EventName": "PM_DISP_STALL_FLUSH", - "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet NTC. PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC." - }, - { - "EventCode": "30008", + "EventCode": "0x30008", "EventName": "PM_EXEC_STALL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting to finish in one of the execution units (BRU, LSU, VSU). Only cycles between issue and finish are counted in this category." }, { - "EventCode": "3001A", + "EventCode": "0x3001A", "EventName": "PM_LSU_ST2_FIN", "BriefDescription": "LSU Finished an internal operation in ST2 port." }, { - "EventCode": "30020", + "EventCode": "0x30020", "EventName": "PM_PMC2_REWIND", "BriefDescription": "The speculative event selected for PMC2 rewinds and the counter for PMC2 is not charged." }, { - "EventCode": "30022", + "EventCode": "0x30022", "EventName": "PM_PMC4_SAVED", "BriefDescription": "The conditions for the speculative event selected for PMC4 are met and PMC4 is charged." }, { - "EventCode": "30024", + "EventCode": "0x30024", "EventName": "PM_PMC6_OVERFLOW", "BriefDescription": "The event selected for PMC6 caused the event counter to overflow." }, { - "EventCode": "30028", + "EventCode": "0x30028", "EventName": "PM_CMPL_STALL_MEM_ECC", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for the non-speculative finish of either a stcx waiting for its result or a load waiting for non-critical sectors of data and ECC." }, { - "EventCode": "30036", + "EventCode": "0x30036", "EventName": "PM_EXEC_STALL_SIMPLE_FX", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a simple fixed point instruction executing in the Load Store Unit." }, { - "EventCode": "3003A", + "EventCode": "0x3003A", "EventName": "PM_CMPL_STALL_EXCEPTION", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was not allowed to complete because it was interrupted by ANY exception, which has to be serviced before the instruction can complete." }, { - "EventCode": "3F044", + "EventCode": "0x3F044", "EventName": "PM_VSU2_ISSUE", "BriefDescription": "VSU instructions issued to VSU pipe 2." }, { - "EventCode": "30058", + "EventCode": "0x30058", "EventName": "PM_TLBIE_FIN", "BriefDescription": "TLBIE instructions finished in the LSU. Two TLBIEs can finish each cycle. All will be counted." }, { - "EventCode": "3D058", + "EventCode": "0x3D058", "EventName": "PM_SCALAR_FSQRT_FDIV_ISSUE", "BriefDescription": "Scalar versions of four floating point operations: fdiv,fsqrt (xvdivdp, xvdivsp, xvsqrtdp, xvsqrtsp)." }, { - "EventCode": "30066", + "EventCode": "0x30066", "EventName": "PM_LSU_FIN", "BriefDescription": "LSU Finished an internal operation (up to 4 per cycle)." }, { - "EventCode": "40004", + "EventCode": "0x40004", "EventName": "PM_FXU_ISSUE", "BriefDescription": "A fixed point instruction was issued to the VSU." }, { - "EventCode": "40008", + "EventCode": "0x40008", "EventName": "PM_NTC_ALL_FIN", "BriefDescription": "Cycles in which both instructions in the ICT entry pair show as finished. These are the cycles between finish and completion for the oldest pair of instructions in the pipeline." }, { - "EventCode": "40010", + "EventCode": "0x40010", "EventName": "PM_PMC3_OVERFLOW", "BriefDescription": "The event selected for PMC3 caused the event counter to overflow." }, { - "EventCode": "4C012", + "EventCode": "0x4C012", "EventName": "PM_EXEC_STALL_DERAT_ONLY_MISS", "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered an ERAT miss and waited for it resolve." }, { - "EventCode": "4C018", + "EventCode": "0x4C018", "EventName": "PM_CMPL_STALL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline cannot complete because the thread was blocked for any reason." }, { - "EventCode": "4C01E", + "EventCode": "0x4C01E", "EventName": "PM_LSU_ST3_FIN", "BriefDescription": "LSU Finished an internal operation in ST3 port." }, { - "EventCode": "4D018", + "EventCode": "0x4D018", "EventName": "PM_EXEC_STALL_BRU", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the Branch unit." }, { - "EventCode": "4D01A", + "EventCode": "0x4D01A", "EventName": "PM_CMPL_STALL_HWSYNC", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a hwsync waiting for response from L2 before completing." }, { - "EventCode": "4D01C", + "EventCode": "0x4D01C", "EventName": "PM_EXEC_STALL_TLBIEL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIEL instruction executing in the Load Store Unit. TLBIEL instructions have lower overhead than TLBIE instructions because they don't get set to the nest." }, { - "EventCode": "4E012", + "EventCode": "0x4E012", "EventName": "PM_EXEC_STALL_UNKNOWN", "BriefDescription": "Cycles in which the oldest instruction in the pipeline completed without an ntf_type pulse. The ntf_pulse was missed by the ISU because the NTF finishes and completions came too close together." }, { - "EventCode": "4D020", + "EventCode": "0x4D020", "EventName": "PM_VSU3_ISSUE", "BriefDescription": "VSU instruction was issued to VSU pipe 3." }, { - "EventCode": "40132", + "EventCode": "0x40132", "EventName": "PM_MRK_LSU_FIN", "BriefDescription": "LSU marked instruction finish." }, { - "EventCode": "45058", + "EventCode": "0x45058", "EventName": "PM_IC_MISS_CMPL", "BriefDescription": "Non-speculative icache miss, counted at completion." }, { - "EventCode": "4D050", + "EventCode": "0x4D050", "EventName": "PM_VSU_NON_FLOP_CMPL", "BriefDescription": "Non-floating point VSU instructions completed." }, { - "EventCode": "4D052", + "EventCode": "0x4D052", "EventName": "PM_2FLOP_CMPL", "BriefDescription": "Double Precision vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg completed." }, { - "EventCode": "400F2", + "EventCode": "0x400F2", "EventName": "PM_1PLUS_PPC_DISP", "BriefDescription": "Cycles at least one Instr Dispatched." }, { - "EventCode": "400F8", + "EventCode": "0x400F8", "EventName": "PM_FLUSH", "BriefDescription": "Flush (any type)." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json index ea122a91ceb0..b5d1bd39cfb2 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json @@ -1,21 +1,21 @@ [ { - "EventCode": "301E8", + "EventCode": "0x301E8", "EventName": "PM_THRESH_EXC_64", "BriefDescription": "Threshold counter exceeded a value of 64." }, { - "EventCode": "45050", + "EventCode": "0x45050", "EventName": "PM_1FLOP_CMPL", "BriefDescription": "One floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)." }, { - "EventCode": "45052", + "EventCode": "0x45052", "EventName": "PM_4FLOP_CMPL", "BriefDescription": "Four floating point instructions completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)." }, { - "EventCode": "4D054", + "EventCode": "0x4D054", "EventName": "PM_8FLOP_CMPL", "BriefDescription": "Four Double Precision vector instructions completed." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/translation.json b/tools/perf/pmu-events/arch/powerpc/power10/translation.json index 5a714e3dd71a..db3766dca07c 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/translation.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/translation.json @@ -1,56 +1,56 @@ [ { - "EventCode": "1F15E", + "EventCode": "0x1F15E", "EventName": "PM_MRK_START_PROBE_NOP_CMPL", "BriefDescription": "Marked Start probe nop (AND R0,R0,R0) completed." }, { - "EventCode": "20016", + "EventCode": "0x20016", "EventName": "PM_ST_FIN", "BriefDescription": "Store finish count. Includes speculative activity." }, { - "EventCode": "20018", + "EventCode": "0x20018", "EventName": "PM_ST_FWD", "BriefDescription": "Store forwards that finished." }, { - "EventCode": "2011C", + "EventCode": "0x2011C", "EventName": "PM_MRK_NTF_CYC", "BriefDescription": "Cycles during which the marked instruction is the oldest in the pipeline (NTF or NTC)." }, { - "EventCode": "2E01C", + "EventCode": "0x2E01C", "EventName": "PM_EXEC_STALL_TLBIE", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIE instruction executing in the Load Store Unit." }, { - "EventCode": "201E6", + "EventCode": "0x201E6", "EventName": "PM_THRESH_EXC_32", "BriefDescription": "Threshold counter exceeded a value of 32." }, { - "EventCode": "200F0", + "EventCode": "0x200F0", "EventName": "PM_ST_CMPL", "BriefDescription": "Stores completed from S2Q (2nd-level store queue). This event includes regular stores, stcx and cache inhibited stores. The following operations are excluded (pteupdate, snoop tlbie complete, store atomics, miso, load atomic payloads, tlbie, tlbsync, slbieg, isync, msgsnd, slbiag, cpabort, copy, tcheck, tend, stsync, dcbst, icbi, dcbf, hwsync, lwsync, ptesync, eieio, msgsync)." }, { - "EventCode": "200FE", + "EventCode": "0x200FE", "EventName": "PM_DATA_FROM_L2MISS", "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss." }, { - "EventCode": "30010", + "EventCode": "0x30010", "EventName": "PM_PMC2_OVERFLOW", "BriefDescription": "The event selected for PMC2 caused the event counter to overflow." }, { - "EventCode": "4D010", + "EventCode": "0x4D010", "EventName": "PM_PMC1_SAVED", "BriefDescription": "The conditions for the speculative event selected for PMC1 are met and PMC1 is charged." }, { - "EventCode": "4D05C", + "EventCode": "0x4D05C", "EventName": "PM_DPP_FLOP_CMPL", "BriefDescription": "Double-Precision or Quad-Precision instructions completed." } diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 7422b0ea8790..9604446f8360 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -960,7 +960,7 @@ static int get_maxfds(void) struct rlimit rlim; if (getrlimit(RLIMIT_NOFILE, &rlim) == 0) - return min((int)rlim.rlim_max / 2, 512); + return min(rlim.rlim_max / 2, (rlim_t)512); return 512; } diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index ddb52f748c8e..974f10e356f0 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -451,10 +451,10 @@ static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd, goto out; } - err = -1; link = bpf_program__attach(skel->progs.on_switch); - if (!link) { + if (IS_ERR(link)) { pr_err("Failed to attach leader program\n"); + err = PTR_ERR(link); goto out; } diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 12ee40284da0..2060bc122c53 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -40,7 +40,7 @@ struct ipv6_packet pkt_v6 = { .tcp.doff = 5, }; -static int settimeo(int fd, int timeout_ms) +int settimeo(int fd, int timeout_ms) { struct timeval timeout = { .tv_sec = 3 }; diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index 7205f8afdba1..5e0d51c07b63 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -33,6 +33,7 @@ struct ipv6_packet { } __packed; extern struct ipv6_packet pkt_v6; +int settimeo(int fd, int timeout_ms); int start_server(int family, int type, const char *addr, __u16 port, int timeout_ms); int connect_to_fd(int server_fd, int timeout_ms); diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index de78617f6550..f9a8ae331963 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -86,8 +86,9 @@ void test_ringbuf(void) const size_t rec_sz = BPF_RINGBUF_HDR_SZ + sizeof(struct sample); pthread_t thread; long bg_ret = -1; - int err, cnt; + int err, cnt, rb_fd; int page_size = getpagesize(); + void *mmap_ptr, *tmp_ptr; skel = test_ringbuf__open(); if (CHECK(!skel, "skel_open", "skeleton open failed\n")) @@ -101,6 +102,52 @@ void test_ringbuf(void) if (CHECK(err != 0, "skel_load", "skeleton load failed\n")) goto cleanup; + rb_fd = bpf_map__fd(skel->maps.ringbuf); + /* good read/write cons_pos */ + mmap_ptr = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, rb_fd, 0); + ASSERT_OK_PTR(mmap_ptr, "rw_cons_pos"); + tmp_ptr = mremap(mmap_ptr, page_size, 2 * page_size, MREMAP_MAYMOVE); + if (!ASSERT_ERR_PTR(tmp_ptr, "rw_extend")) + goto cleanup; + ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_EXEC), "exec_cons_pos_protect"); + ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_rw"); + + /* bad writeable prod_pos */ + mmap_ptr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, rb_fd, page_size); + err = -errno; + ASSERT_ERR_PTR(mmap_ptr, "wr_prod_pos"); + ASSERT_EQ(err, -EPERM, "wr_prod_pos_err"); + + /* bad writeable data pages */ + mmap_ptr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, rb_fd, 2 * page_size); + err = -errno; + ASSERT_ERR_PTR(mmap_ptr, "wr_data_page_one"); + ASSERT_EQ(err, -EPERM, "wr_data_page_one_err"); + mmap_ptr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, rb_fd, 3 * page_size); + ASSERT_ERR_PTR(mmap_ptr, "wr_data_page_two"); + mmap_ptr = mmap(NULL, 2 * page_size, PROT_WRITE, MAP_SHARED, rb_fd, 2 * page_size); + ASSERT_ERR_PTR(mmap_ptr, "wr_data_page_all"); + + /* good read-only pages */ + mmap_ptr = mmap(NULL, 4 * page_size, PROT_READ, MAP_SHARED, rb_fd, 0); + if (!ASSERT_OK_PTR(mmap_ptr, "ro_prod_pos")) + goto cleanup; + + ASSERT_ERR(mprotect(mmap_ptr, 4 * page_size, PROT_WRITE), "write_protect"); + ASSERT_ERR(mprotect(mmap_ptr, 4 * page_size, PROT_EXEC), "exec_protect"); + ASSERT_ERR_PTR(mremap(mmap_ptr, 0, 4 * page_size, MREMAP_MAYMOVE), "ro_remap"); + ASSERT_OK(munmap(mmap_ptr, 4 * page_size), "unmap_ro"); + + /* good read-only pages with initial offset */ + mmap_ptr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, rb_fd, page_size); + if (!ASSERT_OK_PTR(mmap_ptr, "ro_prod_pos")) + goto cleanup; + + ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_WRITE), "write_protect"); + ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_EXEC), "exec_protect"); + ASSERT_ERR_PTR(mremap(mmap_ptr, 0, 3 * page_size, MREMAP_MAYMOVE), "ro_remap"); + ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_ro"); + /* only trigger BPF program for current process */ skel->bss->pid = getpid(); diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c new file mode 100644 index 000000000000..5703c918812b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -0,0 +1,785 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + +/* + * This test sets up 3 netns (src <-> fwd <-> dst). There is no direct veth link + * between src and dst. The netns fwd has veth links to each src and dst. The + * client is in src and server in dst. The test installs a TC BPF program to each + * host facing veth in fwd which calls into i) bpf_redirect_neigh() to perform the + * neigh addr population and redirect or ii) bpf_redirect_peer() for namespace + * switch from ingress side; it also installs a checker prog on the egress side + * to drop unexpected traffic. + */ + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <linux/limits.h> +#include <linux/sysctl.h> +#include <linux/if_tun.h> +#include <linux/if.h> +#include <sched.h> +#include <stdbool.h> +#include <stdio.h> +#include <sys/stat.h> +#include <sys/mount.h> + +#include "test_progs.h" +#include "network_helpers.h" +#include "test_tc_neigh_fib.skel.h" +#include "test_tc_neigh.skel.h" +#include "test_tc_peer.skel.h" + +#define NS_SRC "ns_src" +#define NS_FWD "ns_fwd" +#define NS_DST "ns_dst" + +#define IP4_SRC "172.16.1.100" +#define IP4_DST "172.16.2.100" +#define IP4_TUN_SRC "172.17.1.100" +#define IP4_TUN_FWD "172.17.1.200" +#define IP4_PORT 9004 + +#define IP6_SRC "0::1:dead:beef:cafe" +#define IP6_DST "0::2:dead:beef:cafe" +#define IP6_TUN_SRC "1::1:dead:beef:cafe" +#define IP6_TUN_FWD "1::2:dead:beef:cafe" +#define IP6_PORT 9006 + +#define IP4_SLL "169.254.0.1" +#define IP4_DLL "169.254.0.2" +#define IP4_NET "169.254.0.0" + +#define MAC_DST_FWD "00:11:22:33:44:55" +#define MAC_DST "00:22:33:44:55:66" + +#define IFADDR_STR_LEN 18 +#define PING_ARGS "-i 0.2 -c 3 -w 10 -q" + +#define SRC_PROG_PIN_FILE "/sys/fs/bpf/test_tc_src" +#define DST_PROG_PIN_FILE "/sys/fs/bpf/test_tc_dst" +#define CHK_PROG_PIN_FILE "/sys/fs/bpf/test_tc_chk" + +#define TIMEOUT_MILLIS 10000 + +#define log_err(MSG, ...) \ + fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \ + __FILE__, __LINE__, strerror(errno), ##__VA_ARGS__) + +static const char * const namespaces[] = {NS_SRC, NS_FWD, NS_DST, NULL}; + +static int write_file(const char *path, const char *newval) +{ + FILE *f; + + f = fopen(path, "r+"); + if (!f) + return -1; + if (fwrite(newval, strlen(newval), 1, f) != 1) { + log_err("writing to %s failed", path); + fclose(f); + return -1; + } + fclose(f); + return 0; +} + +struct nstoken { + int orig_netns_fd; +}; + +static int setns_by_fd(int nsfd) +{ + int err; + + err = setns(nsfd, CLONE_NEWNET); + close(nsfd); + + if (!ASSERT_OK(err, "setns")) + return err; + + /* Switch /sys to the new namespace so that e.g. /sys/class/net + * reflects the devices in the new namespace. + */ + err = unshare(CLONE_NEWNS); + if (!ASSERT_OK(err, "unshare")) + return err; + + err = umount2("/sys", MNT_DETACH); + if (!ASSERT_OK(err, "umount2 /sys")) + return err; + + err = mount("sysfs", "/sys", "sysfs", 0, NULL); + if (!ASSERT_OK(err, "mount /sys")) + return err; + + err = mount("bpffs", "/sys/fs/bpf", "bpf", 0, NULL); + if (!ASSERT_OK(err, "mount /sys/fs/bpf")) + return err; + + return 0; +} + +/** + * open_netns() - Switch to specified network namespace by name. + * + * Returns token with which to restore the original namespace + * using close_netns(). + */ +static struct nstoken *open_netns(const char *name) +{ + int nsfd; + char nspath[PATH_MAX]; + int err; + struct nstoken *token; + + token = malloc(sizeof(struct nstoken)); + if (!ASSERT_OK_PTR(token, "malloc token")) + return NULL; + + token->orig_netns_fd = open("/proc/self/ns/net", O_RDONLY); + if (!ASSERT_GE(token->orig_netns_fd, 0, "open /proc/self/ns/net")) + goto fail; + + snprintf(nspath, sizeof(nspath), "%s/%s", "/var/run/netns", name); + nsfd = open(nspath, O_RDONLY | O_CLOEXEC); + if (!ASSERT_GE(nsfd, 0, "open netns fd")) + goto fail; + + err = setns_by_fd(nsfd); + if (!ASSERT_OK(err, "setns_by_fd")) + goto fail; + + return token; +fail: + free(token); + return NULL; +} + +static void close_netns(struct nstoken *token) +{ + ASSERT_OK(setns_by_fd(token->orig_netns_fd), "setns_by_fd"); + free(token); +} + +static int netns_setup_namespaces(const char *verb) +{ + const char * const *ns = namespaces; + char cmd[128]; + + while (*ns) { + snprintf(cmd, sizeof(cmd), "ip netns %s %s", verb, *ns); + if (!ASSERT_OK(system(cmd), cmd)) + return -1; + ns++; + } + return 0; +} + +struct netns_setup_result { + int ifindex_veth_src_fwd; + int ifindex_veth_dst_fwd; +}; + +static int get_ifaddr(const char *name, char *ifaddr) +{ + char path[PATH_MAX]; + FILE *f; + int ret; + + snprintf(path, PATH_MAX, "/sys/class/net/%s/address", name); + f = fopen(path, "r"); + if (!ASSERT_OK_PTR(f, path)) + return -1; + + ret = fread(ifaddr, 1, IFADDR_STR_LEN, f); + if (!ASSERT_EQ(ret, IFADDR_STR_LEN, "fread ifaddr")) { + fclose(f); + return -1; + } + fclose(f); + return 0; +} + +static int get_ifindex(const char *name) +{ + char path[PATH_MAX]; + char buf[32]; + FILE *f; + int ret; + + snprintf(path, PATH_MAX, "/sys/class/net/%s/ifindex", name); + f = fopen(path, "r"); + if (!ASSERT_OK_PTR(f, path)) + return -1; + + ret = fread(buf, 1, sizeof(buf), f); + if (!ASSERT_GT(ret, 0, "fread ifindex")) { + fclose(f); + return -1; + } + fclose(f); + return atoi(buf); +} + +#define SYS(fmt, ...) \ + ({ \ + char cmd[1024]; \ + snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__); \ + if (!ASSERT_OK(system(cmd), cmd)) \ + goto fail; \ + }) + +static int netns_setup_links_and_routes(struct netns_setup_result *result) +{ + struct nstoken *nstoken = NULL; + char veth_src_fwd_addr[IFADDR_STR_LEN+1] = {}; + + SYS("ip link add veth_src type veth peer name veth_src_fwd"); + SYS("ip link add veth_dst type veth peer name veth_dst_fwd"); + + SYS("ip link set veth_dst_fwd address " MAC_DST_FWD); + SYS("ip link set veth_dst address " MAC_DST); + + if (get_ifaddr("veth_src_fwd", veth_src_fwd_addr)) + goto fail; + + result->ifindex_veth_src_fwd = get_ifindex("veth_src_fwd"); + if (result->ifindex_veth_src_fwd < 0) + goto fail; + result->ifindex_veth_dst_fwd = get_ifindex("veth_dst_fwd"); + if (result->ifindex_veth_dst_fwd < 0) + goto fail; + + SYS("ip link set veth_src netns " NS_SRC); + SYS("ip link set veth_src_fwd netns " NS_FWD); + SYS("ip link set veth_dst_fwd netns " NS_FWD); + SYS("ip link set veth_dst netns " NS_DST); + + /** setup in 'src' namespace */ + nstoken = open_netns(NS_SRC); + if (!ASSERT_OK_PTR(nstoken, "setns src")) + goto fail; + + SYS("ip addr add " IP4_SRC "/32 dev veth_src"); + SYS("ip addr add " IP6_SRC "/128 dev veth_src nodad"); + SYS("ip link set dev veth_src up"); + + SYS("ip route add " IP4_DST "/32 dev veth_src scope global"); + SYS("ip route add " IP4_NET "/16 dev veth_src scope global"); + SYS("ip route add " IP6_DST "/128 dev veth_src scope global"); + + SYS("ip neigh add " IP4_DST " dev veth_src lladdr %s", + veth_src_fwd_addr); + SYS("ip neigh add " IP6_DST " dev veth_src lladdr %s", + veth_src_fwd_addr); + + close_netns(nstoken); + + /** setup in 'fwd' namespace */ + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + goto fail; + + /* The fwd netns automatically gets a v6 LL address / routes, but also + * needs v4 one in order to start ARP probing. IP4_NET route is added + * to the endpoints so that the ARP processing will reply. + */ + SYS("ip addr add " IP4_SLL "/32 dev veth_src_fwd"); + SYS("ip addr add " IP4_DLL "/32 dev veth_dst_fwd"); + SYS("ip link set dev veth_src_fwd up"); + SYS("ip link set dev veth_dst_fwd up"); + + SYS("ip route add " IP4_SRC "/32 dev veth_src_fwd scope global"); + SYS("ip route add " IP6_SRC "/128 dev veth_src_fwd scope global"); + SYS("ip route add " IP4_DST "/32 dev veth_dst_fwd scope global"); + SYS("ip route add " IP6_DST "/128 dev veth_dst_fwd scope global"); + + close_netns(nstoken); + + /** setup in 'dst' namespace */ + nstoken = open_netns(NS_DST); + if (!ASSERT_OK_PTR(nstoken, "setns dst")) + goto fail; + + SYS("ip addr add " IP4_DST "/32 dev veth_dst"); + SYS("ip addr add " IP6_DST "/128 dev veth_dst nodad"); + SYS("ip link set dev veth_dst up"); + + SYS("ip route add " IP4_SRC "/32 dev veth_dst scope global"); + SYS("ip route add " IP4_NET "/16 dev veth_dst scope global"); + SYS("ip route add " IP6_SRC "/128 dev veth_dst scope global"); + + SYS("ip neigh add " IP4_SRC " dev veth_dst lladdr " MAC_DST_FWD); + SYS("ip neigh add " IP6_SRC " dev veth_dst lladdr " MAC_DST_FWD); + + close_netns(nstoken); + + return 0; +fail: + if (nstoken) + close_netns(nstoken); + return -1; +} + +static int netns_load_bpf(void) +{ + SYS("tc qdisc add dev veth_src_fwd clsact"); + SYS("tc filter add dev veth_src_fwd ingress bpf da object-pinned " + SRC_PROG_PIN_FILE); + SYS("tc filter add dev veth_src_fwd egress bpf da object-pinned " + CHK_PROG_PIN_FILE); + + SYS("tc qdisc add dev veth_dst_fwd clsact"); + SYS("tc filter add dev veth_dst_fwd ingress bpf da object-pinned " + DST_PROG_PIN_FILE); + SYS("tc filter add dev veth_dst_fwd egress bpf da object-pinned " + CHK_PROG_PIN_FILE); + + return 0; +fail: + return -1; +} + +static void test_tcp(int family, const char *addr, __u16 port) +{ + int listen_fd = -1, accept_fd = -1, client_fd = -1; + char buf[] = "testing testing"; + int n; + struct nstoken *nstoken; + + nstoken = open_netns(NS_DST); + if (!ASSERT_OK_PTR(nstoken, "setns dst")) + return; + + listen_fd = start_server(family, SOCK_STREAM, addr, port, 0); + if (!ASSERT_GE(listen_fd, 0, "listen")) + goto done; + + close_netns(nstoken); + nstoken = open_netns(NS_SRC); + if (!ASSERT_OK_PTR(nstoken, "setns src")) + goto done; + + client_fd = connect_to_fd(listen_fd, TIMEOUT_MILLIS); + if (!ASSERT_GE(client_fd, 0, "connect_to_fd")) + goto done; + + accept_fd = accept(listen_fd, NULL, NULL); + if (!ASSERT_GE(accept_fd, 0, "accept")) + goto done; + + if (!ASSERT_OK(settimeo(accept_fd, TIMEOUT_MILLIS), "settimeo")) + goto done; + + n = write(client_fd, buf, sizeof(buf)); + if (!ASSERT_EQ(n, sizeof(buf), "send to server")) + goto done; + + n = read(accept_fd, buf, sizeof(buf)); + ASSERT_EQ(n, sizeof(buf), "recv from server"); + +done: + if (nstoken) + close_netns(nstoken); + if (listen_fd >= 0) + close(listen_fd); + if (accept_fd >= 0) + close(accept_fd); + if (client_fd >= 0) + close(client_fd); +} + +static int test_ping(int family, const char *addr) +{ + const char *ping = family == AF_INET6 ? "ping6" : "ping"; + + SYS("ip netns exec " NS_SRC " %s " PING_ARGS " %s > /dev/null", ping, addr); + return 0; +fail: + return -1; +} + +static void test_connectivity(void) +{ + test_tcp(AF_INET, IP4_DST, IP4_PORT); + test_ping(AF_INET, IP4_DST); + test_tcp(AF_INET6, IP6_DST, IP6_PORT); + test_ping(AF_INET6, IP6_DST); +} + +static int set_forwarding(bool enable) +{ + int err; + + err = write_file("/proc/sys/net/ipv4/ip_forward", enable ? "1" : "0"); + if (!ASSERT_OK(err, "set ipv4.ip_forward=0")) + return err; + + err = write_file("/proc/sys/net/ipv6/conf/all/forwarding", enable ? "1" : "0"); + if (!ASSERT_OK(err, "set ipv6.forwarding=0")) + return err; + + return 0; +} + +static void test_tc_redirect_neigh_fib(struct netns_setup_result *setup_result) +{ + struct nstoken *nstoken = NULL; + struct test_tc_neigh_fib *skel = NULL; + int err; + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + return; + + skel = test_tc_neigh_fib__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_neigh_fib__open")) + goto done; + + if (!ASSERT_OK(test_tc_neigh_fib__load(skel), "test_tc_neigh_fib__load")) + goto done; + + err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_dst, DST_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE)) + goto done; + + if (netns_load_bpf()) + goto done; + + /* bpf_fib_lookup() checks if forwarding is enabled */ + if (!ASSERT_OK(set_forwarding(true), "enable forwarding")) + goto done; + + test_connectivity(); + +done: + if (skel) + test_tc_neigh_fib__destroy(skel); + close_netns(nstoken); +} + +static void test_tc_redirect_neigh(struct netns_setup_result *setup_result) +{ + struct nstoken *nstoken = NULL; + struct test_tc_neigh *skel = NULL; + int err; + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + return; + + skel = test_tc_neigh__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_neigh__open")) + goto done; + + skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + + err = test_tc_neigh__load(skel); + if (!ASSERT_OK(err, "test_tc_neigh__load")) + goto done; + + err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_dst, DST_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE)) + goto done; + + if (netns_load_bpf()) + goto done; + + if (!ASSERT_OK(set_forwarding(false), "disable forwarding")) + goto done; + + test_connectivity(); + +done: + if (skel) + test_tc_neigh__destroy(skel); + close_netns(nstoken); +} + +static void test_tc_redirect_peer(struct netns_setup_result *setup_result) +{ + struct nstoken *nstoken; + struct test_tc_peer *skel; + int err; + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + return; + + skel = test_tc_peer__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_peer__open")) + goto done; + + skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + + err = test_tc_peer__load(skel); + if (!ASSERT_OK(err, "test_tc_peer__load")) + goto done; + + err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE)) + goto done; + + err = bpf_program__pin(skel->progs.tc_dst, DST_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE)) + goto done; + + if (netns_load_bpf()) + goto done; + + if (!ASSERT_OK(set_forwarding(false), "disable forwarding")) + goto done; + + test_connectivity(); + +done: + if (skel) + test_tc_peer__destroy(skel); + close_netns(nstoken); +} + +static int tun_open(char *name) +{ + struct ifreq ifr; + int fd, err; + + fd = open("/dev/net/tun", O_RDWR); + if (!ASSERT_GE(fd, 0, "open /dev/net/tun")) + return -1; + + memset(&ifr, 0, sizeof(ifr)); + + ifr.ifr_flags = IFF_TUN | IFF_NO_PI; + if (*name) + strncpy(ifr.ifr_name, name, IFNAMSIZ); + + err = ioctl(fd, TUNSETIFF, &ifr); + if (!ASSERT_OK(err, "ioctl TUNSETIFF")) + goto fail; + + SYS("ip link set dev %s up", name); + + return fd; +fail: + close(fd); + return -1; +} + +#define MAX(a, b) ((a) > (b) ? (a) : (b)) +enum { + SRC_TO_TARGET = 0, + TARGET_TO_SRC = 1, +}; + +static int tun_relay_loop(int src_fd, int target_fd) +{ + fd_set rfds, wfds; + + FD_ZERO(&rfds); + FD_ZERO(&wfds); + + for (;;) { + char buf[1500]; + int direction, nread, nwrite; + + FD_SET(src_fd, &rfds); + FD_SET(target_fd, &rfds); + + if (select(1 + MAX(src_fd, target_fd), &rfds, NULL, NULL, NULL) < 0) { + log_err("select failed"); + return 1; + } + + direction = FD_ISSET(src_fd, &rfds) ? SRC_TO_TARGET : TARGET_TO_SRC; + + nread = read(direction == SRC_TO_TARGET ? src_fd : target_fd, buf, sizeof(buf)); + if (nread < 0) { + log_err("read failed"); + return 1; + } + + nwrite = write(direction == SRC_TO_TARGET ? target_fd : src_fd, buf, nread); + if (nwrite != nread) { + log_err("write failed"); + return 1; + } + } +} + +static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result) +{ + struct test_tc_peer *skel = NULL; + struct nstoken *nstoken = NULL; + int err; + int tunnel_pid = -1; + int src_fd, target_fd; + int ifindex; + + /* Start a L3 TUN/TAP tunnel between the src and dst namespaces. + * This test is using TUN/TAP instead of e.g. IPIP or GRE tunnel as those + * expose the L2 headers encapsulating the IP packet to BPF and hence + * don't have skb in suitable state for this test. Alternative to TUN/TAP + * would be e.g. Wireguard which would appear as a pure L3 device to BPF, + * but that requires much more complicated setup. + */ + nstoken = open_netns(NS_SRC); + if (!ASSERT_OK_PTR(nstoken, "setns " NS_SRC)) + return; + + src_fd = tun_open("tun_src"); + if (!ASSERT_GE(src_fd, 0, "tun_open tun_src")) + goto fail; + + close_netns(nstoken); + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns " NS_FWD)) + goto fail; + + target_fd = tun_open("tun_fwd"); + if (!ASSERT_GE(target_fd, 0, "tun_open tun_fwd")) + goto fail; + + tunnel_pid = fork(); + if (!ASSERT_GE(tunnel_pid, 0, "fork tun_relay_loop")) + goto fail; + + if (tunnel_pid == 0) + exit(tun_relay_loop(src_fd, target_fd)); + + skel = test_tc_peer__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_peer__open")) + goto fail; + + ifindex = get_ifindex("tun_fwd"); + if (!ASSERT_GE(ifindex, 0, "get_ifindex tun_fwd")) + goto fail; + + skel->rodata->IFINDEX_SRC = ifindex; + skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + + err = test_tc_peer__load(skel); + if (!ASSERT_OK(err, "test_tc_peer__load")) + goto fail; + + err = bpf_program__pin(skel->progs.tc_src_l3, SRC_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE)) + goto fail; + + err = bpf_program__pin(skel->progs.tc_dst_l3, DST_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE)) + goto fail; + + err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE); + if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE)) + goto fail; + + /* Load "tc_src_l3" to the tun_fwd interface to redirect packets + * towards dst, and "tc_dst" to redirect packets + * and "tc_chk" on veth_dst_fwd to drop non-redirected packets. + */ + SYS("tc qdisc add dev tun_fwd clsact"); + SYS("tc filter add dev tun_fwd ingress bpf da object-pinned " + SRC_PROG_PIN_FILE); + + SYS("tc qdisc add dev veth_dst_fwd clsact"); + SYS("tc filter add dev veth_dst_fwd ingress bpf da object-pinned " + DST_PROG_PIN_FILE); + SYS("tc filter add dev veth_dst_fwd egress bpf da object-pinned " + CHK_PROG_PIN_FILE); + + /* Setup route and neigh tables */ + SYS("ip -netns " NS_SRC " addr add dev tun_src " IP4_TUN_SRC "/24"); + SYS("ip -netns " NS_FWD " addr add dev tun_fwd " IP4_TUN_FWD "/24"); + + SYS("ip -netns " NS_SRC " addr add dev tun_src " IP6_TUN_SRC "/64 nodad"); + SYS("ip -netns " NS_FWD " addr add dev tun_fwd " IP6_TUN_FWD "/64 nodad"); + + SYS("ip -netns " NS_SRC " route del " IP4_DST "/32 dev veth_src scope global"); + SYS("ip -netns " NS_SRC " route add " IP4_DST "/32 via " IP4_TUN_FWD + " dev tun_src scope global"); + SYS("ip -netns " NS_DST " route add " IP4_TUN_SRC "/32 dev veth_dst scope global"); + SYS("ip -netns " NS_SRC " route del " IP6_DST "/128 dev veth_src scope global"); + SYS("ip -netns " NS_SRC " route add " IP6_DST "/128 via " IP6_TUN_FWD + " dev tun_src scope global"); + SYS("ip -netns " NS_DST " route add " IP6_TUN_SRC "/128 dev veth_dst scope global"); + + SYS("ip -netns " NS_DST " neigh add " IP4_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD); + SYS("ip -netns " NS_DST " neigh add " IP6_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD); + + if (!ASSERT_OK(set_forwarding(false), "disable forwarding")) + goto fail; + + test_connectivity(); + +fail: + if (tunnel_pid > 0) { + kill(tunnel_pid, SIGTERM); + waitpid(tunnel_pid, NULL, 0); + } + if (src_fd >= 0) + close(src_fd); + if (target_fd >= 0) + close(target_fd); + if (skel) + test_tc_peer__destroy(skel); + if (nstoken) + close_netns(nstoken); +} + +#define RUN_TEST(name) \ + ({ \ + struct netns_setup_result setup_result; \ + if (test__start_subtest(#name)) \ + if (ASSERT_OK(netns_setup_namespaces("add"), "setup namespaces")) { \ + if (ASSERT_OK(netns_setup_links_and_routes(&setup_result), \ + "setup links and routes")) \ + test_ ## name(&setup_result); \ + netns_setup_namespaces("delete"); \ + } \ + }) + +static void *test_tc_redirect_run_tests(void *arg) +{ + RUN_TEST(tc_redirect_peer); + RUN_TEST(tc_redirect_peer_l3); + RUN_TEST(tc_redirect_neigh); + RUN_TEST(tc_redirect_neigh_fib); + return NULL; +} + +void test_tc_redirect(void) +{ + pthread_t test_thread; + int err; + + /* Run the tests in their own thread to isolate the namespace changes + * so they do not affect the environment of other tests. + * (specifically needed because of unshare(CLONE_NEWNS) in open_netns()) + */ + err = pthread_create(&test_thread, NULL, &test_tc_redirect_run_tests, NULL); + if (ASSERT_OK(err, "pthread_create")) + ASSERT_OK(pthread_join(test_thread, NULL), "pthread_join"); +} diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh.c b/tools/testing/selftests/bpf/progs/test_tc_neigh.c index b985ac4e7a81..0c93d326a663 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_neigh.c +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh.c @@ -33,17 +33,8 @@ a.s6_addr32[3] == b.s6_addr32[3]) #endif -enum { - dev_src, - dev_dst, -}; - -struct bpf_map_def SEC("maps") ifindex_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 2, -}; +volatile const __u32 IFINDEX_SRC; +volatile const __u32 IFINDEX_DST; static __always_inline bool is_remote_ep_v4(struct __sk_buff *skb, __be32 addr) @@ -79,14 +70,8 @@ static __always_inline bool is_remote_ep_v6(struct __sk_buff *skb, return v6_equal(ip6h->daddr, addr); } -static __always_inline int get_dev_ifindex(int which) -{ - int *ifindex = bpf_map_lookup_elem(&ifindex_map, &which); - - return ifindex ? *ifindex : 0; -} - -SEC("chk_egress") int tc_chk(struct __sk_buff *skb) +SEC("classifier/chk_egress") +int tc_chk(struct __sk_buff *skb) { void *data_end = ctx_ptr(skb->data_end); void *data = ctx_ptr(skb->data); @@ -98,7 +83,8 @@ SEC("chk_egress") int tc_chk(struct __sk_buff *skb) return !raw[0] && !raw[1] && !raw[2] ? TC_ACT_SHOT : TC_ACT_OK; } -SEC("dst_ingress") int tc_dst(struct __sk_buff *skb) +SEC("classifier/dst_ingress") +int tc_dst(struct __sk_buff *skb) { __u8 zero[ETH_ALEN * 2]; bool redirect = false; @@ -119,10 +105,11 @@ SEC("dst_ingress") int tc_dst(struct __sk_buff *skb) if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0) return TC_ACT_SHOT; - return bpf_redirect_neigh(get_dev_ifindex(dev_src), NULL, 0, 0); + return bpf_redirect_neigh(IFINDEX_SRC, NULL, 0, 0); } -SEC("src_ingress") int tc_src(struct __sk_buff *skb) +SEC("classifier/src_ingress") +int tc_src(struct __sk_buff *skb) { __u8 zero[ETH_ALEN * 2]; bool redirect = false; @@ -143,7 +130,7 @@ SEC("src_ingress") int tc_src(struct __sk_buff *skb) if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0) return TC_ACT_SHOT; - return bpf_redirect_neigh(get_dev_ifindex(dev_dst), NULL, 0, 0); + return bpf_redirect_neigh(IFINDEX_DST, NULL, 0, 0); } char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c index d82ed3457030..f7ab69cf018e 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c @@ -75,7 +75,8 @@ static __always_inline int fill_fib_params_v6(struct __sk_buff *skb, return 0; } -SEC("chk_egress") int tc_chk(struct __sk_buff *skb) +SEC("classifier/chk_egress") +int tc_chk(struct __sk_buff *skb) { void *data_end = ctx_ptr(skb->data_end); void *data = ctx_ptr(skb->data); @@ -142,12 +143,14 @@ static __always_inline int tc_redir(struct __sk_buff *skb) /* these are identical, but keep them separate for compatibility with the * section names expected by test_tc_redirect.sh */ -SEC("dst_ingress") int tc_dst(struct __sk_buff *skb) +SEC("classifier/dst_ingress") +int tc_dst(struct __sk_buff *skb) { return tc_redir(skb); } -SEC("src_ingress") int tc_src(struct __sk_buff *skb) +SEC("classifier/src_ingress") +int tc_src(struct __sk_buff *skb) { return tc_redir(skb); } diff --git a/tools/testing/selftests/bpf/progs/test_tc_peer.c b/tools/testing/selftests/bpf/progs/test_tc_peer.c index fc84a7685aa2..fe818cd5f010 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_peer.c +++ b/tools/testing/selftests/bpf/progs/test_tc_peer.c @@ -5,41 +5,59 @@ #include <linux/bpf.h> #include <linux/stddef.h> #include <linux/pkt_cls.h> +#include <linux/if_ether.h> +#include <linux/ip.h> #include <bpf/bpf_helpers.h> -enum { - dev_src, - dev_dst, -}; +volatile const __u32 IFINDEX_SRC; +volatile const __u32 IFINDEX_DST; -struct bpf_map_def SEC("maps") ifindex_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 2, -}; +static const __u8 src_mac[] = {0x00, 0x11, 0x22, 0x33, 0x44, 0x55}; +static const __u8 dst_mac[] = {0x00, 0x22, 0x33, 0x44, 0x55, 0x66}; -static __always_inline int get_dev_ifindex(int which) +SEC("classifier/chk_egress") +int tc_chk(struct __sk_buff *skb) { - int *ifindex = bpf_map_lookup_elem(&ifindex_map, &which); + return TC_ACT_SHOT; +} - return ifindex ? *ifindex : 0; +SEC("classifier/dst_ingress") +int tc_dst(struct __sk_buff *skb) +{ + return bpf_redirect_peer(IFINDEX_SRC, 0); } -SEC("chk_egress") int tc_chk(struct __sk_buff *skb) +SEC("classifier/src_ingress") +int tc_src(struct __sk_buff *skb) { - return TC_ACT_SHOT; + return bpf_redirect_peer(IFINDEX_DST, 0); } -SEC("dst_ingress") int tc_dst(struct __sk_buff *skb) +SEC("classifier/dst_ingress_l3") +int tc_dst_l3(struct __sk_buff *skb) { - return bpf_redirect_peer(get_dev_ifindex(dev_src), 0); + return bpf_redirect(IFINDEX_SRC, 0); } -SEC("src_ingress") int tc_src(struct __sk_buff *skb) +SEC("classifier/src_ingress_l3") +int tc_src_l3(struct __sk_buff *skb) { - return bpf_redirect_peer(get_dev_ifindex(dev_dst), 0); + __u16 proto = skb->protocol; + + if (bpf_skb_change_head(skb, ETH_HLEN, 0) != 0) + return TC_ACT_SHOT; + + if (bpf_skb_store_bytes(skb, 0, &src_mac, ETH_ALEN, 0) != 0) + return TC_ACT_SHOT; + + if (bpf_skb_store_bytes(skb, ETH_ALEN, &dst_mac, ETH_ALEN, 0) != 0) + return TC_ACT_SHOT; + + if (bpf_skb_store_bytes(skb, ETH_ALEN + ETH_ALEN, &proto, sizeof(__u16), 0) != 0) + return TC_ACT_SHOT; + + return bpf_redirect_peer(IFINDEX_DST, 0); } char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_tc_redirect.sh b/tools/testing/selftests/bpf/test_tc_redirect.sh deleted file mode 100755 index 8868aa1ca902..000000000000 --- a/tools/testing/selftests/bpf/test_tc_redirect.sh +++ /dev/null @@ -1,216 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# This test sets up 3 netns (src <-> fwd <-> dst). There is no direct veth link -# between src and dst. The netns fwd has veth links to each src and dst. The -# client is in src and server in dst. The test installs a TC BPF program to each -# host facing veth in fwd which calls into i) bpf_redirect_neigh() to perform the -# neigh addr population and redirect or ii) bpf_redirect_peer() for namespace -# switch from ingress side; it also installs a checker prog on the egress side -# to drop unexpected traffic. - -if [[ $EUID -ne 0 ]]; then - echo "This script must be run as root" - echo "FAIL" - exit 1 -fi - -# check that needed tools are present -command -v nc >/dev/null 2>&1 || \ - { echo >&2 "nc is not available"; exit 1; } -command -v dd >/dev/null 2>&1 || \ - { echo >&2 "dd is not available"; exit 1; } -command -v timeout >/dev/null 2>&1 || \ - { echo >&2 "timeout is not available"; exit 1; } -command -v ping >/dev/null 2>&1 || \ - { echo >&2 "ping is not available"; exit 1; } -if command -v ping6 >/dev/null 2>&1; then PING6=ping6; else PING6=ping; fi -command -v perl >/dev/null 2>&1 || \ - { echo >&2 "perl is not available"; exit 1; } -command -v jq >/dev/null 2>&1 || \ - { echo >&2 "jq is not available"; exit 1; } -command -v bpftool >/dev/null 2>&1 || \ - { echo >&2 "bpftool is not available"; exit 1; } - -readonly GREEN='\033[0;92m' -readonly RED='\033[0;31m' -readonly NC='\033[0m' # No Color - -readonly PING_ARG="-c 3 -w 10 -q" - -readonly TIMEOUT=10 - -readonly NS_SRC="ns-src-$(mktemp -u XXXXXX)" -readonly NS_FWD="ns-fwd-$(mktemp -u XXXXXX)" -readonly NS_DST="ns-dst-$(mktemp -u XXXXXX)" - -readonly IP4_SRC="172.16.1.100" -readonly IP4_DST="172.16.2.100" - -readonly IP6_SRC="::1:dead:beef:cafe" -readonly IP6_DST="::2:dead:beef:cafe" - -readonly IP4_SLL="169.254.0.1" -readonly IP4_DLL="169.254.0.2" -readonly IP4_NET="169.254.0.0" - -netns_cleanup() -{ - ip netns del ${NS_SRC} - ip netns del ${NS_FWD} - ip netns del ${NS_DST} -} - -netns_setup() -{ - ip netns add "${NS_SRC}" - ip netns add "${NS_FWD}" - ip netns add "${NS_DST}" - - ip link add veth_src type veth peer name veth_src_fwd - ip link add veth_dst type veth peer name veth_dst_fwd - - ip link set veth_src netns ${NS_SRC} - ip link set veth_src_fwd netns ${NS_FWD} - - ip link set veth_dst netns ${NS_DST} - ip link set veth_dst_fwd netns ${NS_FWD} - - ip -netns ${NS_SRC} addr add ${IP4_SRC}/32 dev veth_src - ip -netns ${NS_DST} addr add ${IP4_DST}/32 dev veth_dst - - # The fwd netns automatically get a v6 LL address / routes, but also - # needs v4 one in order to start ARP probing. IP4_NET route is added - # to the endpoints so that the ARP processing will reply. - - ip -netns ${NS_FWD} addr add ${IP4_SLL}/32 dev veth_src_fwd - ip -netns ${NS_FWD} addr add ${IP4_DLL}/32 dev veth_dst_fwd - - ip -netns ${NS_SRC} addr add ${IP6_SRC}/128 dev veth_src nodad - ip -netns ${NS_DST} addr add ${IP6_DST}/128 dev veth_dst nodad - - ip -netns ${NS_SRC} link set dev veth_src up - ip -netns ${NS_FWD} link set dev veth_src_fwd up - - ip -netns ${NS_DST} link set dev veth_dst up - ip -netns ${NS_FWD} link set dev veth_dst_fwd up - - ip -netns ${NS_SRC} route add ${IP4_DST}/32 dev veth_src scope global - ip -netns ${NS_SRC} route add ${IP4_NET}/16 dev veth_src scope global - ip -netns ${NS_FWD} route add ${IP4_SRC}/32 dev veth_src_fwd scope global - - ip -netns ${NS_SRC} route add ${IP6_DST}/128 dev veth_src scope global - ip -netns ${NS_FWD} route add ${IP6_SRC}/128 dev veth_src_fwd scope global - - ip -netns ${NS_DST} route add ${IP4_SRC}/32 dev veth_dst scope global - ip -netns ${NS_DST} route add ${IP4_NET}/16 dev veth_dst scope global - ip -netns ${NS_FWD} route add ${IP4_DST}/32 dev veth_dst_fwd scope global - - ip -netns ${NS_DST} route add ${IP6_SRC}/128 dev veth_dst scope global - ip -netns ${NS_FWD} route add ${IP6_DST}/128 dev veth_dst_fwd scope global - - fmac_src=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_src_fwd/address) - fmac_dst=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_dst_fwd/address) - - ip -netns ${NS_SRC} neigh add ${IP4_DST} dev veth_src lladdr $fmac_src - ip -netns ${NS_DST} neigh add ${IP4_SRC} dev veth_dst lladdr $fmac_dst - - ip -netns ${NS_SRC} neigh add ${IP6_DST} dev veth_src lladdr $fmac_src - ip -netns ${NS_DST} neigh add ${IP6_SRC} dev veth_dst lladdr $fmac_dst -} - -netns_test_connectivity() -{ - set +e - - ip netns exec ${NS_DST} bash -c "nc -4 -l -p 9004 &" - ip netns exec ${NS_DST} bash -c "nc -6 -l -p 9006 &" - - TEST="TCPv4 connectivity test" - ip netns exec ${NS_SRC} bash -c "timeout ${TIMEOUT} dd if=/dev/zero bs=1000 count=100 > /dev/tcp/${IP4_DST}/9004" - if [ $? -ne 0 ]; then - echo -e "${TEST}: ${RED}FAIL${NC}" - exit 1 - fi - echo -e "${TEST}: ${GREEN}PASS${NC}" - - TEST="TCPv6 connectivity test" - ip netns exec ${NS_SRC} bash -c "timeout ${TIMEOUT} dd if=/dev/zero bs=1000 count=100 > /dev/tcp/${IP6_DST}/9006" - if [ $? -ne 0 ]; then - echo -e "${TEST}: ${RED}FAIL${NC}" - exit 1 - fi - echo -e "${TEST}: ${GREEN}PASS${NC}" - - TEST="ICMPv4 connectivity test" - ip netns exec ${NS_SRC} ping $PING_ARG ${IP4_DST} - if [ $? -ne 0 ]; then - echo -e "${TEST}: ${RED}FAIL${NC}" - exit 1 - fi - echo -e "${TEST}: ${GREEN}PASS${NC}" - - TEST="ICMPv6 connectivity test" - ip netns exec ${NS_SRC} $PING6 $PING_ARG ${IP6_DST} - if [ $? -ne 0 ]; then - echo -e "${TEST}: ${RED}FAIL${NC}" - exit 1 - fi - echo -e "${TEST}: ${GREEN}PASS${NC}" - - set -e -} - -hex_mem_str() -{ - perl -e 'print join(" ", unpack("(H2)8", pack("L", @ARGV)))' $1 -} - -netns_setup_bpf() -{ - local obj=$1 - local use_forwarding=${2:-0} - - ip netns exec ${NS_FWD} tc qdisc add dev veth_src_fwd clsact - ip netns exec ${NS_FWD} tc filter add dev veth_src_fwd ingress bpf da obj $obj sec src_ingress - ip netns exec ${NS_FWD} tc filter add dev veth_src_fwd egress bpf da obj $obj sec chk_egress - - ip netns exec ${NS_FWD} tc qdisc add dev veth_dst_fwd clsact - ip netns exec ${NS_FWD} tc filter add dev veth_dst_fwd ingress bpf da obj $obj sec dst_ingress - ip netns exec ${NS_FWD} tc filter add dev veth_dst_fwd egress bpf da obj $obj sec chk_egress - - if [ "$use_forwarding" -eq "1" ]; then - # bpf_fib_lookup() checks if forwarding is enabled - ip netns exec ${NS_FWD} sysctl -w net.ipv4.ip_forward=1 - ip netns exec ${NS_FWD} sysctl -w net.ipv6.conf.veth_dst_fwd.forwarding=1 - ip netns exec ${NS_FWD} sysctl -w net.ipv6.conf.veth_src_fwd.forwarding=1 - return 0 - fi - - veth_src=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_src_fwd/ifindex) - veth_dst=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_dst_fwd/ifindex) - - progs=$(ip netns exec ${NS_FWD} bpftool net --json | jq -r '.[] | .tc | map(.id) | .[]') - for prog in $progs; do - map=$(bpftool prog show id $prog --json | jq -r '.map_ids | .? | .[]') - if [ ! -z "$map" ]; then - bpftool map update id $map key hex $(hex_mem_str 0) value hex $(hex_mem_str $veth_src) - bpftool map update id $map key hex $(hex_mem_str 1) value hex $(hex_mem_str $veth_dst) - fi - done -} - -trap netns_cleanup EXIT -set -e - -netns_setup -netns_setup_bpf test_tc_neigh.o -netns_test_connectivity -netns_cleanup -netns_setup -netns_setup_bpf test_tc_neigh_fib.o 1 -netns_test_connectivity -netns_cleanup -netns_setup -netns_setup_bpf test_tc_peer.o -netns_test_connectivity diff --git a/tools/testing/selftests/bpf/verifier/stack_ptr.c b/tools/testing/selftests/bpf/verifier/stack_ptr.c index 07eaa04412ae..8ab94d65f3d5 100644 --- a/tools/testing/selftests/bpf/verifier/stack_ptr.c +++ b/tools/testing/selftests/bpf/verifier/stack_ptr.c @@ -295,8 +295,6 @@ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), BPF_EXIT_INSN(), }, - .result_unpriv = REJECT, - .errstr_unpriv = "invalid write to stack R1 off=0 size=1", .result = ACCEPT, .retval = 42, }, diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index e5913fd3b903..7ae2859d495c 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -300,8 +300,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -371,8 +369,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -472,8 +468,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -766,8 +760,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index bd83158e0e0b..524c857a049c 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -41,5 +41,6 @@ /kvm_create_max_vcpus /kvm_page_table_test /memslot_modification_stress_test +/memslot_perf_test /set_memory_region_test /steal_time diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index e439d027939d..daaee1888b12 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -33,7 +33,7 @@ ifeq ($(ARCH),s390) UNAME_M := s390x endif -LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c +LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c @@ -74,6 +74,7 @@ TEST_GEN_PROGS_x86_64 += hardware_disable_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += kvm_page_table_test TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test +TEST_GEN_PROGS_x86_64 += memslot_perf_test TEST_GEN_PROGS_x86_64 += set_memory_region_test TEST_GEN_PROGS_x86_64 += steal_time diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 5f7a229c3af1..b74704305835 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -9,6 +9,7 @@ #define _GNU_SOURCE /* for pipe2 */ +#include <inttypes.h> #include <stdio.h> #include <stdlib.h> #include <time.h> @@ -38,6 +39,7 @@ static int nr_vcpus = 1; static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; +static size_t demand_paging_size; static char *guest_data_prototype; static void *vcpu_worker(void *data) @@ -71,36 +73,51 @@ static void *vcpu_worker(void *data) return NULL; } -static int handle_uffd_page_request(int uffd, uint64_t addr) +static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr) { - pid_t tid; + pid_t tid = syscall(__NR_gettid); struct timespec start; struct timespec ts_diff; - struct uffdio_copy copy; int r; - tid = syscall(__NR_gettid); + clock_gettime(CLOCK_MONOTONIC, &start); - copy.src = (uint64_t)guest_data_prototype; - copy.dst = addr; - copy.len = perf_test_args.host_page_size; - copy.mode = 0; + if (uffd_mode == UFFDIO_REGISTER_MODE_MISSING) { + struct uffdio_copy copy; - clock_gettime(CLOCK_MONOTONIC, &start); + copy.src = (uint64_t)guest_data_prototype; + copy.dst = addr; + copy.len = demand_paging_size; + copy.mode = 0; - r = ioctl(uffd, UFFDIO_COPY, ©); - if (r == -1) { - pr_info("Failed Paged in 0x%lx from thread %d with errno: %d\n", - addr, tid, errno); - return r; + r = ioctl(uffd, UFFDIO_COPY, ©); + if (r == -1) { + pr_info("Failed UFFDIO_COPY in 0x%lx from thread %d with errno: %d\n", + addr, tid, errno); + return r; + } + } else if (uffd_mode == UFFDIO_REGISTER_MODE_MINOR) { + struct uffdio_continue cont = {0}; + + cont.range.start = addr; + cont.range.len = demand_paging_size; + + r = ioctl(uffd, UFFDIO_CONTINUE, &cont); + if (r == -1) { + pr_info("Failed UFFDIO_CONTINUE in 0x%lx from thread %d with errno: %d\n", + addr, tid, errno); + return r; + } + } else { + TEST_FAIL("Invalid uffd mode %d", uffd_mode); } ts_diff = timespec_elapsed(start); - PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid, + PER_PAGE_DEBUG("UFFD page-in %d \t%ld ns\n", tid, timespec_to_ns(ts_diff)); PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n", - perf_test_args.host_page_size, addr, tid); + demand_paging_size, addr, tid); return 0; } @@ -108,6 +125,7 @@ static int handle_uffd_page_request(int uffd, uint64_t addr) bool quit_uffd_thread; struct uffd_handler_args { + int uffd_mode; int uffd; int pipefd; useconds_t delay; @@ -169,7 +187,7 @@ static void *uffd_handler_thread_fn(void *arg) if (r == -1) { if (errno == EAGAIN) continue; - pr_info("Read of uffd gor errno %d", errno); + pr_info("Read of uffd got errno %d\n", errno); return NULL; } @@ -184,7 +202,7 @@ static void *uffd_handler_thread_fn(void *arg) if (delay) usleep(delay); addr = msg.arg.pagefault.address; - r = handle_uffd_page_request(uffd, addr); + r = handle_uffd_page_request(uffd_args->uffd_mode, uffd, addr); if (r < 0) return NULL; pages++; @@ -198,43 +216,53 @@ static void *uffd_handler_thread_fn(void *arg) return NULL; } -static int setup_demand_paging(struct kvm_vm *vm, - pthread_t *uffd_handler_thread, int pipefd, - useconds_t uffd_delay, - struct uffd_handler_args *uffd_args, - void *hva, uint64_t len) +static void setup_demand_paging(struct kvm_vm *vm, + pthread_t *uffd_handler_thread, int pipefd, + int uffd_mode, useconds_t uffd_delay, + struct uffd_handler_args *uffd_args, + void *hva, void *alias, uint64_t len) { + bool is_minor = (uffd_mode == UFFDIO_REGISTER_MODE_MINOR); int uffd; struct uffdio_api uffdio_api; struct uffdio_register uffdio_register; + uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY; - uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); - if (uffd == -1) { - pr_info("uffd creation failed\n"); - return -1; + PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n", + is_minor ? "MINOR" : "MISSING", + is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY"); + + /* In order to get minor faults, prefault via the alias. */ + if (is_minor) { + size_t p; + + expected_ioctls = ((uint64_t) 1) << _UFFDIO_CONTINUE; + + TEST_ASSERT(alias != NULL, "Alias required for minor faults"); + for (p = 0; p < (len / demand_paging_size); ++p) { + memcpy(alias + (p * demand_paging_size), + guest_data_prototype, demand_paging_size); + } } + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + TEST_ASSERT(uffd >= 0, "uffd creation failed, errno: %d", errno); + uffdio_api.api = UFFD_API; uffdio_api.features = 0; - if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) { - pr_info("ioctl uffdio_api failed\n"); - return -1; - } + TEST_ASSERT(ioctl(uffd, UFFDIO_API, &uffdio_api) != -1, + "ioctl UFFDIO_API failed: %" PRIu64, + (uint64_t)uffdio_api.api); uffdio_register.range.start = (uint64_t)hva; uffdio_register.range.len = len; - uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) { - pr_info("ioctl uffdio_register failed\n"); - return -1; - } - - if ((uffdio_register.ioctls & UFFD_API_RANGE_IOCTLS) != - UFFD_API_RANGE_IOCTLS) { - pr_info("unexpected userfaultfd ioctl set\n"); - return -1; - } + uffdio_register.mode = uffd_mode; + TEST_ASSERT(ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) != -1, + "ioctl UFFDIO_REGISTER failed"); + TEST_ASSERT((uffdio_register.ioctls & expected_ioctls) == + expected_ioctls, "missing userfaultfd ioctls"); + uffd_args->uffd_mode = uffd_mode; uffd_args->uffd = uffd; uffd_args->pipefd = pipefd; uffd_args->delay = uffd_delay; @@ -243,13 +271,12 @@ static int setup_demand_paging(struct kvm_vm *vm, PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n", hva, hva + len); - - return 0; } struct test_params { - bool use_uffd; + int uffd_mode; useconds_t uffd_delay; + enum vm_mem_backing_src_type src_type; bool partition_vcpu_memory_access; }; @@ -267,14 +294,16 @@ static void run_test(enum vm_guest_mode mode, void *arg) int r; vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, - VM_MEM_SRC_ANONYMOUS); + p->src_type); perf_test_args.wr_fract = 1; - guest_data_prototype = malloc(perf_test_args.host_page_size); + demand_paging_size = get_backing_src_pagesz(p->src_type); + + guest_data_prototype = malloc(demand_paging_size); TEST_ASSERT(guest_data_prototype, "Failed to allocate buffer for guest data pattern"); - memset(guest_data_prototype, 0xAB, perf_test_args.host_page_size); + memset(guest_data_prototype, 0xAB, demand_paging_size); vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); TEST_ASSERT(vcpu_threads, "Memory allocation failed"); @@ -282,7 +311,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size, p->partition_vcpu_memory_access); - if (p->use_uffd) { + if (p->uffd_mode) { uffd_handler_threads = malloc(nr_vcpus * sizeof(*uffd_handler_threads)); TEST_ASSERT(uffd_handler_threads, "Memory allocation failed"); @@ -296,6 +325,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { vm_paddr_t vcpu_gpa; void *vcpu_hva; + void *vcpu_alias; uint64_t vcpu_mem_size; @@ -310,8 +340,9 @@ static void run_test(enum vm_guest_mode mode, void *arg) PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size); - /* Cache the HVA pointer of the region */ + /* Cache the host addresses of the region */ vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); + vcpu_alias = addr_gpa2alias(vm, vcpu_gpa); /* * Set up user fault fd to handle demand paging @@ -321,13 +352,11 @@ static void run_test(enum vm_guest_mode mode, void *arg) O_CLOEXEC | O_NONBLOCK); TEST_ASSERT(!r, "Failed to set up pipefd"); - r = setup_demand_paging(vm, - &uffd_handler_threads[vcpu_id], - pipefds[vcpu_id * 2], - p->uffd_delay, &uffd_args[vcpu_id], - vcpu_hva, vcpu_mem_size); - if (r < 0) - exit(-r); + setup_demand_paging(vm, &uffd_handler_threads[vcpu_id], + pipefds[vcpu_id * 2], p->uffd_mode, + p->uffd_delay, &uffd_args[vcpu_id], + vcpu_hva, vcpu_alias, + vcpu_mem_size); } } @@ -355,7 +384,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) pr_info("All vCPU threads joined\n"); - if (p->use_uffd) { + if (p->uffd_mode) { char c; /* Tell the user fault fd handler threads to quit */ @@ -377,7 +406,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) free(guest_data_prototype); free(vcpu_threads); - if (p->use_uffd) { + if (p->uffd_mode) { free(uffd_handler_threads); free(uffd_args); free(pipefds); @@ -387,17 +416,19 @@ static void run_test(enum vm_guest_mode mode, void *arg) static void help(char *name) { puts(""); - printf("usage: %s [-h] [-m mode] [-u] [-d uffd_delay_usec]\n" - " [-b memory] [-v vcpus] [-o]\n", name); + printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n" + " [-b memory] [-t type] [-v vcpus] [-o]\n", name); guest_modes_help(); - printf(" -u: use User Fault FD to handle vCPU page\n" - " faults.\n"); + printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n" + " UFFD registration mode: 'MISSING' or 'MINOR'.\n"); printf(" -d: add a delay in usec to the User Fault\n" " FD handler to simulate demand paging\n" " overheads. Ignored without -u.\n"); printf(" -b: specify the size of the memory region which should be\n" " demand paged by each vCPU. e.g. 10M or 3G.\n" " Default: 1G\n"); + printf(" -t: The type of backing memory to use. Default: anonymous\n"); + backing_src_help(); printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); @@ -409,19 +440,24 @@ int main(int argc, char *argv[]) { int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); struct test_params p = { + .src_type = VM_MEM_SRC_ANONYMOUS, .partition_vcpu_memory_access = true, }; int opt; guest_modes_append_default(); - while ((opt = getopt(argc, argv, "hm:ud:b:v:o")) != -1) { + while ((opt = getopt(argc, argv, "hm:u:d:b:t:v:o")) != -1) { switch (opt) { case 'm': guest_modes_cmdline(optarg); break; case 'u': - p.use_uffd = true; + if (!strcmp("MISSING", optarg)) + p.uffd_mode = UFFDIO_REGISTER_MODE_MISSING; + else if (!strcmp("MINOR", optarg)) + p.uffd_mode = UFFDIO_REGISTER_MODE_MINOR; + TEST_ASSERT(p.uffd_mode, "UFFD mode must be 'MISSING' or 'MINOR'."); break; case 'd': p.uffd_delay = strtoul(optarg, NULL, 0); @@ -430,6 +466,9 @@ int main(int argc, char *argv[]) case 'b': guest_percpu_mem_size = parse_size(optarg); break; + case 't': + p.src_type = parse_backing_src_type(optarg); + break; case 'v': nr_vcpus = atoi(optarg); TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus, @@ -445,6 +484,11 @@ int main(int argc, char *argv[]) } } + if (p.uffd_mode == UFFDIO_REGISTER_MODE_MINOR && + !backing_src_is_shared(p.src_type)) { + TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -t"); + } + for_each_guest_mode(run_test, &p); return 0; diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c index 5aadf84c91c0..4b8db3bce610 100644 --- a/tools/testing/selftests/kvm/hardware_disable_test.c +++ b/tools/testing/selftests/kvm/hardware_disable_test.c @@ -132,6 +132,36 @@ static void run_test(uint32_t run) TEST_ASSERT(false, "%s: [%d] child escaped the ninja\n", __func__, run); } +void wait_for_child_setup(pid_t pid) +{ + /* + * Wait for the child to post to the semaphore, but wake up periodically + * to check if the child exited prematurely. + */ + for (;;) { + const struct timespec wait_period = { .tv_sec = 1 }; + int status; + + if (!sem_timedwait(sem, &wait_period)) + return; + + /* Child is still running, keep waiting. */ + if (pid != waitpid(pid, &status, WNOHANG)) + continue; + + /* + * Child is no longer running, which is not expected. + * + * If it exited with a non-zero status, we explicitly forward + * the child's status in case it exited with KSFT_SKIP. + */ + if (WIFEXITED(status)) + exit(WEXITSTATUS(status)); + else + TEST_ASSERT(false, "Child exited unexpectedly"); + } +} + int main(int argc, char **argv) { uint32_t i; @@ -148,7 +178,7 @@ int main(int argc, char **argv) run_test(i); /* This function always exits */ pr_debug("%s: [%d] waiting semaphore\n", __func__, i); - sem_wait(sem); + wait_for_child_setup(pid); r = (rand() % DELAY_US_MAX) + 1; pr_debug("%s: [%d] waiting %dus\n", __func__, i, r); usleep(r); diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index a8f022794ce3..fcd8e3855111 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -77,6 +77,7 @@ struct vm_guest_mode_params { }; extern const struct vm_guest_mode_params vm_guest_mode_params[]; +int open_kvm_dev_path_or_exit(void); int kvm_check_cap(long cap); int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, @@ -146,6 +147,7 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa); void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); +void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa); /* * Address Guest Virtual to Guest Physical @@ -302,7 +304,7 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm); unsigned int vm_get_page_size(struct kvm_vm *vm); unsigned int vm_get_page_shift(struct kvm_vm *vm); -unsigned int vm_get_max_gfn(struct kvm_vm *vm); +uint64_t vm_get_max_gfn(struct kvm_vm *vm); int vm_get_fd(struct kvm_vm *vm); unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size); diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index fade3130eb01..d79be15dd3d2 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -17,6 +17,7 @@ #include <errno.h> #include <unistd.h> #include <fcntl.h> +#include <sys/mman.h> #include "kselftest.h" static inline int _no_printf(const char *format, ...) { return 0; } @@ -84,6 +85,8 @@ enum vm_mem_backing_src_type { VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB, VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB, VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB, + VM_MEM_SRC_SHMEM, + VM_MEM_SRC_SHARED_HUGETLB, NUM_SRC_TYPES, }; @@ -100,4 +103,13 @@ size_t get_backing_src_pagesz(uint32_t i); void backing_src_help(void); enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name); +/* + * Whether or not the given source type is shared memory (as opposed to + * anonymous). + */ +static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t) +{ + return vm_mem_backing_src_alias(t)->flag & MAP_SHARED; +} + #endif /* SELFTEST_KVM_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index fc83f6c5902d..28e528c19d28 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -32,6 +32,34 @@ static void *align(void *x, size_t size) } /* + * Open KVM_DEV_PATH if available, otherwise exit the entire program. + * + * Input Args: + * flags - The flags to pass when opening KVM_DEV_PATH. + * + * Return: + * The opened file descriptor of /dev/kvm. + */ +static int _open_kvm_dev_path_or_exit(int flags) +{ + int fd; + + fd = open(KVM_DEV_PATH, flags); + if (fd < 0) { + print_skip("%s not available, is KVM loaded? (errno: %d)", + KVM_DEV_PATH, errno); + exit(KSFT_SKIP); + } + + return fd; +} + +int open_kvm_dev_path_or_exit(void) +{ + return _open_kvm_dev_path_or_exit(O_RDONLY); +} + +/* * Capability * * Input Args: @@ -52,10 +80,7 @@ int kvm_check_cap(long cap) int ret; int kvm_fd; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); - + kvm_fd = open_kvm_dev_path_or_exit(); ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap); TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n" " rc: %i errno: %i", ret, errno); @@ -128,9 +153,7 @@ void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size) static void vm_open(struct kvm_vm *vm, int perm) { - vm->kvm_fd = open(KVM_DEV_PATH, perm); - if (vm->kvm_fd < 0) - exit(KSFT_SKIP); + vm->kvm_fd = _open_kvm_dev_path_or_exit(perm); if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) { print_skip("immediate_exit not available"); @@ -203,7 +226,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) TEST_ASSERT(vm != NULL, "Insufficient Memory"); INIT_LIST_HEAD(&vm->vcpus); - INIT_LIST_HEAD(&vm->userspace_mem_regions); + vm->regions.gpa_tree = RB_ROOT; + vm->regions.hva_tree = RB_ROOT; + hash_init(vm->regions.slot_hash); vm->mode = mode; vm->type = 0; @@ -295,7 +320,7 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, */ uint64_t vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus; uint64_t extra_pg_pages = (extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2; - uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages; + uint64_t pages = DEFAULT_GUEST_PHY_PAGES + extra_mem_pages + vcpu_pages + extra_pg_pages; struct kvm_vm *vm; int i; @@ -355,13 +380,14 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, */ void kvm_vm_restart(struct kvm_vm *vmp, int perm) { + int ctr; struct userspace_mem_region *region; vm_open(vmp, perm); if (vmp->has_irqchip) vm_create_irqchip(vmp); - list_for_each_entry(region, &vmp->userspace_mem_regions, list) { + hash_for_each(vmp->regions.slot_hash, ctr, region, slot_node) { int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" " rc: %i errno: %i\n" @@ -424,14 +450,21 @@ uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) static struct userspace_mem_region * userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end) { - struct userspace_mem_region *region; + struct rb_node *node; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + for (node = vm->regions.gpa_tree.rb_node; node; ) { + struct userspace_mem_region *region = + container_of(node, struct userspace_mem_region, gpa_node); uint64_t existing_start = region->region.guest_phys_addr; uint64_t existing_end = region->region.guest_phys_addr + region->region.memory_size - 1; if (start <= existing_end && end >= existing_start) return region; + + if (start < existing_start) + node = node->rb_left; + else + node = node->rb_right; } return NULL; @@ -546,11 +579,16 @@ void kvm_vm_release(struct kvm_vm *vmp) } static void __vm_mem_region_delete(struct kvm_vm *vm, - struct userspace_mem_region *region) + struct userspace_mem_region *region, + bool unlink) { int ret; - list_del(®ion->list); + if (unlink) { + rb_erase(®ion->gpa_node, &vm->regions.gpa_tree); + rb_erase(®ion->hva_node, &vm->regions.hva_tree); + hash_del(®ion->slot_node); + } region->region.memory_size = 0; ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); @@ -569,14 +607,16 @@ static void __vm_mem_region_delete(struct kvm_vm *vm, */ void kvm_vm_free(struct kvm_vm *vmp) { - struct userspace_mem_region *region, *tmp; + int ctr; + struct hlist_node *node; + struct userspace_mem_region *region; if (vmp == NULL) return; /* Free userspace_mem_regions. */ - list_for_each_entry_safe(region, tmp, &vmp->userspace_mem_regions, list) - __vm_mem_region_delete(vmp, region); + hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node) + __vm_mem_region_delete(vmp, region, false); /* Free sparsebit arrays. */ sparsebit_free(&vmp->vpages_valid); @@ -658,13 +698,64 @@ int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len) return 0; } +static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree, + struct userspace_mem_region *region) +{ + struct rb_node **cur, *parent; + + for (cur = &gpa_tree->rb_node, parent = NULL; *cur; ) { + struct userspace_mem_region *cregion; + + cregion = container_of(*cur, typeof(*cregion), gpa_node); + parent = *cur; + if (region->region.guest_phys_addr < + cregion->region.guest_phys_addr) + cur = &(*cur)->rb_left; + else { + TEST_ASSERT(region->region.guest_phys_addr != + cregion->region.guest_phys_addr, + "Duplicate GPA in region tree"); + + cur = &(*cur)->rb_right; + } + } + + rb_link_node(®ion->gpa_node, parent, cur); + rb_insert_color(®ion->gpa_node, gpa_tree); +} + +static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree, + struct userspace_mem_region *region) +{ + struct rb_node **cur, *parent; + + for (cur = &hva_tree->rb_node, parent = NULL; *cur; ) { + struct userspace_mem_region *cregion; + + cregion = container_of(*cur, typeof(*cregion), hva_node); + parent = *cur; + if (region->host_mem < cregion->host_mem) + cur = &(*cur)->rb_left; + else { + TEST_ASSERT(region->host_mem != + cregion->host_mem, + "Duplicate HVA in region tree"); + + cur = &(*cur)->rb_right; + } + } + + rb_link_node(®ion->hva_node, parent, cur); + rb_insert_color(®ion->hva_node, hva_tree); +} + /* * VM Userspace Memory Region Add * * Input Args: * vm - Virtual Machine - * backing_src - Storage source for this region. - * NULL to use anonymous memory. + * src_type - Storage source for this region. + * NULL to use anonymous memory. * guest_paddr - Starting guest physical address * slot - KVM region slot * npages - Number of physical pages @@ -722,7 +813,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, (uint64_t) region->region.memory_size); /* Confirm no region with the requested slot already exists. */ - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each_possible(vm->regions.slot_hash, region, slot_node, + slot) { if (region->region.slot != slot) continue; @@ -755,11 +847,30 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, if (alignment > 1) region->mmap_size += alignment; + region->fd = -1; + if (backing_src_is_shared(src_type)) { + int memfd_flags = MFD_CLOEXEC; + + if (src_type == VM_MEM_SRC_SHARED_HUGETLB) + memfd_flags |= MFD_HUGETLB; + + region->fd = memfd_create("kvm_selftest", memfd_flags); + TEST_ASSERT(region->fd != -1, + "memfd_create failed, errno: %i", errno); + + ret = ftruncate(region->fd, region->mmap_size); + TEST_ASSERT(ret == 0, "ftruncate failed, errno: %i", errno); + + ret = fallocate(region->fd, + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, + region->mmap_size); + TEST_ASSERT(ret == 0, "fallocate failed, errno: %i", errno); + } + region->mmap_start = mmap(NULL, region->mmap_size, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS - | vm_mem_backing_src_alias(src_type)->flag, - -1, 0); + vm_mem_backing_src_alias(src_type)->flag, + region->fd, 0); TEST_ASSERT(region->mmap_start != MAP_FAILED, "test_malloc failed, mmap_start: %p errno: %i", region->mmap_start, errno); @@ -793,8 +904,23 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, ret, errno, slot, flags, guest_paddr, (uint64_t) region->region.memory_size); - /* Add to linked-list of memory regions. */ - list_add(®ion->list, &vm->userspace_mem_regions); + /* Add to quick lookup data structures */ + vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region); + vm_userspace_mem_region_hva_insert(&vm->regions.hva_tree, region); + hash_add(vm->regions.slot_hash, ®ion->slot_node, slot); + + /* If shared memory, create an alias. */ + if (region->fd >= 0) { + region->mmap_alias = mmap(NULL, region->mmap_size, + PROT_READ | PROT_WRITE, + vm_mem_backing_src_alias(src_type)->flag, + region->fd, 0); + TEST_ASSERT(region->mmap_alias != MAP_FAILED, + "mmap of alias failed, errno: %i", errno); + + /* Align host alias address */ + region->host_alias = align(region->mmap_alias, alignment); + } } /* @@ -817,10 +943,10 @@ memslot2region(struct kvm_vm *vm, uint32_t memslot) { struct userspace_mem_region *region; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each_possible(vm->regions.slot_hash, region, slot_node, + memslot) if (region->region.slot == memslot) return region; - } fprintf(stderr, "No mem region with the requested slot found,\n" " requested slot: %u\n", memslot); @@ -905,7 +1031,7 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) */ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot) { - __vm_mem_region_delete(vm, memslot2region(vm, slot)); + __vm_mem_region_delete(vm, memslot2region(vm, slot), true); } /* @@ -925,9 +1051,7 @@ static int vcpu_mmap_sz(void) { int dev_fd, ret; - dev_fd = open(KVM_DEV_PATH, O_RDONLY); - if (dev_fd < 0) - exit(KSFT_SKIP); + dev_fd = open_kvm_dev_path_or_exit(); ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL); TEST_ASSERT(ret >= sizeof(struct kvm_run), @@ -1099,6 +1223,9 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0); virt_pgd_alloc(vm, pgd_memslot); + vm_paddr_t paddr = vm_phy_pages_alloc(vm, pages, + KVM_UTIL_MIN_PFN * vm->page_size, + data_memslot); /* * Find an unused range of virtual page addresses of at least @@ -1108,11 +1235,7 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, /* Map the virtual pages. */ for (vm_vaddr_t vaddr = vaddr_start; pages > 0; - pages--, vaddr += vm->page_size) { - vm_paddr_t paddr; - - paddr = vm_phy_page_alloc(vm, - KVM_UTIL_MIN_PFN * vm->page_size, data_memslot); + pages--, vaddr += vm->page_size, paddr += vm->page_size) { virt_pg_map(vm, vaddr, paddr, pgd_memslot); @@ -1177,16 +1300,14 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) { struct userspace_mem_region *region; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { - if ((gpa >= region->region.guest_phys_addr) - && (gpa <= (region->region.guest_phys_addr - + region->region.memory_size - 1))) - return (void *) ((uintptr_t) region->host_mem - + (gpa - region->region.guest_phys_addr)); + region = userspace_mem_region_find(vm, gpa, gpa); + if (!region) { + TEST_FAIL("No vm physical memory at 0x%lx", gpa); + return NULL; } - TEST_FAIL("No vm physical memory at 0x%lx", gpa); - return NULL; + return (void *)((uintptr_t)region->host_mem + + (gpa - region->region.guest_phys_addr)); } /* @@ -1208,15 +1329,22 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) */ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) { - struct userspace_mem_region *region; + struct rb_node *node; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { - if ((hva >= region->host_mem) - && (hva <= (region->host_mem - + region->region.memory_size - 1))) - return (vm_paddr_t) ((uintptr_t) - region->region.guest_phys_addr - + (hva - (uintptr_t) region->host_mem)); + for (node = vm->regions.hva_tree.rb_node; node; ) { + struct userspace_mem_region *region = + container_of(node, struct userspace_mem_region, hva_node); + + if (hva >= region->host_mem) { + if (hva <= (region->host_mem + + region->region.memory_size - 1)) + return (vm_paddr_t)((uintptr_t) + region->region.guest_phys_addr + + (hva - (uintptr_t)region->host_mem)); + + node = node->rb_right; + } else + node = node->rb_left; } TEST_FAIL("No mapping to a guest physical address, hva: %p", hva); @@ -1224,6 +1352,42 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) } /* + * Address VM physical to Host Virtual *alias*. + * + * Input Args: + * vm - Virtual Machine + * gpa - VM physical address + * + * Output Args: None + * + * Return: + * Equivalent address within the host virtual *alias* area, or NULL + * (without failing the test) if the guest memory is not shared (so + * no alias exists). + * + * When vm_create() and related functions are called with a shared memory + * src_type, we also create a writable, shared alias mapping of the + * underlying guest memory. This allows the host to manipulate guest memory + * without mapping that memory in the guest's address space. And, for + * userfaultfd-based demand paging, we can do so without triggering userfaults. + */ +void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa) +{ + struct userspace_mem_region *region; + uintptr_t offset; + + region = userspace_mem_region_find(vm, gpa, gpa); + if (!region) + return NULL; + + if (!region->host_alias) + return NULL; + + offset = gpa - region->region.guest_phys_addr; + return (void *) ((uintptr_t) region->host_alias + offset); +} + +/* * VM Create IRQ Chip * * Input Args: @@ -1822,6 +1986,7 @@ int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, */ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { + int ctr; struct userspace_mem_region *region; struct vcpu *vcpu; @@ -1829,7 +1994,7 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd); fprintf(stream, "%*spage_size: 0x%x\n", indent, "", vm->page_size); fprintf(stream, "%*sMem Regions:\n", indent, ""); - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each(vm->regions.slot_hash, ctr, region, slot_node) { fprintf(stream, "%*sguest_phys: 0x%lx size: 0x%lx " "host_virt: %p\n", indent + 2, "", (uint64_t) region->region.guest_phys_addr, @@ -2015,10 +2180,7 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm) if (vm == NULL) { /* Ensure that the KVM vendor-specific module is loaded. */ - f = fopen(KVM_DEV_PATH, "r"); - TEST_ASSERT(f != NULL, "Error in opening KVM dev file: %d", - errno); - fclose(f); + close(open_kvm_dev_path_or_exit()); } f = fopen("/sys/module/kvm_intel/parameters/unrestricted_guest", "r"); @@ -2041,7 +2203,7 @@ unsigned int vm_get_page_shift(struct kvm_vm *vm) return vm->page_shift; } -unsigned int vm_get_max_gfn(struct kvm_vm *vm) +uint64_t vm_get_max_gfn(struct kvm_vm *vm) { return vm->max_gfn; } diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index 91ce1b5d480b..a03febc24ba6 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -8,6 +8,9 @@ #ifndef SELFTEST_KVM_UTIL_INTERNAL_H #define SELFTEST_KVM_UTIL_INTERNAL_H +#include "linux/hashtable.h" +#include "linux/rbtree.h" + #include "sparsebit.h" struct userspace_mem_region { @@ -16,9 +19,13 @@ struct userspace_mem_region { int fd; off_t offset; void *host_mem; + void *host_alias; void *mmap_start; + void *mmap_alias; size_t mmap_size; - struct list_head list; + struct rb_node gpa_node; + struct rb_node hva_node; + struct hlist_node slot_node; }; struct vcpu { @@ -31,6 +38,12 @@ struct vcpu { uint32_t dirty_gfns_count; }; +struct userspace_mem_regions { + struct rb_root gpa_tree; + struct rb_root hva_tree; + DECLARE_HASHTABLE(slot_hash, 9); +}; + struct kvm_vm { int mode; unsigned long type; @@ -43,7 +56,7 @@ struct kvm_vm { unsigned int va_bits; uint64_t max_gfn; struct list_head vcpus; - struct list_head userspace_mem_regions; + struct userspace_mem_regions regions; struct sparsebit *vpages_valid; struct sparsebit *vpages_mapped; bool has_irqchip; diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c index 81490b9b4e32..abf381800a59 100644 --- a/tools/testing/selftests/kvm/lib/perf_test_util.c +++ b/tools/testing/selftests/kvm/lib/perf_test_util.c @@ -2,6 +2,7 @@ /* * Copyright (C) 2020, Google LLC. */ +#include <inttypes.h> #include "kvm_util.h" #include "perf_test_util.h" @@ -80,7 +81,8 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, */ TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm), "Requested more guest memory than address space allows.\n" - " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n", + " guest pages: %" PRIx64 " max gfn: %" PRIx64 + " vcpus: %d wss: %" PRIx64 "]\n", guest_num_pages, vm_get_max_gfn(vm), vcpus, vcpu_memory_bytes); diff --git a/tools/testing/selftests/kvm/lib/rbtree.c b/tools/testing/selftests/kvm/lib/rbtree.c new file mode 100644 index 000000000000..a703f0194ea3 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/rbtree.c @@ -0,0 +1 @@ +#include "../../../../lib/rbtree.c" diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 63d2bc7d757b..6ad6c8276b2e 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -168,70 +168,87 @@ size_t get_def_hugetlb_pagesz(void) const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i) { + static const int anon_flags = MAP_PRIVATE | MAP_ANONYMOUS; + static const int anon_huge_flags = anon_flags | MAP_HUGETLB; + static const struct vm_mem_backing_src_alias aliases[] = { [VM_MEM_SRC_ANONYMOUS] = { .name = "anonymous", - .flag = 0, + .flag = anon_flags, }, [VM_MEM_SRC_ANONYMOUS_THP] = { .name = "anonymous_thp", - .flag = 0, + .flag = anon_flags, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB] = { .name = "anonymous_hugetlb", - .flag = MAP_HUGETLB, + .flag = anon_huge_flags, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_16KB] = { .name = "anonymous_hugetlb_16kb", - .flag = MAP_HUGETLB | MAP_HUGE_16KB, + .flag = anon_huge_flags | MAP_HUGE_16KB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_64KB] = { .name = "anonymous_hugetlb_64kb", - .flag = MAP_HUGETLB | MAP_HUGE_64KB, + .flag = anon_huge_flags | MAP_HUGE_64KB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_512KB] = { .name = "anonymous_hugetlb_512kb", - .flag = MAP_HUGETLB | MAP_HUGE_512KB, + .flag = anon_huge_flags | MAP_HUGE_512KB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_1MB] = { .name = "anonymous_hugetlb_1mb", - .flag = MAP_HUGETLB | MAP_HUGE_1MB, + .flag = anon_huge_flags | MAP_HUGE_1MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_2MB] = { .name = "anonymous_hugetlb_2mb", - .flag = MAP_HUGETLB | MAP_HUGE_2MB, + .flag = anon_huge_flags | MAP_HUGE_2MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_8MB] = { .name = "anonymous_hugetlb_8mb", - .flag = MAP_HUGETLB | MAP_HUGE_8MB, + .flag = anon_huge_flags | MAP_HUGE_8MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_16MB] = { .name = "anonymous_hugetlb_16mb", - .flag = MAP_HUGETLB | MAP_HUGE_16MB, + .flag = anon_huge_flags | MAP_HUGE_16MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_32MB] = { .name = "anonymous_hugetlb_32mb", - .flag = MAP_HUGETLB | MAP_HUGE_32MB, + .flag = anon_huge_flags | MAP_HUGE_32MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_256MB] = { .name = "anonymous_hugetlb_256mb", - .flag = MAP_HUGETLB | MAP_HUGE_256MB, + .flag = anon_huge_flags | MAP_HUGE_256MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_512MB] = { .name = "anonymous_hugetlb_512mb", - .flag = MAP_HUGETLB | MAP_HUGE_512MB, + .flag = anon_huge_flags | MAP_HUGE_512MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB] = { .name = "anonymous_hugetlb_1gb", - .flag = MAP_HUGETLB | MAP_HUGE_1GB, + .flag = anon_huge_flags | MAP_HUGE_1GB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB] = { .name = "anonymous_hugetlb_2gb", - .flag = MAP_HUGETLB | MAP_HUGE_2GB, + .flag = anon_huge_flags | MAP_HUGE_2GB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB] = { .name = "anonymous_hugetlb_16gb", - .flag = MAP_HUGETLB | MAP_HUGE_16GB, + .flag = anon_huge_flags | MAP_HUGE_16GB, + }, + [VM_MEM_SRC_SHMEM] = { + .name = "shmem", + .flag = MAP_SHARED, + }, + [VM_MEM_SRC_SHARED_HUGETLB] = { + .name = "shared_hugetlb", + /* + * No MAP_HUGETLB, we use MFD_HUGETLB instead. Since + * we're using "file backed" memory, we need to specify + * this when the FD is created, not when the area is + * mapped. + */ + .flag = MAP_SHARED, }, }; _Static_assert(ARRAY_SIZE(aliases) == NUM_SRC_TYPES, @@ -250,10 +267,12 @@ size_t get_backing_src_pagesz(uint32_t i) switch (i) { case VM_MEM_SRC_ANONYMOUS: + case VM_MEM_SRC_SHMEM: return getpagesize(); case VM_MEM_SRC_ANONYMOUS_THP: return get_trans_hugepagesz(); case VM_MEM_SRC_ANONYMOUS_HUGETLB: + case VM_MEM_SRC_SHARED_HUGETLB: return get_def_hugetlb_pagesz(); default: return MAP_HUGE_PAGE_SIZE(flag); diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index a8906e60a108..efe235044421 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -657,9 +657,7 @@ struct kvm_cpuid2 *kvm_get_supported_cpuid(void) return cpuid; cpuid = allocate_kvm_cpuid2(); - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid); TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n", @@ -691,9 +689,7 @@ uint64_t kvm_get_feature_msr(uint64_t msr_index) buffer.header.nmsrs = 1; buffer.entry.index = msr_index; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); r = ioctl(kvm_fd, KVM_GET_MSRS, &buffer.header); TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n" @@ -986,9 +982,7 @@ struct kvm_msr_list *kvm_get_msr_index_list(void) struct kvm_msr_list *list; int nmsrs, r, kvm_fd; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); nmsrs = kvm_get_num_msrs_fd(kvm_fd); list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); @@ -1312,9 +1306,7 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void) return cpuid; cpuid = allocate_kvm_cpuid2(); - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid); TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_HV_CPUID failed %d %d\n", diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index 6096bf0a5b34..98351ba0933c 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -71,14 +71,22 @@ struct memslot_antagonist_args { }; static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay, - uint64_t nr_modifications, uint64_t gpa) + uint64_t nr_modifications) { + const uint64_t pages = 1; + uint64_t gpa; int i; + /* + * Add the dummy memslot just below the perf_test_util memslot, which is + * at the top of the guest physical address space. + */ + gpa = guest_test_phys_mem - pages * vm_get_page_size(vm); + for (i = 0; i < nr_modifications; i++) { usleep(delay); vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, gpa, - DUMMY_MEMSLOT_INDEX, 1, 0); + DUMMY_MEMSLOT_INDEX, pages, 0); vm_mem_region_delete(vm, DUMMY_MEMSLOT_INDEX); } @@ -120,11 +128,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) pr_info("Started all vCPUs\n"); add_remove_memslot(vm, p->memslot_modification_delay, - p->nr_memslot_modifications, - guest_test_phys_mem + - (guest_percpu_mem_size * nr_vcpus) + - perf_test_args.host_page_size + - perf_test_args.guest_page_size); + p->nr_memslot_modifications); run_vcpus = false; diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c new file mode 100644 index 000000000000..9307f25d8130 --- /dev/null +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -0,0 +1,1037 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A memslot-related performance benchmark. + * + * Copyright (C) 2021 Oracle and/or its affiliates. + * + * Basic guest setup / host vCPU thread code lifted from set_memory_region_test. + */ +#include <pthread.h> +#include <sched.h> +#include <semaphore.h> +#include <stdatomic.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <time.h> +#include <unistd.h> + +#include <linux/compiler.h> + +#include <test_util.h> +#include <kvm_util.h> +#include <processor.h> + +#define VCPU_ID 0 + +#define MEM_SIZE ((512U << 20) + 4096) +#define MEM_SIZE_PAGES (MEM_SIZE / 4096) +#define MEM_GPA 0x10000000UL +#define MEM_AUX_GPA MEM_GPA +#define MEM_SYNC_GPA MEM_AUX_GPA +#define MEM_TEST_GPA (MEM_AUX_GPA + 4096) +#define MEM_TEST_SIZE (MEM_SIZE - 4096) +static_assert(MEM_SIZE % 4096 == 0, "invalid mem size"); +static_assert(MEM_TEST_SIZE % 4096 == 0, "invalid mem test size"); + +/* + * 32 MiB is max size that gets well over 100 iterations on 509 slots. + * Considering that each slot needs to have at least one page up to + * 8194 slots in use can then be tested (although with slightly + * limited resolution). + */ +#define MEM_SIZE_MAP ((32U << 20) + 4096) +#define MEM_SIZE_MAP_PAGES (MEM_SIZE_MAP / 4096) +#define MEM_TEST_MAP_SIZE (MEM_SIZE_MAP - 4096) +#define MEM_TEST_MAP_SIZE_PAGES (MEM_TEST_MAP_SIZE / 4096) +static_assert(MEM_SIZE_MAP % 4096 == 0, "invalid map test region size"); +static_assert(MEM_TEST_MAP_SIZE % 4096 == 0, "invalid map test region size"); +static_assert(MEM_TEST_MAP_SIZE_PAGES % 2 == 0, "invalid map test region size"); +static_assert(MEM_TEST_MAP_SIZE_PAGES > 2, "invalid map test region size"); + +/* + * 128 MiB is min size that fills 32k slots with at least one page in each + * while at the same time gets 100+ iterations in such test + */ +#define MEM_TEST_UNMAP_SIZE (128U << 20) +#define MEM_TEST_UNMAP_SIZE_PAGES (MEM_TEST_UNMAP_SIZE / 4096) +/* 2 MiB chunk size like a typical huge page */ +#define MEM_TEST_UNMAP_CHUNK_PAGES (2U << (20 - 12)) +static_assert(MEM_TEST_UNMAP_SIZE <= MEM_TEST_SIZE, + "invalid unmap test region size"); +static_assert(MEM_TEST_UNMAP_SIZE % 4096 == 0, + "invalid unmap test region size"); +static_assert(MEM_TEST_UNMAP_SIZE_PAGES % + (2 * MEM_TEST_UNMAP_CHUNK_PAGES) == 0, + "invalid unmap test region size"); + +/* + * For the move active test the middle of the test area is placed on + * a memslot boundary: half lies in the memslot being moved, half in + * other memslot(s). + * + * When running this test with 32k memslots (32764, really) each memslot + * contains 4 pages. + * The last one additionally contains the remaining 21 pages of memory, + * for the total size of 25 pages. + * Hence, the maximum size here is 50 pages. + */ +#define MEM_TEST_MOVE_SIZE_PAGES (50) +#define MEM_TEST_MOVE_SIZE (MEM_TEST_MOVE_SIZE_PAGES * 4096) +#define MEM_TEST_MOVE_GPA_DEST (MEM_GPA + MEM_SIZE) +static_assert(MEM_TEST_MOVE_SIZE <= MEM_TEST_SIZE, + "invalid move test region size"); + +#define MEM_TEST_VAL_1 0x1122334455667788 +#define MEM_TEST_VAL_2 0x99AABBCCDDEEFF00 + +struct vm_data { + struct kvm_vm *vm; + pthread_t vcpu_thread; + uint32_t nslots; + uint64_t npages; + uint64_t pages_per_slot; + void **hva_slots; + bool mmio_ok; + uint64_t mmio_gpa_min; + uint64_t mmio_gpa_max; +}; + +struct sync_area { + atomic_bool start_flag; + atomic_bool exit_flag; + atomic_bool sync_flag; + void *move_area_ptr; +}; + +/* + * Technically, we need also for the atomic bool to be address-free, which + * is recommended, but not strictly required, by C11 for lockless + * implementations. + * However, in practice both GCC and Clang fulfill this requirement on + * all KVM-supported platforms. + */ +static_assert(ATOMIC_BOOL_LOCK_FREE == 2, "atomic bool is not lockless"); + +static sem_t vcpu_ready; + +static bool map_unmap_verify; + +static bool verbose; +#define pr_info_v(...) \ + do { \ + if (verbose) \ + pr_info(__VA_ARGS__); \ + } while (0) + +static void *vcpu_worker(void *data) +{ + struct vm_data *vm = data; + struct kvm_run *run; + struct ucall uc; + uint64_t cmd; + + run = vcpu_state(vm->vm, VCPU_ID); + while (1) { + vcpu_run(vm->vm, VCPU_ID); + + if (run->exit_reason == KVM_EXIT_IO) { + cmd = get_ucall(vm->vm, VCPU_ID, &uc); + if (cmd != UCALL_SYNC) + break; + + sem_post(&vcpu_ready); + continue; + } + + if (run->exit_reason != KVM_EXIT_MMIO) + break; + + TEST_ASSERT(vm->mmio_ok, "Unexpected mmio exit"); + TEST_ASSERT(run->mmio.is_write, "Unexpected mmio read"); + TEST_ASSERT(run->mmio.len == 8, + "Unexpected exit mmio size = %u", run->mmio.len); + TEST_ASSERT(run->mmio.phys_addr >= vm->mmio_gpa_min && + run->mmio.phys_addr <= vm->mmio_gpa_max, + "Unexpected exit mmio address = 0x%llx", + run->mmio.phys_addr); + } + + if (run->exit_reason == KVM_EXIT_IO && cmd == UCALL_ABORT) + TEST_FAIL("%s at %s:%ld, val = %lu", (const char *)uc.args[0], + __FILE__, uc.args[1], uc.args[2]); + + return NULL; +} + +static void wait_for_vcpu(void) +{ + struct timespec ts; + + TEST_ASSERT(!clock_gettime(CLOCK_REALTIME, &ts), + "clock_gettime() failed: %d\n", errno); + + ts.tv_sec += 2; + TEST_ASSERT(!sem_timedwait(&vcpu_ready, &ts), + "sem_timedwait() failed: %d\n", errno); +} + +static void *vm_gpa2hva(struct vm_data *data, uint64_t gpa, uint64_t *rempages) +{ + uint64_t gpage, pgoffs; + uint32_t slot, slotoffs; + void *base; + + TEST_ASSERT(gpa >= MEM_GPA, "Too low gpa to translate"); + TEST_ASSERT(gpa < MEM_GPA + data->npages * 4096, + "Too high gpa to translate"); + gpa -= MEM_GPA; + + gpage = gpa / 4096; + pgoffs = gpa % 4096; + slot = min(gpage / data->pages_per_slot, (uint64_t)data->nslots - 1); + slotoffs = gpage - (slot * data->pages_per_slot); + + if (rempages) { + uint64_t slotpages; + + if (slot == data->nslots - 1) + slotpages = data->npages - slot * data->pages_per_slot; + else + slotpages = data->pages_per_slot; + + TEST_ASSERT(!pgoffs, + "Asking for remaining pages in slot but gpa not page aligned"); + *rempages = slotpages - slotoffs; + } + + base = data->hva_slots[slot]; + return (uint8_t *)base + slotoffs * 4096 + pgoffs; +} + +static uint64_t vm_slot2gpa(struct vm_data *data, uint32_t slot) +{ + TEST_ASSERT(slot < data->nslots, "Too high slot number"); + + return MEM_GPA + slot * data->pages_per_slot * 4096; +} + +static struct vm_data *alloc_vm(void) +{ + struct vm_data *data; + + data = malloc(sizeof(*data)); + TEST_ASSERT(data, "malloc(vmdata) failed"); + + data->vm = NULL; + data->hva_slots = NULL; + + return data; +} + +static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, + void *guest_code, uint64_t mempages, + struct timespec *slot_runtime) +{ + uint32_t max_mem_slots; + uint64_t rempages; + uint64_t guest_addr; + uint32_t slot; + struct timespec tstart; + struct sync_area *sync; + + max_mem_slots = kvm_check_cap(KVM_CAP_NR_MEMSLOTS); + TEST_ASSERT(max_mem_slots > 1, + "KVM_CAP_NR_MEMSLOTS should be greater than 1"); + TEST_ASSERT(nslots > 1 || nslots == -1, + "Slot count cap should be greater than 1"); + if (nslots != -1) + max_mem_slots = min(max_mem_slots, (uint32_t)nslots); + pr_info_v("Allowed number of memory slots: %"PRIu32"\n", max_mem_slots); + + TEST_ASSERT(mempages > 1, + "Can't test without any memory"); + + data->npages = mempages; + data->nslots = max_mem_slots - 1; + data->pages_per_slot = mempages / data->nslots; + if (!data->pages_per_slot) { + *maxslots = mempages + 1; + return false; + } + + rempages = mempages % data->nslots; + data->hva_slots = malloc(sizeof(*data->hva_slots) * data->nslots); + TEST_ASSERT(data->hva_slots, "malloc() fail"); + + data->vm = vm_create_default(VCPU_ID, 1024, guest_code); + + pr_info_v("Adding slots 1..%i, each slot with %"PRIu64" pages + %"PRIu64" extra pages last\n", + max_mem_slots - 1, data->pages_per_slot, rempages); + + clock_gettime(CLOCK_MONOTONIC, &tstart); + for (slot = 1, guest_addr = MEM_GPA; slot < max_mem_slots; slot++) { + uint64_t npages; + + npages = data->pages_per_slot; + if (slot == max_mem_slots - 1) + npages += rempages; + + vm_userspace_mem_region_add(data->vm, VM_MEM_SRC_ANONYMOUS, + guest_addr, slot, npages, + 0); + guest_addr += npages * 4096; + } + *slot_runtime = timespec_elapsed(tstart); + + for (slot = 0, guest_addr = MEM_GPA; slot < max_mem_slots - 1; slot++) { + uint64_t npages; + uint64_t gpa; + + npages = data->pages_per_slot; + if (slot == max_mem_slots - 2) + npages += rempages; + + gpa = vm_phy_pages_alloc(data->vm, npages, guest_addr, + slot + 1); + TEST_ASSERT(gpa == guest_addr, + "vm_phy_pages_alloc() failed\n"); + + data->hva_slots[slot] = addr_gpa2hva(data->vm, guest_addr); + memset(data->hva_slots[slot], 0, npages * 4096); + + guest_addr += npages * 4096; + } + + virt_map(data->vm, MEM_GPA, MEM_GPA, mempages, 0); + + sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL); + atomic_init(&sync->start_flag, false); + atomic_init(&sync->exit_flag, false); + atomic_init(&sync->sync_flag, false); + + data->mmio_ok = false; + + return true; +} + +static void launch_vm(struct vm_data *data) +{ + pr_info_v("Launching the test VM\n"); + + pthread_create(&data->vcpu_thread, NULL, vcpu_worker, data); + + /* Ensure the guest thread is spun up. */ + wait_for_vcpu(); +} + +static void free_vm(struct vm_data *data) +{ + kvm_vm_free(data->vm); + free(data->hva_slots); + free(data); +} + +static void wait_guest_exit(struct vm_data *data) +{ + pthread_join(data->vcpu_thread, NULL); +} + +static void let_guest_run(struct sync_area *sync) +{ + atomic_store_explicit(&sync->start_flag, true, memory_order_release); +} + +static void guest_spin_until_start(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + while (!atomic_load_explicit(&sync->start_flag, memory_order_acquire)) + ; +} + +static void make_guest_exit(struct sync_area *sync) +{ + atomic_store_explicit(&sync->exit_flag, true, memory_order_release); +} + +static bool _guest_should_exit(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + return atomic_load_explicit(&sync->exit_flag, memory_order_acquire); +} + +#define guest_should_exit() unlikely(_guest_should_exit()) + +/* + * noinline so we can easily see how much time the host spends waiting + * for the guest. + * For the same reason use alarm() instead of polling clock_gettime() + * to implement a wait timeout. + */ +static noinline void host_perform_sync(struct sync_area *sync) +{ + alarm(2); + + atomic_store_explicit(&sync->sync_flag, true, memory_order_release); + while (atomic_load_explicit(&sync->sync_flag, memory_order_acquire)) + ; + + alarm(0); +} + +static bool guest_perform_sync(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + bool expected; + + do { + if (guest_should_exit()) + return false; + + expected = true; + } while (!atomic_compare_exchange_weak_explicit(&sync->sync_flag, + &expected, false, + memory_order_acq_rel, + memory_order_relaxed)); + + return true; +} + +static void guest_code_test_memslot_move(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + uintptr_t base = (typeof(base))READ_ONCE(sync->move_area_ptr); + + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (!guest_should_exit()) { + uintptr_t ptr; + + for (ptr = base; ptr < base + MEM_TEST_MOVE_SIZE; + ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + /* + * No host sync here since the MMIO exits are so expensive + * that the host would spend most of its time waiting for + * the guest and so instead of measuring memslot move + * performance we would measure the performance and + * likelihood of MMIO exits + */ + } + + GUEST_DONE(); +} + +static void guest_code_test_memslot_map(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (1) { + uintptr_t ptr; + + for (ptr = MEM_TEST_GPA; + ptr < MEM_TEST_GPA + MEM_TEST_MAP_SIZE / 2; ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + if (!guest_perform_sync()) + break; + + for (ptr = MEM_TEST_GPA + MEM_TEST_MAP_SIZE / 2; + ptr < MEM_TEST_GPA + MEM_TEST_MAP_SIZE; ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_2; + + if (!guest_perform_sync()) + break; + } + + GUEST_DONE(); +} + +static void guest_code_test_memslot_unmap(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (1) { + uintptr_t ptr = MEM_TEST_GPA; + + /* + * We can afford to access (map) just a small number of pages + * per host sync as otherwise the host will spend + * a significant amount of its time waiting for the guest + * (instead of doing unmap operations), so this will + * effectively turn this test into a map performance test. + * + * Just access a single page to be on the safe side. + */ + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + if (!guest_perform_sync()) + break; + + ptr += MEM_TEST_UNMAP_SIZE / 2; + *(uint64_t *)ptr = MEM_TEST_VAL_2; + + if (!guest_perform_sync()) + break; + } + + GUEST_DONE(); +} + +static void guest_code_test_memslot_rw(void) +{ + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (1) { + uintptr_t ptr; + + for (ptr = MEM_TEST_GPA; + ptr < MEM_TEST_GPA + MEM_TEST_SIZE; ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + if (!guest_perform_sync()) + break; + + for (ptr = MEM_TEST_GPA + 4096 / 2; + ptr < MEM_TEST_GPA + MEM_TEST_SIZE; ptr += 4096) { + uint64_t val = *(uint64_t *)ptr; + + GUEST_ASSERT_1(val == MEM_TEST_VAL_2, val); + *(uint64_t *)ptr = 0; + } + + if (!guest_perform_sync()) + break; + } + + GUEST_DONE(); +} + +static bool test_memslot_move_prepare(struct vm_data *data, + struct sync_area *sync, + uint64_t *maxslots, bool isactive) +{ + uint64_t movesrcgpa, movetestgpa; + + movesrcgpa = vm_slot2gpa(data, data->nslots - 1); + + if (isactive) { + uint64_t lastpages; + + vm_gpa2hva(data, movesrcgpa, &lastpages); + if (lastpages < MEM_TEST_MOVE_SIZE_PAGES / 2) { + *maxslots = 0; + return false; + } + } + + movetestgpa = movesrcgpa - (MEM_TEST_MOVE_SIZE / (isactive ? 2 : 1)); + sync->move_area_ptr = (void *)movetestgpa; + + if (isactive) { + data->mmio_ok = true; + data->mmio_gpa_min = movesrcgpa; + data->mmio_gpa_max = movesrcgpa + MEM_TEST_MOVE_SIZE / 2 - 1; + } + + return true; +} + +static bool test_memslot_move_prepare_active(struct vm_data *data, + struct sync_area *sync, + uint64_t *maxslots) +{ + return test_memslot_move_prepare(data, sync, maxslots, true); +} + +static bool test_memslot_move_prepare_inactive(struct vm_data *data, + struct sync_area *sync, + uint64_t *maxslots) +{ + return test_memslot_move_prepare(data, sync, maxslots, false); +} + +static void test_memslot_move_loop(struct vm_data *data, struct sync_area *sync) +{ + uint64_t movesrcgpa; + + movesrcgpa = vm_slot2gpa(data, data->nslots - 1); + vm_mem_region_move(data->vm, data->nslots - 1 + 1, + MEM_TEST_MOVE_GPA_DEST); + vm_mem_region_move(data->vm, data->nslots - 1 + 1, movesrcgpa); +} + +static void test_memslot_do_unmap(struct vm_data *data, + uint64_t offsp, uint64_t count) +{ + uint64_t gpa, ctr; + + for (gpa = MEM_TEST_GPA + offsp * 4096, ctr = 0; ctr < count; ) { + uint64_t npages; + void *hva; + int ret; + + hva = vm_gpa2hva(data, gpa, &npages); + TEST_ASSERT(npages, "Empty memory slot at gptr 0x%"PRIx64, gpa); + npages = min(npages, count - ctr); + ret = madvise(hva, npages * 4096, MADV_DONTNEED); + TEST_ASSERT(!ret, + "madvise(%p, MADV_DONTNEED) on VM memory should not fail for gptr 0x%"PRIx64, + hva, gpa); + ctr += npages; + gpa += npages * 4096; + } + TEST_ASSERT(ctr == count, + "madvise(MADV_DONTNEED) should exactly cover all of the requested area"); +} + +static void test_memslot_map_unmap_check(struct vm_data *data, + uint64_t offsp, uint64_t valexp) +{ + uint64_t gpa; + uint64_t *val; + + if (!map_unmap_verify) + return; + + gpa = MEM_TEST_GPA + offsp * 4096; + val = (typeof(val))vm_gpa2hva(data, gpa, NULL); + TEST_ASSERT(*val == valexp, + "Guest written values should read back correctly before unmap (%"PRIu64" vs %"PRIu64" @ %"PRIx64")", + *val, valexp, gpa); + *val = 0; +} + +static void test_memslot_map_loop(struct vm_data *data, struct sync_area *sync) +{ + /* + * Unmap the second half of the test area while guest writes to (maps) + * the first half. + */ + test_memslot_do_unmap(data, MEM_TEST_MAP_SIZE_PAGES / 2, + MEM_TEST_MAP_SIZE_PAGES / 2); + + /* + * Wait for the guest to finish writing the first half of the test + * area, verify the written value on the first and the last page of + * this area and then unmap it. + * Meanwhile, the guest is writing to (mapping) the second half of + * the test area. + */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, 0, MEM_TEST_VAL_1); + test_memslot_map_unmap_check(data, + MEM_TEST_MAP_SIZE_PAGES / 2 - 1, + MEM_TEST_VAL_1); + test_memslot_do_unmap(data, 0, MEM_TEST_MAP_SIZE_PAGES / 2); + + + /* + * Wait for the guest to finish writing the second half of the test + * area and verify the written value on the first and the last page + * of this area. + * The area will be unmapped at the beginning of the next loop + * iteration. + * Meanwhile, the guest is writing to (mapping) the first half of + * the test area. + */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, MEM_TEST_MAP_SIZE_PAGES / 2, + MEM_TEST_VAL_2); + test_memslot_map_unmap_check(data, MEM_TEST_MAP_SIZE_PAGES - 1, + MEM_TEST_VAL_2); +} + +static void test_memslot_unmap_loop_common(struct vm_data *data, + struct sync_area *sync, + uint64_t chunk) +{ + uint64_t ctr; + + /* + * Wait for the guest to finish mapping page(s) in the first half + * of the test area, verify the written value and then perform unmap + * of this area. + * Meanwhile, the guest is writing to (mapping) page(s) in the second + * half of the test area. + */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, 0, MEM_TEST_VAL_1); + for (ctr = 0; ctr < MEM_TEST_UNMAP_SIZE_PAGES / 2; ctr += chunk) + test_memslot_do_unmap(data, ctr, chunk); + + /* Likewise, but for the opposite host / guest areas */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, MEM_TEST_UNMAP_SIZE_PAGES / 2, + MEM_TEST_VAL_2); + for (ctr = MEM_TEST_UNMAP_SIZE_PAGES / 2; + ctr < MEM_TEST_UNMAP_SIZE_PAGES; ctr += chunk) + test_memslot_do_unmap(data, ctr, chunk); +} + +static void test_memslot_unmap_loop(struct vm_data *data, + struct sync_area *sync) +{ + test_memslot_unmap_loop_common(data, sync, 1); +} + +static void test_memslot_unmap_loop_chunked(struct vm_data *data, + struct sync_area *sync) +{ + test_memslot_unmap_loop_common(data, sync, MEM_TEST_UNMAP_CHUNK_PAGES); +} + +static void test_memslot_rw_loop(struct vm_data *data, struct sync_area *sync) +{ + uint64_t gptr; + + for (gptr = MEM_TEST_GPA + 4096 / 2; + gptr < MEM_TEST_GPA + MEM_TEST_SIZE; gptr += 4096) + *(uint64_t *)vm_gpa2hva(data, gptr, NULL) = MEM_TEST_VAL_2; + + host_perform_sync(sync); + + for (gptr = MEM_TEST_GPA; + gptr < MEM_TEST_GPA + MEM_TEST_SIZE; gptr += 4096) { + uint64_t *vptr = (typeof(vptr))vm_gpa2hva(data, gptr, NULL); + uint64_t val = *vptr; + + TEST_ASSERT(val == MEM_TEST_VAL_1, + "Guest written values should read back correctly (is %"PRIu64" @ %"PRIx64")", + val, gptr); + *vptr = 0; + } + + host_perform_sync(sync); +} + +struct test_data { + const char *name; + uint64_t mem_size; + void (*guest_code)(void); + bool (*prepare)(struct vm_data *data, struct sync_area *sync, + uint64_t *maxslots); + void (*loop)(struct vm_data *data, struct sync_area *sync); +}; + +static bool test_execute(int nslots, uint64_t *maxslots, + unsigned int maxtime, + const struct test_data *tdata, + uint64_t *nloops, + struct timespec *slot_runtime, + struct timespec *guest_runtime) +{ + uint64_t mem_size = tdata->mem_size ? : MEM_SIZE_PAGES; + struct vm_data *data; + struct sync_area *sync; + struct timespec tstart; + bool ret = true; + + data = alloc_vm(); + if (!prepare_vm(data, nslots, maxslots, tdata->guest_code, + mem_size, slot_runtime)) { + ret = false; + goto exit_free; + } + + sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL); + + if (tdata->prepare && + !tdata->prepare(data, sync, maxslots)) { + ret = false; + goto exit_free; + } + + launch_vm(data); + + clock_gettime(CLOCK_MONOTONIC, &tstart); + let_guest_run(sync); + + while (1) { + *guest_runtime = timespec_elapsed(tstart); + if (guest_runtime->tv_sec >= maxtime) + break; + + tdata->loop(data, sync); + + (*nloops)++; + } + + make_guest_exit(sync); + wait_guest_exit(data); + +exit_free: + free_vm(data); + + return ret; +} + +static const struct test_data tests[] = { + { + .name = "map", + .mem_size = MEM_SIZE_MAP_PAGES, + .guest_code = guest_code_test_memslot_map, + .loop = test_memslot_map_loop, + }, + { + .name = "unmap", + .mem_size = MEM_TEST_UNMAP_SIZE_PAGES + 1, + .guest_code = guest_code_test_memslot_unmap, + .loop = test_memslot_unmap_loop, + }, + { + .name = "unmap chunked", + .mem_size = MEM_TEST_UNMAP_SIZE_PAGES + 1, + .guest_code = guest_code_test_memslot_unmap, + .loop = test_memslot_unmap_loop_chunked, + }, + { + .name = "move active area", + .guest_code = guest_code_test_memslot_move, + .prepare = test_memslot_move_prepare_active, + .loop = test_memslot_move_loop, + }, + { + .name = "move inactive area", + .guest_code = guest_code_test_memslot_move, + .prepare = test_memslot_move_prepare_inactive, + .loop = test_memslot_move_loop, + }, + { + .name = "RW", + .guest_code = guest_code_test_memslot_rw, + .loop = test_memslot_rw_loop + }, +}; + +#define NTESTS ARRAY_SIZE(tests) + +struct test_args { + int tfirst; + int tlast; + int nslots; + int seconds; + int runs; +}; + +static void help(char *name, struct test_args *targs) +{ + int ctr; + + pr_info("usage: %s [-h] [-v] [-d] [-s slots] [-f first_test] [-e last_test] [-l test_length] [-r run_count]\n", + name); + pr_info(" -h: print this help screen.\n"); + pr_info(" -v: enable verbose mode (not for benchmarking).\n"); + pr_info(" -d: enable extra debug checks.\n"); + pr_info(" -s: specify memslot count cap (-1 means no cap; currently: %i)\n", + targs->nslots); + pr_info(" -f: specify the first test to run (currently: %i; max %zu)\n", + targs->tfirst, NTESTS - 1); + pr_info(" -e: specify the last test to run (currently: %i; max %zu)\n", + targs->tlast, NTESTS - 1); + pr_info(" -l: specify the test length in seconds (currently: %i)\n", + targs->seconds); + pr_info(" -r: specify the number of runs per test (currently: %i)\n", + targs->runs); + + pr_info("\nAvailable tests:\n"); + for (ctr = 0; ctr < NTESTS; ctr++) + pr_info("%d: %s\n", ctr, tests[ctr].name); +} + +static bool parse_args(int argc, char *argv[], + struct test_args *targs) +{ + int opt; + + while ((opt = getopt(argc, argv, "hvds:f:e:l:r:")) != -1) { + switch (opt) { + case 'h': + default: + help(argv[0], targs); + return false; + case 'v': + verbose = true; + break; + case 'd': + map_unmap_verify = true; + break; + case 's': + targs->nslots = atoi(optarg); + if (targs->nslots <= 0 && targs->nslots != -1) { + pr_info("Slot count cap has to be positive or -1 for no cap\n"); + return false; + } + break; + case 'f': + targs->tfirst = atoi(optarg); + if (targs->tfirst < 0) { + pr_info("First test to run has to be non-negative\n"); + return false; + } + break; + case 'e': + targs->tlast = atoi(optarg); + if (targs->tlast < 0 || targs->tlast >= NTESTS) { + pr_info("Last test to run has to be non-negative and less than %zu\n", + NTESTS); + return false; + } + break; + case 'l': + targs->seconds = atoi(optarg); + if (targs->seconds < 0) { + pr_info("Test length in seconds has to be non-negative\n"); + return false; + } + break; + case 'r': + targs->runs = atoi(optarg); + if (targs->runs <= 0) { + pr_info("Runs per test has to be positive\n"); + return false; + } + break; + } + } + + if (optind < argc) { + help(argv[0], targs); + return false; + } + + if (targs->tfirst > targs->tlast) { + pr_info("First test to run cannot be greater than the last test to run\n"); + return false; + } + + return true; +} + +struct test_result { + struct timespec slot_runtime, guest_runtime, iter_runtime; + int64_t slottimens, runtimens; + uint64_t nloops; +}; + +static bool test_loop(const struct test_data *data, + const struct test_args *targs, + struct test_result *rbestslottime, + struct test_result *rbestruntime) +{ + uint64_t maxslots; + struct test_result result; + + result.nloops = 0; + if (!test_execute(targs->nslots, &maxslots, targs->seconds, data, + &result.nloops, + &result.slot_runtime, &result.guest_runtime)) { + if (maxslots) + pr_info("Memslot count too high for this test, decrease the cap (max is %"PRIu64")\n", + maxslots); + else + pr_info("Memslot count may be too high for this test, try adjusting the cap\n"); + + return false; + } + + pr_info("Test took %ld.%.9lds for slot setup + %ld.%.9lds all iterations\n", + result.slot_runtime.tv_sec, result.slot_runtime.tv_nsec, + result.guest_runtime.tv_sec, result.guest_runtime.tv_nsec); + if (!result.nloops) { + pr_info("No full loops done - too short test time or system too loaded?\n"); + return true; + } + + result.iter_runtime = timespec_div(result.guest_runtime, + result.nloops); + pr_info("Done %"PRIu64" iterations, avg %ld.%.9lds each\n", + result.nloops, + result.iter_runtime.tv_sec, + result.iter_runtime.tv_nsec); + result.slottimens = timespec_to_ns(result.slot_runtime); + result.runtimens = timespec_to_ns(result.iter_runtime); + + /* + * Only rank the slot setup time for tests using the whole test memory + * area so they are comparable + */ + if (!data->mem_size && + (!rbestslottime->slottimens || + result.slottimens < rbestslottime->slottimens)) + *rbestslottime = result; + if (!rbestruntime->runtimens || + result.runtimens < rbestruntime->runtimens) + *rbestruntime = result; + + return true; +} + +int main(int argc, char *argv[]) +{ + struct test_args targs = { + .tfirst = 0, + .tlast = NTESTS - 1, + .nslots = -1, + .seconds = 5, + .runs = 1, + }; + struct test_result rbestslottime; + int tctr; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + if (!parse_args(argc, argv, &targs)) + return -1; + + rbestslottime.slottimens = 0; + for (tctr = targs.tfirst; tctr <= targs.tlast; tctr++) { + const struct test_data *data = &tests[tctr]; + unsigned int runctr; + struct test_result rbestruntime; + + if (tctr > targs.tfirst) + pr_info("\n"); + + pr_info("Testing %s performance with %i runs, %d seconds each\n", + data->name, targs.runs, targs.seconds); + + rbestruntime.runtimens = 0; + for (runctr = 0; runctr < targs.runs; runctr++) + if (!test_loop(data, &targs, + &rbestslottime, &rbestruntime)) + break; + + if (rbestruntime.runtimens) + pr_info("Best runtime result was %ld.%.9lds per iteration (with %"PRIu64" iterations)\n", + rbestruntime.iter_runtime.tv_sec, + rbestruntime.iter_runtime.tv_nsec, + rbestruntime.nloops); + } + + if (rbestslottime.slottimens) + pr_info("Best slot setup time for the whole test area was %ld.%.9lds\n", + rbestslottime.slot_runtime.tv_sec, + rbestslottime.slot_runtime.tv_nsec); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c index 9b78e8889638..8c77537af5a1 100644 --- a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c +++ b/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c @@ -19,7 +19,12 @@ struct { u32 function; u32 index; } mangled_cpuids[] = { + /* + * These entries depend on the vCPU's XCR0 register and IA32_XSS MSR, + * which are not controlled for by this test. + */ {.function = 0xd, .index = 0}, + {.function = 0xd, .index = 1}, }; static void test_guest_cpuids(struct kvm_cpuid2 *guest_cpuid) diff --git a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c index cb953df4d7d0..8aed0db1331d 100644 --- a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c +++ b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c @@ -37,9 +37,7 @@ static void test_get_msr_index(void) int old_res, res, kvm_fd, r; struct kvm_msr_list *list; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); old_res = kvm_num_index_msrs(kvm_fd, 0); TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0"); @@ -101,9 +99,7 @@ static void test_get_msr_feature(void) int res, old_res, i, kvm_fd; struct kvm_msr_list *feature_list; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); old_res = kvm_num_feature_msrs(kvm_fd, 0); TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0"); diff --git a/tools/testing/selftests/nci/.gitignore b/tools/testing/selftests/nci/.gitignore new file mode 100644 index 000000000000..448eeb4590fc --- /dev/null +++ b/tools/testing/selftests/nci/.gitignore @@ -0,0 +1 @@ +/nci_dev diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json index 1cda2e11b3ad..773c5027553d 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json @@ -9,11 +9,11 @@ "setup": [ "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY root fq_pie flows 65536", - "expExitCode": "2", + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_pie flows 65536", + "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc", - "matchCount": "0", + "matchPattern": "qdisc fq_pie 1: root refcnt 2 limit 10240p flows 65536", + "matchCount": "1", "teardown": [ "$IP link del dev $DUMMY" ] diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 6b4feb92dc79..6a6bc7af0e28 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -307,6 +307,7 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) { return kvm_make_all_cpus_request_except(kvm, req, NULL); } +EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request); #ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL void kvm_flush_remote_tlbs(struct kvm *kvm) @@ -2929,6 +2930,8 @@ static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu) goto out; if (signal_pending(current)) goto out; + if (kvm_check_request(KVM_REQ_UNBLOCK, vcpu)) + goto out; ret = 0; out: @@ -2973,8 +2976,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) goto out; } poll_end = cur = ktime_get(); - } while (single_task_running() && !need_resched() && - ktime_before(cur, stop)); + } while (kvm_vcpu_can_poll(cur, stop)); } prepare_to_rcuwait(&vcpu->wait); diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c index c9bb3957f58a..28fda42e471b 100644 --- a/virt/lib/irqbypass.c +++ b/virt/lib/irqbypass.c @@ -40,21 +40,17 @@ static int __connect(struct irq_bypass_producer *prod, if (prod->add_consumer) ret = prod->add_consumer(prod, cons); - if (ret) - goto err_add_consumer; - - ret = cons->add_producer(cons, prod); - if (ret) - goto err_add_producer; + if (!ret) { + ret = cons->add_producer(cons, prod); + if (ret && prod->del_consumer) + prod->del_consumer(prod, cons); + } if (cons->start) cons->start(cons); if (prod->start) prod->start(prod); -err_add_producer: - if (prod->del_consumer) - prod->del_consumer(prod, cons); -err_add_consumer: + return ret; } |