diff options
249 files changed, 2911 insertions, 1236 deletions
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index c7b165ca70b6..dae68e68ca23 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -855,7 +855,7 @@ in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to use PPIs designated for specific cpus. The irq field is interpreted like this:: -  bits: | 31 ... 28 | 27 ... 24 | 23 ... 16 | 15 ... 0 | + bits: | 31 ... 28 | 27 ... 24 | 23 ... 16 | 15 ... 0 | field: | vcpu2_index | irq_type | vcpu_index | irq_id | The irq_type field has the following values: @@ -2149,10 +2149,10 @@ prior to calling the KVM_RUN ioctl. Errors: ====== ============================================================ -  ENOENT   no such register -  EINVAL   invalid register ID, or no such register or used with VMs in + ENOENT no such register + EINVAL invalid register ID, or no such register or used with VMs in protected virtualization mode on s390 -  EPERM    (arm64) register access not allowed before vcpu finalization + EPERM (arm64) register access not allowed before vcpu finalization ====== ============================================================ (These error codes are indicative only: do not rely on a specific error @@ -2590,10 +2590,10 @@ following id bit patterns:: Errors include: ======== ============================================================ -  ENOENT   no such register -  EINVAL   invalid register ID, or no such register or used with VMs in + ENOENT no such register + EINVAL invalid register ID, or no such register or used with VMs in protected virtualization mode on s390 -  EPERM    (arm64) register access not allowed before vcpu finalization + EPERM (arm64) register access not allowed before vcpu finalization ======== ============================================================ (These error codes are indicative only: do not rely on a specific error @@ -3112,13 +3112,13 @@ current state. "addr" is ignored. Errors: ====== ================================================================= -  EINVAL    the target is unknown, or the combination of features is invalid. -  ENOENT    a features bit specified is unknown. + EINVAL the target is unknown, or the combination of features is invalid. + ENOENT a features bit specified is unknown. ====== ================================================================= This tells KVM what type of CPU to present to the guest, and what -optional features it should have.  This will cause a reset of the cpu -registers to their initial values.  If this is not called, KVM_RUN will +optional features it should have. This will cause a reset of the cpu +registers to their initial values. If this is not called, KVM_RUN will return ENOEXEC for that vcpu. The initial values are defined as: @@ -3239,8 +3239,8 @@ VCPU matching underlying host. Errors: ===== ============================================================== -  E2BIG     the reg index list is too big to fit in the array specified by -             the user (the number required will be written into n). + E2BIG the reg index list is too big to fit in the array specified by + the user (the number required will be written into n). ===== ============================================================== :: @@ -3288,7 +3288,7 @@ specific device. ARM/arm64 divides the id field into two parts, a device id and an address type id specific to the individual device:: -  bits: | 63 ... 32 | 31 ... 16 | 15 ... 0 | + bits: | 63 ... 32 | 31 ... 16 | 15 ... 0 | field: | 0x00000000 | device id | addr type id | ARM/arm64 currently only require this when using the in-kernel GIC @@ -7049,7 +7049,7 @@ In combination with KVM_CAP_X86_USER_SPACE_MSR, this allows user space to trap and emulate MSRs that are outside of the scope of KVM as well as limit the attack surface on KVM's MSR emulation code. -8.28 KVM_CAP_ENFORCE_PV_CPUID +8.28 KVM_CAP_ENFORCE_PV_FEATURE_CPUID ----------------------------- Architectures: x86 diff --git a/MAINTAINERS b/MAINTAINERS index 19135a9d778e..c9467d2839f5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7858,9 +7858,9 @@ S: Maintained F: drivers/input/touchscreen/goodix.c GOOGLE ETHERNET DRIVERS -M: Catherine Sullivan <csully@google.com> -R: Sagi Shahar <sagis@google.com> -R: Jon Olson <jonolson@google.com> +M: Jeroen de Borst <jeroendb@google.com> +R: Catherine Sullivan <csully@google.com> +R: David Awogbemila <awogbemila@google.com> L: netdev@vger.kernel.org S: Supported F: Documentation/networking/device_drivers/ethernet/google/gve.rst @@ -11327,6 +11327,12 @@ W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git F: drivers/media/radio/radio-maxiradio* +MCAB MICROCHIP CAN BUS ANALYZER TOOL DRIVER +R: Yasushi SHOJI <yashi@spacecubics.com> +L: linux-can@vger.kernel.org +S: Maintained +F: drivers/net/can/usb/mcba_usb.c + MCAN MMIO DEVICE DRIVER M: Chandrasekar Ramakrishnan <rcsekar@samsung.com> L: linux-can@vger.kernel.org @@ -15468,6 +15474,8 @@ M: Pan, Xinhui <Xinhui.Pan@amd.com> L: amd-gfx@lists.freedesktop.org S: Supported T: git https://gitlab.freedesktop.org/agd5f/linux.git +B: https://gitlab.freedesktop.org/drm/amd/-/issues +C: irc://irc.oftc.net/radeon F: drivers/gpu/drm/amd/ F: drivers/gpu/drm/radeon/ F: include/uapi/drm/amdgpu_drm.h diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 77d3280dc678..6c50877841df 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -14,7 +14,6 @@ config ALPHA select PCI_SYSCALL if PCI select HAVE_AOUT select HAVE_ASM_MODVERSIONS - select HAVE_IDE select HAVE_PCSPKR_PLATFORM select HAVE_PERF_EVENTS select NEED_DMA_MAP_STATE @@ -532,7 +531,7 @@ config SMP will run faster if you say N here. See also the SMP-HOWTO available at - <http://www.tldp.org/docs.html#howto>. + <https://www.tldp.org/docs.html#howto>. If you don't know what to do here, say N. diff --git a/arch/alpha/boot/bootp.c b/arch/alpha/boot/bootp.c index 00266e6e1b71..b4faba2432d5 100644 --- a/arch/alpha/boot/bootp.c +++ b/arch/alpha/boot/bootp.c @@ -23,7 +23,7 @@ #include "ksize.h" extern unsigned long switch_to_osf_pal(unsigned long nr, - struct pcb_struct * pcb_va, struct pcb_struct * pcb_pa, + struct pcb_struct *pcb_va, struct pcb_struct *pcb_pa, unsigned long *vptb); extern void move_stack(unsigned long new_stack); diff --git a/arch/alpha/boot/bootpz.c b/arch/alpha/boot/bootpz.c index 43af71835adf..90a2b341e9c0 100644 --- a/arch/alpha/boot/bootpz.c +++ b/arch/alpha/boot/bootpz.c @@ -200,7 +200,7 @@ extern char _end; START_ADDR KSEG address of the entry point of kernel code. ZERO_PGE KSEG address of page full of zeroes, but - upon entry to kerne cvan be expected + upon entry to kernel, it can be expected to hold the parameter list and possible INTRD information. diff --git a/arch/alpha/boot/misc.c b/arch/alpha/boot/misc.c index d65192202703..325d4dd4f904 100644 --- a/arch/alpha/boot/misc.c +++ b/arch/alpha/boot/misc.c @@ -30,7 +30,7 @@ extern long srm_printk(const char *, ...) __attribute__ ((format (printf, 1, 2))); /* - * gzip delarations + * gzip declarations */ #define OF(args) args #define STATIC static diff --git a/arch/alpha/configs/defconfig b/arch/alpha/configs/defconfig index dd2dd9f0861f..7f1ca30b115b 100644 --- a/arch/alpha/configs/defconfig +++ b/arch/alpha/configs/defconfig @@ -70,3 +70,4 @@ CONFIG_DEBUG_INFO=y CONFIG_ALPHA_LEGACY_START_ADDRESS=y CONFIG_MATHEMU=y CONFIG_CRYPTO_HMAC=y +CONFIG_DEVTMPFS=y diff --git a/arch/alpha/include/asm/compiler.h b/arch/alpha/include/asm/compiler.h index 5159ba259d65..ae645959018a 100644 --- a/arch/alpha/include/asm/compiler.h +++ b/arch/alpha/include/asm/compiler.h @@ -4,15 +4,4 @@ #include <uapi/asm/compiler.h> -/* Some idiots over in <linux/compiler.h> thought inline should imply - always_inline. This breaks stuff. We'll include this file whenever - we run into such problems. */ - -#include <linux/compiler.h> -#undef inline -#undef __inline__ -#undef __inline -#undef __always_inline -#define __always_inline inline __attribute__((always_inline)) - #endif /* __ALPHA_COMPILER_H */ diff --git a/arch/alpha/include/asm/syscall.h b/arch/alpha/include/asm/syscall.h index 11c688c1d7ec..f21babaeed85 100644 --- a/arch/alpha/include/asm/syscall.h +++ b/arch/alpha/include/asm/syscall.h @@ -9,4 +9,10 @@ static inline int syscall_get_arch(struct task_struct *task) return AUDIT_ARCH_ALPHA; } +static inline long syscall_get_return_value(struct task_struct *task, + struct pt_regs *regs) +{ + return regs->r0; +} + #endif /* _ASM_ALPHA_SYSCALL_H */ diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index d5367a1c6300..d31167e3269c 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -834,7 +834,7 @@ SYSCALL_DEFINE5(osf_setsysinfo, unsigned long, op, void __user *, buffer, return -EFAULT; state = ¤t_thread_info()->ieee_state; - /* Update softare trap enable bits. */ + /* Update software trap enable bits. */ *state = (*state & ~IEEE_SW_MASK) | (swcr & IEEE_SW_MASK); /* Update the real fpcr. */ @@ -854,7 +854,7 @@ SYSCALL_DEFINE5(osf_setsysinfo, unsigned long, op, void __user *, buffer, state = ¤t_thread_info()->ieee_state; exc &= IEEE_STATUS_MASK; - /* Update softare trap enable bits. */ + /* Update software trap enable bits. */ swcr = (*state & IEEE_SW_MASK) | exc; *state |= exc; diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c index e7a59d927d78..efcf7321701b 100644 --- a/arch/alpha/kernel/perf_event.c +++ b/arch/alpha/kernel/perf_event.c @@ -574,7 +574,7 @@ static void alpha_pmu_start(struct perf_event *event, int flags) * Check that CPU performance counters are supported. * - currently support EV67 and later CPUs. * - actually some later revisions of the EV6 have the same PMC model as the - * EV67 but we don't do suffiently deep CPU detection to detect them. + * EV67 but we don't do sufficiently deep CPU detection to detect them. * Bad luck to the very few people who might have one, I guess. */ static int supported_cpu(void) diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index ef0c08ed0481..a5123ea426ce 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -256,7 +256,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, childstack->r26 = (unsigned long) ret_from_kernel_thread; childstack->r9 = usp; /* function */ childstack->r10 = kthread_arg; - childregs->hae = alpha_mv.hae_cache, + childregs->hae = alpha_mv.hae_cache; childti->pcb.usp = 0; return 0; } diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index 7d56c217b235..b4fbbba30aa2 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -319,18 +319,19 @@ setup_memory(void *kernel_end) i, cluster->usage, cluster->start_pfn, cluster->start_pfn + cluster->numpages); - /* Bit 0 is console/PALcode reserved. Bit 1 is - non-volatile memory -- we might want to mark - this for later. */ - if (cluster->usage & 3) - continue; - end = cluster->start_pfn + cluster->numpages; if (end > max_low_pfn) max_low_pfn = end; memblock_add(PFN_PHYS(cluster->start_pfn), cluster->numpages << PAGE_SHIFT); + + /* Bit 0 is console/PALcode reserved. Bit 1 is + non-volatile memory -- we might want to mark + this for later. */ + if (cluster->usage & 3) + memblock_reserve(PFN_PHYS(cluster->start_pfn), + cluster->numpages << PAGE_SHIFT); } /* diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 4b2575f936d4..cb64e4797d2a 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -582,7 +582,7 @@ void smp_send_stop(void) { cpumask_t to_whom; - cpumask_copy(&to_whom, cpu_possible_mask); + cpumask_copy(&to_whom, cpu_online_mask); cpumask_clear_cpu(smp_processor_id(), &to_whom); #ifdef DEBUG_IPI_MSG if (hard_smp_processor_id() != boot_cpu_id) diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c index 53adf43dcd44..96fd6ff3fe81 100644 --- a/arch/alpha/kernel/sys_nautilus.c +++ b/arch/alpha/kernel/sys_nautilus.c @@ -212,7 +212,7 @@ nautilus_init_pci(void) /* Use default IO. */ pci_add_resource(&bridge->windows, &ioport_resource); - /* Irongate PCI memory aperture, calculate requred size before + /* Irongate PCI memory aperture, calculate required size before setting it up. */ pci_add_resource(&bridge->windows, &irongate_mem); diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index 921d4b6e4d95..5398f982bdd1 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -730,7 +730,7 @@ do_entUnaUser(void __user * va, unsigned long opcode, long error; /* Check the UAC bits to decide what the user wants us to do - with the unaliged access. */ + with the unaligned access. */ if (!(current_thread_info()->status & TS_UAC_NOPRINT)) { if (__ratelimit(&ratelimit)) { diff --git a/arch/alpha/math-emu/math.c b/arch/alpha/math-emu/math.c index d568cd9a3e43..f7cef66af88d 100644 --- a/arch/alpha/math-emu/math.c +++ b/arch/alpha/math-emu/math.c @@ -65,7 +65,7 @@ static long (*save_emul) (unsigned long pc); long do_alpha_fp_emul_imprecise(struct pt_regs *, unsigned long); long do_alpha_fp_emul(unsigned long); -int init_module(void) +static int alpha_fp_emul_init_module(void) { save_emul_imprecise = alpha_fp_emul_imprecise; save_emul = alpha_fp_emul; @@ -73,12 +73,14 @@ int init_module(void) alpha_fp_emul = do_alpha_fp_emul; return 0; } +module_init(alpha_fp_emul_init_module); -void cleanup_module(void) +static void alpha_fp_emul_cleanup_module(void) { alpha_fp_emul_imprecise = save_emul_imprecise; alpha_fp_emul = save_emul; } +module_exit(alpha_fp_emul_cleanup_module); #undef alpha_fp_emul_imprecise #define alpha_fp_emul_imprecise do_alpha_fp_emul_imprecise @@ -401,3 +403,5 @@ alpha_fp_emul_imprecise (struct pt_regs *regs, unsigned long write_mask) egress: return si_code; } + +EXPORT_SYMBOL(__udiv_qrnnd); diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 82f908fa5676..2fb7012c3246 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -95,7 +95,6 @@ config ARM select HAVE_FUNCTION_TRACER if !XIP_KERNEL select HAVE_GCC_PLUGINS select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7) - select HAVE_IDE if PCI || ISA || PCMCIA select HAVE_IRQ_TIME_ACCOUNTING select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 @@ -361,7 +360,6 @@ config ARCH_FOOTBRIDGE bool "FootBridge" select CPU_SA110 select FOOTBRIDGE - select HAVE_IDE select NEED_MACH_IO_H if !MMU select NEED_MACH_MEMORY_H help @@ -430,7 +428,6 @@ config ARCH_PXA select GENERIC_IRQ_MULTI_HANDLER select GPIO_PXA select GPIOLIB - select HAVE_IDE select IRQ_DOMAIN select PLAT_PXA select SPARSE_IRQ @@ -446,7 +443,6 @@ config ARCH_RPC select ARM_HAS_SG_CHAIN select CPU_SA110 select FIQ - select HAVE_IDE select HAVE_PATA_PLATFORM select ISA_DMA_API select LEGACY_TIMER_TICK @@ -469,7 +465,6 @@ config ARCH_SA1100 select CPU_SA1100 select GENERIC_IRQ_MULTI_HANDLER select GPIOLIB - select HAVE_IDE select IRQ_DOMAIN select ISA select NEED_MACH_MEMORY_H @@ -505,7 +500,6 @@ config ARCH_OMAP1 select GENERIC_IRQ_CHIP select GENERIC_IRQ_MULTI_HANDLER select GPIOLIB - select HAVE_IDE select HAVE_LEGACY_CLK select IRQ_DOMAIN select NEED_MACH_IO_H if PCCARD diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig index de11030748d0..1d3aef84287d 100644 --- a/arch/arm/mach-davinci/Kconfig +++ b/arch/arm/mach-davinci/Kconfig @@ -9,7 +9,6 @@ menuconfig ARCH_DAVINCI select PM_GENERIC_DOMAINS_OF if PM && OF select REGMAP_MMIO select RESET_CONTROLLER - select HAVE_IDE select PINCTRL_SINGLE if ARCH_DAVINCI diff --git a/arch/arm/mach-rpc/riscpc.c b/arch/arm/mach-rpc/riscpc.c index d23970bd638d..f70fb9c4b0cb 100644 --- a/arch/arm/mach-rpc/riscpc.c +++ b/arch/arm/mach-rpc/riscpc.c @@ -49,6 +49,7 @@ static int __init parse_tag_acorn(const struct tag *tag) fallthrough; /* ??? */ case 256: vram_size += PAGE_SIZE * 256; + break; default: break; } diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 897634d0a67c..a951276f0547 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -1602,6 +1602,9 @@ exit: rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx); emit_ldx_r(dst, rn, off, ctx, BPF_SIZE(code)); break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; /* ST: *(size *)(dst + off) = imm */ case BPF_ST | BPF_MEM | BPF_W: case BPF_ST | BPF_MEM | BPF_H: diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index ca38d0d6c3c4..f4eaab3ecf03 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -579,7 +579,7 @@ }; flexcan1: can@308c0000 { - compatible = "fsl,imx8mp-flexcan", "fsl,imx6q-flexcan"; + compatible = "fsl,imx8mp-flexcan"; reg = <0x308c0000 0x10000>; interrupts = <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MP_CLK_IPG_ROOT>, @@ -594,7 +594,7 @@ }; flexcan2: can@308d0000 { - compatible = "fsl,imx8mp-flexcan", "fsl,imx6q-flexcan"; + compatible = "fsl,imx8mp-flexcan"; reg = <0x308d0000 0x10000>; interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MP_CLK_IPG_ROOT>, diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 3155c9e778f0..0625bf2353c2 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -947,7 +947,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, vma_shift = get_vma_page_shift(vma, hva); } - shared = (vma->vm_flags & VM_PFNMAP); + shared = (vma->vm_flags & VM_SHARED); switch (vma_shift) { #ifndef __PAGETABLE_PMD_FOLDED diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index dccf98a37283..41c23f474ea6 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -823,6 +823,19 @@ emit_cond_jmp: return ret; break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + /* + * Nothing required here. + * + * In case of arm64, we rely on the firmware mitigation of + * Speculative Store Bypass as controlled via the ssbd kernel + * parameter. Whenever the mitigation is enabled, it works + * for all of the kernel code with no need to provide any + * additional instructions. + */ + break; + /* ST: *(size *)(dst + off) = imm */ case BPF_ST | BPF_MEM | BPF_W: case BPF_ST | BPF_MEM | BPF_H: diff --git a/arch/h8300/Kconfig.cpu b/arch/h8300/Kconfig.cpu index b5e14d513e62..c30baa0499fc 100644 --- a/arch/h8300/Kconfig.cpu +++ b/arch/h8300/Kconfig.cpu @@ -44,7 +44,6 @@ config H8300_H8MAX bool "H8MAX" select H83069 select RAMKERNEL - select HAVE_IDE help H8MAX Evaluation Board Support More Information. (Japanese Only) diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index cf425c2c63af..4993c7ac7ff6 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -25,7 +25,6 @@ config IA64 select HAVE_ASM_MODVERSIONS select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_EXIT_THREAD - select HAVE_IDE select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_FTRACE_MCOUNT_RECORD diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 96989ad46f66..d632a1d576f9 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -23,7 +23,6 @@ config M68K select HAVE_DEBUG_BUGVERBOSE select HAVE_EFFICIENT_UNALIGNED_ACCESS if !CPU_HAS_NO_UNALIGNED select HAVE_FUTEX_CMPXCHG if MMU && FUTEX - select HAVE_IDE select HAVE_MOD_ARCH_SPECIFIC select HAVE_UID16 select MMU_GATHER_NO_RANGE if MMU diff --git a/arch/m68k/coldfire/m525x.c b/arch/m68k/coldfire/m525x.c index 2c4d2ca2f20d..485375112e28 100644 --- a/arch/m68k/coldfire/m525x.c +++ b/arch/m68k/coldfire/m525x.c @@ -26,7 +26,7 @@ DEFINE_CLK(pll, "pll.0", MCF_CLK); DEFINE_CLK(sys, "sys.0", MCF_BUSCLK); static struct clk_lookup m525x_clk_lookup[] = { - CLKDEV_INIT(NULL, "pll.0", &pll), + CLKDEV_INIT(NULL, "pll.0", &clk_pll), CLKDEV_INIT(NULL, "sys.0", &clk_sys), CLKDEV_INIT("mcftmr.0", NULL, &clk_sys), CLKDEV_INIT("mcftmr.1", NULL, &clk_sys), diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index cee6087cd686..6dfb27d531dd 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -71,7 +71,6 @@ config MIPS select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS select HAVE_GENERIC_VDSO - select HAVE_IDE select HAVE_IOREMAP_PROT select HAVE_IRQ_EXIT_ON_IRQ_STACK select HAVE_IRQ_TIME_ACCOUNTING diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index 939dd06764bc..3a73e9375712 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -1355,6 +1355,9 @@ jeq_common: } break; + case BPF_ST | BPF_NOSPEC: /* speculation barrier */ + break; + case BPF_ST | BPF_B | BPF_MEM: case BPF_ST | BPF_H | BPF_MEM: case BPF_ST | BPF_W | BPF_MEM: diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index bde9907bc5b2..4f8c1fbf8f2f 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -3,7 +3,6 @@ config PARISC def_bool y select ARCH_32BIT_OFF_T if !64BIT select ARCH_MIGHT_HAVE_PC_PARPORT - select HAVE_IDE select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER select HAVE_SYSCALL_TRACEPOINTS diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index d01e3401581d..663766fbf505 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -220,7 +220,6 @@ config PPC select HAVE_HARDLOCKUP_DETECTOR_ARCH if PPC_BOOK3S_64 && SMP select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx) - select HAVE_IDE select HAVE_IOREMAP_PROT select HAVE_IRQ_EXIT_ON_IRQ_STACK select HAVE_IRQ_TIME_ACCOUNTING diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index 2813e3f98db6..3c5baaa6f1e7 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -27,6 +27,13 @@ KASAN_SANITIZE := n ccflags-y := -shared -fno-common -fno-builtin -nostdlib \ -Wl,-soname=linux-vdso64.so.1 -Wl,--hash-style=both + +# Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true +# by accident when the VDSO was hand-written asm code, but may not be now that the VDSO is +# compiler generated. To avoid breaking Go tell GCC not to use r30. Impact on code +# generation is minimal, it will just use r29 instead. +ccflags-y += $(call cc-option, -ffixed-r30) + asflags-y := -D__VDSO64__ -s targets += vdso64.lds diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index 34bb1583fc0c..beb12cbc8c29 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -738,6 +738,12 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * break; /* + * BPF_ST NOSPEC (speculation barrier) + */ + case BPF_ST | BPF_NOSPEC: + break; + + /* * BPF_ST(X) */ case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src */ diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index de8595880fee..b87a63dba9c8 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -628,6 +628,12 @@ emit_clear: break; /* + * BPF_ST NOSPEC (speculation barrier) + */ + case BPF_ST | BPF_NOSPEC: + break; + + /* * BPF_ST(X) */ case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src */ diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 631a0d57b6cd..6b0886668465 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -77,7 +77,7 @@ #include "../../../../drivers/pci/pci.h" DEFINE_STATIC_KEY_FALSE(shared_processor); -EXPORT_SYMBOL_GPL(shared_processor); +EXPORT_SYMBOL(shared_processor); int CMO_PrPSP = -1; int CMO_SecPSP = -1; diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c index 81de865f4c7c..e6497424cbf6 100644 --- a/arch/riscv/net/bpf_jit_comp32.c +++ b/arch/riscv/net/bpf_jit_comp32.c @@ -1251,6 +1251,10 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, return -1; break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; + case BPF_ST | BPF_MEM | BPF_B: case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_W: diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 87e3bf5b9086..3af4131c22c7 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -939,6 +939,10 @@ out_be: emit_ld(rd, 0, RV_REG_T1, ctx); break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; + /* ST: *(size *)(dst + off) = imm */ case BPF_ST | BPF_MEM | BPF_B: emit_imm(RV_REG_T1, imm, ctx); diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 9b4473f76e56..161a9e12bfb8 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -445,15 +445,15 @@ struct kvm_vcpu_stat { u64 instruction_sigp_init_cpu_reset; u64 instruction_sigp_cpu_reset; u64 instruction_sigp_unknown; - u64 diagnose_10; - u64 diagnose_44; - u64 diagnose_9c; - u64 diagnose_9c_ignored; - u64 diagnose_9c_forward; - u64 diagnose_258; - u64 diagnose_308; - u64 diagnose_500; - u64 diagnose_other; + u64 instruction_diagnose_10; + u64 instruction_diagnose_44; + u64 instruction_diagnose_9c; + u64 diag_9c_ignored; + u64 diag_9c_forward; + u64 instruction_diagnose_258; + u64 instruction_diagnose_308; + u64 instruction_diagnose_500; + u64 instruction_diagnose_other; u64 pfault_sync; }; diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 02c146f9e5cd..807fa9da1e72 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -24,7 +24,7 @@ static int diag_release_pages(struct kvm_vcpu *vcpu) start = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4]; end = vcpu->run->s.regs.gprs[vcpu->arch.sie_block->ipa & 0xf] + PAGE_SIZE; - vcpu->stat.diagnose_10++; + vcpu->stat.instruction_diagnose_10++; if (start & ~PAGE_MASK || end & ~PAGE_MASK || start >= end || start < 2 * PAGE_SIZE) @@ -74,7 +74,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu) VCPU_EVENT(vcpu, 3, "diag page reference parameter block at 0x%llx", vcpu->run->s.regs.gprs[rx]); - vcpu->stat.diagnose_258++; + vcpu->stat.instruction_diagnose_258++; if (vcpu->run->s.regs.gprs[rx] & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], rx, &parm, sizeof(parm)); @@ -145,7 +145,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu) static int __diag_time_slice_end(struct kvm_vcpu *vcpu) { VCPU_EVENT(vcpu, 5, "%s", "diag time slice end"); - vcpu->stat.diagnose_44++; + vcpu->stat.instruction_diagnose_44++; kvm_vcpu_on_spin(vcpu, true); return 0; } @@ -169,7 +169,7 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu) int tid; tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4]; - vcpu->stat.diagnose_9c++; + vcpu->stat.instruction_diagnose_9c++; /* yield to self */ if (tid == vcpu->vcpu_id) @@ -192,7 +192,7 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu) VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d: yield forwarded", tid); - vcpu->stat.diagnose_9c_forward++; + vcpu->stat.diag_9c_forward++; return 0; } @@ -203,7 +203,7 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu) return 0; no_yield: VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d: ignored", tid); - vcpu->stat.diagnose_9c_ignored++; + vcpu->stat.diag_9c_ignored++; return 0; } @@ -213,7 +213,7 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu) unsigned long subcode = vcpu->run->s.regs.gprs[reg] & 0xffff; VCPU_EVENT(vcpu, 3, "diag ipl functions, subcode %lx", subcode); - vcpu->stat.diagnose_308++; + vcpu->stat.instruction_diagnose_308++; switch (subcode) { case 3: vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR; @@ -245,7 +245,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu) { int ret; - vcpu->stat.diagnose_500++; + vcpu->stat.instruction_diagnose_500++; /* No virtio-ccw notification? Get out quickly. */ if (!vcpu->kvm->arch.css_support || (vcpu->run->s.regs.gprs[1] != KVM_S390_VIRTIO_CCW_NOTIFY)) @@ -299,7 +299,7 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu) case 0x500: return __diag_virtio_hypercall(vcpu); default: - vcpu->stat.diagnose_other++; + vcpu->stat.instruction_diagnose_other++; return -EOPNOTSUPP; } } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index b655a7d82bf0..4527ac7b5961 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -163,15 +163,15 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, instruction_sigp_init_cpu_reset), STATS_DESC_COUNTER(VCPU, instruction_sigp_cpu_reset), STATS_DESC_COUNTER(VCPU, instruction_sigp_unknown), - STATS_DESC_COUNTER(VCPU, diagnose_10), - STATS_DESC_COUNTER(VCPU, diagnose_44), - STATS_DESC_COUNTER(VCPU, diagnose_9c), - STATS_DESC_COUNTER(VCPU, diagnose_9c_ignored), - STATS_DESC_COUNTER(VCPU, diagnose_9c_forward), - STATS_DESC_COUNTER(VCPU, diagnose_258), - STATS_DESC_COUNTER(VCPU, diagnose_308), - STATS_DESC_COUNTER(VCPU, diagnose_500), - STATS_DESC_COUNTER(VCPU, diagnose_other), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_10), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_44), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_9c), + STATS_DESC_COUNTER(VCPU, diag_9c_ignored), + STATS_DESC_COUNTER(VCPU, diag_9c_forward), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_258), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_308), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_500), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_other), STATS_DESC_COUNTER(VCPU, pfault_sync) }; static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 2ae419f5115a..88419263a89a 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1154,6 +1154,11 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, } break; /* + * BPF_NOSPEC (speculation barrier) + */ + case BPF_ST | BPF_NOSPEC: + break; + /* * BPF_ST(X) */ case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src_reg */ diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 45a0549421cd..b683b69a4556 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -39,7 +39,6 @@ config SUPERH select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_FTRACE_MCOUNT_RECORD select HAVE_HW_BREAKPOINT - select HAVE_IDE if HAS_IOPORT_MAP select HAVE_IOREMAP_PROT if MMU && !X2TLB select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index c5fa7932b550..f0c0f955e169 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -19,7 +19,6 @@ config SPARC select OF select OF_PROMTREE select HAVE_ASM_MODVERSIONS - select HAVE_IDE select HAVE_ARCH_KGDB if !SMP || SPARC64 select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_SECCOMP if SPARC64 diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index 4b8d3c65d266..9a2f20cbd48b 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -1287,6 +1287,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) return 1; break; } + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; /* ST: *(size *)(dst + off) = imm */ case BPF_ST | BPF_MEM | BPF_W: case BPF_ST | BPF_MEM | BPF_H: diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 49270655e827..88fb922c23a0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -202,7 +202,6 @@ config X86 select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS select HAVE_HW_BREAKPOINT - select HAVE_IDE select HAVE_IOREMAP_PROT select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64 select HAVE_IRQ_TIME_ACCOUNTING diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 698969e18fe3..ff005fe738a4 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -96,7 +96,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic) { ioapic->rtc_status.pending_eoi = 0; - bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID); + bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID + 1); } static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index 660401700075..11e4065e1617 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -43,13 +43,13 @@ struct kvm_vcpu; struct dest_map { /* vcpu bitmap where IRQ has been sent */ - DECLARE_BITMAP(map, KVM_MAX_VCPU_ID); + DECLARE_BITMAP(map, KVM_MAX_VCPU_ID + 1); /* * Vector sent to a given vcpu, only valid when * the vcpu's bit in map is set */ - u8 vectors[KVM_MAX_VCPU_ID]; + u8 vectors[KVM_MAX_VCPU_ID + 1]; }; diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 1d01da64c333..a8ad78a2faa1 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -646,7 +646,7 @@ out: void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - struct vmcb *vmcb = svm->vmcb; + struct vmcb *vmcb = svm->vmcb01.ptr; bool activated = kvm_vcpu_apicv_active(vcpu); if (!enable_apicv) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 3bd09c50c98b..61738ff8ef33 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -515,7 +515,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) * Also covers avic_vapic_bar, avic_backing_page, avic_logical_id, * avic_physical_id. */ - WARN_ON(svm->vmcb01.ptr->control.int_ctl & AVIC_ENABLE_MASK); + WARN_ON(kvm_apicv_activated(svm->vcpu.kvm)); /* Copied from vmcb01. msrpm_base can be overwritten later. */ svm->vmcb->control.nested_ctl = svm->vmcb01.ptr->control.nested_ctl; @@ -702,8 +702,8 @@ out: } /* Copy state save area fields which are handled by VMRUN */ -void svm_copy_vmrun_state(struct vmcb_save_area *from_save, - struct vmcb_save_area *to_save) +void svm_copy_vmrun_state(struct vmcb_save_area *to_save, + struct vmcb_save_area *from_save) { to_save->es = from_save->es; to_save->cs = from_save->cs; @@ -722,7 +722,7 @@ void svm_copy_vmrun_state(struct vmcb_save_area *from_save, to_save->cpl = 0; } -void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) +void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb) { to_vmcb->save.fs = from_vmcb->save.fs; to_vmcb->save.gs = from_vmcb->save.gs; @@ -1385,7 +1385,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa; - svm_copy_vmrun_state(save, &svm->vmcb01.ptr->save); + svm_copy_vmrun_state(&svm->vmcb01.ptr->save, save); nested_load_control_from_vmcb12(svm, ctl); svm_switch_vmcb(svm, &svm->nested.vmcb02); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 664d20f0689c..e8ccab50ebf6 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1406,8 +1406,6 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) goto error_free_vmsa_page; } - svm_vcpu_init_msrpm(vcpu, svm->msrpm); - svm->vmcb01.ptr = page_address(vmcb01_page); svm->vmcb01.pa = __sme_set(page_to_pfn(vmcb01_page) << PAGE_SHIFT); @@ -1419,6 +1417,8 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) svm_switch_vmcb(svm, &svm->vmcb01); init_vmcb(vcpu); + svm_vcpu_init_msrpm(vcpu, svm->msrpm); + svm_init_osvw(vcpu); vcpu->arch.microcode_version = 0x01000065; @@ -1568,8 +1568,11 @@ static void svm_set_vintr(struct vcpu_svm *svm) { struct vmcb_control_area *control; - /* The following fields are ignored when AVIC is enabled */ - WARN_ON(kvm_vcpu_apicv_active(&svm->vcpu)); + /* + * The following fields are ignored when AVIC is enabled + */ + WARN_ON(kvm_apicv_activated(svm->vcpu.kvm)); + svm_set_intercept(svm, INTERCEPT_VINTR); /* @@ -2147,11 +2150,12 @@ static int vmload_vmsave_interception(struct kvm_vcpu *vcpu, bool vmload) ret = kvm_skip_emulated_instruction(vcpu); if (vmload) { - nested_svm_vmloadsave(vmcb12, svm->vmcb); + svm_copy_vmloadsave_state(svm->vmcb, vmcb12); svm->sysenter_eip_hi = 0; svm->sysenter_esp_hi = 0; - } else - nested_svm_vmloadsave(svm->vmcb, vmcb12); + } else { + svm_copy_vmloadsave_state(vmcb12, svm->vmcb); + } kvm_vcpu_unmap(vcpu, &map, true); @@ -4344,8 +4348,8 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400); - svm_copy_vmrun_state(&svm->vmcb01.ptr->save, - map_save.hva + 0x400); + svm_copy_vmrun_state(map_save.hva + 0x400, + &svm->vmcb01.ptr->save); kvm_vcpu_unmap(vcpu, &map_save, true); } @@ -4393,8 +4397,8 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) &map_save) == -EINVAL) return 1; - svm_copy_vmrun_state(map_save.hva + 0x400, - &svm->vmcb01.ptr->save); + svm_copy_vmrun_state(&svm->vmcb01.ptr->save, + map_save.hva + 0x400); kvm_vcpu_unmap(vcpu, &map_save, true); } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 7e2090752d8f..bd0fe94c2920 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -464,9 +464,9 @@ void svm_leave_nested(struct vcpu_svm *svm); void svm_free_nested(struct vcpu_svm *svm); int svm_allocate_nested(struct vcpu_svm *svm); int nested_svm_vmrun(struct kvm_vcpu *vcpu); -void svm_copy_vmrun_state(struct vmcb_save_area *from_save, - struct vmcb_save_area *to_save); -void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb); +void svm_copy_vmrun_state(struct vmcb_save_area *to_save, + struct vmcb_save_area *from_save); +void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb); int nested_svm_vmexit(struct vcpu_svm *svm); static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code) diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h index 9b9a55abc29f..c53b8bf8d013 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.h +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -89,7 +89,7 @@ static inline void svm_hv_vmcb_dirty_nested_enlightenments( * as we mark it dirty unconditionally towards end of vcpu * init phase. */ - if (vmcb && vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) && + if (vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) && hve->hv_enlightenments_control.msr_bitmap) vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a4fd10604f72..4116567f3d44 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3407,7 +3407,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; break; case MSR_KVM_ASYNC_PF_ACK: - if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) return 1; if (data & 0x1) { vcpu->arch.apf.pageready_pending = false; @@ -3746,7 +3746,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.apf.msr_int_val; break; case MSR_KVM_ASYNC_PF_ACK: - if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) return 1; msr_info->data = 0; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 4b951458c9fc..16d76f814e9b 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1219,6 +1219,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, } break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + if (boot_cpu_has(X86_FEATURE_XMM2)) + /* Emit 'lfence' */ + EMIT3(0x0F, 0xAE, 0xE8); + break; + /* ST: *(u8*)(dst_reg + off) = imm */ case BPF_ST | BPF_MEM | BPF_B: if (is_ereg(dst_reg)) diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 3da88ded6ee3..3bfda5f502cb 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1886,6 +1886,12 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, i++; break; } + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + if (boot_cpu_has(X86_FEATURE_XMM2)) + /* Emit 'lfence' */ + EMIT3(0x0F, 0xAE, 0xE8); + break; /* ST: *(u8*)(dst_reg + off) = imm */ case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_B: diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 2332b2156993..3878880469d1 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -327,7 +327,6 @@ config XTENSA_PLATFORM_ISS config XTENSA_PLATFORM_XT2000 bool "XT2000" - select HAVE_IDE help XT2000 is the name of Tensilica's feature-rich emulation platform. This hardware is capable of running a full Linux distribution. diff --git a/block/blk-iocost.c b/block/blk-iocost.c index c2d6bc88d3f1..5fac3757e6e0 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1440,16 +1440,17 @@ static int iocg_wake_fn(struct wait_queue_entry *wq_entry, unsigned mode, return -1; iocg_commit_bio(ctx->iocg, wait->bio, wait->abs_cost, cost); + wait->committed = true; /* * autoremove_wake_function() removes the wait entry only when it - * actually changed the task state. We want the wait always - * removed. Remove explicitly and use default_wake_function(). + * actually changed the task state. We want the wait always removed. + * Remove explicitly and use default_wake_function(). Note that the + * order of operations is important as finish_wait() tests whether + * @wq_entry is removed without grabbing the lock. */ - list_del_init(&wq_entry->entry); - wait->committed = true; - default_wake_function(wq_entry, mode, flags, key); + list_del_init_careful(&wq_entry->entry); return 0; } diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index c838d81ac058..0f006cabfd91 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -515,17 +515,6 @@ void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx, percpu_ref_put(&q->q_usage_counter); } -static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set, - struct blk_mq_hw_ctx *hctx, - unsigned int hctx_idx) -{ - if (hctx->sched_tags) { - blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx); - blk_mq_free_rq_map(hctx->sched_tags, set->flags); - hctx->sched_tags = NULL; - } -} - static int blk_mq_sched_alloc_tags(struct request_queue *q, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) @@ -539,8 +528,10 @@ static int blk_mq_sched_alloc_tags(struct request_queue *q, return -ENOMEM; ret = blk_mq_alloc_rqs(set, hctx->sched_tags, hctx_idx, q->nr_requests); - if (ret) - blk_mq_sched_free_tags(set, hctx, hctx_idx); + if (ret) { + blk_mq_free_rq_map(hctx->sched_tags, set->flags); + hctx->sched_tags = NULL; + } return ret; } diff --git a/block/genhd.c b/block/genhd.c index af4d2ab4a633..298ee78c1bda 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1079,10 +1079,9 @@ static void disk_release(struct device *dev) disk_release_events(disk); kfree(disk->random); xa_destroy(&disk->part_tbl); - bdput(disk->part0); if (test_bit(GD_QUEUE_REF, &disk->state) && disk->queue) blk_put_queue(disk->queue); - kfree(disk); + bdput(disk->part0); /* frees the disk */ } struct class block_class = { .name = "block", diff --git a/drivers/acpi/dptf/dptf_pch_fivr.c b/drivers/acpi/dptf/dptf_pch_fivr.c index 5fca18296bf6..550b9081fcbc 100644 --- a/drivers/acpi/dptf/dptf_pch_fivr.c +++ b/drivers/acpi/dptf/dptf_pch_fivr.c @@ -9,6 +9,42 @@ #include <linux/module.h> #include <linux/platform_device.h> +struct pch_fivr_resp { + u64 status; + u64 result; +}; + +static int pch_fivr_read(acpi_handle handle, char *method, struct pch_fivr_resp *fivr_resp) +{ + struct acpi_buffer resp = { sizeof(struct pch_fivr_resp), fivr_resp}; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + struct acpi_buffer format = { sizeof("NN"), "NN" }; + union acpi_object *obj; + acpi_status status; + int ret = -EFAULT; + + status = acpi_evaluate_object(handle, method, NULL, &buffer); + if (ACPI_FAILURE(status)) + return ret; + + obj = buffer.pointer; + if (!obj || obj->type != ACPI_TYPE_PACKAGE) + goto release_buffer; + + status = acpi_extract_package(obj, &format, &resp); + if (ACPI_FAILURE(status)) + goto release_buffer; + + if (fivr_resp->status) + goto release_buffer; + + ret = 0; + +release_buffer: + kfree(buffer.pointer); + return ret; +} + /* * Presentation of attributes which are defined for INT1045 * They are: @@ -23,15 +59,14 @@ static ssize_t name##_show(struct device *dev,\ char *buf)\ {\ struct acpi_device *acpi_dev = dev_get_drvdata(dev);\ - unsigned long long val;\ - acpi_status status;\ + struct pch_fivr_resp fivr_resp;\ + int status;\ \ - status = acpi_evaluate_integer(acpi_dev->handle, #method,\ - NULL, &val);\ - if (ACPI_SUCCESS(status))\ - return sprintf(buf, "%d\n", (int)val);\ - else\ - return -EINVAL;\ + status = pch_fivr_read(acpi_dev->handle, #method, &fivr_resp);\ + if (status)\ + return status;\ +\ + return sprintf(buf, "%llu\n", fivr_resp.result);\ } #define PCH_FIVR_STORE(name, method) \ diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index dc01fb550b28..ee78a210c606 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -423,13 +423,6 @@ static void acpi_dev_get_irqresource(struct resource *res, u32 gsi, } } -static bool irq_is_legacy(struct acpi_resource_irq *irq) -{ - return irq->triggering == ACPI_EDGE_SENSITIVE && - irq->polarity == ACPI_ACTIVE_HIGH && - irq->shareable == ACPI_EXCLUSIVE; -} - /** * acpi_dev_resource_interrupt - Extract ACPI interrupt resource information. * @ares: Input ACPI resource object. @@ -468,7 +461,7 @@ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, } acpi_dev_get_irqresource(res, irq->interrupts[index], irq->triggering, irq->polarity, - irq->shareable, irq_is_legacy(irq)); + irq->shareable, true); break; case ACPI_RESOURCE_TYPE_EXTENDED_IRQ: ext_irq = &ares->data.extended_irq; diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c index 1c507804fb10..fbdbef0ab552 100644 --- a/drivers/acpi/x86/s2idle.c +++ b/drivers/acpi/x86/s2idle.c @@ -378,19 +378,25 @@ static int lps0_device_attach(struct acpi_device *adev, * AMDI0006: * - should use rev_id 0x0 * - function mask = 0x3: Should use Microsoft method + * AMDI0007: + * - Should use rev_id 0x2 + * - Should only use AMD method */ const char *hid = acpi_device_hid(adev); - rev_id = 0; + rev_id = strcmp(hid, "AMDI0007") ? 0 : 2; lps0_dsm_func_mask = validate_dsm(adev->handle, ACPI_LPS0_DSM_UUID_AMD, rev_id, &lps0_dsm_guid); lps0_dsm_func_mask_microsoft = validate_dsm(adev->handle, - ACPI_LPS0_DSM_UUID_MICROSOFT, rev_id, + ACPI_LPS0_DSM_UUID_MICROSOFT, 0, &lps0_dsm_guid_microsoft); if (lps0_dsm_func_mask > 0x3 && (!strcmp(hid, "AMD0004") || !strcmp(hid, "AMDI0005"))) { lps0_dsm_func_mask = (lps0_dsm_func_mask << 1) | 0x1; acpi_handle_debug(adev->handle, "_DSM UUID %s: Adjusted function mask: 0x%x\n", ACPI_LPS0_DSM_UUID_AMD, lps0_dsm_func_mask); + } else if (lps0_dsm_func_mask_microsoft > 0 && !strcmp(hid, "AMDI0007")) { + lps0_dsm_func_mask_microsoft = -EINVAL; + acpi_handle_debug(adev->handle, "_DSM Using AMD method\n"); } } else { rev_id = 1; diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index ae7189d1a568..b71ea4a680b0 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -637,6 +637,20 @@ unsigned int ata_sff_data_xfer32(struct ata_queued_cmd *qc, unsigned char *buf, } EXPORT_SYMBOL_GPL(ata_sff_data_xfer32); +static void ata_pio_xfer(struct ata_queued_cmd *qc, struct page *page, + unsigned int offset, size_t xfer_size) +{ + bool do_write = (qc->tf.flags & ATA_TFLAG_WRITE); + unsigned char *buf; + + buf = kmap_atomic(page); + qc->ap->ops->sff_data_xfer(qc, buf + offset, xfer_size, do_write); + kunmap_atomic(buf); + + if (!do_write && !PageSlab(page)) + flush_dcache_page(page); +} + /** * ata_pio_sector - Transfer a sector of data. * @qc: Command on going @@ -648,11 +662,9 @@ EXPORT_SYMBOL_GPL(ata_sff_data_xfer32); */ static void ata_pio_sector(struct ata_queued_cmd *qc) { - int do_write = (qc->tf.flags & ATA_TFLAG_WRITE); struct ata_port *ap = qc->ap; struct page *page; unsigned int offset; - unsigned char *buf; if (!qc->cursg) { qc->curbytes = qc->nbytes; @@ -670,13 +682,20 @@ static void ata_pio_sector(struct ata_queued_cmd *qc) DPRINTK("data %s\n", qc->tf.flags & ATA_TFLAG_WRITE ? "write" : "read"); - /* do the actual data transfer */ - buf = kmap_atomic(page); - ap->ops->sff_data_xfer(qc, buf + offset, qc->sect_size, do_write); - kunmap_atomic(buf); + /* + * Split the transfer when it splits a page boundary. Note that the + * split still has to be dword aligned like all ATA data transfers. + */ + WARN_ON_ONCE(offset % 4); + if (offset + qc->sect_size > PAGE_SIZE) { + unsigned int split_len = PAGE_SIZE - offset; - if (!do_write && !PageSlab(page)) - flush_dcache_page(page); + ata_pio_xfer(qc, page, offset, split_len); + ata_pio_xfer(qc, nth_page(page, 1), 0, + qc->sect_size - split_len); + } else { + ata_pio_xfer(qc, page, offset, qc->sect_size); + } qc->curbytes += qc->sect_size; qc->cursg_ofs += qc->sect_size; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index f37b9e3d833c..f0cdff0c5fbf 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -88,6 +88,47 @@ static DEFINE_IDR(loop_index_idr); static DEFINE_MUTEX(loop_ctl_mutex); +static DEFINE_MUTEX(loop_validate_mutex); + +/** + * loop_global_lock_killable() - take locks for safe loop_validate_file() test + * + * @lo: struct loop_device + * @global: true if @lo is about to bind another "struct loop_device", false otherwise + * + * Returns 0 on success, -EINTR otherwise. + * + * Since loop_validate_file() traverses on other "struct loop_device" if + * is_loop_device() is true, we need a global lock for serializing concurrent + * loop_configure()/loop_change_fd()/__loop_clr_fd() calls. + */ +static int loop_global_lock_killable(struct loop_device *lo, bool global) +{ + int err; + + if (global) { + err = mutex_lock_killable(&loop_validate_mutex); + if (err) + return err; + } + err = mutex_lock_killable(&lo->lo_mutex); + if (err && global) + mutex_unlock(&loop_validate_mutex); + return err; +} + +/** + * loop_global_unlock() - release locks taken by loop_global_lock_killable() + * + * @lo: struct loop_device + * @global: true if @lo was about to bind another "struct loop_device", false otherwise + */ +static void loop_global_unlock(struct loop_device *lo, bool global) +{ + mutex_unlock(&lo->lo_mutex); + if (global) + mutex_unlock(&loop_validate_mutex); +} static int max_part; static int part_shift; @@ -672,13 +713,15 @@ static int loop_validate_file(struct file *file, struct block_device *bdev) while (is_loop_device(f)) { struct loop_device *l; + lockdep_assert_held(&loop_validate_mutex); if (f->f_mapping->host->i_rdev == bdev->bd_dev) return -EBADF; l = I_BDEV(f->f_mapping->host)->bd_disk->private_data; - if (l->lo_state != Lo_bound) { + if (l->lo_state != Lo_bound) return -EINVAL; - } + /* Order wrt setting lo->lo_backing_file in loop_configure(). */ + rmb(); f = l->lo_backing_file; } if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) @@ -697,13 +740,18 @@ static int loop_validate_file(struct file *file, struct block_device *bdev) static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, unsigned int arg) { - struct file *file = NULL, *old_file; - int error; - bool partscan; + struct file *file = fget(arg); + struct file *old_file; + int error; + bool partscan; + bool is_loop; - error = mutex_lock_killable(&lo->lo_mutex); + if (!file) + return -EBADF; + is_loop = is_loop_device(file); + error = loop_global_lock_killable(lo, is_loop); if (error) - return error; + goto out_putf; error = -ENXIO; if (lo->lo_state != Lo_bound) goto out_err; @@ -713,11 +761,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, if (!(lo->lo_flags & LO_FLAGS_READ_ONLY)) goto out_err; - error = -EBADF; - file = fget(arg); - if (!file) - goto out_err; - error = loop_validate_file(file, bdev); if (error) goto out_err; @@ -740,7 +783,16 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, loop_update_dio(lo); blk_mq_unfreeze_queue(lo->lo_queue); partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; - mutex_unlock(&lo->lo_mutex); + loop_global_unlock(lo, is_loop); + + /* + * Flush loop_validate_file() before fput(), for l->lo_backing_file + * might be pointing at old_file which might be the last reference. + */ + if (!is_loop) { + mutex_lock(&loop_validate_mutex); + mutex_unlock(&loop_validate_mutex); + } /* * We must drop file reference outside of lo_mutex as dropping * the file ref can take open_mutex which creates circular locking @@ -752,9 +804,9 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, return 0; out_err: - mutex_unlock(&lo->lo_mutex); - if (file) - fput(file); + loop_global_unlock(lo, is_loop); +out_putf: + fput(file); return error; } @@ -1136,22 +1188,22 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, struct block_device *bdev, const struct loop_config *config) { - struct file *file; - struct inode *inode; + struct file *file = fget(config->fd); + struct inode *inode; struct address_space *mapping; - int error; - loff_t size; - bool partscan; - unsigned short bsize; + int error; + loff_t size; + bool partscan; + unsigned short bsize; + bool is_loop; + + if (!file) + return -EBADF; + is_loop = is_loop_device(file); /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE); - error = -EBADF; - file = fget(config->fd); - if (!file) - goto out; - /* * If we don't hold exclusive handle for the device, upgrade to it * here to avoid changing device under exclusive owner. @@ -1162,7 +1214,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, goto out_putf; } - error = mutex_lock_killable(&lo->lo_mutex); + error = loop_global_lock_killable(lo, is_loop); if (error) goto out_bdev; @@ -1242,6 +1294,9 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, size = get_loop_size(lo, file); loop_set_size(lo, size); + /* Order wrt reading lo_state in loop_validate_file(). */ + wmb(); + lo->lo_state = Lo_bound; if (part_shift) lo->lo_flags |= LO_FLAGS_PARTSCAN; @@ -1253,7 +1308,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, * put /dev/loopXX inode. Later in __loop_clr_fd() we bdput(bdev). */ bdgrab(bdev); - mutex_unlock(&lo->lo_mutex); + loop_global_unlock(lo, is_loop); if (partscan) loop_reread_partitions(lo); if (!(mode & FMODE_EXCL)) @@ -1261,13 +1316,12 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, return 0; out_unlock: - mutex_unlock(&lo->lo_mutex); + loop_global_unlock(lo, is_loop); out_bdev: if (!(mode & FMODE_EXCL)) bd_abort_claiming(bdev, loop_configure); out_putf: fput(file); -out: /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); return error; @@ -1283,6 +1337,18 @@ static int __loop_clr_fd(struct loop_device *lo, bool release) int lo_number; struct loop_worker *pos, *worker; + /* + * Flush loop_configure() and loop_change_fd(). It is acceptable for + * loop_validate_file() to succeed, for actual clear operation has not + * started yet. + */ + mutex_lock(&loop_validate_mutex); + mutex_unlock(&loop_validate_mutex); + /* + * loop_validate_file() now fails because l->lo_state != Lo_bound + * became visible. + */ + mutex_lock(&lo->lo_mutex); if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) { err = -ENXIO; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 84a1b4bc9bb4..6cc0d4fa4d0a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -26,6 +26,7 @@ #include <linux/slab.h> #include <linux/power_supply.h> #include <linux/pm_runtime.h> +#include <linux/suspend.h> #include <acpi/video.h> #include <acpi/actbl.h> @@ -1042,7 +1043,7 @@ bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev) #if defined(CONFIG_AMD_PMC) || defined(CONFIG_AMD_PMC_MODULE) if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) { if (adev->flags & AMD_IS_APU) - return true; + return pm_suspend_target_state == PM_SUSPEND_TO_IDLE; } #endif return false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index d303e88e3c23..f3fd5ec710b6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3504,13 +3504,13 @@ int amdgpu_device_init(struct amdgpu_device *adev, r = amdgpu_device_get_job_timeout_settings(adev); if (r) { dev_err(adev->dev, "invalid lockup_timeout parameter syntax\n"); - goto failed_unmap; + return r; } /* early init functions */ r = amdgpu_device_ip_early_init(adev); if (r) - goto failed_unmap; + return r; /* doorbell bar mapping and doorbell index init*/ amdgpu_device_doorbell_init(adev); @@ -3736,10 +3736,6 @@ release_ras_con: failed: amdgpu_vf_error_trans_all(adev); -failed_unmap: - iounmap(adev->rmmio); - adev->rmmio = NULL; - return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c index 618e5b6b85d9..536d41f327c1 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c @@ -67,7 +67,7 @@ static int psp_v12_0_init_microcode(struct psp_context *psp) err = psp_init_asd_microcode(psp, chip_name); if (err) - goto out; + return err; snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name); err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev); @@ -80,7 +80,7 @@ static int psp_v12_0_init_microcode(struct psp_context *psp) } else { err = amdgpu_ucode_validate(adev->psp.ta_fw); if (err) - goto out2; + goto out; ta_hdr = (const struct ta_firmware_header_v1_0 *) adev->psp.ta_fw->data; @@ -105,10 +105,9 @@ static int psp_v12_0_init_microcode(struct psp_context *psp) return 0; -out2: +out: release_firmware(adev->psp.ta_fw); adev->psp.ta_fw = NULL; -out: if (err) { dev_err(adev->dev, "psp v12.0: Failed to load firmware \"%s\"\n", diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index d3a2a5ff57e9..b53f49a23ddc 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2429,9 +2429,9 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector) max_cll = conn_base->hdr_sink_metadata.hdmi_type1.max_cll; min_cll = conn_base->hdr_sink_metadata.hdmi_type1.min_cll; - if (caps->ext_caps->bits.oled == 1 || + if (caps->ext_caps->bits.oled == 1 /*|| caps->ext_caps->bits.sdr_aux_backlight_control == 1 || - caps->ext_caps->bits.hdr_aux_backlight_control == 1) + caps->ext_caps->bits.hdr_aux_backlight_control == 1*/) caps->aux_support = true; if (amdgpu_backlight == 0) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c index 6e0c5c664fdc..a5331b96f551 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c @@ -197,7 +197,7 @@ void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr, struct REG_UPDATE(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, dispclk_wdivider); -// REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 5, 100); + REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 50, 1000); REG_UPDATE(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_WDIVIDER, dppclk_wdivider); REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_CHG_DONE, 1, 5, 100); diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index f3d98e3ba624..bf0a198eae15 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -109,6 +109,7 @@ struct _vcs_dpi_ip_params_st dcn2_1_ip = { .max_page_table_levels = 4, .pte_chunk_size_kbytes = 2, .meta_chunk_size_kbytes = 2, + .min_meta_chunk_size_bytes = 256, .writeback_chunk_size_kbytes = 2, .line_buffer_size_bits = 789504, .is_line_buffer_bpp_fixed = 0, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c index d25a7d38d21f..6655bb99fdfd 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c @@ -841,6 +841,9 @@ static bool CalculatePrefetchSchedule( else *DestinationLinesForPrefetch = dst_y_prefetch_equ; + // Limit to prevent overflow in DST_Y_PREFETCH register + *DestinationLinesForPrefetch = dml_min(*DestinationLinesForPrefetch, 63.75); + dml_print("DML: VStartup: %d\n", VStartup); dml_print("DML: TCalc: %f\n", TCalc); dml_print("DML: TWait: %f\n", TWait); diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index 5b6922e28ef2..aa667fa71158 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -2166,7 +2166,8 @@ static void init_vbt_missing_defaults(struct drm_i915_private *i915) { enum port port; - int ports = PORT_A | PORT_B | PORT_C | PORT_D | PORT_E | PORT_F; + int ports = BIT(PORT_A) | BIT(PORT_B) | BIT(PORT_C) | + BIT(PORT_D) | BIT(PORT_E) | BIT(PORT_F); if (!HAS_DDI(i915) && !IS_CHERRYVIEW(i915)) return; diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 3bad4e00f7be..2d5d21740c25 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -11361,13 +11361,19 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv) intel_ddi_init(dev_priv, PORT_B); intel_ddi_init(dev_priv, PORT_C); vlv_dsi_init(dev_priv); - } else if (DISPLAY_VER(dev_priv) >= 9) { + } else if (DISPLAY_VER(dev_priv) == 10) { intel_ddi_init(dev_priv, PORT_A); intel_ddi_init(dev_priv, PORT_B); intel_ddi_init(dev_priv, PORT_C); intel_ddi_init(dev_priv, PORT_D); intel_ddi_init(dev_priv, PORT_E); intel_ddi_init(dev_priv, PORT_F); + } else if (DISPLAY_VER(dev_priv) >= 9) { + intel_ddi_init(dev_priv, PORT_A); + intel_ddi_init(dev_priv, PORT_B); + intel_ddi_init(dev_priv, PORT_C); + intel_ddi_init(dev_priv, PORT_D); + intel_ddi_init(dev_priv, PORT_E); } else if (HAS_DDI(dev_priv)) { u32 found; diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index 7eaa92fee421..e0a10f36acc1 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -325,7 +325,7 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) info->pipe_mask &= ~BIT(PIPE_C); info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C); } - } else if (HAS_DISPLAY(dev_priv) && GRAPHICS_VER(dev_priv) >= 9) { + } else if (HAS_DISPLAY(dev_priv) && DISPLAY_VER(dev_priv) >= 9) { u32 dfsm = intel_de_read(dev_priv, SKL_DFSM); if (dfsm & SKL_DFSM_PIPE_A_DISABLE) { @@ -340,7 +340,8 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) info->pipe_mask &= ~BIT(PIPE_C); info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C); } - if (GRAPHICS_VER(dev_priv) >= 12 && + + if (DISPLAY_VER(dev_priv) >= 12 && (dfsm & TGL_DFSM_PIPE_D_DISABLE)) { info->pipe_mask &= ~BIT(PIPE_D); info->cpu_transcoder_mask &= ~BIT(TRANSCODER_D); @@ -352,10 +353,10 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) if (dfsm & SKL_DFSM_DISPLAY_PM_DISABLE) info->display.has_fbc = 0; - if (GRAPHICS_VER(dev_priv) >= 11 && (dfsm & ICL_DFSM_DMC_DISABLE)) + if (DISPLAY_VER(dev_priv) >= 11 && (dfsm & ICL_DFSM_DMC_DISABLE)) info->display.has_dmc = 0; - if (GRAPHICS_VER(dev_priv) >= 10 && + if (DISPLAY_VER(dev_priv) >= 10 && (dfsm & CNL_DFSM_DISPLAY_DSC_DISABLE)) info->display.has_dsc = 0; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index d01c4c919504..704dace895cb 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -296,7 +296,7 @@ static const struct dpu_mdp_cfg sc7180_mdp[] = { static const struct dpu_mdp_cfg sm8250_mdp[] = { { .name = "top_0", .id = MDP_TOP, - .base = 0x0, .len = 0x45C, + .base = 0x0, .len = 0x494, .features = 0, .highest_bank_bit = 0x3, /* TODO: 2 for LP_DDR4 */ .clk_ctrls[DPU_CLK_CTRL_VIG0] = { diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.c b/drivers/gpu/drm/msm/dp/dp_catalog.c index ca96e3514790..c0423e76eed7 100644 --- a/drivers/gpu/drm/msm/dp/dp_catalog.c +++ b/drivers/gpu/drm/msm/dp/dp_catalog.c @@ -771,6 +771,7 @@ int dp_catalog_panel_timing_cfg(struct dp_catalog *dp_catalog) dp_write_link(catalog, REG_DP_HSYNC_VSYNC_WIDTH_POLARITY, dp_catalog->width_blanking); dp_write_link(catalog, REG_DP_ACTIVE_HOR_VER, dp_catalog->dp_active); + dp_write_p0(catalog, MMSS_DP_INTF_CONFIG, 0); return 0; } diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index ee221d835fa0..eaddfd739885 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -1526,7 +1526,7 @@ static int dp_ctrl_process_phy_test_request(struct dp_ctrl_private *ctrl) * running. Add the global reset just before disabling the * link clocks and core clocks. */ - ret = dp_ctrl_off(&ctrl->dp_ctrl); + ret = dp_ctrl_off_link_stream(&ctrl->dp_ctrl); if (ret) { DRM_ERROR("failed to disable DP controller\n"); return ret; diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 051c1be1de7e..867388a399ad 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -219,6 +219,7 @@ static int dp_display_bind(struct device *dev, struct device *master, goto end; } + dp->aux->drm_dev = drm; rc = dp_aux_register(dp->aux); if (rc) { DRM_ERROR("DRM DP AUX register failed\n"); @@ -1311,6 +1312,10 @@ static int dp_pm_resume(struct device *dev) else dp->dp_display.is_connected = false; + dp_display_handle_plugged_change(g_dp_display, + dp->dp_display.is_connected); + + mutex_unlock(&dp->event_mutex); return 0; diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index eed2a762e9dd..bcaddbba564d 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -142,6 +142,9 @@ static const struct iommu_flush_ops null_tlb_ops = { .tlb_add_page = msm_iommu_tlb_add_page, }; +static int msm_fault_handler(struct iommu_domain *domain, struct device *dev, + unsigned long iova, int flags, void *arg); + struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) { struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(parent->dev); @@ -157,6 +160,13 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) if (!ttbr1_cfg) return ERR_PTR(-ENODEV); + /* + * Defer setting the fault handler until we have a valid adreno_smmu + * to avoid accidentially installing a GPU specific fault handler for + * the display's iommu + */ + iommu_set_fault_handler(iommu->domain, msm_fault_handler, iommu); + pagetable = kzalloc(sizeof(*pagetable), GFP_KERNEL); if (!pagetable) return ERR_PTR(-ENOMEM); @@ -300,7 +310,6 @@ struct msm_mmu *msm_iommu_new(struct device *dev, struct iommu_domain *domain) iommu->domain = domain; msm_mmu_init(&iommu->base, dev, &funcs, MSM_MMU_IOMMU); - iommu_set_fault_handler(domain, msm_fault_handler, iommu); atomic_set(&iommu->pagetables, 0); diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 21939d4352cf..1b80290c2b53 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -4166,7 +4166,7 @@ static const struct drm_display_mode yes_optoelectronics_ytc700tlag_05_201c_mode static const struct panel_desc yes_optoelectronics_ytc700tlag_05_201c = { .modes = &yes_optoelectronics_ytc700tlag_05_201c_mode, .num_modes = 1, - .bpc = 6, + .bpc = 8, .size = { .width = 154, .height = 90, diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c index 519deea8e39b..74e3b460132b 100644 --- a/drivers/gpu/drm/ttm/ttm_device.c +++ b/drivers/gpu/drm/ttm/ttm_device.c @@ -44,6 +44,8 @@ static unsigned ttm_glob_use_count; struct ttm_global ttm_glob; EXPORT_SYMBOL(ttm_glob); +struct dentry *ttm_debugfs_root; + static void ttm_global_release(void) { struct ttm_global *glob = &ttm_glob; @@ -53,6 +55,7 @@ static void ttm_global_release(void) goto out; ttm_pool_mgr_fini(); + debugfs_remove(ttm_debugfs_root); __free_page(glob->dummy_read_page); memset(glob, 0, sizeof(*glob)); @@ -73,6 +76,13 @@ static int ttm_global_init(void) si_meminfo(&si); + ttm_debugfs_root = debugfs_create_dir("ttm", NULL); + if (IS_ERR(ttm_debugfs_root)) { + ret = PTR_ERR(ttm_debugfs_root); + ttm_debugfs_root = NULL; + goto out; + } + /* Limit the number of pages in the pool to about 50% of the total * system memory. */ @@ -100,6 +110,8 @@ static int ttm_global_init(void) debugfs_create_atomic_t("buffer_objects", 0444, ttm_debugfs_root, &glob->bo_count); out: + if (ret && ttm_debugfs_root) + debugfs_remove(ttm_debugfs_root); if (ret) --ttm_glob_use_count; mutex_unlock(&ttm_global_mutex); diff --git a/drivers/gpu/drm/ttm/ttm_module.c b/drivers/gpu/drm/ttm/ttm_module.c index 997c458f68a9..7fcdef278c74 100644 --- a/drivers/gpu/drm/ttm/ttm_module.c +++ b/drivers/gpu/drm/ttm/ttm_module.c @@ -72,22 +72,6 @@ pgprot_t ttm_prot_from_caching(enum ttm_caching caching, pgprot_t tmp) return tmp; } -struct dentry *ttm_debugfs_root; - -static int __init ttm_init(void) -{ - ttm_debugfs_root = debugfs_create_dir("ttm", NULL); - return 0; -} - -static void __exit ttm_exit(void) -{ - debugfs_remove(ttm_debugfs_root); -} - -module_init(ttm_init); -module_exit(ttm_exit); - MODULE_AUTHOR("Thomas Hellstrom, Jerome Glisse"); MODULE_DESCRIPTION("TTM memory manager subsystem (for DRM device)"); MODULE_LICENSE("GPL and additional rights"); diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 160554903ef9..76937f716fbe 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -576,7 +576,7 @@ config HID_LOGITECH_HIDPP depends on HID_LOGITECH select POWER_SUPPLY help - Support for Logitech devices relyingon the HID++ Logitech specification + Support for Logitech devices relying on the HID++ Logitech specification Say Y if you want support for Logitech devices relying on the HID++ specification. Such devices are the various Logitech Touchpads (T650, diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c index 96e2577fa37e..8d68796aa905 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c @@ -58,7 +58,7 @@ static void amd_stop_sensor_v2(struct amd_mp2_dev *privdata, u16 sensor_idx) cmd_base.cmd_v2.sensor_id = sensor_idx; cmd_base.cmd_v2.length = 16; - writeq(0x0, privdata->mmio + AMD_C2P_MSG2); + writeq(0x0, privdata->mmio + AMD_C2P_MSG1); writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG0); } diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 6b8f0d004d34..dc6bd4299c54 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -501,6 +501,8 @@ static const struct hid_device_id apple_devices[] = { APPLE_RDESC_JIS }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ANSI), .driver_data = APPLE_HAS_FN }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ANSI), + .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ISO), .driver_data = APPLE_HAS_FN }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ISO), diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index fca8fc78a78a..fb807c8e989b 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -485,9 +485,6 @@ static void asus_kbd_backlight_set(struct led_classdev *led_cdev, { struct asus_kbd_leds *led = container_of(led_cdev, struct asus_kbd_leds, cdev); - if (led->brightness == brightness) - return; - led->brightness = brightness; schedule_work(&led->work); } diff --git a/drivers/hid/hid-ft260.c b/drivers/hid/hid-ft260.c index f43a8406cb9a..4ef1c3b8094e 100644 --- a/drivers/hid/hid-ft260.c +++ b/drivers/hid/hid-ft260.c @@ -742,7 +742,7 @@ static int ft260_is_interface_enabled(struct hid_device *hdev) int ret; ret = ft260_get_system_config(hdev, &cfg); - if (ret) + if (ret < 0) return ret; ft260_dbg("interface: 0x%02x\n", interface); @@ -754,23 +754,16 @@ static int ft260_is_interface_enabled(struct hid_device *hdev) switch (cfg.chip_mode) { case FT260_MODE_ALL: case FT260_MODE_BOTH: - if (interface == 1) { + if (interface == 1) hid_info(hdev, "uart interface is not supported\n"); - return 0; - } - ret = 1; + else + ret = 1; break; case FT260_MODE_UART: - if (interface == 0) { - hid_info(hdev, "uart is unsupported on interface 0\n"); - ret = 0; - } + hid_info(hdev, "uart interface is not supported\n"); break; case FT260_MODE_I2C: - if (interface == 1) { - hid_info(hdev, "i2c is unsupported on interface 1\n"); - ret = 0; - } + ret = 1; break; } return ret; @@ -785,7 +778,7 @@ static int ft260_byte_show(struct hid_device *hdev, int id, u8 *cfg, int len, if (ret < 0) return ret; - return scnprintf(buf, PAGE_SIZE, "%hi\n", *field); + return scnprintf(buf, PAGE_SIZE, "%d\n", *field); } static int ft260_word_show(struct hid_device *hdev, int id, u8 *cfg, int len, @@ -797,7 +790,7 @@ static int ft260_word_show(struct hid_device *hdev, int id, u8 *cfg, int len, if (ret < 0) return ret; - return scnprintf(buf, PAGE_SIZE, "%hi\n", le16_to_cpu(*field)); + return scnprintf(buf, PAGE_SIZE, "%d\n", le16_to_cpu(*field)); } #define FT260_ATTR_SHOW(name, reptype, id, type, func) \ @@ -1004,11 +997,9 @@ err_hid_stop: static void ft260_remove(struct hid_device *hdev) { - int ret; struct ft260_device *dev = hid_get_drvdata(hdev); - ret = ft260_is_interface_enabled(hdev); - if (ret <= 0) + if (!dev) return; sysfs_remove_group(&hdev->dev.kobj, &ft260_attr_group); diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c index 6b1fa971b33e..91bf4d01e91a 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c +++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c @@ -784,6 +784,17 @@ static void hid_ishtp_cl_reset_handler(struct work_struct *work) } } +static void hid_ishtp_cl_resume_handler(struct work_struct *work) +{ + struct ishtp_cl_data *client_data = container_of(work, struct ishtp_cl_data, resume_work); + struct ishtp_cl *hid_ishtp_cl = client_data->hid_ishtp_cl; + + if (ishtp_wait_resume(ishtp_get_ishtp_device(hid_ishtp_cl))) { + client_data->suspended = false; + wake_up_interruptible(&client_data->ishtp_resume_wait); + } +} + ishtp_print_log ishtp_hid_print_trace; /** @@ -822,6 +833,8 @@ static int hid_ishtp_cl_probe(struct ishtp_cl_device *cl_device) init_waitqueue_head(&client_data->ishtp_resume_wait); INIT_WORK(&client_data->work, hid_ishtp_cl_reset_handler); + INIT_WORK(&client_data->resume_work, hid_ishtp_cl_resume_handler); + ishtp_hid_print_trace = ishtp_trace_callback(cl_device); @@ -921,7 +934,7 @@ static int hid_ishtp_cl_resume(struct device *device) hid_ishtp_trace(client_data, "%s hid_ishtp_cl %p\n", __func__, hid_ishtp_cl); - client_data->suspended = false; + schedule_work(&client_data->resume_work); return 0; } diff --git a/drivers/hid/intel-ish-hid/ishtp-hid.h b/drivers/hid/intel-ish-hid/ishtp-hid.h index f88443a7d935..6a5cc11aefd8 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid.h +++ b/drivers/hid/intel-ish-hid/ishtp-hid.h @@ -135,6 +135,7 @@ struct ishtp_cl_data { int multi_packet_cnt; struct work_struct work; + struct work_struct resume_work; struct ishtp_cl_device *cl_device; }; diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index f0802b047ed8..aa2c51624012 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -314,13 +314,6 @@ static int ishtp_cl_device_resume(struct device *dev) if (!device) return 0; - /* - * When ISH needs hard reset, it is done asynchrnously, hence bus - * resume will be called before full ISH resume - */ - if (device->ishtp_dev->resume_flag) - return 0; - driver = to_ishtp_cl_driver(dev->driver); if (driver && driver->driver.pm) { if (driver->driver.pm->resume) @@ -850,6 +843,28 @@ struct device *ishtp_device(struct ishtp_cl_device *device) EXPORT_SYMBOL(ishtp_device); /** + * ishtp_wait_resume() - Wait for IPC resume + * + * Wait for IPC resume + * + * Return: resume complete or not + */ +bool ishtp_wait_resume(struct ishtp_device *dev) +{ + /* 50ms to get resume response */ + #define WAIT_FOR_RESUME_ACK_MS 50 + + /* Waiting to get resume response */ + if (dev->resume_flag) + wait_event_interruptible_timeout(dev->resume_wait, + !dev->resume_flag, + msecs_to_jiffies(WAIT_FOR_RESUME_ACK_MS)); + + return (!dev->resume_flag); +} +EXPORT_SYMBOL_GPL(ishtp_wait_resume); + +/** * ishtp_get_pci_device() - Return PCI device dev pointer * This interface is used to return PCI device pointer * from ishtp_cl_device instance. diff --git a/drivers/hid/usbhid/Kconfig b/drivers/hid/usbhid/Kconfig index dcf3a235870f..7c2032f7f44d 100644 --- a/drivers/hid/usbhid/Kconfig +++ b/drivers/hid/usbhid/Kconfig @@ -38,7 +38,7 @@ config USB_HIDDEV help Say Y here if you want to support HID devices (from the USB specification standpoint) that aren't strictly user interface - devices, like monitor controls and Uninterruptable Power Supplies. + devices, like monitor controls and Uninterruptible Power Supplies. This module supports these devices separately using a separate event interface on /dev/usb/hiddevX (char 180:96 to 180:111). diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 81d7d12bcf34..81ba642adcb7 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2548,6 +2548,9 @@ static void wacom_wac_finger_slot(struct wacom_wac *wacom_wac, int slot; slot = input_mt_get_slot_by_key(input, hid_data->id); + if (slot < 0) + return; + input_mt_slot(input, slot); input_mt_report_slot_state(input, MT_TOOL_FINGER, prox); } @@ -3831,7 +3834,7 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev, wacom_wac->shared->touch->product == 0xF6) { input_dev->evbit[0] |= BIT_MASK(EV_SW); __set_bit(SW_MUTE_DEVICE, input_dev->swbit); - wacom_wac->shared->has_mute_touch_switch = true; + wacom_wac->has_mute_touch_switch = true; } fallthrough; diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index d5674026512a..a8688a92c760 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -120,6 +120,7 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev, u8 wqe_mode) if (!chip_ctx) return -ENOMEM; chip_ctx->chip_num = bp->chip_num; + chip_ctx->hw_stats_size = bp->hw_ring_stats_size; rdev->chip_ctx = chip_ctx; /* rest members to follow eventually */ @@ -550,6 +551,7 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev, dma_addr_t dma_map, u32 *fw_stats_ctx_id) { + struct bnxt_qplib_chip_ctx *chip_ctx = rdev->chip_ctx; struct hwrm_stat_ctx_alloc_output resp = {0}; struct hwrm_stat_ctx_alloc_input req = {0}; struct bnxt_en_dev *en_dev = rdev->en_dev; @@ -566,7 +568,7 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev, bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_ALLOC, -1, -1); req.update_period_ms = cpu_to_le32(1000); req.stats_dma_addr = cpu_to_le64(dma_map); - req.stats_dma_length = cpu_to_le16(sizeof(struct ctx_hw_stats_ext)); + req.stats_dma_length = cpu_to_le16(chip_ctx->hw_stats_size); req.stat_ctx_flags = STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE; bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index 17f0701b3cee..44282a8cdd4f 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -56,6 +56,7 @@ static void bnxt_qplib_free_stats_ctx(struct pci_dev *pdev, struct bnxt_qplib_stats *stats); static int bnxt_qplib_alloc_stats_ctx(struct pci_dev *pdev, + struct bnxt_qplib_chip_ctx *cctx, struct bnxt_qplib_stats *stats); /* PBL */ @@ -559,7 +560,7 @@ int bnxt_qplib_alloc_ctx(struct bnxt_qplib_res *res, goto fail; stats_alloc: /* Stats */ - rc = bnxt_qplib_alloc_stats_ctx(res->pdev, &ctx->stats); + rc = bnxt_qplib_alloc_stats_ctx(res->pdev, res->cctx, &ctx->stats); if (rc) goto fail; @@ -889,15 +890,12 @@ static void bnxt_qplib_free_stats_ctx(struct pci_dev *pdev, } static int bnxt_qplib_alloc_stats_ctx(struct pci_dev *pdev, + struct bnxt_qplib_chip_ctx *cctx, struct bnxt_qplib_stats *stats) { memset(stats, 0, sizeof(*stats)); stats->fw_id = -1; - /* 128 byte aligned context memory is required only for 57500. - * However making this unconditional, it does not harm previous - * generation. - */ - stats->size = ALIGN(sizeof(struct ctx_hw_stats), 128); + stats->size = cctx->hw_stats_size; stats->dma = dma_alloc_coherent(&pdev->dev, stats->size, &stats->dma_map, GFP_KERNEL); if (!stats->dma) { diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h index c291f495ae91..91031502e8f5 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h @@ -54,6 +54,7 @@ struct bnxt_qplib_chip_ctx { u16 chip_num; u8 chip_rev; u8 chip_metal; + u16 hw_stats_size; struct bnxt_qplib_drv_modes modes; }; diff --git a/drivers/infiniband/hw/irdma/ctrl.c b/drivers/infiniband/hw/irdma/ctrl.c index b1023a7d0bd1..f1e5515256e0 100644 --- a/drivers/infiniband/hw/irdma/ctrl.c +++ b/drivers/infiniband/hw/irdma/ctrl.c @@ -2845,7 +2845,7 @@ static u64 irdma_sc_decode_fpm_commit(struct irdma_sc_dev *dev, __le64 *buf, * parses fpm commit info and copy base value * of hmc objects in hmc_info */ -static enum irdma_status_code +static void irdma_sc_parse_fpm_commit_buf(struct irdma_sc_dev *dev, __le64 *buf, struct irdma_hmc_obj_info *info, u32 *sd) { @@ -2915,7 +2915,6 @@ irdma_sc_parse_fpm_commit_buf(struct irdma_sc_dev *dev, __le64 *buf, else *sd = (u32)(size >> 21); - return 0; } /** @@ -4187,11 +4186,9 @@ enum irdma_status_code irdma_sc_get_next_aeqe(struct irdma_sc_aeq *aeq, * @dev: sc device struct * @count: allocate count */ -enum irdma_status_code irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, u32 count) +void irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, u32 count) { writel(count, dev->hw_regs[IRDMA_AEQALLOC]); - - return 0; } /** @@ -4434,9 +4431,9 @@ static enum irdma_status_code irdma_sc_cfg_iw_fpm(struct irdma_sc_dev *dev, ret_code = irdma_sc_commit_fpm_val(dev->cqp, 0, hmc_info->hmc_fn_id, &commit_fpm_mem, true, wait_type); if (!ret_code) - ret_code = irdma_sc_parse_fpm_commit_buf(dev, dev->fpm_commit_buf, - hmc_info->hmc_obj, - &hmc_info->sd_table.sd_cnt); + irdma_sc_parse_fpm_commit_buf(dev, dev->fpm_commit_buf, + hmc_info->hmc_obj, + &hmc_info->sd_table.sd_cnt); print_hex_dump_debug("HMC: COMMIT FPM BUFFER", DUMP_PREFIX_OFFSET, 16, 8, commit_fpm_mem.va, IRDMA_COMMIT_FPM_BUF_SIZE, false); diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c index 7afb8a6a0526..00de5ee9a260 100644 --- a/drivers/infiniband/hw/irdma/hw.c +++ b/drivers/infiniband/hw/irdma/hw.c @@ -1920,7 +1920,7 @@ enum irdma_status_code irdma_ctrl_init_hw(struct irdma_pci_f *rf) * irdma_set_hw_rsrc - set hw memory resources. * @rf: RDMA PCI function */ -static u32 irdma_set_hw_rsrc(struct irdma_pci_f *rf) +static void irdma_set_hw_rsrc(struct irdma_pci_f *rf) { rf->allocated_qps = (void *)(rf->mem_rsrc + (sizeof(struct irdma_arp_entry) * rf->arp_table_size)); @@ -1937,8 +1937,6 @@ static u32 irdma_set_hw_rsrc(struct irdma_pci_f *rf) spin_lock_init(&rf->arp_lock); spin_lock_init(&rf->qptable_lock); spin_lock_init(&rf->qh_list_lock); - - return 0; } /** @@ -2000,9 +1998,7 @@ u32 irdma_initialize_hw_rsrc(struct irdma_pci_f *rf) rf->arp_table = (struct irdma_arp_entry *)rf->mem_rsrc; - ret = irdma_set_hw_rsrc(rf); - if (ret) - goto set_hw_rsrc_fail; + irdma_set_hw_rsrc(rf); set_bit(0, rf->allocated_mrs); set_bit(0, rf->allocated_qps); @@ -2025,9 +2021,6 @@ u32 irdma_initialize_hw_rsrc(struct irdma_pci_f *rf) return 0; -set_hw_rsrc_fail: - kfree(rf->mem_rsrc); - rf->mem_rsrc = NULL; mem_rsrc_kzalloc_fail: kfree(rf->allocated_ws_nodes); rf->allocated_ws_nodes = NULL; diff --git a/drivers/infiniband/hw/irdma/main.c b/drivers/infiniband/hw/irdma/main.c index ea59432351fb..51a41359e0b4 100644 --- a/drivers/infiniband/hw/irdma/main.c +++ b/drivers/infiniband/hw/irdma/main.c @@ -215,10 +215,10 @@ static void irdma_remove(struct auxiliary_device *aux_dev) pr_debug("INIT: Gen2 PF[%d] device remove success\n", PCI_FUNC(pf->pdev->devfn)); } -static void irdma_fill_device_info(struct irdma_device *iwdev, struct ice_pf *pf) +static void irdma_fill_device_info(struct irdma_device *iwdev, struct ice_pf *pf, + struct ice_vsi *vsi) { struct irdma_pci_f *rf = iwdev->rf; - struct ice_vsi *vsi = ice_get_main_vsi(pf); rf->cdev = pf; rf->gen_ops.register_qset = irdma_lan_register_qset; @@ -253,12 +253,15 @@ static int irdma_probe(struct auxiliary_device *aux_dev, const struct auxiliary_ struct iidc_auxiliary_dev, adev); struct ice_pf *pf = iidc_adev->pf; + struct ice_vsi *vsi = ice_get_main_vsi(pf); struct iidc_qos_params qos_info = {}; struct irdma_device *iwdev; struct irdma_pci_f *rf; struct irdma_l2params l2params = {}; int err; + if (!vsi) + return -EIO; iwdev = ib_alloc_device(irdma_device, ibdev); if (!iwdev) return -ENOMEM; @@ -268,7 +271,7 @@ static int irdma_probe(struct auxiliary_device *aux_dev, const struct auxiliary_ return -ENOMEM; } - irdma_fill_device_info(iwdev, pf); + irdma_fill_device_info(iwdev, pf, vsi); rf = iwdev->rf; if (irdma_ctrl_init_hw(rf)) { diff --git a/drivers/infiniband/hw/irdma/type.h b/drivers/infiniband/hw/irdma/type.h index 7387b83e826d..874bc25a938b 100644 --- a/drivers/infiniband/hw/irdma/type.h +++ b/drivers/infiniband/hw/irdma/type.h @@ -1222,8 +1222,7 @@ enum irdma_status_code irdma_sc_aeq_init(struct irdma_sc_aeq *aeq, struct irdma_aeq_init_info *info); enum irdma_status_code irdma_sc_get_next_aeqe(struct irdma_sc_aeq *aeq, struct irdma_aeqe_info *info); -enum irdma_status_code irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, - u32 count); +void irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, u32 count); void irdma_sc_pd_init(struct irdma_sc_dev *dev, struct irdma_sc_pd *pd, u32 pd_id, int abi_ver); diff --git a/drivers/infiniband/hw/irdma/uk.c b/drivers/infiniband/hw/irdma/uk.c index a6d52c20091c..5fb92de1f015 100644 --- a/drivers/infiniband/hw/irdma/uk.c +++ b/drivers/infiniband/hw/irdma/uk.c @@ -931,7 +931,7 @@ enum irdma_status_code irdma_uk_mw_bind(struct irdma_qp_uk *qp, enum irdma_status_code irdma_uk_post_receive(struct irdma_qp_uk *qp, struct irdma_post_rq_info *info) { - u32 total_size = 0, wqe_idx, i, byte_off; + u32 wqe_idx, i, byte_off; u32 addl_frag_cnt; __le64 *wqe; u64 hdr; @@ -939,9 +939,6 @@ enum irdma_status_code irdma_uk_post_receive(struct irdma_qp_uk *qp, if (qp->max_rq_frag_cnt < info->num_sges) return IRDMA_ERR_INVALID_FRAG_COUNT; - for (i = 0; i < info->num_sges; i++) - total_size += info->sg_list[i].len; - wqe = irdma_qp_get_next_recv_wqe(qp, &wqe_idx); if (!wqe) return IRDMA_ERR_QP_TOOMANY_WRS_POSTED; diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 9712f6902ba8..717147ed0519 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -557,7 +557,7 @@ static int irdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) * @iwqp: qp ptr * @init_info: initialize info to return */ -static int irdma_setup_virt_qp(struct irdma_device *iwdev, +static void irdma_setup_virt_qp(struct irdma_device *iwdev, struct irdma_qp *iwqp, struct irdma_qp_init_info *init_info) { @@ -574,8 +574,6 @@ static int irdma_setup_virt_qp(struct irdma_device *iwdev, init_info->sq_pa = qpmr->sq_pbl.addr; init_info->rq_pa = qpmr->rq_pbl.addr; } - - return 0; } /** @@ -914,7 +912,7 @@ static struct ib_qp *irdma_create_qp(struct ib_pd *ibpd, } } init_info.qp_uk_init_info.abi_ver = iwpd->sc_pd.abi_ver; - err_code = irdma_setup_virt_qp(iwdev, iwqp, &init_info); + irdma_setup_virt_qp(iwdev, iwqp, &init_info); } else { init_info.qp_uk_init_info.abi_ver = IRDMA_ABI_VER; err_code = irdma_setup_kmode_qp(iwdev, iwqp, &init_info, init_attr); diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c index 6aabcb4de235..be4bcb420fab 100644 --- a/drivers/infiniband/sw/rxe/rxe_mr.c +++ b/drivers/infiniband/sw/rxe/rxe_mr.c @@ -113,13 +113,14 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova, int num_buf; void *vaddr; int err; + int i; umem = ib_umem_get(pd->ibpd.device, start, length, access); if (IS_ERR(umem)) { - pr_warn("err %d from rxe_umem_get\n", - (int)PTR_ERR(umem)); + pr_warn("%s: Unable to pin memory region err = %d\n", + __func__, (int)PTR_ERR(umem)); err = PTR_ERR(umem); - goto err1; + goto err_out; } mr->umem = umem; @@ -129,9 +130,9 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova, err = rxe_mr_alloc(mr, num_buf); if (err) { - pr_warn("err %d from rxe_mr_alloc\n", err); - ib_umem_release(umem); - goto err1; + pr_warn("%s: Unable to allocate memory for map\n", + __func__); + goto err_release_umem; } mr->page_shift = PAGE_SHIFT; @@ -151,10 +152,10 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova, vaddr = page_address(sg_page_iter_page(&sg_iter)); if (!vaddr) { - pr_warn("null vaddr\n"); - ib_umem_release(umem); + pr_warn("%s: Unable to get virtual address\n", + __func__); err = -ENOMEM; - goto err1; + goto err_cleanup_map; } buf->addr = (uintptr_t)vaddr; @@ -177,7 +178,13 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova, return 0; -err1: +err_cleanup_map: + for (i = 0; i < mr->num_map; i++) + kfree(mr->map[i]); + kfree(mr->map); +err_release_umem: + ib_umem_release(umem); +err_out: return err; } diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c index dd17b8c53e1c..89d9c986a229 100644 --- a/drivers/net/can/spi/hi311x.c +++ b/drivers/net/can/spi/hi311x.c @@ -218,7 +218,7 @@ static int hi3110_spi_trans(struct spi_device *spi, int len) return ret; } -static u8 hi3110_cmd(struct spi_device *spi, u8 command) +static int hi3110_cmd(struct spi_device *spi, u8 command) { struct hi3110_priv *priv = spi_get_drvdata(spi); diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 47c3f408a799..9ae48072b6c6 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -2300,6 +2300,7 @@ static irqreturn_t mcp251xfd_irq(int irq, void *dev_id) err, priv->regs_status.intf); mcp251xfd_dump(priv); mcp251xfd_chip_interrupts_disable(priv); + mcp251xfd_timestamp_stop(priv); return handled; } diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index 0a37af4a3fa4..2b5302e72435 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -255,6 +255,8 @@ struct ems_usb { unsigned int free_slots; /* remember number of available slots */ struct ems_cpc_msg active_params; /* active controller parameters */ + void *rxbuf[MAX_RX_URBS]; + dma_addr_t rxbuf_dma[MAX_RX_URBS]; }; static void ems_usb_read_interrupt_callback(struct urb *urb) @@ -587,6 +589,7 @@ static int ems_usb_start(struct ems_usb *dev) for (i = 0; i < MAX_RX_URBS; i++) { struct urb *urb = NULL; u8 *buf = NULL; + dma_addr_t buf_dma; /* create a URB, and a buffer for it */ urb = usb_alloc_urb(0, GFP_KERNEL); @@ -596,7 +599,7 @@ static int ems_usb_start(struct ems_usb *dev) } buf = usb_alloc_coherent(dev->udev, RX_BUFFER_SIZE, GFP_KERNEL, - &urb->transfer_dma); + &buf_dma); if (!buf) { netdev_err(netdev, "No memory left for USB buffer\n"); usb_free_urb(urb); @@ -604,6 +607,8 @@ static int ems_usb_start(struct ems_usb *dev) break; } + urb->transfer_dma = buf_dma; + usb_fill_bulk_urb(urb, dev->udev, usb_rcvbulkpipe(dev->udev, 2), buf, RX_BUFFER_SIZE, ems_usb_read_bulk_callback, dev); @@ -619,6 +624,9 @@ static int ems_usb_start(struct ems_usb *dev) break; } + dev->rxbuf[i] = buf; + dev->rxbuf_dma[i] = buf_dma; + /* Drop reference, USB core will take care of freeing it */ usb_free_urb(urb); } @@ -684,6 +692,10 @@ static void unlink_all_urbs(struct ems_usb *dev) usb_kill_anchored_urbs(&dev->rx_submitted); + for (i = 0; i < MAX_RX_URBS; ++i) + usb_free_coherent(dev->udev, RX_BUFFER_SIZE, + dev->rxbuf[i], dev->rxbuf_dma[i]); + usb_kill_anchored_urbs(&dev->tx_submitted); atomic_set(&dev->active_tx_urbs, 0); diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c index 65b58f8fc328..66fa8b07c2e6 100644 --- a/drivers/net/can/usb/esd_usb2.c +++ b/drivers/net/can/usb/esd_usb2.c @@ -195,6 +195,8 @@ struct esd_usb2 { int net_count; u32 version; int rxinitdone; + void *rxbuf[MAX_RX_URBS]; + dma_addr_t rxbuf_dma[MAX_RX_URBS]; }; struct esd_usb2_net_priv { @@ -545,6 +547,7 @@ static int esd_usb2_setup_rx_urbs(struct esd_usb2 *dev) for (i = 0; i < MAX_RX_URBS; i++) { struct urb *urb = NULL; u8 *buf = NULL; + dma_addr_t buf_dma; /* create a URB, and a buffer for it */ urb = usb_alloc_urb(0, GFP_KERNEL); @@ -554,7 +557,7 @@ static int esd_usb2_setup_rx_urbs(struct esd_usb2 *dev) } buf = usb_alloc_coherent(dev->udev, RX_BUFFER_SIZE, GFP_KERNEL, - &urb->transfer_dma); + &buf_dma); if (!buf) { dev_warn(dev->udev->dev.parent, "No memory left for USB buffer\n"); @@ -562,6 +565,8 @@ static int esd_usb2_setup_rx_urbs(struct esd_usb2 *dev) goto freeurb; } + urb->transfer_dma = buf_dma; + usb_fill_bulk_urb(urb, dev->udev, usb_rcvbulkpipe(dev->udev, 1), buf, RX_BUFFER_SIZE, @@ -574,8 +579,12 @@ static int esd_usb2_setup_rx_urbs(struct esd_usb2 *dev) usb_unanchor_urb(urb); usb_free_coherent(dev->udev, RX_BUFFER_SIZE, buf, urb->transfer_dma); + goto freeurb; } + dev->rxbuf[i] = buf; + dev->rxbuf_dma[i] = buf_dma; + freeurb: /* Drop reference, USB core will take care of freeing it */ usb_free_urb(urb); @@ -663,6 +672,11 @@ static void unlink_all_urbs(struct esd_usb2 *dev) int i, j; usb_kill_anchored_urbs(&dev->rx_submitted); + + for (i = 0; i < MAX_RX_URBS; ++i) + usb_free_coherent(dev->udev, RX_BUFFER_SIZE, + dev->rxbuf[i], dev->rxbuf_dma[i]); + for (i = 0; i < dev->net_count; i++) { priv = dev->nets[i]; if (priv) { diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index a45865bd7254..a1a154c08b7f 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -653,6 +653,8 @@ static int mcba_usb_start(struct mcba_priv *priv) break; } + urb->transfer_dma = buf_dma; + usb_fill_bulk_urb(urb, priv->udev, usb_rcvbulkpipe(priv->udev, MCBA_USB_EP_IN), buf, MCBA_USB_RX_BUFF_SIZE, diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index 1d6f77252f01..899a3d21b77f 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -117,7 +117,8 @@ #define PCAN_USB_BERR_MASK (PCAN_USB_ERR_RXERR | PCAN_USB_ERR_TXERR) /* identify bus event packets with rx/tx error counters */ -#define PCAN_USB_ERR_CNT 0x80 +#define PCAN_USB_ERR_CNT_DEC 0x00 /* counters are decreasing */ +#define PCAN_USB_ERR_CNT_INC 0x80 /* counters are increasing */ /* private to PCAN-USB adapter */ struct pcan_usb { @@ -608,11 +609,12 @@ static int pcan_usb_handle_bus_evt(struct pcan_usb_msg_context *mc, u8 ir) /* acccording to the content of the packet */ switch (ir) { - case PCAN_USB_ERR_CNT: + case PCAN_USB_ERR_CNT_DEC: + case PCAN_USB_ERR_CNT_INC: /* save rx/tx error counters from in the device context */ - pdev->bec.rxerr = mc->ptr[0]; - pdev->bec.txerr = mc->ptr[1]; + pdev->bec.rxerr = mc->ptr[1]; + pdev->bec.txerr = mc->ptr[2]; break; default: diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c index b6e7ef0d5bc6..d1b83bd1b3cb 100644 --- a/drivers/net/can/usb/usb_8dev.c +++ b/drivers/net/can/usb/usb_8dev.c @@ -137,7 +137,8 @@ struct usb_8dev_priv { u8 *cmd_msg_buffer; struct mutex usb_8dev_cmd_lock; - + void *rxbuf[MAX_RX_URBS]; + dma_addr_t rxbuf_dma[MAX_RX_URBS]; }; /* tx frame */ @@ -733,6 +734,7 @@ static int usb_8dev_start(struct usb_8dev_priv *priv) for (i = 0; i < MAX_RX_URBS; i++) { struct urb *urb = NULL; u8 *buf; + dma_addr_t buf_dma; /* create a URB, and a buffer for it */ urb = usb_alloc_urb(0, GFP_KERNEL); @@ -742,7 +744,7 @@ static int usb_8dev_start(struct usb_8dev_priv *priv) } buf = usb_alloc_coherent(priv->udev, RX_BUFFER_SIZE, GFP_KERNEL, - &urb->transfer_dma); + &buf_dma); if (!buf) { netdev_err(netdev, "No memory left for USB buffer\n"); usb_free_urb(urb); @@ -750,6 +752,8 @@ static int usb_8dev_start(struct usb_8dev_priv *priv) break; } + urb->transfer_dma = buf_dma; + usb_fill_bulk_urb(urb, priv->udev, usb_rcvbulkpipe(priv->udev, USB_8DEV_ENDP_DATA_RX), @@ -767,6 +771,9 @@ static int usb_8dev_start(struct usb_8dev_priv *priv) break; } + priv->rxbuf[i] = buf; + priv->rxbuf_dma[i] = buf_dma; + /* Drop reference, USB core will take care of freeing it */ usb_free_urb(urb); } @@ -836,6 +843,10 @@ static void unlink_all_urbs(struct usb_8dev_priv *priv) usb_kill_anchored_urbs(&priv->rx_submitted); + for (i = 0; i < MAX_RX_URBS; ++i) + usb_free_coherent(priv->udev, RX_BUFFER_SIZE, + priv->rxbuf[i], priv->rxbuf_dma[i]); + usb_kill_anchored_urbs(&priv->tx_submitted); atomic_set(&priv->active_tx_urbs, 0); diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index beb41572d04e..272b0535d946 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2155,7 +2155,7 @@ static int mv88e6xxx_port_vlan_leave(struct mv88e6xxx_chip *chip, int i, err; if (!vid) - return -EOPNOTSUPP; + return 0; err = mv88e6xxx_vtu_get(chip, vid, &vlan); if (err) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 4db162cee911..89606587b156 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -12131,9 +12131,8 @@ static void bnxt_fw_reset_task(struct work_struct *work) /* Make sure fw_reset_state is 0 before clearing the flag */ smp_mb__before_atomic(); clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); - bnxt_ulp_start(bp, rc); - if (!rc) - bnxt_reenable_sriov(bp); + bnxt_ulp_start(bp, 0); + bnxt_reenable_sriov(bp); bnxt_vf_reps_alloc(bp); bnxt_vf_reps_open(bp); bnxt_dl_health_recovery_done(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 9089e7f3fbd4..ec381c2423b8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -353,6 +353,12 @@ static long bnxt_ptp_ts_aux_work(struct ptp_clock_info *ptp_info) bnxt_ptp_get_current_time(bp); ptp->next_period = now + HZ; + if (time_after_eq(now, ptp->next_overflow_check)) { + spin_lock_bh(&ptp->ptp_lock); + timecounter_read(&ptp->tc); + spin_unlock_bh(&ptp->ptp_lock); + ptp->next_overflow_check = now + BNXT_PHC_OVERFLOW_PERIOD; + } return HZ; } @@ -423,6 +429,7 @@ int bnxt_ptp_init(struct bnxt *bp) ptp->cc.shift = 0; ptp->cc.mult = 1; + ptp->next_overflow_check = jiffies + BNXT_PHC_OVERFLOW_PERIOD; timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real())); ptp->ptp_info = bnxt_ptp_caps; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h index 4135ea3ec788..254ba7bc0f99 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h @@ -32,6 +32,10 @@ struct bnxt_ptp_cfg { u64 current_time; u64 old_time; unsigned long next_period; + unsigned long next_overflow_check; + /* 48-bit PHC overflows in 78 hours. Check overflow every 19 hours. */ + #define BNXT_PHC_OVERFLOW_PERIOD (19 * 3600 * HZ) + u16 tx_seqid; struct bnxt *bp; atomic_t tx_avail; diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c index f6ff1f76eacb..1876f15dd827 100644 --- a/drivers/net/ethernet/dec/tulip/winbond-840.c +++ b/drivers/net/ethernet/dec/tulip/winbond-840.c @@ -357,7 +357,7 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) int i, option = find_cnt < MAX_UNITS ? options[find_cnt] : 0; void __iomem *ioaddr; - i = pci_enable_device(pdev); + i = pcim_enable_device(pdev); if (i) return i; pci_set_master(pdev); @@ -379,7 +379,7 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) ioaddr = pci_iomap(pdev, TULIP_BAR, netdev_res_size); if (!ioaddr) - goto err_out_free_res; + goto err_out_netdev; for (i = 0; i < 3; i++) ((__le16 *)dev->dev_addr)[i] = cpu_to_le16(eeprom_read(ioaddr, i)); @@ -458,8 +458,6 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) err_out_cleardev: pci_iounmap(pdev, ioaddr); -err_out_free_res: - pci_release_regions(pdev); err_out_netdev: free_netdev (dev); return -ENODEV; @@ -1526,7 +1524,6 @@ static void w840_remove1(struct pci_dev *pdev) if (dev) { struct netdev_private *np = netdev_priv(dev); unregister_netdev(dev); - pci_release_regions(pdev); pci_iounmap(pdev, np->base_addr); free_netdev(dev); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c index 3b1f84502e36..befa9bcc2f2f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c @@ -5,9 +5,27 @@ #include "hclge_main.h" #include "hnae3.h" +static int hclge_ptp_get_cycle(struct hclge_dev *hdev) +{ + struct hclge_ptp *ptp = hdev->ptp; + + ptp->cycle.quo = readl(hdev->ptp->io_base + HCLGE_PTP_CYCLE_QUO_REG) & + HCLGE_PTP_CYCLE_QUO_MASK; + ptp->cycle.numer = readl(hdev->ptp->io_base + HCLGE_PTP_CYCLE_NUM_REG); + ptp->cycle.den = readl(hdev->ptp->io_base + HCLGE_PTP_CYCLE_DEN_REG); + + if (ptp->cycle.den == 0) { + dev_err(&hdev->pdev->dev, "invalid ptp cycle denominator!\n"); + return -EINVAL; + } + + return 0; +} + static int hclge_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) { struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp); + struct hclge_ptp_cycle *cycle = &hdev->ptp->cycle; u64 adj_val, adj_base, diff; unsigned long flags; bool is_neg = false; @@ -18,7 +36,7 @@ static int hclge_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) is_neg = true; } - adj_base = HCLGE_PTP_CYCLE_ADJ_BASE * HCLGE_PTP_CYCLE_ADJ_UNIT; + adj_base = (u64)cycle->quo * (u64)cycle->den + (u64)cycle->numer; adj_val = adj_base * ppb; diff = div_u64(adj_val, 1000000000ULL); @@ -29,16 +47,16 @@ static int hclge_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) /* This clock cycle is defined by three part: quotient, numerator * and denominator. For example, 2.5ns, the quotient is 2, - * denominator is fixed to HCLGE_PTP_CYCLE_ADJ_UNIT, and numerator - * is 0.5 * HCLGE_PTP_CYCLE_ADJ_UNIT. + * denominator is fixed to ptp->cycle.den, and numerator + * is 0.5 * ptp->cycle.den. */ - quo = div_u64_rem(adj_val, HCLGE_PTP_CYCLE_ADJ_UNIT, &numerator); + quo = div_u64_rem(adj_val, cycle->den, &numerator); spin_lock_irqsave(&hdev->ptp->lock, flags); - writel(quo, hdev->ptp->io_base + HCLGE_PTP_CYCLE_QUO_REG); + writel(quo & HCLGE_PTP_CYCLE_QUO_MASK, + hdev->ptp->io_base + HCLGE_PTP_CYCLE_QUO_REG); writel(numerator, hdev->ptp->io_base + HCLGE_PTP_CYCLE_NUM_REG); - writel(HCLGE_PTP_CYCLE_ADJ_UNIT, - hdev->ptp->io_base + HCLGE_PTP_CYCLE_DEN_REG); + writel(cycle->den, hdev->ptp->io_base + HCLGE_PTP_CYCLE_DEN_REG); writel(HCLGE_PTP_CYCLE_ADJ_EN, hdev->ptp->io_base + HCLGE_PTP_CYCLE_CFG_REG); spin_unlock_irqrestore(&hdev->ptp->lock, flags); @@ -475,6 +493,10 @@ int hclge_ptp_init(struct hclge_dev *hdev) ret = hclge_ptp_create_clock(hdev); if (ret) return ret; + + ret = hclge_ptp_get_cycle(hdev); + if (ret) + return ret; } ret = hclge_ptp_int_en(hdev, true); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h index 5a202b775471..dbf5f4c08019 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h @@ -29,6 +29,7 @@ #define HCLGE_PTP_TIME_ADJ_REG 0x60 #define HCLGE_PTP_TIME_ADJ_EN BIT(0) #define HCLGE_PTP_CYCLE_QUO_REG 0x64 +#define HCLGE_PTP_CYCLE_QUO_MASK GENMASK(7, 0) #define HCLGE_PTP_CYCLE_DEN_REG 0x68 #define HCLGE_PTP_CYCLE_NUM_REG 0x6C #define HCLGE_PTP_CYCLE_CFG_REG 0x70 @@ -37,9 +38,7 @@ #define HCLGE_PTP_CUR_TIME_SEC_L_REG 0x78 #define HCLGE_PTP_CUR_TIME_NSEC_REG 0x7C -#define HCLGE_PTP_CYCLE_ADJ_BASE 2 #define HCLGE_PTP_CYCLE_ADJ_MAX 500000000 -#define HCLGE_PTP_CYCLE_ADJ_UNIT 100000000 #define HCLGE_PTP_SEC_H_OFFSET 32u #define HCLGE_PTP_SEC_L_MASK GENMASK(31, 0) @@ -47,6 +46,12 @@ #define HCLGE_PTP_FLAG_TX_EN 1 #define HCLGE_PTP_FLAG_RX_EN 2 +struct hclge_ptp_cycle { + u32 quo; + u32 numer; + u32 den; +}; + struct hclge_ptp { struct hclge_dev *hdev; struct ptp_clock *clock; @@ -58,6 +63,7 @@ struct hclge_ptp { spinlock_t lock; /* protects ptp registers */ u32 ptp_cfg; u32 last_tx_seqid; + struct hclge_ptp_cycle cycle; unsigned long tx_start; unsigned long tx_cnt; unsigned long tx_skipped; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 3e822bad4851..2c9e4eeb7270 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -980,7 +980,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, default: /* if we got here and link is up something bad is afoot */ netdev_info(netdev, - "WARNING: Link is up but PHY type 0x%x is not recognized.\n", + "WARNING: Link is up but PHY type 0x%x is not recognized, or incorrect cable is in use\n", hw_link_info->phy_type); } @@ -5294,6 +5294,10 @@ flags_complete: dev_warn(&pf->pdev->dev, "Device configuration forbids SW from starting the LLDP agent.\n"); return -EINVAL; + case I40E_AQ_RC_EAGAIN: + dev_warn(&pf->pdev->dev, + "Stop FW LLDP agent command is still being processed, please try again in a second.\n"); + return -EBUSY; default: dev_warn(&pf->pdev->dev, "Starting FW LLDP agent failed: error: %s, %s\n", diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 861e59a350bd..1d1f52756a93 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4454,11 +4454,10 @@ int i40e_control_wait_tx_q(int seid, struct i40e_pf *pf, int pf_q, } /** - * i40e_vsi_control_tx - Start or stop a VSI's rings + * i40e_vsi_enable_tx - Start a VSI's rings * @vsi: the VSI being configured - * @enable: start or stop the rings **/ -static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable) +static int i40e_vsi_enable_tx(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; int i, pf_q, ret = 0; @@ -4467,7 +4466,7 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable) for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { ret = i40e_control_wait_tx_q(vsi->seid, pf, pf_q, - false /*is xdp*/, enable); + false /*is xdp*/, true); if (ret) break; @@ -4476,7 +4475,7 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable) ret = i40e_control_wait_tx_q(vsi->seid, pf, pf_q + vsi->alloc_queue_pairs, - true /*is xdp*/, enable); + true /*is xdp*/, true); if (ret) break; } @@ -4574,32 +4573,25 @@ int i40e_control_wait_rx_q(struct i40e_pf *pf, int pf_q, bool enable) } /** - * i40e_vsi_control_rx - Start or stop a VSI's rings + * i40e_vsi_enable_rx - Start a VSI's rings * @vsi: the VSI being configured - * @enable: start or stop the rings **/ -static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable) +static int i40e_vsi_enable_rx(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; int i, pf_q, ret = 0; pf_q = vsi->base_queue; for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { - ret = i40e_control_wait_rx_q(pf, pf_q, enable); + ret = i40e_control_wait_rx_q(pf, pf_q, true); if (ret) { dev_info(&pf->pdev->dev, - "VSI seid %d Rx ring %d %sable timeout\n", - vsi->seid, pf_q, (enable ? "en" : "dis")); + "VSI seid %d Rx ring %d enable timeout\n", + vsi->seid, pf_q); break; } } - /* Due to HW errata, on Rx disable only, the register can indicate done - * before it really is. Needs 50ms to be sure - */ - if (!enable) - mdelay(50); - return ret; } @@ -4612,29 +4604,47 @@ int i40e_vsi_start_rings(struct i40e_vsi *vsi) int ret = 0; /* do rx first for enable and last for disable */ - ret = i40e_vsi_control_rx(vsi, true); + ret = i40e_vsi_enable_rx(vsi); if (ret) return ret; - ret = i40e_vsi_control_tx(vsi, true); + ret = i40e_vsi_enable_tx(vsi); return ret; } +#define I40E_DISABLE_TX_GAP_MSEC 50 + /** * i40e_vsi_stop_rings - Stop a VSI's rings * @vsi: the VSI being configured **/ void i40e_vsi_stop_rings(struct i40e_vsi *vsi) { + struct i40e_pf *pf = vsi->back; + int pf_q, err, q_end; + /* When port TX is suspended, don't wait */ if (test_bit(__I40E_PORT_SUSPENDED, vsi->back->state)) return i40e_vsi_stop_rings_no_wait(vsi); - /* do rx first for enable and last for disable - * Ignore return value, we need to shutdown whatever we can - */ - i40e_vsi_control_tx(vsi, false); - i40e_vsi_control_rx(vsi, false); + q_end = vsi->base_queue + vsi->num_queue_pairs; + for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) + i40e_pre_tx_queue_cfg(&pf->hw, (u32)pf_q, false); + + for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) { + err = i40e_control_wait_rx_q(pf, pf_q, false); + if (err) + dev_info(&pf->pdev->dev, + "VSI seid %d Rx ring %d dissable timeout\n", + vsi->seid, pf_q); + } + + msleep(I40E_DISABLE_TX_GAP_MSEC); + pf_q = vsi->base_queue; + for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) + wr32(&pf->hw, I40E_QTX_ENA(pf_q), 0); + + i40e_vsi_wait_queues_disabled(vsi); } /** @@ -7280,6 +7290,8 @@ static int i40e_validate_mqprio_qopt(struct i40e_vsi *vsi, } if (vsi->num_queue_pairs < (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) { + dev_err(&vsi->back->pdev->dev, + "Failed to create traffic channel, insufficient number of queues.\n"); return -EINVAL; } if (sum_max_rate > i40e_get_link_speed(vsi)) { @@ -13261,6 +13273,7 @@ static const struct net_device_ops i40e_netdev_ops = { .ndo_poll_controller = i40e_netpoll, #endif .ndo_setup_tc = __i40e_setup_tc, + .ndo_select_queue = i40e_lan_select_queue, .ndo_set_features = i40e_set_features, .ndo_set_vf_mac = i40e_ndo_set_vf_mac, .ndo_set_vf_vlan = i40e_ndo_set_vf_port_vlan, diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 38eb8151ee9a..3f25bd8c4924 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -3631,6 +3631,56 @@ dma_error: return -1; } +static u16 i40e_swdcb_skb_tx_hash(struct net_device *dev, + const struct sk_buff *skb, + u16 num_tx_queues) +{ + u32 jhash_initval_salt = 0xd631614b; + u32 hash; + + if (skb->sk && skb->sk->sk_hash) + hash = skb->sk->sk_hash; + else + hash = (__force u16)skb->protocol ^ skb->hash; + + hash = jhash_1word(hash, jhash_initval_salt); + + return (u16)(((u64)hash * num_tx_queues) >> 32); +} + +u16 i40e_lan_select_queue(struct net_device *netdev, + struct sk_buff *skb, + struct net_device __always_unused *sb_dev) +{ + struct i40e_netdev_priv *np = netdev_priv(netdev); + struct i40e_vsi *vsi = np->vsi; + struct i40e_hw *hw; + u16 qoffset; + u16 qcount; + u8 tclass; + u16 hash; + u8 prio; + + /* is DCB enabled at all? */ + if (vsi->tc_config.numtc == 1) + return i40e_swdcb_skb_tx_hash(netdev, skb, + netdev->real_num_tx_queues); + + prio = skb->priority; + hw = &vsi->back->hw; + tclass = hw->local_dcbx_config.etscfg.prioritytable[prio]; + /* sanity check */ + if (unlikely(!(vsi->tc_config.enabled_tc & BIT(tclass)))) + tclass = 0; + + /* select a queue assigned for the given TC */ + qcount = vsi->tc_config.tc_info[tclass].qcount; + hash = i40e_swdcb_skb_tx_hash(netdev, skb, qcount); + + qoffset = vsi->tc_config.tc_info[tclass].qoffset; + return qoffset + hash; +} + /** * i40e_xmit_xdp_ring - transmits an XDP buffer to an XDP Tx ring * @xdpf: data to transmit diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 86fed05b4f19..bfc2845c99d1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -451,6 +451,8 @@ static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring) bool i40e_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count); netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev); +u16 i40e_lan_select_queue(struct net_device *netdev, struct sk_buff *skb, + struct net_device *sb_dev); void i40e_clean_tx_ring(struct i40e_ring *tx_ring); void i40e_clean_rx_ring(struct i40e_ring *rx_ring); int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 9169849881bf..544c96c8fe1d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -1504,8 +1504,8 @@ static int cgx_lmac_init(struct cgx *cgx) /* Add reference */ cgx->lmac_idmap[lmac->lmac_id] = lmac; - cgx->mac_ops->mac_pause_frm_config(cgx, lmac->lmac_id, true); set_bit(lmac->lmac_id, &cgx->lmac_bmap); + cgx->mac_ops->mac_pause_frm_config(cgx, lmac->lmac_id, true); } return cgx_lmac_verify_fwi_version(cgx); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h index 19bad9a59c8f..243cf8070e77 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h @@ -151,7 +151,10 @@ enum npc_kpu_lh_ltype { * Software assigns pkind for each incoming port such as CGX * Ethernet interfaces, LBK interfaces, etc. */ +#define NPC_UNRESERVED_PKIND_COUNT NPC_RX_VLAN_EXDSA_PKIND + enum npc_pkind_type { + NPC_RX_LBK_PKIND = 0ULL, NPC_RX_VLAN_EXDSA_PKIND = 56ULL, NPC_RX_CHLEN24B_PKIND = 57ULL, NPC_RX_CPT_HDR_PKIND, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 017163fb3cd5..5fe277e354f7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -391,8 +391,10 @@ void rvu_get_pf_numvfs(struct rvu *rvu, int pf, int *numvfs, int *hwvf) /* Get numVFs attached to this PF and first HWVF */ cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf)); - *numvfs = (cfg >> 12) & 0xFF; - *hwvf = cfg & 0xFFF; + if (numvfs) + *numvfs = (cfg >> 12) & 0xFF; + if (hwvf) + *hwvf = cfg & 0xFFF; } static int rvu_get_hwvf(struct rvu *rvu, int pcifunc) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 0933699a0d2d..4bfbbdf38770 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -196,11 +196,22 @@ static void nix_rx_sync(struct rvu *rvu, int blkaddr) { int err; - /*Sync all in flight RX packets to LLC/DRAM */ + /* Sync all in flight RX packets to LLC/DRAM */ rvu_write64(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0)); err = rvu_poll_reg(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0), true); if (err) - dev_err(rvu->dev, "NIX RX software sync failed\n"); + dev_err(rvu->dev, "SYNC1: NIX RX software sync failed\n"); + + /* SW_SYNC ensures all existing transactions are finished and pkts + * are written to LLC/DRAM, queues should be teared down after + * successful SW_SYNC. Due to a HW errata, in some rare scenarios + * an existing transaction might end after SW_SYNC operation. To + * ensure operation is fully done, do the SW_SYNC twice. + */ + rvu_write64(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0)); + err = rvu_poll_reg(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0), true); + if (err) + dev_err(rvu->dev, "SYNC2: NIX RX software sync failed\n"); } static bool is_valid_txschq(struct rvu *rvu, int blkaddr, @@ -298,6 +309,7 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf) rvu_nix_chan_lbk(rvu, lbkid, vf + 1); pfvf->rx_chan_cnt = 1; pfvf->tx_chan_cnt = 1; + rvu_npc_set_pkind(rvu, NPC_RX_LBK_PKIND, pfvf); rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf, pfvf->rx_chan_base, pfvf->rx_chan_cnt); @@ -3842,7 +3854,6 @@ static void rvu_nix_block_freemem(struct rvu *rvu, int blkaddr, vlan = &nix_hw->txvlan; kfree(vlan->rsrc.bmap); mutex_destroy(&vlan->rsrc_lock); - devm_kfree(rvu->dev, vlan->entry2pfvf_map); mcast = &nix_hw->mcast; qmem_free(rvu->dev, mcast->mce_ctx); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 1097291aaa45..52b255426c22 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -1721,7 +1721,6 @@ static void npc_parser_profile_init(struct rvu *rvu, int blkaddr) { struct rvu_hwinfo *hw = rvu->hw; int num_pkinds, num_kpus, idx; - struct npc_pkind *pkind; /* Disable all KPUs and their entries */ for (idx = 0; idx < hw->npc_kpus; idx++) { @@ -1739,9 +1738,8 @@ static void npc_parser_profile_init(struct rvu *rvu, int blkaddr) * Check HW max count to avoid configuring junk or * writing to unsupported CSR addresses. */ - pkind = &hw->pkind; num_pkinds = rvu->kpu.pkinds; - num_pkinds = min_t(int, pkind->rsrc.max, num_pkinds); + num_pkinds = min_t(int, hw->npc_pkinds, num_pkinds); for (idx = 0; idx < num_pkinds; idx++) npc_config_kpuaction(rvu, blkaddr, &rvu->kpu.ikpu[idx], 0, idx, true); @@ -1891,7 +1889,8 @@ static void rvu_npc_hw_init(struct rvu *rvu, int blkaddr) if (npc_const1 & BIT_ULL(63)) npc_const2 = rvu_read64(rvu, blkaddr, NPC_AF_CONST2); - pkind->rsrc.max = (npc_const1 >> 12) & 0xFFULL; + pkind->rsrc.max = NPC_UNRESERVED_PKIND_COUNT; + hw->npc_pkinds = (npc_const1 >> 12) & 0xFFULL; hw->npc_kpu_entries = npc_const1 & 0xFFFULL; hw->npc_kpus = (npc_const >> 8) & 0x1FULL; hw->npc_intfs = npc_const & 0xFULL; @@ -2002,6 +2001,10 @@ int rvu_npc_init(struct rvu *rvu) err = rvu_alloc_bitmap(&pkind->rsrc); if (err) return err; + /* Reserve PKIND#0 for LBKs. Power reset value of LBK_CH_PKIND is '0', + * no need to configure PKIND for all LBKs separately. + */ + rvu_alloc_rsrc(&pkind->rsrc); /* Allocate mem for pkind to PF and channel mapping info */ pkind->pfchan_map = devm_kcalloc(rvu->dev, pkind->rsrc.max, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c index 2e5379710aa5..820adf390b8e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c @@ -71,8 +71,8 @@ static int rvu_switch_install_rules(struct rvu *rvu) struct rvu_switch *rswitch = &rvu->rswitch; u16 start = rswitch->start_entry; struct rvu_hwinfo *hw = rvu->hw; - int pf, vf, numvfs, hwvf; u16 pcifunc, entry = 0; + int pf, vf, numvfs; int err; for (pf = 1; pf < hw->total_pfs; pf++) { @@ -110,8 +110,8 @@ static int rvu_switch_install_rules(struct rvu *rvu) rswitch->entry2pcifunc[entry++] = pcifunc; - rvu_get_pf_numvfs(rvu, pf, &numvfs, &hwvf); - for (vf = 0; vf < numvfs; vf++, hwvf++) { + rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL); + for (vf = 0; vf < numvfs; vf++) { pcifunc = pf << 10 | ((vf + 1) & 0x3FF); rvu_get_nix_blkaddr(rvu, pcifunc); @@ -198,7 +198,7 @@ void rvu_switch_disable(struct rvu *rvu) struct npc_mcam_free_entry_req free_req = { 0 }; struct rvu_switch *rswitch = &rvu->rswitch; struct rvu_hwinfo *hw = rvu->hw; - int pf, vf, numvfs, hwvf; + int pf, vf, numvfs; struct msg_rsp rsp; u16 pcifunc; int err; @@ -217,7 +217,8 @@ void rvu_switch_disable(struct rvu *rvu) "Reverting RX rule for PF%d failed(%d)\n", pf, err); - for (vf = 0; vf < numvfs; vf++, hwvf++) { + rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL); + for (vf = 0; vf < numvfs; vf++) { pcifunc = pf << 10 | ((vf + 1) & 0x3FF); err = rvu_switch_install_rx_rule(rvu, pcifunc, 0xFFF); if (err) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 7cccd802c4ed..70fcc1fd962f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -924,12 +924,14 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx) aq->cq.drop = RQ_DROP_LVL_CQ(pfvf->hw.rq_skid, cq->cqe_cnt); aq->cq.drop_ena = 1; - /* Enable receive CQ backpressure */ - aq->cq.bp_ena = 1; - aq->cq.bpid = pfvf->bpid[0]; + if (!is_otx2_lbkvf(pfvf->pdev)) { + /* Enable receive CQ backpressure */ + aq->cq.bp_ena = 1; + aq->cq.bpid = pfvf->bpid[0]; - /* Set backpressure level is same as cq pass level */ - aq->cq.bp = RQ_PASS_LVL_CQ(pfvf->hw.rq_skid, qset->rqe_cnt); + /* Set backpressure level is same as cq pass level */ + aq->cq.bp = RQ_PASS_LVL_CQ(pfvf->hw.rq_skid, qset->rqe_cnt); + } } /* Fill AQ info */ @@ -1186,7 +1188,7 @@ static int otx2_aura_init(struct otx2_nic *pfvf, int aura_id, aq->aura.fc_hyst_bits = 0; /* Store count on all updates */ /* Enable backpressure for RQ aura */ - if (aura_id < pfvf->hw.rqpool_cnt) { + if (aura_id < pfvf->hw.rqpool_cnt && !is_otx2_lbkvf(pfvf->pdev)) { aq->aura.bp_ena = 0; aq->aura.nix0_bpid = pfvf->bpid[0]; /* Set backpressure level for RQ's Aura */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index 8df748e0677b..b906a0eb6e0d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -298,15 +298,14 @@ static int otx2_set_channels(struct net_device *dev, err = otx2_set_real_num_queues(dev, channel->tx_count, channel->rx_count); if (err) - goto fail; + return err; pfvf->hw.rx_queues = channel->rx_count; pfvf->hw.tx_queues = channel->tx_count; pfvf->qset.cq_cnt = pfvf->hw.tx_queues + pfvf->hw.rx_queues; -fail: if (if_up) - dev->netdev_ops->ndo_open(dev); + err = dev->netdev_ops->ndo_open(dev); netdev_info(dev, "Setting num Tx rings to %d, Rx rings to %d success\n", pfvf->hw.tx_queues, pfvf->hw.rx_queues); @@ -410,7 +409,7 @@ static int otx2_set_ringparam(struct net_device *netdev, qs->rqe_cnt = rx_count; if (if_up) - netdev->netdev_ops->ndo_open(netdev); + return netdev->netdev_ops->ndo_open(netdev); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index f300b807a85b..2c24944a4dba 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1662,6 +1662,7 @@ int otx2_open(struct net_device *netdev) err_tx_stop_queues: netif_tx_stop_all_queues(netdev); netif_carrier_off(netdev); + pf->flags |= OTX2_FLAG_INTF_DOWN; err_free_cints: otx2_free_cints(pf, qidx); vec = pci_irq_vector(pf->pdev, @@ -1689,6 +1690,10 @@ int otx2_stop(struct net_device *netdev) struct otx2_rss_info *rss; int qidx, vec, wrk; + /* If the DOWN flag is set resources are already freed */ + if (pf->flags & OTX2_FLAG_INTF_DOWN) + return 0; + netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 00c84656b2e7..28ac4693da3c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3535,6 +3535,7 @@ slave_start: if (!SRIOV_VALID_STATE(dev->flags)) { mlx4_err(dev, "Invalid SRIOV state\n"); + err = -EINVAL; goto err_close; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index ceebfc20f65e..def2156e50ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -500,10 +500,7 @@ static int next_phys_dev(struct device *dev, const void *data) return 1; } -/* This function is called with two flows: - * 1. During initialization of mlx5_core_dev and we don't need to lock it. - * 2. During LAG configure stage and caller holds &mlx5_intf_mutex. - */ +/* Must be called with intf_mutex held */ struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev) { struct auxiliary_device *adev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 150c8e82c738..2cbf18c967f7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -471,6 +471,15 @@ static void mlx5e_build_rx_cq_param(struct mlx5_core_dev *mdev, param->cq_period_mode = params->rx_cq_moderation.cq_period_mode; } +static u8 rq_end_pad_mode(struct mlx5_core_dev *mdev, struct mlx5e_params *params) +{ + bool ro = pcie_relaxed_ordering_enabled(mdev->pdev) && + MLX5_CAP_GEN(mdev, relaxed_ordering_write); + + return ro && params->lro_en ? + MLX5_WQ_END_PAD_MODE_NONE : MLX5_WQ_END_PAD_MODE_ALIGN; +} + int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, @@ -508,7 +517,7 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, } MLX5_SET(wq, wq, wq_type, params->rq_wq_type); - MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN); + MLX5_SET(wq, wq, end_padding_mode, rq_end_pad_mode(mdev, params)); MLX5_SET(wq, wq, log_wq_stride, mlx5e_get_rqwq_log_stride(params->rq_wq_type, ndsegs)); MLX5_SET(wq, wq, pd, mdev->mlx5e_res.hw_objs.pdn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 778e229310a9..efef4adce086 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -482,8 +482,11 @@ static void mlx5e_ptp_build_params(struct mlx5e_ptp *c, params->log_sq_size = orig->log_sq_size; mlx5e_ptp_build_sq_param(c->mdev, params, &cparams->txq_sq_param); } - if (test_bit(MLX5E_PTP_STATE_RX, c->state)) + /* RQ */ + if (test_bit(MLX5E_PTP_STATE_RX, c->state)) { + params->vlan_strip_disable = orig->vlan_strip_disable; mlx5e_ptp_build_rq_param(c->mdev, c->netdev, c->priv->q_counter, cparams); + } } static int mlx5e_init_ptp_rq(struct mlx5e_ptp *c, struct mlx5e_params *params, @@ -494,7 +497,7 @@ static int mlx5e_init_ptp_rq(struct mlx5e_ptp *c, struct mlx5e_params *params, int err; rq->wq_type = params->rq_wq_type; - rq->pdev = mdev->device; + rq->pdev = c->pdev; rq->netdev = priv->netdev; rq->priv = priv; rq->clock = &mdev->clock; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c index 86ab4e864fe6..7f94508594fb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c @@ -37,7 +37,7 @@ static void mlx5e_init_trap_rq(struct mlx5e_trap *t, struct mlx5e_params *params struct mlx5e_priv *priv = t->priv; rq->wq_type = params->rq_wq_type; - rq->pdev = mdev->device; + rq->pdev = t->pdev; rq->netdev = priv->netdev; rq->priv = priv; rq->clock = &mdev->clock; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d09e65557e75..37c440837945 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3384,7 +3384,7 @@ static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool en static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) { - int err = 0; + int err; int i; for (i = 0; i < chs->num; i++) { @@ -3392,6 +3392,8 @@ static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) if (err) return err; } + if (chs->ptp && test_bit(MLX5E_PTP_STATE_RX, chs->ptp->state)) + return mlx5e_modify_rq_vsd(&chs->ptp->rq, vsd); return 0; } @@ -3829,6 +3831,24 @@ int mlx5e_set_features(struct net_device *netdev, netdev_features_t features) return 0; } +static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev, + netdev_features_t features) +{ + features &= ~NETIF_F_HW_TLS_RX; + if (netdev->features & NETIF_F_HW_TLS_RX) + netdev_warn(netdev, "Disabling hw_tls_rx, not supported in switchdev mode\n"); + + features &= ~NETIF_F_HW_TLS_TX; + if (netdev->features & NETIF_F_HW_TLS_TX) + netdev_warn(netdev, "Disabling hw_tls_tx, not supported in switchdev mode\n"); + + features &= ~NETIF_F_NTUPLE; + if (netdev->features & NETIF_F_NTUPLE) + netdev_warn(netdev, "Disabling ntuple, not supported in switchdev mode\n"); + + return features; +} + static netdev_features_t mlx5e_fix_features(struct net_device *netdev, netdev_features_t features) { @@ -3860,15 +3880,8 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, netdev_warn(netdev, "Disabling rxhash, not supported when CQE compress is active\n"); } - if (mlx5e_is_uplink_rep(priv)) { - features &= ~NETIF_F_HW_TLS_RX; - if (netdev->features & NETIF_F_HW_TLS_RX) - netdev_warn(netdev, "Disabling hw_tls_rx, not supported in switchdev mode\n"); - - features &= ~NETIF_F_HW_TLS_TX; - if (netdev->features & NETIF_F_HW_TLS_TX) - netdev_warn(netdev, "Disabling hw_tls_tx, not supported in switchdev mode\n"); - } + if (mlx5e_is_uplink_rep(priv)) + features = mlx5e_fix_uplink_rep_features(netdev, features); mutex_unlock(&priv->state_lock); @@ -4859,6 +4872,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) if (MLX5_CAP_ETH(mdev, scatter_fcs)) netdev->hw_features |= NETIF_F_RXFCS; + if (mlx5_qos_is_supported(mdev)) + netdev->hw_features |= NETIF_F_HW_TC; + netdev->features = netdev->hw_features; /* Defaults */ @@ -4879,8 +4895,6 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_NTUPLE; #endif } - if (mlx5_qos_is_supported(mdev)) - netdev->features |= NETIF_F_HW_TC; netdev->features |= NETIF_F_HIGHDMA; netdev->features |= NETIF_F_HW_VLAN_STAG_FILTER; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 629a61e8022f..d273758255c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -452,12 +452,32 @@ static void mlx5e_detach_mod_hdr(struct mlx5e_priv *priv, static struct mlx5_core_dev *mlx5e_hairpin_get_mdev(struct net *net, int ifindex) { + struct mlx5_core_dev *mdev; struct net_device *netdev; struct mlx5e_priv *priv; - netdev = __dev_get_by_index(net, ifindex); + netdev = dev_get_by_index(net, ifindex); + if (!netdev) + return ERR_PTR(-ENODEV); + priv = netdev_priv(netdev); - return priv->mdev; + mdev = priv->mdev; + dev_put(netdev); + + /* Mirred tc action holds a refcount on the ifindex net_device (see + * net/sched/act_mirred.c:tcf_mirred_get_dev). So, it's okay to continue using mdev + * after dev_put(netdev), while we're in the context of adding a tc flow. + * + * The mdev pointer corresponds to the peer/out net_device of a hairpin. It is then + * stored in a hairpin object, which exists until all flows, that refer to it, get + * removed. + * + * On the other hand, after a hairpin object has been created, the peer net_device may + * be removed/unbound while there are still some hairpin flows that are using it. This + * case is handled by mlx5e_tc_hairpin_update_dead_peer, which is hooked to + * NETDEV_UNREGISTER event of the peer net_device. + */ + return mdev; } static int mlx5e_hairpin_create_transport(struct mlx5e_hairpin *hp) @@ -666,6 +686,10 @@ mlx5e_hairpin_create(struct mlx5e_priv *priv, struct mlx5_hairpin_params *params func_mdev = priv->mdev; peer_mdev = mlx5e_hairpin_get_mdev(dev_net(priv->netdev), peer_ifindex); + if (IS_ERR(peer_mdev)) { + err = PTR_ERR(peer_mdev); + goto create_pair_err; + } pair = mlx5_core_hairpin_create(func_mdev, peer_mdev, params); if (IS_ERR(pair)) { @@ -804,6 +828,11 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, int err; peer_mdev = mlx5e_hairpin_get_mdev(dev_net(priv->netdev), peer_ifindex); + if (IS_ERR(peer_mdev)) { + NL_SET_ERR_MSG_MOD(extack, "invalid ifindex of mirred device"); + return PTR_ERR(peer_mdev); + } + if (!MLX5_CAP_GEN(priv->mdev, hairpin) || !MLX5_CAP_GEN(peer_mdev, hairpin)) { NL_SET_ERR_MSG_MOD(extack, "hairpin is not supported"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 48cac5bf606d..d562edf5b0bc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -636,7 +636,7 @@ struct esw_vport_tbl_namespace { }; struct mlx5_vport_tbl_attr { - u16 chain; + u32 chain; u16 prio; u16 vport; const struct esw_vport_tbl_namespace *vport_ns; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 7579f3402776..011e766e4f67 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -382,10 +382,11 @@ esw_setup_vport_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *f { dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_VPORT; dest[dest_idx].vport.num = esw_attr->dests[attr_idx].rep->vport; - dest[dest_idx].vport.vhca_id = - MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id); - if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) + if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) { + dest[dest_idx].vport.vhca_id = + MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id); dest[dest_idx].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; + } if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP) { if (pkt_reformat) { flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; @@ -2367,6 +2368,9 @@ static int mlx5_esw_offloads_devcom_event(int event, switch (event) { case ESW_OFFLOADS_DEVCOM_PAIR: + if (mlx5_get_next_phys_dev(esw->dev) != peer_esw->dev) + break; + if (mlx5_eswitch_vport_match_metadata_enabled(esw) != mlx5_eswitch_vport_match_metadata_enabled(peer_esw)) break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index d7bf0a3e4a52..c0697e1b7118 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1024,17 +1024,19 @@ static int connect_fwd_rules(struct mlx5_core_dev *dev, static int connect_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft, struct fs_prio *prio) { - struct mlx5_flow_table *next_ft; + struct mlx5_flow_table *next_ft, *first_ft; int err = 0; /* Connect_prev_fts and update_root_ft_create are mutually exclusive */ - if (list_empty(&prio->node.children)) { + first_ft = list_first_entry_or_null(&prio->node.children, + struct mlx5_flow_table, node.list); + if (!first_ft || first_ft->level > ft->level) { err = connect_prev_fts(dev, ft, prio); if (err) return err; - next_ft = find_next_chained_ft(prio); + next_ft = first_ft ? first_ft : find_next_chained_ft(prio); err = connect_fwd_rules(dev, ft, next_ft); if (err) return err; @@ -2120,7 +2122,7 @@ static int disconnect_flow_table(struct mlx5_flow_table *ft) node.list) == ft)) return 0; - next_ft = find_next_chained_ft(prio); + next_ft = find_next_ft(ft); err = connect_fwd_rules(dev, next_ft, ft); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 9ff163c5bcde..9abeb80ffa31 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -626,8 +626,16 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work) } fw_reporter_ctx.err_synd = health->synd; fw_reporter_ctx.miss_counter = health->miss_counter; - devlink_health_report(health->fw_fatal_reporter, - "FW fatal error reported", &fw_reporter_ctx); + if (devlink_health_report(health->fw_fatal_reporter, + "FW fatal error reported", &fw_reporter_ctx) == -ECANCELED) { + /* If recovery wasn't performed, due to grace period, + * unload the driver. This ensures that the driver + * closes all its resources and it is not subjected to + * requests from the kernel. + */ + mlx5_core_err(dev, "Driver is in error state. Unloading\n"); + mlx5_unload_one(dev); + } } static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = { diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index af3a5368529c..e795fa63ca12 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -29,7 +29,7 @@ static const u8 ionic_qtype_versions[IONIC_QTYPE_MAX] = { */ }; -static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode); +static void ionic_lif_rx_mode(struct ionic_lif *lif); static int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr); static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr); static void ionic_link_status_check(struct ionic_lif *lif); @@ -53,7 +53,19 @@ static void ionic_dim_work(struct work_struct *work) cur_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix); qcq = container_of(dim, struct ionic_qcq, dim); new_coal = ionic_coal_usec_to_hw(qcq->q.lif->ionic, cur_moder.usec); - qcq->intr.dim_coal_hw = new_coal ? new_coal : 1; + new_coal = new_coal ? new_coal : 1; + + if (qcq->intr.dim_coal_hw != new_coal) { + unsigned int qi = qcq->cq.bound_q->index; + struct ionic_lif *lif = qcq->q.lif; + + qcq->intr.dim_coal_hw = new_coal; + + ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, + lif->rxqcqs[qi]->intr.index, + qcq->intr.dim_coal_hw); + } + dim->state = DIM_START_MEASURE; } @@ -77,7 +89,7 @@ static void ionic_lif_deferred_work(struct work_struct *work) switch (w->type) { case IONIC_DW_TYPE_RX_MODE: - ionic_lif_rx_mode(lif, w->rx_mode); + ionic_lif_rx_mode(lif); break; case IONIC_DW_TYPE_RX_ADDR_ADD: ionic_lif_addr_add(lif, w->addr); @@ -1301,10 +1313,8 @@ static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr) return 0; } -static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add, - bool can_sleep) +static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add) { - struct ionic_deferred_work *work; unsigned int nmfilters; unsigned int nufilters; @@ -1330,97 +1340,46 @@ static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add, lif->nucast--; } - if (!can_sleep) { - work = kzalloc(sizeof(*work), GFP_ATOMIC); - if (!work) - return -ENOMEM; - work->type = add ? IONIC_DW_TYPE_RX_ADDR_ADD : - IONIC_DW_TYPE_RX_ADDR_DEL; - memcpy(work->addr, addr, ETH_ALEN); - netdev_dbg(lif->netdev, "deferred: rx_filter %s %pM\n", - add ? "add" : "del", addr); - ionic_lif_deferred_enqueue(&lif->deferred, work); - } else { - netdev_dbg(lif->netdev, "rx_filter %s %pM\n", - add ? "add" : "del", addr); - if (add) - return ionic_lif_addr_add(lif, addr); - else - return ionic_lif_addr_del(lif, addr); - } + netdev_dbg(lif->netdev, "rx_filter %s %pM\n", + add ? "add" : "del", addr); + if (add) + return ionic_lif_addr_add(lif, addr); + else + return ionic_lif_addr_del(lif, addr); return 0; } static int ionic_addr_add(struct net_device *netdev, const u8 *addr) { - return ionic_lif_addr(netdev_priv(netdev), addr, ADD_ADDR, CAN_SLEEP); -} - -static int ionic_ndo_addr_add(struct net_device *netdev, const u8 *addr) -{ - return ionic_lif_addr(netdev_priv(netdev), addr, ADD_ADDR, CAN_NOT_SLEEP); + return ionic_lif_addr(netdev_priv(netdev), addr, ADD_ADDR); } static int ionic_addr_del(struct net_device *netdev, const u8 *addr) { - return ionic_lif_addr(netdev_priv(netdev), addr, DEL_ADDR, CAN_SLEEP); + return ionic_lif_addr(netdev_priv(netdev), addr, DEL_ADDR); } -static int ionic_ndo_addr_del(struct net_device *netdev, const u8 *addr) +static void ionic_lif_rx_mode(struct ionic_lif *lif) { - return ionic_lif_addr(netdev_priv(netdev), addr, DEL_ADDR, CAN_NOT_SLEEP); -} - -static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode) -{ - struct ionic_admin_ctx ctx = { - .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), - .cmd.rx_mode_set = { - .opcode = IONIC_CMD_RX_MODE_SET, - .lif_index = cpu_to_le16(lif->index), - .rx_mode = cpu_to_le16(rx_mode), - }, - }; + struct net_device *netdev = lif->netdev; + unsigned int nfilters; + unsigned int nd_flags; char buf[128]; - int err; + u16 rx_mode; int i; #define REMAIN(__x) (sizeof(buf) - (__x)) - i = scnprintf(buf, sizeof(buf), "rx_mode 0x%04x -> 0x%04x:", - lif->rx_mode, rx_mode); - if (rx_mode & IONIC_RX_MODE_F_UNICAST) - i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_UNICAST"); - if (rx_mode & IONIC_RX_MODE_F_MULTICAST) - i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_MULTICAST"); - if (rx_mode & IONIC_RX_MODE_F_BROADCAST) - i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_BROADCAST"); - if (rx_mode & IONIC_RX_MODE_F_PROMISC) - i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_PROMISC"); - if (rx_mode & IONIC_RX_MODE_F_ALLMULTI) - i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_ALLMULTI"); - netdev_dbg(lif->netdev, "lif%d %s\n", lif->index, buf); - - err = ionic_adminq_post_wait(lif, &ctx); - if (err) - netdev_warn(lif->netdev, "set rx_mode 0x%04x failed: %d\n", - rx_mode, err); - else - lif->rx_mode = rx_mode; -} + mutex_lock(&lif->config_lock); -static void ionic_set_rx_mode(struct net_device *netdev, bool can_sleep) -{ - struct ionic_lif *lif = netdev_priv(netdev); - struct ionic_deferred_work *work; - unsigned int nfilters; - unsigned int rx_mode; + /* grab the flags once for local use */ + nd_flags = netdev->flags; rx_mode = IONIC_RX_MODE_F_UNICAST; - rx_mode |= (netdev->flags & IFF_MULTICAST) ? IONIC_RX_MODE_F_MULTICAST : 0; - rx_mode |= (netdev->flags & IFF_BROADCAST) ? IONIC_RX_MODE_F_BROADCAST : 0; - rx_mode |= (netdev->flags & IFF_PROMISC) ? IONIC_RX_MODE_F_PROMISC : 0; - rx_mode |= (netdev->flags & IFF_ALLMULTI) ? IONIC_RX_MODE_F_ALLMULTI : 0; + rx_mode |= (nd_flags & IFF_MULTICAST) ? IONIC_RX_MODE_F_MULTICAST : 0; + rx_mode |= (nd_flags & IFF_BROADCAST) ? IONIC_RX_MODE_F_BROADCAST : 0; + rx_mode |= (nd_flags & IFF_PROMISC) ? IONIC_RX_MODE_F_PROMISC : 0; + rx_mode |= (nd_flags & IFF_ALLMULTI) ? IONIC_RX_MODE_F_ALLMULTI : 0; /* sync unicast addresses * next check to see if we're in an overflow state @@ -1429,49 +1388,83 @@ static void ionic_set_rx_mode(struct net_device *netdev, bool can_sleep) * we remove our overflow flag and check the netdev flags * to see if we can disable NIC PROMISC */ - if (can_sleep) - __dev_uc_sync(netdev, ionic_addr_add, ionic_addr_del); - else - __dev_uc_sync(netdev, ionic_ndo_addr_add, ionic_ndo_addr_del); + __dev_uc_sync(netdev, ionic_addr_add, ionic_addr_del); nfilters = le32_to_cpu(lif->identity->eth.max_ucast_filters); if (netdev_uc_count(netdev) + 1 > nfilters) { rx_mode |= IONIC_RX_MODE_F_PROMISC; lif->uc_overflow = true; } else if (lif->uc_overflow) { lif->uc_overflow = false; - if (!(netdev->flags & IFF_PROMISC)) + if (!(nd_flags & IFF_PROMISC)) rx_mode &= ~IONIC_RX_MODE_F_PROMISC; } /* same for multicast */ - if (can_sleep) - __dev_mc_sync(netdev, ionic_addr_add, ionic_addr_del); - else - __dev_mc_sync(netdev, ionic_ndo_addr_add, ionic_ndo_addr_del); + __dev_mc_sync(netdev, ionic_addr_add, ionic_addr_del); nfilters = le32_to_cpu(lif->identity->eth.max_mcast_filters); if (netdev_mc_count(netdev) > nfilters) { rx_mode |= IONIC_RX_MODE_F_ALLMULTI; lif->mc_overflow = true; } else if (lif->mc_overflow) { lif->mc_overflow = false; - if (!(netdev->flags & IFF_ALLMULTI)) + if (!(nd_flags & IFF_ALLMULTI)) rx_mode &= ~IONIC_RX_MODE_F_ALLMULTI; } + i = scnprintf(buf, sizeof(buf), "rx_mode 0x%04x -> 0x%04x:", + lif->rx_mode, rx_mode); + if (rx_mode & IONIC_RX_MODE_F_UNICAST) + i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_UNICAST"); + if (rx_mode & IONIC_RX_MODE_F_MULTICAST) + i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_MULTICAST"); + if (rx_mode & IONIC_RX_MODE_F_BROADCAST) + i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_BROADCAST"); + if (rx_mode & IONIC_RX_MODE_F_PROMISC) + i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_PROMISC"); + if (rx_mode & IONIC_RX_MODE_F_ALLMULTI) + i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_ALLMULTI"); + if (rx_mode & IONIC_RX_MODE_F_RDMA_SNIFFER) + i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_RDMA_SNIFFER"); + netdev_dbg(netdev, "lif%d %s\n", lif->index, buf); + if (lif->rx_mode != rx_mode) { - if (!can_sleep) { - work = kzalloc(sizeof(*work), GFP_ATOMIC); - if (!work) { - netdev_err(lif->netdev, "rxmode change dropped\n"); - return; - } - work->type = IONIC_DW_TYPE_RX_MODE; - work->rx_mode = rx_mode; - netdev_dbg(lif->netdev, "deferred: rx_mode\n"); - ionic_lif_deferred_enqueue(&lif->deferred, work); - } else { - ionic_lif_rx_mode(lif, rx_mode); + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.rx_mode_set = { + .opcode = IONIC_CMD_RX_MODE_SET, + .lif_index = cpu_to_le16(lif->index), + }, + }; + int err; + + ctx.cmd.rx_mode_set.rx_mode = cpu_to_le16(rx_mode); + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + netdev_warn(netdev, "set rx_mode 0x%04x failed: %d\n", + rx_mode, err); + else + lif->rx_mode = rx_mode; + } + + mutex_unlock(&lif->config_lock); +} + +static void ionic_set_rx_mode(struct net_device *netdev, bool can_sleep) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_deferred_work *work; + + if (!can_sleep) { + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) { + netdev_err(lif->netdev, "rxmode change dropped\n"); + return; } + work->type = IONIC_DW_TYPE_RX_MODE; + netdev_dbg(lif->netdev, "deferred: rx_mode\n"); + ionic_lif_deferred_enqueue(&lif->deferred, work); + } else { + ionic_lif_rx_mode(lif); } } @@ -3058,6 +3051,7 @@ void ionic_lif_deinit(struct ionic_lif *lif) ionic_lif_qcq_deinit(lif, lif->notifyqcq); ionic_lif_qcq_deinit(lif, lif->adminqcq); + mutex_destroy(&lif->config_lock); mutex_destroy(&lif->queue_lock); ionic_lif_reset(lif); } @@ -3185,7 +3179,7 @@ static int ionic_station_set(struct ionic_lif *lif) */ if (!ether_addr_equal(ctx.comp.lif_getattr.mac, netdev->dev_addr)) - ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR, CAN_SLEEP); + ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR); } else { /* Update the netdev mac with the device's mac */ memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len); @@ -3202,7 +3196,7 @@ static int ionic_station_set(struct ionic_lif *lif) netdev_dbg(lif->netdev, "adding station MAC addr %pM\n", netdev->dev_addr); - ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR, CAN_SLEEP); + ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR); return 0; } @@ -3225,6 +3219,7 @@ int ionic_lif_init(struct ionic_lif *lif) lif->hw_index = le16_to_cpu(comp.hw_index); mutex_init(&lif->queue_lock); + mutex_init(&lif->config_lock); /* now that we have the hw_index we can figure out our doorbell page */ lif->dbid_count = le32_to_cpu(lif->ionic->ident.dev.ndbpgs_per_lif); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index 346506f01715..69ab59fedb6c 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -108,7 +108,6 @@ struct ionic_deferred_work { struct list_head list; enum ionic_deferred_work_type type; union { - unsigned int rx_mode; u8 addr[ETH_ALEN]; u8 fw_status; }; @@ -179,6 +178,7 @@ struct ionic_lif { unsigned int index; unsigned int hw_index; struct mutex queue_lock; /* lock for queue structures */ + struct mutex config_lock; /* lock for config actions */ spinlock_t adminq_lock; /* lock for AdminQ operations */ struct ionic_qcq *adminqcq; struct ionic_qcq *notifyqcq; @@ -199,7 +199,7 @@ struct ionic_lif { unsigned int nrxq_descs; u32 rx_copybreak; u64 rxq_features; - unsigned int rx_mode; + u16 rx_mode; u64 hw_features; bool registered; bool mc_overflow; @@ -302,7 +302,7 @@ int ionic_lif_identify(struct ionic *ionic, u8 lif_type, int ionic_lif_size(struct ionic *ionic); #if IS_ENABLED(CONFIG_PTP_1588_CLOCK) -int ionic_lif_hwstamp_replay(struct ionic_lif *lif); +void ionic_lif_hwstamp_replay(struct ionic_lif *lif); int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr); int ionic_lif_hwstamp_get(struct ionic_lif *lif, struct ifreq *ifr); ktime_t ionic_lif_phc_ktime(struct ionic_lif *lif, u64 counter); @@ -311,10 +311,7 @@ void ionic_lif_unregister_phc(struct ionic_lif *lif); void ionic_lif_alloc_phc(struct ionic_lif *lif); void ionic_lif_free_phc(struct ionic_lif *lif); #else -static inline int ionic_lif_hwstamp_replay(struct ionic_lif *lif) -{ - return -EOPNOTSUPP; -} +static inline void ionic_lif_hwstamp_replay(struct ionic_lif *lif) {} static inline int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr) { diff --git a/drivers/net/ethernet/pensando/ionic/ionic_phc.c b/drivers/net/ethernet/pensando/ionic/ionic_phc.c index a87c87e86aef..6e2403c71608 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_phc.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_phc.c @@ -188,6 +188,9 @@ int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr) struct hwtstamp_config config; int err; + if (!lif->phc || !lif->phc->ptp) + return -EOPNOTSUPP; + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; @@ -203,15 +206,16 @@ int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr) return 0; } -int ionic_lif_hwstamp_replay(struct ionic_lif *lif) +void ionic_lif_hwstamp_replay(struct ionic_lif *lif) { int err; + if (!lif->phc || !lif->phc->ptp) + return; + err = ionic_lif_hwstamp_set_ts_config(lif, NULL); if (err) netdev_info(lif->netdev, "hwstamp replay failed: %d\n", err); - - return err; } int ionic_lif_hwstamp_get(struct ionic_lif *lif, struct ifreq *ifr) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 08934888575c..08870190e4d2 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -274,12 +274,11 @@ static void ionic_rx_clean(struct ionic_queue *q, } } - if (likely(netdev->features & NETIF_F_RXCSUM)) { - if (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_CALC) { - skb->ip_summed = CHECKSUM_COMPLETE; - skb->csum = (__force __wsum)le16_to_cpu(comp->csum); - stats->csum_complete++; - } + if (likely(netdev->features & NETIF_F_RXCSUM) && + (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_CALC)) { + skb->ip_summed = CHECKSUM_COMPLETE; + skb->csum = (__force __wsum)le16_to_cpu(comp->csum); + stats->csum_complete++; } else { stats->csum_none++; } @@ -451,11 +450,12 @@ void ionic_rx_empty(struct ionic_queue *q) q->tail_idx = 0; } -static void ionic_dim_update(struct ionic_qcq *qcq) +static void ionic_dim_update(struct ionic_qcq *qcq, int napi_mode) { struct dim_sample dim_sample; struct ionic_lif *lif; unsigned int qi; + u64 pkts, bytes; if (!qcq->intr.dim_coal_hw) return; @@ -463,14 +463,23 @@ static void ionic_dim_update(struct ionic_qcq *qcq) lif = qcq->q.lif; qi = qcq->cq.bound_q->index; - ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, - lif->rxqcqs[qi]->intr.index, - qcq->intr.dim_coal_hw); + switch (napi_mode) { + case IONIC_LIF_F_TX_DIM_INTR: + pkts = lif->txqstats[qi].pkts; + bytes = lif->txqstats[qi].bytes; + break; + case IONIC_LIF_F_RX_DIM_INTR: + pkts = lif->rxqstats[qi].pkts; + bytes = lif->rxqstats[qi].bytes; + break; + default: + pkts = lif->txqstats[qi].pkts + lif->rxqstats[qi].pkts; + bytes = lif->txqstats[qi].bytes + lif->rxqstats[qi].bytes; + break; + } dim_update_sample(qcq->cq.bound_intr->rearm_count, - lif->txqstats[qi].pkts, - lif->txqstats[qi].bytes, - &dim_sample); + pkts, bytes, &dim_sample); net_dim(&qcq->dim, dim_sample); } @@ -491,7 +500,7 @@ int ionic_tx_napi(struct napi_struct *napi, int budget) ionic_tx_service, NULL, NULL); if (work_done < budget && napi_complete_done(napi, work_done)) { - ionic_dim_update(qcq); + ionic_dim_update(qcq, IONIC_LIF_F_TX_DIM_INTR); flags |= IONIC_INTR_CRED_UNMASK; cq->bound_intr->rearm_count++; } @@ -530,7 +539,7 @@ int ionic_rx_napi(struct napi_struct *napi, int budget) ionic_rx_fill(cq->bound_q); if (work_done < budget && napi_complete_done(napi, work_done)) { - ionic_dim_update(qcq); + ionic_dim_update(qcq, IONIC_LIF_F_RX_DIM_INTR); flags |= IONIC_INTR_CRED_UNMASK; cq->bound_intr->rearm_count++; } @@ -576,7 +585,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) ionic_rx_fill(rxcq->bound_q); if (rx_work_done < budget && napi_complete_done(napi, rx_work_done)) { - ionic_dim_update(qcq); + ionic_dim_update(qcq, 0); flags |= IONIC_INTR_CRED_UNMASK; rxcq->bound_intr->rearm_count++; } diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index c59b72c90293..a2e4dfb5cb44 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -831,7 +831,7 @@ int qede_configure_vlan_filters(struct qede_dev *edev) int qede_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct qede_dev *edev = netdev_priv(dev); - struct qede_vlan *vlan = NULL; + struct qede_vlan *vlan; int rc = 0; DP_VERBOSE(edev, NETIF_MSG_IFDOWN, "Removing vlan 0x%04x\n", vid); @@ -842,7 +842,7 @@ int qede_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) if (vlan->vid == vid) break; - if (!vlan || (vlan->vid != vid)) { + if (list_entry_is_head(vlan, &edev->vlan_list, list)) { DP_VERBOSE(edev, (NETIF_MSG_IFUP | NETIF_MSG_IFDOWN), "Vlan isn't configured\n"); goto out; diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 2376b2729633..c00ad57575ea 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -154,7 +154,7 @@ static int ql_wait_for_drvr_lock(struct ql3_adapter *qdev) "driver lock acquired\n"); return 1; } - ssleep(1); + mdelay(1000); } while (++i < 10); netdev_err(qdev->ndev, "Timed out waiting for driver lock...\n"); @@ -3274,7 +3274,7 @@ static int ql_adapter_reset(struct ql3_adapter *qdev) if ((value & ISP_CONTROL_SR) == 0) break; - ssleep(1); + mdelay(1000); } while ((--max_wait_time)); /* @@ -3310,7 +3310,7 @@ static int ql_adapter_reset(struct ql3_adapter *qdev) ispControlStatus); if ((value & ISP_CONTROL_FSR) == 0) break; - ssleep(1); + mdelay(1000); } while ((--max_wait_time)); } if (max_wait_time == 0) diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index ca9c00b7f588..cff87de9178a 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -443,7 +443,7 @@ static int sis900_probe(struct pci_dev *pci_dev, #endif /* setup various bits in PCI command register */ - ret = pci_enable_device(pci_dev); + ret = pcim_enable_device(pci_dev); if(ret) return ret; i = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(32)); @@ -469,7 +469,7 @@ static int sis900_probe(struct pci_dev *pci_dev, ioaddr = pci_iomap(pci_dev, 0, 0); if (!ioaddr) { ret = -ENOMEM; - goto err_out_cleardev; + goto err_out; } sis_priv = netdev_priv(net_dev); @@ -581,8 +581,6 @@ err_unmap_tx: sis_priv->tx_ring_dma); err_out_unmap: pci_iounmap(pci_dev, ioaddr); -err_out_cleardev: - pci_release_regions(pci_dev); err_out: free_netdev(net_dev); return ret; @@ -2499,7 +2497,6 @@ static void sis900_remove(struct pci_dev *pci_dev) sis_priv->tx_ring_dma); pci_iounmap(pci_dev, sis_priv->ioaddr); free_netdev(net_dev); - pci_release_regions(pci_dev); } static int __maybe_unused sis900_suspend(struct device *dev) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 67ba083eb90c..b21745368983 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -1249,6 +1249,7 @@ const struct stmmac_ops dwmac410_ops = { .config_l3_filter = dwmac4_config_l3_filter, .config_l4_filter = dwmac4_config_l4_filter, .est_configure = dwmac5_est_configure, + .est_irq_status = dwmac5_est_irq_status, .fpe_configure = dwmac5_fpe_configure, .fpe_send_mpacket = dwmac5_fpe_send_mpacket, .fpe_irq_status = dwmac5_fpe_irq_status, @@ -1300,6 +1301,7 @@ const struct stmmac_ops dwmac510_ops = { .config_l3_filter = dwmac4_config_l3_filter, .config_l4_filter = dwmac4_config_l4_filter, .est_configure = dwmac5_est_configure, + .est_irq_status = dwmac5_est_irq_status, .fpe_configure = dwmac5_fpe_configure, .fpe_send_mpacket = dwmac5_fpe_send_mpacket, .fpe_irq_status = dwmac5_fpe_irq_status, diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 74e748662ec0..860644d182ab 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -8191,8 +8191,9 @@ static int niu_pci_vpd_fetch(struct niu *np, u32 start) err = niu_pci_vpd_scan_props(np, here, end); if (err < 0) return err; + /* ret == 1 is not an error */ if (err == 1) - return -EINVAL; + return 0; } return 0; } diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 7bf3011b8e77..83aea5c5cd03 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -288,7 +288,7 @@ static void bcm54xx_adjust_rxrefclk(struct phy_device *phydev) if (phydev->dev_flags & PHY_BRCM_DIS_TXCRXC_NOENRGY) { if (BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54210E || BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54810 || - BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54210E) + BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54811) val |= BCM54XX_SHD_SCR3_RXCTXC_DIS; else val |= BCM54XX_SHD_SCR3_TRDDAPD; diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c index 1df959532c7d..514f2c1124b6 100644 --- a/drivers/net/wireless/virt_wifi.c +++ b/drivers/net/wireless/virt_wifi.c @@ -136,6 +136,29 @@ static struct ieee80211_supported_band band_5ghz = { /* Assigned at module init. Guaranteed locally-administered and unicast. */ static u8 fake_router_bssid[ETH_ALEN] __ro_after_init = {}; +static void virt_wifi_inform_bss(struct wiphy *wiphy) +{ + u64 tsf = div_u64(ktime_get_boottime_ns(), 1000); + struct cfg80211_bss *informed_bss; + static const struct { + u8 tag; + u8 len; + u8 ssid[8]; + } __packed ssid = { + .tag = WLAN_EID_SSID, + .len = 8, + .ssid = "VirtWifi", + }; + + informed_bss = cfg80211_inform_bss(wiphy, &channel_5ghz, + CFG80211_BSS_FTYPE_PRESP, + fake_router_bssid, tsf, + WLAN_CAPABILITY_ESS, 0, + (void *)&ssid, sizeof(ssid), + DBM_TO_MBM(-50), GFP_KERNEL); + cfg80211_put_bss(wiphy, informed_bss); +} + /* Called with the rtnl lock held. */ static int virt_wifi_scan(struct wiphy *wiphy, struct cfg80211_scan_request *request) @@ -156,28 +179,13 @@ static int virt_wifi_scan(struct wiphy *wiphy, /* Acquires and releases the rdev BSS lock. */ static void virt_wifi_scan_result(struct work_struct *work) { - struct { - u8 tag; - u8 len; - u8 ssid[8]; - } __packed ssid = { - .tag = WLAN_EID_SSID, .len = 8, .ssid = "VirtWifi", - }; - struct cfg80211_bss *informed_bss; struct virt_wifi_wiphy_priv *priv = container_of(work, struct virt_wifi_wiphy_priv, scan_result.work); struct wiphy *wiphy = priv_to_wiphy(priv); struct cfg80211_scan_info scan_info = { .aborted = false }; - u64 tsf = div_u64(ktime_get_boottime_ns(), 1000); - informed_bss = cfg80211_inform_bss(wiphy, &channel_5ghz, - CFG80211_BSS_FTYPE_PRESP, - fake_router_bssid, tsf, - WLAN_CAPABILITY_ESS, 0, - (void *)&ssid, sizeof(ssid), - DBM_TO_MBM(-50), GFP_KERNEL); - cfg80211_put_bss(wiphy, informed_bss); + virt_wifi_inform_bss(wiphy); /* Schedules work which acquires and releases the rtnl lock. */ cfg80211_scan_done(priv->scan_request, &scan_info); @@ -225,10 +233,12 @@ static int virt_wifi_connect(struct wiphy *wiphy, struct net_device *netdev, if (!could_schedule) return -EBUSY; - if (sme->bssid) + if (sme->bssid) { ether_addr_copy(priv->connect_requested_bss, sme->bssid); - else + } else { + virt_wifi_inform_bss(wiphy); eth_zero_addr(priv->connect_requested_bss); + } wiphy_debug(wiphy, "connect\n"); @@ -241,11 +251,13 @@ static void virt_wifi_connect_complete(struct work_struct *work) struct virt_wifi_netdev_priv *priv = container_of(work, struct virt_wifi_netdev_priv, connect.work); u8 *requested_bss = priv->connect_requested_bss; - bool has_addr = !is_zero_ether_addr(requested_bss); bool right_addr = ether_addr_equal(requested_bss, fake_router_bssid); u16 status = WLAN_STATUS_SUCCESS; - if (!priv->is_up || (has_addr && !right_addr)) + if (is_zero_ether_addr(requested_bss)) + requested_bss = NULL; + + if (!priv->is_up || (requested_bss && !right_addr)) status = WLAN_STATUS_UNSPECIFIED_FAILURE; else priv->is_connected = true; diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index 3e16c318e705..674a81d79db3 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -984,6 +984,8 @@ static void wwan_create_default_link(struct wwan_device *wwandev, goto unlock; } + rtnl_configure_link(dev, NULL); /* Link initialized, notify new link */ + unlock: rtnl_unlock(); diff --git a/drivers/nfc/nfcsim.c b/drivers/nfc/nfcsim.c index a9864fcdfba6..dd27c85190d3 100644 --- a/drivers/nfc/nfcsim.c +++ b/drivers/nfc/nfcsim.c @@ -192,8 +192,7 @@ static void nfcsim_recv_wq(struct work_struct *work) if (!IS_ERR(skb)) dev_kfree_skb(skb); - - skb = ERR_PTR(-ENODEV); + return; } dev->cb(dev->nfc_digital_dev, dev->arg, skb); diff --git a/drivers/nfc/s3fwrn5/firmware.c b/drivers/nfc/s3fwrn5/firmware.c index eb5d7a5beac7..e3e72b8a29e3 100644 --- a/drivers/nfc/s3fwrn5/firmware.c +++ b/drivers/nfc/s3fwrn5/firmware.c @@ -423,7 +423,7 @@ int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info) if (IS_ERR(tfm)) { ret = PTR_ERR(tfm); dev_err(&fw_info->ndev->nfc_dev->dev, - "Cannot allocate shash (code=%d)\n", ret); + "Cannot allocate shash (code=%pe)\n", tfm); goto out; } diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index b9da58ee9b1e..3481479a2942 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -46,34 +46,79 @@ #define AMD_PMC_RESULT_CMD_UNKNOWN 0xFE #define AMD_PMC_RESULT_FAILED 0xFF +/* FCH SSC Registers */ +#define FCH_S0I3_ENTRY_TIME_L_OFFSET 0x30 +#define FCH_S0I3_ENTRY_TIME_H_OFFSET 0x34 +#define FCH_S0I3_EXIT_TIME_L_OFFSET 0x38 +#define FCH_S0I3_EXIT_TIME_H_OFFSET 0x3C +#define FCH_SSC_MAPPING_SIZE 0x800 +#define FCH_BASE_PHY_ADDR_LOW 0xFED81100 +#define FCH_BASE_PHY_ADDR_HIGH 0x00000000 + +/* SMU Message Definations */ +#define SMU_MSG_GETSMUVERSION 0x02 +#define SMU_MSG_LOG_GETDRAM_ADDR_HI 0x04 +#define SMU_MSG_LOG_GETDRAM_ADDR_LO 0x05 +#define SMU_MSG_LOG_START 0x06 +#define SMU_MSG_LOG_RESET 0x07 +#define SMU_MSG_LOG_DUMP_DATA 0x08 +#define SMU_MSG_GET_SUP_CONSTRAINTS 0x09 /* List of supported CPU ids */ #define AMD_CPU_ID_RV 0x15D0 #define AMD_CPU_ID_RN 0x1630 #define AMD_CPU_ID_PCO AMD_CPU_ID_RV #define AMD_CPU_ID_CZN AMD_CPU_ID_RN +#define AMD_CPU_ID_YC 0x14B5 -#define AMD_SMU_FW_VERSION 0x0 #define PMC_MSG_DELAY_MIN_US 100 #define RESPONSE_REGISTER_LOOP_MAX 200 +#define SOC_SUBSYSTEM_IP_MAX 12 +#define DELAY_MIN_US 2000 +#define DELAY_MAX_US 3000 enum amd_pmc_def { MSG_TEST = 0x01, MSG_OS_HINT_PCO, MSG_OS_HINT_RN, }; +struct amd_pmc_bit_map { + const char *name; + u32 bit_mask; +}; + +static const struct amd_pmc_bit_map soc15_ip_blk[] = { + {"DISPLAY", BIT(0)}, + {"CPU", BIT(1)}, + {"GFX", BIT(2)}, + {"VDD", BIT(3)}, + {"ACP", BIT(4)}, + {"VCN", BIT(5)}, + {"ISP", BIT(6)}, + {"NBIO", BIT(7)}, + {"DF", BIT(8)}, + {"USB0", BIT(9)}, + {"USB1", BIT(10)}, + {"LAPIC", BIT(11)}, + {} +}; + struct amd_pmc_dev { void __iomem *regbase; - void __iomem *smu_base; + void __iomem *smu_virt_addr; + void __iomem *fch_virt_addr; u32 base_addr; u32 cpu_id; + u32 active_ips; struct device *dev; + struct mutex lock; /* generic mutex lock */ #if IS_ENABLED(CONFIG_DEBUG_FS) struct dentry *dbgfs_dir; #endif /* CONFIG_DEBUG_FS */ }; static struct amd_pmc_dev pmc; +static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set, u32 *data, u8 msg, bool ret); static inline u32 amd_pmc_reg_read(struct amd_pmc_dev *dev, int reg_offset) { @@ -85,18 +130,77 @@ static inline void amd_pmc_reg_write(struct amd_pmc_dev *dev, int reg_offset, u3 iowrite32(val, dev->regbase + reg_offset); } +struct smu_metrics { + u32 table_version; + u32 hint_count; + u32 s0i3_cyclecount; + u32 timein_s0i2; + u64 timeentering_s0i3_lastcapture; + u64 timeentering_s0i3_totaltime; + u64 timeto_resume_to_os_lastcapture; + u64 timeto_resume_to_os_totaltime; + u64 timein_s0i3_lastcapture; + u64 timein_s0i3_totaltime; + u64 timein_swdrips_lastcapture; + u64 timein_swdrips_totaltime; + u64 timecondition_notmet_lastcapture[SOC_SUBSYSTEM_IP_MAX]; + u64 timecondition_notmet_totaltime[SOC_SUBSYSTEM_IP_MAX]; +} __packed; + #ifdef CONFIG_DEBUG_FS static int smu_fw_info_show(struct seq_file *s, void *unused) { struct amd_pmc_dev *dev = s->private; - u32 value; + struct smu_metrics table; + int idx; + + if (dev->cpu_id == AMD_CPU_ID_PCO) + return -EINVAL; + + memcpy_fromio(&table, dev->smu_virt_addr, sizeof(struct smu_metrics)); + + seq_puts(s, "\n=== SMU Statistics ===\n"); + seq_printf(s, "Table Version: %d\n", table.table_version); + seq_printf(s, "Hint Count: %d\n", table.hint_count); + seq_printf(s, "S0i3 Cycle Count: %d\n", table.s0i3_cyclecount); + seq_printf(s, "Time (in us) to S0i3: %lld\n", table.timeentering_s0i3_lastcapture); + seq_printf(s, "Time (in us) in S0i3: %lld\n", table.timein_s0i3_lastcapture); + + seq_puts(s, "\n=== Active time (in us) ===\n"); + for (idx = 0 ; idx < SOC_SUBSYSTEM_IP_MAX ; idx++) { + if (soc15_ip_blk[idx].bit_mask & dev->active_ips) + seq_printf(s, "%-8s : %lld\n", soc15_ip_blk[idx].name, + table.timecondition_notmet_lastcapture[idx]); + } - value = ioread32(dev->smu_base + AMD_SMU_FW_VERSION); - seq_printf(s, "SMU FW Info: %x\n", value); return 0; } DEFINE_SHOW_ATTRIBUTE(smu_fw_info); +static int s0ix_stats_show(struct seq_file *s, void *unused) +{ + struct amd_pmc_dev *dev = s->private; + u64 entry_time, exit_time, residency; + + entry_time = ioread32(dev->fch_virt_addr + FCH_S0I3_ENTRY_TIME_H_OFFSET); + entry_time = entry_time << 32 | ioread32(dev->fch_virt_addr + FCH_S0I3_ENTRY_TIME_L_OFFSET); + + exit_time = ioread32(dev->fch_virt_addr + FCH_S0I3_EXIT_TIME_H_OFFSET); + exit_time = exit_time << 32 | ioread32(dev->fch_virt_addr + FCH_S0I3_EXIT_TIME_L_OFFSET); + + /* It's in 48MHz. We need to convert it */ + residency = exit_time - entry_time; + do_div(residency, 48); + + seq_puts(s, "=== S0ix statistics ===\n"); + seq_printf(s, "S0ix Entry Time: %lld\n", entry_time); + seq_printf(s, "S0ix Exit Time: %lld\n", exit_time); + seq_printf(s, "Residency Time: %lld\n", residency); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(s0ix_stats); + static void amd_pmc_dbgfs_unregister(struct amd_pmc_dev *dev) { debugfs_remove_recursive(dev->dbgfs_dir); @@ -107,6 +211,8 @@ static void amd_pmc_dbgfs_register(struct amd_pmc_dev *dev) dev->dbgfs_dir = debugfs_create_dir("amd_pmc", NULL); debugfs_create_file("smu_fw_info", 0644, dev->dbgfs_dir, dev, &smu_fw_info_fops); + debugfs_create_file("s0ix_stats", 0644, dev->dbgfs_dir, dev, + &s0ix_stats_fops); } #else static inline void amd_pmc_dbgfs_register(struct amd_pmc_dev *dev) @@ -118,6 +224,32 @@ static inline void amd_pmc_dbgfs_unregister(struct amd_pmc_dev *dev) } #endif /* CONFIG_DEBUG_FS */ +static int amd_pmc_setup_smu_logging(struct amd_pmc_dev *dev) +{ + u32 phys_addr_low, phys_addr_hi; + u64 smu_phys_addr; + + if (dev->cpu_id == AMD_CPU_ID_PCO) + return -EINVAL; + + /* Get Active devices list from SMU */ + amd_pmc_send_cmd(dev, 0, &dev->active_ips, SMU_MSG_GET_SUP_CONSTRAINTS, 1); + + /* Get dram address */ + amd_pmc_send_cmd(dev, 0, &phys_addr_low, SMU_MSG_LOG_GETDRAM_ADDR_LO, 1); + amd_pmc_send_cmd(dev, 0, &phys_addr_hi, SMU_MSG_LOG_GETDRAM_ADDR_HI, 1); + smu_phys_addr = ((u64)phys_addr_hi << 32 | phys_addr_low); + + dev->smu_virt_addr = devm_ioremap(dev->dev, smu_phys_addr, sizeof(struct smu_metrics)); + if (!dev->smu_virt_addr) + return -ENOMEM; + + /* Start the logging */ + amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_START, 0); + + return 0; +} + static void amd_pmc_dump_registers(struct amd_pmc_dev *dev) { u32 value; @@ -132,19 +264,19 @@ static void amd_pmc_dump_registers(struct amd_pmc_dev *dev) dev_dbg(dev->dev, "AMD_PMC_REGISTER_MESSAGE:%x\n", value); } -static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set) +static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set, u32 *data, u8 msg, bool ret) { int rc; - u8 msg; u32 val; + mutex_lock(&dev->lock); /* Wait until we get a valid response */ rc = readx_poll_timeout(ioread32, dev->regbase + AMD_PMC_REGISTER_RESPONSE, - val, val > 0, PMC_MSG_DELAY_MIN_US, + val, val != 0, PMC_MSG_DELAY_MIN_US, PMC_MSG_DELAY_MIN_US * RESPONSE_REGISTER_LOOP_MAX); if (rc) { dev_err(dev->dev, "failed to talk to SMU\n"); - return rc; + goto out_unlock; } /* Write zero to response register */ @@ -154,34 +286,91 @@ static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set) amd_pmc_reg_write(dev, AMD_PMC_REGISTER_ARGUMENT, set); /* Write message ID to message ID register */ - msg = (dev->cpu_id == AMD_CPU_ID_RN) ? MSG_OS_HINT_RN : MSG_OS_HINT_PCO; amd_pmc_reg_write(dev, AMD_PMC_REGISTER_MESSAGE, msg); - return 0; + + /* Wait until we get a valid response */ + rc = readx_poll_timeout(ioread32, dev->regbase + AMD_PMC_REGISTER_RESPONSE, + val, val != 0, PMC_MSG_DELAY_MIN_US, + PMC_MSG_DELAY_MIN_US * RESPONSE_REGISTER_LOOP_MAX); + if (rc) { + dev_err(dev->dev, "SMU response timed out\n"); + goto out_unlock; + } + + switch (val) { + case AMD_PMC_RESULT_OK: + if (ret) { + /* PMFW may take longer time to return back the data */ + usleep_range(DELAY_MIN_US, 10 * DELAY_MAX_US); + *data = amd_pmc_reg_read(dev, AMD_PMC_REGISTER_ARGUMENT); + } + break; + case AMD_PMC_RESULT_CMD_REJECT_BUSY: + dev_err(dev->dev, "SMU not ready. err: 0x%x\n", val); + rc = -EBUSY; + goto out_unlock; + case AMD_PMC_RESULT_CMD_UNKNOWN: + dev_err(dev->dev, "SMU cmd unknown. err: 0x%x\n", val); + rc = -EINVAL; + goto out_unlock; + case AMD_PMC_RESULT_CMD_REJECT_PREREQ: + case AMD_PMC_RESULT_FAILED: + default: + dev_err(dev->dev, "SMU cmd failed. err: 0x%x\n", val); + rc = -EIO; + goto out_unlock; + } + +out_unlock: + mutex_unlock(&dev->lock); + amd_pmc_dump_registers(dev); + return rc; +} + +static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev) +{ + switch (dev->cpu_id) { + case AMD_CPU_ID_PCO: + return MSG_OS_HINT_PCO; + case AMD_CPU_ID_RN: + case AMD_CPU_ID_YC: + return MSG_OS_HINT_RN; + } + return -EINVAL; } static int __maybe_unused amd_pmc_suspend(struct device *dev) { struct amd_pmc_dev *pdev = dev_get_drvdata(dev); int rc; + u8 msg; + + /* Reset and Start SMU logging - to monitor the s0i3 stats */ + amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_RESET, 0); + amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_START, 0); - rc = amd_pmc_send_cmd(pdev, 1); + msg = amd_pmc_get_os_hint(pdev); + rc = amd_pmc_send_cmd(pdev, 1, NULL, msg, 0); if (rc) dev_err(pdev->dev, "suspend failed\n"); - amd_pmc_dump_registers(pdev); - return 0; + return rc; } static int __maybe_unused amd_pmc_resume(struct device *dev) { struct amd_pmc_dev *pdev = dev_get_drvdata(dev); int rc; + u8 msg; + + /* Let SMU know that we are looking for stats */ + amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_DUMP_DATA, 0); - rc = amd_pmc_send_cmd(pdev, 0); + msg = amd_pmc_get_os_hint(pdev); + rc = amd_pmc_send_cmd(pdev, 0, NULL, msg, 0); if (rc) dev_err(pdev->dev, "resume failed\n"); - amd_pmc_dump_registers(pdev); return 0; } @@ -190,6 +379,7 @@ static const struct dev_pm_ops amd_pmc_pm_ops = { }; static const struct pci_device_id pmc_pci_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_YC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_CZN) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_RN) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_PCO) }, @@ -201,9 +391,8 @@ static int amd_pmc_probe(struct platform_device *pdev) { struct amd_pmc_dev *dev = &pmc; struct pci_dev *rdev; - u32 base_addr_lo; - u32 base_addr_hi; - u64 base_addr; + u32 base_addr_lo, base_addr_hi; + u64 base_addr, fch_phys_addr; int err; u32 val; @@ -248,16 +437,25 @@ static int amd_pmc_probe(struct platform_device *pdev) pci_dev_put(rdev); base_addr = ((u64)base_addr_hi << 32 | base_addr_lo); - dev->smu_base = devm_ioremap(dev->dev, base_addr, AMD_PMC_MAPPING_SIZE); - if (!dev->smu_base) - return -ENOMEM; - dev->regbase = devm_ioremap(dev->dev, base_addr + AMD_PMC_BASE_ADDR_OFFSET, AMD_PMC_MAPPING_SIZE); if (!dev->regbase) return -ENOMEM; - amd_pmc_dump_registers(dev); + mutex_init(&dev->lock); + + /* Use FCH registers to get the S0ix stats */ + base_addr_lo = FCH_BASE_PHY_ADDR_LOW; + base_addr_hi = FCH_BASE_PHY_ADDR_HIGH; + fch_phys_addr = ((u64)base_addr_hi << 32 | base_addr_lo); + dev->fch_virt_addr = devm_ioremap(dev->dev, fch_phys_addr, FCH_SSC_MAPPING_SIZE); + if (!dev->fch_virt_addr) + return -ENOMEM; + + /* Use SMU to get the s0i3 debug stats */ + err = amd_pmc_setup_smu_logging(dev); + if (err) + dev_err(dev->dev, "SMU debugging info not supported on this platform\n"); platform_set_drvdata(pdev, dev); amd_pmc_dbgfs_register(dev); @@ -269,11 +467,14 @@ static int amd_pmc_remove(struct platform_device *pdev) struct amd_pmc_dev *dev = platform_get_drvdata(pdev); amd_pmc_dbgfs_unregister(dev); + mutex_destroy(&dev->lock); return 0; } static const struct acpi_device_id amd_pmc_acpi_ids[] = { {"AMDI0005", 0}, + {"AMDI0006", 0}, + {"AMDI0007", 0}, {"AMD0004", 0}, { } }; diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c index 5529d7b0abea..fbb224a82e34 100644 --- a/drivers/platform/x86/gigabyte-wmi.c +++ b/drivers/platform/x86/gigabyte-wmi.c @@ -141,6 +141,7 @@ static u8 gigabyte_wmi_detect_sensor_usability(struct wmi_device *wdev) static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = { DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE V2"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 GAMING X V2"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M AORUS PRO-P"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M DS3H"), diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c index 078648a9201b..e5fbe017f8e1 100644 --- a/drivers/platform/x86/intel-hid.c +++ b/drivers/platform/x86/intel-hid.c @@ -25,6 +25,7 @@ static const struct acpi_device_id intel_hid_ids[] = { {"INT33D5", 0}, {"INTC1051", 0}, {"INTC1054", 0}, + {"INTC1070", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, intel_hid_ids); diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index 3671b5d20613..6cfed4427fb0 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -571,6 +571,11 @@ static ssize_t current_value_store(struct kobject *kobj, else ret = tlmi_save_bios_settings(""); + if (!ret && !tlmi_priv.pending_changes) { + tlmi_priv.pending_changes = true; + /* let userland know it may need to check reboot pending again */ + kobject_uevent(&tlmi_priv.class_dev->kobj, KOBJ_CHANGE); + } out: kfree(auth_str); kfree(set_str); @@ -647,6 +652,14 @@ static struct kobj_type tlmi_pwd_setting_ktype = { .sysfs_ops = &tlmi_kobj_sysfs_ops, }; +static ssize_t pending_reboot_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%d\n", tlmi_priv.pending_changes); +} + +static struct kobj_attribute pending_reboot = __ATTR_RO(pending_reboot); + /* ---- Initialisation --------------------------------------------------------- */ static void tlmi_release_attr(void) { @@ -659,6 +672,7 @@ static void tlmi_release_attr(void) kobject_put(&tlmi_priv.setting[i]->kobj); } } + sysfs_remove_file(&tlmi_priv.attribute_kset->kobj, &pending_reboot.attr); kset_unregister(tlmi_priv.attribute_kset); /* Authentication structures */ @@ -709,8 +723,8 @@ static int tlmi_sysfs_init(void) /* Build attribute */ tlmi_priv.setting[i]->kobj.kset = tlmi_priv.attribute_kset; - ret = kobject_init_and_add(&tlmi_priv.setting[i]->kobj, &tlmi_attr_setting_ktype, - NULL, "%s", tlmi_priv.setting[i]->display_name); + ret = kobject_add(&tlmi_priv.setting[i]->kobj, NULL, + "%s", tlmi_priv.setting[i]->display_name); if (ret) goto fail_create_attr; @@ -719,6 +733,10 @@ static int tlmi_sysfs_init(void) goto fail_create_attr; } + ret = sysfs_create_file(&tlmi_priv.attribute_kset->kobj, &pending_reboot.attr); + if (ret) + goto fail_create_attr; + /* Create authentication entries */ tlmi_priv.authentication_kset = kset_create_and_add("authentication", NULL, &tlmi_priv.class_dev->kobj); @@ -727,8 +745,7 @@ static int tlmi_sysfs_init(void) goto fail_create_attr; } tlmi_priv.pwd_admin->kobj.kset = tlmi_priv.authentication_kset; - ret = kobject_init_and_add(&tlmi_priv.pwd_admin->kobj, &tlmi_pwd_setting_ktype, - NULL, "%s", "Admin"); + ret = kobject_add(&tlmi_priv.pwd_admin->kobj, NULL, "%s", "Admin"); if (ret) goto fail_create_attr; @@ -737,8 +754,7 @@ static int tlmi_sysfs_init(void) goto fail_create_attr; tlmi_priv.pwd_power->kobj.kset = tlmi_priv.authentication_kset; - ret = kobject_init_and_add(&tlmi_priv.pwd_power->kobj, &tlmi_pwd_setting_ktype, - NULL, "%s", "System"); + ret = kobject_add(&tlmi_priv.pwd_power->kobj, NULL, "%s", "System"); if (ret) goto fail_create_attr; @@ -818,6 +834,7 @@ static int tlmi_analyze(void) pr_info("Error retrieving possible values for %d : %s\n", i, setting->display_name); } + kobject_init(&setting->kobj, &tlmi_attr_setting_ktype); tlmi_priv.setting[i] = setting; tlmi_priv.settings_count++; kfree(item); @@ -844,10 +861,12 @@ static int tlmi_analyze(void) if (pwdcfg.password_state & TLMI_PAP_PWD) tlmi_priv.pwd_admin->valid = true; + kobject_init(&tlmi_priv.pwd_admin->kobj, &tlmi_pwd_setting_ktype); + tlmi_priv.pwd_power = kzalloc(sizeof(struct tlmi_pwd_setting), GFP_KERNEL); if (!tlmi_priv.pwd_power) { ret = -ENOMEM; - goto fail_clear_attr; + goto fail_free_pwd_admin; } strscpy(tlmi_priv.pwd_power->kbdlang, "us", TLMI_LANG_MAXLEN); tlmi_priv.pwd_power->encoding = TLMI_ENCODING_ASCII; @@ -859,11 +878,19 @@ static int tlmi_analyze(void) if (pwdcfg.password_state & TLMI_POP_PWD) tlmi_priv.pwd_power->valid = true; + kobject_init(&tlmi_priv.pwd_power->kobj, &tlmi_pwd_setting_ktype); + return 0; +fail_free_pwd_admin: + kfree(tlmi_priv.pwd_admin); fail_clear_attr: - for (i = 0; i < TLMI_SETTINGS_COUNT; ++i) - kfree(tlmi_priv.setting[i]); + for (i = 0; i < TLMI_SETTINGS_COUNT; ++i) { + if (tlmi_priv.setting[i]) { + kfree(tlmi_priv.setting[i]->possible_values); + kfree(tlmi_priv.setting[i]); + } + } return ret; } diff --git a/drivers/platform/x86/think-lmi.h b/drivers/platform/x86/think-lmi.h index 6fa8da7af6c7..eb598846628a 100644 --- a/drivers/platform/x86/think-lmi.h +++ b/drivers/platform/x86/think-lmi.h @@ -60,6 +60,7 @@ struct think_lmi { bool can_get_bios_selections; bool can_set_bios_password; bool can_get_password_settings; + bool pending_changes; struct tlmi_attr_setting *setting[TLMI_SETTINGS_COUNT]; struct device *class_dev; diff --git a/drivers/platform/x86/wireless-hotkey.c b/drivers/platform/x86/wireless-hotkey.c index b010e4ca3383..11c60a273446 100644 --- a/drivers/platform/x86/wireless-hotkey.c +++ b/drivers/platform/x86/wireless-hotkey.c @@ -78,7 +78,7 @@ static int wl_add(struct acpi_device *device) err = wireless_input_setup(); if (err) - pr_err("Failed to setup hp wireless hotkeys\n"); + pr_err("Failed to setup wireless hotkeys\n"); return err; } diff --git a/drivers/scsi/arm/acornscsi.c b/drivers/scsi/arm/acornscsi.c index 84fc7a0c6ff4..4a84599ff491 100644 --- a/drivers/scsi/arm/acornscsi.c +++ b/drivers/scsi/arm/acornscsi.c @@ -2642,6 +2642,7 @@ int acornscsi_abort(struct scsi_cmnd *SCpnt) //#endif clear_bit(SCpnt->device->id * 8 + (u8)(SCpnt->device->lun & 0x7), host->busyluns); + fallthrough; /* * We found the command, and cleared it out. Either diff --git a/drivers/scsi/arm/fas216.c b/drivers/scsi/arm/fas216.c index 6baa9b36367d..9c4458a99025 100644 --- a/drivers/scsi/arm/fas216.c +++ b/drivers/scsi/arm/fas216.c @@ -1375,6 +1375,7 @@ static void fas216_busservice_intr(FAS216_Info *info, unsigned int stat, unsigne case IS_COMPLETE: break; } + break; default: break; diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 06fb7a93a1bd..4d5ae61580aa 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -168,21 +168,6 @@ config OSF4_COMPAT with v4 shared libraries freely available from Compaq. If you're going to use shared libraries from Tru64 version 5.0 or later, say N. -config BINFMT_EM86 - tristate "Kernel support for Linux/Intel ELF binaries" - depends on ALPHA - help - Say Y here if you want to be able to execute Linux/Intel ELF - binaries just like native Alpha binaries on your Alpha machine. For - this to work, you need to have the emulator /usr/bin/em86 in place. - - You can get the same functionality by saying N here and saying Y to - "Kernel support for MISC binaries". - - You may answer M to compile the emulation support as a module and - later load the module when you want to use a Linux/Intel binary. The - module will be called binfmt_em86. If unsure, say Y. - config BINFMT_MISC tristate "Kernel support for MISC binaries" help diff --git a/fs/Makefile b/fs/Makefile index 9c708e1fbe8f..f98f3e691c37 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -39,7 +39,6 @@ obj-$(CONFIG_FS_ENCRYPTION) += crypto/ obj-$(CONFIG_FS_VERITY) += verity/ obj-$(CONFIG_FILE_LOCKING) += locks.o obj-$(CONFIG_BINFMT_AOUT) += binfmt_aout.o -obj-$(CONFIG_BINFMT_EM86) += binfmt_em86.o obj-$(CONFIG_BINFMT_MISC) += binfmt_misc.o obj-$(CONFIG_BINFMT_SCRIPT) += binfmt_script.o obj-$(CONFIG_BINFMT_ELF) += binfmt_elf.o diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c deleted file mode 100644 index 06b9b9fddf70..000000000000 --- a/fs/binfmt_em86.c +++ /dev/null @@ -1,110 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * linux/fs/binfmt_em86.c - * - * Based on linux/fs/binfmt_script.c - * Copyright (C) 1996 Martin von Löwis - * original #!-checking implemented by tytso. - * - * em86 changes Copyright (C) 1997 Jim Paradis - */ - -#include <linux/module.h> -#include <linux/string.h> -#include <linux/stat.h> -#include <linux/binfmts.h> -#include <linux/elf.h> -#include <linux/init.h> -#include <linux/fs.h> -#include <linux/file.h> -#include <linux/errno.h> - - -#define EM86_INTERP "/usr/bin/em86" -#define EM86_I_NAME "em86" - -static int load_em86(struct linux_binprm *bprm) -{ - const char *i_name, *i_arg; - char *interp; - struct file * file; - int retval; - struct elfhdr elf_ex; - - /* Make sure this is a Linux/Intel ELF executable... */ - elf_ex = *((struct elfhdr *)bprm->buf); - - if (memcmp(elf_ex.e_ident, ELFMAG, SELFMAG) != 0) - return -ENOEXEC; - - /* First of all, some simple consistency checks */ - if ((elf_ex.e_type != ET_EXEC && elf_ex.e_type != ET_DYN) || - (!((elf_ex.e_machine == EM_386) || (elf_ex.e_machine == EM_486))) || - !bprm->file->f_op->mmap) { - return -ENOEXEC; - } - - /* Need to be able to load the file after exec */ - if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) - return -ENOENT; - - /* Unlike in the script case, we don't have to do any hairy - * parsing to find our interpreter... it's hardcoded! - */ - interp = EM86_INTERP; - i_name = EM86_I_NAME; - i_arg = NULL; /* We reserve the right to add an arg later */ - - /* - * Splice in (1) the interpreter's name for argv[0] - * (2) (optional) argument to interpreter - * (3) filename of emulated file (replace argv[0]) - * - * This is done in reverse order, because of how the - * user environment and arguments are stored. - */ - remove_arg_zero(bprm); - retval = copy_string_kernel(bprm->filename, bprm); - if (retval < 0) return retval; - bprm->argc++; - if (i_arg) { - retval = copy_string_kernel(i_arg, bprm); - if (retval < 0) return retval; - bprm->argc++; - } - retval = copy_string_kernel(i_name, bprm); - if (retval < 0) return retval; - bprm->argc++; - - /* - * OK, now restart the process with the interpreter's inode. - * Note that we use open_exec() as the name is now in kernel - * space, and we don't need to copy it. - */ - file = open_exec(interp); - if (IS_ERR(file)) - return PTR_ERR(file); - - bprm->interpreter = file; - return 0; -} - -static struct linux_binfmt em86_format = { - .module = THIS_MODULE, - .load_binary = load_em86, -}; - -static int __init init_em86_binfmt(void) -{ - register_binfmt(&em86_format); - return 0; -} - -static void __exit exit_em86_binfmt(void) -{ - unregister_binfmt(&em86_format); -} - -core_initcall(init_em86_binfmt); -module_exit(exit_em86_binfmt); -MODULE_LICENSE("GPL"); diff --git a/fs/block_dev.c b/fs/block_dev.c index 0c424a0cadaa..9ef4f1fc2cb0 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -812,6 +812,8 @@ static void bdev_free_inode(struct inode *inode) free_percpu(bdev->bd_stats); kfree(bdev->bd_meta_info); + if (!bdev_is_partition(bdev)) + kfree(bdev->bd_disk); kmem_cache_free(bdev_cachep, BDEV_I(inode)); } diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 9a023ae0f98b..30d82cdf128c 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -352,7 +352,7 @@ static void end_compressed_bio_write(struct bio *bio) btrfs_record_physical_zoned(inode, cb->start, bio); btrfs_writepage_endio_finish_ordered(BTRFS_I(inode), NULL, cb->start, cb->start + cb->len - 1, - bio->bi_status == BLK_STS_OK); + !cb->errors); end_compressed_writeback(inode, cb); /* note, our inode could be gone now */ diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b117dd3b8172..a59ab7b9aea0 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -209,7 +209,7 @@ void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, static void csum_tree_block(struct extent_buffer *buf, u8 *result) { struct btrfs_fs_info *fs_info = buf->fs_info; - const int num_pages = fs_info->nodesize >> PAGE_SHIFT; + const int num_pages = num_extent_pages(buf); const int first_page_part = min_t(u32, PAGE_SIZE, fs_info->nodesize); SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); char *kaddr; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 9fd0348be7f5..e6430ac9bbe8 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -6503,8 +6503,8 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, * if this inode hasn't been logged and directory we're renaming it * from hasn't been logged, we don't need to log it */ - if (inode->logged_trans < trans->transid && - (!old_dir || old_dir->logged_trans < trans->transid)) + if (!inode_logged(trans, inode) && + (!old_dir || !inode_logged(trans, old_dir))) return; /* diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 1e4d43ffe38b..70f94b75f25a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1078,6 +1078,7 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { list_del_init(&device->dev_alloc_list); clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); + fs_devices->rw_devices--; } list_del_init(&device->dev_list); fs_devices->num_devices--; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index cd108607a070..0a72840a88f1 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4619,7 +4619,7 @@ read_complete: static int cifs_readpage(struct file *file, struct page *page) { - loff_t offset = (loff_t)page->index << PAGE_SHIFT; + loff_t offset = page_file_offset(page); int rc = -EACCES; unsigned int xid; diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 9a59d7ff9a11..eed59bc1d913 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -925,6 +925,13 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, ctx->cred_uid = uid; ctx->cruid_specified = true; break; + case Opt_backupuid: + uid = make_kuid(current_user_ns(), result.uint_32); + if (!uid_valid(uid)) + goto cifs_parse_mount_err; + ctx->backupuid = uid; + ctx->backupuid_specified = true; + break; case Opt_backupgid: gid = make_kgid(current_user_ns(), result.uint_32); if (!gid_valid(gid)) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 23d6f4d71649..2dfd0d8297eb 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3617,7 +3617,8 @@ static int smb3_simple_fallocate_write_range(unsigned int xid, char *buf) { struct cifs_io_parms io_parms = {0}; - int rc, nbytes; + int nbytes; + int rc = 0; struct kvec iov[2]; io_parms.netfid = cfile->fid.netfid; diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 14292dba3a12..2c2f179b6977 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -106,12 +106,11 @@ static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len) return err; } -static bool ext2_check_page(struct page *page, int quiet) +static bool ext2_check_page(struct page *page, int quiet, char *kaddr) { struct inode *dir = page->mapping->host; struct super_block *sb = dir->i_sb; unsigned chunk_size = ext2_chunk_size(dir); - char *kaddr = page_address(page); u32 max_inumber = le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count); unsigned offs, rec_len; unsigned limit = PAGE_SIZE; @@ -205,7 +204,8 @@ static struct page * ext2_get_page(struct inode *dir, unsigned long n, if (!IS_ERR(page)) { *page_addr = kmap_local_page(page); if (unlikely(!PageChecked(page))) { - if (PageError(page) || !ext2_check_page(page, quiet)) + if (PageError(page) || !ext2_check_page(page, quiet, + *page_addr)) goto fail; } } @@ -584,10 +584,10 @@ out_unlock: * ext2_delete_entry deletes a directory entry by merging it with the * previous entry. Page is up-to-date. */ -int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page ) +int ext2_delete_entry (struct ext2_dir_entry_2 *dir, struct page *page, + char *kaddr) { struct inode *inode = page->mapping->host; - char *kaddr = page_address(page); unsigned from = ((char*)dir - kaddr) & ~(ext2_chunk_size(inode)-1); unsigned to = ((char *)dir - kaddr) + ext2_rec_len_from_disk(dir->rec_len); @@ -607,7 +607,7 @@ int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page ) de = ext2_next_entry(de); } if (pde) - from = (char*)pde - (char*)page_address(page); + from = (char *)pde - kaddr; pos = page_offset(page) + from; lock_page(page); err = ext2_prepare_chunk(page, pos, to - from); diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index b0a694820cb7..e512630cb63e 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -740,7 +740,8 @@ extern int ext2_inode_by_name(struct inode *dir, extern int ext2_make_empty(struct inode *, struct inode *); extern struct ext2_dir_entry_2 *ext2_find_entry(struct inode *, const struct qstr *, struct page **, void **res_page_addr); -extern int ext2_delete_entry (struct ext2_dir_entry_2 *, struct page *); +extern int ext2_delete_entry(struct ext2_dir_entry_2 *dir, struct page *page, + char *kaddr); extern int ext2_empty_dir (struct inode *); extern struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p, void **pa); extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, void *, diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 1f69b81655b6..5f6b7560eb3f 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -293,7 +293,7 @@ static int ext2_unlink(struct inode * dir, struct dentry *dentry) goto out; } - err = ext2_delete_entry (de, page); + err = ext2_delete_entry (de, page, page_addr); ext2_put_page(page, page_addr); if (err) goto out; @@ -397,7 +397,7 @@ static int ext2_rename (struct user_namespace * mnt_userns, old_inode->i_ctime = current_time(old_inode); mark_inode_dirty(old_inode); - ext2_delete_entry(old_de, old_page); + ext2_delete_entry(old_de, old_page, old_page_addr); if (dir_de) { if (old_dir != new_dir) diff --git a/fs/internal.h b/fs/internal.h index 3ce8edbaa3ca..82e8eb32ff3d 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -61,7 +61,6 @@ extern void __init chrdev_init(void); */ extern const struct fs_context_operations legacy_fs_context_ops; extern int parse_monolithic_mount_data(struct fs_context *, void *); -extern void fc_drop_locked(struct fs_context *); extern void vfs_clean_context(struct fs_context *fc); extern int finish_clean_context(struct fs_context *fc); diff --git a/fs/io_uring.c b/fs/io_uring.c index 5a0fd6bcd318..bf548af0426c 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1279,8 +1279,17 @@ static void io_prep_async_link(struct io_kiocb *req) { struct io_kiocb *cur; - io_for_each_link(cur, req) - io_prep_async_work(cur); + if (req->flags & REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = req->ctx; + + spin_lock_irq(&ctx->completion_lock); + io_for_each_link(cur, req) + io_prep_async_work(cur); + spin_unlock_irq(&ctx->completion_lock); + } else { + io_for_each_link(cur, req) + io_prep_async_work(cur); + } } static void io_queue_async_work(struct io_kiocb *req) @@ -1950,9 +1959,13 @@ static void tctx_task_work(struct callback_head *cb) node = next; } if (wq_list_empty(&tctx->task_list)) { + spin_lock_irq(&tctx->task_lock); clear_bit(0, &tctx->task_state); - if (wq_list_empty(&tctx->task_list)) + if (wq_list_empty(&tctx->task_list)) { + spin_unlock_irq(&tctx->task_lock); break; + } + spin_unlock_irq(&tctx->task_lock); /* another tctx_task_work() is enqueued, yield */ if (test_and_set_bit(0, &tctx->task_state)) break; @@ -2047,6 +2060,12 @@ static void io_req_task_queue(struct io_kiocb *req) io_req_task_work_add(req); } +static void io_req_task_queue_reissue(struct io_kiocb *req) +{ + req->io_task_work.func = io_queue_async_work; + io_req_task_work_add(req); +} + static inline void io_queue_next(struct io_kiocb *req) { struct io_kiocb *nxt = io_req_find_next(req); @@ -2235,7 +2254,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, !(req->flags & REQ_F_DONT_REISSUE)) { req->iopoll_completed = 0; req_ref_get(req); - io_queue_async_work(req); + io_req_task_queue_reissue(req); continue; } @@ -2428,6 +2447,12 @@ static bool io_rw_should_reissue(struct io_kiocb *req) */ if (percpu_ref_is_dying(&ctx->refs)) return false; + /* + * Play it safe and assume not safe to re-import and reissue if we're + * not in the original thread group (or in task context). + */ + if (!same_thread_group(req->task, current) || !in_task()) + return false; return true; } #else @@ -2758,7 +2783,7 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, req->flags &= ~REQ_F_REISSUE; if (io_resubmit_prep(req)) { req_ref_get(req); - io_queue_async_work(req); + io_req_task_queue_reissue(req); } else { int cflags = 0; @@ -4914,7 +4939,6 @@ static bool io_poll_complete(struct io_kiocb *req, __poll_t mask) if (req->poll.events & EPOLLONESHOT) flags = 0; if (!io_cqring_fill_event(ctx, req->user_data, error, flags)) { - io_poll_remove_waitqs(req); req->poll.done = true; flags = 0; } @@ -4937,6 +4961,7 @@ static void io_poll_task_func(struct io_kiocb *req) done = io_poll_complete(req, req->result); if (done) { + io_poll_remove_double(req); hash_del(&req->hash_node); } else { req->result = 0; @@ -5124,7 +5149,7 @@ static __poll_t __io_arm_poll_handler(struct io_kiocb *req, ipt->error = -EINVAL; spin_lock_irq(&ctx->completion_lock); - if (ipt->error) + if (ipt->error || (mask && (poll->events & EPOLLONESHOT))) io_poll_remove_double(req); if (likely(poll->head)) { spin_lock(&poll->head->lock); @@ -5196,7 +5221,6 @@ static int io_arm_poll_handler(struct io_kiocb *req) ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask, io_async_wake); if (ret || ipt.error) { - io_poll_remove_double(req); spin_unlock_irq(&ctx->completion_lock); if (ret) return IO_APOLL_READY; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 775657943057..54d7843c0211 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1529,6 +1529,45 @@ static void ocfs2_truncate_cluster_pages(struct inode *inode, u64 byte_start, } } +/* + * zero out partial blocks of one cluster. + * + * start: file offset where zero starts, will be made upper block aligned. + * len: it will be trimmed to the end of current cluster if "start + len" + * is bigger than it. + */ +static int ocfs2_zeroout_partial_cluster(struct inode *inode, + u64 start, u64 len) +{ + int ret; + u64 start_block, end_block, nr_blocks; + u64 p_block, offset; + u32 cluster, p_cluster, nr_clusters; + struct super_block *sb = inode->i_sb; + u64 end = ocfs2_align_bytes_to_clusters(sb, start); + + if (start + len < end) + end = start + len; + + start_block = ocfs2_blocks_for_bytes(sb, start); + end_block = ocfs2_blocks_for_bytes(sb, end); + nr_blocks = end_block - start_block; + if (!nr_blocks) + return 0; + + cluster = ocfs2_bytes_to_clusters(sb, start); + ret = ocfs2_get_clusters(inode, cluster, &p_cluster, + &nr_clusters, NULL); + if (ret) + return ret; + if (!p_cluster) + return 0; + + offset = start_block - ocfs2_clusters_to_blocks(sb, cluster); + p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset; + return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS); +} + static int ocfs2_zero_partial_clusters(struct inode *inode, u64 start, u64 len) { @@ -1538,6 +1577,7 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); unsigned int csize = osb->s_clustersize; handle_t *handle; + loff_t isize = i_size_read(inode); /* * The "start" and "end" values are NOT necessarily part of @@ -1558,6 +1598,26 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, if ((start & (csize - 1)) == 0 && (end & (csize - 1)) == 0) goto out; + /* No page cache for EOF blocks, issue zero out to disk. */ + if (end > isize) { + /* + * zeroout eof blocks in last cluster starting from + * "isize" even "start" > "isize" because it is + * complicated to zeroout just at "start" as "start" + * may be not aligned with block size, buffer write + * would be required to do that, but out of eof buffer + * write is not supported. + */ + ret = ocfs2_zeroout_partial_cluster(inode, isize, + end - isize); + if (ret) { + mlog_errno(ret); + goto out; + } + if (start >= isize) + goto out; + end = isize; + } handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { ret = PTR_ERR(handle); @@ -1856,45 +1916,6 @@ out: } /* - * zero out partial blocks of one cluster. - * - * start: file offset where zero starts, will be made upper block aligned. - * len: it will be trimmed to the end of current cluster if "start + len" - * is bigger than it. - */ -static int ocfs2_zeroout_partial_cluster(struct inode *inode, - u64 start, u64 len) -{ - int ret; - u64 start_block, end_block, nr_blocks; - u64 p_block, offset; - u32 cluster, p_cluster, nr_clusters; - struct super_block *sb = inode->i_sb; - u64 end = ocfs2_align_bytes_to_clusters(sb, start); - - if (start + len < end) - end = start + len; - - start_block = ocfs2_blocks_for_bytes(sb, start); - end_block = ocfs2_blocks_for_bytes(sb, end); - nr_blocks = end_block - start_block; - if (!nr_blocks) - return 0; - - cluster = ocfs2_bytes_to_clusters(sb, start); - ret = ocfs2_get_clusters(inode, cluster, &p_cluster, - &nr_clusters, NULL); - if (ret) - return ret; - if (!p_cluster) - return 0; - - offset = start_block - ocfs2_clusters_to_blocks(sb, cluster); - p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset; - return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS); -} - -/* * Parts of this function taken from xfs_change_file_space() */ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, @@ -1935,7 +1956,6 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, goto out_inode_unlock; } - orig_isize = i_size_read(inode); switch (sr->l_whence) { case 0: /*SEEK_SET*/ break; @@ -1943,7 +1963,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, sr->l_start += f_pos; break; case 2: /*SEEK_END*/ - sr->l_start += orig_isize; + sr->l_start += i_size_read(inode); break; default: ret = -EINVAL; @@ -1998,6 +2018,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, ret = -EINVAL; } + orig_isize = i_size_read(inode); /* zeroout eof blocks in the cluster. */ if (!ret && change_size && orig_isize < size) { ret = ocfs2_zeroout_partial_cluster(inode, orig_isize, diff --git a/fs/pipe.c b/fs/pipe.c index bfd946a9ad01..9ef4231cce61 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -429,20 +429,20 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) #endif /* - * Only wake up if the pipe started out empty, since - * otherwise there should be no readers waiting. + * Epoll nonsensically wants a wakeup whether the pipe + * was already empty or not. * * If it wasn't empty we try to merge new data into * the last buffer. * * That naturally merges small writes, but it also - * page-aligs the rest of the writes for large writes + * page-aligns the rest of the writes for large writes * spanning multiple pages. */ head = pipe->head; - was_empty = pipe_empty(head, pipe->tail); + was_empty = true; chars = total_len & (PAGE_SIZE-1); - if (chars && !was_empty) { + if (chars && !pipe_empty(head, pipe->tail)) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask]; int offset = buf->offset + buf->len; diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index 476a7ff49482..ef42729216d1 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -387,6 +387,24 @@ void pathrelse(struct treepath *search_path) search_path->path_length = ILLEGAL_PATH_ELEMENT_OFFSET; } +static int has_valid_deh_location(struct buffer_head *bh, struct item_head *ih) +{ + struct reiserfs_de_head *deh; + int i; + + deh = B_I_DEH(bh, ih); + for (i = 0; i < ih_entry_count(ih); i++) { + if (deh_location(&deh[i]) > ih_item_len(ih)) { + reiserfs_warning(NULL, "reiserfs-5094", + "directory entry location seems wrong %h", + &deh[i]); + return 0; + } + } + + return 1; +} + static int is_leaf(char *buf, int blocksize, struct buffer_head *bh) { struct block_head *blkh; @@ -454,11 +472,14 @@ static int is_leaf(char *buf, int blocksize, struct buffer_head *bh) "(second one): %h", ih); return 0; } - if (is_direntry_le_ih(ih) && (ih_item_len(ih) < (ih_entry_count(ih) * IH_SIZE))) { - reiserfs_warning(NULL, "reiserfs-5093", - "item entry count seems wrong %h", - ih); - return 0; + if (is_direntry_le_ih(ih)) { + if (ih_item_len(ih) < (ih_entry_count(ih) * IH_SIZE)) { + reiserfs_warning(NULL, "reiserfs-5093", + "item entry count seems wrong %h", + ih); + return 0; + } + return has_valid_deh_location(bh, ih); } prev_location = ih_location(ih); } diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 3ffafc73acf0..58481f8d63d5 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -2082,6 +2082,14 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) unlock_new_inode(root_inode); } + if (!S_ISDIR(root_inode->i_mode) || !inode_get_bytes(root_inode) || + !root_inode->i_size) { + SWARN(silent, s, "", "corrupt root inode, run fsck"); + iput(root_inode); + errval = -EUCLEAN; + goto error; + } + s->s_root = d_make_root(root_inode); if (!s->s_root) goto error; diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index d548ea4b6aab..2c5bcbc19264 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -411,7 +411,16 @@ struct xfs_log_dinode { /* start of the extended dinode, writable fields */ uint32_t di_crc; /* CRC of the inode */ uint64_t di_changecount; /* number of attribute changes */ - xfs_lsn_t di_lsn; /* flush sequence */ + + /* + * The LSN we write to this field during formatting is not a reflection + * of the current on-disk LSN. It should never be used for recovery + * sequencing, nor should it be recovered into the on-disk inode at all. + * See xlog_recover_inode_commit_pass2() and xfs_log_dinode_to_disk() + * for details. + */ + xfs_lsn_t di_lsn; + uint64_t di_flags2; /* more random flags */ uint32_t di_cowextsize; /* basic cow extent size for file */ uint8_t di_pad2[12]; /* more padding for future expansion */ diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c index d44e8b4a3391..4775485b4062 100644 --- a/fs/xfs/xfs_buf_item_recover.c +++ b/fs/xfs/xfs_buf_item_recover.c @@ -698,7 +698,8 @@ xlog_recover_do_inode_buffer( static xfs_lsn_t xlog_recover_get_buf_lsn( struct xfs_mount *mp, - struct xfs_buf *bp) + struct xfs_buf *bp, + struct xfs_buf_log_format *buf_f) { uint32_t magic32; uint16_t magic16; @@ -706,11 +707,20 @@ xlog_recover_get_buf_lsn( void *blk = bp->b_addr; uuid_t *uuid; xfs_lsn_t lsn = -1; + uint16_t blft; /* v4 filesystems always recover immediately */ if (!xfs_sb_version_hascrc(&mp->m_sb)) goto recover_immediately; + /* + * realtime bitmap and summary file blocks do not have magic numbers or + * UUIDs, so we must recover them immediately. + */ + blft = xfs_blft_from_flags(buf_f); + if (blft == XFS_BLFT_RTBITMAP_BUF || blft == XFS_BLFT_RTSUMMARY_BUF) + goto recover_immediately; + magic32 = be32_to_cpu(*(__be32 *)blk); switch (magic32) { case XFS_ABTB_CRC_MAGIC: @@ -796,6 +806,7 @@ xlog_recover_get_buf_lsn( switch (magicda) { case XFS_DIR3_LEAF1_MAGIC: case XFS_DIR3_LEAFN_MAGIC: + case XFS_ATTR3_LEAF_MAGIC: case XFS_DA3_NODE_MAGIC: lsn = be64_to_cpu(((struct xfs_da3_blkinfo *)blk)->lsn); uuid = &((struct xfs_da3_blkinfo *)blk)->uuid; @@ -919,7 +930,7 @@ xlog_recover_buf_commit_pass2( * the verifier will be reset to match whatever recover turns that * buffer into. */ - lsn = xlog_recover_get_buf_lsn(mp, bp); + lsn = xlog_recover_get_buf_lsn(mp, bp, buf_f); if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) { trace_xfs_log_recover_buf_skip(log, buf_f); xlog_recover_validate_buf_type(mp, bp, buf_f, NULLCOMMITLSN); diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c index 7b79518b6c20..e0072a6cd2d3 100644 --- a/fs/xfs/xfs_inode_item_recover.c +++ b/fs/xfs/xfs_inode_item_recover.c @@ -145,7 +145,8 @@ xfs_log_dinode_to_disk_ts( STATIC void xfs_log_dinode_to_disk( struct xfs_log_dinode *from, - struct xfs_dinode *to) + struct xfs_dinode *to, + xfs_lsn_t lsn) { to->di_magic = cpu_to_be16(from->di_magic); to->di_mode = cpu_to_be16(from->di_mode); @@ -182,7 +183,7 @@ xfs_log_dinode_to_disk( to->di_flags2 = cpu_to_be64(from->di_flags2); to->di_cowextsize = cpu_to_be32(from->di_cowextsize); to->di_ino = cpu_to_be64(from->di_ino); - to->di_lsn = cpu_to_be64(from->di_lsn); + to->di_lsn = cpu_to_be64(lsn); memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2)); uuid_copy(&to->di_uuid, &from->di_uuid); to->di_flushiter = 0; @@ -261,16 +262,25 @@ xlog_recover_inode_commit_pass2( } /* - * If the inode has an LSN in it, recover the inode only if it's less - * than the lsn of the transaction we are replaying. Note: we still - * need to replay an owner change even though the inode is more recent - * than the transaction as there is no guarantee that all the btree - * blocks are more recent than this transaction, too. + * If the inode has an LSN in it, recover the inode only if the on-disk + * inode's LSN is older than the lsn of the transaction we are + * replaying. We can have multiple checkpoints with the same start LSN, + * so the current LSN being equal to the on-disk LSN doesn't necessarily + * mean that the on-disk inode is more recent than the change being + * replayed. + * + * We must check the current_lsn against the on-disk inode + * here because the we can't trust the log dinode to contain a valid LSN + * (see comment below before replaying the log dinode for details). + * + * Note: we still need to replay an owner change even though the inode + * is more recent than the transaction as there is no guarantee that all + * the btree blocks are more recent than this transaction, too. */ if (dip->di_version >= 3) { xfs_lsn_t lsn = be64_to_cpu(dip->di_lsn); - if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) { + if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) > 0) { trace_xfs_log_recover_inode_skip(log, in_f); error = 0; goto out_owner_change; @@ -368,8 +378,17 @@ xlog_recover_inode_commit_pass2( goto out_release; } - /* recover the log dinode inode into the on disk inode */ - xfs_log_dinode_to_disk(ldip, dip); + /* + * Recover the log dinode inode into the on disk inode. + * + * The LSN in the log dinode is garbage - it can be zero or reflect + * stale in-memory runtime state that isn't coherent with the changes + * logged in this transaction or the changes written to the on-disk + * inode. Hence we write the current lSN into the inode because that + * matches what xfs_iflush() would write inode the inode when flushing + * the changes in this transaction. + */ + xfs_log_dinode_to_disk(ldip, dip, current_lsn); fields = in_f->ilf_fields; if (fields & XFS_ILOG_DEV) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 36fa2650b081..60ac5fd63f1e 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -78,13 +78,12 @@ xlog_verify_iclog( STATIC void xlog_verify_tail_lsn( struct xlog *log, - struct xlog_in_core *iclog, - xfs_lsn_t tail_lsn); + struct xlog_in_core *iclog); #else #define xlog_verify_dest_ptr(a,b) #define xlog_verify_grant_tail(a) #define xlog_verify_iclog(a,b,c) -#define xlog_verify_tail_lsn(a,b,c) +#define xlog_verify_tail_lsn(a,b) #endif STATIC int @@ -487,51 +486,80 @@ out_error: return error; } -static bool -__xlog_state_release_iclog( - struct xlog *log, - struct xlog_in_core *iclog) -{ - lockdep_assert_held(&log->l_icloglock); - - if (iclog->ic_state == XLOG_STATE_WANT_SYNC) { - /* update tail before writing to iclog */ - xfs_lsn_t tail_lsn = xlog_assign_tail_lsn(log->l_mp); - - iclog->ic_state = XLOG_STATE_SYNCING; - iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn); - xlog_verify_tail_lsn(log, iclog, tail_lsn); - /* cycle incremented when incrementing curr_block */ - trace_xlog_iclog_syncing(iclog, _RET_IP_); - return true; - } - - ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE); - return false; -} - /* * Flush iclog to disk if this is the last reference to the given iclog and the * it is in the WANT_SYNC state. + * + * If the caller passes in a non-zero @old_tail_lsn and the current log tail + * does not match, there may be metadata on disk that must be persisted before + * this iclog is written. To satisfy that requirement, set the + * XLOG_ICL_NEED_FLUSH flag as a condition for writing this iclog with the new + * log tail value. + * + * If XLOG_ICL_NEED_FUA is already set on the iclog, we need to ensure that the + * log tail is updated correctly. NEED_FUA indicates that the iclog will be + * written to stable storage, and implies that a commit record is contained + * within the iclog. We need to ensure that the log tail does not move beyond + * the tail that the first commit record in the iclog ordered against, otherwise + * correct recovery of that checkpoint becomes dependent on future operations + * performed on this iclog. + * + * Hence if NEED_FUA is set and the current iclog tail lsn is empty, write the + * current tail into iclog. Once the iclog tail is set, future operations must + * not modify it, otherwise they potentially violate ordering constraints for + * the checkpoint commit that wrote the initial tail lsn value. The tail lsn in + * the iclog will get zeroed on activation of the iclog after sync, so we + * always capture the tail lsn on the iclog on the first NEED_FUA release + * regardless of the number of active reference counts on this iclog. */ + int xlog_state_release_iclog( struct xlog *log, - struct xlog_in_core *iclog) + struct xlog_in_core *iclog, + xfs_lsn_t old_tail_lsn) { + xfs_lsn_t tail_lsn; lockdep_assert_held(&log->l_icloglock); trace_xlog_iclog_release(iclog, _RET_IP_); if (iclog->ic_state == XLOG_STATE_IOERROR) return -EIO; - if (atomic_dec_and_test(&iclog->ic_refcnt) && - __xlog_state_release_iclog(log, iclog)) { - spin_unlock(&log->l_icloglock); - xlog_sync(log, iclog); - spin_lock(&log->l_icloglock); + /* + * Grabbing the current log tail needs to be atomic w.r.t. the writing + * of the tail LSN into the iclog so we guarantee that the log tail does + * not move between deciding if a cache flush is required and writing + * the LSN into the iclog below. + */ + if (old_tail_lsn || iclog->ic_state == XLOG_STATE_WANT_SYNC) { + tail_lsn = xlog_assign_tail_lsn(log->l_mp); + + if (old_tail_lsn && tail_lsn != old_tail_lsn) + iclog->ic_flags |= XLOG_ICL_NEED_FLUSH; + + if ((iclog->ic_flags & XLOG_ICL_NEED_FUA) && + !iclog->ic_header.h_tail_lsn) + iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn); } + if (!atomic_dec_and_test(&iclog->ic_refcnt)) + return 0; + + if (iclog->ic_state != XLOG_STATE_WANT_SYNC) { + ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE); + return 0; + } + + iclog->ic_state = XLOG_STATE_SYNCING; + if (!iclog->ic_header.h_tail_lsn) + iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn); + xlog_verify_tail_lsn(log, iclog); + trace_xlog_iclog_syncing(iclog, _RET_IP_); + + spin_unlock(&log->l_icloglock); + xlog_sync(log, iclog); + spin_lock(&log->l_icloglock); return 0; } @@ -774,6 +802,21 @@ xfs_log_mount_cancel( } /* + * Flush out the iclog to disk ensuring that device caches are flushed and + * the iclog hits stable storage before any completion waiters are woken. + */ +static inline int +xlog_force_iclog( + struct xlog_in_core *iclog) +{ + atomic_inc(&iclog->ic_refcnt); + iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; + if (iclog->ic_state == XLOG_STATE_ACTIVE) + xlog_state_switch_iclogs(iclog->ic_log, iclog, 0); + return xlog_state_release_iclog(iclog->ic_log, iclog, 0); +} + +/* * Wait for the iclog and all prior iclogs to be written disk as required by the * log force state machine. Waiting on ic_force_wait ensures iclog completions * have been ordered and callbacks run before we are woken here, hence @@ -827,13 +870,6 @@ xlog_write_unmount_record( /* account for space used by record data */ ticket->t_curr_res -= sizeof(ulf); - /* - * For external log devices, we need to flush the data device cache - * first to ensure all metadata writeback is on stable storage before we - * stamp the tail LSN into the unmount record. - */ - if (log->l_targ != log->l_mp->m_ddev_targp) - blkdev_issue_flush(log->l_targ->bt_bdev); return xlog_write(log, &vec, ticket, NULL, NULL, XLOG_UNMOUNT_TRANS); } @@ -865,18 +901,7 @@ out_err: spin_lock(&log->l_icloglock); iclog = log->l_iclog; - atomic_inc(&iclog->ic_refcnt); - if (iclog->ic_state == XLOG_STATE_ACTIVE) - xlog_state_switch_iclogs(log, iclog, 0); - else - ASSERT(iclog->ic_state == XLOG_STATE_WANT_SYNC || - iclog->ic_state == XLOG_STATE_IOERROR); - /* - * Ensure the journal is fully flushed and on stable storage once the - * iclog containing the unmount record is written. - */ - iclog->ic_flags |= (XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA); - error = xlog_state_release_iclog(log, iclog); + error = xlog_force_iclog(iclog); xlog_wait_on_iclog(iclog); if (tic) { @@ -1796,10 +1821,20 @@ xlog_write_iclog( * metadata writeback and causing priority inversions. */ iclog->ic_bio.bi_opf = REQ_OP_WRITE | REQ_META | REQ_SYNC | REQ_IDLE; - if (iclog->ic_flags & XLOG_ICL_NEED_FLUSH) + if (iclog->ic_flags & XLOG_ICL_NEED_FLUSH) { iclog->ic_bio.bi_opf |= REQ_PREFLUSH; + /* + * For external log devices, we also need to flush the data + * device cache first to ensure all metadata writeback covered + * by the LSN in this iclog is on stable storage. This is slow, + * but it *must* complete before we issue the external log IO. + */ + if (log->l_targ != log->l_mp->m_ddev_targp) + blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev); + } if (iclog->ic_flags & XLOG_ICL_NEED_FUA) iclog->ic_bio.bi_opf |= REQ_FUA; + iclog->ic_flags &= ~(XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA); if (xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count)) { @@ -2310,7 +2345,7 @@ xlog_write_copy_finish( return 0; release_iclog: - error = xlog_state_release_iclog(log, iclog); + error = xlog_state_release_iclog(log, iclog, 0); spin_unlock(&log->l_icloglock); return error; } @@ -2529,7 +2564,7 @@ next_lv: ASSERT(optype & XLOG_COMMIT_TRANS); *commit_iclog = iclog; } else { - error = xlog_state_release_iclog(log, iclog); + error = xlog_state_release_iclog(log, iclog, 0); } spin_unlock(&log->l_icloglock); @@ -2567,6 +2602,7 @@ xlog_state_activate_iclog( memset(iclog->ic_header.h_cycle_data, 0, sizeof(iclog->ic_header.h_cycle_data)); iclog->ic_header.h_lsn = 0; + iclog->ic_header.h_tail_lsn = 0; } /* @@ -2967,7 +3003,7 @@ restart: * reference to the iclog. */ if (!atomic_add_unless(&iclog->ic_refcnt, -1, 1)) - error = xlog_state_release_iclog(log, iclog); + error = xlog_state_release_iclog(log, iclog, 0); spin_unlock(&log->l_icloglock); if (error) return error; @@ -3132,6 +3168,35 @@ xlog_state_switch_iclogs( } /* + * Force the iclog to disk and check if the iclog has been completed before + * xlog_force_iclog() returns. This can happen on synchronous (e.g. + * pmem) or fast async storage because we drop the icloglock to issue the IO. + * If completion has already occurred, tell the caller so that it can avoid an + * unnecessary wait on the iclog. + */ +static int +xlog_force_and_check_iclog( + struct xlog_in_core *iclog, + bool *completed) +{ + xfs_lsn_t lsn = be64_to_cpu(iclog->ic_header.h_lsn); + int error; + + *completed = false; + error = xlog_force_iclog(iclog); + if (error) + return error; + + /* + * If the iclog has already been completed and reused the header LSN + * will have been rewritten by completion + */ + if (be64_to_cpu(iclog->ic_header.h_lsn) != lsn) + *completed = true; + return 0; +} + +/* * Write out all data in the in-core log as of this exact moment in time. * * Data may be written to the in-core log during this call. However, @@ -3165,7 +3230,6 @@ xfs_log_force( { struct xlog *log = mp->m_log; struct xlog_in_core *iclog; - xfs_lsn_t lsn; XFS_STATS_INC(mp, xs_log_force); trace_xfs_log_force(mp, 0, _RET_IP_); @@ -3193,39 +3257,33 @@ xfs_log_force( iclog = iclog->ic_prev; } else if (iclog->ic_state == XLOG_STATE_ACTIVE) { if (atomic_read(&iclog->ic_refcnt) == 0) { - /* - * We are the only one with access to this iclog. - * - * Flush it out now. There should be a roundoff of zero - * to show that someone has already taken care of the - * roundoff from the previous sync. - */ - atomic_inc(&iclog->ic_refcnt); - lsn = be64_to_cpu(iclog->ic_header.h_lsn); - xlog_state_switch_iclogs(log, iclog, 0); - if (xlog_state_release_iclog(log, iclog)) + /* We have exclusive access to this iclog. */ + bool completed; + + if (xlog_force_and_check_iclog(iclog, &completed)) goto out_error; - if (be64_to_cpu(iclog->ic_header.h_lsn) != lsn) + if (completed) goto out_unlock; } else { /* - * Someone else is writing to this iclog. - * - * Use its call to flush out the data. However, the - * other thread may not force out this LR, so we mark - * it WANT_SYNC. + * Someone else is still writing to this iclog, so we + * need to ensure that when they release the iclog it + * gets synced immediately as we may be waiting on it. */ xlog_state_switch_iclogs(log, iclog, 0); } - } else { - /* - * If the head iclog is not active nor dirty, we just attach - * ourselves to the head and go to sleep if necessary. - */ - ; } + /* + * The iclog we are about to wait on may contain the checkpoint pushed + * by the above xlog_cil_force() call, but it may not have been pushed + * to disk yet. Like the ACTIVE case above, we need to make sure caches + * are flushed when this iclog is written. + */ + if (iclog->ic_state == XLOG_STATE_WANT_SYNC) + iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; + if (flags & XFS_LOG_SYNC) return xlog_wait_on_iclog(iclog); out_unlock: @@ -3245,6 +3303,7 @@ xlog_force_lsn( bool already_slept) { struct xlog_in_core *iclog; + bool completed; spin_lock(&log->l_icloglock); iclog = log->l_iclog; @@ -3258,7 +3317,8 @@ xlog_force_lsn( goto out_unlock; } - if (iclog->ic_state == XLOG_STATE_ACTIVE) { + switch (iclog->ic_state) { + case XLOG_STATE_ACTIVE: /* * We sleep here if we haven't already slept (e.g. this is the * first time we've looked at the correct iclog buf) and the @@ -3281,12 +3341,31 @@ xlog_force_lsn( &log->l_icloglock); return -EAGAIN; } - atomic_inc(&iclog->ic_refcnt); - xlog_state_switch_iclogs(log, iclog, 0); - if (xlog_state_release_iclog(log, iclog)) + if (xlog_force_and_check_iclog(iclog, &completed)) goto out_error; if (log_flushed) *log_flushed = 1; + if (completed) + goto out_unlock; + break; + case XLOG_STATE_WANT_SYNC: + /* + * This iclog may contain the checkpoint pushed by the + * xlog_cil_force_seq() call, but there are other writers still + * accessing it so it hasn't been pushed to disk yet. Like the + * ACTIVE case above, we need to make sure caches are flushed + * when this iclog is written. + */ + iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; + break; + default: + /* + * The entire checkpoint was written by the CIL force and is on + * its way to disk already. It will be stable when it + * completes, so we don't need to manipulate caches here at all. + * We just need to wait for completion if necessary. + */ + break; } if (flags & XFS_LOG_SYNC) @@ -3559,10 +3638,10 @@ xlog_verify_grant_tail( STATIC void xlog_verify_tail_lsn( struct xlog *log, - struct xlog_in_core *iclog, - xfs_lsn_t tail_lsn) + struct xlog_in_core *iclog) { - int blocks; + xfs_lsn_t tail_lsn = be64_to_cpu(iclog->ic_header.h_tail_lsn); + int blocks; if (CYCLE_LSN(tail_lsn) == log->l_prev_cycle) { blocks = diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index b128aaa9b870..4c44bc3786c0 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -654,8 +654,9 @@ xlog_cil_push_work( struct xfs_trans_header thdr; struct xfs_log_iovec lhdr; struct xfs_log_vec lvhdr = { NULL }; + xfs_lsn_t preflush_tail_lsn; xfs_lsn_t commit_lsn; - xfs_lsn_t push_seq; + xfs_csn_t push_seq; struct bio bio; DECLARE_COMPLETION_ONSTACK(bdev_flush); @@ -730,7 +731,15 @@ xlog_cil_push_work( * because we hold the flush lock exclusively. Hence we can now issue * a cache flush to ensure all the completed metadata in the journal we * are about to overwrite is on stable storage. + * + * Because we are issuing this cache flush before we've written the + * tail lsn to the iclog, we can have metadata IO completions move the + * tail forwards between the completion of this flush and the iclog + * being written. In this case, we need to re-issue the cache flush + * before the iclog write. To detect whether the log tail moves, sample + * the tail LSN *before* we issue the flush. */ + preflush_tail_lsn = atomic64_read(&log->l_tail_lsn); xfs_flush_bdev_async(&bio, log->l_mp->m_ddev_targp->bt_bdev, &bdev_flush); @@ -941,7 +950,7 @@ restart: * storage. */ commit_iclog->ic_flags |= XLOG_ICL_NEED_FUA; - xlog_state_release_iclog(log, commit_iclog); + xlog_state_release_iclog(log, commit_iclog, preflush_tail_lsn); spin_unlock(&log->l_icloglock); return; diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 4c41bbfa33b0..f3e79a45d60a 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -59,6 +59,16 @@ enum xlog_iclog_state { { XLOG_STATE_DIRTY, "XLOG_STATE_DIRTY" }, \ { XLOG_STATE_IOERROR, "XLOG_STATE_IOERROR" } +/* + * In core log flags + */ +#define XLOG_ICL_NEED_FLUSH (1 << 0) /* iclog needs REQ_PREFLUSH */ +#define XLOG_ICL_NEED_FUA (1 << 1) /* iclog needs REQ_FUA */ + +#define XLOG_ICL_STRINGS \ + { XLOG_ICL_NEED_FLUSH, "XLOG_ICL_NEED_FLUSH" }, \ + { XLOG_ICL_NEED_FUA, "XLOG_ICL_NEED_FUA" } + /* * Log ticket flags @@ -143,9 +153,6 @@ enum xlog_iclog_state { #define XLOG_COVER_OPS 5 -#define XLOG_ICL_NEED_FLUSH (1 << 0) /* iclog needs REQ_PREFLUSH */ -#define XLOG_ICL_NEED_FUA (1 << 1) /* iclog needs REQ_FUA */ - /* Ticket reservation region accounting */ #define XLOG_TIC_LEN_MAX 15 @@ -497,7 +504,8 @@ int xlog_commit_record(struct xlog *log, struct xlog_ticket *ticket, void xfs_log_ticket_ungrant(struct xlog *log, struct xlog_ticket *ticket); void xfs_log_ticket_regrant(struct xlog *log, struct xlog_ticket *ticket); -int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog); +int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog, + xfs_lsn_t log_tail_lsn); /* * When we crack an atomic LSN, we sample it first so that the value will not diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index f9d8d605f9b1..19260291ff8b 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -3944,6 +3944,7 @@ DECLARE_EVENT_CLASS(xlog_iclog_class, __field(uint32_t, state) __field(int32_t, refcount) __field(uint32_t, offset) + __field(uint32_t, flags) __field(unsigned long long, lsn) __field(unsigned long, caller_ip) ), @@ -3952,15 +3953,17 @@ DECLARE_EVENT_CLASS(xlog_iclog_class, __entry->state = iclog->ic_state; __entry->refcount = atomic_read(&iclog->ic_refcnt); __entry->offset = iclog->ic_offset; + __entry->flags = iclog->ic_flags; __entry->lsn = be64_to_cpu(iclog->ic_header.h_lsn); __entry->caller_ip = caller_ip; ), - TP_printk("dev %d:%d state %s refcnt %d offset %u lsn 0x%llx caller %pS", + TP_printk("dev %d:%d state %s refcnt %d offset %u lsn 0x%llx flags %s caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->state, XLOG_STATE_STRINGS), __entry->refcount, __entry->offset, __entry->lsn, + __print_flags(__entry->flags, "|", XLOG_ICL_STRINGS), (char *)__entry->caller_ip) ); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index a9db1eae6796..ae3ac3a2018c 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -134,4 +134,5 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup) BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter) #ifdef CONFIG_NET BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns) +BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) #endif diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e774ecc1cd1f..828d08afeee0 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -340,8 +340,8 @@ struct bpf_insn_aux_data { }; u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ - int sanitize_stack_off; /* stack slot to be cleared */ u32 seen; /* this insn was processed by the verifier at env->pass_cnt */ + bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */ bool zext_dst; /* this insn zero extends dst reg */ u8 alu_state; /* used in combination with alu_limit */ @@ -414,6 +414,7 @@ struct bpf_verifier_env { u32 used_map_cnt; /* number of used maps */ u32 used_btf_cnt; /* number of used BTF objects */ u32 id_gen; /* used to generate unique reg IDs */ + bool explore_alu_limits; bool allow_ptr_leaks; bool allow_uninit_stack; bool allow_ptr_to_map_access; diff --git a/include/linux/filter.h b/include/linux/filter.h index 472f97074da0..83b896044e79 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -73,6 +73,11 @@ struct ctl_table_header; /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 +/* unused opcode to mark speculation barrier for mitigating + * Speculative Store Bypass + */ +#define BPF_NOSPEC 0xc0 + /* As per nm, we expose JITed images as text (code) section for * kallsyms. That way, tools like perf can find it to match * addresses. @@ -390,6 +395,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) .off = 0, \ .imm = 0 }) +/* Speculation barrier */ + +#define BPF_ST_NOSPEC() \ + ((struct bpf_insn) { \ + .code = BPF_ST | BPF_NOSPEC, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = 0 }) + /* Internal classic blocks for direct assignment */ #define __BPF_STMT(CODE, K) \ diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index e2bc16300c82..6b54982fc5f3 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -141,6 +141,7 @@ extern int vfs_get_tree(struct fs_context *fc); extern void put_fs_context(struct fs_context *fc); extern int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param); +extern void fc_drop_locked(struct fs_context *fc); /* * sget() wrappers to be called from the ->get_tree() op. diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index 25e2b4e80502..aee8ff4739b1 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -81,6 +81,8 @@ int ishtp_register_event_cb(struct ishtp_cl_device *device, /* Get the device * from ishtp device instance */ struct device *ishtp_device(struct ishtp_cl_device *cl_device); +/* wait for IPC resume */ +bool ishtp_wait_resume(struct ishtp_device *dev); /* Trace interface for clients */ ishtp_print_log ishtp_trace_callback(struct ishtp_cl_device *cl_device); /* Get device pointer of PCI device for DMA acces */ diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 96f319099744..14ab0c0bc924 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -285,11 +285,45 @@ static inline struct sk_psock *sk_psock(const struct sock *sk) return rcu_dereference_sk_user_data(sk); } +static inline void sk_psock_set_state(struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + set_bit(bit, &psock->state); +} + +static inline void sk_psock_clear_state(struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + clear_bit(bit, &psock->state); +} + +static inline bool sk_psock_test_state(const struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + return test_bit(bit, &psock->state); +} + +static inline void sock_drop(struct sock *sk, struct sk_buff *skb) +{ + sk_drops_add(sk, skb); + kfree_skb(skb); +} + +static inline void drop_sk_msg(struct sk_psock *psock, struct sk_msg *msg) +{ + if (msg->skb) + sock_drop(psock->sk, msg->skb); + kfree(msg); +} + static inline void sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { spin_lock_bh(&psock->ingress_lock); - list_add_tail(&msg->list, &psock->ingress_msg); + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + list_add_tail(&msg->list, &psock->ingress_msg); + else + drop_sk_msg(psock, msg); spin_unlock_bh(&psock->ingress_lock); } @@ -406,24 +440,6 @@ static inline void sk_psock_restore_proto(struct sock *sk, psock->psock_update_sk_prot(sk, psock, true); } -static inline void sk_psock_set_state(struct sk_psock *psock, - enum sk_psock_state_bits bit) -{ - set_bit(bit, &psock->state); -} - -static inline void sk_psock_clear_state(struct sk_psock *psock, - enum sk_psock_state_bits bit) -{ - clear_bit(bit, &psock->state); -} - -static inline bool sk_psock_test_state(const struct sk_psock *psock, - enum sk_psock_state_bits bit) -{ - return test_bit(bit, &psock->state); -} - static inline struct sk_psock *sk_psock_get(struct sock *sk) { struct sk_psock *psock; diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index c0f0a13ed818..49aa79c7b278 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -15,9 +15,11 @@ #include <linux/if_ether.h> /* Lengths of frame formats */ -#define LLC_PDU_LEN_I 4 /* header and 2 control bytes */ -#define LLC_PDU_LEN_S 4 -#define LLC_PDU_LEN_U 3 /* header and 1 control byte */ +#define LLC_PDU_LEN_I 4 /* header and 2 control bytes */ +#define LLC_PDU_LEN_S 4 +#define LLC_PDU_LEN_U 3 /* header and 1 control byte */ +/* header and 1 control byte and XID info */ +#define LLC_PDU_LEN_U_XID (LLC_PDU_LEN_U + sizeof(struct llc_xid_info)) /* Known SAP addresses */ #define LLC_GLOBAL_SAP 0xFF #define LLC_NULL_SAP 0x00 /* not network-layer visible */ @@ -50,9 +52,10 @@ #define LLC_PDU_TYPE_U_MASK 0x03 /* 8-bit control field */ #define LLC_PDU_TYPE_MASK 0x03 -#define LLC_PDU_TYPE_I 0 /* first bit */ -#define LLC_PDU_TYPE_S 1 /* first two bits */ -#define LLC_PDU_TYPE_U 3 /* first two bits */ +#define LLC_PDU_TYPE_I 0 /* first bit */ +#define LLC_PDU_TYPE_S 1 /* first two bits */ +#define LLC_PDU_TYPE_U 3 /* first two bits */ +#define LLC_PDU_TYPE_U_XID 4 /* private type for detecting XID commands */ #define LLC_PDU_TYPE_IS_I(pdu) \ ((!(pdu->ctrl_1 & LLC_PDU_TYPE_I_MASK)) ? 1 : 0) @@ -230,9 +233,18 @@ static inline struct llc_pdu_un *llc_pdu_un_hdr(struct sk_buff *skb) static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, u8 ssap, u8 dsap, u8 cr) { - const int hlen = type == LLC_PDU_TYPE_U ? 3 : 4; + int hlen = 4; /* default value for I and S types */ struct llc_pdu_un *pdu; + switch (type) { + case LLC_PDU_TYPE_U: + hlen = 3; + break; + case LLC_PDU_TYPE_U_XID: + hlen = 6; + break; + } + skb_push(skb, hlen); skb_reset_network_header(skb); pdu = llc_pdu_un_hdr(skb); @@ -374,7 +386,10 @@ static inline void llc_pdu_init_as_xid_cmd(struct sk_buff *skb, xid_info->fmt_id = LLC_XID_FMT_ID; /* 0x81 */ xid_info->type = svcs_supported; xid_info->rw = rx_window << 1; /* size of receive window */ - skb_put(skb, sizeof(struct llc_xid_info)); + + /* no need to push/put since llc_pdu_header_init() has already + * pushed 3 + 3 bytes + */ } /** diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 32fc4a309df5..651bba654d77 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -984,6 +984,7 @@ struct sctp_transport { } cacc; struct { + __u32 last_rtx_chunks; __u16 pmtu; __u16 probe_size; __u16 probe_high; @@ -1024,8 +1025,8 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu); void sctp_transport_immediate_rtx(struct sctp_transport *); void sctp_transport_dst_release(struct sctp_transport *t); void sctp_transport_dst_confirm(struct sctp_transport *t); -void sctp_transport_pl_send(struct sctp_transport *t); -void sctp_transport_pl_recv(struct sctp_transport *t); +bool sctp_transport_pl_send(struct sctp_transport *t); +bool sctp_transport_pl_recv(struct sctp_transport *t); /* This is the structure we use to queue packets as they come into diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index e33997b4d750..edc346a77c91 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: LGPL-2.1 WITH Linux-syscall-note */ /* Copyright(c) 2019 Intel Corporation. All rights rsvd. */ #ifndef _USR_IDXD_H_ #define _USR_IDXD_H_ diff --git a/include/uapi/rdma/irdma-abi.h b/include/uapi/rdma/irdma-abi.h index 26b638a7ad97..a7085e092d34 100644 --- a/include/uapi/rdma/irdma-abi.h +++ b/include/uapi/rdma/irdma-abi.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */ +/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB */ /* * Copyright (c) 2006 - 2021 Intel Corporation. All rights reserved. * Copyright (c) 2005 Topspin Communications. All rights reserved. diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9b1577498373..b1a5fc04492b 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -32,6 +32,8 @@ #include <linux/perf_event.h> #include <linux/extable.h> #include <linux/log2.h> + +#include <asm/barrier.h> #include <asm/unaligned.h> /* Registers */ @@ -1377,6 +1379,7 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) /* Non-UAPI available opcodes. */ [BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS, [BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL, + [BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC, [BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B, [BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H, [BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W, @@ -1621,7 +1624,21 @@ out: COND_JMP(s, JSGE, >=) COND_JMP(s, JSLE, <=) #undef COND_JMP - /* STX and ST and LDX*/ + /* ST, STX and LDX*/ + ST_NOSPEC: + /* Speculation barrier for mitigating Speculative Store Bypass. + * In case of arm64, we rely on the firmware mitigation as + * controlled via the ssbd kernel parameter. Whenever the + * mitigation is enabled, it works for all of the kernel code + * with no need to provide any additional instructions here. + * In case of x86, we use 'lfence' insn for mitigation. We + * reuse preexisting logic from Spectre v1 mitigation that + * happens to produce the required code on x86 for v4 as well. + */ +#ifdef CONFIG_X86 + barrier_nospec(); +#endif + CONT; #define LDST(SIZEOP, SIZE) \ STX_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \ diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index bbfc6bb79240..ca3cd9aaa6ce 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -206,15 +206,17 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, verbose(cbs->private_data, "BUG_%02x\n", insn->code); } } else if (class == BPF_ST) { - if (BPF_MODE(insn->code) != BPF_MEM) { + if (BPF_MODE(insn->code) == BPF_MEM) { + verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->imm); + } else if (BPF_MODE(insn->code) == 0xc0 /* BPF_NOSPEC, no UAPI */) { + verbose(cbs->private_data, "(%02x) nospec\n", insn->code); + } else { verbose(cbs->private_data, "BUG_st_%02x\n", insn->code); - return; } - verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->dst_reg, - insn->off, insn->imm); } else if (class == BPF_LDX) { if (BPF_MODE(insn->code) != BPF_MEM) { verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9de3c9c3267c..f9bda5476ea5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2610,6 +2610,19 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, cur = env->cur_state->frame[env->cur_state->curframe]; if (value_regno >= 0) reg = &cur->regs[value_regno]; + if (!env->bypass_spec_v4) { + bool sanitize = reg && is_spillable_regtype(reg->type); + + for (i = 0; i < size; i++) { + if (state->stack[spi].slot_type[i] == STACK_INVALID) { + sanitize = true; + break; + } + } + + if (sanitize) + env->insn_aux_data[insn_idx].sanitize_stack_spill = true; + } if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) && !register_is_null(reg) && env->bpf_capable) { @@ -2632,47 +2645,10 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, verbose(env, "invalid size of register spill\n"); return -EACCES; } - if (state != cur && reg->type == PTR_TO_STACK) { verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } - - if (!env->bypass_spec_v4) { - bool sanitize = false; - - if (state->stack[spi].slot_type[0] == STACK_SPILL && - register_is_const(&state->stack[spi].spilled_ptr)) - sanitize = true; - for (i = 0; i < BPF_REG_SIZE; i++) - if (state->stack[spi].slot_type[i] == STACK_MISC) { - sanitize = true; - break; - } - if (sanitize) { - int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off; - int soff = (-spi - 1) * BPF_REG_SIZE; - - /* detected reuse of integer stack slot with a pointer - * which means either llvm is reusing stack slot or - * an attacker is trying to exploit CVE-2018-3639 - * (speculative store bypass) - * Have to sanitize that slot with preemptive - * store of zero. - */ - if (*poff && *poff != soff) { - /* disallow programs where single insn stores - * into two different stack slots, since verifier - * cannot sanitize them - */ - verbose(env, - "insn %d cannot access two stack slots fp%d and fp%d", - insn_idx, *poff, soff); - return -EINVAL; - } - *poff = soff; - } - } save_register_state(state, spi, reg); } else { u8 type = STACK_MISC; @@ -6561,6 +6537,12 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0; alu_state |= ptr_is_dst_reg ? BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST; + + /* Limit pruning on unknown scalars to enable deep search for + * potential masking differences from other program paths. + */ + if (!off_is_imm) + env->explore_alu_limits = true; } err = update_alu_sanitation_state(aux, alu_state, alu_limit); @@ -9936,8 +9918,8 @@ next: } /* Returns true if (rold safe implies rcur safe) */ -static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, - struct bpf_id_pair *idmap) +static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, + struct bpf_reg_state *rcur, struct bpf_id_pair *idmap) { bool equal; @@ -9963,6 +9945,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return false; switch (rold->type) { case SCALAR_VALUE: + if (env->explore_alu_limits) + return false; if (rcur->type == SCALAR_VALUE) { if (!rold->precise && !rcur->precise) return true; @@ -10053,9 +10037,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return false; } -static bool stacksafe(struct bpf_func_state *old, - struct bpf_func_state *cur, - struct bpf_id_pair *idmap) +static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, + struct bpf_func_state *cur, struct bpf_id_pair *idmap) { int i, spi; @@ -10100,9 +10083,8 @@ static bool stacksafe(struct bpf_func_state *old, continue; if (old->stack[spi].slot_type[0] != STACK_SPILL) continue; - if (!regsafe(&old->stack[spi].spilled_ptr, - &cur->stack[spi].spilled_ptr, - idmap)) + if (!regsafe(env, &old->stack[spi].spilled_ptr, + &cur->stack[spi].spilled_ptr, idmap)) /* when explored and current stack slot are both storing * spilled registers, check that stored pointers types * are the same as well. @@ -10159,10 +10141,11 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch)); for (i = 0; i < MAX_BPF_REG; i++) - if (!regsafe(&old->regs[i], &cur->regs[i], env->idmap_scratch)) + if (!regsafe(env, &old->regs[i], &cur->regs[i], + env->idmap_scratch)) return false; - if (!stacksafe(old, cur, env->idmap_scratch)) + if (!stacksafe(env, old, cur, env->idmap_scratch)) return false; if (!refsafe(old, cur)) @@ -11906,35 +11889,33 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) for (i = 0; i < insn_cnt; i++, insn++) { bpf_convert_ctx_access_t convert_ctx_access; + bool ctx_access; if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) || insn->code == (BPF_LDX | BPF_MEM | BPF_H) || insn->code == (BPF_LDX | BPF_MEM | BPF_W) || - insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) + insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) { type = BPF_READ; - else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) || - insn->code == (BPF_STX | BPF_MEM | BPF_H) || - insn->code == (BPF_STX | BPF_MEM | BPF_W) || - insn->code == (BPF_STX | BPF_MEM | BPF_DW)) + ctx_access = true; + } else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) || + insn->code == (BPF_STX | BPF_MEM | BPF_H) || + insn->code == (BPF_STX | BPF_MEM | BPF_W) || + insn->code == (BPF_STX | BPF_MEM | BPF_DW) || + insn->code == (BPF_ST | BPF_MEM | BPF_B) || + insn->code == (BPF_ST | BPF_MEM | BPF_H) || + insn->code == (BPF_ST | BPF_MEM | BPF_W) || + insn->code == (BPF_ST | BPF_MEM | BPF_DW)) { type = BPF_WRITE; - else + ctx_access = BPF_CLASS(insn->code) == BPF_STX; + } else { continue; + } if (type == BPF_WRITE && - env->insn_aux_data[i + delta].sanitize_stack_off) { + env->insn_aux_data[i + delta].sanitize_stack_spill) { struct bpf_insn patch[] = { - /* Sanitize suspicious stack slot with zero. - * There are no memory dependencies for this store, - * since it's only using frame pointer and immediate - * constant of zero - */ - BPF_ST_MEM(BPF_DW, BPF_REG_FP, - env->insn_aux_data[i + delta].sanitize_stack_off, - 0), - /* the original STX instruction will immediately - * overwrite the same stack slot with appropriate value - */ *insn, + BPF_ST_NOSPEC(), }; cnt = ARRAY_SIZE(patch); @@ -11948,6 +11929,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) continue; } + if (!ctx_access) + continue; + switch (env->insn_aux_data[i + delta].ptr_type) { case PTR_TO_CTX: if (!ops->convert_ctx_access) @@ -12752,37 +12736,6 @@ static void free_states(struct bpf_verifier_env *env) } } -/* The verifier is using insn_aux_data[] to store temporary data during - * verification and to store information for passes that run after the - * verification like dead code sanitization. do_check_common() for subprogram N - * may analyze many other subprograms. sanitize_insn_aux_data() clears all - * temporary data after do_check_common() finds that subprogram N cannot be - * verified independently. pass_cnt counts the number of times - * do_check_common() was run and insn->aux->seen tells the pass number - * insn_aux_data was touched. These variables are compared to clear temporary - * data from failed pass. For testing and experiments do_check_common() can be - * run multiple times even when prior attempt to verify is unsuccessful. - * - * Note that special handling is needed on !env->bypass_spec_v1 if this is - * ever called outside of error path with subsequent program rejection. - */ -static void sanitize_insn_aux_data(struct bpf_verifier_env *env) -{ - struct bpf_insn *insn = env->prog->insnsi; - struct bpf_insn_aux_data *aux; - int i, class; - - for (i = 0; i < env->prog->len; i++) { - class = BPF_CLASS(insn[i].code); - if (class != BPF_LDX && class != BPF_STX) - continue; - aux = &env->insn_aux_data[i]; - if (aux->seen != env->pass_cnt) - continue; - memset(aux, 0, offsetof(typeof(*aux), orig_idx)); - } -} - static int do_check_common(struct bpf_verifier_env *env, int subprog) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); @@ -12859,9 +12812,6 @@ out: if (!ret && pop_log) bpf_vlog_reset(&env->log, 0); free_states(env); - if (ret) - /* clean aux data in case subprog was rejected */ - sanitize_insn_aux_data(env); return ret; } diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 8d6bf56ed77a..de2c432dee20 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -1221,9 +1221,7 @@ int cgroup1_get_tree(struct fs_context *fc) ret = cgroup_do_get_tree(fc); if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) { - struct super_block *sb = fc->root->d_sb; - dput(fc->root); - deactivate_locked_super(sb); + fc_drop_locked(fc); ret = 1; } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 50142fc08902..f148eacda55a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3676,15 +3676,21 @@ static void pwq_unbound_release_workfn(struct work_struct *work) unbound_release_work); struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; - bool is_last; + bool is_last = false; - if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) - return; + /* + * when @pwq is not linked, it doesn't hold any reference to the + * @wq, and @wq is invalid to access. + */ + if (!list_empty(&pwq->pwqs_node)) { + if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) + return; - mutex_lock(&wq->mutex); - list_del_rcu(&pwq->pwqs_node); - is_last = list_empty(&wq->pwqs); - mutex_unlock(&wq->mutex); + mutex_lock(&wq->mutex); + list_del_rcu(&pwq->pwqs_node); + is_last = list_empty(&wq->pwqs); + mutex_unlock(&wq->mutex); + } mutex_lock(&wq_pool_mutex); put_unbound_pool(pool); diff --git a/lib/Kconfig b/lib/Kconfig index d241fe476fda..5c9c0687f76d 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -683,9 +683,6 @@ config PARMAN config OBJAGG tristate "objagg" if COMPILE_TEST -config STRING_SELFTEST - tristate "Test string functions" - endmenu config GENERIC_IOREMAP diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 831212722924..5ddd575159fb 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2180,6 +2180,9 @@ config ASYNC_RAID6_TEST config TEST_HEXDUMP tristate "Test functions located in the hexdump module at runtime" +config STRING_SELFTEST + tristate "Test string functions at runtime" + config TEST_STRING_HELPERS tristate "Test functions located in the string_helpers module at runtime" diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ae1f5d0cb581..eb8e87c4833f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3574,7 +3574,8 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) unsigned long val; if (mem_cgroup_is_root(memcg)) { - cgroup_rstat_flush(memcg->css.cgroup); + /* mem_cgroup_threshold() calls here from irqsafe context */ + cgroup_rstat_flush_irqsafe(memcg->css.cgroup); val = memcg_page_state(memcg, NR_FILE_PAGES) + memcg_page_state(memcg, NR_ANON_MAPPED); if (swap) diff --git a/mm/migrate.c b/mm/migrate.c index 34a9ad3e0a4f..7e240437e7d9 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2068,7 +2068,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, LIST_HEAD(migratepages); new_page_t *new; bool compound; - unsigned int nr_pages = thp_nr_pages(page); + int nr_pages = thp_nr_pages(page); /* * PTE mapped THP or HugeTLB page can't reach here so the page could diff --git a/mm/slab.h b/mm/slab.h index f997fd5e42c8..58c01a34e5b8 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -346,7 +346,7 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig, continue; page = virt_to_head_page(p[i]); - objcgs = page_objcgs(page); + objcgs = page_objcgs_check(page); if (!objcgs) continue; diff --git a/mm/slub.c b/mm/slub.c index 090fa14628f9..af984e4990e8 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3236,6 +3236,16 @@ struct detached_freelist { struct kmem_cache *s; }; +static inline void free_nonslab_page(struct page *page) +{ + unsigned int order = compound_order(page); + + VM_BUG_ON_PAGE(!PageCompound(page), page); + kfree_hook(page_address(page)); + mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, -(PAGE_SIZE << order)); + __free_pages(page, order); +} + /* * This function progressively scans the array with free objects (with * a limited look ahead) and extract objects belonging to the same @@ -3272,9 +3282,7 @@ int build_detached_freelist(struct kmem_cache *s, size_t size, if (!s) { /* Handle kalloc'ed objects */ if (unlikely(!PageSlab(page))) { - BUG_ON(!PageCompound(page)); - kfree_hook(object); - __free_pages(page, compound_order(page)); + free_nonslab_page(page); p[size] = NULL; /* mark object processed */ return size; } @@ -4250,13 +4258,7 @@ void kfree(const void *x) page = virt_to_head_page(x); if (unlikely(!PageSlab(page))) { - unsigned int order = compound_order(page); - - BUG_ON(!PageCompound(page)); - kfree_hook(object); - mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, - -(PAGE_SIZE << order)); - __free_pages(page, order); + free_nonslab_page(page); return; } slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index c3946c355882..bdc95bd7a851 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1075,11 +1075,16 @@ static bool j1939_session_deactivate_locked(struct j1939_session *session) static bool j1939_session_deactivate(struct j1939_session *session) { + struct j1939_priv *priv = session->priv; bool active; - j1939_session_list_lock(session->priv); + j1939_session_list_lock(priv); + /* This function should be called with a session ref-count of at + * least 2. + */ + WARN_ON_ONCE(kref_read(&session->kref) < 2); active = j1939_session_deactivate_locked(session); - j1939_session_list_unlock(session->priv); + j1939_session_list_unlock(priv); return active; } @@ -1869,7 +1874,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, if (!session->transmission) j1939_tp_schedule_txtimer(session, 0); } else { - j1939_tp_set_rxtimeout(session, 250); + j1939_tp_set_rxtimeout(session, 750); } session->last_cmd = 0xff; consume_skb(se_skb); diff --git a/net/can/raw.c b/net/can/raw.c index ed4fcb7ab0c3..cd5a49380116 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -546,10 +546,18 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, return -EFAULT; } + rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) + if (ro->bound && ro->ifindex) { dev = dev_get_by_index(sock_net(sk), ro->ifindex); + if (!dev) { + if (count > 1) + kfree(filter); + err = -ENODEV; + goto out_fil; + } + } if (ro->bound) { /* (try to) register the new filters */ @@ -588,6 +596,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, dev_put(dev); release_sock(sk); + rtnl_unlock(); break; @@ -600,10 +609,16 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, err_mask &= CAN_ERR_MASK; + rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) + if (ro->bound && ro->ifindex) { dev = dev_get_by_index(sock_net(sk), ro->ifindex); + if (!dev) { + err = -ENODEV; + goto out_err; + } + } /* remove current error mask */ if (ro->bound) { @@ -627,6 +642,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, dev_put(dev); release_sock(sk); + rtnl_unlock(); break; diff --git a/net/core/devlink.c b/net/core/devlink.c index 8fdd04f00fd7..85032626de24 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -9328,18 +9328,10 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, switch (attrs->flavour) { case DEVLINK_PORT_FLAVOUR_PHYSICAL: - case DEVLINK_PORT_FLAVOUR_VIRTUAL: n = snprintf(name, len, "p%u", attrs->phys.port_number); if (n < len && attrs->split) n += snprintf(name + n, len - n, "s%u", attrs->phys.split_subport_number); - if (!attrs->split) - n = snprintf(name, len, "p%u", attrs->phys.port_number); - else - n = snprintf(name, len, "p%us%u", - attrs->phys.port_number, - attrs->phys.split_subport_number); - break; case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: @@ -9381,6 +9373,8 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, attrs->pci_sf.sf); break; + case DEVLINK_PORT_FLAVOUR_VIRTUAL: + return -EOPNOTSUPP; } if (n >= len) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 2aadbfc5193b..4b2415d34873 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1504,7 +1504,7 @@ __be32 flow_get_u32_dst(const struct flow_keys *flow) } EXPORT_SYMBOL(flow_get_u32_dst); -/* Sort the source and destination IP (and the ports if the IP are the same), +/* Sort the source and destination IP and the ports, * to have consistent hash within the two directions */ static inline void __flow_hash_consistentify(struct flow_keys *keys) @@ -1515,11 +1515,11 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys) case FLOW_DISSECTOR_KEY_IPV4_ADDRS: addr_diff = (__force u32)keys->addrs.v4addrs.dst - (__force u32)keys->addrs.v4addrs.src; - if ((addr_diff < 0) || - (addr_diff == 0 && - ((__force u16)keys->ports.dst < - (__force u16)keys->ports.src))) { + if (addr_diff < 0) swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst); + + if ((__force u16)keys->ports.dst < + (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; @@ -1527,13 +1527,13 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys) addr_diff = memcmp(&keys->addrs.v6addrs.dst, &keys->addrs.v6addrs.src, sizeof(keys->addrs.v6addrs.dst)); - if ((addr_diff < 0) || - (addr_diff == 0 && - ((__force u16)keys->ports.dst < - (__force u16)keys->ports.src))) { + if (addr_diff < 0) { for (i = 0; i < 4; i++) swap(keys->addrs.v6addrs.src.s6_addr32[i], keys->addrs.v6addrs.dst.s6_addr32[i]); + } + if ((__force u16)keys->ports.dst < + (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 15d71288e741..2d6249b28928 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -584,29 +584,42 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, return sk_psock_skb_ingress(psock, skb); } -static void sock_drop(struct sock *sk, struct sk_buff *skb) +static void sk_psock_skb_state(struct sk_psock *psock, + struct sk_psock_work_state *state, + struct sk_buff *skb, + int len, int off) { - sk_drops_add(sk, skb); - kfree_skb(skb); + spin_lock_bh(&psock->ingress_lock); + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { + state->skb = skb; + state->len = len; + state->off = off; + } else { + sock_drop(psock->sk, skb); + } + spin_unlock_bh(&psock->ingress_lock); } static void sk_psock_backlog(struct work_struct *work) { struct sk_psock *psock = container_of(work, struct sk_psock, work); struct sk_psock_work_state *state = &psock->work_state; - struct sk_buff *skb; + struct sk_buff *skb = NULL; bool ingress; u32 len, off; int ret; mutex_lock(&psock->work_mutex); - if (state->skb) { + if (unlikely(state->skb)) { + spin_lock_bh(&psock->ingress_lock); skb = state->skb; len = state->len; off = state->off; state->skb = NULL; - goto start; + spin_unlock_bh(&psock->ingress_lock); } + if (skb) + goto start; while ((skb = skb_dequeue(&psock->ingress_skb))) { len = skb->len; @@ -621,9 +634,8 @@ start: len, ingress); if (ret <= 0) { if (ret == -EAGAIN) { - state->skb = skb; - state->len = len; - state->off = off; + sk_psock_skb_state(psock, state, skb, + len, off); goto end; } /* Hard errors break pipe and stop xmit. */ @@ -722,6 +734,11 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock) skb_bpf_redirect_clear(skb); sock_drop(psock->sk, skb); } + kfree_skb(psock->work_state.skb); + /* We null the skb here to ensure that calls to sk_psock_backlog + * do not pick up the free'd skb. + */ + psock->work_state.skb = NULL; __sk_psock_purge_ingress_msg(psock); } @@ -773,8 +790,6 @@ static void sk_psock_destroy(struct work_struct *work) void sk_psock_drop(struct sock *sk, struct sk_psock *psock) { - sk_psock_stop(psock, false); - write_lock_bh(&sk->sk_callback_lock); sk_psock_restore_proto(sk, psock); rcu_assign_sk_user_data(sk, NULL); @@ -784,6 +799,8 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock) sk_psock_stop_verdict(sk, psock); write_unlock_bh(&sk->sk_callback_lock); + sk_psock_stop(psock, false); + INIT_RCU_WORK(&psock->rwork, sk_psock_destroy); queue_rcu_work(system_wq, &psock->rwork); } diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 0dca00745ac3..be75b409445c 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -390,7 +390,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, tunnel->i_seqno = ntohl(tpi->seq) + 1; } - skb_reset_network_header(skb); + skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e1b9f7ac8bad..8e6ca9ad6812 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -549,9 +549,10 @@ int ip6_forward(struct sk_buff *skb) if (net->ipv6.devconf_all->proxy_ndp && pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) { int proxied = ip6_forward_proxy_check(skb); - if (proxied > 0) + if (proxied > 0) { + hdr->hop_limit--; return ip6_input(skb); - else if (proxied < 0) { + } else if (proxied < 0) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 7180979114e4..ac5cadd02cfa 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -98,8 +98,16 @@ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr) { u8 rc = LLC_PDU_LEN_U; - if (addr->sllc_test || addr->sllc_xid) + if (addr->sllc_test) rc = LLC_PDU_LEN_U; + else if (addr->sllc_xid) + /* We need to expand header to sizeof(struct llc_xid_info) + * since llc_pdu_init_as_xid_cmd() sets 4,5,6 bytes of LLC header + * as XID PDU. In llc_ui_sendmsg() we reserved header size and then + * filled all other space with user data. If we won't reserve this + * bytes, llc_pdu_init_as_xid_cmd() will overwrite user data + */ + rc = LLC_PDU_LEN_U_XID; else if (sk->sk_type == SOCK_STREAM) rc = LLC_PDU_LEN_I; return rc; diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c index b554f26c68ee..79d1cef8f15a 100644 --- a/net/llc/llc_s_ac.c +++ b/net/llc/llc_s_ac.c @@ -79,7 +79,7 @@ int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb) struct llc_sap_state_ev *ev = llc_sap_ev(skb); int rc; - llc_pdu_header_init(skb, LLC_PDU_TYPE_U, ev->saddr.lsap, + llc_pdu_header_init(skb, LLC_PDU_TYPE_U_XID, ev->saddr.lsap, ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 84cc7733ea66..4e6f11e63df3 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -152,6 +152,8 @@ static int ieee80211_change_iface(struct wiphy *wiphy, struct vif_params *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; int ret; ret = ieee80211_if_change_type(sdata, type); @@ -162,7 +164,24 @@ static int ieee80211_change_iface(struct wiphy *wiphy, RCU_INIT_POINTER(sdata->u.vlan.sta, NULL); ieee80211_check_fast_rx_iface(sdata); } else if (type == NL80211_IFTYPE_STATION && params->use_4addr >= 0) { + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + + if (params->use_4addr == ifmgd->use_4addr) + return 0; + sdata->u.mgd.use_4addr = params->use_4addr; + if (!ifmgd->associated) + return 0; + + mutex_lock(&local->sta_mtx); + sta = sta_info_get(sdata, ifmgd->bssid); + if (sta) + drv_sta_set_4addr(local, sdata, &sta->sta, + params->use_4addr); + mutex_unlock(&local->sta_mtx); + + if (params->use_4addr) + ieee80211_send_4addr_nullfunc(local, sdata); } if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 22549b95d1aa..30ce6d2ec7ce 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -2201,6 +2201,8 @@ void ieee80211_dynamic_ps_timer(struct timer_list *t); void ieee80211_send_nullfunc(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, bool powersave); +void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata); void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata, struct ieee80211_hdr *hdr, bool ack, u16 tx_time); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index a00f11a33699..c0ea3b1aa9e1 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1095,8 +1095,8 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local, ieee80211_tx_skb(sdata, skb); } -static void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata) +void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) { struct sk_buff *skb; struct ieee80211_hdr *nullfunc; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 771921c057e8..2563473b5cf1 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -730,7 +730,8 @@ ieee80211_make_monitor_skb(struct ieee80211_local *local, * Need to make a copy and possibly remove radiotap header * and FCS from the original. */ - skb = skb_copy_expand(*origskb, needed_headroom, 0, GFP_ATOMIC); + skb = skb_copy_expand(*origskb, needed_headroom + NET_SKB_PAD, + 0, GFP_ATOMIC); if (!skb) return NULL; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index e96981144358..8509778ff31f 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1147,6 +1147,29 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx, return queued; } +static void +ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + struct sk_buff *skb) +{ + struct rate_control_ref *ref = sdata->local->rate_ctrl; + u16 tid; + + if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER)) + return; + + if (!sta || !sta->sta.ht_cap.ht_supported || + !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO || + skb->protocol == sdata->control_port_protocol) + return; + + tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; + if (likely(sta->ampdu_mlme.tid_tx[tid])) + return; + + ieee80211_start_tx_ba_session(&sta->sta, tid, 0); +} + /* * initialises @tx * pass %NULL for the station if unknown, a valid pointer if known @@ -1160,6 +1183,7 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct ieee80211_hdr *hdr; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + bool aggr_check = false; int tid; memset(tx, 0, sizeof(*tx)); @@ -1188,8 +1212,10 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, } else if (tx->sdata->control_port_protocol == tx->skb->protocol) { tx->sta = sta_info_get_bss(sdata, hdr->addr1); } - if (!tx->sta && !is_multicast_ether_addr(hdr->addr1)) + if (!tx->sta && !is_multicast_ether_addr(hdr->addr1)) { tx->sta = sta_info_get(sdata, hdr->addr1); + aggr_check = true; + } } if (tx->sta && ieee80211_is_data_qos(hdr->frame_control) && @@ -1199,8 +1225,12 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, struct tid_ampdu_tx *tid_tx; tid = ieee80211_get_tid(hdr); - tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]); + if (!tid_tx && aggr_check) { + ieee80211_aggr_check(sdata, tx->sta, skb); + tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]); + } + if (tid_tx) { bool queued; @@ -4120,29 +4150,6 @@ void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) } EXPORT_SYMBOL(ieee80211_txq_schedule_start); -static void -ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata, - struct sta_info *sta, - struct sk_buff *skb) -{ - struct rate_control_ref *ref = sdata->local->rate_ctrl; - u16 tid; - - if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER)) - return; - - if (!sta || !sta->sta.ht_cap.ht_supported || - !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO || - skb->protocol == sdata->control_port_protocol) - return; - - tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; - if (likely(sta->ampdu_mlme.tid_tx[tid])) - return; - - ieee80211_start_tx_ba_session(&sta->sta, tid, 0); -} - void __ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev, u32 info_flags, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 83c52df85870..5c03e5106751 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -670,8 +670,13 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report) return false; tstamp = nf_conn_tstamp_find(ct); - if (tstamp && tstamp->stop == 0) + if (tstamp) { + s32 timeout = ct->timeout - nfct_time_stamp; + tstamp->stop = ktime_get_real_ns(); + if (timeout < 0) + tstamp->stop -= jiffies_to_nsecs(-timeout); + } if (nf_conntrack_event_report(IPCT_DESTROY, ct, portid, report) < 0) { diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 1e50908b1b7e..551976e4284c 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -331,7 +331,11 @@ EXPORT_SYMBOL_GPL(flow_offload_add); void flow_offload_refresh(struct nf_flowtable *flow_table, struct flow_offload *flow) { - flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); + u32 timeout; + + timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); + if (READ_ONCE(flow->timeout) != timeout) + WRITE_ONCE(flow->timeout, timeout); if (likely(!nf_flowtable_hw_offload(flow_table))) return; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index de182d1f7c4e..081437dd75b7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8445,6 +8445,16 @@ static int nf_tables_commit_audit_alloc(struct list_head *adl, return 0; } +static void nf_tables_commit_audit_free(struct list_head *adl) +{ + struct nft_audit_data *adp, *adn; + + list_for_each_entry_safe(adp, adn, adl, list) { + list_del(&adp->list); + kfree(adp); + } +} + static void nf_tables_commit_audit_collect(struct list_head *adl, struct nft_table *table, u32 op) { @@ -8509,6 +8519,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) ret = nf_tables_commit_audit_alloc(&adl, trans->ctx.table); if (ret) { nf_tables_commit_chain_prepare_cancel(net); + nf_tables_commit_audit_free(&adl); return ret; } if (trans->msg_type == NFT_MSG_NEWRULE || @@ -8518,6 +8529,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) ret = nf_tables_commit_chain_prepare(net, chain); if (ret < 0) { nf_tables_commit_chain_prepare_cancel(net); + nf_tables_commit_audit_free(&adl); return ret; } } diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index 50b4e3c9347a..202f57d17bab 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -174,7 +174,9 @@ static const struct nf_hook_entries * nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev) { const struct nf_hook_entries *hook_head = NULL; +#ifdef CONFIG_NETFILTER_INGRESS struct net_device *netdev; +#endif switch (pf) { case NFPROTO_IPV4: diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index 8088b99f2ee3..304e33cbed9b 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -48,24 +48,30 @@ static void nft_last_eval(const struct nft_expr *expr, { struct nft_last_priv *priv = nft_expr_priv(expr); - priv->last_jiffies = jiffies; - priv->last_set = 1; + if (READ_ONCE(priv->last_jiffies) != jiffies) + WRITE_ONCE(priv->last_jiffies, jiffies); + if (READ_ONCE(priv->last_set) == 0) + WRITE_ONCE(priv->last_set, 1); } static int nft_last_dump(struct sk_buff *skb, const struct nft_expr *expr) { struct nft_last_priv *priv = nft_expr_priv(expr); + unsigned long last_jiffies = READ_ONCE(priv->last_jiffies); + u32 last_set = READ_ONCE(priv->last_set); __be64 msecs; - if (time_before(jiffies, priv->last_jiffies)) - priv->last_set = 0; + if (time_before(jiffies, last_jiffies)) { + WRITE_ONCE(priv->last_set, 0); + last_set = 0; + } - if (priv->last_set) - msecs = nf_jiffies64_to_msecs(jiffies - priv->last_jiffies); + if (last_set) + msecs = nf_jiffies64_to_msecs(jiffies - last_jiffies); else msecs = 0; - if (nla_put_be32(skb, NFTA_LAST_SET, htonl(priv->last_set)) || + if (nla_put_be32(skb, NFTA_LAST_SET, htonl(last_set)) || nla_put_be64(skb, NFTA_LAST_MSECS, msecs, NFTA_LAST_PAD)) goto nla_put_failure; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 0840c635b752..be1595d6979d 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -201,7 +201,9 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, alen = sizeof_field(struct nf_nat_range, min_addr.ip6); break; default: - return -EAFNOSUPPORT; + if (tb[NFTA_NAT_REG_ADDR_MIN]) + return -EAFNOSUPPORT; + break; } priv->family = family; diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index e6f4a6202f82..171b7f3be6ef 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -518,8 +518,10 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (!ipc) goto err; - if (sock_queue_rcv_skb(&ipc->sk, skb)) + if (sock_queue_rcv_skb(&ipc->sk, skb)) { + qrtr_port_put(ipc); goto err; + } qrtr_port_put(ipc); } @@ -839,6 +841,8 @@ static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb, ipc = qrtr_port_lookup(to->sq_port); if (!ipc || &ipc->sk == skb->sk) { /* do not send to self */ + if (ipc) + qrtr_port_put(ipc); kfree_skb(skb); return -ENODEV; } diff --git a/net/sctp/input.c b/net/sctp/input.c index eb3c2a34a31c..5ef86fdb1176 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -1203,7 +1203,7 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( if (unlikely(!af)) return NULL; - if (af->from_addr_param(&paddr, param, peer_port, 0)) + if (!af->from_addr_param(&paddr, param, peer_port, 0)) return NULL; return __sctp_lookup_association(net, laddr, &paddr, transportp); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e48dd909dee5..470dbdc27d58 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -100,8 +100,9 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, list_for_each_entry_safe(addr, temp, &net->sctp.local_addr_list, list) { if (addr->a.sa.sa_family == AF_INET6 && - ipv6_addr_equal(&addr->a.v6.sin6_addr, - &ifa->addr)) { + ipv6_addr_equal(&addr->a.v6.sin6_addr, + &ifa->addr) && + addr->a.v6.sin6_scope_id == ifa->idev->dev->ifindex) { sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL); found = 1; addr->valid = 0; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 09a8f23ec709..32df65f68c12 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1109,12 +1109,12 @@ enum sctp_disposition sctp_sf_send_probe(struct net *net, if (!sctp_transport_pl_enabled(transport)) return SCTP_DISPOSITION_CONSUME; - sctp_transport_pl_send(transport); - - reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size); - if (!reply) - return SCTP_DISPOSITION_NOMEM; - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); + if (sctp_transport_pl_send(transport)) { + reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size); + if (!reply) + return SCTP_DISPOSITION_NOMEM; + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); + } sctp_add_cmd_sf(commands, SCTP_CMD_PROBE_TIMER_UPDATE, SCTP_TRANSPORT(transport)); @@ -1274,8 +1274,7 @@ enum sctp_disposition sctp_sf_backbeat_8_3(struct net *net, !sctp_transport_pl_enabled(link)) return SCTP_DISPOSITION_DISCARD; - sctp_transport_pl_recv(link); - if (link->pl.state == SCTP_PL_COMPLETE) + if (sctp_transport_pl_recv(link)) return SCTP_DISPOSITION_CONSUME; return sctp_sf_send_probe(net, ep, asoc, type, link, commands); diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 397a6244dd97..a3d3ca6dd63d 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -258,16 +258,13 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) sctp_transport_pl_update(transport); } -void sctp_transport_pl_send(struct sctp_transport *t) +bool sctp_transport_pl_send(struct sctp_transport *t) { - pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", - __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); - - if (t->pl.probe_count < SCTP_MAX_PROBES) { - t->pl.probe_count++; - return; - } + if (t->pl.probe_count < SCTP_MAX_PROBES) + goto out; + t->pl.last_rtx_chunks = t->asoc->rtx_data_chunks; + t->pl.probe_count = 0; if (t->pl.state == SCTP_PL_BASE) { if (t->pl.probe_size == SCTP_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */ t->pl.state = SCTP_PL_ERROR; /* Base -> Error */ @@ -299,14 +296,27 @@ void sctp_transport_pl_send(struct sctp_transport *t) sctp_assoc_sync_pmtu(t->asoc); } } - t->pl.probe_count = 1; + +out: + if (t->pl.state == SCTP_PL_COMPLETE && t->pl.raise_count < 30 && + !t->pl.probe_count && t->pl.last_rtx_chunks == t->asoc->rtx_data_chunks) { + t->pl.raise_count++; + return false; + } + + pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", + __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); + + t->pl.probe_count++; + return true; } -void sctp_transport_pl_recv(struct sctp_transport *t) +bool sctp_transport_pl_recv(struct sctp_transport *t) { pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); + t->pl.last_rtx_chunks = t->asoc->rtx_data_chunks; t->pl.pmtu = t->pl.probe_size; t->pl.probe_count = 0; if (t->pl.state == SCTP_PL_BASE) { @@ -323,7 +333,7 @@ void sctp_transport_pl_recv(struct sctp_transport *t) if (!t->pl.probe_high) { t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP, SCTP_MAX_PLPMTU); - return; + return false; } t->pl.probe_size += SCTP_PL_MIN_STEP; if (t->pl.probe_size >= t->pl.probe_high) { @@ -335,14 +345,13 @@ void sctp_transport_pl_recv(struct sctp_transport *t) t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); sctp_assoc_sync_pmtu(t->asoc); } - } else if (t->pl.state == SCTP_PL_COMPLETE) { - t->pl.raise_count++; - if (t->pl.raise_count == 30) { - /* Raise probe_size again after 30 * interval in Search Complete */ - t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ - t->pl.probe_size += SCTP_PL_MIN_STEP; - } + } else if (t->pl.state == SCTP_PL_COMPLETE && t->pl.raise_count == 30) { + /* Raise probe_size again after 30 * interval in Search Complete */ + t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ + t->pl.probe_size += SCTP_PL_MIN_STEP; } + + return t->pl.state == SCTP_PL_COMPLETE; } static bool sctp_transport_pl_toobig(struct sctp_transport *t, u32 pmtu) diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index e5c43d4d5a75..c9391d38de85 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -898,16 +898,10 @@ static int tipc_aead_decrypt(struct net *net, struct tipc_aead *aead, if (unlikely(!aead)) return -ENOKEY; - /* Cow skb data if needed */ - if (likely(!skb_cloned(skb) && - (!skb_is_nonlinear(skb) || !skb_has_frag_list(skb)))) { - nsg = 1 + skb_shinfo(skb)->nr_frags; - } else { - nsg = skb_cow_data(skb, 0, &unused); - if (unlikely(nsg < 0)) { - pr_err("RX: skb_cow_data() returned %d\n", nsg); - return nsg; - } + nsg = skb_cow_data(skb, 0, &unused); + if (unlikely(nsg < 0)) { + pr_err("RX: skb_cow_data() returned %d\n", nsg); + return nsg; } /* Allocate memory for the AEAD operation */ diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 34a97ea36cc8..75b99b7eda22 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -158,6 +158,7 @@ static void tipc_sk_remove(struct tipc_sock *tsk); static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dsz); static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz); static void tipc_sk_push_backlog(struct tipc_sock *tsk, bool nagle_ack); +static int tipc_wait_for_connect(struct socket *sock, long *timeo_p); static const struct proto_ops packet_ops; static const struct proto_ops stream_ops; @@ -1515,8 +1516,13 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) rc = 0; } - if (unlikely(syn && !rc)) + if (unlikely(syn && !rc)) { tipc_set_sk_state(sk, TIPC_CONNECTING); + if (timeout) { + timeout = msecs_to_jiffies(timeout); + tipc_wait_for_connect(sock, &timeout); + } + } return rc ? rc : dlen; } @@ -1564,7 +1570,7 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen) return -EMSGSIZE; /* Handle implicit connection setup */ - if (unlikely(dest)) { + if (unlikely(dest && sk->sk_state == TIPC_OPEN)) { rc = __tipc_sendmsg(sock, m, dlen); if (dlen && dlen == rc) { tsk->peer_caps = tipc_node_get_capabilities(net, dnode); @@ -2646,7 +2652,7 @@ static int tipc_listen(struct socket *sock, int len) static int tipc_wait_for_accept(struct socket *sock, long timeo) { struct sock *sk = sock->sk; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); int err; /* True wake-one mechanism for incoming connections: only @@ -2655,12 +2661,12 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) * anymore, the common case will execute the loop only once. */ for (;;) { - prepare_to_wait_exclusive(sk_sleep(sk), &wait, - TASK_INTERRUPTIBLE); if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { + add_wait_queue(sk_sleep(sk), &wait); release_sock(sk); - timeo = schedule_timeout(timeo); + timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); + remove_wait_queue(sk_sleep(sk), &wait); } err = 0; if (!skb_queue_empty(&sk->sk_receive_queue)) @@ -2672,7 +2678,6 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) if (signal_pending(current)) break; } - finish_wait(sk_sleep(sk), &wait); return err; } @@ -2689,9 +2694,10 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, bool kern) { struct sock *new_sk, *sk = sock->sk; - struct sk_buff *buf; struct tipc_sock *new_tsock; + struct msghdr m = {NULL,}; struct tipc_msg *msg; + struct sk_buff *buf; long timeo; int res; @@ -2737,19 +2743,17 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, } /* - * Respond to 'SYN-' by discarding it & returning 'ACK'-. - * Respond to 'SYN+' by queuing it on new socket. + * Respond to 'SYN-' by discarding it & returning 'ACK'. + * Respond to 'SYN+' by queuing it on new socket & returning 'ACK'. */ if (!msg_data_sz(msg)) { - struct msghdr m = {NULL,}; - tsk_advance_rx_queue(sk); - __tipc_sendstream(new_sock, &m, 0); } else { __skb_dequeue(&sk->sk_receive_queue); __skb_queue_head(&new_sk->sk_receive_queue, buf); skb_set_owner_r(buf, new_sk); } + __tipc_sendstream(new_sock, &m, 0); release_sock(new_sk); exit: release_sock(sk); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 23c92ad15c61..ba7ced947e51 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1526,6 +1526,53 @@ out: return err; } +static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + scm->fp = scm_fp_dup(UNIXCB(skb).fp); + + /* + * Garbage collection of unix sockets starts by selecting a set of + * candidate sockets which have reference only from being in flight + * (total_refs == inflight_refs). This condition is checked once during + * the candidate collection phase, and candidates are marked as such, so + * that non-candidates can later be ignored. While inflight_refs is + * protected by unix_gc_lock, total_refs (file count) is not, hence this + * is an instantaneous decision. + * + * Once a candidate, however, the socket must not be reinstalled into a + * file descriptor while the garbage collection is in progress. + * + * If the above conditions are met, then the directed graph of + * candidates (*) does not change while unix_gc_lock is held. + * + * Any operations that changes the file count through file descriptors + * (dup, close, sendmsg) does not change the graph since candidates are + * not installed in fds. + * + * Dequeing a candidate via recvmsg would install it into an fd, but + * that takes unix_gc_lock to decrement the inflight count, so it's + * serialized with garbage collection. + * + * MSG_PEEK is special in that it does not change the inflight count, + * yet does install the socket into an fd. The following lock/unlock + * pair is to ensure serialization with garbage collection. It must be + * done between incrementing the file count and installing the file into + * an fd. + * + * If garbage collection starts after the barrier provided by the + * lock/unlock, then it will see the elevated refcount and not mark this + * as a candidate. If a garbage collection is already in progress + * before the file count was incremented, then the lock/unlock pair will + * ensure that garbage collection is finished before progressing to + * installing the fd. + * + * (*) A -> B where B is on the queue of A or B is on the queue of C + * which is on the queue of listening socket A. + */ + spin_lock(&unix_gc_lock); + spin_unlock(&unix_gc_lock); +} + static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) { int err = 0; @@ -2175,7 +2222,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, sk_peek_offset_fwd(sk, size); if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); } err = (flags & MSG_TRUNC) ? skb->len - skip : size; @@ -2418,7 +2465,7 @@ unlock: /* It is questionable, see note in unix_dgram_recvmsg. */ if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); sk_peek_offset_fwd(sk, chunk); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 50eb405b0690..16c88beea48b 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2351,7 +2351,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, goto nla_put_failure; for (band = state->band_start; - band < NUM_NL80211_BANDS; band++) { + band < (state->split ? + NUM_NL80211_BANDS : + NL80211_BAND_60GHZ + 1); + band++) { struct ieee80211_supported_band *sband; /* omit higher bands for ancient software */ diff --git a/net/wireless/scan.c b/net/wireless/scan.c index f03c7ac8e184..7897b1478c3c 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1754,16 +1754,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, * be grouped with this beacon for updates ... */ if (!cfg80211_combine_bsses(rdev, new)) { - kfree(new); + bss_ref_put(rdev, new); goto drop; } } if (rdev->bss_entries >= bss_entries_limit && !cfg80211_bss_expire_oldest(rdev)) { - if (!list_empty(&new->hidden_list)) - list_del(&new->hidden_list); - kfree(new); + bss_ref_put(rdev, new); goto drop; } diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index a3e593ddfafc..2debba4e8a3a 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -1,4 +1,233 @@ { + "map access: known scalar += value_ptr unknown vs const", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_MOV64_IMM(BPF_REG_1, 3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 tried to add from different maps, paths or scalars", + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr const vs unknown", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2), + BPF_MOV64_IMM(BPF_REG_1, 3), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 tried to add from different maps, paths or scalars", + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr const vs const (ne)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2), + BPF_MOV64_IMM(BPF_REG_1, 3), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_MOV64_IMM(BPF_REG_1, 5), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 tried to add from different maps, paths or scalars", + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr const vs const (eq)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2), + BPF_MOV64_IMM(BPF_REG_1, 5), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_MOV64_IMM(BPF_REG_1, 5), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr unknown vs unknown (eq)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr unknown vs unknown (lt)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 tried to add from different maps, paths or scalars", + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr unknown vs unknown (gt)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 tried to add from different maps, paths or scalars", + .result = ACCEPT, + .retval = 1, +}, +{ "map access: known scalar += value_ptr from different maps", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 06a351b4f93b..0709af0144c8 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -38,6 +38,7 @@ /x86_64/xen_vmcall_test /x86_64/xss_msr_test /x86_64/vmx_pmu_msrs_test +/access_tracking_perf_test /demand_paging_test /dirty_log_test /dirty_log_perf_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index b853be2ae3c6..5832f510a16c 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -71,6 +71,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test +TEST_GEN_PROGS_x86_64 += access_tracking_perf_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_perf_test diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index a16c8f05366c..cc898181faab 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -1019,7 +1019,8 @@ static __u64 sve_rejects_set[] = { #define VREGS_SUBLIST \ { "vregs", .regs = vregs, .regs_n = ARRAY_SIZE(vregs), } #define PMU_SUBLIST \ - { "pmu", .regs = pmu_regs, .regs_n = ARRAY_SIZE(pmu_regs), } + { "pmu", .capability = KVM_CAP_ARM_PMU_V3, .feature = KVM_ARM_VCPU_PMU_V3, \ + .regs = pmu_regs, .regs_n = ARRAY_SIZE(pmu_regs), } #define SVE_SUBLIST \ { "sve", .capability = KVM_CAP_ARM_SVE, .feature = KVM_ARM_VCPU_SVE, .finalize = true, \ .regs = sve_regs, .regs_n = ARRAY_SIZE(sve_regs), \ diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c new file mode 100644 index 000000000000..e2baa187a21e --- /dev/null +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -0,0 +1,429 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * access_tracking_perf_test + * + * Copyright (C) 2021, Google, Inc. + * + * This test measures the performance effects of KVM's access tracking. + * Access tracking is driven by the MMU notifiers test_young, clear_young, and + * clear_flush_young. These notifiers do not have a direct userspace API, + * however the clear_young notifier can be triggered by marking a pages as idle + * in /sys/kernel/mm/page_idle/bitmap. This test leverages that mechanism to + * enable access tracking on guest memory. + * + * To measure performance this test runs a VM with a configurable number of + * vCPUs that each touch every page in disjoint regions of memory. Performance + * is measured in the time it takes all vCPUs to finish touching their + * predefined region. + * + * Note that a deterministic correctness test of access tracking is not possible + * by using page_idle as it exists today. This is for a few reasons: + * + * 1. page_idle only issues clear_young notifiers, which lack a TLB flush. This + * means subsequent guest accesses are not guaranteed to see page table + * updates made by KVM until some time in the future. + * + * 2. page_idle only operates on LRU pages. Newly allocated pages are not + * immediately allocated to LRU lists. Instead they are held in a "pagevec", + * which is drained to LRU lists some time in the future. There is no + * userspace API to force this drain to occur. + * + * These limitations are worked around in this test by using a large enough + * region of memory for each vCPU such that the number of translations cached in + * the TLB and the number of pages held in pagevecs are a small fraction of the + * overall workload. And if either of those conditions are not true this test + * will fail rather than silently passing. + */ +#include <inttypes.h> +#include <limits.h> +#include <pthread.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <sys/stat.h> + +#include "kvm_util.h" +#include "test_util.h" +#include "perf_test_util.h" +#include "guest_modes.h" + +/* Global variable used to synchronize all of the vCPU threads. */ +static int iteration = -1; + +/* Defines what vCPU threads should do during a given iteration. */ +static enum { + /* Run the vCPU to access all its memory. */ + ITERATION_ACCESS_MEMORY, + /* Mark the vCPU's memory idle in page_idle. */ + ITERATION_MARK_IDLE, +} iteration_work; + +/* Set to true when vCPU threads should exit. */ +static bool done; + +/* The iteration that was last completed by each vCPU. */ +static int vcpu_last_completed_iteration[KVM_MAX_VCPUS]; + +/* Whether to overlap the regions of memory vCPUs access. */ +static bool overlap_memory_access; + +struct test_params { + /* The backing source for the region of memory. */ + enum vm_mem_backing_src_type backing_src; + + /* The amount of memory to allocate for each vCPU. */ + uint64_t vcpu_memory_bytes; + + /* The number of vCPUs to create in the VM. */ + int vcpus; +}; + +static uint64_t pread_uint64(int fd, const char *filename, uint64_t index) +{ + uint64_t value; + off_t offset = index * sizeof(value); + + TEST_ASSERT(pread(fd, &value, sizeof(value), offset) == sizeof(value), + "pread from %s offset 0x%" PRIx64 " failed!", + filename, offset); + + return value; + +} + +#define PAGEMAP_PRESENT (1ULL << 63) +#define PAGEMAP_PFN_MASK ((1ULL << 55) - 1) + +static uint64_t lookup_pfn(int pagemap_fd, struct kvm_vm *vm, uint64_t gva) +{ + uint64_t hva = (uint64_t) addr_gva2hva(vm, gva); + uint64_t entry; + uint64_t pfn; + + entry = pread_uint64(pagemap_fd, "pagemap", hva / getpagesize()); + if (!(entry & PAGEMAP_PRESENT)) + return 0; + + pfn = entry & PAGEMAP_PFN_MASK; + if (!pfn) { + print_skip("Looking up PFNs requires CAP_SYS_ADMIN"); + exit(KSFT_SKIP); + } + + return pfn; +} + +static bool is_page_idle(int page_idle_fd, uint64_t pfn) +{ + uint64_t bits = pread_uint64(page_idle_fd, "page_idle", pfn / 64); + + return !!((bits >> (pfn % 64)) & 1); +} + +static void mark_page_idle(int page_idle_fd, uint64_t pfn) +{ + uint64_t bits = 1ULL << (pfn % 64); + + TEST_ASSERT(pwrite(page_idle_fd, &bits, 8, 8 * (pfn / 64)) == 8, + "Set page_idle bits for PFN 0x%" PRIx64, pfn); +} + +static void mark_vcpu_memory_idle(struct kvm_vm *vm, int vcpu_id) +{ + uint64_t base_gva = perf_test_args.vcpu_args[vcpu_id].gva; + uint64_t pages = perf_test_args.vcpu_args[vcpu_id].pages; + uint64_t page; + uint64_t still_idle = 0; + uint64_t no_pfn = 0; + int page_idle_fd; + int pagemap_fd; + + /* If vCPUs are using an overlapping region, let vCPU 0 mark it idle. */ + if (overlap_memory_access && vcpu_id) + return; + + page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR); + TEST_ASSERT(page_idle_fd > 0, "Failed to open page_idle."); + + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + TEST_ASSERT(pagemap_fd > 0, "Failed to open pagemap."); + + for (page = 0; page < pages; page++) { + uint64_t gva = base_gva + page * perf_test_args.guest_page_size; + uint64_t pfn = lookup_pfn(pagemap_fd, vm, gva); + + if (!pfn) { + no_pfn++; + continue; + } + + if (is_page_idle(page_idle_fd, pfn)) { + still_idle++; + continue; + } + + mark_page_idle(page_idle_fd, pfn); + } + + /* + * Assumption: Less than 1% of pages are going to be swapped out from + * under us during this test. + */ + TEST_ASSERT(no_pfn < pages / 100, + "vCPU %d: No PFN for %" PRIu64 " out of %" PRIu64 " pages.", + vcpu_id, no_pfn, pages); + + /* + * Test that at least 90% of memory has been marked idle (the rest might + * not be marked idle because the pages have not yet made it to an LRU + * list or the translations are still cached in the TLB). 90% is + * arbitrary; high enough that we ensure most memory access went through + * access tracking but low enough as to not make the test too brittle + * over time and across architectures. + */ + TEST_ASSERT(still_idle < pages / 10, + "vCPU%d: Too many pages still idle (%"PRIu64 " out of %" + PRIu64 ").\n", + vcpu_id, still_idle, pages); + + close(page_idle_fd); + close(pagemap_fd); +} + +static void assert_ucall(struct kvm_vm *vm, uint32_t vcpu_id, + uint64_t expected_ucall) +{ + struct ucall uc; + uint64_t actual_ucall = get_ucall(vm, vcpu_id, &uc); + + TEST_ASSERT(expected_ucall == actual_ucall, + "Guest exited unexpectedly (expected ucall %" PRIu64 + ", got %" PRIu64 ")", + expected_ucall, actual_ucall); +} + +static bool spin_wait_for_next_iteration(int *current_iteration) +{ + int last_iteration = *current_iteration; + + do { + if (READ_ONCE(done)) + return false; + + *current_iteration = READ_ONCE(iteration); + } while (last_iteration == *current_iteration); + + return true; +} + +static void *vcpu_thread_main(void *arg) +{ + struct perf_test_vcpu_args *vcpu_args = arg; + struct kvm_vm *vm = perf_test_args.vm; + int vcpu_id = vcpu_args->vcpu_id; + int current_iteration = -1; + + vcpu_args_set(vm, vcpu_id, 1, vcpu_id); + + while (spin_wait_for_next_iteration(¤t_iteration)) { + switch (READ_ONCE(iteration_work)) { + case ITERATION_ACCESS_MEMORY: + vcpu_run(vm, vcpu_id); + assert_ucall(vm, vcpu_id, UCALL_SYNC); + break; + case ITERATION_MARK_IDLE: + mark_vcpu_memory_idle(vm, vcpu_id); + break; + }; + + vcpu_last_completed_iteration[vcpu_id] = current_iteration; + } + + return NULL; +} + +static void spin_wait_for_vcpu(int vcpu_id, int target_iteration) +{ + while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != + target_iteration) { + continue; + } +} + +/* The type of memory accesses to perform in the VM. */ +enum access_type { + ACCESS_READ, + ACCESS_WRITE, +}; + +static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description) +{ + struct timespec ts_start; + struct timespec ts_elapsed; + int next_iteration; + int vcpu_id; + + /* Kick off the vCPUs by incrementing iteration. */ + next_iteration = ++iteration; + + clock_gettime(CLOCK_MONOTONIC, &ts_start); + + /* Wait for all vCPUs to finish the iteration. */ + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) + spin_wait_for_vcpu(vcpu_id, next_iteration); + + ts_elapsed = timespec_elapsed(ts_start); + pr_info("%-30s: %ld.%09lds\n", + description, ts_elapsed.tv_sec, ts_elapsed.tv_nsec); +} + +static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access, + const char *description) +{ + perf_test_args.wr_fract = (access == ACCESS_READ) ? INT_MAX : 1; + sync_global_to_guest(vm, perf_test_args); + iteration_work = ITERATION_ACCESS_MEMORY; + run_iteration(vm, vcpus, description); +} + +static void mark_memory_idle(struct kvm_vm *vm, int vcpus) +{ + /* + * Even though this parallelizes the work across vCPUs, this is still a + * very slow operation because page_idle forces the test to mark one pfn + * at a time and the clear_young notifier serializes on the KVM MMU + * lock. + */ + pr_debug("Marking VM memory idle (slow)...\n"); + iteration_work = ITERATION_MARK_IDLE; + run_iteration(vm, vcpus, "Mark memory idle"); +} + +static pthread_t *create_vcpu_threads(int vcpus) +{ + pthread_t *vcpu_threads; + int i; + + vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0])); + TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads."); + + for (i = 0; i < vcpus; i++) { + vcpu_last_completed_iteration[i] = iteration; + pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main, + &perf_test_args.vcpu_args[i]); + } + + return vcpu_threads; +} + +static void terminate_vcpu_threads(pthread_t *vcpu_threads, int vcpus) +{ + int i; + + /* Set done to signal the vCPU threads to exit */ + done = true; + + for (i = 0; i < vcpus; i++) + pthread_join(vcpu_threads[i], NULL); +} + +static void run_test(enum vm_guest_mode mode, void *arg) +{ + struct test_params *params = arg; + struct kvm_vm *vm; + pthread_t *vcpu_threads; + int vcpus = params->vcpus; + + vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes, + params->backing_src); + + perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes, + !overlap_memory_access); + + vcpu_threads = create_vcpu_threads(vcpus); + + pr_info("\n"); + access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory"); + + /* As a control, read and write to the populated memory first. */ + access_memory(vm, vcpus, ACCESS_WRITE, "Writing to populated memory"); + access_memory(vm, vcpus, ACCESS_READ, "Reading from populated memory"); + + /* Repeat on memory that has been marked as idle. */ + mark_memory_idle(vm, vcpus); + access_memory(vm, vcpus, ACCESS_WRITE, "Writing to idle memory"); + mark_memory_idle(vm, vcpus); + access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory"); + + terminate_vcpu_threads(vcpu_threads, vcpus); + free(vcpu_threads); + perf_test_destroy_vm(vm); +} + +static void help(char *name) +{ + puts(""); + printf("usage: %s [-h] [-m mode] [-b vcpu_bytes] [-v vcpus] [-o] [-s mem_type]\n", + name); + puts(""); + printf(" -h: Display this help message."); + guest_modes_help(); + printf(" -b: specify the size of the memory region which should be\n" + " dirtied by each vCPU. e.g. 10M or 3G.\n" + " (default: 1G)\n"); + 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"); + printf(" -s: specify the type of memory that should be used to\n" + " back the guest data region.\n\n"); + backing_src_help(); + puts(""); + exit(0); +} + +int main(int argc, char *argv[]) +{ + struct test_params params = { + .backing_src = VM_MEM_SRC_ANONYMOUS, + .vcpu_memory_bytes = DEFAULT_PER_VCPU_MEM_SIZE, + .vcpus = 1, + }; + int page_idle_fd; + int opt; + + guest_modes_append_default(); + + while ((opt = getopt(argc, argv, "hm:b:v:os:")) != -1) { + switch (opt) { + case 'm': + guest_modes_cmdline(optarg); + break; + case 'b': + params.vcpu_memory_bytes = parse_size(optarg); + break; + case 'v': + params.vcpus = atoi(optarg); + break; + case 'o': + overlap_memory_access = true; + break; + case 's': + params.backing_src = parse_backing_src_type(optarg); + break; + case 'h': + default: + help(argv[0]); + break; + } + } + + page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR); + if (page_idle_fd < 0) { + print_skip("CONFIG_IDLE_PAGE_TRACKING is not enabled"); + exit(KSFT_SKIP); + } + close(page_idle_fd); + + for_each_guest_mode(run_test, ¶ms); + + return 0; +} diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 04a2641261be..80cbd3a748c0 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -312,6 +312,7 @@ int main(int argc, char *argv[]) break; case 'o': p.partition_vcpu_memory_access = false; + break; case 's': p.backing_src = parse_backing_src_type(optarg); break; diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index b0031f2d38fd..ecec30865a74 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -320,7 +320,7 @@ int main(int ac, char **av) run_delay = get_run_delay(); pthread_create(&thread, &attr, do_steal_time, NULL); do - pthread_yield(); + sched_yield(); while (get_run_delay() - run_delay < MIN_RUN_DELAY_NS); pthread_join(thread, NULL); run_delay = get_run_delay() - run_delay; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 986959833d70..d20fba0fc290 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3110,6 +3110,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) ++vcpu->stat.generic.halt_poll_invalid; goto out; } + cpu_relax(); poll_end = cur = ktime_get(); } while (kvm_vcpu_can_poll(cur, stop)); } @@ -4390,6 +4391,16 @@ struct compat_kvm_dirty_log { }; }; +struct compat_kvm_clear_dirty_log { + __u32 slot; + __u32 num_pages; + __u64 first_page; + union { + compat_uptr_t dirty_bitmap; /* one bit per page */ + __u64 padding2; + }; +}; + static long kvm_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -4399,6 +4410,24 @@ static long kvm_vm_compat_ioctl(struct file *filp, if (kvm->mm != current->mm) return -EIO; switch (ioctl) { +#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT + case KVM_CLEAR_DIRTY_LOG: { + struct compat_kvm_clear_dirty_log compat_log; + struct kvm_clear_dirty_log log; + + if (copy_from_user(&compat_log, (void __user *)arg, + sizeof(compat_log))) + return -EFAULT; + log.slot = compat_log.slot; + log.num_pages = compat_log.num_pages; + log.first_page = compat_log.first_page; + log.padding2 = compat_log.padding2; + log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap); + + r = kvm_vm_ioctl_clear_dirty_log(kvm, &log); + break; + } +#endif case KVM_GET_DIRTY_LOG: { struct compat_kvm_dirty_log compat_log; struct kvm_dirty_log log; |