diff options
220 files changed, 2814 insertions, 1744 deletions
diff --git a/Documentation/cpu-freq/index.txt b/Documentation/cpu-freq/index.txt index 03a7cee..c15e753 100644 --- a/Documentation/cpu-freq/index.txt +++ b/Documentation/cpu-freq/index.txt @@ -32,8 +32,6 @@ cpufreq-stats.txt - General description of sysfs cpufreq stats. index.txt - File index, Mailing list and Links (this document) -intel-pstate.txt - Intel pstate cpufreq driver specific file. - pcc-cpufreq.txt - PCC cpufreq driver specific file. diff --git a/Documentation/devicetree/bindings/leds/ams,as3645a.txt b/Documentation/devicetree/bindings/leds/ams,as3645a.txt index 12c5ef2..fdc40e3 100644 --- a/Documentation/devicetree/bindings/leds/ams,as3645a.txt +++ b/Documentation/devicetree/bindings/leds/ams,as3645a.txt @@ -15,11 +15,14 @@ Required properties compatible : Must be "ams,as3645a". reg : The I2C address of the device. Typically 0x30. +#address-cells : 1 +#size-cells : 0 -Required properties of the "flash" child node -============================================= +Required properties of the flash child node (0) +=============================================== +reg: 0 flash-timeout-us: Flash timeout in microseconds. The value must be in the range [100000, 850000] and divisible by 50000. flash-max-microamp: Maximum flash current in microamperes. Has to be @@ -33,20 +36,21 @@ ams,input-max-microamp: Maximum flash controller input current. The and divisible by 50000. -Optional properties of the "flash" child node -============================================= +Optional properties of the flash child node +=========================================== label : The label of the flash LED. -Required properties of the "indicator" child node -================================================= +Required properties of the indicator child node (1) +=================================================== +reg: 1 led-max-microamp: Maximum indicator current. The allowed values are 2500, 5000, 7500 and 10000. -Optional properties of the "indicator" child node -================================================= +Optional properties of the indicator child node +=============================================== label : The label of the indicator LED. @@ -55,16 +59,20 @@ Example ======= as3645a@30 { + #address-cells: 1 + #size-cells: 0 reg = <0x30>; compatible = "ams,as3645a"; - flash { + flash@0 { + reg = <0x0>; flash-timeout-us = <150000>; flash-max-microamp = <320000>; led-max-microamp = <60000>; ams,input-max-microamp = <1750000>; label = "as3645a:flash"; }; - indicator { + indicator@1 { + reg = <0x1>; led-max-microamp = <10000>; label = "as3645a:indicator"; }; diff --git a/MAINTAINERS b/MAINTAINERS index 6671f37..65b0c88 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8597,6 +8597,12 @@ M: Sean Wang <sean.wang@mediatek.com> S: Maintained F: drivers/media/rc/mtk-cir.c +MEDIATEK PMIC LED DRIVER +M: Sean Wang <sean.wang@mediatek.com> +S: Maintained +F: drivers/leds/leds-mt6323.c +F: Documentation/devicetree/bindings/leds/leds-mt6323.txt + MEDIATEK ETHERNET DRIVER M: Felix Fietkau <nbd@openwrt.org> M: John Crispin <john@phrozen.org> @@ -1172,11 +1172,11 @@ headers_check: headers_install PHONY += kselftest kselftest: - $(Q)$(MAKE) -C tools/testing/selftests run_tests + $(Q)$(MAKE) -C $(srctree)/tools/testing/selftests run_tests PHONY += kselftest-clean kselftest-clean: - $(Q)$(MAKE) -C tools/testing/selftests clean + $(Q)$(MAKE) -C $(srctree)/tools/testing/selftests clean PHONY += kselftest-merge kselftest-merge: diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi index cb47ae7..1b0bd72 100644 --- a/arch/arm/boot/dts/omap3-n950-n9.dtsi +++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi @@ -267,15 +267,19 @@ clock-frequency = <400000>; as3645a@30 { + #address-cells = <1>; + #size-cells = <0>; reg = <0x30>; compatible = "ams,as3645a"; - flash { + flash@0 { + reg = <0x0>; flash-timeout-us = <150000>; flash-max-microamp = <320000>; led-max-microamp = <60000>; - peak-current-limit = <1750000>; + ams,input-max-microamp = <1750000>; }; - indicator { + indicator@1 { + reg = <0x1>; led-max-microamp = <10000>; }; }; diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index bc4e923..b46e54c 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -401,7 +401,7 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd) /* Find an entry in the third-level page table. */ #define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) -#define pte_offset_phys(dir,addr) (pmd_page_paddr(*(dir)) + pte_index(addr) * sizeof(pte_t)) +#define pte_offset_phys(dir,addr) (pmd_page_paddr(READ_ONCE(*(dir))) + pte_index(addr) * sizeof(pte_t)) #define pte_offset_kernel(dir,addr) ((pte_t *)__va(pte_offset_phys((dir), (addr)))) #define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr)) diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 7434ec0..0b243ec 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -384,6 +384,7 @@ ENTRY(kimage_vaddr) * booted in EL1 or EL2 respectively. */ ENTRY(el2_setup) + msr SPsel, #1 // We want to use SP_EL{1,2} mrs x0, CurrentEL cmp x0, #CurrentEL_EL2 b.eq 1f diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 89993c4..2069e9b 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -651,7 +651,7 @@ static const struct fault_info fault_info[] = { { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 0 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" }, - { do_page_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, + { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, { do_bad, SIGBUS, 0, "unknown 8" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" }, diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 9d26abd..4f798aa 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -39,7 +39,7 @@ config MICROBLAZE # Endianness selection choice prompt "Endianness selection" - default CPU_BIG_ENDIAN + default CPU_LITTLE_ENDIAN help microblaze architectures can be configured for either little or big endian formats. Be sure to select the appropriate mode. diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild index e77a596..06609ca 100644 --- a/arch/microblaze/include/uapi/asm/Kbuild +++ b/arch/microblaze/include/uapi/asm/Kbuild @@ -7,6 +7,7 @@ generic-y += fcntl.h generic-y += ioctl.h generic-y += ioctls.h generic-y += ipcbuf.h +generic-y += kvm_para.h generic-y += mman.h generic-y += msgbuf.h generic-y += param.h diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c index e45ada8..94700c5 100644 --- a/arch/microblaze/kernel/dma.c +++ b/arch/microblaze/kernel/dma.c @@ -165,7 +165,7 @@ int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma, unsigned long attrs) { #ifdef CONFIG_MMU - unsigned long user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + unsigned long user_count = vma_pages(vma); unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; unsigned long off = vma->vm_pgoff; unsigned long pfn; diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 17936f8..ec69fa4 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1121,6 +1121,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) BEGIN_FTR_SECTION mtspr SPRN_PPR, r0 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + +/* Move canary into DSISR to check for later */ +BEGIN_FTR_SECTION + li r0, 0x7fff + mtspr SPRN_HDSISR, r0 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + ld r0, VCPU_GPR(R0)(r4) ld r4, VCPU_GPR(R4)(r4) @@ -1956,9 +1963,14 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) kvmppc_hdsi: ld r3, VCPU_KVM(r9) lbz r0, KVM_RADIX(r3) - cmpwi r0, 0 mfspr r4, SPRN_HDAR mfspr r6, SPRN_HDSISR +BEGIN_FTR_SECTION + /* Look for DSISR canary. If we find it, retry instruction */ + cmpdi r6, 0x7fff + beq 6f +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + cmpwi r0, 0 bne .Lradix_hdsi /* on radix, just save DAR/DSISR/ASDR */ /* HPTE not found fault or protection fault? */ andis. r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index e0bb46c..0e2a5ed 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -231,7 +231,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, ksig->ka.sa.sa_restorer) sp = (unsigned long) ksig->ka.sa.sa_restorer; - if (fpu->fpstate_active) { + if (fpu->initialized) { unsigned long fx_aligned, math_size; sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size); diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 554cdb2..e3221ff 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -23,11 +23,9 @@ /* * High level FPU state handling functions: */ -extern void fpu__activate_curr(struct fpu *fpu); -extern void fpu__activate_fpstate_read(struct fpu *fpu); -extern void fpu__activate_fpstate_write(struct fpu *fpu); -extern void fpu__current_fpstate_write_begin(void); -extern void fpu__current_fpstate_write_end(void); +extern void fpu__initialize(struct fpu *fpu); +extern void fpu__prepare_read(struct fpu *fpu); +extern void fpu__prepare_write(struct fpu *fpu); extern void fpu__save(struct fpu *fpu); extern void fpu__restore(struct fpu *fpu); extern int fpu__restore_sig(void __user *buf, int ia32_frame); @@ -120,20 +118,11 @@ extern void fpstate_sanitize_xstate(struct fpu *fpu); err; \ }) -#define check_insn(insn, output, input...) \ -({ \ - int err; \ +#define kernel_insn(insn, output, input...) \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err), output \ - : "0"(0), input); \ - err; \ -}) + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore) \ + : output : input) static inline int copy_fregs_to_user(struct fregs_state __user *fx) { @@ -153,20 +142,16 @@ static inline int copy_fxregs_to_user(struct fxregs_state __user *fx) static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) { - int err; - if (IS_ENABLED(CONFIG_X86_32)) { - err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } else { if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) { - err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); + kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } else { /* See comment in copy_fxregs_to_kernel() below. */ - err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx)); + kernel_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx)); } } - /* Copying from a kernel buffer to FPU registers should never fail: */ - WARN_ON_FPU(err); } static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) @@ -183,9 +168,7 @@ static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) static inline void copy_kernel_to_fregs(struct fregs_state *fx) { - int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - - WARN_ON_FPU(err); + kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_user_to_fregs(struct fregs_state __user *fx) @@ -281,18 +264,13 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact * XSAVE area format. */ -#define XSTATE_XRESTORE(st, lmask, hmask, err) \ +#define XSTATE_XRESTORE(st, lmask, hmask) \ asm volatile(ALTERNATIVE(XRSTOR, \ XRSTORS, X86_FEATURE_XSAVES) \ "\n" \ - "xor %[err], %[err]\n" \ "3:\n" \ - ".pushsection .fixup,\"ax\"\n" \ - "4: movl $-2, %[err]\n" \ - "jmp 3b\n" \ - ".popsection\n" \ - _ASM_EXTABLE(661b, 4b) \ - : [err] "=r" (err) \ + _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\ + : \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") @@ -336,7 +314,10 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); - /* We should never fault when copying from a kernel buffer: */ + /* + * We should never fault when copying from a kernel buffer, and the FPU + * state we set at boot time should be valid. + */ WARN_ON_FPU(err); } @@ -350,7 +331,7 @@ static inline void copy_xregs_to_kernel(struct xregs_state *xstate) u32 hmask = mask >> 32; int err; - WARN_ON(!alternatives_patched); + WARN_ON_FPU(!alternatives_patched); XSTATE_XSAVE(xstate, lmask, hmask, err); @@ -365,12 +346,8 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; - int err; - - XSTATE_XRESTORE(xstate, lmask, hmask, err); - /* We should never fault when copying from a kernel buffer: */ - WARN_ON_FPU(err); + XSTATE_XRESTORE(xstate, lmask, hmask); } /* @@ -526,38 +503,17 @@ static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) */ static inline void fpregs_deactivate(struct fpu *fpu) { - WARN_ON_FPU(!fpu->fpregs_active); - - fpu->fpregs_active = 0; this_cpu_write(fpu_fpregs_owner_ctx, NULL); trace_x86_fpu_regs_deactivated(fpu); } static inline void fpregs_activate(struct fpu *fpu) { - WARN_ON_FPU(fpu->fpregs_active); - - fpu->fpregs_active = 1; this_cpu_write(fpu_fpregs_owner_ctx, fpu); trace_x86_fpu_regs_activated(fpu); } /* - * The question "does this thread have fpu access?" - * is slightly racy, since preemption could come in - * and revoke it immediately after the test. - * - * However, even in that very unlikely scenario, - * we can just assume we have FPU access - typically - * to save the FP state - we'll just take a #NM - * fault and get the FPU access back. - */ -static inline int fpregs_active(void) -{ - return current->thread.fpu.fpregs_active; -} - -/* * FPU state switching for scheduling. * * This is a two-stage process: @@ -571,14 +527,13 @@ static inline int fpregs_active(void) static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { - if (old_fpu->fpregs_active) { + if (old_fpu->initialized) { if (!copy_fpregs_to_fpstate(old_fpu)) old_fpu->last_cpu = -1; else old_fpu->last_cpu = cpu; /* But leave fpu_fpregs_owner_ctx! */ - old_fpu->fpregs_active = 0; trace_x86_fpu_regs_deactivated(old_fpu); } else old_fpu->last_cpu = -1; @@ -595,7 +550,7 @@ switch_fpu_prepare(struct fpu *old_fpu, int cpu) static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu) { bool preload = static_cpu_has(X86_FEATURE_FPU) && - new_fpu->fpstate_active; + new_fpu->initialized; if (preload) { if (!fpregs_state_valid(new_fpu, cpu)) @@ -617,8 +572,7 @@ static inline void user_fpu_begin(void) struct fpu *fpu = ¤t->thread.fpu; preempt_disable(); - if (!fpregs_active()) - fpregs_activate(fpu); + fpregs_activate(fpu); preempt_enable(); } diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index 3c80f5b..a152057 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -68,6 +68,9 @@ struct fxregs_state { /* Default value for fxregs_state.mxcsr: */ #define MXCSR_DEFAULT 0x1f80 +/* Copy both mxcsr & mxcsr_flags with a single u64 memcpy: */ +#define MXCSR_AND_FLAGS_SIZE sizeof(u64) + /* * Software based FPU emulation state. This is arbitrary really, * it matches the x87 format to make it easier to understand: @@ -290,36 +293,13 @@ struct fpu { unsigned int last_cpu; /* - * @fpstate_active: + * @initialized: * - * This flag indicates whether this context is active: if the task + * This flag indicates whether this context is initialized: if the task * is not running then we can restore from this context, if the task * is running then we should save into this context. */ - unsigned char fpstate_active; - - /* - * @fpregs_active: - * - * This flag determines whether a given context is actively - * loaded into the FPU's registers and that those registers - * represent the task's current FPU state. - * - * Note the interaction with fpstate_active: - * - * # task does not use the FPU: - * fpstate_active == 0 - * - * # task uses the FPU and regs are active: - * fpstate_active == 1 && fpregs_active == 1 - * - * # the regs are inactive but still match fpstate: - * fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu - * - * The third state is what we use for the lazy restore optimization - * on lazy-switching CPUs. - */ - unsigned char fpregs_active; + unsigned char initialized; /* * @state: diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 1b2799e..83fee24 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -48,8 +48,12 @@ void fpu__xstate_clear_all_cpu_caps(void); void *get_xsave_addr(struct xregs_state *xsave, int xstate); const void *get_xsave_field_ptr(int xstate_field); int using_compacted_format(void); -int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, - void __user *ubuf, struct xregs_state *xsave); -int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, - struct xregs_state *xsave); +int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); +int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); +int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf); +int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf); + +/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ +extern int validate_xstate_header(const struct xstate_header *hdr); + #endif diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h index 342e597..39f7a27 100644 --- a/arch/x86/include/asm/trace/fpu.h +++ b/arch/x86/include/asm/trace/fpu.h @@ -12,25 +12,22 @@ DECLARE_EVENT_CLASS(x86_fpu, TP_STRUCT__entry( __field(struct fpu *, fpu) - __field(bool, fpregs_active) - __field(bool, fpstate_active) + __field(bool, initialized) __field(u64, xfeatures) __field(u64, xcomp_bv) ), TP_fast_assign( __entry->fpu = fpu; - __entry->fpregs_active = fpu->fpregs_active; - __entry->fpstate_active = fpu->fpstate_active; + __entry->initialized = fpu->initialized; if (boot_cpu_has(X86_FEATURE_OSXSAVE)) { __entry->xfeatures = fpu->state.xsave.header.xfeatures; __entry->xcomp_bv = fpu->state.xsave.header.xcomp_bv; } ), - TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d xfeatures: %llx xcomp_bv: %llx", + TP_printk("x86/fpu: %p initialized: %d xfeatures: %llx xcomp_bv: %llx", __entry->fpu, - __entry->fpregs_active, - __entry->fpstate_active, + __entry->initialized, __entry->xfeatures, __entry->xcomp_bv ) diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 128a1a0..7cb282e 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -551,13 +551,13 @@ static inline void MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr, struct desc_struct desc) { - u32 *p = (u32 *) &desc; - mcl->op = __HYPERVISOR_update_descriptor; if (sizeof(maddr) == sizeof(long)) { mcl->args[0] = maddr; mcl->args[1] = *(unsigned long *)&desc; } else { + u32 *p = (u32 *)&desc; + mcl->args[0] = maddr; mcl->args[1] = maddr >> 32; mcl->args[2] = *p++; diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index e1114f0..f92a659 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -100,7 +100,7 @@ void __kernel_fpu_begin(void) kernel_fpu_disable(); - if (fpu->fpregs_active) { + if (fpu->initialized) { /* * Ignore return value -- we don't care if reg state * is clobbered. @@ -116,7 +116,7 @@ void __kernel_fpu_end(void) { struct fpu *fpu = ¤t->thread.fpu; - if (fpu->fpregs_active) + if (fpu->initialized) copy_kernel_to_fpregs(&fpu->state); kernel_fpu_enable(); @@ -148,7 +148,7 @@ void fpu__save(struct fpu *fpu) preempt_disable(); trace_x86_fpu_before_save(fpu); - if (fpu->fpregs_active) { + if (fpu->initialized) { if (!copy_fpregs_to_fpstate(fpu)) { copy_kernel_to_fpregs(&fpu->state); } @@ -189,10 +189,9 @@ EXPORT_SYMBOL_GPL(fpstate_init); int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) { - dst_fpu->fpregs_active = 0; dst_fpu->last_cpu = -1; - if (!src_fpu->fpstate_active || !static_cpu_has(X86_FEATURE_FPU)) + if (!src_fpu->initialized || !static_cpu_has(X86_FEATURE_FPU)) return 0; WARN_ON_FPU(src_fpu != ¤t->thread.fpu); @@ -206,26 +205,14 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) /* * Save current FPU registers directly into the child * FPU context, without any memory-to-memory copying. - * In lazy mode, if the FPU context isn't loaded into - * fpregs, CR0.TS will be set and do_device_not_available - * will load the FPU context. * - * We have to do all this with preemption disabled, - * mostly because of the FNSAVE case, because in that - * case we must not allow preemption in the window - * between the FNSAVE and us marking the context lazy. - * - * It shouldn't be an issue as even FNSAVE is plenty - * fast in terms of critical section length. + * ( The function 'fails' in the FNSAVE case, which destroys + * register contents so we have to copy them back. ) */ - preempt_disable(); if (!copy_fpregs_to_fpstate(dst_fpu)) { - memcpy(&src_fpu->state, &dst_fpu->state, - fpu_kernel_xstate_size); - + memcpy(&src_fpu->state, &dst_fpu->state, fpu_kernel_xstate_size); copy_kernel_to_fpregs(&src_fpu->state); } - preempt_enable(); trace_x86_fpu_copy_src(src_fpu); trace_x86_fpu_copy_dst(dst_fpu); @@ -237,45 +224,48 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) * Activate the current task's in-memory FPU context, * if it has not been used before: */ -void fpu__activate_curr(struct fpu *fpu) +void fpu__initialize(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); - if (!fpu->fpstate_active) { + if (!fpu->initialized) { fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); trace_x86_fpu_activate_state(fpu); /* Safe to do for the current task: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } -EXPORT_SYMBOL_GPL(fpu__activate_curr); +EXPORT_SYMBOL_GPL(fpu__initialize); /* * This function must be called before we read a task's fpstate. * - * If the task has not used the FPU before then initialize its - * fpstate. + * There's two cases where this gets called: + * + * - for the current task (when coredumping), in which case we have + * to save the latest FPU registers into the fpstate, + * + * - or it's called for stopped tasks (ptrace), in which case the + * registers were already saved by the context-switch code when + * the task scheduled out - we only have to initialize the registers + * if they've never been initialized. * * If the task has used the FPU before then save it. */ -void fpu__activate_fpstate_read(struct fpu *fpu) +void fpu__prepare_read(struct fpu *fpu) { - /* - * If fpregs are active (in the current CPU), then - * copy them to the fpstate: - */ - if (fpu->fpregs_active) { + if (fpu == ¤t->thread.fpu) { fpu__save(fpu); } else { - if (!fpu->fpstate_active) { + if (!fpu->initialized) { fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); trace_x86_fpu_activate_state(fpu); /* Safe to do for current and for stopped child tasks: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } } @@ -283,17 +273,17 @@ void fpu__activate_fpstate_read(struct fpu *fpu) /* * This function must be called before we write a task's fpstate. * - * If the task has used the FPU before then unlazy it. + * If the task has used the FPU before then invalidate any cached FPU registers. * If the task has not used the FPU before then initialize its fpstate. * * After this function call, after registers in the fpstate are * modified and the child task has woken up, the child task will * restore the modified FPU state from the modified context. If we - * didn't clear its lazy status here then the lazy in-registers + * didn't clear its cached status here then the cached in-registers * state pending on its former CPU could be restored, corrupting * the modifications. */ -void fpu__activate_fpstate_write(struct fpu *fpu) +void fpu__prepare_write(struct fpu *fpu) { /* * Only stopped child tasks can be used to modify the FPU @@ -301,8 +291,8 @@ void fpu__activate_fpstate_write(struct fpu *fpu) */ WARN_ON_FPU(fpu == ¤t->thread.fpu); - if (fpu->fpstate_active) { - /* Invalidate any lazy state: */ + if (fpu->initialized) { + /* Invalidate any cached state: */ __fpu_invalidate_fpregs_state(fpu); } else { fpstate_init(&fpu->state); @@ -310,74 +300,11 @@ void fpu__activate_fpstate_write(struct fpu *fpu) trace_x86_fpu_activate_state(fpu); /* Safe to do for stopped child tasks: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } /* - * This function must be called before we write the current - * task's fpstate. - * - * This call gets the current FPU register state and moves - * it in to the 'fpstate'. Preemption is disabled so that - * no writes to the 'fpstate' can occur from context - * swiches. - * - * Must be followed by a fpu__current_fpstate_write_end(). - */ -void fpu__current_fpstate_write_begin(void) -{ - struct fpu *fpu = ¤t->thread.fpu; - - /* - * Ensure that the context-switching code does not write - * over the fpstate while we are doing our update. - */ - preempt_disable(); - - /* - * Move the fpregs in to the fpu's 'fpstate'. - */ - fpu__activate_fpstate_read(fpu); - - /* - * The caller is about to write to 'fpu'. Ensure that no - * CPU thinks that its fpregs match the fpstate. This - * ensures we will not be lazy and skip a XRSTOR in the - * future. - */ - __fpu_invalidate_fpregs_state(fpu); -} - -/* - * This function must be paired with fpu__current_fpstate_write_begin() - * - * This will ensure that the modified fpstate gets placed back in - * the fpregs if necessary. - * - * Note: This function may be called whether or not an _actual_ - * write to the fpstate occurred. - */ -void fpu__current_fpstate_write_end(void) -{ - struct fpu *fpu = ¤t->thread.fpu; - - /* - * 'fpu' now has an updated copy of the state, but the - * registers may still be out of date. Update them with - * an XRSTOR if they are active. - */ - if (fpregs_active()) - copy_kernel_to_fpregs(&fpu->state); - - /* - * Our update is done and the fpregs/fpstate are in sync - * if necessary. Context switches can happen again. - */ - preempt_enable(); -} - -/* * 'fpu__restore()' is called to copy FPU registers from * the FPU fpstate to the live hw registers and to activate * access to the hardware registers, so that FPU instructions @@ -389,7 +316,7 @@ void fpu__current_fpstate_write_end(void) */ void fpu__restore(struct fpu *fpu) { - fpu__activate_curr(fpu); + fpu__initialize(fpu); /* Avoid __kernel_fpu_begin() right after fpregs_activate() */ kernel_fpu_disable(); @@ -414,15 +341,17 @@ void fpu__drop(struct fpu *fpu) { preempt_disable(); - if (fpu->fpregs_active) { - /* Ignore delayed exceptions from user space */ - asm volatile("1: fwait\n" - "2:\n" - _ASM_EXTABLE(1b, 2b)); - fpregs_deactivate(fpu); + if (fpu == ¤t->thread.fpu) { + if (fpu->initialized) { + /* Ignore delayed exceptions from user space */ + asm volatile("1: fwait\n" + "2:\n" + _ASM_EXTABLE(1b, 2b)); + fpregs_deactivate(fpu); + } } - fpu->fpstate_active = 0; + fpu->initialized = 0; trace_x86_fpu_dropped(fpu); @@ -462,9 +391,11 @@ void fpu__clear(struct fpu *fpu) * Make sure fpstate is cleared and initialized. */ if (static_cpu_has(X86_FEATURE_FPU)) { - fpu__activate_curr(fpu); + preempt_disable(); + fpu__initialize(fpu); user_fpu_begin(); copy_init_fpstate_to_fpregs(); + preempt_enable(); } } diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index d5d44c4..7affb7e 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -240,7 +240,7 @@ static void __init fpu__init_system_ctx_switch(void) WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; - WARN_ON_FPU(current->thread.fpu.fpstate_active); + WARN_ON_FPU(current->thread.fpu.initialized); } /* diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index b188b16..3ea1513 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -16,14 +16,14 @@ int regset_fpregs_active(struct task_struct *target, const struct user_regset *r { struct fpu *target_fpu = &target->thread.fpu; - return target_fpu->fpstate_active ? regset->n : 0; + return target_fpu->initialized ? regset->n : 0; } int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset) { struct fpu *target_fpu = &target->thread.fpu; - if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->fpstate_active) + if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->initialized) return regset->n; else return 0; @@ -38,7 +38,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); fpstate_sanitize_xstate(fpu); return user_regset_copyout(&pos, &count, &kbuf, &ubuf, @@ -55,7 +55,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); fpstate_sanitize_xstate(fpu); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, @@ -89,10 +89,13 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, xsave = &fpu->state.xsave; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); if (using_compacted_format()) { - ret = copyout_from_xsaves(pos, count, kbuf, ubuf, xsave); + if (kbuf) + ret = copy_xstate_to_kernel(kbuf, xsave, pos, count); + else + ret = copy_xstate_to_user(ubuf, xsave, pos, count); } else { fpstate_sanitize_xstate(fpu); /* @@ -129,28 +132,29 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, xsave = &fpu->state.xsave; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - ret = copyin_to_xsaves(kbuf, ubuf, xsave); - else + if (using_compacted_format()) { + if (kbuf) + ret = copy_kernel_to_xstate(xsave, kbuf); + else + ret = copy_user_to_xstate(xsave, ubuf); + } else { ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); - - /* - * In case of failure, mark all states as init: - */ - if (ret) - fpstate_init(&fpu->state); + if (!ret) + ret = validate_xstate_header(&xsave->header); + } /* * mxcsr reserved bits must be masked to zero for security reasons. */ xsave->i387.mxcsr &= mxcsr_feature_mask; - xsave->header.xfeatures &= xfeatures_mask; + /* - * These bits must be zero. + * In case of failure, mark all states as init: */ - memset(&xsave->header.reserved, 0, 48); + if (ret) + fpstate_init(&fpu->state); return ret; } @@ -299,7 +303,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, struct fpu *fpu = &target->thread.fpu; struct user_i387_ia32_struct env; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); if (!boot_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); @@ -329,7 +333,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, struct user_i387_ia32_struct env; int ret; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); fpstate_sanitize_xstate(fpu); if (!boot_cpu_has(X86_FEATURE_FPU)) @@ -369,7 +373,7 @@ int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu) struct fpu *fpu = &tsk->thread.fpu; int fpvalid; - fpvalid = fpu->fpstate_active; + fpvalid = fpu->initialized; if (fpvalid) fpvalid = !fpregs_get(tsk, NULL, 0, sizeof(struct user_i387_ia32_struct), diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 83c23c2..fb639e7 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -155,7 +155,8 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) */ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) { - struct xregs_state *xsave = ¤t->thread.fpu.state.xsave; + struct fpu *fpu = ¤t->thread.fpu; + struct xregs_state *xsave = &fpu->state.xsave; struct task_struct *tsk = current; int ia32_fxstate = (buf != buf_fx); @@ -170,13 +171,13 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) sizeof(struct user_i387_ia32_struct), NULL, (struct _fpstate_32 __user *) buf) ? -1 : 1; - if (fpregs_active() || using_compacted_format()) { + if (fpu->initialized || using_compacted_format()) { /* Save the live register state to the user directly. */ if (copy_fpregs_to_sigframe(buf_fx)) return -1; /* Update the thread's fxstate to save the fsave header. */ if (ia32_fxstate) - copy_fxregs_to_kernel(&tsk->thread.fpu); + copy_fxregs_to_kernel(fpu); } else { /* * It is a *bug* if kernel uses compacted-format for xsave @@ -189,7 +190,7 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) return -1; } - fpstate_sanitize_xstate(&tsk->thread.fpu); + fpstate_sanitize_xstate(fpu); if (__copy_to_user(buf_fx, xsave, fpu_user_xstate_size)) return -1; } @@ -213,8 +214,11 @@ sanitize_restored_xstate(struct task_struct *tsk, struct xstate_header *header = &xsave->header; if (use_xsave()) { - /* These bits must be zero. */ - memset(header->reserved, 0, 48); + /* + * Note: we don't need to zero the reserved bits in the + * xstate_header here because we either didn't copy them at all, + * or we checked earlier that they aren't set. + */ /* * Init the state that is not present in the memory @@ -223,7 +227,7 @@ sanitize_restored_xstate(struct task_struct *tsk, if (fx_only) header->xfeatures = XFEATURE_MASK_FPSSE; else - header->xfeatures &= (xfeatures_mask & xfeatures); + header->xfeatures &= xfeatures; } if (use_fxsr()) { @@ -279,7 +283,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) if (!access_ok(VERIFY_READ, buf, size)) return -EACCES; - fpu__activate_curr(fpu); + fpu__initialize(fpu); if (!static_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_set(current, NULL, @@ -307,28 +311,29 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) /* * For 32-bit frames with fxstate, copy the user state to the * thread's fpu state, reconstruct fxstate from the fsave - * header. Sanitize the copied state etc. + * header. Validate and sanitize the copied state. */ struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; int err = 0; /* - * Drop the current fpu which clears fpu->fpstate_active. This ensures + * Drop the current fpu which clears fpu->initialized. This ensures * that any context-switch during the copy of the new state, * avoids the intermediate state from getting restored/saved. * Thus avoiding the new restored state from getting corrupted. * We will be ready to restore/save the state only after - * fpu->fpstate_active is again set. + * fpu->initialized is again set. */ fpu__drop(fpu); if (using_compacted_format()) { - err = copyin_to_xsaves(NULL, buf_fx, - &fpu->state.xsave); + err = copy_user_to_xstate(&fpu->state.xsave, buf_fx); } else { - err = __copy_from_user(&fpu->state.xsave, - buf_fx, state_size); + err = __copy_from_user(&fpu->state.xsave, buf_fx, state_size); + + if (!err && state_size > offsetof(struct xregs_state, header)) + err = validate_xstate_header(&fpu->state.xsave.header); } if (err || __copy_from_user(&env, buf, sizeof(env))) { @@ -339,7 +344,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) sanitize_restored_xstate(tsk, &env, xfeatures, fx_only); } - fpu->fpstate_active = 1; + fpu->initialized = 1; preempt_disable(); fpu__restore(fpu); preempt_enable(); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index c24ac1e..f1d5476 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -483,6 +483,30 @@ int using_compacted_format(void) return boot_cpu_has(X86_FEATURE_XSAVES); } +/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ +int validate_xstate_header(const struct xstate_header *hdr) +{ + /* No unknown or supervisor features may be set */ + if (hdr->xfeatures & (~xfeatures_mask | XFEATURE_MASK_SUPERVISOR)) + return -EINVAL; + + /* Userspace must use the uncompacted format */ + if (hdr->xcomp_bv) + return -EINVAL; + + /* + * If 'reserved' is shrunken to add a new field, make sure to validate + * that new field here! + */ + BUILD_BUG_ON(sizeof(hdr->reserved) != 48); + + /* No reserved bits may be set */ + if (memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved))) + return -EINVAL; + + return 0; +} + static void __xstate_dump_leaves(void) { int i; @@ -867,7 +891,7 @@ const void *get_xsave_field_ptr(int xsave_state) { struct fpu *fpu = ¤t->thread.fpu; - if (!fpu->fpstate_active) + if (!fpu->initialized) return NULL; /* * fpu__save() takes the CPU's xstate registers @@ -921,38 +945,129 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, #endif /* ! CONFIG_ARCH_HAS_PKEYS */ /* + * Weird legacy quirk: SSE and YMM states store information in the + * MXCSR and MXCSR_FLAGS fields of the FP area. That means if the FP + * area is marked as unused in the xfeatures header, we need to copy + * MXCSR and MXCSR_FLAGS if either SSE or YMM are in use. + */ +static inline bool xfeatures_mxcsr_quirk(u64 xfeatures) +{ + if (!(xfeatures & (XFEATURE_MASK_SSE|XFEATURE_MASK_YMM))) + return false; + + if (xfeatures & XFEATURE_MASK_FP) + return false; + + return true; +} + +/* * This is similar to user_regset_copyout(), but will not add offset to * the source data pointer or increment pos, count, kbuf, and ubuf. */ -static inline int xstate_copyout(unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf, - const void *data, const int start_pos, - const int end_pos) +static inline void +__copy_xstate_to_kernel(void *kbuf, const void *data, + unsigned int offset, unsigned int size, unsigned int size_total) { - if ((count == 0) || (pos < start_pos)) - return 0; + if (offset < size_total) { + unsigned int copy = min(size, size_total - offset); - if (end_pos < 0 || pos < end_pos) { - unsigned int copy = (end_pos < 0 ? count : min(count, end_pos - pos)); + memcpy(kbuf + offset, data, copy); + } +} - if (kbuf) { - memcpy(kbuf + pos, data, copy); - } else { - if (__copy_to_user(ubuf + pos, data, copy)) - return -EFAULT; +/* + * Convert from kernel XSAVES compacted format to standard format and copy + * to a kernel-space ptrace buffer. + * + * It supports partial copy but pos always starts from zero. This is called + * from xstateregs_get() and there we check the CPU has XSAVES. + */ +int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) +{ + unsigned int offset, size; + struct xstate_header header; + int i; + + /* + * Currently copy_regset_to_user() starts from pos 0: + */ + if (unlikely(offset_start != 0)) + return -EFAULT; + + /* + * The destination is a ptrace buffer; we put in only user xstates: + */ + memset(&header, 0, sizeof(header)); + header.xfeatures = xsave->header.xfeatures; + header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR; + + /* + * Copy xregs_state->header: + */ + offset = offsetof(struct xregs_state, header); + size = sizeof(header); + + __copy_xstate_to_kernel(kbuf, &header, offset, size, size_total); + + for (i = 0; i < XFEATURE_MAX; i++) { + /* + * Copy only in-use xstates: + */ + if ((header.xfeatures >> i) & 1) { + void *src = __raw_xsave_addr(xsave, 1 << i); + + offset = xstate_offsets[i]; + size = xstate_sizes[i]; + + /* The next component has to fit fully into the output buffer: */ + if (offset + size > size_total) + break; + + __copy_xstate_to_kernel(kbuf, src, offset, size, size_total); } + + } + + if (xfeatures_mxcsr_quirk(header.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + __copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total); + } + + /* + * Fill xsave->i387.sw_reserved value for ptrace frame: + */ + offset = offsetof(struct fxregs_state, sw_reserved); + size = sizeof(xstate_fx_sw_bytes); + + __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total); + + return 0; +} + +static inline int +__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int offset, unsigned int size, unsigned int size_total) +{ + if (!size) + return 0; + + if (offset < size_total) { + unsigned int copy = min(size, size_total - offset); + + if (__copy_to_user(ubuf + offset, data, copy)) + return -EFAULT; } return 0; } /* * Convert from kernel XSAVES compacted format to standard format and copy - * to a ptrace buffer. It supports partial copy but pos always starts from + * to a user-space buffer. It supports partial copy but pos always starts from * zero. This is called from xstateregs_get() and there we check the CPU * has XSAVES. */ -int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, - void __user *ubuf, struct xregs_state *xsave) +int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) { unsigned int offset, size; int ret, i; @@ -961,7 +1076,7 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, /* * Currently copy_regset_to_user() starts from pos 0: */ - if (unlikely(pos != 0)) + if (unlikely(offset_start != 0)) return -EFAULT; /* @@ -977,8 +1092,7 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, offset = offsetof(struct xregs_state, header); size = sizeof(header); - ret = xstate_copyout(offset, size, kbuf, ubuf, &header, 0, count); - + ret = __copy_xstate_to_user(ubuf, &header, offset, size, size_total); if (ret) return ret; @@ -992,25 +1106,30 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, offset = xstate_offsets[i]; size = xstate_sizes[i]; - ret = xstate_copyout(offset, size, kbuf, ubuf, src, 0, count); + /* The next component has to fit fully into the output buffer: */ + if (offset + size > size_total) + break; + ret = __copy_xstate_to_user(ubuf, src, offset, size, size_total); if (ret) return ret; - - if (offset + size >= count) - break; } } + if (xfeatures_mxcsr_quirk(header.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + __copy_xstate_to_user(ubuf, &xsave->i387.mxcsr, offset, size, size_total); + } + /* * Fill xsave->i387.sw_reserved value for ptrace frame: */ offset = offsetof(struct fxregs_state, sw_reserved); size = sizeof(xstate_fx_sw_bytes); - ret = xstate_copyout(offset, size, kbuf, ubuf, xstate_fx_sw_bytes, 0, count); - + ret = __copy_xstate_to_user(ubuf, xstate_fx_sw_bytes, offset, size, size_total); if (ret) return ret; @@ -1018,55 +1137,98 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, } /* - * Convert from a ptrace standard-format buffer to kernel XSAVES format - * and copy to the target thread. This is called from xstateregs_set() and - * there we check the CPU has XSAVES and a whole standard-sized buffer - * exists. + * Convert from a ptrace standard-format kernel buffer to kernel XSAVES format + * and copy to the target thread. This is called from xstateregs_set(). */ -int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, - struct xregs_state *xsave) +int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) { unsigned int offset, size; int i; - u64 xfeatures; - u64 allowed_features; + struct xstate_header hdr; offset = offsetof(struct xregs_state, header); - size = sizeof(xfeatures); + size = sizeof(hdr); - if (kbuf) { - memcpy(&xfeatures, kbuf + offset, size); - } else { - if (__copy_from_user(&xfeatures, ubuf + offset, size)) - return -EFAULT; + memcpy(&hdr, kbuf + offset, size); + + if (validate_xstate_header(&hdr)) + return -EINVAL; + + for (i = 0; i < XFEATURE_MAX; i++) { + u64 mask = ((u64)1 << i); + + if (hdr.xfeatures & mask) { + void *dst = __raw_xsave_addr(xsave, 1 << i); + + offset = xstate_offsets[i]; + size = xstate_sizes[i]; + + memcpy(dst, kbuf + offset, size); + } + } + + if (xfeatures_mxcsr_quirk(hdr.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + memcpy(&xsave->i387.mxcsr, kbuf + offset, size); } /* - * Reject if the user sets any disabled or supervisor features: + * The state that came in from userspace was user-state only. + * Mask all the user states out of 'xfeatures': + */ + xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR; + + /* + * Add back in the features that came in from userspace: */ - allowed_features = xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR; + xsave->header.xfeatures |= hdr.xfeatures; - if (xfeatures & ~allowed_features) + return 0; +} + +/* + * Convert from a ptrace or sigreturn standard-format user-space buffer to + * kernel XSAVES format and copy to the target thread. This is called from + * xstateregs_set(), as well as potentially from the sigreturn() and + * rt_sigreturn() system calls. + */ +int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) +{ + unsigned int offset, size; + int i; + struct xstate_header hdr; + + offset = offsetof(struct xregs_state, header); + size = sizeof(hdr); + + if (__copy_from_user(&hdr, ubuf + offset, size)) + return -EFAULT; + + if (validate_xstate_header(&hdr)) return -EINVAL; for (i = 0; i < XFEATURE_MAX; i++) { u64 mask = ((u64)1 << i); - if (xfeatures & mask) { + if (hdr.xfeatures & mask) { void *dst = __raw_xsave_addr(xsave, 1 << i); offset = xstate_offsets[i]; size = xstate_sizes[i]; - if (kbuf) { - memcpy(dst, kbuf + offset, size); - } else { - if (__copy_from_user(dst, ubuf + offset, size)) - return -EFAULT; - } + if (__copy_from_user(dst, ubuf + offset, size)) + return -EFAULT; } } + if (xfeatures_mxcsr_quirk(hdr.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + if (__copy_from_user(&xsave->i387.mxcsr, ubuf + offset, size)) + return -EFAULT; + } + /* * The state that came in from userspace was user-state only. * Mask all the user states out of 'xfeatures': @@ -1076,7 +1238,7 @@ int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, /* * Add back in the features that came in from userspace: */ - xsave->header.xfeatures |= xfeatures; + xsave->header.xfeatures |= hdr.xfeatures; return 0; } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index aa60a08..e675704 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -140,7 +140,8 @@ void kvm_async_pf_task_wait(u32 token) n.token = token; n.cpu = smp_processor_id(); - n.halted = is_idle_task(current) || preempt_count() > 1; + n.halted = is_idle_task(current) || preempt_count() > 1 || + rcu_preempt_depth(); init_swait_queue_head(&n.wq); hlist_add_head(&n.link, &b->list); raw_spin_unlock(&b->lock); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index e044423..4e188fd 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -263,7 +263,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, sp = (unsigned long) ka->sa.sa_restorer; } - if (fpu->fpstate_active) { + if (fpu->initialized) { sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32), &buf_fx, &math_size); *fpstate = (void __user *)sp; @@ -279,7 +279,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, return (void __user *)-1L; /* save i387 and extended state */ - if (fpu->fpstate_active && + if (fpu->initialized && copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0) return (void __user *)-1L; @@ -755,7 +755,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) /* * Ensure the signal handler starts with the new fpu state. */ - if (fpu->fpstate_active) + if (fpu->initialized) fpu__clear(fpu); } signal_setup_done(failed, ksig, stepping); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 6970249..a2b804e 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -200,6 +200,8 @@ struct loaded_vmcs { int cpu; bool launched; bool nmi_known_unmasked; + unsigned long vmcs_host_cr3; /* May not match real cr3 */ + unsigned long vmcs_host_cr4; /* May not match real cr4 */ struct list_head loaded_vmcss_on_cpu_link; }; @@ -600,8 +602,6 @@ struct vcpu_vmx { int gs_ldt_reload_needed; int fs_reload_needed; u64 msr_host_bndcfgs; - unsigned long vmcs_host_cr3; /* May not match real cr3 */ - unsigned long vmcs_host_cr4; /* May not match real cr4 */ } host_state; struct { int vm86_active; @@ -2202,46 +2202,44 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) struct pi_desc old, new; unsigned int dest; - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + /* + * In case of hot-plug or hot-unplug, we may have to undo + * vmx_vcpu_pi_put even if there is no assigned device. And we + * always keep PI.NDST up to date for simplicity: it makes the + * code easier, and CPU migration is not a fast path. + */ + if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) return; + /* + * First handle the simple case where no cmpxchg is necessary; just + * allow posting non-urgent interrupts. + * + * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change + * PI.NDST: pi_post_block will do it for us and the wakeup_handler + * expects the VCPU to be on the blocked_vcpu_list that matches + * PI.NDST. + */ + if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || + vcpu->cpu == cpu) { + pi_clear_sn(pi_desc); + return; + } + + /* The full case. */ do { old.control = new.control = pi_desc->control; - /* - * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there - * are two possible cases: - * 1. After running 'pre_block', context switch - * happened. For this case, 'sn' was set in - * vmx_vcpu_put(), so we need to clear it here. - * 2. After running 'pre_block', we were blocked, - * and woken up by some other guy. For this case, - * we don't need to do anything, 'pi_post_block' - * will do everything for us. However, we cannot - * check whether it is case #1 or case #2 here - * (maybe, not needed), so we also clear sn here, - * I think it is not a big deal. - */ - if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) { - if (vcpu->cpu != cpu) { - dest = cpu_physical_id(cpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - } + dest = cpu_physical_id(cpu); - /* set 'NV' to 'notification vector' */ - new.nv = POSTED_INTR_VECTOR; - } + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; - /* Allow posting non-urgent interrupts */ new.sn = 0; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); } static void decache_tsc_multiplier(struct vcpu_vmx *vmx) @@ -5178,12 +5176,12 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) */ cr3 = __read_cr3(); vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */ - vmx->host_state.vmcs_host_cr3 = cr3; + vmx->loaded_vmcs->vmcs_host_cr3 = cr3; /* Save the most likely value for this task's CR4 in the VMCS. */ cr4 = cr4_read_shadow(); vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */ - vmx->host_state.vmcs_host_cr4 = cr4; + vmx->loaded_vmcs->vmcs_host_cr4 = cr4; vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ #ifdef CONFIG_X86_64 @@ -9273,15 +9271,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) { + if (unlikely(cr3 != vmx->loaded_vmcs->vmcs_host_cr3)) { vmcs_writel(HOST_CR3, cr3); - vmx->host_state.vmcs_host_cr3 = cr3; + vmx->loaded_vmcs->vmcs_host_cr3 = cr3; } cr4 = cr4_read_shadow(); - if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) { + if (unlikely(cr4 != vmx->loaded_vmcs->vmcs_host_cr4)) { vmcs_writel(HOST_CR4, cr4); - vmx->host_state.vmcs_host_cr4 = cr4; + vmx->loaded_vmcs->vmcs_host_cr4 = cr4; } /* When single-stepping over STI and MOV SS, we must clear the @@ -9591,6 +9589,13 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED; + /* + * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR + * or POSTED_INTR_WAKEUP_VECTOR. + */ + vmx->pi_desc.nv = POSTED_INTR_VECTOR; + vmx->pi_desc.sn = 1; + return &vmx->vcpu; free_vmcs: @@ -9839,7 +9844,8 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, WARN_ON(!is_guest_mode(vcpu)); - if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) { + if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) && + !to_vmx(vcpu)->nested.nested_run_pending) { vmcs12->vm_exit_intr_error_code = fault->error_code; nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, PF_VECTOR | INTR_TYPE_HARD_EXCEPTION | @@ -11704,6 +11710,37 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask); } +static void __pi_post_block(struct kvm_vcpu *vcpu) +{ + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + struct pi_desc old, new; + unsigned int dest; + + do { + old.control = new.control = pi_desc->control; + WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR, + "Wakeup handler not enabled while the VCPU is blocked\n"); + + dest = cpu_physical_id(vcpu->cpu); + + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; + + /* set 'NV' to 'notification vector' */ + new.nv = POSTED_INTR_VECTOR; + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); + + if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) { + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + vcpu->pre_pcpu = -1; + } +} + /* * This routine does the following things for vCPU which is going * to be blocked if VT-d PI is enabled. @@ -11719,7 +11756,6 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, */ static int pi_pre_block(struct kvm_vcpu *vcpu) { - unsigned long flags; unsigned int dest; struct pi_desc old, new; struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); @@ -11729,34 +11765,20 @@ static int pi_pre_block(struct kvm_vcpu *vcpu) !kvm_vcpu_apicv_active(vcpu)) return 0; - vcpu->pre_pcpu = vcpu->cpu; - spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_add_tail(&vcpu->blocked_vcpu_list, - &per_cpu(blocked_vcpu_on_cpu, - vcpu->pre_pcpu)); - spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); + WARN_ON(irqs_disabled()); + local_irq_disable(); + if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) { + vcpu->pre_pcpu = vcpu->cpu; + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + list_add_tail(&vcpu->blocked_vcpu_list, + &per_cpu(blocked_vcpu_on_cpu, + vcpu->pre_pcpu)); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + } do { old.control = new.control = pi_desc->control; - /* - * We should not block the vCPU if - * an interrupt is posted for it. - */ - if (pi_test_on(pi_desc) == 1) { - spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock_irqrestore( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - vcpu->pre_pcpu = -1; - - return 1; - } - WARN((pi_desc->sn == 1), "Warning: SN field of posted-interrupts " "is set before blocking\n"); @@ -11778,10 +11800,15 @@ static int pi_pre_block(struct kvm_vcpu *vcpu) /* set 'NV' to 'wakeup vector' */ new.nv = POSTED_INTR_WAKEUP_VECTOR; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); - return 0; + /* We should not block the vCPU if an interrupt is posted for it. */ + if (pi_test_on(pi_desc) == 1) + __pi_post_block(vcpu); + + local_irq_enable(); + return (vcpu->pre_pcpu == -1); } static int vmx_pre_block(struct kvm_vcpu *vcpu) @@ -11797,44 +11824,13 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu) static void pi_post_block(struct kvm_vcpu *vcpu) { - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - struct pi_desc old, new; - unsigned int dest; - unsigned long flags; - - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + if (vcpu->pre_pcpu == -1) return; - do { - old.control = new.control = pi_desc->control; - - dest = cpu_physical_id(vcpu->cpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - - /* Allow posting non-urgent interrupts */ - new.sn = 0; - - /* set 'NV' to 'notification vector' */ - new.nv = POSTED_INTR_VECTOR; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); - - if(vcpu->pre_pcpu != -1) { - spin_lock_irqsave( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock_irqrestore( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - vcpu->pre_pcpu = -1; - } + WARN_ON(irqs_disabled()); + local_irq_disable(); + __pi_post_block(vcpu); + local_irq_enable(); } static void vmx_post_block(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cd17b7d..03869eb 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7225,7 +7225,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) int r; sigset_t sigsaved; - fpu__activate_curr(fpu); + fpu__initialize(fpu); if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index d4a7df2..220638a 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -114,7 +114,7 @@ void math_emulate(struct math_emu_info *info) struct desc_struct code_descriptor; struct fpu *fpu = ¤t->thread.fpu; - fpu__activate_curr(fpu); + fpu__initialize(fpu); #ifdef RE_ENTRANT_CHECKING if (emulating) { diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index c076f71..c3521e2 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -2,6 +2,7 @@ #include <linux/uaccess.h> #include <linux/sched/debug.h> +#include <asm/fpu/internal.h> #include <asm/traps.h> #include <asm/kdebug.h> @@ -78,6 +79,29 @@ bool ex_handler_refcount(const struct exception_table_entry *fixup, } EXPORT_SYMBOL_GPL(ex_handler_refcount); +/* + * Handler for when we fail to restore a task's FPU state. We should never get + * here because the FPU state of a task using the FPU (task->thread.fpu.state) + * should always be valid. However, past bugs have allowed userspace to set + * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn(). + * These caused XRSTOR to fail when switching to the task, leaking the FPU + * registers of the task previously executing on the CPU. Mitigate this class + * of vulnerability by restoring from the initial state (essentially, zeroing + * out all the FPU registers) if we can't restore from the task's FPU state. + */ +bool ex_handler_fprestore(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) +{ + regs->ip = ex_fixup_addr(fixup); + + WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.", + (void *)instruction_pointer(regs)); + + __copy_kernel_to_fpregs(&init_fpstate, -1); + return true; +} +EXPORT_SYMBOL_GPL(ex_handler_fprestore); + bool ex_handler_ext(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index 2dab69a..d7bc0eea 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -18,7 +18,6 @@ #include <asm/cpufeature.h> /* boot_cpu_has, ... */ #include <asm/mmu_context.h> /* vma_pkey() */ -#include <asm/fpu/internal.h> /* fpregs_active() */ int __execute_only_pkey(struct mm_struct *mm) { @@ -45,7 +44,7 @@ int __execute_only_pkey(struct mm_struct *mm) */ preempt_disable(); if (!need_to_set_mm_pkey && - fpregs_active() && + current->thread.fpu.initialized && !__pkru_allows_read(read_pkru(), execute_only_pkey)) { preempt_enable(); return execute_only_pkey; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 7330cb3..71495f1 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1238,21 +1238,16 @@ static void __init xen_pagetable_cleanhighmap(void) * from _brk_limit way up to the max_pfn_mapped (which is the end of * the ramdisk). We continue on, erasing PMD entries that point to page * tables - do note that they are accessible at this stage via __va. - * For good measure we also round up to the PMD - which means that if + * As Xen is aligning the memory end to a 4MB boundary, for good + * measure we also round up to PMD_SIZE * 2 - which means that if * anybody is using __ka address to the initial boot-stack - and try * to use it - they are going to crash. The xen_start_info has been * taken care of already in xen_setup_kernel_pagetable. */ addr = xen_start_info->pt_base; - size = roundup(xen_start_info->nr_pt_frames * PAGE_SIZE, PMD_SIZE); + size = xen_start_info->nr_pt_frames * PAGE_SIZE; - xen_cleanhighmap(addr, addr + size); + xen_cleanhighmap(addr, roundup(addr + size, PMD_SIZE * 2)); xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base)); -#ifdef DEBUG - /* This is superfluous and is not necessary, but you know what - * lets do it. The MODULES_VADDR -> MODULES_END should be clear of - * anything at this stage. */ - xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1); -#endif } #endif diff --git a/block/blk-core.c b/block/blk-core.c index aebe676..048be4a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -854,6 +854,9 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) kobject_init(&q->kobj, &blk_queue_ktype); +#ifdef CONFIG_BLK_DEV_IO_TRACE + mutex_init(&q->blk_trace_mutex); +#endif mutex_init(&q->sysfs_lock); spin_lock_init(&q->__queue_lock); diff --git a/block/bsg-lib.c b/block/bsg-lib.c index c82408c..dbddff8 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -154,7 +154,6 @@ static int bsg_prepare_job(struct device *dev, struct request *req) failjob_rls_rqst_payload: kfree(job->request_payload.sg_list); failjob_rls_job: - kfree(job); return -ENOMEM; } diff --git a/block/partition-generic.c b/block/partition-generic.c index 86e8fe1..88c555d 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -112,7 +112,7 @@ ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { struct hd_struct *p = dev_to_part(dev); - struct request_queue *q = dev_to_disk(dev)->queue; + struct request_queue *q = part_to_disk(p)->queue; unsigned int inflight[2]; int cpu; diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 077f9ba..3c3a37b 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -743,17 +743,19 @@ static int ghes_proc(struct ghes *ghes) } ghes_do_proc(ghes, ghes->estatus); +out: + ghes_clear_estatus(ghes); + + if (rc == -ENOENT) + return rc; + /* * GHESv2 type HEST entries introduce support for error acknowledgment, * so only acknowledge the error if this support is present. */ - if (is_hest_type_generic_v2(ghes)) { - rc = ghes_ack_error(ghes->generic_v2); - if (rc) - return rc; - } -out: - ghes_clear_estatus(ghes); + if (is_hest_type_generic_v2(ghes)) + return ghes_ack_error(ghes->generic_v2); + return rc; } diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c index a8cc14f..a6de325 100644 --- a/drivers/base/power/opp/core.c +++ b/drivers/base/power/opp/core.c @@ -1581,6 +1581,9 @@ static int _opp_set_availability(struct device *dev, unsigned long freq, opp->available = availability_req; + dev_pm_opp_get(opp); + mutex_unlock(&opp_table->lock); + /* Notify the change of the OPP availability */ if (availability_req) blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ENABLE, @@ -1589,8 +1592,12 @@ static int _opp_set_availability(struct device *dev, unsigned long freq, blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_DISABLE, opp); + dev_pm_opp_put(opp); + goto put_table; + unlock: mutex_unlock(&opp_table->lock); +put_table: dev_pm_opp_put_opp_table(opp_table); return r; } diff --git a/drivers/block/brd.c b/drivers/block/brd.c index bbd0d18..2d7178f 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -342,7 +342,7 @@ static long __brd_direct_access(struct brd_device *brd, pgoff_t pgoff, if (!brd) return -ENODEV; - page = brd_insert_page(brd, PFN_PHYS(pgoff) / 512); + page = brd_insert_page(brd, (sector_t)pgoff << PAGE_SECTORS_SHIFT); if (!page) return -ENOSPC; *kaddr = page_address(page); diff --git a/drivers/block/loop.h b/drivers/block/loop.h index f68c1d5..1f39567 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -67,10 +67,8 @@ struct loop_device { struct loop_cmd { struct kthread_work work; struct request *rq; - union { - bool use_aio; /* use AIO interface to handle I/O */ - atomic_t ref; /* only for aio */ - }; + bool use_aio; /* use AIO interface to handle I/O */ + atomic_t ref; /* only for aio */ long ret; struct kiocb iocb; struct bio_vec *bvec; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 2aa87cb..3684e21 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1194,6 +1194,12 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode, if (!capable(CAP_SYS_ADMIN)) return -EPERM; + /* The block layer will pass back some non-nbd ioctls in case we have + * special handling for them, but we don't so just return an error. + */ + if (_IOC_TYPE(cmd) != 0xab) + return -EINVAL; + mutex_lock(&nbd->config_lock); /* Don't allow ioctl operations on a nbd device that was created with diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 430edad..a753c50 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -118,6 +118,10 @@ static const struct of_device_id blacklist[] __initconst = { { .compatible = "sigma,tango4", }, + { .compatible = "ti,am33xx", }, + { .compatible = "ti,am43", }, + { .compatible = "ti,dra7", }, + { } }; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index d228f5a..dbbe986 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -636,7 +636,194 @@ static void gfx_v6_0_tiling_mode_table_init(struct amdgpu_device *adev) NUM_BANKS(ADDR_SURF_2_BANK); for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) WREG32(mmGB_TILE_MODE0 + reg_offset, tilemode[reg_offset]); - } else if (adev->asic_type == CHIP_OLAND || adev->asic_type == CHIP_HAINAN) { + } else if (adev->asic_type == CHIP_OLAND) { + tilemode[0] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[1] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[2] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[3] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[4] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[5] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[6] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[7] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[8] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_LINEAR_ALIGNED) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[9] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[10] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[11] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[12] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[13] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[14] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[15] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[16] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[17] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[21] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_2) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[22] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[23] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[24] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[25] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) | + NUM_BANKS(ADDR_SURF_8_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1); + for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) + WREG32(mmGB_TILE_MODE0 + reg_offset, tilemode[reg_offset]); + } else if (adev->asic_type == CHIP_HAINAN) { tilemode[0] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | ARRAY_MODE(ARRAY_2D_TILED_THIN1) | PIPE_CONFIG(ADDR_SURF_P2) | diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index e4a8c2e..660b3fb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -892,6 +892,8 @@ static int kfd_ioctl_get_tile_config(struct file *filep, int err = 0; dev = kfd_device_by_id(args->gpu_id); + if (!dev) + return -EINVAL; dev->kfd2kgd->get_tile_config(dev->kgd, &config); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 5979158..944abfa 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -292,7 +292,10 @@ static int create_signal_event(struct file *devkfd, struct kfd_event *ev) { if (p->signal_event_count == KFD_SIGNAL_EVENT_LIMIT) { - pr_warn("Signal event wasn't created because limit was reached\n"); + if (!p->signal_event_limit_reached) { + pr_warn("Signal event wasn't created because limit was reached\n"); + p->signal_event_limit_reached = true; + } return -ENOMEM; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c index 0649dd4..ed71ad4 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c @@ -184,7 +184,7 @@ static void uninitialize(struct kernel_queue *kq) if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ) kq->mqd->destroy_mqd(kq->mqd, kq->queue->mqd, - false, + KFD_PREEMPT_TYPE_WAVEFRONT_RESET, QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS, kq->queue->pipe, kq->queue->queue); @@ -210,6 +210,11 @@ static int acquire_packet_buffer(struct kernel_queue *kq, uint32_t wptr, rptr; unsigned int *queue_address; + /* When rptr == wptr, the buffer is empty. + * When rptr == wptr + 1, the buffer is full. + * It is always rptr that advances to the position of wptr, rather than + * the opposite. So we can only use up to queue_size_dwords - 1 dwords. + */ rptr = *kq->rptr_kernel; wptr = *kq->wptr_kernel; queue_address = (unsigned int *)kq->pq_kernel_addr; @@ -219,11 +224,10 @@ static int acquire_packet_buffer(struct kernel_queue *kq, pr_debug("wptr: %d\n", wptr); pr_debug("queue_address 0x%p\n", queue_address); - available_size = (rptr - 1 - wptr + queue_size_dwords) % + available_size = (rptr + queue_size_dwords - 1 - wptr) % queue_size_dwords; - if (packet_size_in_dwords >= queue_size_dwords || - packet_size_in_dwords >= available_size) { + if (packet_size_in_dwords > available_size) { /* * make sure calling functions know * acquire_packet_buffer() failed @@ -233,6 +237,14 @@ static int acquire_packet_buffer(struct kernel_queue *kq, } if (wptr + packet_size_in_dwords >= queue_size_dwords) { + /* make sure after rolling back to position 0, there is + * still enough space. + */ + if (packet_size_in_dwords >= rptr) { + *buffer_ptr = NULL; + return -ENOMEM; + } + /* fill nops, roll back and start at position 0 */ while (wptr > 0) { queue_address[wptr] = kq->nop_packet; wptr = (wptr + 1) % queue_size_dwords; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index b397ec7..b87e96c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -521,6 +521,7 @@ struct kfd_process { struct list_head signal_event_pages; u32 next_nonsignal_event_id; size_t signal_event_count; + bool signal_event_limit_reached; }; /** diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 5a63459..5788116 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -551,12 +551,15 @@ static const struct etnaviv_gem_ops etnaviv_gem_shmem_ops = { void etnaviv_gem_free_object(struct drm_gem_object *obj) { struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj); + struct etnaviv_drm_private *priv = obj->dev->dev_private; struct etnaviv_vram_mapping *mapping, *tmp; /* object should not be active */ WARN_ON(is_active(etnaviv_obj)); + mutex_lock(&priv->gem_lock); list_del(&etnaviv_obj->gem_node); + mutex_unlock(&priv->gem_lock); list_for_each_entry_safe(mapping, tmp, &etnaviv_obj->vram_list, obj_node) { diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index 026ef4e..46dfe07 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -445,8 +445,10 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data, cmdbuf->user_size = ALIGN(args->stream_size, 8); ret = etnaviv_gpu_submit(gpu, submit, cmdbuf); - if (ret == 0) - cmdbuf = NULL; + if (ret) + goto out; + + cmdbuf = NULL; if (args->flags & ETNA_SUBMIT_FENCE_FD_OUT) { /* diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 14c5613..afbf50d 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -509,23 +509,25 @@ static void qxl_primary_atomic_update(struct drm_plane *plane, .y2 = qfb->base.height }; - if (!old_state->fb) { - qxl_io_log(qdev, - "create primary fb: %dx%d,%d,%d\n", - bo->surf.width, bo->surf.height, - bo->surf.stride, bo->surf.format); + if (old_state->fb) { + qfb_old = to_qxl_framebuffer(old_state->fb); + bo_old = gem_to_qxl_bo(qfb_old->obj); + } else { + bo_old = NULL; + } - qxl_io_create_primary(qdev, 0, bo); - bo->is_primary = true; + if (bo == bo_old) return; - } else { - qfb_old = to_qxl_framebuffer(old_state->fb); - bo_old = gem_to_qxl_bo(qfb_old->obj); + if (bo_old && bo_old->is_primary) { + qxl_io_destroy_primary(qdev); bo_old->is_primary = false; } - bo->is_primary = true; + if (!bo->is_primary) { + qxl_io_create_primary(qdev, 0, bo); + bo->is_primary = true; + } qxl_draw_dirty_fb(qdev, qfb, bo, 0, 0, &norect, 1, 1); } @@ -534,13 +536,15 @@ static void qxl_primary_atomic_disable(struct drm_plane *plane, { struct qxl_device *qdev = plane->dev->dev_private; - if (old_state->fb) - { struct qxl_framebuffer *qfb = + if (old_state->fb) { + struct qxl_framebuffer *qfb = to_qxl_framebuffer(old_state->fb); struct qxl_bo *bo = gem_to_qxl_bo(qfb->obj); - qxl_io_destroy_primary(qdev); - bo->is_primary = false; + if (bo->is_primary) { + qxl_io_destroy_primary(qdev); + bo->is_primary = false; + } } } @@ -698,14 +702,15 @@ static void qxl_plane_cleanup_fb(struct drm_plane *plane, struct drm_gem_object *obj; struct qxl_bo *user_bo; - if (!plane->state->fb) { - /* we never executed prepare_fb, so there's nothing to + if (!old_state->fb) { + /* + * we never executed prepare_fb, so there's nothing to * unpin. */ return; } - obj = to_qxl_framebuffer(plane->state->fb)->obj; + obj = to_qxl_framebuffer(old_state->fb)->obj; user_bo = gem_to_qxl_bo(obj); qxl_bo_unpin(user_bo); } diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 997131d..ffc10ca 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1663,7 +1663,7 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend, radeon_agp_suspend(rdev); pci_save_state(dev->pdev); - if (freeze && rdev->family >= CHIP_CEDAR) { + if (freeze && rdev->family >= CHIP_CEDAR && !(rdev->flags & RADEON_IS_IGP)) { rdev->asic->asic_reset(rdev, true); pci_restore_state(dev->pdev); } else if (suspend) { diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig index 06f0530..882d85d 100644 --- a/drivers/gpu/drm/sun4i/Kconfig +++ b/drivers/gpu/drm/sun4i/Kconfig @@ -26,7 +26,7 @@ config DRM_SUN4I_HDMI_CEC bool "Allwinner A10 HDMI CEC Support" depends on DRM_SUN4I_HDMI select CEC_CORE - depends on CEC_PIN + select CEC_PIN help Choose this option if you have an Allwinner SoC with an HDMI controller and want to use CEC. diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi.h b/drivers/gpu/drm/sun4i/sun4i_hdmi.h index 1457750..a1f8cba 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi.h +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi.h @@ -15,7 +15,7 @@ #include <drm/drm_connector.h> #include <drm/drm_encoder.h> -#include <media/cec.h> +#include <media/cec-pin.h> #define SUN4I_HDMI_CTRL_REG 0x004 #define SUN4I_HDMI_CTRL_ENABLE BIT(31) diff --git a/drivers/gpu/drm/tegra/trace.h b/drivers/gpu/drm/tegra/trace.h index e9b7cdad..5a1ab40 100644 --- a/drivers/gpu/drm/tegra/trace.h +++ b/drivers/gpu/drm/tegra/trace.h @@ -63,6 +63,6 @@ DEFINE_EVENT(register_access, sor_readl, /* This part must be outside protection */ #undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/tegra #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c index 70ad19c..88bdafb 100644 --- a/drivers/infiniband/core/security.c +++ b/drivers/infiniband/core/security.c @@ -432,8 +432,10 @@ int ib_create_qp_security(struct ib_qp *qp, struct ib_device *dev) atomic_set(&qp->qp_sec->error_list_count, 0); init_completion(&qp->qp_sec->error_complete); ret = security_ib_alloc_security(&qp->qp_sec->security); - if (ret) + if (ret) { kfree(qp->qp_sec); + qp->qp_sec = NULL; + } return ret; } diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 4ab30d8..52a2cf2 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -3869,15 +3869,15 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file, resp.raw_packet_caps = attr.raw_packet_caps; resp.response_length += sizeof(resp.raw_packet_caps); - if (ucore->outlen < resp.response_length + sizeof(resp.xrq_caps)) + if (ucore->outlen < resp.response_length + sizeof(resp.tm_caps)) goto end; - resp.xrq_caps.max_rndv_hdr_size = attr.xrq_caps.max_rndv_hdr_size; - resp.xrq_caps.max_num_tags = attr.xrq_caps.max_num_tags; - resp.xrq_caps.max_ops = attr.xrq_caps.max_ops; - resp.xrq_caps.max_sge = attr.xrq_caps.max_sge; - resp.xrq_caps.flags = attr.xrq_caps.flags; - resp.response_length += sizeof(resp.xrq_caps); + resp.tm_caps.max_rndv_hdr_size = attr.tm_caps.max_rndv_hdr_size; + resp.tm_caps.max_num_tags = attr.tm_caps.max_num_tags; + resp.tm_caps.max_ops = attr.tm_caps.max_ops; + resp.tm_caps.max_sge = attr.tm_caps.max_sge; + resp.tm_caps.flags = attr.tm_caps.flags; + resp.response_length += sizeof(resp.tm_caps); end: err = ib_copy_to_udata(ucore, &resp, resp.response_length); return err; diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index b2ed4b9..0be4278 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -1066,6 +1066,8 @@ static int read_idle_sma(struct hfi1_devdata *dd, u64 *data); static int thermal_init(struct hfi1_devdata *dd); static void update_statusp(struct hfi1_pportdata *ppd, u32 state); +static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd, + int msecs); static int wait_logical_linkstate(struct hfi1_pportdata *ppd, u32 state, int msecs); static void log_state_transition(struct hfi1_pportdata *ppd, u32 state); @@ -8238,6 +8240,7 @@ static irqreturn_t general_interrupt(int irq, void *data) u64 regs[CCE_NUM_INT_CSRS]; u32 bit; int i; + irqreturn_t handled = IRQ_NONE; this_cpu_inc(*dd->int_counter); @@ -8258,9 +8261,10 @@ static irqreturn_t general_interrupt(int irq, void *data) for_each_set_bit(bit, (unsigned long *)®s[0], CCE_NUM_INT_CSRS * 64) { is_interrupt(dd, bit); + handled = IRQ_HANDLED; } - return IRQ_HANDLED; + return handled; } static irqreturn_t sdma_interrupt(int irq, void *data) @@ -9413,7 +9417,7 @@ static void set_qsfp_int_n(struct hfi1_pportdata *ppd, u8 enable) write_csr(dd, dd->hfi1_id ? ASIC_QSFP2_MASK : ASIC_QSFP1_MASK, mask); } -void reset_qsfp(struct hfi1_pportdata *ppd) +int reset_qsfp(struct hfi1_pportdata *ppd) { struct hfi1_devdata *dd = ppd->dd; u64 mask, qsfp_mask; @@ -9443,6 +9447,13 @@ void reset_qsfp(struct hfi1_pportdata *ppd) * for alarms and warnings */ set_qsfp_int_n(ppd, 1); + + /* + * After the reset, AOC transmitters are enabled by default. They need + * to be turned off to complete the QSFP setup before they can be + * enabled again. + */ + return set_qsfp_tx(ppd, 0); } static int handle_qsfp_error_conditions(struct hfi1_pportdata *ppd, @@ -10305,6 +10316,7 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) { struct hfi1_devdata *dd = ppd->dd; u32 previous_state; + int offline_state_ret; int ret; update_lcb_cache(dd); @@ -10326,28 +10338,11 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) ppd->offline_disabled_reason = HFI1_ODR_MASK(OPA_LINKDOWN_REASON_TRANSIENT); - /* - * Wait for offline transition. It can take a while for - * the link to go down. - */ - ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 10000); - if (ret < 0) - return ret; - - /* - * Now in charge of LCB - must be after the physical state is - * offline.quiet and before host_link_state is changed. - */ - set_host_lcb_access(dd); - write_csr(dd, DC_LCB_ERR_EN, ~0ull); /* watch LCB errors */ - - /* make sure the logical state is also down */ - ret = wait_logical_linkstate(ppd, IB_PORT_DOWN, 1000); - if (ret) - force_logical_link_state_down(ppd); - - ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */ + offline_state_ret = wait_phys_link_offline_substates(ppd, 10000); + if (offline_state_ret < 0) + return offline_state_ret; + /* Disabling AOC transmitters */ if (ppd->port_type == PORT_TYPE_QSFP && ppd->qsfp_info.limiting_active && qsfp_mod_present(ppd)) { @@ -10365,6 +10360,30 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) } /* + * Wait for the offline.Quiet transition if it hasn't happened yet. It + * can take a while for the link to go down. + */ + if (offline_state_ret != PLS_OFFLINE_QUIET) { + ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 30000); + if (ret < 0) + return ret; + } + + /* + * Now in charge of LCB - must be after the physical state is + * offline.quiet and before host_link_state is changed. + */ + set_host_lcb_access(dd); + write_csr(dd, DC_LCB_ERR_EN, ~0ull); /* watch LCB errors */ + + /* make sure the logical state is also down */ + ret = wait_logical_linkstate(ppd, IB_PORT_DOWN, 1000); + if (ret) + force_logical_link_state_down(ppd); + + ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */ + + /* * The LNI has a mandatory wait time after the physical state * moves to Offline.Quiet. The wait time may be different * depending on how the link went down. The 8051 firmware @@ -10396,6 +10415,9 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) & (HLS_DN_POLL | HLS_VERIFY_CAP | HLS_GOING_UP)) { /* went down while attempting link up */ check_lni_states(ppd); + + /* The QSFP doesn't need to be reset on LNI failure */ + ppd->qsfp_info.reset_needed = 0; } /* the active link width (downgrade) is 0 on link down */ @@ -12804,6 +12826,39 @@ static int wait_physical_linkstate(struct hfi1_pportdata *ppd, u32 state, return 0; } +/* + * wait_phys_link_offline_quiet_substates - wait for any offline substate + * @ppd: port device + * @msecs: the number of milliseconds to wait + * + * Wait up to msecs milliseconds for any offline physical link + * state change to occur. + * Returns 0 if at least one state is reached, otherwise -ETIMEDOUT. + */ +static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd, + int msecs) +{ + u32 read_state; + unsigned long timeout; + + timeout = jiffies + msecs_to_jiffies(msecs); + while (1) { + read_state = read_physical_state(ppd->dd); + if ((read_state & 0xF0) == PLS_OFFLINE) + break; + if (time_after(jiffies, timeout)) { + dd_dev_err(ppd->dd, + "timeout waiting for phy link offline.quiet substates. Read state 0x%x, %dms\n", + read_state, msecs); + return -ETIMEDOUT; + } + usleep_range(1950, 2050); /* sleep 2ms-ish */ + } + + log_state_transition(ppd, read_state); + return read_state; +} + #define CLEAR_STATIC_RATE_CONTROL_SMASK(r) \ (r &= ~SEND_CTXT_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK) diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h index b8345a6..50b8645 100644 --- a/drivers/infiniband/hw/hfi1/chip.h +++ b/drivers/infiniband/hw/hfi1/chip.h @@ -204,6 +204,7 @@ #define PLS_OFFLINE_READY_TO_QUIET_LT 0x92 #define PLS_OFFLINE_REPORT_FAILURE 0x93 #define PLS_OFFLINE_READY_TO_QUIET_BCC 0x94 +#define PLS_OFFLINE_QUIET_DURATION 0x95 #define PLS_POLLING 0x20 #define PLS_POLLING_QUIET 0x20 #define PLS_POLLING_ACTIVE 0x21 @@ -722,7 +723,7 @@ void handle_link_downgrade(struct work_struct *work); void handle_link_bounce(struct work_struct *work); void handle_start_link(struct work_struct *work); void handle_sma_message(struct work_struct *work); -void reset_qsfp(struct hfi1_pportdata *ppd); +int reset_qsfp(struct hfi1_pportdata *ppd); void qsfp_event(struct work_struct *work); void start_freeze_handling(struct hfi1_pportdata *ppd, int flags); int send_idle_sma(struct hfi1_devdata *dd, u64 message); diff --git a/drivers/infiniband/hw/hfi1/eprom.c b/drivers/infiniband/hw/hfi1/eprom.c index d46b171..1613af1 100644 --- a/drivers/infiniband/hw/hfi1/eprom.c +++ b/drivers/infiniband/hw/hfi1/eprom.c @@ -204,7 +204,10 @@ done_asic: return ret; } -/* magic character sequence that trails an image */ +/* magic character sequence that begins an image */ +#define IMAGE_START_MAGIC "APO=" + +/* magic character sequence that might trail an image */ #define IMAGE_TRAIL_MAGIC "egamiAPO" /* EPROM file types */ @@ -250,6 +253,7 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data, { void *buffer; void *p; + u32 length; int ret; buffer = kmalloc(P1_SIZE, GFP_KERNEL); @@ -262,15 +266,21 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data, return ret; } - /* scan for image magic that may trail the actual data */ - p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE); - if (!p) { + /* config partition is valid only if it starts with IMAGE_START_MAGIC */ + if (memcmp(buffer, IMAGE_START_MAGIC, strlen(IMAGE_START_MAGIC))) { kfree(buffer); return -ENOENT; } + /* scan for image magic that may trail the actual data */ + p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE); + if (p) + length = p - buffer; + else + length = P1_SIZE; + *data = buffer; - *size = p - buffer; + *size = length; return 0; } diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 2bc8926..d9a1e98 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -930,15 +930,8 @@ static int assign_ctxt(struct hfi1_filedata *fd, struct hfi1_user_info *uinfo) switch (ret) { case 0: ret = setup_base_ctxt(fd, uctxt); - if (uctxt->subctxt_cnt) { - /* - * Base context is done (successfully or not), notify - * anybody using a sub-context that is waiting for - * this completion. - */ - clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags); - wake_up(&uctxt->wait); - } + if (ret) + deallocate_ctxt(uctxt); break; case 1: ret = complete_subctxt(fd); @@ -1305,25 +1298,25 @@ static int setup_base_ctxt(struct hfi1_filedata *fd, /* Now allocate the RcvHdr queue and eager buffers. */ ret = hfi1_create_rcvhdrq(dd, uctxt); if (ret) - return ret; + goto done; ret = hfi1_setup_eagerbufs(uctxt); if (ret) - goto setup_failed; + goto done; /* If sub-contexts are enabled, do the appropriate setup */ if (uctxt->subctxt_cnt) ret = setup_subctxt(uctxt); if (ret) - goto setup_failed; + goto done; ret = hfi1_alloc_ctxt_rcv_groups(uctxt); if (ret) - goto setup_failed; + goto done; ret = init_user_ctxt(fd, uctxt); if (ret) - goto setup_failed; + goto done; user_init(uctxt); @@ -1331,12 +1324,22 @@ static int setup_base_ctxt(struct hfi1_filedata *fd, fd->uctxt = uctxt; hfi1_rcd_get(uctxt); - return 0; +done: + if (uctxt->subctxt_cnt) { + /* + * On error, set the failed bit so sub-contexts will clean up + * correctly. + */ + if (ret) + set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags); -setup_failed: - /* Set the failed bit so sub-context init can do the right thing */ - set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags); - deallocate_ctxt(uctxt); + /* + * Base context is done (successfully or not), notify anybody + * using a sub-context that is waiting for this completion. + */ + clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags); + wake_up(&uctxt->wait); + } return ret; } diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index 82447b7..09e50fd 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -68,7 +68,7 @@ /* * Code to adjust PCIe capabilities. */ -static int tune_pcie_caps(struct hfi1_devdata *); +static void tune_pcie_caps(struct hfi1_devdata *); /* * Do all the common PCIe setup and initialization. @@ -351,7 +351,7 @@ int pcie_speeds(struct hfi1_devdata *dd) */ int request_msix(struct hfi1_devdata *dd, u32 msireq) { - int nvec, ret; + int nvec; nvec = pci_alloc_irq_vectors(dd->pcidev, 1, msireq, PCI_IRQ_MSIX | PCI_IRQ_LEGACY); @@ -360,12 +360,7 @@ int request_msix(struct hfi1_devdata *dd, u32 msireq) return nvec; } - ret = tune_pcie_caps(dd); - if (ret) { - dd_dev_err(dd, "tune_pcie_caps() failed: %d\n", ret); - pci_free_irq_vectors(dd->pcidev); - return ret; - } + tune_pcie_caps(dd); /* check for legacy IRQ */ if (nvec == 1 && !dd->pcidev->msix_enabled) @@ -502,7 +497,7 @@ uint aspm_mode = ASPM_MODE_DISABLED; module_param_named(aspm, aspm_mode, uint, S_IRUGO); MODULE_PARM_DESC(aspm, "PCIe ASPM: 0: disable, 1: enable, 2: dynamic"); -static int tune_pcie_caps(struct hfi1_devdata *dd) +static void tune_pcie_caps(struct hfi1_devdata *dd) { struct pci_dev *parent; u16 rc_mpss, rc_mps, ep_mpss, ep_mps; @@ -513,22 +508,14 @@ static int tune_pcie_caps(struct hfi1_devdata *dd) * Turn on extended tags in DevCtl in case the BIOS has turned it off * to improve WFR SDMA bandwidth */ - ret = pcie_capability_read_word(dd->pcidev, - PCI_EXP_DEVCTL, &ectl); - if (ret) { - dd_dev_err(dd, "Unable to read from PCI config\n"); - return ret; - } - - if (!(ectl & PCI_EXP_DEVCTL_EXT_TAG)) { + ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL, &ectl); + if ((!ret) && !(ectl & PCI_EXP_DEVCTL_EXT_TAG)) { dd_dev_info(dd, "Enabling PCIe extended tags\n"); ectl |= PCI_EXP_DEVCTL_EXT_TAG; ret = pcie_capability_write_word(dd->pcidev, PCI_EXP_DEVCTL, ectl); - if (ret) { - dd_dev_err(dd, "Unable to write to PCI config\n"); - return ret; - } + if (ret) + dd_dev_info(dd, "Unable to write to PCI config\n"); } /* Find out supported and configured values for parent (root) */ parent = dd->pcidev->bus->self; @@ -536,15 +523,22 @@ static int tune_pcie_caps(struct hfi1_devdata *dd) * The driver cannot perform the tuning if it does not have * access to the upstream component. */ - if (!parent) - return -EINVAL; + if (!parent) { + dd_dev_info(dd, "Parent not found\n"); + return; + } if (!pci_is_root_bus(parent->bus)) { dd_dev_info(dd, "Parent not root\n"); - return -EINVAL; + return; + } + if (!pci_is_pcie(parent)) { + dd_dev_info(dd, "Parent is not PCI Express capable\n"); + return; + } + if (!pci_is_pcie(dd->pcidev)) { + dd_dev_info(dd, "PCI device is not PCI Express capable\n"); + return; } - - if (!pci_is_pcie(parent) || !pci_is_pcie(dd->pcidev)) - return -EINVAL; rc_mpss = parent->pcie_mpss; rc_mps = ffs(pcie_get_mps(parent)) - 8; /* Find out supported and configured values for endpoint (us) */ @@ -590,8 +584,6 @@ static int tune_pcie_caps(struct hfi1_devdata *dd) ep_mrrs = max_mrrs; pcie_set_readrq(dd->pcidev, ep_mrrs); } - - return 0; } /* End of PCIe capability tuning */ diff --git a/drivers/infiniband/hw/hfi1/platform.c b/drivers/infiniband/hw/hfi1/platform.c index a8af96d..d486355 100644 --- a/drivers/infiniband/hw/hfi1/platform.c +++ b/drivers/infiniband/hw/hfi1/platform.c @@ -790,7 +790,9 @@ static int tune_active_qsfp(struct hfi1_pportdata *ppd, u32 *ptr_tx_preset, * reuse of stale settings established in our previous pass through. */ if (ppd->qsfp_info.reset_needed) { - reset_qsfp(ppd); + ret = reset_qsfp(ppd); + if (ret) + return ret; refresh_qsfp_cache(ppd, &ppd->qsfp_info); } else { ppd->qsfp_info.reset_needed = 1; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 05fb4bd..d6fbad8 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -778,13 +778,13 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, } if (MLX5_CAP_GEN(mdev, tag_matching)) { - props->xrq_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE; - props->xrq_caps.max_num_tags = + props->tm_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE; + props->tm_caps.max_num_tags = (1 << MLX5_CAP_GEN(mdev, log_tag_matching_list_sz)) - 1; - props->xrq_caps.flags = IB_TM_CAP_RC; - props->xrq_caps.max_ops = + props->tm_caps.flags = IB_TM_CAP_RC; + props->tm_caps.max_ops = 1 << MLX5_CAP_GEN(mdev, log_max_qp_sz); - props->xrq_caps.max_sge = MLX5_TM_MAX_SGE; + props->tm_caps.max_sge = MLX5_TM_MAX_SGE; } if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) { diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c index 914f212..f3dbd75 100644 --- a/drivers/infiniband/hw/mlx5/mem.c +++ b/drivers/infiniband/hw/mlx5/mem.c @@ -50,13 +50,9 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, { unsigned long tmp; unsigned long m; - int i, k; - u64 base = 0; - int p = 0; - int skip; - int mask; - u64 len; - u64 pfn; + u64 base = ~0, p = 0; + u64 len, pfn; + int i = 0; struct scatterlist *sg; int entry; unsigned long page_shift = umem->page_shift; @@ -76,33 +72,24 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, m = find_first_bit(&tmp, BITS_PER_LONG); if (max_page_shift) m = min_t(unsigned long, max_page_shift - page_shift, m); - skip = 1 << m; - mask = skip - 1; - i = 0; + for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) { len = sg_dma_len(sg) >> page_shift; pfn = sg_dma_address(sg) >> page_shift; - for (k = 0; k < len; k++) { - if (!(i & mask)) { - tmp = (unsigned long)pfn; - m = min_t(unsigned long, m, find_first_bit(&tmp, BITS_PER_LONG)); - skip = 1 << m; - mask = skip - 1; - base = pfn; - p = 0; - } else { - if (base + p != pfn) { - tmp = (unsigned long)p; - m = find_first_bit(&tmp, BITS_PER_LONG); - skip = 1 << m; - mask = skip - 1; - base = pfn; - p = 0; - } - } - p++; - i++; + if (base + p != pfn) { + /* If either the offset or the new + * base are unaligned update m + */ + tmp = (unsigned long)(pfn | p); + if (!IS_ALIGNED(tmp, 1 << m)) + m = find_first_bit(&tmp, BITS_PER_LONG); + + base = pfn; + p = 0; } + + p += len; + i += len; } if (i) { diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 0e2789d..37bbc54 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -47,7 +47,8 @@ enum { #define MLX5_UMR_ALIGN 2048 -static int clean_mr(struct mlx5_ib_mr *mr); +static int clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); +static int dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); static int mr_cache_max_order(struct mlx5_ib_dev *dev); static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); @@ -1270,8 +1271,9 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, err = mlx5_ib_update_xlt(mr, 0, ncont, page_shift, update_xlt_flags); + if (err) { - mlx5_ib_dereg_mr(&mr->ibmr); + dereg_mr(dev, mr); return ERR_PTR(err); } } @@ -1356,7 +1358,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, err = mr_umem_get(pd, addr, len, access_flags, &mr->umem, &npages, &page_shift, &ncont, &order); if (err < 0) { - clean_mr(mr); + clean_mr(dev, mr); return err; } } @@ -1410,7 +1412,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, if (err) { mlx5_ib_warn(dev, "Failed to rereg UMR\n"); ib_umem_release(mr->umem); - clean_mr(mr); + clean_mr(dev, mr); return err; } } @@ -1469,9 +1471,8 @@ mlx5_free_priv_descs(struct mlx5_ib_mr *mr) } } -static int clean_mr(struct mlx5_ib_mr *mr) +static int clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { - struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device); int allocated_from_cache = mr->allocated_from_cache; int err; @@ -1507,10 +1508,8 @@ static int clean_mr(struct mlx5_ib_mr *mr) return 0; } -int mlx5_ib_dereg_mr(struct ib_mr *ibmr) +static int dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { - struct mlx5_ib_dev *dev = to_mdev(ibmr->device); - struct mlx5_ib_mr *mr = to_mmr(ibmr); int npages = mr->npages; struct ib_umem *umem = mr->umem; @@ -1539,7 +1538,7 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr) } #endif - clean_mr(mr); + clean_mr(dev, mr); if (umem) { ib_umem_release(umem); @@ -1549,6 +1548,14 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr) return 0; } +int mlx5_ib_dereg_mr(struct ib_mr *ibmr) +{ + struct mlx5_ib_dev *dev = to_mdev(ibmr->device); + struct mlx5_ib_mr *mr = to_mmr(ibmr); + + return dereg_mr(dev, mr); +} + struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg) diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c index f0dc5f4..442b9bd 100644 --- a/drivers/infiniband/hw/nes/nes_verbs.c +++ b/drivers/infiniband/hw/nes/nes_verbs.c @@ -3232,7 +3232,7 @@ static int nes_post_send(struct ib_qp *ibqp, struct ib_send_wr *ib_wr, mr->ibmr.iova); set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_FMR_WQE_LENGTH_LOW_IDX, - mr->ibmr.length); + lower_32_bits(mr->ibmr.length)); set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_FMR_WQE_LENGTH_HIGH_IDX, 0); set_wqe_32bit_value(wqe->wqe_words, @@ -3274,7 +3274,7 @@ static int nes_post_send(struct ib_qp *ibqp, struct ib_send_wr *ib_wr, mr->npages * 8); nes_debug(NES_DBG_IW_TX, "SQ_REG_MR: iova_start: %llx, " - "length: %d, rkey: %0x, pgl_paddr: %llx, " + "length: %lld, rkey: %0x, pgl_paddr: %llx, " "page_list_len: %u, wqe_misc: %x\n", (unsigned long long) mr->ibmr.iova, mr->ibmr.length, diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 2e07537..6cd6163 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -1000,19 +1000,6 @@ static inline int update_parent_pkey(struct ipoib_dev_priv *priv) */ priv->dev->broadcast[8] = priv->pkey >> 8; priv->dev->broadcast[9] = priv->pkey & 0xff; - - /* - * Update the broadcast address in the priv->broadcast object, - * in case it already exists, otherwise no one will do that. - */ - if (priv->broadcast) { - spin_lock_irq(&priv->lock); - memcpy(priv->broadcast->mcmember.mgid.raw, - priv->dev->broadcast + 4, - sizeof(union ib_gid)); - spin_unlock_irq(&priv->lock); - } - return 0; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index bac95b5..dcc77014 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -2180,6 +2180,7 @@ static struct net_device *ipoib_add_port(const char *format, { struct ipoib_dev_priv *priv; struct ib_port_attr attr; + struct rdma_netdev *rn; int result = -ENOMEM; priv = ipoib_intf_alloc(hca, port, format); @@ -2279,7 +2280,8 @@ register_failed: ipoib_dev_cleanup(priv->dev); device_init_failed: - free_netdev(priv->dev); + rn = netdev_priv(priv->dev); + rn->free_rdma_netdev(priv->dev); kfree(priv); alloc_mem_failed: @@ -2328,7 +2330,7 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data) return; list_for_each_entry_safe(priv, tmp, dev_list, list) { - struct rdma_netdev *rn = netdev_priv(priv->dev); + struct rdma_netdev *parent_rn = netdev_priv(priv->dev); ib_unregister_event_handler(&priv->event_handler); flush_workqueue(ipoib_workqueue); @@ -2350,10 +2352,15 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data) unregister_netdev(priv->dev); mutex_unlock(&priv->sysfs_mutex); - rn->free_rdma_netdev(priv->dev); + parent_rn->free_rdma_netdev(priv->dev); + + list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) { + struct rdma_netdev *child_rn; - list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) + child_rn = netdev_priv(cpriv->dev); + child_rn->free_rdma_netdev(cpriv->dev); kfree(cpriv); + } kfree(priv); } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c index 9927cd6..55a9b71 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c @@ -141,14 +141,17 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) return restart_syscall(); } - priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name); - if (!priv) { + if (!down_write_trylock(&ppriv->vlan_rwsem)) { rtnl_unlock(); mutex_unlock(&ppriv->sysfs_mutex); - return -ENOMEM; + return restart_syscall(); } - down_write(&ppriv->vlan_rwsem); + priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name); + if (!priv) { + result = -ENOMEM; + goto out; + } /* * First ensure this isn't a duplicate. We check the parent device and @@ -175,8 +178,11 @@ out: rtnl_unlock(); mutex_unlock(&ppriv->sysfs_mutex); - if (result) { - free_netdev(priv->dev); + if (result && priv) { + struct rdma_netdev *rn; + + rn = netdev_priv(priv->dev); + rn->free_rdma_netdev(priv->dev); kfree(priv); } @@ -204,7 +210,12 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey) return restart_syscall(); } - down_write(&ppriv->vlan_rwsem); + if (!down_write_trylock(&ppriv->vlan_rwsem)) { + rtnl_unlock(); + mutex_unlock(&ppriv->sysfs_mutex); + return restart_syscall(); + } + list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) { if (priv->pkey == pkey && priv->child_type == IPOIB_LEGACY_CHILD) { @@ -224,7 +235,10 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey) mutex_unlock(&ppriv->sysfs_mutex); if (dev) { - free_netdev(dev); + struct rdma_netdev *rn; + + rn = netdev_priv(dev); + rn->free_rdma_netdev(priv->dev); kfree(priv); return 0; } diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c index 9c3e9ab..322209d 100644 --- a/drivers/infiniband/ulp/iser/iser_memory.c +++ b/drivers/infiniband/ulp/iser/iser_memory.c @@ -154,7 +154,7 @@ static void iser_dump_page_vec(struct iser_page_vec *page_vec) { int i; - iser_err("page vec npages %d data length %d\n", + iser_err("page vec npages %d data length %lld\n", page_vec->npages, page_vec->fake_mr.length); for (i = 0; i < page_vec->npages; i++) iser_err("vec[%d]: %llx\n", i, page_vec->pages[i]); diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 382de42..6fe2d03 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -874,7 +874,7 @@ static bool copy_device_table(void) hi = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET + 4); entry = (((u64) hi) << 32) + lo; if (last_entry && last_entry != entry) { - pr_err("IOMMU:%d should use the same dev table as others!/n", + pr_err("IOMMU:%d should use the same dev table as others!\n", iommu->index); return false; } @@ -882,7 +882,7 @@ static bool copy_device_table(void) old_devtb_size = ((entry & ~PAGE_MASK) + 1) << 12; if (old_devtb_size != dev_table_size) { - pr_err("The device table size of IOMMU:%d is not expected!/n", + pr_err("The device table size of IOMMU:%d is not expected!\n", iommu->index); return false; } @@ -890,7 +890,7 @@ static bool copy_device_table(void) old_devtb_phys = entry & PAGE_MASK; if (old_devtb_phys >= 0x100000000ULL) { - pr_err("The address of old device table is above 4G, not trustworthy!/n"); + pr_err("The address of old device table is above 4G, not trustworthy!\n"); return false; } old_devtb = memremap(old_devtb_phys, dev_table_size, MEMREMAP_WB); @@ -901,7 +901,7 @@ static bool copy_device_table(void) old_dev_tbl_cpy = (void *)__get_free_pages(gfp_flag, get_order(dev_table_size)); if (old_dev_tbl_cpy == NULL) { - pr_err("Failed to allocate memory for copying old device table!/n"); + pr_err("Failed to allocate memory for copying old device table!\n"); return false; } diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index d665d0d..6961fc3 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -245,7 +245,7 @@ static void __arm_v7s_free_table(void *table, int lvl, static void __arm_v7s_pte_sync(arm_v7s_iopte *ptep, int num_entries, struct io_pgtable_cfg *cfg) { - if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) + if (cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA) return; dma_sync_single_for_device(cfg->iommu_dev, __arm_v7s_dma_addr(ptep), diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index bd515be..16d33ac 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -371,7 +371,8 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova, int ret; spin_lock_irqsave(&dom->pgtlock, flags); - ret = dom->iop->map(dom->iop, iova, paddr, size, prot); + ret = dom->iop->map(dom->iop, iova, paddr & DMA_BIT_MASK(32), + size, prot); spin_unlock_irqrestore(&dom->pgtlock, flags); return ret; diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 40159ac..c90976d 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -175,14 +175,13 @@ static void gic_mask_irq(struct irq_data *d) static void gic_unmask_irq(struct irq_data *d) { - struct cpumask *affinity = irq_data_get_affinity_mask(d); unsigned int intr = GIC_HWIRQ_TO_SHARED(d->hwirq); unsigned int cpu; write_gic_smask(intr); gic_clear_pcpu_masks(intr); - cpu = cpumask_first_and(affinity, cpu_online_mask); + cpu = cpumask_first(irq_data_get_effective_affinity_mask(d)); set_bit(intr, per_cpu_ptr(pcpu_masks, cpu)); } @@ -420,13 +419,17 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hw, unsigned int cpu) { int intr = GIC_HWIRQ_TO_SHARED(hw); + struct irq_data *data; unsigned long flags; + data = irq_get_irq_data(virq); + spin_lock_irqsave(&gic_lock, flags); write_gic_map_pin(intr, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin); write_gic_map_vp(intr, BIT(mips_cm_vp_id(cpu))); gic_clear_pcpu_masks(intr); set_bit(intr, per_cpu_ptr(pcpu_masks, cpu)); + irq_data_update_effective_affinity(data, cpumask_of(cpu)); spin_unlock_irqrestore(&gic_lock, flags); return 0; @@ -645,7 +648,7 @@ static int __init gic_of_init(struct device_node *node, /* Find the first available CPU vector. */ i = 0; - reserved = (C_SW0 | C_SW1) >> __fls(C_SW0); + reserved = (C_SW0 | C_SW1) >> __ffs(C_SW0); while (!of_property_read_u32_index(node, "mti,reserved-cpu-vectors", i++, &cpu_vec)) reserved |= BIT(cpu_vec); @@ -684,11 +687,11 @@ static int __init gic_of_init(struct device_node *node, gicconfig = read_gic_config(); gic_shared_intrs = gicconfig & GIC_CONFIG_NUMINTERRUPTS; - gic_shared_intrs >>= __fls(GIC_CONFIG_NUMINTERRUPTS); + gic_shared_intrs >>= __ffs(GIC_CONFIG_NUMINTERRUPTS); gic_shared_intrs = (gic_shared_intrs + 1) * 8; gic_vpes = gicconfig & GIC_CONFIG_PVPS; - gic_vpes >>= __fls(GIC_CONFIG_PVPS); + gic_vpes >>= __ffs(GIC_CONFIG_PVPS); gic_vpes = gic_vpes + 1; if (cpu_has_veic) { diff --git a/drivers/leds/leds-as3645a.c b/drivers/leds/leds-as3645a.c index bbbbe08..9a257f9 100644 --- a/drivers/leds/leds-as3645a.c +++ b/drivers/leds/leds-as3645a.c @@ -112,6 +112,10 @@ #define AS_PEAK_mA_TO_REG(a) \ ((min_t(u32, AS_PEAK_mA_MAX, a) - 1250) / 250) +/* LED numbers for Devicetree */ +#define AS_LED_FLASH 0 +#define AS_LED_INDICATOR 1 + enum as_mode { AS_MODE_EXT_TORCH = 0 << AS_CONTROL_MODE_SETTING_SHIFT, AS_MODE_INDICATOR = 1 << AS_CONTROL_MODE_SETTING_SHIFT, @@ -491,10 +495,29 @@ static int as3645a_parse_node(struct as3645a *flash, struct device_node *node) { struct as3645a_config *cfg = &flash->cfg; + struct device_node *child; const char *name; int rval; - flash->flash_node = of_get_child_by_name(node, "flash"); + for_each_child_of_node(node, child) { + u32 id = 0; + + of_property_read_u32(child, "reg", &id); + + switch (id) { + case AS_LED_FLASH: + flash->flash_node = of_node_get(child); + break; + case AS_LED_INDICATOR: + flash->indicator_node = of_node_get(child); + break; + default: + dev_warn(&flash->client->dev, + "unknown LED %u encountered, ignoring\n", id); + break; + } + } + if (!flash->flash_node) { dev_err(&flash->client->dev, "can't find flash node\n"); return -ENODEV; @@ -534,11 +557,10 @@ static int as3645a_parse_node(struct as3645a *flash, of_property_read_u32(flash->flash_node, "voltage-reference", &cfg->voltage_reference); - of_property_read_u32(flash->flash_node, "peak-current-limit", + of_property_read_u32(flash->flash_node, "ams,input-max-microamp", &cfg->peak); cfg->peak = AS_PEAK_mA_TO_REG(cfg->peak); - flash->indicator_node = of_get_child_by_name(node, "indicator"); if (!flash->indicator_node) { dev_warn(&flash->client->dev, "can't find indicator node\n"); @@ -721,6 +743,7 @@ static int as3645a_remove(struct i2c_client *client) as3645a_set_control(flash, AS_MODE_EXT_TORCH, false); v4l2_flash_release(flash->vf); + v4l2_flash_release(flash->vfind); led_classdev_flash_unregister(&flash->fled); led_classdev_unregister(&flash->iled_cdev); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 5bfe285..1ac58c5 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3238,7 +3238,7 @@ static int raid_map(struct dm_target *ti, struct bio *bio) if (unlikely(bio_end_sector(bio) > mddev->array_sectors)) return DM_MAPIO_REQUEUE; - mddev->pers->make_request(mddev, bio); + md_handle_request(mddev, bio); return DM_MAPIO_SUBMITTED; } diff --git a/drivers/md/md.c b/drivers/md/md.c index 08fcaeb..0ff1bbf 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -266,6 +266,37 @@ static DEFINE_SPINLOCK(all_mddevs_lock); * call has finished, the bio has been linked into some internal structure * and so is visible to ->quiesce(), so we don't need the refcount any more. */ +void md_handle_request(struct mddev *mddev, struct bio *bio) +{ +check_suspended: + rcu_read_lock(); + if (mddev->suspended) { + DEFINE_WAIT(__wait); + for (;;) { + prepare_to_wait(&mddev->sb_wait, &__wait, + TASK_UNINTERRUPTIBLE); + if (!mddev->suspended) + break; + rcu_read_unlock(); + schedule(); + rcu_read_lock(); + } + finish_wait(&mddev->sb_wait, &__wait); + } + atomic_inc(&mddev->active_io); + rcu_read_unlock(); + + if (!mddev->pers->make_request(mddev, bio)) { + atomic_dec(&mddev->active_io); + wake_up(&mddev->sb_wait); + goto check_suspended; + } + + if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) + wake_up(&mddev->sb_wait); +} +EXPORT_SYMBOL(md_handle_request); + static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) { const int rw = bio_data_dir(bio); @@ -285,23 +316,6 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) bio_endio(bio); return BLK_QC_T_NONE; } -check_suspended: - rcu_read_lock(); - if (mddev->suspended) { - DEFINE_WAIT(__wait); - for (;;) { - prepare_to_wait(&mddev->sb_wait, &__wait, - TASK_UNINTERRUPTIBLE); - if (!mddev->suspended) - break; - rcu_read_unlock(); - schedule(); - rcu_read_lock(); - } - finish_wait(&mddev->sb_wait, &__wait); - } - atomic_inc(&mddev->active_io); - rcu_read_unlock(); /* * save the sectors now since our bio can @@ -310,20 +324,14 @@ check_suspended: sectors = bio_sectors(bio); /* bio could be mergeable after passing to underlayer */ bio->bi_opf &= ~REQ_NOMERGE; - if (!mddev->pers->make_request(mddev, bio)) { - atomic_dec(&mddev->active_io); - wake_up(&mddev->sb_wait); - goto check_suspended; - } + + md_handle_request(mddev, bio); cpu = part_stat_lock(); part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors); part_stat_unlock(); - if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) - wake_up(&mddev->sb_wait); - return BLK_QC_T_NONE; } @@ -439,16 +447,22 @@ static void md_submit_flush_data(struct work_struct *ws) struct mddev *mddev = container_of(ws, struct mddev, flush_work); struct bio *bio = mddev->flush_bio; + /* + * must reset flush_bio before calling into md_handle_request to avoid a + * deadlock, because other bios passed md_handle_request suspend check + * could wait for this and below md_handle_request could wait for those + * bios because of suspend check + */ + mddev->flush_bio = NULL; + wake_up(&mddev->sb_wait); + if (bio->bi_iter.bi_size == 0) /* an empty barrier - all done */ bio_endio(bio); else { bio->bi_opf &= ~REQ_PREFLUSH; - mddev->pers->make_request(mddev, bio); + md_handle_request(mddev, bio); } - - mddev->flush_bio = NULL; - wake_up(&mddev->sb_wait); } void md_flush_request(struct mddev *mddev, struct bio *bio) diff --git a/drivers/md/md.h b/drivers/md/md.h index 561d22b..d8287d3 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -692,6 +692,7 @@ extern void md_stop_writes(struct mddev *mddev); extern int md_rdev_init(struct md_rdev *rdev); extern void md_rdev_clear(struct md_rdev *rdev); +extern void md_handle_request(struct mddev *mddev, struct bio *bio); extern void mddev_suspend(struct mddev *mddev); extern void mddev_resume(struct mddev *mddev); extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 0764094..928e24a 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6575,14 +6575,17 @@ static ssize_t raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len) { struct r5conf *conf; - unsigned long new; + unsigned int new; int err; struct r5worker_group *new_groups, *old_groups; int group_cnt, worker_cnt_per_group; if (len >= PAGE_SIZE) return -EINVAL; - if (kstrtoul(page, 10, &new)) + if (kstrtouint(page, 10, &new)) + return -EINVAL; + /* 8192 should be big enough */ + if (new > 8192) return -EINVAL; err = mddev_lock(mddev); diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index bbaddf1..d0ccc67 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -392,6 +392,7 @@ static const struct sdhci_pci_fixes sdhci_intel_pch_sdio = { enum { INTEL_DSM_FNS = 0, + INTEL_DSM_V18_SWITCH = 3, INTEL_DSM_DRV_STRENGTH = 9, INTEL_DSM_D3_RETUNE = 10, }; @@ -557,6 +558,19 @@ static void intel_hs400_enhanced_strobe(struct mmc_host *mmc, sdhci_writel(host, val, INTEL_HS400_ES_REG); } +static void sdhci_intel_voltage_switch(struct sdhci_host *host) +{ + struct sdhci_pci_slot *slot = sdhci_priv(host); + struct intel_host *intel_host = sdhci_pci_priv(slot); + struct device *dev = &slot->chip->pdev->dev; + u32 result = 0; + int err; + + err = intel_dsm(intel_host, dev, INTEL_DSM_V18_SWITCH, &result); + pr_debug("%s: %s DSM error %d result %u\n", + mmc_hostname(host->mmc), __func__, err, result); +} + static const struct sdhci_ops sdhci_intel_byt_ops = { .set_clock = sdhci_set_clock, .set_power = sdhci_intel_set_power, @@ -565,6 +579,7 @@ static const struct sdhci_ops sdhci_intel_byt_ops = { .reset = sdhci_reset, .set_uhs_signaling = sdhci_set_uhs_signaling, .hw_reset = sdhci_pci_hw_reset, + .voltage_switch = sdhci_intel_voltage_switch, }; static void byt_read_dsm(struct sdhci_pci_slot *slot) diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index 12cf828..a7293e1 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -129,50 +129,6 @@ static int tmio_mmc_next_sg(struct tmio_mmc_host *host) #define CMDREQ_TIMEOUT 5000 -#ifdef CONFIG_MMC_DEBUG - -#define STATUS_TO_TEXT(a, status, i) \ - do { \ - if ((status) & TMIO_STAT_##a) { \ - if ((i)++) \ - printk(KERN_DEBUG " | "); \ - printk(KERN_DEBUG #a); \ - } \ - } while (0) - -static void pr_debug_status(u32 status) -{ - int i = 0; - - pr_debug("status: %08x = ", status); - STATUS_TO_TEXT(CARD_REMOVE, status, i); - STATUS_TO_TEXT(CARD_INSERT, status, i); - STATUS_TO_TEXT(SIGSTATE, status, i); - STATUS_TO_TEXT(WRPROTECT, status, i); - STATUS_TO_TEXT(CARD_REMOVE_A, status, i); - STATUS_TO_TEXT(CARD_INSERT_A, status, i); - STATUS_TO_TEXT(SIGSTATE_A, status, i); - STATUS_TO_TEXT(CMD_IDX_ERR, status, i); - STATUS_TO_TEXT(STOPBIT_ERR, status, i); - STATUS_TO_TEXT(ILL_FUNC, status, i); - STATUS_TO_TEXT(CMD_BUSY, status, i); - STATUS_TO_TEXT(CMDRESPEND, status, i); - STATUS_TO_TEXT(DATAEND, status, i); - STATUS_TO_TEXT(CRCFAIL, status, i); - STATUS_TO_TEXT(DATATIMEOUT, status, i); - STATUS_TO_TEXT(CMDTIMEOUT, status, i); - STATUS_TO_TEXT(RXOVERFLOW, status, i); - STATUS_TO_TEXT(TXUNDERRUN, status, i); - STATUS_TO_TEXT(RXRDY, status, i); - STATUS_TO_TEXT(TXRQ, status, i); - STATUS_TO_TEXT(ILL_ACCESS, status, i); - printk("\n"); -} - -#else -#define pr_debug_status(s) do { } while (0) -#endif - static void tmio_mmc_enable_sdio_irq(struct mmc_host *mmc, int enable) { struct tmio_mmc_host *host = mmc_priv(mmc); @@ -762,9 +718,6 @@ irqreturn_t tmio_mmc_irq(int irq, void *devid) status = sd_ctrl_read16_and_16_as_32(host, CTL_STATUS); ireg = status & TMIO_MASK_IRQ & ~host->sdcard_irq_mask; - pr_debug_status(status); - pr_debug_status(ireg); - /* Clear the status except the interrupt status */ sd_ctrl_write32_as_16_and_16(host, CTL_STATUS, TMIO_MASK_IRQ); diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 5736b0c..a308e70 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -581,6 +581,14 @@ static struct mtd_part *allocate_partition(struct mtd_info *parent, slave->mtd.erasesize = parent->erasesize; } + /* + * Slave erasesize might differ from the master one if the master + * exposes several regions with different erasesize. Adjust + * wr_alignment accordingly. + */ + if (!(slave->mtd.flags & MTD_NO_ERASE)) + wr_alignment = slave->mtd.erasesize; + tmp = slave->offset; remainder = do_div(tmp, wr_alignment); if ((slave->mtd.flags & MTD_WRITEABLE) && remainder) { diff --git a/drivers/mtd/nand/atmel/pmecc.c b/drivers/mtd/nand/atmel/pmecc.c index 146af821..8268636 100644 --- a/drivers/mtd/nand/atmel/pmecc.c +++ b/drivers/mtd/nand/atmel/pmecc.c @@ -363,7 +363,7 @@ atmel_pmecc_create_user(struct atmel_pmecc *pmecc, size += (req->ecc.strength + 1) * sizeof(u16); /* Reserve space for mu, dmu and delta. */ size = ALIGN(size, sizeof(s32)); - size += (req->ecc.strength + 1) * sizeof(s32); + size += (req->ecc.strength + 1) * sizeof(s32) * 3; user = kzalloc(size, GFP_KERNEL); if (!user) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index acc816b..bb2aad0 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -134,8 +134,6 @@ static inline bool nvme_req_needs_retry(struct request *req) return false; if (nvme_req(req)->status & NVME_SC_DNR) return false; - if (jiffies - req->start_time >= req->timeout) - return false; if (nvme_req(req)->retries >= nvme_max_retries) return false; return true; @@ -2590,7 +2588,7 @@ static void nvme_async_event_work(struct work_struct *work) container_of(work, struct nvme_ctrl, async_event_work); spin_lock_irq(&ctrl->lock); - while (ctrl->event_limit > 0) { + while (ctrl->state == NVME_CTRL_LIVE && ctrl->event_limit > 0) { int aer_idx = --ctrl->event_limit; spin_unlock_irq(&ctrl->lock); @@ -2677,7 +2675,8 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, /*FALLTHRU*/ case NVME_SC_ABORT_REQ: ++ctrl->event_limit; - queue_work(nvme_wq, &ctrl->async_event_work); + if (ctrl->state == NVME_CTRL_LIVE) + queue_work(nvme_wq, &ctrl->async_event_work); break; default: break; @@ -2692,7 +2691,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, nvme_queue_scan(ctrl); break; case NVME_AER_NOTICE_FW_ACT_STARTING: - schedule_work(&ctrl->fw_act_work); + queue_work(nvme_wq, &ctrl->fw_act_work); break; default: dev_warn(ctrl->device, "async event result %08x\n", result); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 4730775..555c976 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -565,6 +565,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, opts->queue_size = NVMF_DEF_QUEUE_SIZE; opts->nr_io_queues = num_online_cpus(); opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY; + opts->kato = NVME_DEFAULT_KATO; options = o = kstrdup(buf, GFP_KERNEL); if (!options) @@ -655,21 +656,22 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, goto out; } - if (opts->discovery_nqn) { - pr_err("Discovery controllers cannot accept keep_alive_tmo != 0\n"); - ret = -EINVAL; - goto out; - } - if (token < 0) { pr_err("Invalid keep_alive_tmo %d\n", token); ret = -EINVAL; goto out; - } else if (token == 0) { + } else if (token == 0 && !opts->discovery_nqn) { /* Allowed for debug */ pr_warn("keep_alive_tmo 0 won't execute keep alives!!!\n"); } opts->kato = token; + + if (opts->discovery_nqn && opts->kato) { + pr_err("Discovery controllers cannot accept KATO != 0\n"); + ret = -EINVAL; + goto out; + } + break; case NVMF_OPT_CTRL_LOSS_TMO: if (match_int(args, &token)) { @@ -762,8 +764,6 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, uuid_copy(&opts->host->id, &hostid); out: - if (!opts->discovery_nqn && !opts->kato) - opts->kato = NVME_DEFAULT_KATO; kfree(options); return ret; } diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index d2e882c..af075e9 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1376,7 +1376,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) if (atomic_read(&op->state) == FCPOP_STATE_ABORTED) status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1); else if (freq->status) - status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1); + status = cpu_to_le16(NVME_SC_INTERNAL << 1); /* * For the linux implementation, if we have an unsuccesful @@ -1404,7 +1404,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) */ if (freq->transferred_length != be32_to_cpu(op->cmd_iu.data_len)) { - status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1); + status = cpu_to_le16(NVME_SC_INTERNAL << 1); goto done; } result.u64 = 0; @@ -1421,7 +1421,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) freq->transferred_length || op->rsp_iu.status_code || sqe->common.command_id != cqe->command_id)) { - status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1); + status = cpu_to_le16(NVME_SC_INTERNAL << 1); goto done; } result = cqe->result; @@ -1429,7 +1429,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) break; default: - status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1); + status = cpu_to_le16(NVME_SC_INTERNAL << 1); goto done; } @@ -1989,16 +1989,17 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, * as well as those by FC-NVME spec. */ WARN_ON_ONCE(sqe->common.metadata); - WARN_ON_ONCE(sqe->common.dptr.prp1); - WARN_ON_ONCE(sqe->common.dptr.prp2); sqe->common.flags |= NVME_CMD_SGL_METABUF; /* - * format SQE DPTR field per FC-NVME rules - * type=data block descr; subtype=offset; - * offset is currently 0. + * format SQE DPTR field per FC-NVME rules: + * type=0x5 Transport SGL Data Block Descriptor + * subtype=0xA Transport-specific value + * address=0 + * length=length of the data series */ - sqe->rw.dptr.sgl.type = NVME_SGL_FMT_OFFSET; + sqe->rw.dptr.sgl.type = (NVME_TRANSPORT_SGL_DATA_DESC << 4) | + NVME_SGL_FMT_TRANSPORT_A; sqe->rw.dptr.sgl.length = cpu_to_le32(data_len); sqe->rw.dptr.sgl.addr = 0; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 4a21213..cb73bc8 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -24,6 +24,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/mutex.h> +#include <linux/once.h> #include <linux/pci.h> #include <linux/poison.h> #include <linux/t10-pi.h> @@ -540,6 +541,20 @@ static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi) } #endif +static void nvme_print_sgl(struct scatterlist *sgl, int nents) +{ + int i; + struct scatterlist *sg; + + for_each_sg(sgl, sg, nents, i) { + dma_addr_t phys = sg_phys(sg); + pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d " + "dma_address:%pad dma_length:%d\n", + i, &phys, sg->offset, sg->length, &sg_dma_address(sg), + sg_dma_len(sg)); + } +} + static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); @@ -622,19 +637,10 @@ static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req) return BLK_STS_OK; bad_sgl: - if (WARN_ONCE(1, "Invalid SGL for payload:%d nents:%d\n", - blk_rq_payload_bytes(req), iod->nents)) { - for_each_sg(iod->sg, sg, iod->nents, i) { - dma_addr_t phys = sg_phys(sg); - pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d " - "dma_address:%pad dma_length:%d\n", i, &phys, - sg->offset, sg->length, - &sg_dma_address(sg), - sg_dma_len(sg)); - } - } + WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents), + "Invalid SGL for payload:%d nents:%d\n", + blk_rq_payload_bytes(req), iod->nents); return BLK_STS_IOERR; - } static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, @@ -1313,11 +1319,11 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid) if (result < 0) goto release_cq; + nvme_init_queue(nvmeq, qid); result = queue_request_irq(nvmeq); if (result < 0) goto release_sq; - nvme_init_queue(nvmeq, qid); return result; release_sq: @@ -1464,6 +1470,7 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev) return result; nvmeq->cq_vector = 0; + nvme_init_queue(nvmeq, 0); result = queue_request_irq(nvmeq); if (result) { nvmeq->cq_vector = -1; @@ -2156,7 +2163,6 @@ static void nvme_reset_work(struct work_struct *work) if (result) goto out; - nvme_init_queue(dev->queues[0], 0); result = nvme_alloc_admin_tags(dev); if (result) goto out; diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 5898300..92a03ff 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -942,7 +942,12 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) } changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); - WARN_ON_ONCE(!changed); + if (!changed) { + /* state change failure is ok if we're in DELETING state */ + WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING); + return; + } + ctrl->ctrl.nr_reconnects = 0; nvme_start_ctrl(&ctrl->ctrl); @@ -962,7 +967,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) struct nvme_rdma_ctrl *ctrl = container_of(work, struct nvme_rdma_ctrl, err_work); - nvme_stop_ctrl(&ctrl->ctrl); + nvme_stop_keep_alive(&ctrl->ctrl); if (ctrl->ctrl.queue_count > 1) { nvme_stop_queues(&ctrl->ctrl); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 7c23eaf..1b208be 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -390,10 +390,10 @@ static void __nvmet_req_complete(struct nvmet_req *req, u16 status) if (status) nvmet_set_status(req, status); - /* XXX: need to fill in something useful for sq_head */ - req->rsp->sq_head = 0; - if (likely(req->sq)) /* may happen during early failure */ - req->rsp->sq_id = cpu_to_le16(req->sq->qid); + if (req->sq->size) + req->sq->sqhd = (req->sq->sqhd + 1) % req->sq->size; + req->rsp->sq_head = cpu_to_le16(req->sq->sqhd); + req->rsp->sq_id = cpu_to_le16(req->sq->qid); req->rsp->command_id = req->cmd->common.command_id; if (req->ns) @@ -420,6 +420,7 @@ void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq, void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, u16 qid, u16 size) { + sq->sqhd = 0; sq->qid = qid; sq->size = size; diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 859a667..db3bf6b 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -109,9 +109,14 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req) pr_warn("queue already connected!\n"); return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR; } + if (!sqsize) { + pr_warn("queue size zero!\n"); + return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR; + } - nvmet_cq_setup(ctrl, req->cq, qid, sqsize); - nvmet_sq_setup(ctrl, req->sq, qid, sqsize); + /* note: convert queue size from 0's-based value to 1's-based value */ + nvmet_cq_setup(ctrl, req->cq, qid, sqsize + 1); + nvmet_sq_setup(ctrl, req->sq, qid, sqsize + 1); return 0; } diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 421e43b..58e010b 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -148,7 +148,7 @@ struct nvmet_fc_tgt_assoc { u32 a_id; struct nvmet_fc_tgtport *tgtport; struct list_head a_list; - struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES]; + struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES + 1]; struct kref ref; }; @@ -608,7 +608,7 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, unsigned long flags; int ret; - if (qid >= NVMET_NR_QUEUES) + if (qid > NVMET_NR_QUEUES) return NULL; queue = kzalloc((sizeof(*queue) + @@ -783,6 +783,9 @@ nvmet_fc_find_target_queue(struct nvmet_fc_tgtport *tgtport, u16 qid = nvmet_fc_getqueueid(connection_id); unsigned long flags; + if (qid > NVMET_NR_QUEUES) + return NULL; + spin_lock_irqsave(&tgtport->lock, flags); list_for_each_entry(assoc, &tgtport->assoc_list, a_list) { if (association_id == assoc->association_id) { @@ -888,7 +891,7 @@ nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc) int i; spin_lock_irqsave(&tgtport->lock, flags); - for (i = NVMET_NR_QUEUES - 1; i >= 0; i--) { + for (i = NVMET_NR_QUEUES; i >= 0; i--) { queue = assoc->queues[i]; if (queue) { if (!nvmet_fc_tgt_q_get(queue)) @@ -1910,8 +1913,7 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport, spin_lock_irqsave(&fod->flock, flags); fod->writedataactive = false; spin_unlock_irqrestore(&fod->flock, flags); - nvmet_req_complete(&fod->req, - NVME_SC_FC_TRANSPORT_ERROR); + nvmet_req_complete(&fod->req, NVME_SC_INTERNAL); } else /* NVMET_FCOP_READDATA or NVMET_FCOP_READDATA_RSP */ { fcpreq->fcp_error = ret; fcpreq->transferred_length = 0; @@ -1929,8 +1931,7 @@ __nvmet_fc_fod_op_abort(struct nvmet_fc_fcp_iod *fod, bool abort) /* if in the middle of an io and we need to tear down */ if (abort) { if (fcpreq->op == NVMET_FCOP_WRITEDATA) { - nvmet_req_complete(&fod->req, - NVME_SC_FC_TRANSPORT_ERROR); + nvmet_req_complete(&fod->req, NVME_SC_INTERNAL); return true; } @@ -1968,8 +1969,7 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod) fod->abort = true; spin_unlock(&fod->flock); - nvmet_req_complete(&fod->req, - NVME_SC_FC_TRANSPORT_ERROR); + nvmet_req_complete(&fod->req, NVME_SC_INTERNAL); return; } @@ -2533,13 +2533,17 @@ nvmet_fc_remove_port(struct nvmet_port *port) { struct nvmet_fc_tgtport *tgtport = port->priv; unsigned long flags; + bool matched = false; spin_lock_irqsave(&nvmet_fc_tgtlock, flags); if (tgtport->port == port) { - nvmet_fc_tgtport_put(tgtport); + matched = true; tgtport->port = NULL; } spin_unlock_irqrestore(&nvmet_fc_tgtlock, flags); + + if (matched) + nvmet_fc_tgtport_put(tgtport); } static struct nvmet_fabrics_ops nvmet_fc_tgt_fcp_ops = { diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 1cb9847..7b75d9d 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -224,8 +224,6 @@ struct fcloop_nport { struct fcloop_lport *lport; struct list_head nport_list; struct kref ref; - struct completion rport_unreg_done; - struct completion tport_unreg_done; u64 node_name; u64 port_name; u32 port_role; @@ -576,7 +574,7 @@ fcloop_tgt_fcp_abort(struct nvmet_fc_target_port *tgtport, tfcp_req->aborted = true; spin_unlock(&tfcp_req->reqlock); - tfcp_req->status = NVME_SC_FC_TRANSPORT_ABORTED; + tfcp_req->status = NVME_SC_INTERNAL; /* * nothing more to do. If io wasn't active, the transport should @@ -631,6 +629,32 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport, } static void +fcloop_nport_free(struct kref *ref) +{ + struct fcloop_nport *nport = + container_of(ref, struct fcloop_nport, ref); + unsigned long flags; + + spin_lock_irqsave(&fcloop_lock, flags); + list_del(&nport->nport_list); + spin_unlock_irqrestore(&fcloop_lock, flags); + + kfree(nport); +} + +static void +fcloop_nport_put(struct fcloop_nport *nport) +{ + kref_put(&nport->ref, fcloop_nport_free); +} + +static int +fcloop_nport_get(struct fcloop_nport *nport) +{ + return kref_get_unless_zero(&nport->ref); +} + +static void fcloop_localport_delete(struct nvme_fc_local_port *localport) { struct fcloop_lport *lport = localport->private; @@ -644,8 +668,7 @@ fcloop_remoteport_delete(struct nvme_fc_remote_port *remoteport) { struct fcloop_rport *rport = remoteport->private; - /* release any threads waiting for the unreg to complete */ - complete(&rport->nport->rport_unreg_done); + fcloop_nport_put(rport->nport); } static void @@ -653,8 +676,7 @@ fcloop_targetport_delete(struct nvmet_fc_target_port *targetport) { struct fcloop_tport *tport = targetport->private; - /* release any threads waiting for the unreg to complete */ - complete(&tport->nport->tport_unreg_done); + fcloop_nport_put(tport->nport); } #define FCLOOP_HW_QUEUES 4 @@ -722,6 +744,7 @@ fcloop_create_local_port(struct device *dev, struct device_attribute *attr, goto out_free_opts; } + memset(&pinfo, 0, sizeof(pinfo)); pinfo.node_name = opts->wwnn; pinfo.port_name = opts->wwpn; pinfo.port_role = opts->roles; @@ -804,32 +827,6 @@ fcloop_delete_local_port(struct device *dev, struct device_attribute *attr, return ret ? ret : count; } -static void -fcloop_nport_free(struct kref *ref) -{ - struct fcloop_nport *nport = - container_of(ref, struct fcloop_nport, ref); - unsigned long flags; - - spin_lock_irqsave(&fcloop_lock, flags); - list_del(&nport->nport_list); - spin_unlock_irqrestore(&fcloop_lock, flags); - - kfree(nport); -} - -static void -fcloop_nport_put(struct fcloop_nport *nport) -{ - kref_put(&nport->ref, fcloop_nport_free); -} - -static int -fcloop_nport_get(struct fcloop_nport *nport) -{ - return kref_get_unless_zero(&nport->ref); -} - static struct fcloop_nport * fcloop_alloc_nport(const char *buf, size_t count, bool remoteport) { @@ -938,6 +935,7 @@ fcloop_create_remote_port(struct device *dev, struct device_attribute *attr, if (!nport) return -EIO; + memset(&pinfo, 0, sizeof(pinfo)); pinfo.node_name = nport->node_name; pinfo.port_name = nport->port_name; pinfo.port_role = nport->port_role; @@ -979,24 +977,12 @@ __unlink_remote_port(struct fcloop_nport *nport) } static int -__wait_remoteport_unreg(struct fcloop_nport *nport, struct fcloop_rport *rport) +__remoteport_unreg(struct fcloop_nport *nport, struct fcloop_rport *rport) { - int ret; - if (!rport) return -EALREADY; - init_completion(&nport->rport_unreg_done); - - ret = nvme_fc_unregister_remoteport(rport->remoteport); - if (ret) - return ret; - - wait_for_completion(&nport->rport_unreg_done); - - fcloop_nport_put(nport); - - return ret; + return nvme_fc_unregister_remoteport(rport->remoteport); } static ssize_t @@ -1029,7 +1015,7 @@ fcloop_delete_remote_port(struct device *dev, struct device_attribute *attr, if (!nport) return -ENOENT; - ret = __wait_remoteport_unreg(nport, rport); + ret = __remoteport_unreg(nport, rport); return ret ? ret : count; } @@ -1086,24 +1072,12 @@ __unlink_target_port(struct fcloop_nport *nport) } static int -__wait_targetport_unreg(struct fcloop_nport *nport, struct fcloop_tport *tport) +__targetport_unreg(struct fcloop_nport *nport, struct fcloop_tport *tport) { - int ret; - if (!tport) return -EALREADY; - init_completion(&nport->tport_unreg_done); - - ret = nvmet_fc_unregister_targetport(tport->targetport); - if (ret) - return ret; - - wait_for_completion(&nport->tport_unreg_done); - - fcloop_nport_put(nport); - - return ret; + return nvmet_fc_unregister_targetport(tport->targetport); } static ssize_t @@ -1136,7 +1110,7 @@ fcloop_delete_target_port(struct device *dev, struct device_attribute *attr, if (!nport) return -ENOENT; - ret = __wait_targetport_unreg(nport, tport); + ret = __targetport_unreg(nport, tport); return ret ? ret : count; } @@ -1223,11 +1197,11 @@ static void __exit fcloop_exit(void) spin_unlock_irqrestore(&fcloop_lock, flags); - ret = __wait_targetport_unreg(nport, tport); + ret = __targetport_unreg(nport, tport); if (ret) pr_warn("%s: Failed deleting target port\n", __func__); - ret = __wait_remoteport_unreg(nport, rport); + ret = __remoteport_unreg(nport, rport); if (ret) pr_warn("%s: Failed deleting remote port\n", __func__); diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 7d261ab..7b8e20a 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -74,6 +74,7 @@ struct nvmet_sq { struct percpu_ref ref; u16 qid; u16 size; + u16 sqhd; struct completion free_done; struct completion confirm_done; }; diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 1eecfa3..8e075ea 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -686,7 +686,7 @@ static ssize_t driver_override_store(struct device *dev, const char *buf, size_t count) { struct pci_dev *pdev = to_pci_dev(dev); - char *driver_override, *old = pdev->driver_override, *cp; + char *driver_override, *old, *cp; /* We need to keep extra room for a newline */ if (count >= (PAGE_SIZE - 1)) @@ -700,12 +700,15 @@ static ssize_t driver_override_store(struct device *dev, if (cp) *cp = '\0'; + device_lock(dev); + old = pdev->driver_override; if (strlen(driver_override)) { pdev->driver_override = driver_override; } else { kfree(driver_override); pdev->driver_override = NULL; } + device_unlock(dev); kfree(old); @@ -716,8 +719,12 @@ static ssize_t driver_override_show(struct device *dev, struct device_attribute *attr, char *buf) { struct pci_dev *pdev = to_pci_dev(dev); + ssize_t len; - return snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override); + device_lock(dev); + len = snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override); + device_unlock(dev); + return len; } static DEVICE_ATTR_RW(driver_override); diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c index 85de30f..56a8195 100644 --- a/drivers/platform/x86/fujitsu-laptop.c +++ b/drivers/platform/x86/fujitsu-laptop.c @@ -254,10 +254,12 @@ static int bl_update_status(struct backlight_device *b) { struct acpi_device *device = bl_get_data(b); - if (b->props.power == FB_BLANK_POWERDOWN) - call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x3); - else - call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x0); + if (fext) { + if (b->props.power == FB_BLANK_POWERDOWN) + call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x3); + else + call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x0); + } return set_lcd_level(device, b->props.brightness); } diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c index a64285a..af3e4d3 100644 --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@ -699,13 +699,13 @@ static void _aac_probe_container1(void * context, struct fib * fibptr) int status; dresp = (struct aac_mount *) fib_data(fibptr); - if (!(fibptr->dev->supplement_adapter_info.supported_options2 & - AAC_OPTION_VARIABLE_BLOCK_SIZE)) + if (!aac_supports_2T(fibptr->dev)) { dresp->mnt[0].capacityhigh = 0; - if ((le32_to_cpu(dresp->status) != ST_OK) || - (le32_to_cpu(dresp->mnt[0].vol) != CT_NONE)) { - _aac_probe_container2(context, fibptr); - return; + if ((le32_to_cpu(dresp->status) == ST_OK) && + (le32_to_cpu(dresp->mnt[0].vol) != CT_NONE)) { + _aac_probe_container2(context, fibptr); + return; + } } scsicmd = (struct scsi_cmnd *) context; diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 92fabf2..403a639 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -2701,6 +2701,11 @@ static inline int aac_is_src(struct aac_dev *dev) return 0; } +static inline int aac_supports_2T(struct aac_dev *dev) +{ + return (dev->adapter_info.options & AAC_OPT_NEW_COMM_64); +} + char * get_container_type(unsigned type); extern int numacb; extern char aac_driver_version[]; diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index 87cc4a9..62beb25 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -906,12 +906,14 @@ static int aac_eh_dev_reset(struct scsi_cmnd *cmd) bus = aac_logical_to_phys(scmd_channel(cmd)); cid = scmd_id(cmd); - info = &aac->hba_map[bus][cid]; - if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS || - info->devtype != AAC_DEVTYPE_NATIVE_RAW) + + if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS) return FAILED; - if (info->reset_state > 0) + info = &aac->hba_map[bus][cid]; + + if (info->devtype != AAC_DEVTYPE_NATIVE_RAW && + info->reset_state > 0) return FAILED; pr_err("%s: Host adapter reset request. SCSI hang ?\n", @@ -962,12 +964,14 @@ static int aac_eh_target_reset(struct scsi_cmnd *cmd) bus = aac_logical_to_phys(scmd_channel(cmd)); cid = scmd_id(cmd); - info = &aac->hba_map[bus][cid]; - if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS || - info->devtype != AAC_DEVTYPE_NATIVE_RAW) + + if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS) return FAILED; - if (info->reset_state > 0) + info = &aac->hba_map[bus][cid]; + + if (info->devtype != AAC_DEVTYPE_NATIVE_RAW && + info->reset_state > 0) return FAILED; pr_err("%s: Host adapter reset request. SCSI hang ?\n", diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c index 48c2b2b..0c9361c 100644 --- a/drivers/scsi/aacraid/src.c +++ b/drivers/scsi/aacraid/src.c @@ -740,6 +740,8 @@ static void aac_send_iop_reset(struct aac_dev *dev) aac_set_intx_mode(dev); src_writel(dev, MUnit.IDR, IOP_SRC_RESET_MASK); + + msleep(5000); } static void aac_send_hardware_soft_reset(struct aac_dev *dev) diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 7e7ae78..100bc4c 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -6131,6 +6131,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) "Extents and RPI headers enabled.\n"); } mempool_free(mboxq, phba->mbox_mem_pool); + rc = -EIO; goto out_free_bsmbx; } diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 79ba3ce..23bdb1c 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -884,7 +884,7 @@ out_err: wcqe->total_data_placed); nCmd->transferred_length = 0; nCmd->rcv_rsplen = 0; - nCmd->status = NVME_SC_FC_TRANSPORT_ERROR; + nCmd->status = NVME_SC_INTERNAL; } } diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 1f59e7a..6b33a1f 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -180,7 +180,7 @@ static void qla_nvme_sp_done(void *ptr, int res) goto rel; if (unlikely(res == QLA_FUNCTION_FAILED)) - fd->status = NVME_SC_FC_TRANSPORT_ERROR; + fd->status = NVME_SC_INTERNAL; else fd->status = 0; diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 3894205..dab876c 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -580,7 +580,8 @@ int scsi_check_sense(struct scsi_cmnd *scmd) if (sshdr.asc == 0x20 || /* Invalid command operation code */ sshdr.asc == 0x21 || /* Logical block address out of range */ sshdr.asc == 0x24 || /* Invalid field in cdb */ - sshdr.asc == 0x26) { /* Parameter value invalid */ + sshdr.asc == 0x26 || /* Parameter value invalid */ + sshdr.asc == 0x27) { /* Write protected */ set_host_byte(scmd, DID_TARGET_FAILURE); } return SUCCESS; diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index ba9d70f..cbd4495 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -2739,7 +2739,8 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel, list_for_each_entry(rport, &fc_host->rports, peers) { - if ((rport->port_state == FC_PORTSTATE_BLOCKED) && + if ((rport->port_state == FC_PORTSTATE_BLOCKED || + rport->port_state == FC_PORTSTATE_NOTPRESENT) && (rport->channel == channel)) { switch (fc_host->tgtid_bind_type) { @@ -2876,7 +2877,6 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel, memcpy(&rport->port_name, &ids->port_name, sizeof(rport->port_name)); rport->port_id = ids->port_id; - rport->roles = ids->roles; rport->port_state = FC_PORTSTATE_ONLINE; rport->flags &= ~FC_RPORT_FAST_FAIL_TIMEDOUT; @@ -2885,15 +2885,7 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel, fci->f->dd_fcrport_size); spin_unlock_irqrestore(shost->host_lock, flags); - if (ids->roles & FC_PORT_ROLE_FCP_TARGET) { - scsi_target_unblock(&rport->dev, SDEV_RUNNING); - - /* initiate a scan of the target */ - spin_lock_irqsave(shost->host_lock, flags); - rport->flags |= FC_RPORT_SCAN_PENDING; - scsi_queue_work(shost, &rport->scan_work); - spin_unlock_irqrestore(shost->host_lock, flags); - } + fc_remote_port_rolechg(rport, ids->roles); return rport; } } diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 8934f19..0190aef 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -3689,7 +3689,7 @@ iscsi_if_rx(struct sk_buff *skb) uint32_t group; nlh = nlmsg_hdr(skb); - if (nlh->nlmsg_len < sizeof(*nlh) || + if (nlh->nlmsg_len < sizeof(*nlh) + sizeof(*ev) || skb->len < nlh->nlmsg_len) { break; } diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c index 5fbfd9c..5b3d57f 100644 --- a/drivers/xen/xen-pciback/conf_space_header.c +++ b/drivers/xen/xen-pciback/conf_space_header.c @@ -169,6 +169,9 @@ static int rom_write(struct pci_dev *dev, int offset, u32 value, void *data) static int bar_write(struct pci_dev *dev, int offset, u32 value, void *data) { struct pci_bar_info *bar = data; + unsigned int pos = (offset - PCI_BASE_ADDRESS_0) / 4; + const struct resource *res = dev->resource; + u32 mask; if (unlikely(!bar)) { pr_warn(DRV_NAME ": driver data not found for %s\n", @@ -179,7 +182,13 @@ static int bar_write(struct pci_dev *dev, int offset, u32 value, void *data) /* A write to obtain the length must happen as a 32-bit write. * This does not (yet) support writing individual bytes */ - if (value == ~0) + if (res[pos].flags & IORESOURCE_IO) + mask = ~PCI_BASE_ADDRESS_IO_MASK; + else if (pos && (res[pos - 1].flags & IORESOURCE_MEM_64)) + mask = 0; + else + mask = ~PCI_BASE_ADDRESS_MEM_MASK; + if ((value | mask) == ~0U) bar->which = 1; else { u32 tmpval; diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index b51d23f..280384b 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -107,7 +107,8 @@ static void end_compressed_bio_read(struct bio *bio) struct inode *inode; struct page *page; unsigned long index; - int ret; + unsigned int mirror = btrfs_io_bio(bio)->mirror_num; + int ret = 0; if (bio->bi_status) cb->errors = 1; @@ -118,6 +119,21 @@ static void end_compressed_bio_read(struct bio *bio) if (!refcount_dec_and_test(&cb->pending_bios)) goto out; + /* + * Record the correct mirror_num in cb->orig_bio so that + * read-repair can work properly. + */ + ASSERT(btrfs_io_bio(cb->orig_bio)); + btrfs_io_bio(cb->orig_bio)->mirror_num = mirror; + cb->mirror_num = mirror; + + /* + * Some IO in this cb have failed, just skip checksum as there + * is no way it could be correct. + */ + if (cb->errors == 1) + goto csum_failed; + inode = cb->inode; ret = check_compressed_csum(BTRFS_I(inode), cb, (u64)bio->bi_iter.bi_sector << 9); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 5a8933d..899ddae 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -709,7 +709,6 @@ struct btrfs_delayed_root; #define BTRFS_FS_OPEN 5 #define BTRFS_FS_QUOTA_ENABLED 6 #define BTRFS_FS_QUOTA_ENABLING 7 -#define BTRFS_FS_QUOTA_DISABLING 8 #define BTRFS_FS_UPDATE_UUID_TREE_GEN 9 #define BTRFS_FS_CREATING_FREE_SPACE_TREE 10 #define BTRFS_FS_BTREE_ERR 11 diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 487bbe4..dfdab84 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3643,7 +3643,14 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) u64 flags; do_barriers = !btrfs_test_opt(fs_info, NOBARRIER); - backup_super_roots(fs_info); + + /* + * max_mirrors == 0 indicates we're from commit_transaction, + * not from fsync where the tree roots in fs_info have not + * been consistent on disk. + */ + if (max_mirrors == 0) + backup_super_roots(fs_info); sb = fs_info->super_for_commit; dev_item = &sb->dev_item; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 3e5bb0c..12ab19a 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3471,8 +3471,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, unsigned int write_flags = 0; unsigned long nr_written = 0; - if (wbc->sync_mode == WB_SYNC_ALL) - write_flags = REQ_SYNC; + write_flags = wbc_to_write_flags(wbc); trace___extent_writepage(page, inode, wbc); @@ -3718,7 +3717,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, unsigned long i, num_pages; unsigned long bio_flags = 0; unsigned long start, end; - unsigned int write_flags = (epd->sync_io ? REQ_SYNC : 0) | REQ_META; + unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META; int ret = 0; clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags); @@ -4063,9 +4062,6 @@ static void flush_epd_write_bio(struct extent_page_data *epd) if (epd->bio) { int ret; - bio_set_op_attrs(epd->bio, REQ_OP_WRITE, - epd->sync_io ? REQ_SYNC : 0); - ret = submit_one_bio(epd->bio, 0, epd->bio_flags); BUG_ON(ret < 0); /* -ENOMEM */ epd->bio = NULL; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 128f3e5..d94e3f6 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -135,6 +135,18 @@ static inline void btrfs_cleanup_ordered_extents(struct inode *inode, const u64 offset, const u64 bytes) { + unsigned long index = offset >> PAGE_SHIFT; + unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT; + struct page *page; + + while (index <= end_index) { + page = find_get_page(inode->i_mapping, index); + index++; + if (!page) + continue; + ClearPagePrivate2(page); + put_page(page); + } return __endio_write_update_ordered(inode, offset + PAGE_SIZE, bytes - PAGE_SIZE, false); } @@ -8357,11 +8369,8 @@ static void btrfs_endio_direct_read(struct bio *bio) struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); blk_status_t err = bio->bi_status; - if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) { + if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) err = btrfs_subio_endio_read(inode, io_bio, err); - if (!err) - bio->bi_status = 0; - } unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset, dip->logical_offset + dip->bytes - 1); @@ -8369,7 +8378,7 @@ static void btrfs_endio_direct_read(struct bio *bio) kfree(dip); - dio_bio->bi_status = bio->bi_status; + dio_bio->bi_status = err; dio_end_io(dio_bio); if (io_bio->end_io) @@ -8387,6 +8396,7 @@ static void __endio_write_update_ordered(struct inode *inode, btrfs_work_func_t func; u64 ordered_offset = offset; u64 ordered_bytes = bytes; + u64 last_offset; int ret; if (btrfs_is_free_space_inode(BTRFS_I(inode))) { @@ -8398,6 +8408,7 @@ static void __endio_write_update_ordered(struct inode *inode, } again: + last_offset = ordered_offset; ret = btrfs_dec_test_first_ordered_pending(inode, &ordered, &ordered_offset, ordered_bytes, @@ -8409,6 +8420,12 @@ again: btrfs_queue_work(wq, &ordered->work); out_test: /* + * If btrfs_dec_test_ordered_pending does not find any ordered extent + * in the range, we can exit. + */ + if (ordered_offset == last_offset) + return; + /* * our bio might span multiple ordered extents. If we haven't * completed the accounting for the whole dio, go back and try again */ diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index d6715c2..6c7a49f 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2773,9 +2773,9 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info, } mutex_unlock(&fs_devices->device_list_mutex); - fi_args->nodesize = fs_info->super_copy->nodesize; - fi_args->sectorsize = fs_info->super_copy->sectorsize; - fi_args->clone_alignment = fs_info->super_copy->sectorsize; + fi_args->nodesize = fs_info->nodesize; + fi_args->sectorsize = fs_info->sectorsize; + fi_args->clone_alignment = fs_info->sectorsize; if (copy_to_user(arg, fi_args, sizeof(*fi_args))) ret = -EFAULT; @@ -3032,7 +3032,7 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff, out: if (ret) btrfs_cmp_data_free(cmp); - return 0; + return ret; } static int btrfs_cmp_data(u64 len, struct cmp_pages *cmp) @@ -4061,6 +4061,10 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) ret = PTR_ERR(new_root); goto out; } + if (!is_fstree(new_root->objectid)) { + ret = -ENOENT; + goto out; + } path = btrfs_alloc_path(); if (!path) { diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 5c8b61c..e172d48 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -807,7 +807,6 @@ static int btrfs_clean_quota_tree(struct btrfs_trans_handle *trans, } ret = 0; out: - set_bit(BTRFS_FS_QUOTA_DISABLING, &root->fs_info->flags); btrfs_free_path(path); return ret; } @@ -953,7 +952,6 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, if (!fs_info->quota_root) goto out; clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - set_bit(BTRFS_FS_QUOTA_DISABLING, &fs_info->flags); btrfs_qgroup_wait_for_completion(fs_info, false); spin_lock(&fs_info->qgroup_lock); quota_root = fs_info->quota_root; @@ -1307,6 +1305,8 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, } } ret = del_qgroup_item(trans, quota_root, qgroupid); + if (ret && ret != -ENOENT) + goto out; while (!list_empty(&qgroup->groups)) { list = list_first_entry(&qgroup->groups, @@ -2086,8 +2086,6 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans, if (test_and_clear_bit(BTRFS_FS_QUOTA_ENABLING, &fs_info->flags)) set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - if (test_and_clear_bit(BTRFS_FS_QUOTA_DISABLING, &fs_info->flags)) - clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); spin_lock(&fs_info->qgroup_lock); while (!list_empty(&fs_info->dirty_qgroups)) { diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 3a49a3c..9841fae 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2400,11 +2400,11 @@ void free_reloc_roots(struct list_head *list) while (!list_empty(list)) { reloc_root = list_entry(list->next, struct btrfs_root, root_list); + __del_reloc_root(reloc_root); free_extent_buffer(reloc_root->node); free_extent_buffer(reloc_root->commit_root); reloc_root->node = NULL; reloc_root->commit_root = NULL; - __del_reloc_root(reloc_root); } } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 32b043e..8fd195c 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -2630,7 +2630,7 @@ static int send_create_inode(struct send_ctx *sctx, u64 ino) } else { btrfs_warn(sctx->send_root->fs_info, "unexpected inode type %o", (int)(mode & S_IFMT)); - ret = -ENOTSUPP; + ret = -EOPNOTSUPP; goto out; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index ad7f4ba..c800d06 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4181,6 +4181,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, struct extent_map *em, *n; struct list_head extents; struct extent_map_tree *tree = &inode->extent_tree; + u64 logged_start, logged_end; u64 test_gen; int ret = 0; int num = 0; @@ -4190,10 +4191,11 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, down_write(&inode->dio_sem); write_lock(&tree->lock); test_gen = root->fs_info->last_trans_committed; + logged_start = start; + logged_end = end; list_for_each_entry_safe(em, n, &tree->modified_extents, list) { list_del_init(&em->list); - /* * Just an arbitrary number, this can be really CPU intensive * once we start getting a lot of extents, and really once we @@ -4208,6 +4210,12 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, if (em->generation <= test_gen) continue; + + if (em->start < logged_start) + logged_start = em->start; + if ((em->start + em->len - 1) > logged_end) + logged_end = em->start + em->len - 1; + /* Need a ref to keep it from getting evicted from cache */ refcount_inc(&em->refs); set_bit(EXTENT_FLAG_LOGGING, &em->flags); @@ -4216,7 +4224,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, } list_sort(NULL, &extents, extent_cmp); - btrfs_get_logged_extents(inode, logged_list, start, end); + btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end); /* * Some ordered extents started by fsync might have completed * before we could collect them into the list logged_list, which diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 0e8f16c..b397375 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6166,7 +6166,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, map_length = length; btrfs_bio_counter_inc_blocked(fs_info); - ret = __btrfs_map_block(fs_info, bio_op(bio), logical, + ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length, &bbio, mirror_num, 1); if (ret) { btrfs_bio_counter_dec(fs_info); diff --git a/fs/direct-io.c b/fs/direct-io.c index 5fa2211..62cf812 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -229,6 +229,7 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async) { loff_t offset = dio->iocb->ki_pos; ssize_t transferred = 0; + int err; /* * AIO submission can race with bio completion to get here while @@ -258,8 +259,22 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async) if (ret == 0) ret = transferred; + /* + * Try again to invalidate clean pages which might have been cached by + * non-direct readahead, or faulted in by get_user_pages() if the source + * of the write was an mmap'ed region of the file we're writing. Either + * one is a pretty crazy thing to do, so we don't support it 100%. If + * this invalidation fails, tough, the write still worked... + */ + if (ret > 0 && dio->op == REQ_OP_WRITE && + dio->inode->i_mapping->nrpages) { + err = invalidate_inode_pages2_range(dio->inode->i_mapping, + offset >> PAGE_SHIFT, + (offset + ret - 1) >> PAGE_SHIFT); + WARN_ON_ONCE(err); + } + if (dio->end_io) { - int err; // XXX: ki_pos?? err = dio->end_io(dio->iocb, offset, ret, dio->private); @@ -304,6 +319,7 @@ static void dio_bio_end_aio(struct bio *bio) struct dio *dio = bio->bi_private; unsigned long remaining; unsigned long flags; + bool defer_completion = false; /* cleanup the bio */ dio_bio_complete(dio, bio); @@ -315,7 +331,19 @@ static void dio_bio_end_aio(struct bio *bio) spin_unlock_irqrestore(&dio->bio_lock, flags); if (remaining == 0) { - if (dio->result && dio->defer_completion) { + /* + * Defer completion when defer_completion is set or + * when the inode has pages mapped and this is AIO write. + * We need to invalidate those pages because there is a + * chance they contain stale data in the case buffered IO + * went in between AIO submission and completion into the + * same region. + */ + if (dio->result) + defer_completion = dio->defer_completion || + (dio->op == REQ_OP_WRITE && + dio->inode->i_mapping->nrpages); + if (defer_completion) { INIT_WORK(&dio->complete_work, dio_aio_complete_work); queue_work(dio->inode->i_sb->s_dio_done_wq, &dio->complete_work); @@ -1210,10 +1238,19 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, * For AIO O_(D)SYNC writes we need to defer completions to a workqueue * so that we can call ->fsync. */ - if (dio->is_async && iov_iter_rw(iter) == WRITE && - ((iocb->ki_filp->f_flags & O_DSYNC) || - IS_SYNC(iocb->ki_filp->f_mapping->host))) { - retval = dio_set_defer_completion(dio); + if (dio->is_async && iov_iter_rw(iter) == WRITE) { + retval = 0; + if ((iocb->ki_filp->f_flags & O_DSYNC) || + IS_SYNC(iocb->ki_filp->f_mapping->host)) + retval = dio_set_defer_completion(dio); + else if (!dio->inode->i_sb->s_dio_done_wq) { + /* + * In case of AIO write racing with buffered read we + * need to defer completion. We can't decide this now, + * however the workqueue needs to be initialized here. + */ + retval = sb_init_dio_done_wq(dio->inode->i_sb); + } if (retval) { /* * We grab i_mutex only for reads so we don't have diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 98e845b..11066d8 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1945,13 +1945,9 @@ static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos) { struct gfs2_glock_iter *gi = seq->private; loff_t n = *pos; - int ret; - - if (gi->last_pos <= *pos) - n = (*pos - gi->last_pos); - ret = rhashtable_walk_start(&gi->hti); - if (ret) + rhashtable_walk_enter(&gl_hash_table, &gi->hti); + if (rhashtable_walk_start(&gi->hti) != 0) return NULL; do { @@ -1959,6 +1955,7 @@ static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos) } while (gi->gl && n--); gi->last_pos = *pos; + return gi->gl; } @@ -1970,6 +1967,7 @@ static void *gfs2_glock_seq_next(struct seq_file *seq, void *iter_ptr, (*pos)++; gi->last_pos = *pos; gfs2_glock_iter_next(gi); + return gi->gl; } @@ -1980,6 +1978,7 @@ static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr) gi->gl = NULL; rhashtable_walk_stop(&gi->hti); + rhashtable_walk_exit(&gi->hti); } static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr) @@ -2042,12 +2041,10 @@ static int __gfs2_glocks_open(struct inode *inode, struct file *file, struct gfs2_glock_iter *gi = seq->private; gi->sdp = inode->i_private; - gi->last_pos = 0; seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN); if (seq->buf) seq->size = GFS2_SEQ_GOODSIZE; gi->gl = NULL; - rhashtable_walk_enter(&gl_hash_table, &gi->hti); } return ret; } @@ -2063,7 +2060,6 @@ static int gfs2_glocks_release(struct inode *inode, struct file *file) struct gfs2_glock_iter *gi = seq->private; gi->gl = NULL; - rhashtable_walk_exit(&gi->hti); return seq_release_private(inode, file); } @@ -713,8 +713,24 @@ struct iomap_dio { static ssize_t iomap_dio_complete(struct iomap_dio *dio) { struct kiocb *iocb = dio->iocb; + struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; + /* + * Try again to invalidate clean pages which might have been cached by + * non-direct readahead, or faulted in by get_user_pages() if the source + * of the write was an mmap'ed region of the file we're writing. Either + * one is a pretty crazy thing to do, so we don't support it 100%. If + * this invalidation fails, tough, the write still worked... + */ + if (!dio->error && + (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) { + ret = invalidate_inode_pages2_range(inode->i_mapping, + iocb->ki_pos >> PAGE_SHIFT, + (iocb->ki_pos + dio->size - 1) >> PAGE_SHIFT); + WARN_ON_ONCE(ret); + } + if (dio->end_io) { ret = dio->end_io(iocb, dio->error ? dio->error : dio->size, @@ -993,6 +1009,13 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, WARN_ON_ONCE(ret); ret = 0; + if (iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) && + !inode->i_sb->s_dio_done_wq) { + ret = sb_init_dio_done_wq(inode->i_sb); + if (ret < 0) + goto out_free_dio; + } + inode_dio_begin(inode); blk_start_plug(&plug); @@ -1015,13 +1038,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (ret < 0) iomap_dio_set_error(dio, ret); - if (ret >= 0 && iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) && - !inode->i_sb->s_dio_done_wq) { - ret = sb_init_dio_done_wq(inode->i_sb); - if (ret < 0) - iomap_dio_set_error(dio, ret); - } - if (!atomic_dec_and_test(&dio->ref)) { if (!is_sync_kiocb(iocb)) return -EIOCBQUEUED; @@ -1042,19 +1058,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, ret = iomap_dio_complete(dio); - /* - * Try again to invalidate clean pages which might have been cached by - * non-direct readahead, or faulted in by get_user_pages() if the source - * of the write was an mmap'ed region of the file we're writing. Either - * one is a pretty crazy thing to do, so we don't support it 100%. If - * this invalidation fails, tough, the write still worked... - */ - if (iov_iter_rw(iter) == WRITE) { - int err = invalidate_inode_pages2_range(mapping, - start >> PAGE_SHIFT, end >> PAGE_SHIFT); - WARN_ON_ONCE(err); - } - return ret; out_free_dio: diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index db692f5..447a24d 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -514,9 +514,11 @@ static int isofs_show_options(struct seq_file *m, struct dentry *root) if (sbi->s_fmode != ISOFS_INVALID_MODE) seq_printf(m, ",fmode=%o", sbi->s_fmode); +#ifdef CONFIG_JOLIET if (sbi->s_nls_iocharset && strcmp(sbi->s_nls_iocharset->charset, CONFIG_NLS_DEFAULT) != 0) seq_printf(m, ",iocharset=%s", sbi->s_nls_iocharset->charset); +#endif return 0; } diff --git a/fs/proc/array.c b/fs/proc/array.c index 525157c..77a8eac 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -119,30 +119,25 @@ static inline void task_name(struct seq_file *m, struct task_struct *p) * simple bit tests. */ static const char * const task_state_array[] = { - "R (running)", /* 0 */ - "S (sleeping)", /* 1 */ - "D (disk sleep)", /* 2 */ - "T (stopped)", /* 4 */ - "t (tracing stop)", /* 8 */ - "X (dead)", /* 16 */ - "Z (zombie)", /* 32 */ + + /* states in TASK_REPORT: */ + "R (running)", /* 0x00 */ + "S (sleeping)", /* 0x01 */ + "D (disk sleep)", /* 0x02 */ + "T (stopped)", /* 0x04 */ + "t (tracing stop)", /* 0x08 */ + "X (dead)", /* 0x10 */ + "Z (zombie)", /* 0x20 */ + "P (parked)", /* 0x40 */ + + /* states beyond TASK_REPORT: */ + "I (idle)", /* 0x80 */ }; static inline const char *get_task_state(struct task_struct *tsk) { - unsigned int state = (tsk->state | tsk->exit_state) & TASK_REPORT; - - /* - * Parked tasks do not run; they sit in __kthread_parkme(). - * Without this check, we would report them as running, which is - * clearly wrong, so we report them as sleeping instead. - */ - if (tsk->state == TASK_PARKED) - state = TASK_INTERRUPTIBLE; - - BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array)-1); - - return task_state_array[fls(state)]; + BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != ARRAY_SIZE(task_state_array)); + return task_state_array[__get_task_state(tsk)]; } static inline int get_task_umask(struct task_struct *tsk) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 8381db9..50b0556 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1980,7 +1980,9 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) ret = dquot_add_space(transfer_to[cnt], cur_space, rsv_space, 0, &warn_to[cnt]); if (ret) { + spin_lock(&transfer_to[cnt]->dq_dqb_lock); dquot_decr_inodes(transfer_to[cnt], inode_usage); + spin_unlock(&transfer_to[cnt]->dq_dqb_lock); goto over_quota; } } diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index c0187cd..a73e5b3 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -328,12 +328,16 @@ static int v2_write_dquot(struct dquot *dquot) if (!dquot->dq_off) { alloc = true; down_write(&dqopt->dqio_sem); + } else { + down_read(&dqopt->dqio_sem); } ret = qtree_write_dquot( sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); if (alloc) up_write(&dqopt->dqio_sem); + else + up_read(&dqopt->dqio_sem); return ret; } diff --git a/fs/read_write.c b/fs/read_write.c index a2b9a47..f0d4b16 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -112,7 +112,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence, * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ - if (offset >= eof) + if ((unsigned long long)offset >= eof) return -ENXIO; break; case SEEK_HOLE: @@ -120,7 +120,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence, * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ - if (offset >= eof) + if ((unsigned long long)offset >= eof) return -ENXIO; offset = eof; break; diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index b008ff3..df3e600 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -156,7 +156,8 @@ __xfs_ag_resv_free( trace_xfs_ag_resv_free(pag, type, 0); resv = xfs_perag_resv(pag, type); - pag->pag_mount->m_ag_max_usable += resv->ar_asked; + if (pag->pag_agno == 0) + pag->pag_mount->m_ag_max_usable += resv->ar_asked; /* * AGFL blocks are always considered "free", so whatever * was reserved at mount time must be given back at umount. @@ -216,7 +217,14 @@ __xfs_ag_resv_init( return error; } - mp->m_ag_max_usable -= ask; + /* + * Reduce the maximum per-AG allocation length by however much we're + * trying to reserve for an AG. Since this is a filesystem-wide + * counter, we only make the adjustment for AG 0. This assumes that + * there aren't any AGs hungrier for per-AG reservation than AG 0. + */ + if (pag->pag_agno == 0) + mp->m_ag_max_usable -= ask; resv = xfs_perag_resv(pag, type); resv->ar_asked = ask; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 459f4b4f0..044a363 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -49,7 +49,6 @@ #include "xfs_rmap.h" #include "xfs_ag_resv.h" #include "xfs_refcount.h" -#include "xfs_rmap_btree.h" #include "xfs_icache.h" @@ -192,12 +191,8 @@ xfs_bmap_worst_indlen( int maxrecs; /* maximum record count at this level */ xfs_mount_t *mp; /* mount structure */ xfs_filblks_t rval; /* return value */ - xfs_filblks_t orig_len; mp = ip->i_mount; - - /* Calculate the worst-case size of the bmbt. */ - orig_len = len; maxrecs = mp->m_bmap_dmxr[0]; for (level = 0, rval = 0; level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK); @@ -205,20 +200,12 @@ xfs_bmap_worst_indlen( len += maxrecs - 1; do_div(len, maxrecs); rval += len; - if (len == 1) { - rval += XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) - + if (len == 1) + return rval + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) - level - 1; - break; - } if (level == 0) maxrecs = mp->m_bmap_dmxr[1]; } - - /* Calculate the worst-case size of the rmapbt. */ - if (xfs_sb_version_hasrmapbt(&mp->m_sb)) - rval += 1 + xfs_rmapbt_calc_size(mp, orig_len) + - mp->m_rmap_maxlevels; - return rval; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 2917260..f18e593 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -343,7 +343,8 @@ xfs_end_io( error = xfs_reflink_end_cow(ip, offset, size); break; case XFS_IO_UNWRITTEN: - error = xfs_iomap_write_unwritten(ip, offset, size); + /* writeback should never update isize */ + error = xfs_iomap_write_unwritten(ip, offset, size, false); break; default: ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans); diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index cd9a540..bc6c6e1 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1459,7 +1459,19 @@ xfs_shift_file_space( return error; /* - * The extent shiting code works on extent granularity. So, if + * Clean out anything hanging around in the cow fork now that + * we've flushed all the dirty data out to disk to avoid having + * CoW extents at the wrong offsets. + */ + if (xfs_is_reflink_inode(ip)) { + error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF, + true); + if (error) + return error; + } + + /* + * The extent shifting code works on extent granularity. So, if * stop_fsb is not the starting block of extent, we need to split * the extent at stop_fsb. */ diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index da14658..2f97c12 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1258,8 +1258,6 @@ xfs_buf_ioapply_map( int size; int offset; - total_nr_pages = bp->b_page_count; - /* skip the pages in the buffer before the start offset */ page_index = 0; offset = *buf_offset; diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index bd786a9..eaf86f5 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -347,7 +347,7 @@ xfs_verifier_error( { struct xfs_mount *mp = bp->b_target->bt_mount; - xfs_alert(mp, "Metadata %s detected at %pF, %s block 0x%llx", + xfs_alert(mp, "Metadata %s detected at %pS, %s block 0x%llx", bp->b_error == -EFSBADCRC ? "CRC error" : "corruption", __return_address, bp->b_ops->name, bp->b_bn); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index ebdd0bd..309e26c 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -58,7 +58,7 @@ xfs_zero_range( xfs_off_t count, bool *did_zero) { - return iomap_zero_range(VFS_I(ip), pos, count, NULL, &xfs_iomap_ops); + return iomap_zero_range(VFS_I(ip), pos, count, did_zero, &xfs_iomap_ops); } int @@ -377,8 +377,6 @@ restart: */ spin_lock(&ip->i_flags_lock); if (iocb->ki_pos > i_size_read(inode)) { - bool zero = false; - spin_unlock(&ip->i_flags_lock); if (!drained_dio) { if (*iolock == XFS_IOLOCK_SHARED) { @@ -399,7 +397,7 @@ restart: drained_dio = true; goto restart; } - error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero); + error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), NULL); if (error) return error; } else @@ -436,7 +434,6 @@ xfs_dio_write_end_io( struct inode *inode = file_inode(iocb->ki_filp); struct xfs_inode *ip = XFS_I(inode); loff_t offset = iocb->ki_pos; - bool update_size = false; int error = 0; trace_xfs_end_io_direct_write(ip, offset, size); @@ -447,6 +444,21 @@ xfs_dio_write_end_io( if (size <= 0) return size; + if (flags & IOMAP_DIO_COW) { + error = xfs_reflink_end_cow(ip, offset, size); + if (error) + return error; + } + + /* + * Unwritten conversion updates the in-core isize after extent + * conversion but before updating the on-disk size. Updating isize any + * earlier allows a racing dio read to find unwritten extents before + * they are converted. + */ + if (flags & IOMAP_DIO_UNWRITTEN) + return xfs_iomap_write_unwritten(ip, offset, size, true); + /* * We need to update the in-core inode size here so that we don't end up * with the on-disk inode size being outside the in-core inode size. We @@ -461,20 +473,11 @@ xfs_dio_write_end_io( spin_lock(&ip->i_flags_lock); if (offset + size > i_size_read(inode)) { i_size_write(inode, offset + size); - update_size = true; - } - spin_unlock(&ip->i_flags_lock); - - if (flags & IOMAP_DIO_COW) { - error = xfs_reflink_end_cow(ip, offset, size); - if (error) - return error; - } - - if (flags & IOMAP_DIO_UNWRITTEN) - error = xfs_iomap_write_unwritten(ip, offset, size); - else if (update_size) + spin_unlock(&ip->i_flags_lock); error = xfs_setfilesize(ip, offset, size); + } else { + spin_unlock(&ip->i_flags_lock); + } return error; } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 5599dda..4ec5b7f 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1624,10 +1624,12 @@ xfs_itruncate_extents( goto out; /* - * Clear the reflink flag if we truncated everything. + * Clear the reflink flag if there are no data fork blocks and + * there are no extents staged in the cow fork. */ - if (ip->i_d.di_nblocks == 0 && xfs_is_reflink_inode(ip)) { - ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; + if (xfs_is_reflink_inode(ip) && ip->i_cnextents == 0) { + if (ip->i_d.di_nblocks == 0) + ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; xfs_inode_clear_cowblocks_tag(ip); } diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 6d0f74e..a705f34 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -745,7 +745,7 @@ xfs_iflush_done( */ iip = INODE_ITEM(blip); if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) || - lip->li_flags & XFS_LI_FAILED) + (blip->li_flags & XFS_LI_FAILED)) need_ail++; blip = next; diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 5049e8a..aa75389 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1088,6 +1088,7 @@ xfs_ioctl_setattr_dax_invalidate( int *join_flags) { struct inode *inode = VFS_I(ip); + struct super_block *sb = inode->i_sb; int error; *join_flags = 0; @@ -1100,7 +1101,7 @@ xfs_ioctl_setattr_dax_invalidate( if (fa->fsx_xflags & FS_XFLAG_DAX) { if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) return -EINVAL; - if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE) + if (bdev_dax_supported(sb, sb->s_blocksize) < 0) return -EINVAL; } diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index a1909bc..f179bdf 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -829,7 +829,8 @@ int xfs_iomap_write_unwritten( xfs_inode_t *ip, xfs_off_t offset, - xfs_off_t count) + xfs_off_t count, + bool update_isize) { xfs_mount_t *mp = ip->i_mount; xfs_fileoff_t offset_fsb; @@ -840,6 +841,7 @@ xfs_iomap_write_unwritten( xfs_trans_t *tp; xfs_bmbt_irec_t imap; struct xfs_defer_ops dfops; + struct inode *inode = VFS_I(ip); xfs_fsize_t i_size; uint resblks; int error; @@ -899,7 +901,8 @@ xfs_iomap_write_unwritten( i_size = XFS_FSB_TO_B(mp, offset_fsb + count_fsb); if (i_size > offset + count) i_size = offset + count; - + if (update_isize && i_size > i_size_read(inode)) + i_size_write(inode, i_size); i_size = xfs_new_eof(ip, i_size); if (i_size) { ip->i_d.di_size = i_size; diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index 00db3ec..ee53506 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -27,7 +27,7 @@ int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t, struct xfs_bmbt_irec *, int); int xfs_iomap_write_allocate(struct xfs_inode *, int, xfs_off_t, struct xfs_bmbt_irec *); -int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t); +int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool); void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *, struct xfs_bmbt_irec *); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 2f2dc3c..4246876 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -274,7 +274,7 @@ xfs_fs_commit_blocks( (end - 1) >> PAGE_SHIFT); WARN_ON_ONCE(error); - error = xfs_iomap_write_unwritten(ip, start, length); + error = xfs_iomap_write_unwritten(ip, start, length, false); if (error) goto out_drop_iolock; } diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index c996f4a..584cf2d 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1654,6 +1654,16 @@ xfs_fs_fill_super( "DAX and reflink have not been tested together!"); } + if (mp->m_flags & XFS_MOUNT_DISCARD) { + struct request_queue *q = bdev_get_queue(sb->s_bdev); + + if (!blk_queue_discard(q)) { + xfs_warn(mp, "mounting with \"discard\" option, but " + "the device does not support discard"); + mp->m_flags &= ~XFS_MOUNT_DISCARD; + } + } + if (xfs_sb_version_hasrmapbt(&mp->m_sb)) { if (mp->m_sb.sb_rblocks) { xfs_alert(mp, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 460294b..02fa42d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -551,6 +551,7 @@ struct request_queue { int node; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace *blk_trace; + struct mutex blk_trace_mutex; #endif /* * for flush operations diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index f24bfb2..6d50876 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -3,8 +3,27 @@ #include <linux/types.h> +/* + * CPU-up CPU-down + * + * BP AP BP AP + * + * OFFLINE OFFLINE + * | ^ + * v | + * BRINGUP_CPU->AP_OFFLINE BRINGUP_CPU <- AP_IDLE_DEAD (idle thread/play_dead) + * | AP_OFFLINE + * v (IRQ-off) ,---------------^ + * AP_ONLNE | (stop_machine) + * | TEARDOWN_CPU <- AP_ONLINE_IDLE + * | ^ + * v | + * AP_ACTIVE AP_ACTIVE + */ + enum cpuhp_state { - CPUHP_OFFLINE, + CPUHP_INVALID = -1, + CPUHP_OFFLINE = 0, CPUHP_CREATE_THREADS, CPUHP_PERF_PREPARE, CPUHP_PERF_X86_PREPARE, diff --git a/include/linux/iommu.h b/include/linux/iommu.h index a7f2ac6..41b8c57 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -167,11 +167,11 @@ struct iommu_resv_region { * @map: map a physically contiguous memory region to an iommu domain * @unmap: unmap a physically contiguous memory region from an iommu domain * @map_sg: map a scatter-gather list of physically contiguous memory chunks + * to an iommu domain * @flush_tlb_all: Synchronously flush all hardware TLBs for this domain * @tlb_range_add: Add a given iova range to the flush queue for this domain * @tlb_sync: Flush all queued ranges from the hardware TLBs and empty flush * queue - * to an iommu domain * @iova_to_phys: translate iova to physical address * @add_device: add device to iommu grouping * @remove_device: remove device from iommu grouping diff --git a/include/linux/key.h b/include/linux/key.h index 0441141..e315e16 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -187,6 +187,7 @@ struct key { #define KEY_FLAG_BUILTIN 8 /* set if key is built in to the kernel */ #define KEY_FLAG_ROOT_CAN_INVAL 9 /* set if key can be invalidated by root without permission */ #define KEY_FLAG_KEEP 10 /* set if key should not be removed */ +#define KEY_FLAG_UID_KEYRING 11 /* set if key is a user or user session keyring */ /* the key type and key description string * - the desc is used to match a key against search criteria @@ -243,6 +244,7 @@ extern struct key *key_alloc(struct key_type *type, #define KEY_ALLOC_NOT_IN_QUOTA 0x0002 /* not in quota */ #define KEY_ALLOC_BUILT_IN 0x0004 /* Key is built into kernel */ #define KEY_ALLOC_BYPASS_RESTRICTION 0x0008 /* Override the check on restricted keyrings */ +#define KEY_ALLOC_UID_KEYRING 0x0010 /* allocating a user or user session keyring */ extern void key_revoke(struct key *key); extern void key_invalidate(struct key *key); diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 9c5cb44..a726f96 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -346,11 +346,6 @@ struct nvme_fc_remote_port { * indicating an FC transport Aborted status. * Entrypoint is Mandatory. * - * @defer_rcv: Called by the transport to signal the LLLD that it has - * begun processing of a previously received NVME CMD IU. The LLDD - * is now free to re-use the rcv buffer associated with the - * nvmefc_tgt_fcp_req. - * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -806,11 +801,19 @@ struct nvmet_fc_target_port { * outstanding operation (if there was one) to complete, then will * call the fcp_req_release() callback to return the command's * exchange context back to the LLDD. + * Entrypoint is Mandatory. * * @fcp_req_release: Called by the transport to return a nvmefc_tgt_fcp_req * to the LLDD after all operations on the fcp operation are complete. * This may be due to the command completing or upon completion of * abort cleanup. + * Entrypoint is Mandatory. + * + * @defer_rcv: Called by the transport to signal the LLLD that it has + * begun processing of a previously received NVME CMD IU. The LLDD + * is now free to re-use the rcv buffer associated with the + * nvmefc_tgt_fcp_req. + * Entrypoint is Optional. * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 87723c8..9310ce77 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -471,12 +471,14 @@ enum nvme_opcode { * * @NVME_SGL_FMT_ADDRESS: absolute address of the data block * @NVME_SGL_FMT_OFFSET: relative offset of the in-capsule data block + * @NVME_SGL_FMT_TRANSPORT_A: transport defined format, value 0xA * @NVME_SGL_FMT_INVALIDATE: RDMA transport specific remote invalidation * request subtype */ enum { NVME_SGL_FMT_ADDRESS = 0x00, NVME_SGL_FMT_OFFSET = 0x01, + NVME_SGL_FMT_TRANSPORT_A = 0x0A, NVME_SGL_FMT_INVALIDATE = 0x0f, }; @@ -490,12 +492,16 @@ enum { * * For struct nvme_keyed_sgl_desc: * @NVME_KEY_SGL_FMT_DATA_DESC: keyed data block descriptor + * + * Transport-specific SGL types: + * @NVME_TRANSPORT_SGL_DATA_DESC: Transport SGL data dlock descriptor */ enum { NVME_SGL_FMT_DATA_DESC = 0x00, NVME_SGL_FMT_SEG_DESC = 0x02, NVME_SGL_FMT_LAST_SEG_DESC = 0x03, NVME_KEY_SGL_FMT_DATA_DESC = 0x04, + NVME_TRANSPORT_SGL_DATA_DESC = 0x05, }; struct nvme_sgl_desc { @@ -1127,19 +1133,6 @@ enum { NVME_SC_UNWRITTEN_BLOCK = 0x287, NVME_SC_DNR = 0x4000, - - - /* - * FC Transport-specific error status values for NVME commands - * - * Transport-specific status code values must be in the range 0xB0..0xBF - */ - - /* Generic FC failure - catchall */ - NVME_SC_FC_TRANSPORT_ERROR = 0x00B0, - - /* I/O failure due to FC ABTS'd */ - NVME_SC_FC_TRANSPORT_ABORTED = 0x00B1, }; struct nvme_completion { diff --git a/include/linux/pci.h b/include/linux/pci.h index f68c58a..f4f8ee5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1685,6 +1685,8 @@ static inline int pci_get_new_domain_nr(void) { return -ENOSYS; } #define dev_is_pci(d) (false) #define dev_is_pf(d) (false) +static inline bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags) +{ return false; } #endif /* CONFIG_PCI */ /* Include architecture-dependent settings and functions */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 92fb8dd..26a7df4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -65,25 +65,23 @@ struct task_group; */ /* Used in tsk->state: */ -#define TASK_RUNNING 0 -#define TASK_INTERRUPTIBLE 1 -#define TASK_UNINTERRUPTIBLE 2 -#define __TASK_STOPPED 4 -#define __TASK_TRACED 8 +#define TASK_RUNNING 0x0000 +#define TASK_INTERRUPTIBLE 0x0001 +#define TASK_UNINTERRUPTIBLE 0x0002 +#define __TASK_STOPPED 0x0004 +#define __TASK_TRACED 0x0008 /* Used in tsk->exit_state: */ -#define EXIT_DEAD 16 -#define EXIT_ZOMBIE 32 +#define EXIT_DEAD 0x0010 +#define EXIT_ZOMBIE 0x0020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->state again: */ -#define TASK_DEAD 64 -#define TASK_WAKEKILL 128 -#define TASK_WAKING 256 -#define TASK_PARKED 512 -#define TASK_NOLOAD 1024 -#define TASK_NEW 2048 -#define TASK_STATE_MAX 4096 - -#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn" +#define TASK_PARKED 0x0040 +#define TASK_DEAD 0x0080 +#define TASK_WAKEKILL 0x0100 +#define TASK_WAKING 0x0200 +#define TASK_NOLOAD 0x0400 +#define TASK_NEW 0x0800 +#define TASK_STATE_MAX 0x1000 /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) @@ -99,7 +97,8 @@ struct task_group; /* get_task_state(): */ #define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ - __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD) + __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ + TASK_PARKED) #define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) @@ -1243,17 +1242,34 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) return task_pgrp_nr_ns(tsk, &init_pid_ns); } -static inline char task_state_to_char(struct task_struct *task) +#define TASK_REPORT_IDLE (TASK_REPORT + 1) +#define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) + +static inline unsigned int __get_task_state(struct task_struct *tsk) +{ + unsigned int tsk_state = READ_ONCE(tsk->state); + unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT; + + BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); + + if (tsk_state == TASK_IDLE) + state = TASK_REPORT_IDLE; + + return fls(state); +} + +static inline char __task_state_to_char(unsigned int state) { - const char stat_nam[] = TASK_STATE_TO_CHAR_STR; - unsigned long state = task->state; + static const char state_char[] = "RSDTtXZPI"; - state = state ? __ffs(state) + 1 : 0; + BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1); - /* Make sure the string lines up properly with the number of task states: */ - BUILD_BUG_ON(sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1); + return state_char[state]; +} - return state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'; +static inline char task_state_to_char(struct task_struct *tsk) +{ + return __task_state_to_char(__get_task_state(tsk)); } /** diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index bdb1279..e8608b2 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -285,7 +285,7 @@ enum ib_tm_cap_flags { IB_TM_CAP_RC = 1 << 0, }; -struct ib_xrq_caps { +struct ib_tm_caps { /* Max size of RNDV header */ u32 max_rndv_hdr_size; /* Max number of entries in tag matching list */ @@ -358,7 +358,7 @@ struct ib_device_attr { struct ib_rss_caps rss_caps; u32 max_wq_type_rq; u32 raw_packet_caps; /* Use ib_raw_packet_caps enum */ - struct ib_xrq_caps xrq_caps; + struct ib_tm_caps tm_caps; }; enum ib_mtu { @@ -1739,7 +1739,7 @@ struct ib_mr { u32 lkey; u32 rkey; u64 iova; - u32 length; + u64 length; unsigned int page_size; bool need_inval; union { diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index ae1409f..3c8b7f6 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -114,7 +114,10 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct * * Preemption ignores task state, therefore preempted tasks are always * RUNNING (we will not have dequeued if state != RUNNING). */ - return preempt ? TASK_RUNNING | TASK_STATE_MAX : p->state; + if (preempt) + return TASK_STATE_MAX; + + return __get_task_state(p); } #endif /* CREATE_TRACE_POINTS */ @@ -152,12 +155,14 @@ TRACE_EVENT(sched_switch, TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d", __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, - __entry->prev_state & (TASK_STATE_MAX-1) ? - __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|", - { 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" }, - { 16, "Z" }, { 32, "X" }, { 64, "x" }, - { 128, "K" }, { 256, "W" }, { 512, "P" }, - { 1024, "N" }) : "R", + + (__entry->prev_state & (TASK_REPORT_MAX - 1)) ? + __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|", + { 0x01, "S" }, { 0x02, "D" }, { 0x04, "T" }, + { 0x08, "t" }, { 0x10, "X" }, { 0x20, "Z" }, + { 0x40, "P" }, { 0x80, "I" }) : + "R", + __entry->prev_state & TASK_STATE_MAX ? "+" : "", __entry->next_comm, __entry->next_pid, __entry->next_prio) ); diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 9a0b647..d4e0b53 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -261,7 +261,7 @@ struct ib_uverbs_ex_query_device_resp { struct ib_uverbs_rss_caps rss_caps; __u32 max_wq_type_rq; __u32 raw_packet_caps; - struct ib_uverbs_tm_caps xrq_caps; + struct ib_uverbs_tm_caps tm_caps; }; struct ib_uverbs_query_port { @@ -1154,7 +1154,7 @@ static int put_compat_shm_info(struct shm_info *ip, info.shm_swp = ip->shm_swp; info.swap_attempts = ip->swap_attempts; info.swap_successes = ip->swap_successes; - return copy_to_user(up, &info, sizeof(info)); + return copy_to_user(uip, &info, sizeof(info)); } static int copy_compat_shmid_to_user(void __user *buf, struct shmid64_ds *in, diff --git a/kernel/cpu.c b/kernel/cpu.c index acf5308..8de11a2 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -46,11 +46,13 @@ * @bringup: Single callback bringup or teardown selector * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation - * @done: Signal completion to the issuer of the task + * @done_up: Signal completion to the issuer of the task for cpu-up + * @done_down: Signal completion to the issuer of the task for cpu-down */ struct cpuhp_cpu_state { enum cpuhp_state state; enum cpuhp_state target; + enum cpuhp_state fail; #ifdef CONFIG_SMP struct task_struct *thread; bool should_run; @@ -58,18 +60,39 @@ struct cpuhp_cpu_state { bool single; bool bringup; struct hlist_node *node; + struct hlist_node *last; enum cpuhp_state cb_state; int result; - struct completion done; + struct completion done_up; + struct completion done_down; #endif }; -static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state); +static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { + .fail = CPUHP_INVALID, +}; #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) -static struct lock_class_key cpuhp_state_key; -static struct lockdep_map cpuhp_state_lock_map = - STATIC_LOCKDEP_MAP_INIT("cpuhp_state", &cpuhp_state_key); +static struct lockdep_map cpuhp_state_up_map = + STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); +static struct lockdep_map cpuhp_state_down_map = + STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map); + + +static void inline cpuhp_lock_acquire(bool bringup) +{ + lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); +} + +static void inline cpuhp_lock_release(bool bringup) +{ + lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); +} +#else + +static void inline cpuhp_lock_acquire(bool bringup) { } +static void inline cpuhp_lock_release(bool bringup) { } + #endif /** @@ -123,13 +146,16 @@ static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) /** * cpuhp_invoke_callback _ Invoke the callbacks for a given state * @cpu: The cpu for which the callback should be invoked - * @step: The step in the state machine + * @state: The state to do callbacks for * @bringup: True if the bringup callback should be invoked + * @node: For multi-instance, do a single entry callback for install/remove + * @lastp: For multi-instance rollback, remember how far we got * * Called from cpu hotplug and from the state register machinery. */ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, - bool bringup, struct hlist_node *node) + bool bringup, struct hlist_node *node, + struct hlist_node **lastp) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct cpuhp_step *step = cpuhp_get_step(state); @@ -137,7 +163,17 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, int (*cb)(unsigned int cpu); int ret, cnt; + if (st->fail == state) { + st->fail = CPUHP_INVALID; + + if (!(bringup ? step->startup.single : step->teardown.single)) + return 0; + + return -EAGAIN; + } + if (!step->multi_instance) { + WARN_ON_ONCE(lastp && *lastp); cb = bringup ? step->startup.single : step->teardown.single; if (!cb) return 0; @@ -152,6 +188,7 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, /* Single invocation for instance add/remove */ if (node) { + WARN_ON_ONCE(lastp && *lastp); trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); @@ -161,13 +198,23 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, /* State transition. Invoke on all instances */ cnt = 0; hlist_for_each(node, &step->list) { + if (lastp && node == *lastp) + break; + trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); - if (ret) - goto err; + if (ret) { + if (!lastp) + goto err; + + *lastp = node; + return ret; + } cnt++; } + if (lastp) + *lastp = NULL; return 0; err: /* Rollback the instances if one failed */ @@ -178,12 +225,39 @@ err: hlist_for_each(node, &step->list) { if (!cnt--) break; - cbm(cpu, node); + + trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); + ret = cbm(cpu, node); + trace_cpuhp_exit(cpu, st->state, state, ret); + /* + * Rollback must not fail, + */ + WARN_ON_ONCE(ret); } return ret; } #ifdef CONFIG_SMP +static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup) +{ + struct completion *done = bringup ? &st->done_up : &st->done_down; + wait_for_completion(done); +} + +static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup) +{ + struct completion *done = bringup ? &st->done_up : &st->done_down; + complete(done); +} + +/* + * The former STARTING/DYING states, ran with IRQs disabled and must not fail. + */ +static bool cpuhp_is_atomic_state(enum cpuhp_state state) +{ + return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; +} + /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; @@ -271,14 +345,79 @@ void cpu_hotplug_enable(void) EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #endif /* CONFIG_HOTPLUG_CPU */ -static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st); +static inline enum cpuhp_state +cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + + st->rollback = false; + st->last = NULL; + + st->target = target; + st->single = false; + st->bringup = st->state < target; + + return prev_state; +} + +static inline void +cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) +{ + st->rollback = true; + + /* + * If we have st->last we need to undo partial multi_instance of this + * state first. Otherwise start undo at the previous state. + */ + if (!st->last) { + if (st->bringup) + st->state--; + else + st->state++; + } + + st->target = prev_state; + st->bringup = !st->bringup; +} + +/* Regular hotplug invocation of the AP hotplug thread */ +static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) +{ + if (!st->single && st->state == st->target) + return; + + st->result = 0; + /* + * Make sure the above stores are visible before should_run becomes + * true. Paired with the mb() above in cpuhp_thread_fun() + */ + smp_mb(); + st->should_run = true; + wake_up_process(st->thread); + wait_for_ap_thread(st, st->bringup); +} + +static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target) +{ + enum cpuhp_state prev_state; + int ret; + + prev_state = cpuhp_set_state(st, target); + __cpuhp_kick_ap(st); + if ((ret = st->result)) { + cpuhp_reset_state(st, prev_state); + __cpuhp_kick_ap(st); + } + + return ret; +} static int bringup_wait_for_ap(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ - wait_for_completion(&st->done); + wait_for_ap_thread(st, true); if (WARN_ON_ONCE((!cpu_online(cpu)))) return -ECANCELED; @@ -286,12 +425,10 @@ static int bringup_wait_for_ap(unsigned int cpu) stop_machine_unpark(cpu); kthread_unpark(st->thread); - /* Should we go further up ? */ - if (st->target > CPUHP_AP_ONLINE_IDLE) { - __cpuhp_kick_ap_work(st); - wait_for_completion(&st->done); - } - return st->result; + if (st->target <= CPUHP_AP_ONLINE_IDLE) + return 0; + + return cpuhp_kick_ap(st, st->target); } static int bringup_cpu(unsigned int cpu) @@ -317,32 +454,6 @@ static int bringup_cpu(unsigned int cpu) /* * Hotplug state machine related functions */ -static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - for (st->state++; st->state < st->target; st->state++) { - struct cpuhp_step *step = cpuhp_get_step(st->state); - - if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, true, NULL); - } -} - -static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, - enum cpuhp_state target) -{ - enum cpuhp_state prev_state = st->state; - int ret = 0; - - for (; st->state > target; st->state--) { - ret = cpuhp_invoke_callback(cpu, st->state, false, NULL); - if (ret) { - st->target = prev_state; - undo_cpu_down(cpu, st); - break; - } - } - return ret; -} static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) { @@ -350,7 +461,7 @@ static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) struct cpuhp_step *step = cpuhp_get_step(st->state); if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, false, NULL); + cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); } } @@ -362,7 +473,7 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, while (st->state < target) { st->state++; - ret = cpuhp_invoke_callback(cpu, st->state, true, NULL); + ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); if (ret) { st->target = prev_state; undo_cpu_up(cpu, st); @@ -379,7 +490,8 @@ static void cpuhp_create(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); - init_completion(&st->done); + init_completion(&st->done_up); + init_completion(&st->done_down); } static int cpuhp_should_run(unsigned int cpu) @@ -389,69 +501,90 @@ static int cpuhp_should_run(unsigned int cpu) return st->should_run; } -/* Execute the teardown callbacks. Used to be CPU_DOWN_PREPARE */ -static int cpuhp_ap_offline(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - enum cpuhp_state target = max((int)st->target, CPUHP_TEARDOWN_CPU); - - return cpuhp_down_callbacks(cpu, st, target); -} - -/* Execute the online startup callbacks. Used to be CPU_ONLINE */ -static int cpuhp_ap_online(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - return cpuhp_up_callbacks(cpu, st, st->target); -} - /* * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke * callbacks when a state gets [un]installed at runtime. + * + * Each invocation of this function by the smpboot thread does a single AP + * state callback. + * + * It has 3 modes of operation: + * - single: runs st->cb_state + * - up: runs ++st->state, while st->state < st->target + * - down: runs st->state--, while st->state > st->target + * + * When complete or on error, should_run is cleared and the completion is fired. */ static void cpuhp_thread_fun(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); - int ret = 0; + bool bringup = st->bringup; + enum cpuhp_state state; /* - * Paired with the mb() in cpuhp_kick_ap_work and - * cpuhp_invoke_ap_callback, so the work set is consistent visible. + * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures + * that if we see ->should_run we also see the rest of the state. */ smp_mb(); - if (!st->should_run) + + if (WARN_ON_ONCE(!st->should_run)) return; - st->should_run = false; + cpuhp_lock_acquire(bringup); - lock_map_acquire(&cpuhp_state_lock_map); - /* Single callback invocation for [un]install ? */ if (st->single) { - if (st->cb_state < CPUHP_AP_ONLINE) { - local_irq_disable(); - ret = cpuhp_invoke_callback(cpu, st->cb_state, - st->bringup, st->node); - local_irq_enable(); + state = st->cb_state; + st->should_run = false; + } else { + if (bringup) { + st->state++; + state = st->state; + st->should_run = (st->state < st->target); + WARN_ON_ONCE(st->state > st->target); } else { - ret = cpuhp_invoke_callback(cpu, st->cb_state, - st->bringup, st->node); + state = st->state; + st->state--; + st->should_run = (st->state > st->target); + WARN_ON_ONCE(st->state < st->target); } - } else if (st->rollback) { - BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE); + } + + WARN_ON_ONCE(!cpuhp_is_ap_state(state)); - undo_cpu_down(cpu, st); - st->rollback = false; + if (st->rollback) { + struct cpuhp_step *step = cpuhp_get_step(state); + if (step->skip_onerr) + goto next; + } + + if (cpuhp_is_atomic_state(state)) { + local_irq_disable(); + st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); + local_irq_enable(); + + /* + * STARTING/DYING must not fail! + */ + WARN_ON_ONCE(st->result); } else { - /* Cannot happen .... */ - BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE); - - /* Regular hotplug work */ - if (st->state < st->target) - ret = cpuhp_ap_online(cpu, st); - else if (st->state > st->target) - ret = cpuhp_ap_offline(cpu, st); + st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); + } + + if (st->result) { + /* + * If we fail on a rollback, we're up a creek without no + * paddle, no way forward, no way back. We loose, thanks for + * playing. + */ + WARN_ON_ONCE(st->rollback); + st->should_run = false; } - lock_map_release(&cpuhp_state_lock_map); - st->result = ret; - complete(&st->done); + +next: + cpuhp_lock_release(bringup); + + if (!st->should_run) + complete_ap_thread(st, bringup); } /* Invoke a single callback on a remote cpu */ @@ -460,62 +593,64 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int ret; if (!cpu_online(cpu)) return 0; - lock_map_acquire(&cpuhp_state_lock_map); - lock_map_release(&cpuhp_state_lock_map); + cpuhp_lock_acquire(false); + cpuhp_lock_release(false); + + cpuhp_lock_acquire(true); + cpuhp_lock_release(true); /* * If we are up and running, use the hotplug thread. For early calls * we invoke the thread function directly. */ if (!st->thread) - return cpuhp_invoke_callback(cpu, state, bringup, node); + return cpuhp_invoke_callback(cpu, state, bringup, node, NULL); + st->rollback = false; + st->last = NULL; + + st->node = node; + st->bringup = bringup; st->cb_state = state; st->single = true; - st->bringup = bringup; - st->node = node; - /* - * Make sure the above stores are visible before should_run becomes - * true. Paired with the mb() above in cpuhp_thread_fun() - */ - smp_mb(); - st->should_run = true; - wake_up_process(st->thread); - wait_for_completion(&st->done); - return st->result; -} + __cpuhp_kick_ap(st); -/* Regular hotplug invocation of the AP hotplug thread */ -static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st) -{ - st->result = 0; - st->single = false; /* - * Make sure the above stores are visible before should_run becomes - * true. Paired with the mb() above in cpuhp_thread_fun() + * If we failed and did a partial, do a rollback. */ - smp_mb(); - st->should_run = true; - wake_up_process(st->thread); + if ((ret = st->result) && st->last) { + st->rollback = true; + st->bringup = !bringup; + + __cpuhp_kick_ap(st); + } + + return ret; } static int cpuhp_kick_ap_work(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); - enum cpuhp_state state = st->state; + enum cpuhp_state prev_state = st->state; + int ret; + + cpuhp_lock_acquire(false); + cpuhp_lock_release(false); + + cpuhp_lock_acquire(true); + cpuhp_lock_release(true); + + trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); + ret = cpuhp_kick_ap(st, st->target); + trace_cpuhp_exit(cpu, st->state, prev_state, ret); - trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work); - lock_map_acquire(&cpuhp_state_lock_map); - lock_map_release(&cpuhp_state_lock_map); - __cpuhp_kick_ap_work(st); - wait_for_completion(&st->done); - trace_cpuhp_exit(cpu, st->state, state, st->result); - return st->result; + return ret; } static struct smp_hotplug_thread cpuhp_threads = { @@ -581,6 +716,7 @@ static int take_cpu_down(void *_param) struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); + int ret; /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); @@ -594,8 +730,13 @@ static int take_cpu_down(void *_param) WARN_ON(st->state != CPUHP_TEARDOWN_CPU); st->state--; /* Invoke the former CPU_DYING callbacks */ - for (; st->state > target; st->state--) - cpuhp_invoke_callback(cpu, st->state, false, NULL); + for (; st->state > target; st->state--) { + ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); + /* + * DYING must not fail! + */ + WARN_ON_ONCE(ret); + } /* Give up timekeeping duties */ tick_handover_do_timer(); @@ -639,7 +780,7 @@ static int takedown_cpu(unsigned int cpu) * * Wait for the stop thread to go away. */ - wait_for_completion(&st->done); + wait_for_ap_thread(st, false); BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ @@ -658,7 +799,7 @@ static void cpuhp_complete_idle_dead(void *arg) { struct cpuhp_cpu_state *st = arg; - complete(&st->done); + complete_ap_thread(st, false); } void cpuhp_report_idle_dead(void) @@ -676,11 +817,32 @@ void cpuhp_report_idle_dead(void) cpuhp_complete_idle_dead, st, 0); } -#else -#define takedown_cpu NULL -#endif +static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) +{ + for (st->state++; st->state < st->target; st->state++) { + struct cpuhp_step *step = cpuhp_get_step(st->state); -#ifdef CONFIG_HOTPLUG_CPU + if (!step->skip_onerr) + cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); + } +} + +static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, + enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + int ret = 0; + + for (; st->state > target; st->state--) { + ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); + if (ret) { + st->target = prev_state; + undo_cpu_down(cpu, st); + break; + } + } + return ret; +} /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, @@ -699,13 +861,13 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, cpuhp_tasks_frozen = tasks_frozen; - prev_state = st->state; - st->target = target; + prev_state = cpuhp_set_state(st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. */ if (st->state > CPUHP_TEARDOWN_CPU) { + st->target = max((int)target, CPUHP_TEARDOWN_CPU); ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just @@ -720,6 +882,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, */ if (st->state > CPUHP_TEARDOWN_CPU) goto out; + + st->target = target; } /* * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need @@ -727,9 +891,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, */ ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) { - st->target = prev_state; - st->rollback = true; - cpuhp_kick_ap_work(cpu); + cpuhp_reset_state(st, prev_state); + __cpuhp_kick_ap(st); } out: @@ -754,11 +917,15 @@ out: cpu_maps_update_done(); return err; } + int cpu_down(unsigned int cpu) { return do_cpu_down(cpu, CPUHP_OFFLINE); } EXPORT_SYMBOL(cpu_down); + +#else +#define takedown_cpu NULL #endif /*CONFIG_HOTPLUG_CPU*/ /** @@ -772,11 +939,16 @@ void notify_cpu_starting(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); + int ret; rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ while (st->state < target) { st->state++; - cpuhp_invoke_callback(cpu, st->state, true, NULL); + ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); + /* + * STARTING must not fail! + */ + WARN_ON_ONCE(ret); } } @@ -794,7 +966,7 @@ void cpuhp_online_idle(enum cpuhp_state state) return; st->state = CPUHP_AP_ONLINE_IDLE; - complete(&st->done); + complete_ap_thread(st, true); } /* Requires cpu_add_remove_lock to be held */ @@ -829,7 +1001,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) cpuhp_tasks_frozen = tasks_frozen; - st->target = target; + cpuhp_set_state(st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. @@ -1296,6 +1468,10 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, struct cpuhp_step *sp = cpuhp_get_step(state); int ret; + /* + * If there's nothing to do, we done. + * Relies on the union for multi_instance. + */ if ((bringup && !sp->startup.single) || (!bringup && !sp->teardown.single)) return 0; @@ -1307,9 +1483,9 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, if (cpuhp_is_ap_state(state)) ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node); else - ret = cpuhp_invoke_callback(cpu, state, bringup, node); + ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #else - ret = cpuhp_invoke_callback(cpu, state, bringup, node); + ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #endif BUG_ON(ret && !bringup); return ret; @@ -1641,9 +1817,55 @@ static ssize_t show_cpuhp_target(struct device *dev, } static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target); + +static ssize_t write_cpuhp_fail(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + struct cpuhp_step *sp; + int fail, ret; + + ret = kstrtoint(buf, 10, &fail); + if (ret) + return ret; + + /* + * Cannot fail STARTING/DYING callbacks. + */ + if (cpuhp_is_atomic_state(fail)) + return -EINVAL; + + /* + * Cannot fail anything that doesn't have callbacks. + */ + mutex_lock(&cpuhp_state_mutex); + sp = cpuhp_get_step(fail); + if (!sp->startup.single && !sp->teardown.single) + ret = -EINVAL; + mutex_unlock(&cpuhp_state_mutex); + if (ret) + return ret; + + st->fail = fail; + + return count; +} + +static ssize_t show_cpuhp_fail(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + + return sprintf(buf, "%d\n", st->fail); +} + +static DEVICE_ATTR(fail, 0644, show_cpuhp_fail, write_cpuhp_fail); + static struct attribute *cpuhp_cpu_attrs[] = { &dev_attr_state.attr, &dev_attr_target.attr, + &dev_attr_fail.attr, NULL }; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index af71a84e..f684d8e 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -412,6 +412,19 @@ err: return NULL; } +static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb) +{ + if (rb->aux_overwrite) + return false; + + if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); + return true; + } + + return false; +} + /* * Commit the data written by hardware into the ring buffer by adjusting * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the @@ -451,10 +464,8 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) } rb->user_page->aux_head = rb->aux_head; - if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + if (rb_need_aux_wakeup(rb)) wakeup = true; - rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); - } if (wakeup) { if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED) @@ -484,9 +495,8 @@ int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) rb->aux_head += size; rb->user_page->aux_head = rb->aux_head; - if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + if (rb_need_aux_wakeup(rb)) { perf_output_wakeup(handle); - rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); handle->wakeup = rb->aux_wakeup + rb->aux_watermark; } diff --git a/kernel/exit.c b/kernel/exit.c index 3481aba..f2cd53e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1600,12 +1600,10 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, upid, &info, options, ru ? &r : NULL); int signo = 0; + if (err > 0) { signo = SIGCHLD; err = 0; - } - - if (!err) { if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) return -EFAULT; } @@ -1723,16 +1721,15 @@ COMPAT_SYSCALL_DEFINE5(waitid, if (err > 0) { signo = SIGCHLD; err = 0; - } - - if (!err && uru) { - /* kernel_waitid() overwrites everything in ru */ - if (COMPAT_USE_64BIT_TIME) - err = copy_to_user(uru, &ru, sizeof(ru)); - else - err = put_compat_rusage(&ru, uru); - if (err) - return -EFAULT; + if (uru) { + /* kernel_waitid() overwrites everything in ru */ + if (COMPAT_USE_64BIT_TIME) + err = copy_to_user(uru, &ru, sizeof(ru)); + else + err = put_compat_rusage(&ru, uru); + if (err) + return -EFAULT; + } } if (!infop) diff --git a/kernel/extable.c b/kernel/extable.c index 38c2412..9aa1cc4 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -102,15 +102,7 @@ int core_kernel_data(unsigned long addr) int __kernel_text_address(unsigned long addr) { - if (core_kernel_text(addr)) - return 1; - if (is_module_text_address(addr)) - return 1; - if (is_ftrace_trampoline(addr)) - return 1; - if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr)) - return 1; - if (is_bpf_text_address(addr)) + if (kernel_text_address(addr)) return 1; /* * There might be init symbols in saved stacktraces. @@ -127,17 +119,42 @@ int __kernel_text_address(unsigned long addr) int kernel_text_address(unsigned long addr) { + bool no_rcu; + int ret = 1; + if (core_kernel_text(addr)) return 1; + + /* + * If a stack dump happens while RCU is not watching, then + * RCU needs to be notified that it requires to start + * watching again. This can happen either by tracing that + * triggers a stack trace, or a WARN() that happens during + * coming back from idle, or cpu on or offlining. + * + * is_module_text_address() as well as the kprobe slots + * and is_bpf_text_address() require RCU to be watching. + */ + no_rcu = !rcu_is_watching(); + + /* Treat this like an NMI as it can happen anywhere */ + if (no_rcu) + rcu_nmi_enter(); + if (is_module_text_address(addr)) - return 1; + goto out; if (is_ftrace_trampoline(addr)) - return 1; + goto out; if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr)) - return 1; + goto out; if (is_bpf_text_address(addr)) - return 1; - return 0; + goto out; + ret = 0; +out: + if (no_rcu) + rcu_nmi_exit(); + + return ret; } /* diff --git a/kernel/futex.c b/kernel/futex.c index 3d38eaf..0518a0b 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -821,8 +821,6 @@ static void get_pi_state(struct futex_pi_state *pi_state) /* * Drops a reference to the pi_state object and frees or caches it * when the last reference is gone. - * - * Must be called with the hb lock held. */ static void put_pi_state(struct futex_pi_state *pi_state) { @@ -837,16 +835,22 @@ static void put_pi_state(struct futex_pi_state *pi_state) * and has cleaned up the pi_state already */ if (pi_state->owner) { - raw_spin_lock_irq(&pi_state->owner->pi_lock); - list_del_init(&pi_state->list); - raw_spin_unlock_irq(&pi_state->owner->pi_lock); + struct task_struct *owner; - rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + owner = pi_state->owner; + if (owner) { + raw_spin_lock(&owner->pi_lock); + list_del_init(&pi_state->list); + raw_spin_unlock(&owner->pi_lock); + } + rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); } - if (current->pi_state_cache) + if (current->pi_state_cache) { kfree(pi_state); - else { + } else { /* * pi_state->list is already empty. * clear pi_state->owner. @@ -907,13 +911,14 @@ void exit_pi_state_list(struct task_struct *curr) raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); - - raw_spin_lock_irq(&curr->pi_lock); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_lock(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); continue; } @@ -922,9 +927,10 @@ void exit_pi_state_list(struct task_struct *curr) WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; - raw_spin_unlock_irq(&curr->pi_lock); + raw_spin_unlock(&curr->pi_lock); get_pi_state(pi_state); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); rt_mutex_futex_unlock(&pi_state->pi_mutex); @@ -1208,6 +1214,10 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key, WARN_ON(!list_empty(&pi_state->list)); list_add(&pi_state->list, &p->pi_state_list); + /* + * Assignment without holding pi_state->pi_mutex.wait_lock is safe + * because there is no concurrency as the object is not published yet. + */ pi_state->owner = p; raw_spin_unlock_irq(&p->pi_lock); @@ -2878,6 +2888,7 @@ retry: raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); + /* drops pi_state->pi_mutex.wait_lock */ ret = wake_futex_pi(uaddr, uval, pi_state); put_pi_state(pi_state); diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index f7086b7..5270a54 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -322,7 +322,6 @@ int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, /* Calc pointer to the next generic chip */ tmp += sizeof(*gc) + num_ct * sizeof(struct irq_chip_type); } - d->name = name; return 0; } EXPORT_SYMBOL_GPL(__irq_alloc_domain_generic_chips); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index e84b705..ac4644e 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -945,7 +945,7 @@ static int virq_debug_show(struct seq_file *m, void *private) struct irq_desc *desc; struct irq_domain *domain; struct radix_tree_iter iter; - void **slot; + void __rcu **slot; int i; seq_printf(m, " %-16s %-6s %-10s %-10s %s\n", @@ -1453,7 +1453,7 @@ out_free_desc: /* The irq_data was moved, fix the revmap to refer to the new location */ static void irq_domain_fix_revmap(struct irq_data *d) { - void **slot; + void __rcu **slot; if (d->hwirq < d->domain->revmap_size) return; /* Not using radix tree. */ diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 573dc52..d00132b 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1643,6 +1643,10 @@ const void *free_irq(unsigned int irq, void *dev_id) #endif action = __free_irq(irq, dev_id); + + if (!action) + return NULL; + devname = action->name; kfree(action); return devname; diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 02f6606..1fefe6d 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -613,6 +613,33 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) DEFINE_WAKE_Q(wake_q); /* + * __rwsem_down_write_failed_common(sem) + * rwsem_optimistic_spin(sem) + * osq_unlock(sem->osq) + * ... + * atomic_long_add_return(&sem->count) + * + * - VS - + * + * __up_write() + * if (atomic_long_sub_return_release(&sem->count) < 0) + * rwsem_wake(sem) + * osq_is_locked(&sem->osq) + * + * And __up_write() must observe !osq_is_locked() when it observes the + * atomic_long_add_return() in order to not miss a wakeup. + * + * This boils down to: + * + * [S.rel] X = 1 [RmW] r0 = (Y += 0) + * MB RMB + * [RmW] Y += 1 [L] r1 = X + * + * exists (r0=1 /\ r1=0) + */ + smp_rmb(); + + /* * If a spinner is present, it is not necessary to do the wakeup. * Try to do wakeup only if the trylock succeeds to minimize * spinlock contention which may introduce too much delay in the diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 1250e4b..0c44c7b 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -882,6 +882,11 @@ void rcu_irq_exit(void) RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Page faults can happen in NMI handlers, so check... */ + if (READ_ONCE(rdtp->dynticks_nmi_nesting)) + return; + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && rdtp->dynticks_nesting < 1); if (rdtp->dynticks_nesting <= 1) { @@ -1015,6 +1020,11 @@ void rcu_irq_enter(void) RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Page faults can happen in NMI handlers, so check... */ + if (READ_ONCE(rdtp->dynticks_nmi_nesting)) + return; + oldval = rdtp->dynticks_nesting; rdtp->dynticks_nesting++; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 18a6966..d17c5da 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5166,6 +5166,28 @@ void sched_show_task(struct task_struct *p) put_task_stack(p); } +static inline bool +state_filter_match(unsigned long state_filter, struct task_struct *p) +{ + /* no filter, everything matches */ + if (!state_filter) + return true; + + /* filter, but doesn't match */ + if (!(p->state & state_filter)) + return false; + + /* + * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows + * TASK_KILLABLE). + */ + if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE) + return false; + + return true; +} + + void show_state_filter(unsigned long state_filter) { struct task_struct *g, *p; @@ -5188,7 +5210,7 @@ void show_state_filter(unsigned long state_filter) */ touch_nmi_watchdog(); touch_all_softlockup_watchdogs(); - if (!state_filter || (p->state & state_filter)) + if (state_filter_match(state_filter, p)) sched_show_task(p); } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 01217fb..2f93e4a 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -466,8 +466,6 @@ static char *task_group_path(struct task_group *tg) } #endif -static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; - static void print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) { diff --git a/kernel/seccomp.c b/kernel/seccomp.c index c24579d..bb3a380 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -473,14 +473,19 @@ static long seccomp_attach_filter(unsigned int flags, return 0; } +void __get_seccomp_filter(struct seccomp_filter *filter) +{ + /* Reference count is bounded by the number of total processes. */ + refcount_inc(&filter->usage); +} + /* get_seccomp_filter - increments the reference count of the filter on @tsk */ void get_seccomp_filter(struct task_struct *tsk) { struct seccomp_filter *orig = tsk->seccomp.filter; if (!orig) return; - /* Reference count is bounded by the number of total processes. */ - refcount_inc(&orig->usage); + __get_seccomp_filter(orig); } static inline void seccomp_filter_free(struct seccomp_filter *filter) @@ -491,10 +496,8 @@ static inline void seccomp_filter_free(struct seccomp_filter *filter) } } -/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ -void put_seccomp_filter(struct task_struct *tsk) +static void __put_seccomp_filter(struct seccomp_filter *orig) { - struct seccomp_filter *orig = tsk->seccomp.filter; /* Clean up single-reference branches iteratively. */ while (orig && refcount_dec_and_test(&orig->usage)) { struct seccomp_filter *freeme = orig; @@ -503,6 +506,12 @@ void put_seccomp_filter(struct task_struct *tsk) } } +/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ +void put_seccomp_filter(struct task_struct *tsk) +{ + __put_seccomp_filter(tsk->seccomp.filter); +} + static void seccomp_init_siginfo(siginfo_t *info, int syscall, int reason) { memset(info, 0, sizeof(*info)); @@ -1025,13 +1034,13 @@ long seccomp_get_filter(struct task_struct *task, unsigned long filter_off, if (!data) goto out; - get_seccomp_filter(task); + __get_seccomp_filter(filter); spin_unlock_irq(&task->sighand->siglock); if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog))) ret = -EFAULT; - put_seccomp_filter(task); + __put_seccomp_filter(filter); return ret; out: diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6648fbb..423554a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -367,7 +367,8 @@ static struct ctl_table kern_table[] = { .data = &sysctl_sched_time_avg, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, #ifdef CONFIG_SCHEDSTATS { diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 2a685b4..45a3928 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -648,6 +648,12 @@ int blk_trace_startstop(struct request_queue *q, int start) } EXPORT_SYMBOL_GPL(blk_trace_startstop); +/* + * When reading or writing the blktrace sysfs files, the references to the + * opened sysfs or device files should prevent the underlying block device + * from being removed. So no further delete protection is really needed. + */ + /** * blk_trace_ioctl: - handle the ioctls associated with tracing * @bdev: the block device @@ -665,7 +671,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) if (!q) return -ENXIO; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); switch (cmd) { case BLKTRACESETUP: @@ -691,7 +697,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) break; } - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); return ret; } @@ -1727,7 +1733,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); if (attr == &dev_attr_enable) { ret = sprintf(buf, "%u\n", !!q->blk_trace); @@ -1746,7 +1752,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba); out_unlock_bdev: - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); out_bdput: bdput(bdev); out: @@ -1788,7 +1794,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); if (attr == &dev_attr_enable) { if (value) @@ -1814,7 +1820,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, } out_unlock_bdev: - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); out_bdput: bdput(bdev); out: diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index bac629a..c738e76 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -656,15 +656,6 @@ int trace_print_lat_context(struct trace_iterator *iter) return !trace_seq_has_overflowed(s); } -static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; - -static int task_state_char(unsigned long state) -{ - int bit = state ? __ffs(state) + 1 : 0; - - return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; -} - /** * ftrace_find_event - find a registered event * @type: the type of event to look for @@ -930,8 +921,8 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, trace_assign_type(field, iter->ent); - T = task_state_char(field->next_state); - S = task_state_char(field->prev_state); + T = __task_state_to_char(field->next_state); + S = __task_state_to_char(field->prev_state); trace_find_cmdline(field->next_pid, comm); trace_seq_printf(&iter->seq, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", @@ -966,8 +957,8 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = task_state_char(field->prev_state); - T = task_state_char(field->next_state); + S = __task_state_to_char(field->prev_state); + T = __task_state_to_char(field->next_state); trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n", field->prev_pid, field->prev_prio, @@ -1002,8 +993,8 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = task_state_char(field->prev_state); - T = task_state_char(field->next_state); + S = __task_state_to_char(field->prev_state); + T = __task_state_to_char(field->next_state); SEQ_PUT_HEX_FIELD(s, field->prev_pid); SEQ_PUT_HEX_FIELD(s, field->prev_prio); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index ddec53b..0c33197 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -397,10 +397,10 @@ tracing_sched_switch_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = prev->pid; entry->prev_prio = prev->prio; - entry->prev_state = prev->state; + entry->prev_state = __get_task_state(prev); entry->next_pid = next->pid; entry->next_prio = next->prio; - entry->next_state = next->state; + entry->next_state = __get_task_state(next); entry->next_cpu = task_cpu(next); if (!call_filter_check_discard(call, entry, buffer, event)) @@ -425,10 +425,10 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = curr->pid; entry->prev_prio = curr->prio; - entry->prev_state = curr->state; + entry->prev_state = __get_task_state(curr); entry->next_pid = wakee->pid; entry->next_prio = wakee->prio; - entry->next_state = wakee->state; + entry->next_state = __get_task_state(wakee); entry->next_cpu = task_cpu(wakee); if (!call_filter_check_discard(call, entry, buffer, event)) diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index a4df67c..49cb414 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -96,23 +96,9 @@ check_stack(unsigned long ip, unsigned long *stack) if (in_nmi()) return; - /* - * There's a slight chance that we are tracing inside the - * RCU infrastructure, and rcu_irq_enter() will not work - * as expected. - */ - if (unlikely(rcu_irq_enter_disabled())) - return; - local_irq_save(flags); arch_spin_lock(&stack_trace_max_lock); - /* - * RCU may not be watching, make it see us. - * The stack trace code uses rcu_sched. - */ - rcu_irq_enter(); - /* In case another CPU set the tracer_frame on us */ if (unlikely(!frame_size)) this_size -= tracer_frame; @@ -205,7 +191,6 @@ check_stack(unsigned long ip, unsigned long *stack) } out: - rcu_irq_exit(); arch_spin_unlock(&stack_trace_max_lock); local_irq_restore(flags); } diff --git a/mm/filemap.c b/mm/filemap.c index 870971e..db250d0 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2926,9 +2926,15 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) * we're writing. Either one is a pretty crazy thing to do, * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... + * + * Most of the time we do not need this since dio_complete() will do + * the invalidation for us. However there are some file systems that + * do not end up with dio_complete() being called, so let's not break + * them by removing it completely */ - invalidate_inode_pages2_range(mapping, - pos >> PAGE_SHIFT, end); + if (mapping->nrpages) + invalidate_inode_pages2_range(mapping, + pos >> PAGE_SHIFT, end); if (written > 0) { pos += written; diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index c18115d..db82a40 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -126,14 +126,4 @@ config BT_DEBUGFS Provide extensive information about internal Bluetooth states in debugfs. -config BT_LEGACY_IOCTL - bool "Enable legacy ioctl interfaces" - depends on BT && BT_BREDR - default y - help - Enable support for legacy ioctl interfaces. This is only needed - for old and deprecated applications using direct ioctl calls for - controller management. Since Linux 3.4 all configuration and - setup is done via mgmt interface and this is no longer needed. - source "drivers/bluetooth/Kconfig" diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 0bad296..65d734c 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -878,7 +878,6 @@ static int hci_sock_release(struct socket *sock) return 0; } -#ifdef CONFIG_BT_LEGACY_IOCTL static int hci_sock_blacklist_add(struct hci_dev *hdev, void __user *arg) { bdaddr_t bdaddr; @@ -1050,7 +1049,6 @@ done: release_sock(sk); return err; } -#endif static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) @@ -1971,11 +1969,7 @@ static const struct proto_ops hci_sock_ops = { .getname = hci_sock_getname, .sendmsg = hci_sock_sendmsg, .recvmsg = hci_sock_recvmsg, -#ifdef CONFIG_BT_LEGACY_IOCTL .ioctl = hci_sock_ioctl, -#else - .ioctl = sock_no_ioctl, -#endif .poll = datagram_poll, .listen = sock_no_listen, .shutdown = sock_no_shutdown, diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 5a936a6..df062e0 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -401,7 +401,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, if (unlikely(n != mw->mw_nents)) goto out_mapmr_err; - dprintk("RPC: %s: Using frmr %p to map %u segments (%u bytes)\n", + dprintk("RPC: %s: Using frmr %p to map %u segments (%llu bytes)\n", __func__, frmr, mw->mw_nents, mr->length); key = (u8)(mr->rkey & 0x000000FF); diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 2e3a10e7..061d0c3 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -265,6 +265,8 @@ objtool_args += --no-fp endif ifdef CONFIG_GCOV_KERNEL objtool_args += --no-unreachable +else +objtool_args += $(call cc-ifversion, -lt, 0405, --no-unreachable) endif # 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory diff --git a/security/keys/Kconfig b/security/keys/Kconfig index a7a23b5..91eafad 100644 --- a/security/keys/Kconfig +++ b/security/keys/Kconfig @@ -45,10 +45,8 @@ config BIG_KEYS bool "Large payload keys" depends on KEYS depends on TMPFS - depends on (CRYPTO_ANSI_CPRNG = y || CRYPTO_DRBG = y) select CRYPTO_AES - select CRYPTO_ECB - select CRYPTO_RNG + select CRYPTO_GCM help This option provides support for holding large keys within the kernel (for example Kerberos ticket caches). The data may be stored out to diff --git a/security/keys/big_key.c b/security/keys/big_key.c index 6acb00f..e607830 100644 --- a/security/keys/big_key.c +++ b/security/keys/big_key.c @@ -1,5 +1,6 @@ /* Large capacity key type * + * Copyright (C) 2017 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * @@ -16,10 +17,10 @@ #include <linux/shmem_fs.h> #include <linux/err.h> #include <linux/scatterlist.h> +#include <linux/random.h> #include <keys/user-type.h> #include <keys/big_key-type.h> -#include <crypto/rng.h> -#include <crypto/skcipher.h> +#include <crypto/aead.h> /* * Layout of key payload words. @@ -49,7 +50,12 @@ enum big_key_op { /* * Key size for big_key data encryption */ -#define ENC_KEY_SIZE 16 +#define ENC_KEY_SIZE 32 + +/* + * Authentication tag length + */ +#define ENC_AUTHTAG_SIZE 16 /* * big_key defined keys take an arbitrary string as the description and an @@ -64,57 +70,62 @@ struct key_type key_type_big_key = { .destroy = big_key_destroy, .describe = big_key_describe, .read = big_key_read, + /* no ->update(); don't add it without changing big_key_crypt() nonce */ }; /* - * Crypto names for big_key data encryption + * Crypto names for big_key data authenticated encryption */ -static const char big_key_rng_name[] = "stdrng"; -static const char big_key_alg_name[] = "ecb(aes)"; +static const char big_key_alg_name[] = "gcm(aes)"; /* - * Crypto algorithms for big_key data encryption + * Crypto algorithms for big_key data authenticated encryption */ -static struct crypto_rng *big_key_rng; -static struct crypto_skcipher *big_key_skcipher; +static struct crypto_aead *big_key_aead; /* - * Generate random key to encrypt big_key data + * Since changing the key affects the entire object, we need a mutex. */ -static inline int big_key_gen_enckey(u8 *key) -{ - return crypto_rng_get_bytes(big_key_rng, key, ENC_KEY_SIZE); -} +static DEFINE_MUTEX(big_key_aead_lock); /* * Encrypt/decrypt big_key data */ static int big_key_crypt(enum big_key_op op, u8 *data, size_t datalen, u8 *key) { - int ret = -EINVAL; + int ret; struct scatterlist sgio; - SKCIPHER_REQUEST_ON_STACK(req, big_key_skcipher); - - if (crypto_skcipher_setkey(big_key_skcipher, key, ENC_KEY_SIZE)) { + struct aead_request *aead_req; + /* We always use a zero nonce. The reason we can get away with this is + * because we're using a different randomly generated key for every + * different encryption. Notably, too, key_type_big_key doesn't define + * an .update function, so there's no chance we'll wind up reusing the + * key to encrypt updated data. Simply put: one key, one encryption. + */ + u8 zero_nonce[crypto_aead_ivsize(big_key_aead)]; + + aead_req = aead_request_alloc(big_key_aead, GFP_KERNEL); + if (!aead_req) + return -ENOMEM; + + memset(zero_nonce, 0, sizeof(zero_nonce)); + sg_init_one(&sgio, data, datalen + (op == BIG_KEY_ENC ? ENC_AUTHTAG_SIZE : 0)); + aead_request_set_crypt(aead_req, &sgio, &sgio, datalen, zero_nonce); + aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); + aead_request_set_ad(aead_req, 0); + + mutex_lock(&big_key_aead_lock); + if (crypto_aead_setkey(big_key_aead, key, ENC_KEY_SIZE)) { ret = -EAGAIN; goto error; } - - skcipher_request_set_tfm(req, big_key_skcipher); - skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, - NULL, NULL); - - sg_init_one(&sgio, data, datalen); - skcipher_request_set_crypt(req, &sgio, &sgio, datalen, NULL); - if (op == BIG_KEY_ENC) - ret = crypto_skcipher_encrypt(req); + ret = crypto_aead_encrypt(aead_req); else - ret = crypto_skcipher_decrypt(req); - - skcipher_request_zero(req); - + ret = crypto_aead_decrypt(aead_req); error: + mutex_unlock(&big_key_aead_lock); + aead_request_free(aead_req); return ret; } @@ -146,16 +157,13 @@ int big_key_preparse(struct key_preparsed_payload *prep) * * File content is stored encrypted with randomly generated key. */ - size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher)); + size_t enclen = datalen + ENC_AUTHTAG_SIZE; loff_t pos = 0; - /* prepare aligned data to encrypt */ data = kmalloc(enclen, GFP_KERNEL); if (!data) return -ENOMEM; - memcpy(data, prep->data, datalen); - memset(data + datalen, 0x00, enclen - datalen); /* generate random key */ enckey = kmalloc(ENC_KEY_SIZE, GFP_KERNEL); @@ -163,13 +171,12 @@ int big_key_preparse(struct key_preparsed_payload *prep) ret = -ENOMEM; goto error; } - - ret = big_key_gen_enckey(enckey); - if (ret) + ret = get_random_bytes_wait(enckey, ENC_KEY_SIZE); + if (unlikely(ret)) goto err_enckey; /* encrypt aligned data */ - ret = big_key_crypt(BIG_KEY_ENC, data, enclen, enckey); + ret = big_key_crypt(BIG_KEY_ENC, data, datalen, enckey); if (ret) goto err_enckey; @@ -195,7 +202,7 @@ int big_key_preparse(struct key_preparsed_payload *prep) *path = file->f_path; path_get(path); fput(file); - kfree(data); + kzfree(data); } else { /* Just store the data in a buffer */ void *data = kmalloc(datalen, GFP_KERNEL); @@ -211,9 +218,9 @@ int big_key_preparse(struct key_preparsed_payload *prep) err_fput: fput(file); err_enckey: - kfree(enckey); + kzfree(enckey); error: - kfree(data); + kzfree(data); return ret; } @@ -227,7 +234,7 @@ void big_key_free_preparse(struct key_preparsed_payload *prep) path_put(path); } - kfree(prep->payload.data[big_key_data]); + kzfree(prep->payload.data[big_key_data]); } /* @@ -259,7 +266,7 @@ void big_key_destroy(struct key *key) path->mnt = NULL; path->dentry = NULL; } - kfree(key->payload.data[big_key_data]); + kzfree(key->payload.data[big_key_data]); key->payload.data[big_key_data] = NULL; } @@ -295,7 +302,7 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen) struct file *file; u8 *data; u8 *enckey = (u8 *)key->payload.data[big_key_data]; - size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher)); + size_t enclen = datalen + ENC_AUTHTAG_SIZE; loff_t pos = 0; data = kmalloc(enclen, GFP_KERNEL); @@ -328,7 +335,7 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen) err_fput: fput(file); error: - kfree(data); + kzfree(data); } else { ret = datalen; if (copy_to_user(buffer, key->payload.data[big_key_data], @@ -344,47 +351,31 @@ error: */ static int __init big_key_init(void) { - struct crypto_skcipher *cipher; - struct crypto_rng *rng; int ret; - rng = crypto_alloc_rng(big_key_rng_name, 0, 0); - if (IS_ERR(rng)) { - pr_err("Can't alloc rng: %ld\n", PTR_ERR(rng)); - return PTR_ERR(rng); - } - - big_key_rng = rng; - - /* seed RNG */ - ret = crypto_rng_reset(rng, NULL, crypto_rng_seedsize(rng)); - if (ret) { - pr_err("Can't reset rng: %d\n", ret); - goto error_rng; - } - /* init block cipher */ - cipher = crypto_alloc_skcipher(big_key_alg_name, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(cipher)) { - ret = PTR_ERR(cipher); + big_key_aead = crypto_alloc_aead(big_key_alg_name, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(big_key_aead)) { + ret = PTR_ERR(big_key_aead); pr_err("Can't alloc crypto: %d\n", ret); - goto error_rng; + return ret; + } + ret = crypto_aead_setauthsize(big_key_aead, ENC_AUTHTAG_SIZE); + if (ret < 0) { + pr_err("Can't set crypto auth tag len: %d\n", ret); + goto free_aead; } - - big_key_skcipher = cipher; ret = register_key_type(&key_type_big_key); if (ret < 0) { pr_err("Can't register type: %d\n", ret); - goto error_cipher; + goto free_aead; } return 0; -error_cipher: - crypto_free_skcipher(big_key_skcipher); -error_rng: - crypto_free_rng(big_key_rng); +free_aead: + crypto_free_aead(big_key_aead); return ret; } diff --git a/security/keys/internal.h b/security/keys/internal.h index 1c02c65..503adba 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -141,7 +141,7 @@ extern key_ref_t keyring_search_aux(key_ref_t keyring_ref, extern key_ref_t search_my_process_keyrings(struct keyring_search_context *ctx); extern key_ref_t search_process_keyrings(struct keyring_search_context *ctx); -extern struct key *find_keyring_by_name(const char *name, bool skip_perm_check); +extern struct key *find_keyring_by_name(const char *name, bool uid_keyring); extern int install_user_keyrings(void); extern int install_thread_keyring_to_cred(struct cred *); diff --git a/security/keys/key.c b/security/keys/key.c index 83da68d..eb914a8 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -54,10 +54,10 @@ void __key_check(const struct key *key) struct key_user *key_user_lookup(kuid_t uid) { struct key_user *candidate = NULL, *user; - struct rb_node *parent = NULL; - struct rb_node **p; + struct rb_node *parent, **p; try_again: + parent = NULL; p = &key_user_tree.rb_node; spin_lock(&key_user_lock); @@ -302,6 +302,8 @@ struct key *key_alloc(struct key_type *type, const char *desc, key->flags |= 1 << KEY_FLAG_IN_QUOTA; if (flags & KEY_ALLOC_BUILT_IN) key->flags |= 1 << KEY_FLAG_BUILTIN; + if (flags & KEY_ALLOC_UID_KEYRING) + key->flags |= 1 << KEY_FLAG_UID_KEYRING; #ifdef KEY_DEBUGGING key->magic = KEY_DEBUG_MAGIC; diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index ab0b337..365ff85 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -766,12 +766,17 @@ long keyctl_read_key(key_serial_t keyid, char __user *buffer, size_t buflen) key = key_ref_to_ptr(key_ref); + if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) { + ret = -ENOKEY; + goto error2; + } + /* see if we can read it directly */ ret = key_permission(key_ref, KEY_NEED_READ); if (ret == 0) goto can_read_key; if (ret != -EACCES) - goto error; + goto error2; /* we can't; see if it's searchable from this process's keyrings * - we automatically take account of the fact that it may be @@ -1406,11 +1411,9 @@ long keyctl_assume_authority(key_serial_t id) } ret = keyctl_change_reqkey_auth(authkey); - if (ret < 0) - goto error; + if (ret == 0) + ret = authkey->serial; key_put(authkey); - - ret = authkey->serial; error: return ret; } diff --git a/security/keys/keyring.c b/security/keys/keyring.c index de81793..4fa82a8 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -423,7 +423,7 @@ static void keyring_describe(const struct key *keyring, struct seq_file *m) } struct keyring_read_iterator_context { - size_t qty; + size_t buflen; size_t count; key_serial_t __user *buffer; }; @@ -435,9 +435,9 @@ static int keyring_read_iterator(const void *object, void *data) int ret; kenter("{%s,%d},,{%zu/%zu}", - key->type->name, key->serial, ctx->count, ctx->qty); + key->type->name, key->serial, ctx->count, ctx->buflen); - if (ctx->count >= ctx->qty) + if (ctx->count >= ctx->buflen) return 1; ret = put_user(key->serial, ctx->buffer); @@ -472,16 +472,12 @@ static long keyring_read(const struct key *keyring, return 0; /* Calculate how much data we could return */ - ctx.qty = nr_keys * sizeof(key_serial_t); - if (!buffer || !buflen) - return ctx.qty; - - if (buflen > ctx.qty) - ctx.qty = buflen; + return nr_keys * sizeof(key_serial_t); /* Copy the IDs of the subscribed keys into the buffer */ ctx.buffer = (key_serial_t __user *)buffer; + ctx.buflen = buflen; ctx.count = 0; ret = assoc_array_iterate(&keyring->keys, keyring_read_iterator, &ctx); if (ret < 0) { @@ -1101,15 +1097,15 @@ found: /* * Find a keyring with the specified name. * - * All named keyrings in the current user namespace are searched, provided they - * grant Search permission directly to the caller (unless this check is - * skipped). Keyrings whose usage points have reached zero or who have been - * revoked are skipped. + * Only keyrings that have nonzero refcount, are not revoked, and are owned by a + * user in the current user namespace are considered. If @uid_keyring is %true, + * the keyring additionally must have been allocated as a user or user session + * keyring; otherwise, it must grant Search permission directly to the caller. * * Returns a pointer to the keyring with the keyring's refcount having being * incremented on success. -ENOKEY is returned if a key could not be found. */ -struct key *find_keyring_by_name(const char *name, bool skip_perm_check) +struct key *find_keyring_by_name(const char *name, bool uid_keyring) { struct key *keyring; int bucket; @@ -1137,10 +1133,15 @@ struct key *find_keyring_by_name(const char *name, bool skip_perm_check) if (strcmp(keyring->description, name) != 0) continue; - if (!skip_perm_check && - key_permission(make_key_ref(keyring, 0), - KEY_NEED_SEARCH) < 0) - continue; + if (uid_keyring) { + if (!test_bit(KEY_FLAG_UID_KEYRING, + &keyring->flags)) + continue; + } else { + if (key_permission(make_key_ref(keyring, 0), + KEY_NEED_SEARCH) < 0) + continue; + } /* we've got a match but we might end up racing with * key_cleanup() if the keyring is currently 'dead' diff --git a/security/keys/proc.c b/security/keys/proc.c index bf08d02..de83430 100644 --- a/security/keys/proc.c +++ b/security/keys/proc.c @@ -187,7 +187,7 @@ static int proc_keys_show(struct seq_file *m, void *v) struct keyring_search_context ctx = { .index_key.type = key->type, .index_key.description = key->description, - .cred = current_cred(), + .cred = m->file->f_cred, .match_data.cmp = lookup_user_key_possessed, .match_data.raw_data = key, .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT, @@ -207,11 +207,7 @@ static int proc_keys_show(struct seq_file *m, void *v) } } - /* check whether the current task is allowed to view the key (assuming - * non-possession) - * - the caller holds a spinlock, and thus the RCU read lock, making our - * access to __current_cred() safe - */ + /* check whether the current task is allowed to view the key */ rc = key_task_permission(key_ref, ctx.cred, KEY_NEED_VIEW); if (rc < 0) return 0; diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index 86bced9..293d359 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -77,7 +77,8 @@ int install_user_keyrings(void) if (IS_ERR(uid_keyring)) { uid_keyring = keyring_alloc(buf, user->uid, INVALID_GID, cred, user_keyring_perm, - KEY_ALLOC_IN_QUOTA, + KEY_ALLOC_UID_KEYRING | + KEY_ALLOC_IN_QUOTA, NULL, NULL); if (IS_ERR(uid_keyring)) { ret = PTR_ERR(uid_keyring); @@ -94,7 +95,8 @@ int install_user_keyrings(void) session_keyring = keyring_alloc(buf, user->uid, INVALID_GID, cred, user_keyring_perm, - KEY_ALLOC_IN_QUOTA, + KEY_ALLOC_UID_KEYRING | + KEY_ALLOC_IN_QUOTA, NULL, NULL); if (IS_ERR(session_keyring)) { ret = PTR_ERR(session_keyring); diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c index afe9d22..6ebf1af 100644 --- a/security/keys/request_key_auth.c +++ b/security/keys/request_key_auth.c @@ -120,6 +120,18 @@ static void request_key_auth_revoke(struct key *key) } } +static void free_request_key_auth(struct request_key_auth *rka) +{ + if (!rka) + return; + key_put(rka->target_key); + key_put(rka->dest_keyring); + if (rka->cred) + put_cred(rka->cred); + kfree(rka->callout_info); + kfree(rka); +} + /* * Destroy an instantiation authorisation token key. */ @@ -129,15 +141,7 @@ static void request_key_auth_destroy(struct key *key) kenter("{%d}", key->serial); - if (rka->cred) { - put_cred(rka->cred); - rka->cred = NULL; - } - - key_put(rka->target_key); - key_put(rka->dest_keyring); - kfree(rka->callout_info); - kfree(rka); + free_request_key_auth(rka); } /* @@ -151,22 +155,18 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, const struct cred *cred = current->cred; struct key *authkey = NULL; char desc[20]; - int ret; + int ret = -ENOMEM; kenter("%d,", target->serial); /* allocate a auth record */ - rka = kmalloc(sizeof(*rka), GFP_KERNEL); - if (!rka) { - kleave(" = -ENOMEM"); - return ERR_PTR(-ENOMEM); - } - rka->callout_info = kmalloc(callout_len, GFP_KERNEL); - if (!rka->callout_info) { - kleave(" = -ENOMEM"); - kfree(rka); - return ERR_PTR(-ENOMEM); - } + rka = kzalloc(sizeof(*rka), GFP_KERNEL); + if (!rka) + goto error; + rka->callout_info = kmemdup(callout_info, callout_len, GFP_KERNEL); + if (!rka->callout_info) + goto error_free_rka; + rka->callout_len = callout_len; /* see if the calling process is already servicing the key request of * another process */ @@ -176,8 +176,12 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, /* if the auth key has been revoked, then the key we're * servicing is already instantiated */ - if (test_bit(KEY_FLAG_REVOKED, &cred->request_key_auth->flags)) - goto auth_key_revoked; + if (test_bit(KEY_FLAG_REVOKED, + &cred->request_key_auth->flags)) { + up_read(&cred->request_key_auth->sem); + ret = -EKEYREVOKED; + goto error_free_rka; + } irka = cred->request_key_auth->payload.data[0]; rka->cred = get_cred(irka->cred); @@ -193,8 +197,6 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, rka->target_key = key_get(target); rka->dest_keyring = key_get(dest_keyring); - memcpy(rka->callout_info, callout_info, callout_len); - rka->callout_len = callout_len; /* allocate the auth key */ sprintf(desc, "%x", target->serial); @@ -205,32 +207,22 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, KEY_USR_VIEW, KEY_ALLOC_NOT_IN_QUOTA, NULL); if (IS_ERR(authkey)) { ret = PTR_ERR(authkey); - goto error_alloc; + goto error_free_rka; } /* construct the auth key */ ret = key_instantiate_and_link(authkey, rka, 0, NULL, NULL); if (ret < 0) - goto error_inst; + goto error_put_authkey; kleave(" = {%d,%d}", authkey->serial, refcount_read(&authkey->usage)); return authkey; -auth_key_revoked: - up_read(&cred->request_key_auth->sem); - kfree(rka->callout_info); - kfree(rka); - kleave("= -EKEYREVOKED"); - return ERR_PTR(-EKEYREVOKED); - -error_inst: - key_revoke(authkey); +error_put_authkey: key_put(authkey); -error_alloc: - key_put(rka->target_key); - key_put(rka->dest_keyring); - kfree(rka->callout_info); - kfree(rka); +error_free_rka: + free_request_key_auth(rka); +error: kleave("= %d", ret); return ERR_PTR(ret); } diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 69d09c3..cd7359e 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -88,6 +88,12 @@ struct kvm_s390_io_adapter_req { /* kvm attributes for KVM_S390_VM_TOD */ #define KVM_S390_VM_TOD_LOW 0 #define KVM_S390_VM_TOD_HIGH 1 +#define KVM_S390_VM_TOD_EXT 2 + +struct kvm_s390_vm_tod_clock { + __u8 epoch_idx; + __u64 tod; +}; /* kvm attributes for KVM_S390_VM_CPU_MODEL */ /* processor related attributes are r/w */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 8ea315a1..2519c6c 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -196,6 +196,7 @@ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ +#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ @@ -287,6 +288,7 @@ #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ #define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ +#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 5dff775..c10c912 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -21,11 +21,13 @@ # define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31)) # define DISABLE_CYRIX_ARR (1<<(X86_FEATURE_CYRIX_ARR & 31)) # define DISABLE_CENTAUR_MCR (1<<(X86_FEATURE_CENTAUR_MCR & 31)) +# define DISABLE_PCID 0 #else # define DISABLE_VME 0 # define DISABLE_K6_MTRR 0 # define DISABLE_CYRIX_ARR 0 # define DISABLE_CENTAUR_MCR 0 +# define DISABLE_PCID (1<<(X86_FEATURE_PCID & 31)) #endif /* CONFIG_X86_64 */ #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS @@ -49,7 +51,7 @@ #define DISABLED_MASK1 0 #define DISABLED_MASK2 0 #define DISABLED_MASK3 (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR) -#define DISABLED_MASK4 0 +#define DISABLED_MASK4 (DISABLE_PCID) #define DISABLED_MASK5 0 #define DISABLED_MASK6 0 #define DISABLED_MASK7 0 diff --git a/tools/include/asm-generic/hugetlb_encode.h b/tools/include/asm-generic/hugetlb_encode.h new file mode 100644 index 0000000..e4732d3 --- /dev/null +++ b/tools/include/asm-generic/hugetlb_encode.h @@ -0,0 +1,34 @@ +#ifndef _ASM_GENERIC_HUGETLB_ENCODE_H_ +#define _ASM_GENERIC_HUGETLB_ENCODE_H_ + +/* + * Several system calls take a flag to request "hugetlb" huge pages. + * Without further specification, these system calls will use the + * system's default huge page size. If a system supports multiple + * huge page sizes, the desired huge page size can be specified in + * bits [26:31] of the flag arguments. The value in these 6 bits + * will encode the log2 of the huge page size. + * + * The following definitions are associated with this huge page size + * encoding in flag arguments. System call specific header files + * that use this encoding should include this file. They can then + * provide definitions based on these with their own specific prefix. + * for example: + * #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT + */ + +#define HUGETLB_FLAG_ENCODE_SHIFT 26 +#define HUGETLB_FLAG_ENCODE_MASK 0x3f + +#define HUGETLB_FLAG_ENCODE_64KB (16 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_512KB (19 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_1MB (20 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_2MB (21 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_8MB (23 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16MB (24 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_256MB (28 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_1GB (30 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_2GB (31 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16GB (34 << HUGETLB_FLAG_ENCODE_SHIFT) + +#endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */ diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h index 8c27db0..203268f 100644 --- a/tools/include/uapi/asm-generic/mman-common.h +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -58,20 +58,12 @@ overrides the coredump filter bits */ #define MADV_DODUMP 17 /* Clear the MADV_DONTDUMP flag */ +#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */ +#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */ + /* compatibility flags */ #define MAP_FILE 0 -/* - * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define MAP_HUGE_SHIFT 26 -#define MAP_HUGE_MASK 0x3f - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 #define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 101593a..97677cd 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -700,6 +700,7 @@ struct drm_prime_handle { struct drm_syncobj_create { __u32 handle; +#define DRM_SYNCOBJ_CREATE_SIGNALED (1 << 0) __u32 flags; }; @@ -718,6 +719,24 @@ struct drm_syncobj_handle { __u32 pad; }; +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0) +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1) +struct drm_syncobj_wait { + __u64 handles; + /* absolute timeout */ + __s64 timeout_nsec; + __u32 count_handles; + __u32 flags; + __u32 first_signaled; /* only valid when not waiting all */ + __u32 pad; +}; + +struct drm_syncobj_array { + __u64 handles; + __u32 count_handles; + __u32 pad; +}; + #if defined(__cplusplus) } #endif @@ -840,6 +859,9 @@ extern "C" { #define DRM_IOCTL_SYNCOBJ_DESTROY DRM_IOWR(0xC0, struct drm_syncobj_destroy) #define DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD DRM_IOWR(0xC1, struct drm_syncobj_handle) #define DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE DRM_IOWR(0xC2, struct drm_syncobj_handle) +#define DRM_IOCTL_SYNCOBJ_WAIT DRM_IOWR(0xC3, struct drm_syncobj_wait) +#define DRM_IOCTL_SYNCOBJ_RESET DRM_IOWR(0xC4, struct drm_syncobj_array) +#define DRM_IOCTL_SYNCOBJ_SIGNAL DRM_IOWR(0xC5, struct drm_syncobj_array) /** * Device specific ioctls should only be in their respective headers diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 7ccbd6a..6598fb7 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -260,6 +260,8 @@ typedef struct _drm_i915_sarea { #define DRM_I915_GEM_CONTEXT_GETPARAM 0x34 #define DRM_I915_GEM_CONTEXT_SETPARAM 0x35 #define DRM_I915_PERF_OPEN 0x36 +#define DRM_I915_PERF_ADD_CONFIG 0x37 +#define DRM_I915_PERF_REMOVE_CONFIG 0x38 #define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t) #define DRM_IOCTL_I915_FLUSH DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH) @@ -315,6 +317,8 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param) #define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param) #define DRM_IOCTL_I915_PERF_OPEN DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param) +#define DRM_IOCTL_I915_PERF_ADD_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config) +#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64) /* Allow drivers to submit batchbuffers directly to hardware, relying * on the security mechanisms provided by hardware. @@ -431,6 +435,11 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_HAS_EXEC_BATCH_FIRST 48 +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of + * drm_i915_gem_exec_fence structures. See I915_EXEC_FENCE_ARRAY. + */ +#define I915_PARAM_HAS_EXEC_FENCE_ARRAY 49 + typedef struct drm_i915_getparam { __s32 param; /* @@ -812,6 +821,17 @@ struct drm_i915_gem_exec_object2 { __u64 rsvd2; }; +struct drm_i915_gem_exec_fence { + /** + * User's handle for a drm_syncobj to wait on or signal. + */ + __u32 handle; + +#define I915_EXEC_FENCE_WAIT (1<<0) +#define I915_EXEC_FENCE_SIGNAL (1<<1) + __u32 flags; +}; + struct drm_i915_gem_execbuffer2 { /** * List of gem_exec_object2 structs @@ -826,7 +846,11 @@ struct drm_i915_gem_execbuffer2 { __u32 DR1; __u32 DR4; __u32 num_cliprects; - /** This is a struct drm_clip_rect *cliprects */ + /** + * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY + * is not set. If I915_EXEC_FENCE_ARRAY is set, then this is a + * struct drm_i915_gem_exec_fence *fences. + */ __u64 cliprects_ptr; #define I915_EXEC_RING_MASK (7<<0) #define I915_EXEC_DEFAULT (0<<0) @@ -927,7 +951,14 @@ struct drm_i915_gem_execbuffer2 { * element). */ #define I915_EXEC_BATCH_FIRST (1<<18) -#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_BATCH_FIRST<<1)) + +/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr + * define an array of i915_gem_exec_fence structures which specify a set of + * dma fences to wait upon or signal. + */ +#define I915_EXEC_FENCE_ARRAY (1<<19) + +#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1)) #define I915_EXEC_CONTEXT_ID_MASK (0xffffffff) #define i915_execbuffer2_set_context_id(eb2, context) \ @@ -1467,6 +1498,22 @@ enum drm_i915_perf_record_type { DRM_I915_PERF_RECORD_MAX /* non-ABI */ }; +/** + * Structure to upload perf dynamic configuration into the kernel. + */ +struct drm_i915_perf_oa_config { + /** String formatted like "%08x-%04x-%04x-%04x-%012x" */ + char uuid[36]; + + __u32 n_mux_regs; + __u32 n_boolean_regs; + __u32 n_flex_regs; + + __u64 __user mux_regs_ptr; + __u64 __user boolean_regs_ptr; + __u64 __user flex_regs_ptr; +}; + #if defined(__cplusplus) } #endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 461811e..43ab5c4 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -143,12 +143,6 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE -enum bpf_sockmap_flags { - BPF_SOCKMAP_UNSPEC, - BPF_SOCKMAP_STRPARSER, - __MAX_BPF_SOCKMAP_FLAG -}; - /* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command * to the given target_fd cgroup the descendent cgroup will be able to * override effective bpf program that was inherited from this cgroup @@ -368,9 +362,20 @@ union bpf_attr { * int bpf_redirect(ifindex, flags) * redirect to another netdev * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: TC_ACT_REDIRECT + * @flags: + * cls_bpf: + * bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * xdp_bpf: + * all bits - reserved + * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error + * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error + * int bpf_redirect_map(map, key, flags) + * redirect to endpoint in map + * @map: pointer to dev map + * @key: index in map to lookup + * @flags: -- + * Return: XDP_REDIRECT on success or XDP_ABORT on error * * u32 bpf_get_route_realm(skb) * retrieve a dst's tclassid @@ -632,7 +637,7 @@ union bpf_attr { FN(skb_adjust_room), \ FN(redirect_map), \ FN(sk_redirect_map), \ - FN(sock_map_update), + FN(sock_map_update), \ /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -753,20 +758,23 @@ struct bpf_sock { __u32 family; __u32 type; __u32 protocol; + __u32 mark; + __u32 priority; }; #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. * A valid XDP program must return one of these defined values. All other - * return codes are reserved for future use. Unknown return codes will result - * in packet drop. + * return codes are reserved for future use. Unknown return codes will + * result in packet drops and a warning via bpf_warn_invalid_xdp_action(). */ enum xdp_action { XDP_ABORTED = 0, XDP_DROP, XDP_PASS, XDP_TX, + XDP_REDIRECT, }; /* user accessible metadata for XDP packet hook diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 6cd63c1..8388875 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -711,7 +711,8 @@ struct kvm_ppc_one_seg_page_size { struct kvm_ppc_smmu_info { __u64 flags; __u32 slb_size; - __u32 pad; + __u16 data_keys; /* # storage keys supported for data */ + __u16 instr_keys; /* # storage keys supported for instructions */ struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; }; diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h index 81d8edf..a937480 100644 --- a/tools/include/uapi/linux/mman.h +++ b/tools/include/uapi/linux/mman.h @@ -1,7 +1,8 @@ #ifndef _UAPI_LINUX_MMAN_H #define _UAPI_LINUX_MMAN_H -#include <uapi/asm/mman.h> +#include <asm/mman.h> +#include <asm-generic/hugetlb_encode.h> #define MREMAP_MAYMOVE 1 #define MREMAP_FIXED 2 @@ -10,4 +11,25 @@ #define OVERCOMMIT_ALWAYS 1 #define OVERCOMMIT_NEVER 2 +/* + * Huge page size encoding when MAP_HUGETLB is specified, and a huge page + * size other than the default is desired. See hugetlb_encode.h. + * All known huge page size encodings are provided here. It is the + * responsibility of the application to know which sizes are supported on + * the running system. See mmap(2) man page for details. + */ +#define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT +#define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK + +#define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB +#define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB +#define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB +#define MAP_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB +#define MAP_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB +#define MAP_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MAP_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MAP_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB +#define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB +#define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB + #endif /* _UAPI_LINUX_MMAN_H */ diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 0f22768..34a579f 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -284,11 +284,16 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, case 0x8d: if (sib == 0x24 && rex_w && !rex_b && !rex_x) { - /* lea disp(%rsp), reg */ *type = INSN_STACK; - op->src.type = OP_SRC_ADD; + if (!insn.displacement.value) { + /* lea (%rsp), reg */ + op->src.type = OP_SRC_REG; + } else { + /* lea disp(%rsp), reg */ + op->src.type = OP_SRC_ADD; + op->src.offset = insn.displacement.value; + } op->src.reg = CFI_SP; - op->src.offset = insn.displacement.value; op->dest.type = OP_DEST_REG; op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r]; diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 6207282..627b7ca 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -1,34 +1,8 @@ tools/perf -tools/arch/alpha/include/asm/barrier.h -tools/arch/arm/include/asm/barrier.h -tools/arch/arm64/include/asm/barrier.h -tools/arch/ia64/include/asm/barrier.h -tools/arch/mips/include/asm/barrier.h -tools/arch/powerpc/include/asm/barrier.h -tools/arch/s390/include/asm/barrier.h -tools/arch/sh/include/asm/barrier.h -tools/arch/sparc/include/asm/barrier.h -tools/arch/sparc/include/asm/barrier_32.h -tools/arch/sparc/include/asm/barrier_64.h -tools/arch/tile/include/asm/barrier.h -tools/arch/x86/include/asm/barrier.h -tools/arch/x86/include/asm/cmpxchg.h -tools/arch/x86/include/asm/cpufeatures.h -tools/arch/x86/include/asm/disabled-features.h -tools/arch/x86/include/asm/required-features.h -tools/arch/x86/include/uapi/asm/svm.h -tools/arch/x86/include/uapi/asm/vmx.h -tools/arch/x86/include/uapi/asm/kvm.h -tools/arch/x86/include/uapi/asm/kvm_perf.h -tools/arch/x86/lib/memcpy_64.S -tools/arch/x86/lib/memset_64.S -tools/arch/s390/include/uapi/asm/kvm_perf.h -tools/arch/s390/include/uapi/asm/sie.h -tools/arch/xtensa/include/asm/barrier.h +tools/arch tools/scripts tools/build -tools/arch/x86/include/asm/atomic.h -tools/arch/x86/include/asm/rmwcc.h +tools/include tools/lib/traceevent tools/lib/api tools/lib/bpf @@ -42,60 +16,3 @@ tools/lib/find_bit.c tools/lib/bitmap.c tools/lib/str_error_r.c tools/lib/vsprintf.c -tools/include/asm/alternative-asm.h -tools/include/asm/atomic.h -tools/include/asm/barrier.h -tools/include/asm/bug.h -tools/include/asm-generic/atomic-gcc.h -tools/include/asm-generic/barrier.h -tools/include/asm-generic/bitops/arch_hweight.h -tools/include/asm-generic/bitops/atomic.h -tools/include/asm-generic/bitops/const_hweight.h -tools/include/asm-generic/bitops/__ffs.h -tools/include/asm-generic/bitops/__ffz.h -tools/include/asm-generic/bitops/__fls.h -tools/include/asm-generic/bitops/find.h -tools/include/asm-generic/bitops/fls64.h -tools/include/asm-generic/bitops/fls.h -tools/include/asm-generic/bitops/hweight.h -tools/include/asm-generic/bitops.h -tools/include/linux/atomic.h -tools/include/linux/bitops.h -tools/include/linux/compiler.h -tools/include/linux/compiler-gcc.h -tools/include/linux/coresight-pmu.h -tools/include/linux/bug.h -tools/include/linux/filter.h -tools/include/linux/hash.h -tools/include/linux/kernel.h -tools/include/linux/list.h -tools/include/linux/log2.h -tools/include/uapi/asm-generic/fcntl.h -tools/include/uapi/asm-generic/ioctls.h -tools/include/uapi/asm-generic/mman-common.h -tools/include/uapi/asm-generic/mman.h -tools/include/uapi/drm/drm.h -tools/include/uapi/drm/i915_drm.h -tools/include/uapi/linux/bpf.h -tools/include/uapi/linux/bpf_common.h -tools/include/uapi/linux/fcntl.h -tools/include/uapi/linux/hw_breakpoint.h -tools/include/uapi/linux/kvm.h -tools/include/uapi/linux/mman.h -tools/include/uapi/linux/perf_event.h -tools/include/uapi/linux/sched.h -tools/include/uapi/linux/stat.h -tools/include/uapi/linux/vhost.h -tools/include/uapi/sound/asound.h -tools/include/linux/poison.h -tools/include/linux/rbtree.h -tools/include/linux/rbtree_augmented.h -tools/include/linux/refcount.h -tools/include/linux/string.h -tools/include/linux/stringify.h -tools/include/linux/types.h -tools/include/linux/err.h -tools/include/linux/bitmap.h -tools/include/linux/time64.h -tools/arch/*/include/uapi/asm/mman.h -tools/arch/*/include/uapi/asm/perf_regs.h diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build index bd518b6..5bd7b92 100644 --- a/tools/perf/arch/s390/util/Build +++ b/tools/perf/arch/s390/util/Build @@ -1,5 +1,4 @@ libperf-y += header.o -libperf-y += sym-handling.o libperf-y += kvm-stat.o libperf-$(CONFIG_DWARF) += dwarf-regs.o diff --git a/tools/perf/arch/s390/util/sym-handling.c b/tools/perf/arch/s390/util/sym-handling.c deleted file mode 100644 index e103f6e..0000000 --- a/tools/perf/arch/s390/util/sym-handling.c +++ /dev/null @@ -1,29 +0,0 @@ -/* - * Architecture specific ELF symbol handling and relocation mapping. - * - * Copyright 2017 IBM Corp. - * Author(s): Thomas Richter <tmricht@linux.vnet.ibm.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - */ - -#include "symbol.h" - -#ifdef HAVE_LIBELF_SUPPORT -bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) -{ - if (ehdr.e_type == ET_EXEC) - return false; - return ehdr.e_type == ET_REL || ehdr.e_type == ET_DYN; -} - -void arch__adjust_sym_map_offset(GElf_Sym *sym, - GElf_Shdr *shdr __maybe_unused, - struct map *map) -{ - if (map->type == MAP__FUNCTION) - sym->st_value += map->start; -} -#endif diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 510b513..be09d77 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -65,8 +65,6 @@ static int parse_callchain_mode(const char *value) callchain_param.mode = CHAIN_FOLDED; return 0; } - - pr_err("Invalid callchain mode: %s\n", value); return -1; } @@ -82,8 +80,6 @@ static int parse_callchain_order(const char *value) callchain_param.order_set = true; return 0; } - - pr_err("Invalid callchain order: %s\n", value); return -1; } @@ -105,8 +101,6 @@ static int parse_callchain_sort_key(const char *value) callchain_param.branch_callstack = 1; return 0; } - - pr_err("Invalid callchain sort key: %s\n", value); return -1; } @@ -124,8 +118,6 @@ static int parse_callchain_value(const char *value) callchain_param.value = CCVAL_COUNT; return 0; } - - pr_err("Invalid callchain config key: %s\n", value); return -1; } @@ -319,12 +311,27 @@ int perf_callchain_config(const char *var, const char *value) return ret; } - if (!strcmp(var, "print-type")) - return parse_callchain_mode(value); - if (!strcmp(var, "order")) - return parse_callchain_order(value); - if (!strcmp(var, "sort-key")) - return parse_callchain_sort_key(value); + if (!strcmp(var, "print-type")){ + int ret; + ret = parse_callchain_mode(value); + if (ret == -1) + pr_err("Invalid callchain mode: %s\n", value); + return ret; + } + if (!strcmp(var, "order")){ + int ret; + ret = parse_callchain_order(value); + if (ret == -1) + pr_err("Invalid callchain order: %s\n", value); + return ret; + } + if (!strcmp(var, "sort-key")){ + int ret; + ret = parse_callchain_sort_key(value); + if (ret == -1) + pr_err("Invalid callchain sort key: %s\n", value); + return ret; + } if (!strcmp(var, "threshold")) { callchain_param.min_percent = strtod(value, &endptr); if (value == endptr) { diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 4bb8937..0dccdb8 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -271,12 +271,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) return evsel; } +static bool perf_event_can_profile_kernel(void) +{ + return geteuid() == 0 || perf_event_paranoid() == -1; +} + struct perf_evsel *perf_evsel__new_cycles(bool precise) { struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, - .exclude_kernel = geteuid() != 0, + .exclude_kernel = !perf_event_can_profile_kernel(), }; struct perf_evsel *evsel; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 5c39f42..9cf781f 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -810,12 +810,6 @@ static u64 ref_reloc(struct kmap *kmap) void __weak arch__sym_update(struct symbol *s __maybe_unused, GElf_Sym *sym __maybe_unused) { } -void __weak arch__adjust_sym_map_offset(GElf_Sym *sym, GElf_Shdr *shdr, - struct map *map __maybe_unused) -{ - sym->st_value -= shdr->sh_addr - shdr->sh_offset; -} - int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule) { @@ -996,7 +990,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, /* Adjust symbol to map to file offset */ if (adjust_kernel_syms) - arch__adjust_sym_map_offset(&sym, &shdr, map); + sym.st_value -= shdr.sh_addr - shdr.sh_offset; if (strcmp(section_name, (curr_dso->short_name + diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 2bd6a1f..aad99e7 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -344,9 +344,6 @@ int setup_intlist(struct intlist **list, const char *list_str, #ifdef HAVE_LIBELF_SUPPORT bool elf__needs_adjust_symbols(GElf_Ehdr ehdr); void arch__sym_update(struct symbol *s, GElf_Sym *sym); -void arch__adjust_sym_map_offset(GElf_Sym *sym, - GElf_Shdr *shdr __maybe_unused, - struct map *map __maybe_unused); #endif #define SYMBOL_A 0 diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 19e5db9..6eea7cf 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -15,9 +15,9 @@ #include "syscalltbl.h" #include <stdlib.h> +#include <linux/compiler.h> #ifdef HAVE_SYSCALL_TABLE -#include <linux/compiler.h> #include <string.h> #include "string2.h" #include "util.h" diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 26ce4f7..ff80564 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -52,6 +52,10 @@ override LDFLAGS = override MAKEFLAGS = endif +ifneq ($(KBUILD_SRC),) +override LDFLAGS = +endif + BUILD := $(O) ifndef BUILD BUILD := $(KBUILD_OUTPUT) @@ -62,32 +66,32 @@ endif export BUILD all: - for TARGET in $(TARGETS); do \ + @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET;\ done; run_tests: all - for TARGET in $(TARGETS); do \ + @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\ done; hotplug: - for TARGET in $(TARGETS_HOTPLUG); do \ + @for TARGET in $(TARGETS_HOTPLUG); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET;\ done; run_hotplug: hotplug - for TARGET in $(TARGETS_HOTPLUG); do \ + @for TARGET in $(TARGETS_HOTPLUG); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET run_full_test;\ done; clean_hotplug: - for TARGET in $(TARGETS_HOTPLUG); do \ + @for TARGET in $(TARGETS_HOTPLUG); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\ done; @@ -103,7 +107,7 @@ install: ifdef INSTALL_PATH @# Ask all targets to install their files mkdir -p $(INSTALL_PATH) - for TARGET in $(TARGETS); do \ + @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \ done; @@ -128,7 +132,7 @@ else endif clean: - for TARGET in $(TARGETS); do \ + @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\ done; diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index 20ecbaa..6c53a89 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -12,6 +12,7 @@ static inline unsigned int bpf_num_possible_cpus(void) unsigned int start, end, possible_cpus = 0; char buff[128]; FILE *fp; + int n; fp = fopen(fcpu, "r"); if (!fp) { @@ -20,17 +21,17 @@ static inline unsigned int bpf_num_possible_cpus(void) } while (fgets(buff, sizeof(buff), fp)) { - if (sscanf(buff, "%u-%u", &start, &end) == 2) { - possible_cpus = start == 0 ? end + 1 : 0; - break; + n = sscanf(buff, "%u-%u", &start, &end); + if (n == 0) { + printf("Failed to retrieve # possible CPUs!\n"); + exit(1); + } else if (n == 1) { + end = start; } + possible_cpus = start == 0 ? end + 1 : 0; + break; } - fclose(fp); - if (!possible_cpus) { - printf("Failed to retrieve # possible CPUs!\n"); - exit(1); - } return possible_cpus; } diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile index 6b214b7..247b0a1 100644 --- a/tools/testing/selftests/breakpoints/Makefile +++ b/tools/testing/selftests/breakpoints/Makefile @@ -2,14 +2,14 @@ uname_M := $(shell uname -m 2>/dev/null || echo not) ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) +TEST_GEN_PROGS := step_after_suspend_test + ifeq ($(ARCH),x86) -TEST_GEN_PROGS := breakpoint_test +TEST_GEN_PROGS += breakpoint_test endif ifneq (,$(filter $(ARCH),aarch64 arm64)) -TEST_GEN_PROGS := breakpoint_test_arm64 +TEST_GEN_PROGS += breakpoint_test_arm64 endif -TEST_GEN_PROGS += step_after_suspend_test - include ../lib.mk diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc index 2a1cb99..a4fd4c8 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc @@ -1,6 +1,8 @@ #!/bin/sh # description: Register/unregister many kprobe events +[ -f kprobe_events ] || exit_unsupported # this is configurable + # ftrace fentry skip size depends on the machine architecture. # Currently HAVE_KPROBES_ON_FTRACE defined on x86 and powerpc64le case `uname -m` in diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile index 7c647f6..f0c0369 100644 --- a/tools/testing/selftests/futex/Makefile +++ b/tools/testing/selftests/futex/Makefile @@ -7,14 +7,17 @@ TEST_PROGS := run.sh include ../lib.mk all: - for DIR in $(SUBDIRS); do \ + @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ + if [ -e $$DIR/$(TEST_PROGS) ]; then + rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; + fi done override define RUN_TESTS - $(OUTPUT)/run.sh + @cd $(OUTPUT); ./run.sh endef override define INSTALL_RULE @@ -33,7 +36,7 @@ override define EMIT_TESTS endef override define CLEAN - for DIR in $(SUBDIRS); do \ + @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ diff --git a/tools/testing/selftests/intel_pstate/Makefile b/tools/testing/selftests/intel_pstate/Makefile index 849a90f..a97e24e 100644 --- a/tools/testing/selftests/intel_pstate/Makefile +++ b/tools/testing/selftests/intel_pstate/Makefile @@ -1,7 +1,9 @@ CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE LDLIBS := $(LDLIBS) -lm +ifeq (,$(filter $(ARCH),x86)) TEST_GEN_FILES := msr aperf +endif TEST_PROGS := run.sh diff --git a/tools/testing/selftests/intel_pstate/run.sh b/tools/testing/selftests/intel_pstate/run.sh index 7868c10..d3ab48f 100755 --- a/tools/testing/selftests/intel_pstate/run.sh +++ b/tools/testing/selftests/intel_pstate/run.sh @@ -29,13 +29,12 @@ EVALUATE_ONLY=0 -max_cpus=$(($(nproc)-1)) +if ! uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ | grep -q x86; then + echo "$0 # Skipped: Test can only run on x86 architectures." + exit 0 +fi -# compile programs -gcc aperf.c -Wall -D_GNU_SOURCE -o aperf -lm -[ $? -ne 0 ] && echo "Problem compiling aperf.c." && exit 1 -gcc -o msr msr.c -lm -[ $? -ne 0 ] && echo "Problem compiling msr.c." && exit 1 +max_cpus=$(($(nproc)-1)) function run_test () { diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 6936166..f65886a 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -6,7 +6,14 @@ ifeq (0,$(MAKELEVEL)) OUTPUT := $(shell pwd) endif +# The following are built by lib.mk common compile rules. +# TEST_CUSTOM_PROGS should be used by tests that require +# custom build rule and prevent common build rule use. +# TEST_PROGS are for test shell scripts. +# TEST_CUSTOM_PROGS and TEST_PROGS will be run by common run_tests +# and install targets. Common clean doesn't touch them. TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) +TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) @@ -20,17 +27,28 @@ define RUN_TESTS test_num=`echo $$test_num+1 | bc`; \ echo "selftests: $$BASENAME_TEST"; \ echo "========================================"; \ - if [ ! -x $$BASENAME_TEST ]; then \ + if [ ! -x $$TEST ]; then \ echo "selftests: Warning: file $$BASENAME_TEST is not executable, correct this.";\ echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; \ else \ - cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\ + cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\ fi; \ done; endef run_tests: all - $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_PROGS)) +ifneq ($(KBUILD_SRC),) + @if [ "X$(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)" != "X" ]; then + @rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT) + fi + @if [ "X$(TEST_PROGS)" != "X" ]; then + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(OUTPUT)/$(TEST_PROGS)) + else + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS)) + fi +else + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS)) +endif define INSTALL_RULE @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ @@ -38,10 +56,10 @@ define INSTALL_RULE echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/"; \ rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/; \ fi - @if [ "X$(TEST_GEN_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \ + @if [ "X$(TEST_GEN_PROGS)$(TEST_CUSTOM_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \ mkdir -p ${INSTALL_PATH}; \ - echo "rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \ - rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \ + echo "rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \ + rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \ fi endef @@ -53,15 +71,20 @@ else endif define EMIT_TESTS - @for TEST in $(TEST_GEN_PROGS) $(TEST_PROGS); do \ + @for TEST in $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS); do \ BASENAME_TEST=`basename $$TEST`; \ - echo "(./$$BASENAME_TEST && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \ + echo "(./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \ done; endef emit_tests: $(EMIT_TESTS) +# define if isn't already. It is undefined in make O= case. +ifeq ($(RM),) +RM := rm -f +endif + define CLEAN $(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN) endef @@ -69,6 +92,15 @@ endef clean: $(CLEAN) +# When make O= with kselftest target from main level +# the following aren't defined. +# +ifneq ($(KBUILD_SRC),) +LINK.c = $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) +COMPILE.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c +LINK.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) +endif + $(OUTPUT)/%:%.c $(LINK.c) $^ $(LDLIBS) -o $@ diff --git a/tools/testing/selftests/memfd/run_tests.sh b/tools/testing/selftests/memfd/run_tests.sh index daabb35..daabb35 100644..100755 --- a/tools/testing/selftests/memfd/run_tests.sh +++ b/tools/testing/selftests/memfd/run_tests.sh diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile index 79a664a..0f5e347 100644 --- a/tools/testing/selftests/mqueue/Makefile +++ b/tools/testing/selftests/mqueue/Makefile @@ -5,8 +5,8 @@ TEST_GEN_PROGS := mq_open_tests mq_perf_tests include ../lib.mk override define RUN_TESTS - @./mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]" - @./mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]" + $(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]" + $(OUTPUT)//mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]" endef override define EMIT_TESTS diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 9801253..c612d6e 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -6,3 +6,4 @@ reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa reuseport_dualstack +reuseaddr_conflict diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index de1f577..d86bca9 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -5,9 +5,9 @@ CFLAGS += -I../../../../usr/include/ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh TEST_GEN_FILES = socket -TEST_GEN_FILES += psock_fanout psock_tpacket -TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa -TEST_GEN_FILES += reuseport_dualstack msg_zerocopy +TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy +TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa +TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict include ../lib.mk diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index 40232af..3ab6ec4 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -55,7 +55,7 @@ #include <unistd.h> #ifndef SO_EE_ORIGIN_ZEROCOPY -#define SO_EE_ORIGIN_ZEROCOPY SO_EE_ORIGIN_UPAGE +#define SO_EE_ORIGIN_ZEROCOPY 5 #endif #ifndef SO_ZEROCOPY diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh index 4e00568..90cb903 100755 --- a/tools/testing/selftests/net/netdevice.sh +++ b/tools/testing/selftests/net/netdevice.sh @@ -178,7 +178,7 @@ if [ "$(id -u)" -ne 0 ];then exit 0 fi -ip -Version 2>/dev/null >/dev/null +ip link show 2>/dev/null >/dev/null if [ $? -ne 0 ];then echo "SKIP: Could not run test without the ip tool" exit 0 diff --git a/tools/testing/selftests/net/reuseaddr_conflict.c b/tools/testing/selftests/net/reuseaddr_conflict.c new file mode 100644 index 0000000..7c5b126 --- /dev/null +++ b/tools/testing/selftests/net/reuseaddr_conflict.c @@ -0,0 +1,114 @@ +/* + * Test for the regression introduced by + * + * b9470c27607b ("inet: kill smallest_size and smallest_port") + * + * If we open an ipv4 socket on a port with reuseaddr we shouldn't reset the tb + * when we open the ipv6 conterpart, which is what was happening previously. + */ +#include <errno.h> +#include <error.h> +#include <arpa/inet.h> +#include <netinet/in.h> +#include <stdbool.h> +#include <stdio.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <unistd.h> + +#define PORT 9999 + +int open_port(int ipv6, int any) +{ + int fd = -1; + int reuseaddr = 1; + int v6only = 1; + int addrlen; + int ret = -1; + struct sockaddr *addr; + int family = ipv6 ? AF_INET6 : AF_INET; + + struct sockaddr_in6 addr6 = { + .sin6_family = AF_INET6, + .sin6_port = htons(PORT), + .sin6_addr = in6addr_any + }; + struct sockaddr_in addr4 = { + .sin_family = AF_INET, + .sin_port = htons(PORT), + .sin_addr.s_addr = any ? htonl(INADDR_ANY) : inet_addr("127.0.0.1"), + }; + + + if (ipv6) { + addr = (struct sockaddr*)&addr6; + addrlen = sizeof(addr6); + } else { + addr = (struct sockaddr*)&addr4; + addrlen = sizeof(addr4); + } + + if ((fd = socket(family, SOCK_STREAM, IPPROTO_TCP)) < 0) { + perror("socket"); + goto out; + } + + if (ipv6 && setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (void*)&v6only, + sizeof(v6only)) < 0) { + perror("setsockopt IPV6_V6ONLY"); + goto out; + } + + if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &reuseaddr, + sizeof(reuseaddr)) < 0) { + perror("setsockopt SO_REUSEADDR"); + goto out; + } + + if (bind(fd, addr, addrlen) < 0) { + perror("bind"); + goto out; + } + + if (any) + return fd; + + if (listen(fd, 1) < 0) { + perror("listen"); + goto out; + } + return fd; +out: + close(fd); + return ret; +} + +int main(void) +{ + int listenfd; + int fd1, fd2; + + fprintf(stderr, "Opening 127.0.0.1:%d\n", PORT); + listenfd = open_port(0, 0); + if (listenfd < 0) + error(1, errno, "Couldn't open listen socket"); + fprintf(stderr, "Opening INADDR_ANY:%d\n", PORT); + fd1 = open_port(0, 1); + if (fd1 >= 0) + error(1, 0, "Was allowed to create an ipv4 reuseport on a already bound non-reuseport socket"); + fprintf(stderr, "Opening in6addr_any:%d\n", PORT); + fd1 = open_port(1, 1); + if (fd1 < 0) + error(1, errno, "Couldn't open ipv6 reuseport"); + fprintf(stderr, "Opening INADDR_ANY:%d\n", PORT); + fd2 = open_port(0, 1); + if (fd2 >= 0) + error(1, 0, "Was allowed to create an ipv4 reuseport on a already bound non-reuseport socket"); + close(fd1); + fprintf(stderr, "Opening INADDR_ANY:%d after closing ipv6 socket\n", PORT); + fd1 = open_port(0, 1); + if (fd1 >= 0) + error(1, 0, "Was allowed to create an ipv4 reuseport on an already bound non-reuseport socket with no ipv6"); + fprintf(stderr, "Success"); + return 0; +} diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 67c3e27..24dbf63 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -6,10 +6,18 @@ */ #include <sys/types.h> -#include <asm/siginfo.h> -#define __have_siginfo_t 1 -#define __have_sigval_t 1 -#define __have_sigevent_t 1 + +/* + * glibc 2.26 and later have SIGSYS in siginfo_t. Before that, + * we need to use the kernel's siginfo.h file and trick glibc + * into accepting it. + */ +#if !__GLIBC_PREREQ(2, 26) +# include <asm/siginfo.h> +# define __have_siginfo_t 1 +# define __have_sigval_t 1 +# define __have_sigevent_t 1 +#endif #include <errno.h> #include <linux/filter.h> @@ -884,7 +892,7 @@ TEST_F_SIGNAL(TRAP, ign, SIGSYS) syscall(__NR_getpid); } -static struct siginfo TRAP_info; +static siginfo_t TRAP_info; static volatile int TRAP_nr; static void TRAP_action(int nr, siginfo_t *info, void *void_context) { diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c index 7d406c3..97bb150 100644 --- a/tools/testing/selftests/sigaltstack/sas.c +++ b/tools/testing/selftests/sigaltstack/sas.c @@ -39,7 +39,11 @@ void my_usr1(int sig, siginfo_t *si, void *u) stack_t stk; struct stk_data *p; +#if __s390x__ + register unsigned long sp asm("%15"); +#else register unsigned long sp asm("sp"); +#endif if (sp < (unsigned long)sstack || sp >= (unsigned long)sstack + SIGSTKSZ) { diff --git a/tools/testing/selftests/sync/Makefile b/tools/testing/selftests/sync/Makefile index 4981c6b..8e04d0a 100644 --- a/tools/testing/selftests/sync/Makefile +++ b/tools/testing/selftests/sync/Makefile @@ -2,12 +2,16 @@ CFLAGS += -O2 -g -std=gnu89 -pthread -Wall -Wextra CFLAGS += -I../../../../usr/include/ LDFLAGS += -pthread -TEST_PROGS = sync_test - -all: $(TEST_PROGS) +.PHONY: all clean include ../lib.mk +# lib.mk TEST_CUSTOM_PROGS var is for custom tests that need special +# build rules. lib.mk will run and install them. + +TEST_CUSTOM_PROGS := $(OUTPUT)/sync_test +all: $(TEST_CUSTOM_PROGS) + OBJS = sync_test.o sync.o TESTS += sync_alloc.o @@ -18,6 +22,16 @@ TESTS += sync_stress_parallelism.o TESTS += sync_stress_consumer.o TESTS += sync_stress_merge.o -sync_test: $(OBJS) $(TESTS) +OBJS := $(patsubst %,$(OUTPUT)/%,$(OBJS)) +TESTS := $(patsubst %,$(OUTPUT)/%,$(TESTS)) + +$(TEST_CUSTOM_PROGS): $(TESTS) $(OBJS) + $(CC) -o $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS) $(CFLAGS) $(LDFLAGS) + +$(OBJS): $(OUTPUT)/%.o: %.c + $(CC) -c $^ -o $@ + +$(TESTS): $(OUTPUT)/%.o: %.c + $(CC) -c $^ -o $@ -EXTRA_CLEAN := sync_test $(OBJS) $(TESTS) +EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS) diff --git a/tools/testing/selftests/timers/set-timer-lat.c b/tools/testing/selftests/timers/set-timer-lat.c index 9c92b7b..50da454 100644 --- a/tools/testing/selftests/timers/set-timer-lat.c +++ b/tools/testing/selftests/timers/set-timer-lat.c @@ -143,7 +143,8 @@ int setup_timer(int clock_id, int flags, int interval, timer_t *tm1) printf("%-22s %s missing CAP_WAKE_ALARM? : [UNSUPPORTED]\n", clockstring(clock_id), flags ? "ABSTIME":"RELTIME"); - return 0; + /* Indicate timer isn't set, so caller doesn't wait */ + return 1; } printf("%s - timer_create() failed\n", clockstring(clock_id)); return -1; @@ -213,8 +214,9 @@ int do_timer(int clock_id, int flags) int err; err = setup_timer(clock_id, flags, interval, &tm1); + /* Unsupported case - return 0 to not fail the test */ if (err) - return err; + return err == 1 ? 0 : err; while (alarmcount < 5) sleep(1); @@ -228,18 +230,17 @@ int do_timer_oneshot(int clock_id, int flags) timer_t tm1; const int interval = 0; struct timeval timeout; - fd_set fds; int err; err = setup_timer(clock_id, flags, interval, &tm1); + /* Unsupported case - return 0 to not fail the test */ if (err) - return err; + return err == 1 ? 0 : err; memset(&timeout, 0, sizeof(timeout)); timeout.tv_sec = 5; - FD_ZERO(&fds); do { - err = select(FD_SETSIZE, &fds, NULL, NULL, &timeout); + err = select(0, NULL, NULL, NULL, &timeout); } while (err == -1 && errno == EINTR); timer_delete(tm1); diff --git a/tools/testing/selftests/watchdog/Makefile b/tools/testing/selftests/watchdog/Makefile index f863c66..ee06851 100644 --- a/tools/testing/selftests/watchdog/Makefile +++ b/tools/testing/selftests/watchdog/Makefile @@ -1,8 +1,3 @@ -TEST_PROGS := watchdog-test - -all: $(TEST_PROGS) +TEST_GEN_PROGS := watchdog-test include ../lib.mk - -clean: - rm -fr $(TEST_PROGS) |
