diff options
276 files changed, 2696 insertions, 1535 deletions
@@ -137,6 +137,7 @@ Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com> Rudolf Marek <R.Marek@sh.cvut.cz> Rui Saraiva <rmps@joel.ist.utl.pt> Sachin P Sant <ssant@in.ibm.com> +Sarangdhar Joshi <spjoshi@codeaurora.org> Sam Ravnborg <sam@mars.ravnborg.org> Santosh Shilimkar <ssantosh@kernel.org> Santosh Shilimkar <santosh.shilimkar@oracle.org> @@ -150,10 +151,13 @@ Shuah Khan <shuah@kernel.org> <shuah.kh@samsung.com> Simon Kelley <simon@thekelleys.org.uk> Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr> Stephen Hemminger <shemminger@osdl.org> +Subash Abhinov Kasiviswanathan <subashab@codeaurora.org> +Subhash Jadavani <subhashj@codeaurora.org> Sudeep Holla <sudeep.holla@arm.com> Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> Sumit Semwal <sumit.semwal@ti.com> Tejun Heo <htejun@gmail.com> Thomas Graf <tgraf@suug.ch> +Thomas Pedersen <twp@codeaurora.org> Tony Luck <tony.luck@intel.com> Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com> Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de> diff --git a/Documentation/vm/page_frags b/Documentation/vm/page_frags new file mode 100644 index 000000000000..a6714565dbf9 --- /dev/null +++ b/Documentation/vm/page_frags @@ -0,0 +1,42 @@ +Page fragments +-------------- + +A page fragment is an arbitrary-length arbitrary-offset area of memory +which resides within a 0 or higher order compound page. Multiple +fragments within that page are individually refcounted, in the page's +reference counter. + +The page_frag functions, page_frag_alloc and page_frag_free, provide a +simple allocation framework for page fragments. This is used by the +network stack and network device drivers to provide a backing region of +memory for use as either an sk_buff->head, or to be used in the "frags" +portion of skb_shared_info. + +In order to make use of the page fragment APIs a backing page fragment +cache is needed. This provides a central point for the fragment allocation +and tracks allows multiple calls to make use of a cached page. The +advantage to doing this is that multiple calls to get_page can be avoided +which can be expensive at allocation time. However due to the nature of +this caching it is required that any calls to the cache be protected by +either a per-cpu limitation, or a per-cpu limitation and forcing interrupts +to be disabled when executing the fragment allocation. + +The network stack uses two separate caches per CPU to handle fragment +allocation. The netdev_alloc_cache is used by callers making use of the +__netdev_alloc_frag and __netdev_alloc_skb calls. The napi_alloc_cache is +used by callers of the __napi_alloc_frag and __napi_alloc_skb calls. The +main difference between these two calls is the context in which they may be +called. The "netdev" prefixed functions are usable in any context as these +functions will disable interrupts, while the "napi" prefixed functions are +only usable within the softirq context. + +Many network device drivers use a similar methodology for allocating page +fragments, but the page fragments are cached at the ring or descriptor +level. In order to enable these cases it is necessary to provide a generic +way of tearing down a page cache. For this reason __page_frag_cache_drain +was implemented. It allows for freeing multiple references from a single +page via a single call. The advantage to doing this is that it allows for +cleaning up the multiple references that were added to a page in order to +avoid calling get_page per allocation. + +Alexander Duyck, Nov 29, 2016. diff --git a/MAINTAINERS b/MAINTAINERS index 5f0420a0da5b..c36976d3bd1a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -81,7 +81,6 @@ Descriptions of section entries: Q: Patchwork web based patch tracking system site T: SCM tree type and location. Type is one of: git, hg, quilt, stgit, topgit - B: Bug tracking system location. S: Status, one of the following: Supported: Someone is actually paid to look after this. Maintained: Someone actually looks after it. @@ -2194,14 +2193,6 @@ L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Supported F: sound/soc/atmel -ATMEL DMA DRIVER -M: Nicolas Ferre <nicolas.ferre@atmel.com> -L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Supported -F: drivers/dma/at_hdmac.c -F: drivers/dma/at_hdmac_regs.h -F: include/linux/platform_data/dma-atmel.h - ATMEL XDMA DRIVER M: Ludovic Desroches <ludovic.desroches@atmel.com> L: linux-arm-kernel@lists.infradead.org @@ -4117,7 +4108,7 @@ F: drivers/gpu/drm/cirrus/ RADEON and AMDGPU DRM DRIVERS M: Alex Deucher <alexander.deucher@amd.com> M: Christian König <christian.koenig@amd.com> -L: dri-devel@lists.freedesktop.org +L: amd-gfx@lists.freedesktop.org T: git git://people.freedesktop.org/~agd5f/linux S: Supported F: drivers/gpu/drm/radeon/ @@ -8179,6 +8170,15 @@ S: Maintained F: drivers/tty/serial/atmel_serial.c F: include/linux/atmel_serial.h +MICROCHIP / ATMEL DMA DRIVER +M: Ludovic Desroches <ludovic.desroches@microchip.com> +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +L: dmaengine@vger.kernel.org +S: Supported +F: drivers/dma/at_hdmac.c +F: drivers/dma/at_hdmac_regs.h +F: include/linux/platform_data/dma-atmel.h + MICROCHIP / ATMEL ISC DRIVER M: Songjun Wu <songjun.wu@microchip.com> L: linux-media@vger.kernel.org diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 446f6c46d4b1..3a4301163e04 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -164,22 +164,25 @@ lr .req x30 // link register /* * Pseudo-ops for PC-relative adr/ldr/str <reg>, <symbol> where - * <symbol> is within the range +/- 4 GB of the PC. + * <symbol> is within the range +/- 4 GB of the PC when running + * in core kernel context. In module context, a movz/movk sequence + * is used, since modules may be loaded far away from the kernel + * when KASLR is in effect. */ /* * @dst: destination register (64 bit wide) * @sym: name of the symbol - * @tmp: optional scratch register to be used if <dst> == sp, which - * is not allowed in an adrp instruction */ - .macro adr_l, dst, sym, tmp= - .ifb \tmp + .macro adr_l, dst, sym +#ifndef MODULE adrp \dst, \sym add \dst, \dst, :lo12:\sym - .else - adrp \tmp, \sym - add \dst, \tmp, :lo12:\sym - .endif +#else + movz \dst, #:abs_g3:\sym + movk \dst, #:abs_g2_nc:\sym + movk \dst, #:abs_g1_nc:\sym + movk \dst, #:abs_g0_nc:\sym +#endif .endm /* @@ -190,6 +193,7 @@ lr .req x30 // link register * the address */ .macro ldr_l, dst, sym, tmp= +#ifndef MODULE .ifb \tmp adrp \dst, \sym ldr \dst, [\dst, :lo12:\sym] @@ -197,6 +201,15 @@ lr .req x30 // link register adrp \tmp, \sym ldr \dst, [\tmp, :lo12:\sym] .endif +#else + .ifb \tmp + adr_l \dst, \sym + ldr \dst, [\dst] + .else + adr_l \tmp, \sym + ldr \dst, [\tmp] + .endif +#endif .endm /* @@ -206,8 +219,13 @@ lr .req x30 // link register * while <src> needs to be preserved. */ .macro str_l, src, sym, tmp +#ifndef MODULE adrp \tmp, \sym str \src, [\tmp, :lo12:\sym] +#else + adr_l \tmp, \sym + str \src, [\tmp] +#endif .endm /* diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 964b7549af5c..e25584d72396 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -239,7 +239,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, ncontig = find_num_contig(vma->vm_mm, addr, cpte, *cpte, &pgsize); for (i = 0; i < ncontig; ++i, ++cpte, addr += pgsize) { - changed = ptep_set_access_flags(vma, addr, cpte, + changed |= ptep_set_access_flags(vma, addr, cpte, pfn_pte(pfn, hugeprot), dirty); diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index cc3bd583dce1..9e240fcba784 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -14,6 +14,7 @@ #include <linux/types.h> #include "ctype.h" +#include "string.h" int memcmp(const void *s1, const void *s2, size_t len) { diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h index 725e820602b1..113588ddb43f 100644 --- a/arch/x86/boot/string.h +++ b/arch/x86/boot/string.h @@ -18,4 +18,13 @@ int memcmp(const void *s1, const void *s2, size_t len); #define memset(d,c,l) __builtin_memset(d,c,l) #define memcmp __builtin_memcmp +extern int strcmp(const char *str1, const char *str2); +extern int strncmp(const char *cs, const char *ct, size_t count); +extern size_t strlen(const char *s); +extern char *strstr(const char *s1, const char *s2); +extern size_t strnlen(const char *s, size_t maxlen); +extern unsigned int atou(const char *s); +extern unsigned long long simple_strtoull(const char *cp, char **endp, + unsigned int base); + #endif /* BOOT_STRING_H */ diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 31c34ee131f3..6ef688a1ef3e 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -1020,7 +1020,8 @@ struct { const char *basename; struct simd_skcipher_alg *simd; } aesni_simd_skciphers2[] = { -#if IS_ENABLED(CONFIG_CRYPTO_PCBC) +#if (defined(MODULE) && IS_ENABLED(CONFIG_CRYPTO_PCBC)) || \ + IS_BUILTIN(CONFIG_CRYPTO_PCBC) { .algname = "pcbc(aes)", .drvname = "pcbc-aes-aesni", diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 701d29f8e4d3..57f7ec35216e 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -255,23 +255,6 @@ ENTRY(__switch_to_asm) END(__switch_to_asm) /* - * The unwinder expects the last frame on the stack to always be at the same - * offset from the end of the page, which allows it to validate the stack. - * Calling schedule_tail() directly would break that convention because its an - * asmlinkage function so its argument has to be pushed on the stack. This - * wrapper creates a proper "end of stack" frame header before the call. - */ -ENTRY(schedule_tail_wrapper) - FRAME_BEGIN - - pushl %eax - call schedule_tail - popl %eax - - FRAME_END - ret -ENDPROC(schedule_tail_wrapper) -/* * A newly forked process directly context switches into this address. * * eax: prev task we switched from @@ -279,15 +262,24 @@ ENDPROC(schedule_tail_wrapper) * edi: kernel thread arg */ ENTRY(ret_from_fork) - call schedule_tail_wrapper + FRAME_BEGIN /* help unwinder find end of stack */ + + /* + * schedule_tail() is asmlinkage so we have to put its 'prev' argument + * on the stack. + */ + pushl %eax + call schedule_tail + popl %eax testl %ebx, %ebx jnz 1f /* kernel threads are uncommon */ 2: /* When we fork, we trace the syscall return in the child, too. */ - movl %esp, %eax + leal FRAME_OFFSET(%esp), %eax call syscall_return_slowpath + FRAME_END jmp restore_all /* kernel thread */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 5b219707c2f2..044d18ebc43c 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -36,6 +36,7 @@ #include <asm/smap.h> #include <asm/pgtable_types.h> #include <asm/export.h> +#include <asm/frame.h> #include <linux/err.h> .code64 @@ -408,17 +409,19 @@ END(__switch_to_asm) * r12: kernel thread arg */ ENTRY(ret_from_fork) + FRAME_BEGIN /* help unwinder find end of stack */ movq %rax, %rdi - call schedule_tail /* rdi: 'prev' task parameter */ + call schedule_tail /* rdi: 'prev' task parameter */ - testq %rbx, %rbx /* from kernel_thread? */ - jnz 1f /* kernel threads are uncommon */ + testq %rbx, %rbx /* from kernel_thread? */ + jnz 1f /* kernel threads are uncommon */ 2: - movq %rsp, %rdi + leaq FRAME_OFFSET(%rsp),%rdi /* pt_regs pointer */ call syscall_return_slowpath /* returns with IRQs disabled */ TRACE_IRQS_ON /* user mode is traced as IRQS on */ SWAPGS + FRAME_END jmp restore_regs_and_iret 1: diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 019c5887b698..1635c0c8df23 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -505,6 +505,10 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.precise_ip > precise) return -EOPNOTSUPP; + + /* There's no sense in having PEBS for non sampling events: */ + if (!is_sampling_event(event)) + return -EINVAL; } /* * check that PEBS LBR correction does not conflict with diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 86138267b68a..d611cab214a6 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3987,7 +3987,7 @@ __init int intel_pmu_init(void) x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC); x86_pmu.num_counters = INTEL_PMC_MAX_GENERIC; } - x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1; + x86_pmu.intel_ctrl = (1ULL << x86_pmu.num_counters) - 1; if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED) { WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!", diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index fec8a461bdef..1076c9a77292 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -434,6 +434,7 @@ static struct pmu cstate_core_pmu = { .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT, + .module = THIS_MODULE, }; static struct pmu cstate_pkg_pmu = { @@ -447,6 +448,7 @@ static struct pmu cstate_pkg_pmu = { .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT, + .module = THIS_MODULE, }; static const struct cstate_model nhm_cstates __initconst = { diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index be202390bbd3..9dfeeeca0ea8 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1389,9 +1389,13 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) continue; /* log dropped samples number */ - if (error[bit]) + if (error[bit]) { perf_log_lost_samples(event, error[bit]); + if (perf_event_account_interrupt(event)) + x86_pmu_stop(event, 0); + } + if (counts[bit]) { __intel_pmu_pebs_event(event, iregs, base, top, bit, counts[bit]); diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index bd34124449b0..17c3564d087a 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -697,6 +697,7 @@ static int __init init_rapl_pmus(void) rapl_pmus->pmu.start = rapl_pmu_event_start; rapl_pmus->pmu.stop = rapl_pmu_event_stop; rapl_pmus->pmu.read = rapl_pmu_event_read; + rapl_pmus->pmu.module = THIS_MODULE; return 0; } diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 97c246f84dea..8c4ccdc3a3f3 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -733,6 +733,7 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu) .start = uncore_pmu_event_start, .stop = uncore_pmu_event_stop, .read = uncore_pmu_event_read, + .module = THIS_MODULE, }; } else { pmu->pmu = *pmu->type->pmu; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index e6832be714bc..dae2fedc1601 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -2686,7 +2686,7 @@ static struct intel_uncore_type *hswep_msr_uncores[] = { void hswep_uncore_cpu_init(void) { - int pkg = topology_phys_to_logical_pkg(0); + int pkg = boot_cpu_data.logical_proc_id; if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 34a46dc076d3..8167fdb67ae8 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -57,7 +57,7 @@ #define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */ #define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */ #define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */ -#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Annidale */ +#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Anniedale */ #define INTEL_FAM6_ATOM_GOLDMONT 0x5C #define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */ diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h index 195becc6f780..e793fc9a9b20 100644 --- a/arch/x86/include/asm/microcode_intel.h +++ b/arch/x86/include/asm/microcode_intel.h @@ -52,6 +52,21 @@ struct extended_sigtable { #define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE) +static inline u32 intel_get_microcode_revision(void) +{ + u32 rev, dummy; + + native_wrmsrl(MSR_IA32_UCODE_REV, 0); + + /* As documented in the SDM: Do a CPUID 1 here */ + native_cpuid_eax(1); + + /* get the current revision from MSR 0x8B */ + native_rdmsr(MSR_IA32_UCODE_REV, dummy, rev); + + return rev; +} + #ifdef CONFIG_MICROCODE_INTEL extern void __init load_ucode_intel_bsp(void); extern void load_ucode_intel_ap(void); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index eaf100508c36..1be64da0384e 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -219,6 +219,24 @@ static inline void native_cpuid(unsigned int *eax, unsigned int *ebx, : "memory"); } +#define native_cpuid_reg(reg) \ +static inline unsigned int native_cpuid_##reg(unsigned int op) \ +{ \ + unsigned int eax = op, ebx, ecx = 0, edx; \ + \ + native_cpuid(&eax, &ebx, &ecx, &edx); \ + \ + return reg; \ +} + +/* + * Native CPUID functions returning a single datum. + */ +native_cpuid_reg(eax) +native_cpuid_reg(ebx) +native_cpuid_reg(ecx) +native_cpuid_reg(edx) + static inline void load_cr3(pgd_t *pgdir) { write_cr3(__pa(pgdir)); diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index a3269c897ec5..2e41c50ddf47 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -58,7 +58,7 @@ get_frame_pointer(struct task_struct *task, struct pt_regs *regs) if (task == current) return __builtin_frame_address(0); - return (unsigned long *)((struct inactive_task_frame *)task->thread.sp)->bp; + return &((struct inactive_task_frame *)task->thread.sp)->bp; } #else static inline unsigned long * diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 5cb436acd463..fcc5cd387fd1 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -36,7 +36,10 @@ static inline void prepare_switch_to(struct task_struct *prev, asmlinkage void ret_from_fork(void); -/* data that is pointed to by thread.sp */ +/* + * This is the structure pointed to by thread.sp for an inactive task. The + * order of the fields must match the code in __switch_to_asm(). + */ struct inactive_task_frame { #ifdef CONFIG_X86_64 unsigned long r15; @@ -48,6 +51,11 @@ struct inactive_task_frame { unsigned long di; #endif unsigned long bx; + + /* + * These two fields must be together. They form a stack frame header, + * needed by get_frame_pointer(). + */ unsigned long bp; unsigned long ret_addr; }; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 71cae73a5076..1d3167269a67 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -309,15 +309,8 @@ static void amd_get_topology(struct cpuinfo_x86 *c) /* get information required for multi-node processors */ if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { - u32 eax, ebx, ecx, edx; - cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - node_id = ecx & 7; - - /* get compute unit information */ - smp_num_siblings = ((ebx >> 8) & 3) + 1; - c->x86_max_cores /= smp_num_siblings; - c->cpu_core_id = ebx & 0xff; + node_id = cpuid_ecx(0x8000001e) & 7; /* * We may have multiple LLCs if L3 caches exist, so check if we diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index dc1697ca5191..9bab7a8a4293 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1221,7 +1221,7 @@ static __init int setup_disablecpuid(char *arg) { int bit; - if (get_option(&arg, &bit) && bit < NCAPINTS*32) + if (get_option(&arg, &bit) && bit >= 0 && bit < NCAPINTS * 32) setup_clear_cpu_cap(bit); else return 0; diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index fcd484d2bb03..203f860d2ab3 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -14,6 +14,7 @@ #include <asm/bugs.h> #include <asm/cpu.h> #include <asm/intel-family.h> +#include <asm/microcode_intel.h> #ifdef CONFIG_X86_64 #include <linux/topology.h> @@ -78,14 +79,8 @@ static void early_init_intel(struct cpuinfo_x86 *c) (c->x86 == 0x6 && c->x86_model >= 0x0e)) set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); - if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) { - unsigned lower_word; - - wrmsr(MSR_IA32_UCODE_REV, 0, 0); - /* Required by the SDM */ - sync_core(); - rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode); - } + if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) + c->microcode = intel_get_microcode_revision(); /* * Atom erratum AAE44/AAF40/AAG38/AAH41: diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index b624b54912e1..3f329b74e040 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -150,7 +150,7 @@ static struct ucode_patch *__alloc_microcode_buf(void *data, unsigned int size) { struct ucode_patch *p; - p = kzalloc(size, GFP_KERNEL); + p = kzalloc(sizeof(struct ucode_patch), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); @@ -368,26 +368,6 @@ next: return patch; } -static void cpuid_1(void) -{ - /* - * According to the Intel SDM, Volume 3, 9.11.7: - * - * CPUID returns a value in a model specific register in - * addition to its usual register return values. The - * semantics of CPUID cause it to deposit an update ID value - * in the 64-bit model-specific register at address 08BH - * (IA32_BIOS_SIGN_ID). If no update is present in the - * processor, the value in the MSR remains unmodified. - * - * Use native_cpuid -- this code runs very early and we don't - * want to mess with paravirt. - */ - unsigned int eax = 1, ebx, ecx = 0, edx; - - native_cpuid(&eax, &ebx, &ecx, &edx); -} - static int collect_cpu_info_early(struct ucode_cpu_info *uci) { unsigned int val[2]; @@ -410,15 +390,8 @@ static int collect_cpu_info_early(struct ucode_cpu_info *uci) native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); csig.pf = 1 << ((val[1] >> 18) & 7); } - native_wrmsrl(MSR_IA32_UCODE_REV, 0); - - /* As documented in the SDM: Do a CPUID 1 here */ - cpuid_1(); - /* get the current revision from MSR 0x8B */ - native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); - - csig.rev = val[1]; + csig.rev = intel_get_microcode_revision(); uci->cpu_sig = csig; uci->valid = 1; @@ -602,7 +575,7 @@ static inline void print_ucode(struct ucode_cpu_info *uci) static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) { struct microcode_intel *mc; - unsigned int val[2]; + u32 rev; mc = uci->mc; if (!mc) @@ -610,21 +583,16 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) /* write microcode via MSR 0x79 */ native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); - native_wrmsrl(MSR_IA32_UCODE_REV, 0); - /* As documented in the SDM: Do a CPUID 1 here */ - cpuid_1(); - - /* get the current revision from MSR 0x8B */ - native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); - if (val[1] != mc->hdr.rev) + rev = intel_get_microcode_revision(); + if (rev != mc->hdr.rev) return -1; #ifdef CONFIG_X86_64 /* Flush global tlb. This is precaution. */ flush_tlb_early(); #endif - uci->cpu_sig.rev = val[1]; + uci->cpu_sig.rev = rev; if (early) print_ucode(uci); @@ -804,8 +772,8 @@ static int apply_microcode_intel(int cpu) struct microcode_intel *mc; struct ucode_cpu_info *uci; struct cpuinfo_x86 *c; - unsigned int val[2]; static int prev_rev; + u32 rev; /* We should bind the task to the CPU */ if (WARN_ON(raw_smp_processor_id() != cpu)) @@ -822,33 +790,28 @@ static int apply_microcode_intel(int cpu) /* write microcode via MSR 0x79 */ wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); - wrmsrl(MSR_IA32_UCODE_REV, 0); - - /* As documented in the SDM: Do a CPUID 1 here */ - cpuid_1(); - /* get the current revision from MSR 0x8B */ - rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); + rev = intel_get_microcode_revision(); - if (val[1] != mc->hdr.rev) { + if (rev != mc->hdr.rev) { pr_err("CPU%d update to revision 0x%x failed\n", cpu, mc->hdr.rev); return -1; } - if (val[1] != prev_rev) { + if (rev != prev_rev) { pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n", - val[1], + rev, mc->hdr.date & 0xffff, mc->hdr.date >> 24, (mc->hdr.date >> 16) & 0xff); - prev_rev = val[1]; + prev_rev = rev; } c = &cpu_data(cpu); - uci->cpu_sig.rev = val[1]; - c->microcode = val[1]; + uci->cpu_sig.rev = rev; + c->microcode = rev; return 0; } @@ -860,7 +823,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, u8 *ucode_ptr = data, *new_mc = NULL, *mc = NULL; int new_rev = uci->cpu_sig.rev; unsigned int leftover = size; - unsigned int curr_mc_size = 0; + unsigned int curr_mc_size = 0, new_mc_size = 0; unsigned int csig, cpf; while (leftover) { @@ -901,6 +864,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, vfree(new_mc); new_rev = mc_header.rev; new_mc = mc; + new_mc_size = mc_size; mc = NULL; /* trigger new vmalloc */ } @@ -926,7 +890,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, * permanent memory. So it will be loaded early when a CPU is hot added * or resumes. */ - save_mc_for_early(new_mc, curr_mc_size); + save_mc_for_early(new_mc, new_mc_size); pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", cpu, new_rev, uci->cpu_sig.rev); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index be3a49ee0356..e41af597aed8 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -694,6 +694,7 @@ unsigned long native_calibrate_tsc(void) crystal_khz = 24000; /* 24.0 MHz */ break; case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_ATOM_DENVERTON: crystal_khz = 25000; /* 25.0 MHz */ break; case INTEL_FAM6_ATOM_GOLDMONT: diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index 4443e499f279..23d15565d02a 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -6,6 +6,21 @@ #define FRAME_HEADER_SIZE (sizeof(long) * 2) +/* + * This disables KASAN checking when reading a value from another task's stack, + * since the other task could be running on another CPU and could have poisoned + * the stack in the meantime. + */ +#define READ_ONCE_TASK_STACK(task, x) \ +({ \ + unsigned long val; \ + if (task == current) \ + val = READ_ONCE(x); \ + else \ + val = READ_ONCE_NOCHECK(x); \ + val; \ +}) + static void unwind_dump(struct unwind_state *state, unsigned long *sp) { static bool dumped_before = false; @@ -48,7 +63,8 @@ unsigned long unwind_get_return_address(struct unwind_state *state) if (state->regs && user_mode(state->regs)) return 0; - addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p, + addr = READ_ONCE_TASK_STACK(state->task, *addr_p); + addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, addr, addr_p); return __kernel_text_address(addr) ? addr : 0; @@ -162,7 +178,7 @@ bool unwind_next_frame(struct unwind_state *state) if (state->regs) next_bp = (unsigned long *)state->regs->bp; else - next_bp = (unsigned long *)*state->bp; + next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task,*state->bp); /* is the next frame pointer an encoded pointer to pt_regs? */ regs = decode_frame_pointer(next_bp); @@ -207,6 +223,16 @@ bool unwind_next_frame(struct unwind_state *state) return true; bad_address: + /* + * When unwinding a non-current task, the task might actually be + * running on another CPU, in which case it could be modifying its + * stack while we're reading it. This is generally not a problem and + * can be ignored as long as the caller understands that unwinding + * another task will not always succeed. + */ + if (state->task != current) + goto the_end; + if (state->regs) { printk_deferred_once(KERN_WARNING "WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n", diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 56628a44668b..cedbba0f3402 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -818,6 +818,20 @@ static int segmented_read_std(struct x86_emulate_ctxt *ctxt, return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception); } +static int segmented_write_std(struct x86_emulate_ctxt *ctxt, + struct segmented_address addr, + void *data, + unsigned int size) +{ + int rc; + ulong linear; + + rc = linearize(ctxt, addr, size, true, &linear); + if (rc != X86EMUL_CONTINUE) + return rc; + return ctxt->ops->write_std(ctxt, linear, data, size, &ctxt->exception); +} + /* * Prefetch the remaining bytes of the instruction without crossing page * boundary if they are not in fetch_cache yet. @@ -1571,7 +1585,6 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt, &ctxt->exception); } -/* Does not support long mode */ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, u16 selector, int seg, u8 cpl, enum x86_transfer_type transfer, @@ -1608,20 +1621,34 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, rpl = selector & 3; - /* NULL selector is not valid for TR, CS and SS (except for long mode) */ - if ((seg == VCPU_SREG_CS - || (seg == VCPU_SREG_SS - && (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl)) - || seg == VCPU_SREG_TR) - && null_selector) - goto exception; - /* TR should be in GDT only */ if (seg == VCPU_SREG_TR && (selector & (1 << 2))) goto exception; - if (null_selector) /* for NULL selector skip all following checks */ + /* NULL selector is not valid for TR, CS and (except for long mode) SS */ + if (null_selector) { + if (seg == VCPU_SREG_CS || seg == VCPU_SREG_TR) + goto exception; + + if (seg == VCPU_SREG_SS) { + if (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl) + goto exception; + + /* + * ctxt->ops->set_segment expects the CPL to be in + * SS.DPL, so fake an expand-up 32-bit data segment. + */ + seg_desc.type = 3; + seg_desc.p = 1; + seg_desc.s = 1; + seg_desc.dpl = cpl; + seg_desc.d = 1; + seg_desc.g = 1; + } + + /* Skip all following checks */ goto load; + } ret = read_segment_descriptor(ctxt, selector, &seg_desc, &desc_addr); if (ret != X86EMUL_CONTINUE) @@ -1737,6 +1764,21 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, u16 selector, int seg) { u8 cpl = ctxt->ops->cpl(ctxt); + + /* + * None of MOV, POP and LSS can load a NULL selector in CPL=3, but + * they can load it at CPL<3 (Intel's manual says only LSS can, + * but it's wrong). + * + * However, the Intel manual says that putting IST=1/DPL=3 in + * an interrupt gate will result in SS=3 (the AMD manual instead + * says it doesn't), so allow SS=3 in __load_segment_descriptor + * and only forbid it here. + */ + if (seg == VCPU_SREG_SS && selector == 3 && + ctxt->mode == X86EMUL_MODE_PROT64) + return emulate_exception(ctxt, GP_VECTOR, 0, true); + return __load_segment_descriptor(ctxt, selector, seg, cpl, X86_TRANSFER_NONE, NULL); } @@ -3685,8 +3727,8 @@ static int emulate_store_desc_ptr(struct x86_emulate_ctxt *ctxt, } /* Disable writeback. */ ctxt->dst.type = OP_NONE; - return segmented_write(ctxt, ctxt->dst.addr.mem, - &desc_ptr, 2 + ctxt->op_bytes); + return segmented_write_std(ctxt, ctxt->dst.addr.mem, + &desc_ptr, 2 + ctxt->op_bytes); } static int em_sgdt(struct x86_emulate_ctxt *ctxt) @@ -3932,7 +3974,7 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt) else size = offsetof(struct fxregs_state, xmm_space[0]); - return segmented_write(ctxt, ctxt->memop.addr.mem, &fx_state, size); + return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, size); } static int fxrstor_fixup(struct x86_emulate_ctxt *ctxt, @@ -3974,7 +4016,7 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - rc = segmented_read(ctxt, ctxt->memop.addr.mem, &fx_state, 512); + rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, 512); if (rc != X86EMUL_CONTINUE) return rc; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 5fe290c1b7d8..2f6ef5121a4c 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2426,3 +2426,9 @@ void kvm_lapic_init(void) jump_label_rate_limit(&apic_hw_disabled, HZ); jump_label_rate_limit(&apic_sw_disabled, HZ); } + +void kvm_lapic_exit(void) +{ + static_key_deferred_flush(&apic_hw_disabled); + static_key_deferred_flush(&apic_sw_disabled); +} diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index e0c80233b3e1..ff8039d61672 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -110,6 +110,7 @@ static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu) int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data); void kvm_lapic_init(void); +void kvm_lapic_exit(void); #define VEC_POS(v) ((v) & (32 - 1)) #define REG_POS(v) (((v) >> 5) << 4) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2f22810a7e0c..57d8a856cdc5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3342,6 +3342,8 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, switch (cap->cap) { case KVM_CAP_HYPERV_SYNIC: + if (!irqchip_in_kernel(vcpu->kvm)) + return -EINVAL; return kvm_hv_activate_synic(vcpu); default: return -EINVAL; @@ -6045,6 +6047,7 @@ out: void kvm_arch_exit(void) { + kvm_lapic_exit(); perf_unregister_guest_info_callbacks(&kvm_guest_cbs); if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index 324e5713d386..af59f808742f 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -293,7 +293,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs) * We were not able to extract an address from the instruction, * probably because there was something invalid in it. */ - if (info->si_addr == (void *)-1) { + if (info->si_addr == (void __user *)-1) { err = -EINVAL; goto err_out; } diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index e76d1af60f7a..bb660e53cbd6 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1172,6 +1172,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) set_memory_ro((unsigned long)header, header->pages); prog->bpf_func = (void *)image; prog->jited = 1; + } else { + prog = orig_prog; } out_addrs: diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 936a488d6cf6..274dfc481849 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -210,6 +210,70 @@ int __init efi_memblock_x86_reserve_range(void) return 0; } +#define OVERFLOW_ADDR_SHIFT (64 - EFI_PAGE_SHIFT) +#define OVERFLOW_ADDR_MASK (U64_MAX << OVERFLOW_ADDR_SHIFT) +#define U64_HIGH_BIT (~(U64_MAX >> 1)) + +static bool __init efi_memmap_entry_valid(const efi_memory_desc_t *md, int i) +{ + u64 end = (md->num_pages << EFI_PAGE_SHIFT) + md->phys_addr - 1; + u64 end_hi = 0; + char buf[64]; + + if (md->num_pages == 0) { + end = 0; + } else if (md->num_pages > EFI_PAGES_MAX || + EFI_PAGES_MAX - md->num_pages < + (md->phys_addr >> EFI_PAGE_SHIFT)) { + end_hi = (md->num_pages & OVERFLOW_ADDR_MASK) + >> OVERFLOW_ADDR_SHIFT; + + if ((md->phys_addr & U64_HIGH_BIT) && !(end & U64_HIGH_BIT)) + end_hi += 1; + } else { + return true; + } + + pr_warn_once(FW_BUG "Invalid EFI memory map entries:\n"); + + if (end_hi) { + pr_warn("mem%02u: %s range=[0x%016llx-0x%llx%016llx] (invalid)\n", + i, efi_md_typeattr_format(buf, sizeof(buf), md), + md->phys_addr, end_hi, end); + } else { + pr_warn("mem%02u: %s range=[0x%016llx-0x%016llx] (invalid)\n", + i, efi_md_typeattr_format(buf, sizeof(buf), md), + md->phys_addr, end); + } + return false; +} + +static void __init efi_clean_memmap(void) +{ + efi_memory_desc_t *out = efi.memmap.map; + const efi_memory_desc_t *in = out; + const efi_memory_desc_t *end = efi.memmap.map_end; + int i, n_removal; + + for (i = n_removal = 0; in < end; i++) { + if (efi_memmap_entry_valid(in, i)) { + if (out != in) + memcpy(out, in, efi.memmap.desc_size); + out = (void *)out + efi.memmap.desc_size; + } else { + n_removal++; + } + in = (void *)in + efi.memmap.desc_size; + } + + if (n_removal > 0) { + u64 size = efi.memmap.nr_map - n_removal; + + pr_warn("Removing %d invalid memory map entries.\n", n_removal); + efi_memmap_install(efi.memmap.phys_map, size); + } +} + void __init efi_print_memmap(void) { efi_memory_desc_t *md; @@ -472,6 +536,8 @@ void __init efi_init(void) } } + efi_clean_memmap(); + if (efi_enabled(EFI_DBG)) efi_print_memmap(); } diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 10aca63a50d7..30031d5293c4 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -214,7 +214,7 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) new_size = efi.memmap.desc_size * num_entries; - new_phys = memblock_alloc(new_size, 0); + new_phys = efi_memmap_alloc(num_entries); if (!new_phys) { pr_err("Could not allocate boot services memmap\n"); return; @@ -355,7 +355,7 @@ void __init efi_free_boot_services(void) } new_size = efi.memmap.desc_size * num_entries; - new_phys = memblock_alloc(new_size, 0); + new_phys = efi_memmap_alloc(num_entries); if (!new_phys) { pr_err("Failed to allocate new EFI memmap\n"); return; diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile index 61b5ed2b7d40..90e4f2a6625b 100644 --- a/arch/x86/platform/intel-mid/device_libs/Makefile +++ b/arch/x86/platform/intel-mid/device_libs/Makefile @@ -15,7 +15,7 @@ obj-$(subst m,y,$(CONFIG_INTEL_MID_POWER_BUTTON)) += platform_msic_power_btn.o obj-$(subst m,y,$(CONFIG_GPIO_INTEL_PMIC)) += platform_pmic_gpio.o obj-$(subst m,y,$(CONFIG_INTEL_MFLD_THERMAL)) += platform_msic_thermal.o # SPI Devices -obj-$(subst m,y,$(CONFIG_SPI_SPIDEV)) += platform_spidev.o +obj-$(subst m,y,$(CONFIG_SPI_SPIDEV)) += platform_mrfld_spidev.o # I2C Devices obj-$(subst m,y,$(CONFIG_SENSORS_EMC1403)) += platform_emc1403.o obj-$(subst m,y,$(CONFIG_SENSORS_LIS3LV02D)) += platform_lis331.o diff --git a/arch/x86/platform/intel-mid/device_libs/platform_spidev.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_spidev.c index 30c601b399ee..27186ad654c9 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_spidev.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_spidev.c @@ -11,6 +11,7 @@ * of the License. */ +#include <linux/err.h> #include <linux/init.h> #include <linux/sfi.h> #include <linux/spi/pxa2xx_spi.h> @@ -34,6 +35,9 @@ static void __init *spidev_platform_data(void *info) { struct spi_board_info *spi_info = info; + if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER) + return ERR_PTR(-ENODEV); + spi_info->mode = SPI_MODE_0; spi_info->controller_data = &spidev_spi_chip; diff --git a/block/blk-lib.c b/block/blk-lib.c index ed89c8f4b2a0..f8c82a9b4012 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -301,13 +301,6 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, if ((sector | nr_sects) & bs_mask) return -EINVAL; - if (discard) { - ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, - BLKDEV_DISCARD_ZERO, biop); - if (ret == 0 || (ret && ret != -EOPNOTSUPP)) - goto out; - } - ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask, biop); if (ret == 0 || (ret && ret != -EOPNOTSUPP)) @@ -370,6 +363,12 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, struct bio *bio = NULL; struct blk_plug plug; + if (discard) { + if (!blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, + BLKDEV_DISCARD_ZERO)) + return 0; + } + blk_start_plug(&plug); ret = __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask, &bio, discard); diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 472211fa183a..3bd15d8095b1 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -16,7 +16,7 @@ static inline sector_t blk_zone_start(struct request_queue *q, sector_t sector) { - sector_t zone_mask = blk_queue_zone_size(q) - 1; + sector_t zone_mask = blk_queue_zone_sectors(q) - 1; return sector & ~zone_mask; } @@ -222,7 +222,7 @@ int blkdev_reset_zones(struct block_device *bdev, return -EINVAL; /* Check alignment (handle eventual smaller last zone) */ - zone_sectors = blk_queue_zone_size(q); + zone_sectors = blk_queue_zone_sectors(q); if (sector & (zone_sectors - 1)) return -EINVAL; diff --git a/block/partition-generic.c b/block/partition-generic.c index d7beb6bbbf66..7afb9907821f 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -434,7 +434,7 @@ static bool part_zone_aligned(struct gendisk *disk, struct block_device *bdev, sector_t from, sector_t size) { - unsigned int zone_size = bdev_zone_size(bdev); + unsigned int zone_sectors = bdev_zone_sectors(bdev); /* * If this function is called, then the disk is a zoned block device @@ -446,7 +446,7 @@ static bool part_zone_aligned(struct gendisk *disk, * regular block devices (no zone operation) and their zone size will * be reported as 0. Allow this case. */ - if (!zone_size) + if (!zone_sectors) return true; /* @@ -455,24 +455,24 @@ static bool part_zone_aligned(struct gendisk *disk, * use it. Check the zone size too: it should be a power of 2 number * of sectors. */ - if (WARN_ON_ONCE(!is_power_of_2(zone_size))) { + if (WARN_ON_ONCE(!is_power_of_2(zone_sectors))) { u32 rem; - div_u64_rem(from, zone_size, &rem); + div_u64_rem(from, zone_sectors, &rem); if (rem) return false; if ((from + size) < get_capacity(disk)) { - div_u64_rem(size, zone_size, &rem); + div_u64_rem(size, zone_sectors, &rem); if (rem) return false; } } else { - if (from & (zone_size - 1)) + if (from & (zone_sectors - 1)) return false; if ((from + size) < get_capacity(disk) && - (size & (zone_size - 1))) + (size & (zone_sectors - 1))) return false; } diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 38c576f76d36..50a2020b5b72 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1042,6 +1042,7 @@ static int __init nbd_init(void) return -ENOMEM; for (i = 0; i < nbds_max; i++) { + struct request_queue *q; struct gendisk *disk = alloc_disk(1 << part_shift); if (!disk) goto out; @@ -1067,12 +1068,13 @@ static int __init nbd_init(void) * every gendisk to have its very own request_queue struct. * These structs are big so we dynamically allocate them. */ - disk->queue = blk_mq_init_queue(&nbd_dev[i].tag_set); - if (!disk->queue) { + q = blk_mq_init_queue(&nbd_dev[i].tag_set); + if (IS_ERR(q)) { blk_mq_free_tag_set(&nbd_dev[i].tag_set); put_disk(disk); goto out; } + disk->queue = q; /* * Tell the block layer that we are not a rotational device diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 5545a679abd8..10332c24f961 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -56,6 +56,7 @@ struct virtblk_req { struct virtio_blk_outhdr out_hdr; struct virtio_scsi_inhdr in_hdr; u8 status; + u8 sense[SCSI_SENSE_BUFFERSIZE]; struct scatterlist sg[]; }; @@ -102,7 +103,8 @@ static int __virtblk_add_req(struct virtqueue *vq, } if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) { - sg_init_one(&sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE); + memcpy(vbr->sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE); + sg_init_one(&sense, vbr->sense, SCSI_SENSE_BUFFERSIZE); sgs[num_out + num_in++] = &sense; sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr)); sgs[num_out + num_in++] = &inhdr; @@ -628,11 +630,12 @@ static int virtblk_probe(struct virtio_device *vdev) if (err) goto out_put_disk; - q = vblk->disk->queue = blk_mq_init_queue(&vblk->tag_set); + q = blk_mq_init_queue(&vblk->tag_set); if (IS_ERR(q)) { err = -ENOMEM; goto out_free_tags; } + vblk->disk->queue = q; q->queuedata = vblk; diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 15f58ab44d0b..e5ab7d9e8c45 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -25,6 +25,7 @@ #include <linux/genhd.h> #include <linux/highmem.h> #include <linux/slab.h> +#include <linux/backing-dev.h> #include <linux/string.h> #include <linux/vmalloc.h> #include <linux/err.h> @@ -112,6 +113,14 @@ static inline bool is_partial_io(struct bio_vec *bvec) return bvec->bv_len != PAGE_SIZE; } +static void zram_revalidate_disk(struct zram *zram) +{ + revalidate_disk(zram->disk); + /* revalidate_disk reset the BDI_CAP_STABLE_WRITES so set again */ + zram->disk->queue->backing_dev_info.capabilities |= + BDI_CAP_STABLE_WRITES; +} + /* * Check if request is within bounds and aligned on zram logical blocks. */ @@ -1095,15 +1104,9 @@ static ssize_t disksize_store(struct device *dev, zram->comp = comp; zram->disksize = disksize; set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT); + zram_revalidate_disk(zram); up_write(&zram->init_lock); - /* - * Revalidate disk out of the init_lock to avoid lockdep splat. - * It's okay because disk's capacity is protected by init_lock - * so that revalidate_disk always sees up-to-date capacity. - */ - revalidate_disk(zram->disk); - return len; out_destroy_comp: @@ -1149,7 +1152,7 @@ static ssize_t reset_store(struct device *dev, /* Make sure all the pending I/O are finished */ fsync_bdev(bdev); zram_reset_device(zram); - revalidate_disk(zram->disk); + zram_revalidate_disk(zram); bdput(bdev); mutex_lock(&bdev->bd_mutex); diff --git a/drivers/dma/dw/Kconfig b/drivers/dma/dw/Kconfig index e00c9b022964..5a37b9fcf40d 100644 --- a/drivers/dma/dw/Kconfig +++ b/drivers/dma/dw/Kconfig @@ -24,5 +24,5 @@ config DW_DMAC_PCI select DW_DMAC_CORE help Support the Synopsys DesignWare AHB DMA controller on the - platfroms that enumerate it as a PCI device. For example, + platforms that enumerate it as a PCI device. For example, Intel Medfield has integrated this GPDMA controller. diff --git a/drivers/dma/ioat/hw.h b/drivers/dma/ioat/hw.h index 8e67895bcca3..abcc51b343ce 100644 --- a/drivers/dma/ioat/hw.h +++ b/drivers/dma/ioat/hw.h @@ -64,6 +64,8 @@ #define PCI_DEVICE_ID_INTEL_IOAT_BDX8 0x6f2e #define PCI_DEVICE_ID_INTEL_IOAT_BDX9 0x6f2f +#define PCI_DEVICE_ID_INTEL_IOAT_SKX 0x2021 + #define IOAT_VER_1_2 0x12 /* Version 1.2 */ #define IOAT_VER_2_0 0x20 /* Version 2.0 */ #define IOAT_VER_3_0 0x30 /* Version 3.0 */ diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c index 90eddd9f07e4..cc5259b881d4 100644 --- a/drivers/dma/ioat/init.c +++ b/drivers/dma/ioat/init.c @@ -106,6 +106,8 @@ static struct pci_device_id ioat_pci_tbl[] = { { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX8) }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX9) }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SKX) }, + /* I/OAT v3.3 platforms */ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD0) }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD1) }, @@ -243,10 +245,15 @@ static bool is_bdx_ioat(struct pci_dev *pdev) } } +static inline bool is_skx_ioat(struct pci_dev *pdev) +{ + return (pdev->device == PCI_DEVICE_ID_INTEL_IOAT_SKX) ? true : false; +} + static bool is_xeon_cb32(struct pci_dev *pdev) { return is_jf_ioat(pdev) || is_snb_ioat(pdev) || is_ivb_ioat(pdev) || - is_hsw_ioat(pdev) || is_bdx_ioat(pdev); + is_hsw_ioat(pdev) || is_bdx_ioat(pdev) || is_skx_ioat(pdev); } bool is_bwd_ioat(struct pci_dev *pdev) @@ -693,7 +700,7 @@ static int ioat_alloc_chan_resources(struct dma_chan *c) /* doing 2 32bit writes to mmio since 1 64b write doesn't work */ ioat_chan->completion = dma_pool_zalloc(ioat_chan->ioat_dma->completion_pool, - GFP_KERNEL, &ioat_chan->completion_dma); + GFP_NOWAIT, &ioat_chan->completion_dma); if (!ioat_chan->completion) return -ENOMEM; @@ -703,7 +710,7 @@ static int ioat_alloc_chan_resources(struct dma_chan *c) ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH); order = IOAT_MAX_ORDER; - ring = ioat_alloc_ring(c, order, GFP_KERNEL); + ring = ioat_alloc_ring(c, order, GFP_NOWAIT); if (!ring) return -ENOMEM; @@ -1357,6 +1364,8 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) device->version = readb(device->reg_base + IOAT_VER_OFFSET); if (device->version >= IOAT_VER_3_0) { + if (is_skx_ioat(pdev)) + device->version = IOAT_VER_3_2; err = ioat3_dma_probe(device, ioat_dca_enabled); if (device->version >= IOAT_VER_3_3) diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c index ac68666cd3f4..daf479cce691 100644 --- a/drivers/dma/omap-dma.c +++ b/drivers/dma/omap-dma.c @@ -938,21 +938,14 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg( d->ccr |= CCR_DST_AMODE_POSTINC; if (port_window) { d->ccr |= CCR_SRC_AMODE_DBLIDX; - d->ei = 1; - /* - * One frame covers the port_window and by configure - * the source frame index to be -1 * (port_window - 1) - * we instruct the sDMA that after a frame is processed - * it should move back to the start of the window. - */ - d->fi = -(port_window_bytes - 1); if (port_window_bytes >= 64) - d->csdp = CSDP_SRC_BURST_64 | CSDP_SRC_PACKED; + d->csdp |= CSDP_SRC_BURST_64; else if (port_window_bytes >= 32) - d->csdp = CSDP_SRC_BURST_32 | CSDP_SRC_PACKED; + d->csdp |= CSDP_SRC_BURST_32; else if (port_window_bytes >= 16) - d->csdp = CSDP_SRC_BURST_16 | CSDP_SRC_PACKED; + d->csdp |= CSDP_SRC_BURST_16; + } else { d->ccr |= CCR_SRC_AMODE_CONSTANT; } @@ -962,13 +955,21 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg( d->ccr |= CCR_SRC_AMODE_POSTINC; if (port_window) { d->ccr |= CCR_DST_AMODE_DBLIDX; + d->ei = 1; + /* + * One frame covers the port_window and by configure + * the source frame index to be -1 * (port_window - 1) + * we instruct the sDMA that after a frame is processed + * it should move back to the start of the window. + */ + d->fi = -(port_window_bytes - 1); if (port_window_bytes >= 64) - d->csdp = CSDP_DST_BURST_64 | CSDP_DST_PACKED; + d->csdp |= CSDP_DST_BURST_64; else if (port_window_bytes >= 32) - d->csdp = CSDP_DST_BURST_32 | CSDP_DST_PACKED; + d->csdp |= CSDP_DST_BURST_32; else if (port_window_bytes >= 16) - d->csdp = CSDP_DST_BURST_16 | CSDP_DST_PACKED; + d->csdp |= CSDP_DST_BURST_16; } else { d->ccr |= CCR_DST_AMODE_CONSTANT; } @@ -1017,7 +1018,7 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg( osg->addr = sg_dma_address(sgent); osg->en = en; osg->fn = sg_dma_len(sgent) / frame_bytes; - if (port_window && dir == DMA_MEM_TO_DEV) { + if (port_window && dir == DMA_DEV_TO_MEM) { osg->ei = 1; /* * One frame covers the port_window and by configure @@ -1452,6 +1453,7 @@ static int omap_dma_probe(struct platform_device *pdev) struct omap_dmadev *od; struct resource *res; int rc, i, irq; + u32 lch_count; od = devm_kzalloc(&pdev->dev, sizeof(*od), GFP_KERNEL); if (!od) @@ -1494,20 +1496,31 @@ static int omap_dma_probe(struct platform_device *pdev) spin_lock_init(&od->lock); spin_lock_init(&od->irq_lock); - if (!pdev->dev.of_node) { - od->dma_requests = od->plat->dma_attr->lch_count; - if (unlikely(!od->dma_requests)) - od->dma_requests = OMAP_SDMA_REQUESTS; - } else if (of_property_read_u32(pdev->dev.of_node, "dma-requests", - &od->dma_requests)) { + /* Number of DMA requests */ + od->dma_requests = OMAP_SDMA_REQUESTS; + if (pdev->dev.of_node && of_property_read_u32(pdev->dev.of_node, + "dma-requests", + &od->dma_requests)) { dev_info(&pdev->dev, "Missing dma-requests property, using %u.\n", OMAP_SDMA_REQUESTS); - od->dma_requests = OMAP_SDMA_REQUESTS; } - od->lch_map = devm_kcalloc(&pdev->dev, od->dma_requests, - sizeof(*od->lch_map), GFP_KERNEL); + /* Number of available logical channels */ + if (!pdev->dev.of_node) { + lch_count = od->plat->dma_attr->lch_count; + if (unlikely(!lch_count)) + lch_count = OMAP_SDMA_CHANNELS; + } else if (of_property_read_u32(pdev->dev.of_node, "dma-channels", + &lch_count)) { + dev_info(&pdev->dev, + "Missing dma-channels property, using %u.\n", + OMAP_SDMA_CHANNELS); + lch_count = OMAP_SDMA_CHANNELS; + } + + od->lch_map = devm_kcalloc(&pdev->dev, lch_count, sizeof(*od->lch_map), + GFP_KERNEL); if (!od->lch_map) return -ENOMEM; diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 87fd01539fcb..740bbb942594 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -448,6 +448,9 @@ struct dma_pl330_chan { /* for cyclic capability */ bool cyclic; + + /* for runtime pm tracking */ + bool active; }; struct pl330_dmac { @@ -2033,6 +2036,7 @@ static void pl330_tasklet(unsigned long data) _stop(pch->thread); spin_unlock(&pch->thread->dmac->lock); power_down = true; + pch->active = false; } else { /* Make sure the PL330 Channel thread is active */ spin_lock(&pch->thread->dmac->lock); @@ -2052,6 +2056,7 @@ static void pl330_tasklet(unsigned long data) desc->status = PREP; list_move_tail(&desc->node, &pch->work_list); if (power_down) { + pch->active = true; spin_lock(&pch->thread->dmac->lock); _start(pch->thread); spin_unlock(&pch->thread->dmac->lock); @@ -2166,6 +2171,7 @@ static int pl330_terminate_all(struct dma_chan *chan) unsigned long flags; struct pl330_dmac *pl330 = pch->dmac; LIST_HEAD(list); + bool power_down = false; pm_runtime_get_sync(pl330->ddma.dev); spin_lock_irqsave(&pch->lock, flags); @@ -2176,6 +2182,8 @@ static int pl330_terminate_all(struct dma_chan *chan) pch->thread->req[0].desc = NULL; pch->thread->req[1].desc = NULL; pch->thread->req_running = -1; + power_down = pch->active; + pch->active = false; /* Mark all desc done */ list_for_each_entry(desc, &pch->submitted_list, node) { @@ -2193,6 +2201,8 @@ static int pl330_terminate_all(struct dma_chan *chan) list_splice_tail_init(&pch->completed_list, &pl330->desc_pool); spin_unlock_irqrestore(&pch->lock, flags); pm_runtime_mark_last_busy(pl330->ddma.dev); + if (power_down) + pm_runtime_put_autosuspend(pl330->ddma.dev); pm_runtime_put_autosuspend(pl330->ddma.dev); return 0; @@ -2357,6 +2367,7 @@ static void pl330_issue_pending(struct dma_chan *chan) * updated on work_list emptiness status. */ WARN_ON(list_empty(&pch->submitted_list)); + pch->active = true; pm_runtime_get_sync(pch->dmac->ddma.dev); } list_splice_tail_init(&pch->submitted_list, &pch->work_list); diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c index 2e441d0ccd79..4c357d475465 100644 --- a/drivers/dma/sh/rcar-dmac.c +++ b/drivers/dma/sh/rcar-dmac.c @@ -986,6 +986,7 @@ static void rcar_dmac_free_chan_resources(struct dma_chan *chan) { struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan); struct rcar_dmac *dmac = to_rcar_dmac(chan->device); + struct rcar_dmac_chan_map *map = &rchan->map; struct rcar_dmac_desc_page *page, *_page; struct rcar_dmac_desc *desc; LIST_HEAD(list); @@ -1019,6 +1020,13 @@ static void rcar_dmac_free_chan_resources(struct dma_chan *chan) free_page((unsigned long)page); } + /* Remove slave mapping if present. */ + if (map->slave.xfer_size) { + dma_unmap_resource(chan->device->dev, map->addr, + map->slave.xfer_size, map->dir, 0); + map->slave.xfer_size = 0; + } + pm_runtime_put(chan->device->dev); } diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c index 3688d0873a3e..3056ce7f8c69 100644 --- a/drivers/dma/stm32-dma.c +++ b/drivers/dma/stm32-dma.c @@ -880,7 +880,7 @@ static enum dma_status stm32_dma_tx_status(struct dma_chan *c, struct virt_dma_desc *vdesc; enum dma_status status; unsigned long flags; - u32 residue; + u32 residue = 0; status = dma_cookie_status(c, cookie, state); if ((status == DMA_COMPLETE) || (!state)) @@ -888,16 +888,12 @@ static enum dma_status stm32_dma_tx_status(struct dma_chan *c, spin_lock_irqsave(&chan->vchan.lock, flags); vdesc = vchan_find_desc(&chan->vchan, cookie); - if (cookie == chan->desc->vdesc.tx.cookie) { + if (chan->desc && cookie == chan->desc->vdesc.tx.cookie) residue = stm32_dma_desc_residue(chan, chan->desc, chan->next_sg); - } else if (vdesc) { + else if (vdesc) residue = stm32_dma_desc_residue(chan, to_stm32_dma_desc(vdesc), 0); - } else { - residue = 0; - } - dma_set_residue(state, residue); spin_unlock_irqrestore(&chan->vchan.lock, flags); @@ -972,21 +968,18 @@ static struct dma_chan *stm32_dma_of_xlate(struct of_phandle_args *dma_spec, struct stm32_dma_chan *chan; struct dma_chan *c; - if (dma_spec->args_count < 3) + if (dma_spec->args_count < 4) return NULL; cfg.channel_id = dma_spec->args[0]; cfg.request_line = dma_spec->args[1]; cfg.stream_config = dma_spec->args[2]; - cfg.threshold = 0; + cfg.threshold = dma_spec->args[3]; if ((cfg.channel_id >= STM32_DMA_MAX_CHANNELS) || (cfg.request_line >= STM32_DMA_MAX_REQUEST_ID)) return NULL; - if (dma_spec->args_count > 3) - cfg.threshold = dma_spec->args[3]; - chan = &dmadev->chan[cfg.channel_id]; c = dma_get_slave_channel(&chan->vchan.chan); diff --git a/drivers/dma/ti-dma-crossbar.c b/drivers/dma/ti-dma-crossbar.c index 3f24aeb48c0e..2403475a37cf 100644 --- a/drivers/dma/ti-dma-crossbar.c +++ b/drivers/dma/ti-dma-crossbar.c @@ -149,6 +149,7 @@ static int ti_am335x_xbar_probe(struct platform_device *pdev) match = of_match_node(ti_am335x_master_match, dma_node); if (!match) { dev_err(&pdev->dev, "DMA master is not supported\n"); + of_node_put(dma_node); return -EINVAL; } @@ -339,6 +340,7 @@ static int ti_dra7_xbar_probe(struct platform_device *pdev) match = of_match_node(ti_dra7_master_match, dma_node); if (!match) { dev_err(&pdev->dev, "DMA master is not supported\n"); + of_node_put(dma_node); return -EINVAL; } diff --git a/drivers/firmware/efi/fake_mem.c b/drivers/firmware/efi/fake_mem.c index 520a40e5e0e4..6c7d60c239b5 100644 --- a/drivers/firmware/efi/fake_mem.c +++ b/drivers/firmware/efi/fake_mem.c @@ -71,8 +71,7 @@ void __init efi_fake_memmap(void) } /* allocate memory for new EFI memmap */ - new_memmap_phy = memblock_alloc(efi.memmap.desc_size * new_nr_map, - PAGE_SIZE); + new_memmap_phy = efi_memmap_alloc(new_nr_map); if (!new_memmap_phy) return; diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index b98824e3800a..0e2a96b12cb3 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -39,14 +39,6 @@ efi_status_t efi_file_close(void *handle); unsigned long get_dram_base(efi_system_table_t *sys_table_arg); -efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, - unsigned long orig_fdt_size, - void *fdt, int new_fdt_size, char *cmdline_ptr, - u64 initrd_addr, u64 initrd_size, - efi_memory_desc_t *memory_map, - unsigned long map_size, unsigned long desc_size, - u32 desc_ver); - efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, void *handle, unsigned long *new_fdt_addr, diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c index a6a93116a8f0..921dfa047202 100644 --- a/drivers/firmware/efi/libstub/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -16,13 +16,10 @@ #include "efistub.h" -efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, - unsigned long orig_fdt_size, - void *fdt, int new_fdt_size, char *cmdline_ptr, - u64 initrd_addr, u64 initrd_size, - efi_memory_desc_t *memory_map, - unsigned long map_size, unsigned long desc_size, - u32 desc_ver) +static efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, + unsigned long orig_fdt_size, + void *fdt, int new_fdt_size, char *cmdline_ptr, + u64 initrd_addr, u64 initrd_size) { int node, num_rsv; int status; @@ -101,25 +98,23 @@ efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, if (status) goto fdt_set_fail; - fdt_val64 = cpu_to_fdt64((u64)(unsigned long)memory_map); + fdt_val64 = U64_MAX; /* placeholder */ status = fdt_setprop(fdt, node, "linux,uefi-mmap-start", &fdt_val64, sizeof(fdt_val64)); if (status) goto fdt_set_fail; - fdt_val32 = cpu_to_fdt32(map_size); + fdt_val32 = U32_MAX; /* placeholder */ status = fdt_setprop(fdt, node, "linux,uefi-mmap-size", &fdt_val32, sizeof(fdt_val32)); if (status) goto fdt_set_fail; - fdt_val32 = cpu_to_fdt32(desc_size); status = fdt_setprop(fdt, node, "linux,uefi-mmap-desc-size", &fdt_val32, sizeof(fdt_val32)); if (status) goto fdt_set_fail; - fdt_val32 = cpu_to_fdt32(desc_ver); status = fdt_setprop(fdt, node, "linux,uefi-mmap-desc-ver", &fdt_val32, sizeof(fdt_val32)); if (status) @@ -148,6 +143,43 @@ fdt_set_fail: return EFI_LOAD_ERROR; } +static efi_status_t update_fdt_memmap(void *fdt, struct efi_boot_memmap *map) +{ + int node = fdt_path_offset(fdt, "/chosen"); + u64 fdt_val64; + u32 fdt_val32; + int err; + + if (node < 0) + return EFI_LOAD_ERROR; + + fdt_val64 = cpu_to_fdt64((unsigned long)*map->map); + err = fdt_setprop_inplace(fdt, node, "linux,uefi-mmap-start", + &fdt_val64, sizeof(fdt_val64)); + if (err) + return EFI_LOAD_ERROR; + + fdt_val32 = cpu_to_fdt32(*map->map_size); + err = fdt_setprop_inplace(fdt, node, "linux,uefi-mmap-size", + &fdt_val32, sizeof(fdt_val32)); + if (err) + return EFI_LOAD_ERROR; + + fdt_val32 = cpu_to_fdt32(*map->desc_size); + err = fdt_setprop_inplace(fdt, node, "linux,uefi-mmap-desc-size", + &fdt_val32, sizeof(fdt_val32)); + if (err) + return EFI_LOAD_ERROR; + + fdt_val32 = cpu_to_fdt32(*map->desc_ver); + err = fdt_setprop_inplace(fdt, node, "linux,uefi-mmap-desc-ver", + &fdt_val32, sizeof(fdt_val32)); + if (err) + return EFI_LOAD_ERROR; + + return EFI_SUCCESS; +} + #ifndef EFI_FDT_ALIGN #define EFI_FDT_ALIGN EFI_PAGE_SIZE #endif @@ -243,20 +275,10 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, goto fail; } - /* - * Now that we have done our final memory allocation (and free) - * we can get the memory map key needed for - * exit_boot_services(). - */ - status = efi_get_memory_map(sys_table, &map); - if (status != EFI_SUCCESS) - goto fail_free_new_fdt; - status = update_fdt(sys_table, (void *)fdt_addr, fdt_size, (void *)*new_fdt_addr, new_fdt_size, - cmdline_ptr, initrd_addr, initrd_size, - memory_map, map_size, desc_size, desc_ver); + cmdline_ptr, initrd_addr, initrd_size); /* Succeeding the first time is the expected case. */ if (status == EFI_SUCCESS) @@ -266,20 +288,16 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, /* * We need to allocate more space for the new * device tree, so free existing buffer that is - * too small. Also free memory map, as we will need - * to get new one that reflects the free/alloc we do - * on the device tree buffer. + * too small. */ efi_free(sys_table, new_fdt_size, *new_fdt_addr); - sys_table->boottime->free_pool(memory_map); new_fdt_size += EFI_PAGE_SIZE; } else { pr_efi_err(sys_table, "Unable to construct new device tree.\n"); - goto fail_free_mmap; + goto fail_free_new_fdt; } } - sys_table->boottime->free_pool(memory_map); priv.runtime_map = runtime_map; priv.runtime_entry_count = &runtime_entry_count; status = efi_exit_boot_services(sys_table, handle, &map, &priv, @@ -288,6 +306,16 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, if (status == EFI_SUCCESS) { efi_set_virtual_address_map_t *svam; + status = update_fdt_memmap((void *)*new_fdt_addr, &map); + if (status != EFI_SUCCESS) { + /* + * The kernel won't get far without the memory map, but + * may still be able to print something meaningful so + * return success here. + */ + return EFI_SUCCESS; + } + /* Install the new virtual address map */ svam = sys_table->runtime->set_virtual_address_map; status = svam(runtime_entry_count * desc_size, desc_size, @@ -319,9 +347,6 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, pr_efi_err(sys_table, "Exit boot services failed.\n"); -fail_free_mmap: - sys_table->boottime->free_pool(memory_map); - fail_free_new_fdt: efi_free(sys_table, new_fdt_size, *new_fdt_addr); diff --git a/drivers/firmware/efi/memmap.c b/drivers/firmware/efi/memmap.c index f03ddecd232b..78686443cb37 100644 --- a/drivers/firmware/efi/memmap.c +++ b/drivers/firmware/efi/memmap.c @@ -9,6 +9,44 @@ #include <linux/efi.h> #include <linux/io.h> #include <asm/early_ioremap.h> +#include <linux/memblock.h> +#include <linux/slab.h> + +static phys_addr_t __init __efi_memmap_alloc_early(unsigned long size) +{ + return memblock_alloc(size, 0); +} + +static phys_addr_t __init __efi_memmap_alloc_late(unsigned long size) +{ + unsigned int order = get_order(size); + struct page *p = alloc_pages(GFP_KERNEL, order); + + if (!p) + return 0; + + return PFN_PHYS(page_to_pfn(p)); +} + +/** + * efi_memmap_alloc - Allocate memory for the EFI memory map + * @num_entries: Number of entries in the allocated map. + * + * Depending on whether mm_init() has already been invoked or not, + * either memblock or "normal" page allocation is used. + * + * Returns the physical address of the allocated memory map on + * success, zero on failure. + */ +phys_addr_t __init efi_memmap_alloc(unsigned int num_entries) +{ + unsigned long size = num_entries * efi.memmap.desc_size; + + if (slab_is_available()) + return __efi_memmap_alloc_late(size); + + return __efi_memmap_alloc_early(size); +} /** * __efi_memmap_init - Common code for mapping the EFI memory map diff --git a/drivers/gpio/gpio-mxs.c b/drivers/gpio/gpio-mxs.c index 1e8fde8cb803..2292742eac8f 100644 --- a/drivers/gpio/gpio-mxs.c +++ b/drivers/gpio/gpio-mxs.c @@ -205,7 +205,7 @@ static int mxs_gpio_set_wake_irq(struct irq_data *d, unsigned int enable) return 0; } -static int __init mxs_gpio_init_gc(struct mxs_gpio_port *port, int irq_base) +static int mxs_gpio_init_gc(struct mxs_gpio_port *port, int irq_base) { struct irq_chip_generic *gc; struct irq_chip_type *ct; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index f4c26c7826cd..86bf3b84ada5 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1317,12 +1317,12 @@ void gpiochip_remove(struct gpio_chip *chip) /* FIXME: should the legacy sysfs handling be moved to gpio_device? */ gpiochip_sysfs_unregister(gdev); + gpiochip_free_hogs(chip); /* Numb the device, cancelling all outstanding operations */ gdev->chip = NULL; gpiochip_irqchip_remove(chip); acpi_gpiochip_remove(chip); gpiochip_remove_pin_ranges(chip); - gpiochip_free_hogs(chip); of_gpiochip_remove(chip); /* * We accept no more calls into the driver from this point, so diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c index 9ada56c16a58..4c851fde1e82 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c @@ -840,6 +840,9 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, else if (type == CGS_UCODE_ID_SMU_SK) strcpy(fw_name, "amdgpu/polaris10_smc_sk.bin"); break; + case CHIP_POLARIS12: + strcpy(fw_name, "amdgpu/polaris12_smc.bin"); + break; default: DRM_ERROR("SMC firmware not supported\n"); return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 60bd4afe45c8..fe3bb94fe58d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -73,6 +73,7 @@ static const char *amdgpu_asic_name[] = { "STONEY", "POLARIS10", "POLARIS11", + "POLARIS12", "LAST", }; @@ -1277,6 +1278,7 @@ static int amdgpu_early_init(struct amdgpu_device *adev) case CHIP_FIJI: case CHIP_POLARIS11: case CHIP_POLARIS10: + case CHIP_POLARIS12: case CHIP_CARRIZO: case CHIP_STONEY: if (adev->asic_type == CHIP_CARRIZO || adev->asic_type == CHIP_STONEY) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 8cb937b2bfcc..2534adaebe30 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -418,6 +418,13 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x67CA, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10}, {0x1002, 0x67CC, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10}, {0x1002, 0x67CF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10}, + /* Polaris12 */ + {0x1002, 0x6980, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12}, + {0x1002, 0x6981, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12}, + {0x1002, 0x6985, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12}, + {0x1002, 0x6986, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12}, + {0x1002, 0x6987, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12}, + {0x1002, 0x699F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12}, {0, 0, 0} }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c index fc592c2b0e16..95a568df8551 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c @@ -98,6 +98,7 @@ static int amdgpu_pp_early_init(void *handle) switch (adev->asic_type) { case CHIP_POLARIS11: case CHIP_POLARIS10: + case CHIP_POLARIS12: case CHIP_TONGA: case CHIP_FIJI: case CHIP_TOPAZ: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index a81dfaeeb8c0..1d564beb0fde 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -65,6 +65,7 @@ #define FIRMWARE_STONEY "amdgpu/stoney_uvd.bin" #define FIRMWARE_POLARIS10 "amdgpu/polaris10_uvd.bin" #define FIRMWARE_POLARIS11 "amdgpu/polaris11_uvd.bin" +#define FIRMWARE_POLARIS12 "amdgpu/polaris12_uvd.bin" /** * amdgpu_uvd_cs_ctx - Command submission parser context @@ -98,6 +99,7 @@ MODULE_FIRMWARE(FIRMWARE_FIJI); MODULE_FIRMWARE(FIRMWARE_STONEY); MODULE_FIRMWARE(FIRMWARE_POLARIS10); MODULE_FIRMWARE(FIRMWARE_POLARIS11); +MODULE_FIRMWARE(FIRMWARE_POLARIS12); static void amdgpu_uvd_idle_work_handler(struct work_struct *work); @@ -149,6 +151,9 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev) case CHIP_POLARIS11: fw_name = FIRMWARE_POLARIS11; break; + case CHIP_POLARIS12: + fw_name = FIRMWARE_POLARIS12; + break; default: return -EINVAL; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index 69b66b9e7f57..8fec802d3908 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -52,6 +52,7 @@ #define FIRMWARE_STONEY "amdgpu/stoney_vce.bin" #define FIRMWARE_POLARIS10 "amdgpu/polaris10_vce.bin" #define FIRMWARE_POLARIS11 "amdgpu/polaris11_vce.bin" +#define FIRMWARE_POLARIS12 "amdgpu/polaris12_vce.bin" #ifdef CONFIG_DRM_AMDGPU_CIK MODULE_FIRMWARE(FIRMWARE_BONAIRE); @@ -66,6 +67,7 @@ MODULE_FIRMWARE(FIRMWARE_FIJI); MODULE_FIRMWARE(FIRMWARE_STONEY); MODULE_FIRMWARE(FIRMWARE_POLARIS10); MODULE_FIRMWARE(FIRMWARE_POLARIS11); +MODULE_FIRMWARE(FIRMWARE_POLARIS12); static void amdgpu_vce_idle_work_handler(struct work_struct *work); @@ -121,6 +123,9 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size) case CHIP_POLARIS11: fw_name = FIRMWARE_POLARIS11; break; + case CHIP_POLARIS12: + fw_name = FIRMWARE_POLARIS12; + break; default: return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index b3d62b909f43..2006abbbfb62 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -167,6 +167,7 @@ static void dce_v11_0_init_golden_registers(struct amdgpu_device *adev) (const u32)ARRAY_SIZE(stoney_golden_settings_a11)); break; case CHIP_POLARIS11: + case CHIP_POLARIS12: amdgpu_program_register_sequence(adev, polaris11_golden_settings_a11, (const u32)ARRAY_SIZE(polaris11_golden_settings_a11)); @@ -608,6 +609,7 @@ static int dce_v11_0_get_num_crtc (struct amdgpu_device *adev) num_crtc = 6; break; case CHIP_POLARIS11: + case CHIP_POLARIS12: num_crtc = 5; break; default: @@ -1589,6 +1591,7 @@ static int dce_v11_0_audio_init(struct amdgpu_device *adev) adev->mode_info.audio.num_pins = 8; break; case CHIP_POLARIS11: + case CHIP_POLARIS12: adev->mode_info.audio.num_pins = 6; break; default: @@ -2388,7 +2391,8 @@ static u32 dce_v11_0_pick_pll(struct drm_crtc *crtc) int pll; if ((adev->asic_type == CHIP_POLARIS10) || - (adev->asic_type == CHIP_POLARIS11)) { + (adev->asic_type == CHIP_POLARIS11) || + (adev->asic_type == CHIP_POLARIS12)) { struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(amdgpu_crtc->encoder); struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv; @@ -2822,7 +2826,8 @@ static int dce_v11_0_crtc_mode_set(struct drm_crtc *crtc, return -EINVAL; if ((adev->asic_type == CHIP_POLARIS10) || - (adev->asic_type == CHIP_POLARIS11)) { + (adev->asic_type == CHIP_POLARIS11) || + (adev->asic_type == CHIP_POLARIS12)) { struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(amdgpu_crtc->encoder); int encoder_mode = @@ -2992,6 +2997,7 @@ static int dce_v11_0_early_init(void *handle) adev->mode_info.num_dig = 6; break; case CHIP_POLARIS11: + case CHIP_POLARIS12: adev->mode_info.num_hpd = 5; adev->mode_info.num_dig = 5; break; @@ -3101,7 +3107,8 @@ static int dce_v11_0_hw_init(void *handle) amdgpu_atombios_crtc_powergate_init(adev); amdgpu_atombios_encoder_init_dig(adev); if ((adev->asic_type == CHIP_POLARIS10) || - (adev->asic_type == CHIP_POLARIS11)) { + (adev->asic_type == CHIP_POLARIS11) || + (adev->asic_type == CHIP_POLARIS12)) { amdgpu_atombios_crtc_set_dce_clock(adev, adev->clock.default_dispclk, DCE_CLOCK_TYPE_DISPCLK, ATOM_GCK_DFS); amdgpu_atombios_crtc_set_dce_clock(adev, 0, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index d0ec00986f38..373374164bd5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -139,6 +139,13 @@ MODULE_FIRMWARE("amdgpu/polaris10_mec.bin"); MODULE_FIRMWARE("amdgpu/polaris10_mec2.bin"); MODULE_FIRMWARE("amdgpu/polaris10_rlc.bin"); +MODULE_FIRMWARE("amdgpu/polaris12_ce.bin"); +MODULE_FIRMWARE("amdgpu/polaris12_pfp.bin"); +MODULE_FIRMWARE("amdgpu/polaris12_me.bin"); +MODULE_FIRMWARE("amdgpu/polaris12_mec.bin"); +MODULE_FIRMWARE("amdgpu/polaris12_mec2.bin"); +MODULE_FIRMWARE("amdgpu/polaris12_rlc.bin"); + static const struct amdgpu_gds_reg_offset amdgpu_gds_reg_offset[] = { {mmGDS_VMID0_BASE, mmGDS_VMID0_SIZE, mmGDS_GWS_VMID0, mmGDS_OA_VMID0}, @@ -689,6 +696,7 @@ static void gfx_v8_0_init_golden_registers(struct amdgpu_device *adev) (const u32)ARRAY_SIZE(tonga_golden_common_all)); break; case CHIP_POLARIS11: + case CHIP_POLARIS12: amdgpu_program_register_sequence(adev, golden_settings_polaris11_a11, (const u32)ARRAY_SIZE(golden_settings_polaris11_a11)); @@ -903,6 +911,9 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev) case CHIP_POLARIS10: chip_name = "polaris10"; break; + case CHIP_POLARIS12: + chip_name = "polaris12"; + break; case CHIP_STONEY: chip_name = "stoney"; break; @@ -1768,6 +1779,7 @@ static int gfx_v8_0_gpu_early_init(struct amdgpu_device *adev) gb_addr_config = TONGA_GB_ADDR_CONFIG_GOLDEN; break; case CHIP_POLARIS11: + case CHIP_POLARIS12: ret = amdgpu_atombios_get_gfx_info(adev); if (ret) return ret; @@ -2682,6 +2694,7 @@ static void gfx_v8_0_tiling_mode_table_init(struct amdgpu_device *adev) break; case CHIP_POLARIS11: + case CHIP_POLARIS12: modearray[0] = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | PIPE_CONFIG(ADDR_SURF_P4_16x16) | TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | @@ -3503,6 +3516,7 @@ gfx_v8_0_raster_config(struct amdgpu_device *adev, u32 *rconf, u32 *rconf1) *rconf1 |= 0x0; break; case CHIP_POLARIS11: + case CHIP_POLARIS12: *rconf |= RB_MAP_PKR0(2) | RB_XSEL2(1) | SE_MAP(2) | SE_XSEL(1) | SE_YSEL(1); *rconf1 |= 0x0; @@ -4021,7 +4035,8 @@ static void gfx_v8_0_init_pg(struct amdgpu_device *adev) cz_enable_cp_power_gating(adev, true); else cz_enable_cp_power_gating(adev, false); - } else if (adev->asic_type == CHIP_POLARIS11) { + } else if ((adev->asic_type == CHIP_POLARIS11) || + (adev->asic_type == CHIP_POLARIS12)) { gfx_v8_0_init_csb(adev); gfx_v8_0_init_save_restore_list(adev); gfx_v8_0_enable_save_restore_machine(adev); @@ -4095,7 +4110,8 @@ static int gfx_v8_0_rlc_resume(struct amdgpu_device *adev) RLC_CGCG_CGLS_CTRL__CGLS_EN_MASK); WREG32(mmRLC_CGCG_CGLS_CTRL, tmp); if (adev->asic_type == CHIP_POLARIS11 || - adev->asic_type == CHIP_POLARIS10) { + adev->asic_type == CHIP_POLARIS10 || + adev->asic_type == CHIP_POLARIS12) { tmp = RREG32(mmRLC_CGCG_CGLS_CTRL_3D); tmp &= ~0x3; WREG32(mmRLC_CGCG_CGLS_CTRL_3D, tmp); @@ -4283,6 +4299,7 @@ static int gfx_v8_0_cp_gfx_start(struct amdgpu_device *adev) amdgpu_ring_write(ring, 0x0000002A); break; case CHIP_POLARIS11: + case CHIP_POLARIS12: amdgpu_ring_write(ring, 0x16000012); amdgpu_ring_write(ring, 0x00000000); break; @@ -4664,7 +4681,8 @@ static int gfx_v8_0_cp_compute_resume(struct amdgpu_device *adev) (adev->asic_type == CHIP_FIJI) || (adev->asic_type == CHIP_STONEY) || (adev->asic_type == CHIP_POLARIS11) || - (adev->asic_type == CHIP_POLARIS10)) { + (adev->asic_type == CHIP_POLARIS10) || + (adev->asic_type == CHIP_POLARIS12)) { WREG32(mmCP_MEC_DOORBELL_RANGE_LOWER, AMDGPU_DOORBELL_KIQ << 2); WREG32(mmCP_MEC_DOORBELL_RANGE_UPPER, @@ -4700,7 +4718,8 @@ static int gfx_v8_0_cp_compute_resume(struct amdgpu_device *adev) mqd->cp_hqd_persistent_state = tmp; if (adev->asic_type == CHIP_STONEY || adev->asic_type == CHIP_POLARIS11 || - adev->asic_type == CHIP_POLARIS10) { + adev->asic_type == CHIP_POLARIS10 || + adev->asic_type == CHIP_POLARIS12) { tmp = RREG32(mmCP_ME1_PIPE3_INT_CNTL); tmp = REG_SET_FIELD(tmp, CP_ME1_PIPE3_INT_CNTL, GENERIC2_INT_ENABLE, 1); WREG32(mmCP_ME1_PIPE3_INT_CNTL, tmp); @@ -5279,7 +5298,8 @@ static int gfx_v8_0_late_init(void *handle) static void gfx_v8_0_enable_gfx_static_mg_power_gating(struct amdgpu_device *adev, bool enable) { - if (adev->asic_type == CHIP_POLARIS11) + if ((adev->asic_type == CHIP_POLARIS11) || + (adev->asic_type == CHIP_POLARIS12)) /* Send msg to SMU via Powerplay */ amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_SMC, @@ -5353,6 +5373,7 @@ static int gfx_v8_0_set_powergating_state(void *handle, gfx_v8_0_enable_gfx_dynamic_mg_power_gating(adev, false); break; case CHIP_POLARIS11: + case CHIP_POLARIS12: if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_SMG) && enable) gfx_v8_0_enable_gfx_static_mg_power_gating(adev, true); else diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 0daac3a5be79..476bc9f1954b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -46,6 +46,7 @@ static int gmc_v8_0_wait_for_idle(void *handle); MODULE_FIRMWARE("amdgpu/tonga_mc.bin"); MODULE_FIRMWARE("amdgpu/polaris11_mc.bin"); MODULE_FIRMWARE("amdgpu/polaris10_mc.bin"); +MODULE_FIRMWARE("amdgpu/polaris12_mc.bin"); static const u32 golden_settings_tonga_a11[] = { @@ -130,6 +131,7 @@ static void gmc_v8_0_init_golden_registers(struct amdgpu_device *adev) (const u32)ARRAY_SIZE(golden_settings_tonga_a11)); break; case CHIP_POLARIS11: + case CHIP_POLARIS12: amdgpu_program_register_sequence(adev, golden_settings_polaris11_a11, (const u32)ARRAY_SIZE(golden_settings_polaris11_a11)); @@ -225,6 +227,9 @@ static int gmc_v8_0_init_microcode(struct amdgpu_device *adev) case CHIP_POLARIS10: chip_name = "polaris10"; break; + case CHIP_POLARIS12: + chip_name = "polaris12"; + break; case CHIP_FIJI: case CHIP_CARRIZO: case CHIP_STONEY: diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index 1170a64a3184..034ace79ed49 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -60,6 +60,8 @@ MODULE_FIRMWARE("amdgpu/polaris10_sdma.bin"); MODULE_FIRMWARE("amdgpu/polaris10_sdma1.bin"); MODULE_FIRMWARE("amdgpu/polaris11_sdma.bin"); MODULE_FIRMWARE("amdgpu/polaris11_sdma1.bin"); +MODULE_FIRMWARE("amdgpu/polaris12_sdma.bin"); +MODULE_FIRMWARE("amdgpu/polaris12_sdma1.bin"); static const u32 sdma_offsets[SDMA_MAX_INSTANCE] = @@ -206,6 +208,7 @@ static void sdma_v3_0_init_golden_registers(struct amdgpu_device *adev) (const u32)ARRAY_SIZE(golden_settings_tonga_a11)); break; case CHIP_POLARIS11: + case CHIP_POLARIS12: amdgpu_program_register_sequence(adev, golden_settings_polaris11_a11, (const u32)ARRAY_SIZE(golden_settings_polaris11_a11)); @@ -278,6 +281,9 @@ static int sdma_v3_0_init_microcode(struct amdgpu_device *adev) case CHIP_POLARIS10: chip_name = "polaris10"; break; + case CHIP_POLARIS12: + chip_name = "polaris12"; + break; case CHIP_CARRIZO: chip_name = "carrizo"; break; diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c index 6c65a1a2de79..10bedfac27b8 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c @@ -56,7 +56,6 @@ #define BIOS_SCRATCH_4 0x5cd MODULE_FIRMWARE("radeon/tahiti_smc.bin"); -MODULE_FIRMWARE("radeon/tahiti_k_smc.bin"); MODULE_FIRMWARE("radeon/pitcairn_smc.bin"); MODULE_FIRMWARE("radeon/pitcairn_k_smc.bin"); MODULE_FIRMWARE("radeon/verde_smc.bin"); @@ -3488,19 +3487,6 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev, (adev->pdev->device == 0x6817) || (adev->pdev->device == 0x6806)) max_mclk = 120000; - } else if (adev->asic_type == CHIP_VERDE) { - if ((adev->pdev->revision == 0x81) || - (adev->pdev->revision == 0x83) || - (adev->pdev->revision == 0x87) || - (adev->pdev->device == 0x6820) || - (adev->pdev->device == 0x6821) || - (adev->pdev->device == 0x6822) || - (adev->pdev->device == 0x6823) || - (adev->pdev->device == 0x682A) || - (adev->pdev->device == 0x682B)) { - max_sclk = 75000; - max_mclk = 80000; - } } else if (adev->asic_type == CHIP_OLAND) { if ((adev->pdev->revision == 0xC7) || (adev->pdev->revision == 0x80) || @@ -7687,49 +7673,49 @@ static int si_dpm_init_microcode(struct amdgpu_device *adev) chip_name = "tahiti"; break; case CHIP_PITCAIRN: - if ((adev->pdev->revision == 0x81) || - (adev->pdev->device == 0x6810) || - (adev->pdev->device == 0x6811) || - (adev->pdev->device == 0x6816) || - (adev->pdev->device == 0x6817) || - (adev->pdev->device == 0x6806)) + if ((adev->pdev->revision == 0x81) && + ((adev->pdev->device == 0x6810) || + (adev->pdev->device == 0x6811))) chip_name = "pitcairn_k"; else chip_name = "pitcairn"; break; case CHIP_VERDE: - if ((adev->pdev->revision == 0x81) || - (adev->pdev->revision == 0x83) || - (adev->pdev->revision == 0x87) || - (adev->pdev->device == 0x6820) || - (adev->pdev->device == 0x6821) || - (adev->pdev->device == 0x6822) || - (adev->pdev->device == 0x6823) || - (adev->pdev->device == 0x682A) || - (adev->pdev->device == 0x682B)) + if (((adev->pdev->device == 0x6820) && + ((adev->pdev->revision == 0x81) || + (adev->pdev->revision == 0x83))) || + ((adev->pdev->device == 0x6821) && + ((adev->pdev->revision == 0x83) || + (adev->pdev->revision == 0x87))) || + ((adev->pdev->revision == 0x87) && + ((adev->pdev->device == 0x6823) || + (adev->pdev->device == 0x682b)))) chip_name = "verde_k"; else chip_name = "verde"; break; case CHIP_OLAND: - if ((adev->pdev->revision == 0xC7) || - (adev->pdev->revision == 0x80) || - (adev->pdev->revision == 0x81) || - (adev->pdev->revision == 0x83) || - (adev->pdev->revision == 0x87) || - (adev->pdev->device == 0x6604) || - (adev->pdev->device == 0x6605)) + if (((adev->pdev->revision == 0x81) && + ((adev->pdev->device == 0x6600) || + (adev->pdev->device == 0x6604) || + (adev->pdev->device == 0x6605) || + (adev->pdev->device == 0x6610))) || + ((adev->pdev->revision == 0x83) && + (adev->pdev->device == 0x6610))) chip_name = "oland_k"; else chip_name = "oland"; break; case CHIP_HAINAN: - if ((adev->pdev->revision == 0x81) || - (adev->pdev->revision == 0x83) || - (adev->pdev->revision == 0xC3) || - (adev->pdev->device == 0x6664) || - (adev->pdev->device == 0x6665) || - (adev->pdev->device == 0x6667)) + if (((adev->pdev->revision == 0x81) && + (adev->pdev->device == 0x6660)) || + ((adev->pdev->revision == 0x83) && + ((adev->pdev->device == 0x6660) || + (adev->pdev->device == 0x6663) || + (adev->pdev->device == 0x6665) || + (adev->pdev->device == 0x6667))) || + ((adev->pdev->revision == 0xc3) && + (adev->pdev->device == 0x6665))) chip_name = "hainan_k"; else chip_name = "hainan"; diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c index a79e283590fb..6de6becce745 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c @@ -791,15 +791,10 @@ static int uvd_v5_0_set_clockgating_state(void *handle, { struct amdgpu_device *adev = (struct amdgpu_device *)handle; bool enable = (state == AMD_CG_STATE_GATE) ? true : false; - static int curstate = -1; if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG)) return 0; - if (curstate == state) - return 0; - - curstate = state; if (enable) { /* wait for STATUS to clear */ if (uvd_v5_0_wait_for_idle(handle)) diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c index 6b3293a1c7b8..5fb0b7f5c065 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c @@ -320,11 +320,12 @@ static unsigned vce_v3_0_get_harvest_config(struct amdgpu_device *adev) { u32 tmp; - /* Fiji, Stoney, Polaris10, Polaris11 are single pipe */ + /* Fiji, Stoney, Polaris10, Polaris11, Polaris12 are single pipe */ if ((adev->asic_type == CHIP_FIJI) || (adev->asic_type == CHIP_STONEY) || (adev->asic_type == CHIP_POLARIS10) || - (adev->asic_type == CHIP_POLARIS11)) + (adev->asic_type == CHIP_POLARIS11) || + (adev->asic_type == CHIP_POLARIS12)) return AMDGPU_VCE_HARVEST_VCE1; /* Tonga and CZ are dual or single pipe */ diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index bf088d6d9bf1..c2ac54f11341 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -88,6 +88,7 @@ MODULE_FIRMWARE("amdgpu/polaris10_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris10_smc_sk.bin"); MODULE_FIRMWARE("amdgpu/polaris11_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris11_smc_sk.bin"); +MODULE_FIRMWARE("amdgpu/polaris12_smc.bin"); /* * Indirect registers accessor @@ -312,6 +313,7 @@ static void vi_init_golden_registers(struct amdgpu_device *adev) break; case CHIP_POLARIS11: case CHIP_POLARIS10: + case CHIP_POLARIS12: default: break; } @@ -671,6 +673,7 @@ static int vi_read_register(struct amdgpu_device *adev, u32 se_num, case CHIP_TONGA: case CHIP_POLARIS11: case CHIP_POLARIS10: + case CHIP_POLARIS12: case CHIP_CARRIZO: case CHIP_STONEY: asic_register_table = cz_allowed_read_registers; @@ -994,6 +997,11 @@ static int vi_common_early_init(void *handle) adev->pg_flags = 0; adev->external_rev_id = adev->rev_id + 0x50; break; + case CHIP_POLARIS12: + adev->cg_flags = AMD_CG_SUPPORT_UVD_MGCG; + adev->pg_flags = 0; + adev->external_rev_id = adev->rev_id + 0x64; + break; case CHIP_CARRIZO: adev->cg_flags = AMD_CG_SUPPORT_UVD_MGCG | AMD_CG_SUPPORT_GFX_MGCG | @@ -1346,6 +1354,7 @@ static int vi_common_set_clockgating_state(void *handle, case CHIP_TONGA: case CHIP_POLARIS10: case CHIP_POLARIS11: + case CHIP_POLARIS12: vi_common_set_clockgating_state_by_smu(adev, state); default: break; @@ -1429,6 +1438,7 @@ int vi_set_ip_blocks(struct amdgpu_device *adev) break; case CHIP_POLARIS11: case CHIP_POLARIS10: + case CHIP_POLARIS12: amdgpu_ip_block_add(adev, &vi_common_ip_block); amdgpu_ip_block_add(adev, &gmc_v8_1_ip_block); amdgpu_ip_block_add(adev, &tonga_ih_ip_block); diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index c02469ada9f1..85f358764bbc 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -23,7 +23,7 @@ #ifndef __AMD_SHARED_H__ #define __AMD_SHARED_H__ -#define AMD_MAX_USEC_TIMEOUT 100000 /* 100 ms */ +#define AMD_MAX_USEC_TIMEOUT 200000 /* 200 ms */ /* * Supported ASIC types @@ -46,6 +46,7 @@ enum amd_asic_type { CHIP_STONEY, CHIP_POLARIS10, CHIP_POLARIS11, + CHIP_POLARIS12, CHIP_LAST, }; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c index dc6700aee18f..b03606405a53 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c @@ -95,6 +95,7 @@ int hwmgr_init(struct amd_pp_init *pp_init, struct pp_instance *handle) break; case CHIP_POLARIS11: case CHIP_POLARIS10: + case CHIP_POLARIS12: polaris_set_asic_special_caps(hwmgr); hwmgr->feature_mask &= ~(PP_UVD_HANDSHAKE_MASK); break; @@ -745,7 +746,7 @@ int polaris_set_asic_special_caps(struct pp_hwmgr *hwmgr) phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_TablelessHardwareInterface); - if (hwmgr->chip_id == CHIP_POLARIS11) + if ((hwmgr->chip_id == CHIP_POLARIS11) || (hwmgr->chip_id == CHIP_POLARIS12)) phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SPLLShutdownSupport); return 0; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c index 26477f0f09dc..6cd1287a7a8f 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c @@ -521,7 +521,7 @@ int smu7_enable_didt_config(struct pp_hwmgr *hwmgr) PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result); result = smu7_program_pt_config_registers(hwmgr, DIDTConfig_Polaris10); PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result); - } else if (hwmgr->chip_id == CHIP_POLARIS11) { + } else if ((hwmgr->chip_id == CHIP_POLARIS11) || (hwmgr->chip_id == CHIP_POLARIS12)) { result = smu7_program_pt_config_registers(hwmgr, GCCACConfig_Polaris11); PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result); result = smu7_program_pt_config_registers(hwmgr, DIDTConfig_Polaris11); diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c index e5812aa456f3..6e618aa20719 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c @@ -65,6 +65,7 @@ int smum_init(struct amd_pp_init *pp_init, struct pp_instance *handle) break; case CHIP_POLARIS11: case CHIP_POLARIS10: + case CHIP_POLARIS12: polaris10_smum_init(smumgr); break; default: diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 583f47f27b36..34f757bcabae 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1259,8 +1259,10 @@ int drm_atomic_helper_commit(struct drm_device *dev, if (!nonblock) { ret = drm_atomic_helper_wait_for_fences(dev, state, true); - if (ret) + if (ret) { + drm_atomic_helper_cleanup_planes(dev, state); return ret; + } } /* diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c index 4942ca090b46..7890e30eb584 100644 --- a/drivers/gpu/drm/meson/meson_plane.c +++ b/drivers/gpu/drm/meson/meson_plane.c @@ -51,6 +51,9 @@ static int meson_plane_atomic_check(struct drm_plane *plane, struct drm_crtc_state *crtc_state; struct drm_rect clip = { 0, }; + if (!state->crtc) + return 0; + crtc_state = drm_atomic_get_crtc_state(state->state, state->crtc); if (IS_ERR(crtc_state)) return PTR_ERR(crtc_state); diff --git a/drivers/gpu/drm/meson/meson_venc.c b/drivers/gpu/drm/meson/meson_venc.c index d836b2274531..f7c870172220 100644 --- a/drivers/gpu/drm/meson/meson_venc.c +++ b/drivers/gpu/drm/meson/meson_venc.c @@ -38,6 +38,11 @@ * - TV Panel encoding via ENCT */ +/* HHI Registers */ +#define HHI_VDAC_CNTL0 0x2F4 /* 0xbd offset in data sheet */ +#define HHI_VDAC_CNTL1 0x2F8 /* 0xbe offset in data sheet */ +#define HHI_HDMI_PHY_CNTL0 0x3a0 /* 0xe8 offset in data sheet */ + struct meson_cvbs_enci_mode meson_cvbs_enci_pal = { .mode_tag = MESON_VENC_MODE_CVBS_PAL, .hso_begin = 3, @@ -242,6 +247,20 @@ void meson_venc_disable_vsync(struct meson_drm *priv) void meson_venc_init(struct meson_drm *priv) { + /* Disable CVBS VDAC */ + regmap_write(priv->hhi, HHI_VDAC_CNTL0, 0); + regmap_write(priv->hhi, HHI_VDAC_CNTL1, 8); + + /* Power Down Dacs */ + writel_relaxed(0xff, priv->io_base + _REG(VENC_VDAC_SETTING)); + + /* Disable HDMI PHY */ + regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL0, 0); + + /* Disable HDMI */ + writel_bits_relaxed(0x3, 0, + priv->io_base + _REG(VPU_HDMI_SETTING)); + /* Disable all encoders */ writel_relaxed(0, priv->io_base + _REG(ENCI_VIDEO_EN)); writel_relaxed(0, priv->io_base + _REG(ENCP_VIDEO_EN)); diff --git a/drivers/gpu/drm/meson/meson_venc_cvbs.c b/drivers/gpu/drm/meson/meson_venc_cvbs.c index c809c085fd78..a2bcc70a03ef 100644 --- a/drivers/gpu/drm/meson/meson_venc_cvbs.c +++ b/drivers/gpu/drm/meson/meson_venc_cvbs.c @@ -167,7 +167,7 @@ static void meson_venc_cvbs_encoder_disable(struct drm_encoder *encoder) /* Disable CVBS VDAC */ regmap_write(priv->hhi, HHI_VDAC_CNTL0, 0); - regmap_write(priv->hhi, HHI_VDAC_CNTL1, 0); + regmap_write(priv->hhi, HHI_VDAC_CNTL1, 8); } static void meson_venc_cvbs_encoder_enable(struct drm_encoder *encoder) diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index a18126150e11..14ff87686a36 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -213,7 +213,14 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, void adreno_flush(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); - uint32_t wptr = get_wptr(gpu->rb); + uint32_t wptr; + + /* + * Mask wptr value that we calculate to fit in the HW range. This is + * to account for the possibility that the last command fit exactly into + * the ringbuffer and rb->next hasn't wrapped to zero yet + */ + wptr = get_wptr(gpu->rb) & ((gpu->rb->size / 4) - 1); /* ensure writes to ringbuffer have hit system memory: */ mb(); diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 166e84e4f0d4..489676568a10 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -106,7 +106,8 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, pagefault_disable(); } - if (submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) { + if ((submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) || + !(submit_bo.flags & MSM_SUBMIT_BO_FLAGS)) { DRM_ERROR("invalid flags: %x\n", submit_bo.flags); ret = -EINVAL; goto out_unlock; @@ -290,7 +291,7 @@ static int submit_reloc(struct msm_gem_submit *submit, struct msm_gem_object *ob { uint32_t i, last_offset = 0; uint32_t *ptr; - int ret; + int ret = 0; if (offset % 4) { DRM_ERROR("non-aligned cmdstream buffer: %u\n", offset); @@ -318,12 +319,13 @@ static int submit_reloc(struct msm_gem_submit *submit, struct msm_gem_object *ob ret = copy_from_user(&submit_reloc, userptr, sizeof(submit_reloc)); if (ret) - return -EFAULT; + goto out; if (submit_reloc.submit_offset % 4) { DRM_ERROR("non-aligned reloc offset: %u\n", submit_reloc.submit_offset); - return -EINVAL; + ret = -EINVAL; + goto out; } /* offset in dwords: */ @@ -332,12 +334,13 @@ static int submit_reloc(struct msm_gem_submit *submit, struct msm_gem_object *ob if ((off >= (obj->base.size / 4)) || (off < last_offset)) { DRM_ERROR("invalid offset %u at reloc %u\n", off, i); - return -EINVAL; + ret = -EINVAL; + goto out; } ret = submit_bo(submit, submit_reloc.reloc_idx, NULL, &iova, &valid); if (ret) - return ret; + goto out; if (valid) continue; @@ -354,9 +357,10 @@ static int submit_reloc(struct msm_gem_submit *submit, struct msm_gem_object *ob last_offset = off; } +out: msm_gem_put_vaddr_locked(&obj->base); - return 0; + return ret; } static void submit_cleanup(struct msm_gem_submit *submit) diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index f326cf6a32e6..67b34e069abf 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -23,7 +23,8 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int size) struct msm_ringbuffer *ring; int ret; - size = ALIGN(size, 4); /* size should be dword aligned */ + if (WARN_ON(!is_power_of_2(size))) + return ERR_PTR(-EINVAL); ring = kzalloc(sizeof(*ring), GFP_KERNEL); if (!ring) { diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index ad4d7b8b8322..e8a38d296855 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -50,7 +50,6 @@ MODULE_FIRMWARE("radeon/tahiti_ce.bin"); MODULE_FIRMWARE("radeon/tahiti_mc.bin"); MODULE_FIRMWARE("radeon/tahiti_rlc.bin"); MODULE_FIRMWARE("radeon/tahiti_smc.bin"); -MODULE_FIRMWARE("radeon/tahiti_k_smc.bin"); MODULE_FIRMWARE("radeon/PITCAIRN_pfp.bin"); MODULE_FIRMWARE("radeon/PITCAIRN_me.bin"); @@ -1657,9 +1656,6 @@ static int si_init_microcode(struct radeon_device *rdev) switch (rdev->family) { case CHIP_TAHITI: chip_name = "TAHITI"; - /* XXX: figure out which Tahitis need the new ucode */ - if (0) - new_smc = true; new_chip_name = "tahiti"; pfp_req_size = SI_PFP_UCODE_SIZE * 4; me_req_size = SI_PM4_UCODE_SIZE * 4; @@ -1671,12 +1667,9 @@ static int si_init_microcode(struct radeon_device *rdev) break; case CHIP_PITCAIRN: chip_name = "PITCAIRN"; - if ((rdev->pdev->revision == 0x81) || - (rdev->pdev->device == 0x6810) || - (rdev->pdev->device == 0x6811) || - (rdev->pdev->device == 0x6816) || - (rdev->pdev->device == 0x6817) || - (rdev->pdev->device == 0x6806)) + if ((rdev->pdev->revision == 0x81) && + ((rdev->pdev->device == 0x6810) || + (rdev->pdev->device == 0x6811))) new_smc = true; new_chip_name = "pitcairn"; pfp_req_size = SI_PFP_UCODE_SIZE * 4; @@ -1689,15 +1682,15 @@ static int si_init_microcode(struct radeon_device *rdev) break; case CHIP_VERDE: chip_name = "VERDE"; - if ((rdev->pdev->revision == 0x81) || - (rdev->pdev->revision == 0x83) || - (rdev->pdev->revision == 0x87) || - (rdev->pdev->device == 0x6820) || - (rdev->pdev->device == 0x6821) || - (rdev->pdev->device == 0x6822) || - (rdev->pdev->device == 0x6823) || - (rdev->pdev->device == 0x682A) || - (rdev->pdev->device == 0x682B)) + if (((rdev->pdev->device == 0x6820) && + ((rdev->pdev->revision == 0x81) || + (rdev->pdev->revision == 0x83))) || + ((rdev->pdev->device == 0x6821) && + ((rdev->pdev->revision == 0x83) || + (rdev->pdev->revision == 0x87))) || + ((rdev->pdev->revision == 0x87) && + ((rdev->pdev->device == 0x6823) || + (rdev->pdev->device == 0x682b)))) new_smc = true; new_chip_name = "verde"; pfp_req_size = SI_PFP_UCODE_SIZE * 4; @@ -1710,13 +1703,13 @@ static int si_init_microcode(struct radeon_device *rdev) break; case CHIP_OLAND: chip_name = "OLAND"; - if ((rdev->pdev->revision == 0xC7) || - (rdev->pdev->revision == 0x80) || - (rdev->pdev->revision == 0x81) || - (rdev->pdev->revision == 0x83) || - (rdev->pdev->revision == 0x87) || - (rdev->pdev->device == 0x6604) || - (rdev->pdev->device == 0x6605)) + if (((rdev->pdev->revision == 0x81) && + ((rdev->pdev->device == 0x6600) || + (rdev->pdev->device == 0x6604) || + (rdev->pdev->device == 0x6605) || + (rdev->pdev->device == 0x6610))) || + ((rdev->pdev->revision == 0x83) && + (rdev->pdev->device == 0x6610))) new_smc = true; new_chip_name = "oland"; pfp_req_size = SI_PFP_UCODE_SIZE * 4; @@ -1728,12 +1721,15 @@ static int si_init_microcode(struct radeon_device *rdev) break; case CHIP_HAINAN: chip_name = "HAINAN"; - if ((rdev->pdev->revision == 0x81) || - (rdev->pdev->revision == 0x83) || - (rdev->pdev->revision == 0xC3) || - (rdev->pdev->device == 0x6664) || - (rdev->pdev->device == 0x6665) || - (rdev->pdev->device == 0x6667)) + if (((rdev->pdev->revision == 0x81) && + (rdev->pdev->device == 0x6660)) || + ((rdev->pdev->revision == 0x83) && + ((rdev->pdev->device == 0x6660) || + (rdev->pdev->device == 0x6663) || + (rdev->pdev->device == 0x6665) || + (rdev->pdev->device == 0x6667))) || + ((rdev->pdev->revision == 0xc3) && + (rdev->pdev->device == 0x6665))) new_smc = true; new_chip_name = "hainan"; pfp_req_size = SI_PFP_UCODE_SIZE * 4; diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index 8b5e697f2549..13ba73fd9b68 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -3008,19 +3008,6 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev, (rdev->pdev->device == 0x6817) || (rdev->pdev->device == 0x6806)) max_mclk = 120000; - } else if (rdev->family == CHIP_VERDE) { - if ((rdev->pdev->revision == 0x81) || - (rdev->pdev->revision == 0x83) || - (rdev->pdev->revision == 0x87) || - (rdev->pdev->device == 0x6820) || - (rdev->pdev->device == 0x6821) || - (rdev->pdev->device == 0x6822) || - (rdev->pdev->device == 0x6823) || - (rdev->pdev->device == 0x682A) || - (rdev->pdev->device == 0x682B)) { - max_sclk = 75000; - max_mclk = 80000; - } } else if (rdev->family == CHIP_OLAND) { if ((rdev->pdev->revision == 0xC7) || (rdev->pdev->revision == 0x80) || diff --git a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c index 725dffad5640..6dfdb145f3bb 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c @@ -856,7 +856,7 @@ irqreturn_t tilcdc_crtc_irq(struct drm_crtc *crtc) struct tilcdc_crtc *tilcdc_crtc = to_tilcdc_crtc(crtc); struct drm_device *dev = crtc->dev; struct tilcdc_drm_private *priv = dev->dev_private; - uint32_t stat; + uint32_t stat, reg; stat = tilcdc_read_irqstatus(dev); tilcdc_clear_irqstatus(dev, stat); @@ -921,17 +921,26 @@ irqreturn_t tilcdc_crtc_irq(struct drm_crtc *crtc) dev_err_ratelimited(dev->dev, "%s(0x%08x): Sync lost", __func__, stat); tilcdc_crtc->frame_intact = false; - if (tilcdc_crtc->sync_lost_count++ > - SYNC_LOST_COUNT_LIMIT) { - dev_err(dev->dev, "%s(0x%08x): Sync lost flood detected, recovering", __func__, stat); - queue_work(system_wq, &tilcdc_crtc->recover_work); - if (priv->rev == 1) + if (priv->rev == 1) { + reg = tilcdc_read(dev, LCDC_RASTER_CTRL_REG); + if (reg & LCDC_RASTER_ENABLE) { tilcdc_clear(dev, LCDC_RASTER_CTRL_REG, - LCDC_V1_SYNC_LOST_INT_ENA); - else + LCDC_RASTER_ENABLE); + tilcdc_set(dev, LCDC_RASTER_CTRL_REG, + LCDC_RASTER_ENABLE); + } + } else { + if (tilcdc_crtc->sync_lost_count++ > + SYNC_LOST_COUNT_LIMIT) { + dev_err(dev->dev, + "%s(0x%08x): Sync lost flood detected, recovering", + __func__, stat); + queue_work(system_wq, + &tilcdc_crtc->recover_work); tilcdc_write(dev, LCDC_INT_ENABLE_CLR_REG, LCDC_SYNC_LOST); - tilcdc_crtc->sync_lost_count = 0; + tilcdc_crtc->sync_lost_count = 0; + } } } diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index cff060b56da9..ea36b557d5ee 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2496,6 +2496,7 @@ static const struct hid_device_id hid_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_PANJIT, 0x0002) }, { HID_USB_DEVICE(USB_VENDOR_ID_PANJIT, 0x0003) }, { HID_USB_DEVICE(USB_VENDOR_ID_PANJIT, 0x0004) }, + { HID_USB_DEVICE(USB_VENDOR_ID_PETZL, USB_DEVICE_ID_PETZL_HEADLAMP) }, { HID_USB_DEVICE(USB_VENDOR_ID_PHILIPS, USB_DEVICE_ID_PHILIPS_IEEE802154_DONGLE) }, { HID_USB_DEVICE(USB_VENDOR_ID_POWERCOM, USB_DEVICE_ID_POWERCOM_UPS) }, #if IS_ENABLED(CONFIG_MOUSE_SYNAPTICS_USB) diff --git a/drivers/hid/hid-cypress.c b/drivers/hid/hid-cypress.c index 1b764d1745f3..1689568b597d 100644 --- a/drivers/hid/hid-cypress.c +++ b/drivers/hid/hid-cypress.c @@ -39,6 +39,9 @@ static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc, if (!(quirks & CP_RDESC_SWAPPED_MIN_MAX)) return rdesc; + if (*rsize < 4) + return rdesc; + for (i = 0; i < *rsize - 4; i++) if (rdesc[i] == 0x29 && rdesc[i + 2] == 0x19) { rdesc[i] = 0x19; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 54bd22dc1411..f46f2c5117fa 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -816,6 +816,9 @@ #define USB_VENDOR_ID_PETALYNX 0x18b1 #define USB_DEVICE_ID_PETALYNX_MAXTER_REMOTE 0x0037 +#define USB_VENDOR_ID_PETZL 0x2122 +#define USB_DEVICE_ID_PETZL_HEADLAMP 0x1234 + #define USB_VENDOR_ID_PHILIPS 0x0471 #define USB_DEVICE_ID_PHILIPS_IEEE802154_DONGLE 0x0617 diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index 78fb32a7b103..ea3c3546cef7 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -426,6 +426,15 @@ static int i2c_hid_hwreset(struct i2c_client *client) if (ret) goto out_unlock; + /* + * The HID over I2C specification states that if a DEVICE needs time + * after the PWR_ON request, it should utilise CLOCK stretching. + * However, it has been observered that the Windows driver provides a + * 1ms sleep between the PWR_ON and RESET requests and that some devices + * rely on this. + */ + usleep_range(1000, 5000); + i2c_hid_dbg(ihid, "resetting...\n"); ret = i2c_hid_command(client, &hid_reset_cmd, NULL, 0); diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c index f3135ae22df4..abd18f31b24f 100644 --- a/drivers/input/joydev.c +++ b/drivers/input/joydev.c @@ -22,7 +22,6 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/mm.h> -#include <linux/miscdevice.h> #include <linux/module.h> #include <linux/poll.h> #include <linux/init.h> diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 6d9499658671..c7d5b2b643d1 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -1377,6 +1377,12 @@ static int xpad_init_input(struct usb_xpad *xpad) input_dev->name = xpad->name; input_dev->phys = xpad->phys; usb_to_input_id(xpad->udev, &input_dev->id); + + if (xpad->xtype == XTYPE_XBOX360W) { + /* x360w controllers and the receiver have different ids */ + input_dev->id.product = 0x02a1; + } + input_dev->dev.parent = &xpad->intf->dev; input_set_drvdata(input_dev, xpad); diff --git a/drivers/input/misc/adxl34x-i2c.c b/drivers/input/misc/adxl34x-i2c.c index a8b0a2eec344..7fed92fb8cc1 100644 --- a/drivers/input/misc/adxl34x-i2c.c +++ b/drivers/input/misc/adxl34x-i2c.c @@ -136,7 +136,6 @@ static const struct i2c_device_id adxl34x_id[] = { MODULE_DEVICE_TABLE(i2c, adxl34x_id); -#ifdef CONFIG_OF static const struct of_device_id adxl34x_of_id[] = { /* * The ADXL346 is backward-compatible with the ADXL345. Differences are @@ -153,13 +152,12 @@ static const struct of_device_id adxl34x_of_id[] = { }; MODULE_DEVICE_TABLE(of, adxl34x_of_id); -#endif static struct i2c_driver adxl34x_driver = { .driver = { .name = "adxl34x", .pm = &adxl34x_i2c_pm, - .of_match_table = of_match_ptr(adxl34x_of_id), + .of_match_table = adxl34x_of_id, }, .probe = adxl34x_i2c_probe, .remove = adxl34x_i2c_remove, diff --git a/drivers/input/mouse/alps.h b/drivers/input/mouse/alps.h index cde6f4bd8ea2..6d279aa27cb9 100644 --- a/drivers/input/mouse/alps.h +++ b/drivers/input/mouse/alps.h @@ -114,7 +114,7 @@ enum SS4_PACKET_ID { (_b[1] & 0x7F) \ ) -#define SS4_TS_Y_V2(_b) (s8)( \ +#define SS4_TS_Y_V2(_b) -(s8)( \ ((_b[3] & 0x01) << 7) | \ (_b[2] & 0x7F) \ ) diff --git a/drivers/input/mouse/synaptics_i2c.c b/drivers/input/mouse/synaptics_i2c.c index aa7c5da60800..cb2bf203f4ca 100644 --- a/drivers/input/mouse/synaptics_i2c.c +++ b/drivers/input/mouse/synaptics_i2c.c @@ -29,7 +29,7 @@ * after soft reset, we should wait for 1 ms * before the device becomes operational */ -#define SOFT_RESET_DELAY_MS 3 +#define SOFT_RESET_DELAY_US 3000 /* and after hard reset, we should wait for max 500ms */ #define HARD_RESET_DELAY_MS 500 @@ -311,7 +311,7 @@ static int synaptics_i2c_reset_config(struct i2c_client *client) if (ret) { dev_err(&client->dev, "Unable to reset device\n"); } else { - msleep(SOFT_RESET_DELAY_MS); + usleep_range(SOFT_RESET_DELAY_US, SOFT_RESET_DELAY_US + 100); ret = synaptics_i2c_config(client); if (ret) dev_err(&client->dev, "Unable to config device\n"); diff --git a/drivers/input/rmi4/Kconfig b/drivers/input/rmi4/Kconfig index 30cc627a4f45..8993983e3fe4 100644 --- a/drivers/input/rmi4/Kconfig +++ b/drivers/input/rmi4/Kconfig @@ -41,7 +41,8 @@ config RMI4_SMB config RMI4_F03 bool "RMI4 Function 03 (PS2 Guest)" - depends on RMI4_CORE && SERIO + depends on RMI4_CORE + depends on SERIO=y || RMI4_CORE=SERIO help Say Y here if you want to add support for RMI4 function 03. diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 77551f522202..a7618776705a 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -211,6 +211,12 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "Rev 1"), }, }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "PEGATRON CORPORATION"), + DMI_MATCH(DMI_PRODUCT_NAME, "C15B"), + }, + }, { } }; diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c index 02aec284deca..3e6003d32e56 100644 --- a/drivers/input/touchscreen/elants_i2c.c +++ b/drivers/input/touchscreen/elants_i2c.c @@ -914,9 +914,9 @@ static irqreturn_t elants_i2c_irq(int irq, void *_dev) case QUEUE_HEADER_NORMAL: report_count = ts->buf[FW_HDR_COUNT]; - if (report_count > 3) { + if (report_count == 0 || report_count > 3) { dev_err(&client->dev, - "too large report count: %*ph\n", + "bad report count: %*ph\n", HEADER_SIZE, ts->buf); break; } diff --git a/drivers/md/md.h b/drivers/md/md.h index e38936d05df1..2a514036a83d 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -212,6 +212,7 @@ extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int is_new); struct md_cluster_info; +/* change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */ enum mddev_flags { MD_ARRAY_FIRST_USE, /* First use of array, needs initialization */ MD_CLOSING, /* If set, we are closing the array, do not open @@ -702,4 +703,11 @@ static inline int mddev_is_clustered(struct mddev *mddev) { return mddev->cluster_info && mddev->bitmap_info.nodes > 1; } + +/* clear unsupported mddev_flags */ +static inline void mddev_clear_unsupported_flags(struct mddev *mddev, + unsigned long unsupported_flags) +{ + mddev->flags &= ~unsupported_flags; +} #endif /* _MD_MD_H */ diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index a162fedeb51a..848365d474f3 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -26,6 +26,11 @@ #include "raid0.h" #include "raid5.h" +#define UNSUPPORTED_MDDEV_FLAGS \ + ((1L << MD_HAS_JOURNAL) | \ + (1L << MD_JOURNAL_CLEAN) | \ + (1L << MD_FAILFAST_SUPPORTED)) + static int raid0_congested(struct mddev *mddev, int bits) { struct r0conf *conf = mddev->private; @@ -539,8 +544,7 @@ static void *raid0_takeover_raid45(struct mddev *mddev) mddev->delta_disks = -1; /* make sure it will be not marked as dirty */ mddev->recovery_cp = MaxSector; - clear_bit(MD_HAS_JOURNAL, &mddev->flags); - clear_bit(MD_JOURNAL_CLEAN, &mddev->flags); + mddev_clear_unsupported_flags(mddev, UNSUPPORTED_MDDEV_FLAGS); create_strip_zones(mddev, &priv_conf); @@ -583,7 +587,7 @@ static void *raid0_takeover_raid10(struct mddev *mddev) mddev->degraded = 0; /* make sure it will be not marked as dirty */ mddev->recovery_cp = MaxSector; - clear_bit(MD_FAILFAST_SUPPORTED, &mddev->flags); + mddev_clear_unsupported_flags(mddev, UNSUPPORTED_MDDEV_FLAGS); create_strip_zones(mddev, &priv_conf); return priv_conf; @@ -626,7 +630,7 @@ static void *raid0_takeover_raid1(struct mddev *mddev) mddev->raid_disks = 1; /* make sure it will be not marked as dirty */ mddev->recovery_cp = MaxSector; - clear_bit(MD_FAILFAST_SUPPORTED, &mddev->flags); + mddev_clear_unsupported_flags(mddev, UNSUPPORTED_MDDEV_FLAGS); create_strip_zones(mddev, &priv_conf); return priv_conf; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index a1f3fbed9100..7b0f647bcccb 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -42,6 +42,10 @@ #include "raid1.h" #include "bitmap.h" +#define UNSUPPORTED_MDDEV_FLAGS \ + ((1L << MD_HAS_JOURNAL) | \ + (1L << MD_JOURNAL_CLEAN)) + /* * Number of guaranteed r1bios in case of extreme VM load: */ @@ -1066,17 +1070,107 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule) kfree(plug); } -static void raid1_make_request(struct mddev *mddev, struct bio * bio) +static void raid1_read_request(struct mddev *mddev, struct bio *bio, + struct r1bio *r1_bio) { struct r1conf *conf = mddev->private; struct raid1_info *mirror; - struct r1bio *r1_bio; struct bio *read_bio; + struct bitmap *bitmap = mddev->bitmap; + const int op = bio_op(bio); + const unsigned long do_sync = (bio->bi_opf & REQ_SYNC); + int sectors_handled; + int max_sectors; + int rdisk; + + wait_barrier(conf, bio); + +read_again: + rdisk = read_balance(conf, r1_bio, &max_sectors); + + if (rdisk < 0) { + /* couldn't find anywhere to read from */ + raid_end_bio_io(r1_bio); + return; + } + mirror = conf->mirrors + rdisk; + + if (test_bit(WriteMostly, &mirror->rdev->flags) && + bitmap) { + /* + * Reading from a write-mostly device must take care not to + * over-take any writes that are 'behind' + */ + raid1_log(mddev, "wait behind writes"); + wait_event(bitmap->behind_wait, + atomic_read(&bitmap->behind_writes) == 0); + } + r1_bio->read_disk = rdisk; + r1_bio->start_next_window = 0; + + read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev); + bio_trim(read_bio, r1_bio->sector - bio->bi_iter.bi_sector, + max_sectors); + + r1_bio->bios[rdisk] = read_bio; + + read_bio->bi_iter.bi_sector = r1_bio->sector + + mirror->rdev->data_offset; + read_bio->bi_bdev = mirror->rdev->bdev; + read_bio->bi_end_io = raid1_end_read_request; + bio_set_op_attrs(read_bio, op, do_sync); + if (test_bit(FailFast, &mirror->rdev->flags) && + test_bit(R1BIO_FailFast, &r1_bio->state)) + read_bio->bi_opf |= MD_FAILFAST; + read_bio->bi_private = r1_bio; + + if (mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev), + read_bio, disk_devt(mddev->gendisk), + r1_bio->sector); + + if (max_sectors < r1_bio->sectors) { + /* + * could not read all from this device, so we will need another + * r1_bio. + */ + sectors_handled = (r1_bio->sector + max_sectors + - bio->bi_iter.bi_sector); + r1_bio->sectors = max_sectors; + spin_lock_irq(&conf->device_lock); + if (bio->bi_phys_segments == 0) + bio->bi_phys_segments = 2; + else + bio->bi_phys_segments++; + spin_unlock_irq(&conf->device_lock); + + /* + * Cannot call generic_make_request directly as that will be + * queued in __make_request and subsequent mempool_alloc might + * block waiting for it. So hand bio over to raid1d. + */ + reschedule_retry(r1_bio); + + r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO); + + r1_bio->master_bio = bio; + r1_bio->sectors = bio_sectors(bio) - sectors_handled; + r1_bio->state = 0; + r1_bio->mddev = mddev; + r1_bio->sector = bio->bi_iter.bi_sector + sectors_handled; + goto read_again; + } else + generic_make_request(read_bio); +} + +static void raid1_write_request(struct mddev *mddev, struct bio *bio, + struct r1bio *r1_bio) +{ + struct r1conf *conf = mddev->private; int i, disks; - struct bitmap *bitmap; + struct bitmap *bitmap = mddev->bitmap; unsigned long flags; const int op = bio_op(bio); - const int rw = bio_data_dir(bio); const unsigned long do_sync = (bio->bi_opf & REQ_SYNC); const unsigned long do_flush_fua = (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)); @@ -1096,15 +1190,15 @@ static void raid1_make_request(struct mddev *mddev, struct bio * bio) md_write_start(mddev, bio); /* wait on superblock update early */ - if (bio_data_dir(bio) == WRITE && - ((bio_end_sector(bio) > mddev->suspend_lo && + if ((bio_end_sector(bio) > mddev->suspend_lo && bio->bi_iter.bi_sector < mddev->suspend_hi) || (mddev_is_clustered(mddev) && md_cluster_ops->area_resyncing(mddev, WRITE, - bio->bi_iter.bi_sector, bio_end_sector(bio))))) { - /* As the suspend_* range is controlled by - * userspace, we want an interruptible - * wait. + bio->bi_iter.bi_sector, bio_end_sector(bio)))) { + + /* + * As the suspend_* range is controlled by userspace, we want + * an interruptible wait. */ DEFINE_WAIT(w); for (;;) { @@ -1115,128 +1209,15 @@ static void raid1_make_request(struct mddev *mddev, struct bio * bio) bio->bi_iter.bi_sector >= mddev->suspend_hi || (mddev_is_clustered(mddev) && !md_cluster_ops->area_resyncing(mddev, WRITE, - bio->bi_iter.bi_sector, bio_end_sector(bio)))) + bio->bi_iter.bi_sector, + bio_end_sector(bio)))) break; schedule(); } finish_wait(&conf->wait_barrier, &w); } - start_next_window = wait_barrier(conf, bio); - bitmap = mddev->bitmap; - - /* - * make_request() can abort the operation when read-ahead is being - * used and no empty request is available. - * - */ - r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO); - - r1_bio->master_bio = bio; - r1_bio->sectors = bio_sectors(bio); - r1_bio->state = 0; - r1_bio->mddev = mddev; - r1_bio->sector = bio->bi_iter.bi_sector; - - /* We might need to issue multiple reads to different - * devices if there are bad blocks around, so we keep - * track of the number of reads in bio->bi_phys_segments. - * If this is 0, there is only one r1_bio and no locking - * will be needed when requests complete. If it is - * non-zero, then it is the number of not-completed requests. - */ - bio->bi_phys_segments = 0; - bio_clear_flag(bio, BIO_SEG_VALID); - - if (rw == READ) { - /* - * read balancing logic: - */ - int rdisk; - -read_again: - rdisk = read_balance(conf, r1_bio, &max_sectors); - - if (rdisk < 0) { - /* couldn't find anywhere to read from */ - raid_end_bio_io(r1_bio); - return; - } - mirror = conf->mirrors + rdisk; - - if (test_bit(WriteMostly, &mirror->rdev->flags) && - bitmap) { - /* Reading from a write-mostly device must - * take care not to over-take any writes - * that are 'behind' - */ - raid1_log(mddev, "wait behind writes"); - wait_event(bitmap->behind_wait, - atomic_read(&bitmap->behind_writes) == 0); - } - r1_bio->read_disk = rdisk; - r1_bio->start_next_window = 0; - - read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev); - bio_trim(read_bio, r1_bio->sector - bio->bi_iter.bi_sector, - max_sectors); - - r1_bio->bios[rdisk] = read_bio; - - read_bio->bi_iter.bi_sector = r1_bio->sector + - mirror->rdev->data_offset; - read_bio->bi_bdev = mirror->rdev->bdev; - read_bio->bi_end_io = raid1_end_read_request; - bio_set_op_attrs(read_bio, op, do_sync); - if (test_bit(FailFast, &mirror->rdev->flags) && - test_bit(R1BIO_FailFast, &r1_bio->state)) - read_bio->bi_opf |= MD_FAILFAST; - read_bio->bi_private = r1_bio; - - if (mddev->gendisk) - trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev), - read_bio, disk_devt(mddev->gendisk), - r1_bio->sector); - - if (max_sectors < r1_bio->sectors) { - /* could not read all from this device, so we will - * need another r1_bio. - */ - - sectors_handled = (r1_bio->sector + max_sectors - - bio->bi_iter.bi_sector); - r1_bio->sectors = max_sectors; - spin_lock_irq(&conf->device_lock); - if (bio->bi_phys_segments == 0) - bio->bi_phys_segments = 2; - else - bio->bi_phys_segments++; - spin_unlock_irq(&conf->device_lock); - /* Cannot call generic_make_request directly - * as that will be queued in __make_request - * and subsequent mempool_alloc might block waiting - * for it. So hand bio over to raid1d. - */ - reschedule_retry(r1_bio); - - r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO); - - r1_bio->master_bio = bio; - r1_bio->sectors = bio_sectors(bio) - sectors_handled; - r1_bio->state = 0; - r1_bio->mddev = mddev; - r1_bio->sector = bio->bi_iter.bi_sector + - sectors_handled; - goto read_again; - } else - generic_make_request(read_bio); - return; - } - - /* - * WRITE: - */ if (conf->pending_count >= max_queued_requests) { md_wakeup_thread(mddev->thread); raid1_log(mddev, "wait queued"); @@ -1280,8 +1261,7 @@ read_again: int bad_sectors; int is_bad; - is_bad = is_badblock(rdev, r1_bio->sector, - max_sectors, + is_bad = is_badblock(rdev, r1_bio->sector, max_sectors, &first_bad, &bad_sectors); if (is_bad < 0) { /* mustn't write here until the bad block is @@ -1370,7 +1350,8 @@ read_again: continue; mbio = bio_clone_mddev(bio, GFP_NOIO, mddev); - bio_trim(mbio, r1_bio->sector - bio->bi_iter.bi_sector, max_sectors); + bio_trim(mbio, r1_bio->sector - bio->bi_iter.bi_sector, + max_sectors); if (first_clone) { /* do behind I/O ? @@ -1464,6 +1445,40 @@ read_again: wake_up(&conf->wait_barrier); } +static void raid1_make_request(struct mddev *mddev, struct bio *bio) +{ + struct r1conf *conf = mddev->private; + struct r1bio *r1_bio; + + /* + * make_request() can abort the operation when read-ahead is being + * used and no empty request is available. + * + */ + r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO); + + r1_bio->master_bio = bio; + r1_bio->sectors = bio_sectors(bio); + r1_bio->state = 0; + r1_bio->mddev = mddev; + r1_bio->sector = bio->bi_iter.bi_sector; + + /* + * We might need to issue multiple reads to different devices if there + * are bad blocks around, so we keep track of the number of reads in + * bio->bi_phys_segments. If this is 0, there is only one r1_bio and + * no locking will be needed when requests complete. If it is + * non-zero, then it is the number of not-completed requests. + */ + bio->bi_phys_segments = 0; + bio_clear_flag(bio, BIO_SEG_VALID); + + if (bio_data_dir(bio) == READ) + raid1_read_request(mddev, bio, r1_bio); + else + raid1_write_request(mddev, bio, r1_bio); +} + static void raid1_status(struct seq_file *seq, struct mddev *mddev) { struct r1conf *conf = mddev->private; @@ -3246,8 +3261,8 @@ static void *raid1_takeover(struct mddev *mddev) if (!IS_ERR(conf)) { /* Array must appear to be quiesced */ conf->array_frozen = 1; - clear_bit(MD_HAS_JOURNAL, &mddev->flags); - clear_bit(MD_JOURNAL_CLEAN, &mddev->flags); + mddev_clear_unsupported_flags(mddev, + UNSUPPORTED_MDDEV_FLAGS); } return conf; } diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index ab5e86209322..1920756828df 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1087,23 +1087,122 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) kfree(plug); } -static void __make_request(struct mddev *mddev, struct bio *bio) +static void raid10_read_request(struct mddev *mddev, struct bio *bio, + struct r10bio *r10_bio) { struct r10conf *conf = mddev->private; - struct r10bio *r10_bio; struct bio *read_bio; + const int op = bio_op(bio); + const unsigned long do_sync = (bio->bi_opf & REQ_SYNC); + int sectors_handled; + int max_sectors; + sector_t sectors; + struct md_rdev *rdev; + int slot; + + /* + * Register the new request and wait if the reconstruction + * thread has put up a bar for new requests. + * Continue immediately if no resync is active currently. + */ + wait_barrier(conf); + + sectors = bio_sectors(bio); + while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && + bio->bi_iter.bi_sector < conf->reshape_progress && + bio->bi_iter.bi_sector + sectors > conf->reshape_progress) { + /* + * IO spans the reshape position. Need to wait for reshape to + * pass + */ + raid10_log(conf->mddev, "wait reshape"); + allow_barrier(conf); + wait_event(conf->wait_barrier, + conf->reshape_progress <= bio->bi_iter.bi_sector || + conf->reshape_progress >= bio->bi_iter.bi_sector + + sectors); + wait_barrier(conf); + } + +read_again: + rdev = read_balance(conf, r10_bio, &max_sectors); + if (!rdev) { + raid_end_bio_io(r10_bio); + return; + } + slot = r10_bio->read_slot; + + read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev); + bio_trim(read_bio, r10_bio->sector - bio->bi_iter.bi_sector, + max_sectors); + + r10_bio->devs[slot].bio = read_bio; + r10_bio->devs[slot].rdev = rdev; + + read_bio->bi_iter.bi_sector = r10_bio->devs[slot].addr + + choose_data_offset(r10_bio, rdev); + read_bio->bi_bdev = rdev->bdev; + read_bio->bi_end_io = raid10_end_read_request; + bio_set_op_attrs(read_bio, op, do_sync); + if (test_bit(FailFast, &rdev->flags) && + test_bit(R10BIO_FailFast, &r10_bio->state)) + read_bio->bi_opf |= MD_FAILFAST; + read_bio->bi_private = r10_bio; + + if (mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev), + read_bio, disk_devt(mddev->gendisk), + r10_bio->sector); + if (max_sectors < r10_bio->sectors) { + /* + * Could not read all from this device, so we will need another + * r10_bio. + */ + sectors_handled = (r10_bio->sector + max_sectors + - bio->bi_iter.bi_sector); + r10_bio->sectors = max_sectors; + spin_lock_irq(&conf->device_lock); + if (bio->bi_phys_segments == 0) + bio->bi_phys_segments = 2; + else + bio->bi_phys_segments++; + spin_unlock_irq(&conf->device_lock); + /* + * Cannot call generic_make_request directly as that will be + * queued in __generic_make_request and subsequent + * mempool_alloc might block waiting for it. so hand bio over + * to raid10d. + */ + reschedule_retry(r10_bio); + + r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO); + + r10_bio->master_bio = bio; + r10_bio->sectors = bio_sectors(bio) - sectors_handled; + r10_bio->state = 0; + r10_bio->mddev = mddev; + r10_bio->sector = bio->bi_iter.bi_sector + sectors_handled; + goto read_again; + } else + generic_make_request(read_bio); + return; +} + +static void raid10_write_request(struct mddev *mddev, struct bio *bio, + struct r10bio *r10_bio) +{ + struct r10conf *conf = mddev->private; int i; const int op = bio_op(bio); - const int rw = bio_data_dir(bio); const unsigned long do_sync = (bio->bi_opf & REQ_SYNC); const unsigned long do_fua = (bio->bi_opf & REQ_FUA); unsigned long flags; struct md_rdev *blocked_rdev; struct blk_plug_cb *cb; struct raid10_plug_cb *plug = NULL; + sector_t sectors; int sectors_handled; int max_sectors; - int sectors; md_write_start(mddev, bio); @@ -1118,8 +1217,9 @@ static void __make_request(struct mddev *mddev, struct bio *bio) while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && bio->bi_iter.bi_sector < conf->reshape_progress && bio->bi_iter.bi_sector + sectors > conf->reshape_progress) { - /* IO spans the reshape position. Need to wait for - * reshape to pass + /* + * IO spans the reshape position. Need to wait for reshape to + * pass */ raid10_log(conf->mddev, "wait reshape"); allow_barrier(conf); @@ -1129,8 +1229,8 @@ static void __make_request(struct mddev *mddev, struct bio *bio) sectors); wait_barrier(conf); } + if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && - bio_data_dir(bio) == WRITE && (mddev->reshape_backwards ? (bio->bi_iter.bi_sector < conf->reshape_safe && bio->bi_iter.bi_sector + sectors > conf->reshape_progress) @@ -1148,98 +1248,6 @@ static void __make_request(struct mddev *mddev, struct bio *bio) conf->reshape_safe = mddev->reshape_position; } - r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO); - - r10_bio->master_bio = bio; - r10_bio->sectors = sectors; - - r10_bio->mddev = mddev; - r10_bio->sector = bio->bi_iter.bi_sector; - r10_bio->state = 0; - - /* We might need to issue multiple reads to different - * devices if there are bad blocks around, so we keep - * track of the number of reads in bio->bi_phys_segments. - * If this is 0, there is only one r10_bio and no locking - * will be needed when the request completes. If it is - * non-zero, then it is the number of not-completed requests. - */ - bio->bi_phys_segments = 0; - bio_clear_flag(bio, BIO_SEG_VALID); - - if (rw == READ) { - /* - * read balancing logic: - */ - struct md_rdev *rdev; - int slot; - -read_again: - rdev = read_balance(conf, r10_bio, &max_sectors); - if (!rdev) { - raid_end_bio_io(r10_bio); - return; - } - slot = r10_bio->read_slot; - - read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev); - bio_trim(read_bio, r10_bio->sector - bio->bi_iter.bi_sector, - max_sectors); - - r10_bio->devs[slot].bio = read_bio; - r10_bio->devs[slot].rdev = rdev; - - read_bio->bi_iter.bi_sector = r10_bio->devs[slot].addr + - choose_data_offset(r10_bio, rdev); - read_bio->bi_bdev = rdev->bdev; - read_bio->bi_end_io = raid10_end_read_request; - bio_set_op_attrs(read_bio, op, do_sync); - if (test_bit(FailFast, &rdev->flags) && - test_bit(R10BIO_FailFast, &r10_bio->state)) - read_bio->bi_opf |= MD_FAILFAST; - read_bio->bi_private = r10_bio; - - if (mddev->gendisk) - trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev), - read_bio, disk_devt(mddev->gendisk), - r10_bio->sector); - if (max_sectors < r10_bio->sectors) { - /* Could not read all from this device, so we will - * need another r10_bio. - */ - sectors_handled = (r10_bio->sector + max_sectors - - bio->bi_iter.bi_sector); - r10_bio->sectors = max_sectors; - spin_lock_irq(&conf->device_lock); - if (bio->bi_phys_segments == 0) - bio->bi_phys_segments = 2; - else - bio->bi_phys_segments++; - spin_unlock_irq(&conf->device_lock); - /* Cannot call generic_make_request directly - * as that will be queued in __generic_make_request - * and subsequent mempool_alloc might block - * waiting for it. so hand bio over to raid10d. - */ - reschedule_retry(r10_bio); - - r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO); - - r10_bio->master_bio = bio; - r10_bio->sectors = bio_sectors(bio) - sectors_handled; - r10_bio->state = 0; - r10_bio->mddev = mddev; - r10_bio->sector = bio->bi_iter.bi_sector + - sectors_handled; - goto read_again; - } else - generic_make_request(read_bio); - return; - } - - /* - * WRITE: - */ if (conf->pending_count >= max_queued_requests) { md_wakeup_thread(mddev->thread); raid10_log(mddev, "wait queued"); @@ -1300,8 +1308,7 @@ retry_write: int bad_sectors; int is_bad; - is_bad = is_badblock(rdev, dev_sector, - max_sectors, + is_bad = is_badblock(rdev, dev_sector, max_sectors, &first_bad, &bad_sectors); if (is_bad < 0) { /* Mustn't write here until the bad block @@ -1405,8 +1412,7 @@ retry_write: r10_bio->devs[i].bio = mbio; mbio->bi_iter.bi_sector = (r10_bio->devs[i].addr+ - choose_data_offset(r10_bio, - rdev)); + choose_data_offset(r10_bio, rdev)); mbio->bi_bdev = rdev->bdev; mbio->bi_end_io = raid10_end_write_request; bio_set_op_attrs(mbio, op, do_sync | do_fua); @@ -1457,8 +1463,7 @@ retry_write: r10_bio->devs[i].repl_bio = mbio; mbio->bi_iter.bi_sector = (r10_bio->devs[i].addr + - choose_data_offset( - r10_bio, rdev)); + choose_data_offset(r10_bio, rdev)); mbio->bi_bdev = rdev->bdev; mbio->bi_end_io = raid10_end_write_request; bio_set_op_attrs(mbio, op, do_sync | do_fua); @@ -1503,6 +1508,36 @@ retry_write: one_write_done(r10_bio); } +static void __make_request(struct mddev *mddev, struct bio *bio) +{ + struct r10conf *conf = mddev->private; + struct r10bio *r10_bio; + + r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO); + + r10_bio->master_bio = bio; + r10_bio->sectors = bio_sectors(bio); + + r10_bio->mddev = mddev; + r10_bio->sector = bio->bi_iter.bi_sector; + r10_bio->state = 0; + + /* + * We might need to issue multiple reads to different devices if there + * are bad blocks around, so we keep track of the number of reads in + * bio->bi_phys_segments. If this is 0, there is only one r10_bio and + * no locking will be needed when the request completes. If it is + * non-zero, then it is the number of not-completed requests. + */ + bio->bi_phys_segments = 0; + bio_clear_flag(bio, BIO_SEG_VALID); + + if (bio_data_dir(bio) == READ) + raid10_read_request(mddev, bio, r10_bio); + else + raid10_write_request(mddev, bio, r10_bio); +} + static void raid10_make_request(struct mddev *mddev, struct bio *bio) { struct r10conf *conf = mddev->private; diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index d7bfb6fc8aef..0e8ed2c327b0 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -1682,8 +1682,7 @@ out: static struct stripe_head * r5c_recovery_alloc_stripe(struct r5conf *conf, - sector_t stripe_sect, - sector_t log_start) + sector_t stripe_sect) { struct stripe_head *sh; @@ -1692,7 +1691,6 @@ r5c_recovery_alloc_stripe(struct r5conf *conf, return NULL; /* no more stripe available */ r5l_recovery_reset_stripe(sh); - sh->log_start = log_start; return sh; } @@ -1862,7 +1860,7 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log, stripe_sect); if (!sh) { - sh = r5c_recovery_alloc_stripe(conf, stripe_sect, ctx->pos); + sh = r5c_recovery_alloc_stripe(conf, stripe_sect); /* * cannot get stripe from raid5_get_active_stripe * try replay some stripes @@ -1871,7 +1869,7 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log, r5c_recovery_replay_stripes( cached_stripe_list, ctx); sh = r5c_recovery_alloc_stripe( - conf, stripe_sect, ctx->pos); + conf, stripe_sect); } if (!sh) { pr_debug("md/raid:%s: Increasing stripe cache size to %d to recovery data on journal.\n", @@ -1879,8 +1877,8 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log, conf->min_nr_stripes * 2); raid5_set_cache_size(mddev, conf->min_nr_stripes * 2); - sh = r5c_recovery_alloc_stripe( - conf, stripe_sect, ctx->pos); + sh = r5c_recovery_alloc_stripe(conf, + stripe_sect); } if (!sh) { pr_err("md/raid:%s: Cannot get enough stripes due to memory pressure. Recovery failed.\n", @@ -1894,7 +1892,6 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log, if (!test_bit(STRIPE_R5C_CACHING, &sh->state) && test_bit(R5_Wantwrite, &sh->dev[sh->pd_idx].flags)) { r5l_recovery_replay_one_stripe(conf, sh, ctx); - sh->log_start = ctx->pos; list_move_tail(&sh->lru, cached_stripe_list); } r5l_recovery_load_data(log, sh, ctx, payload, @@ -1933,8 +1930,6 @@ static void r5c_recovery_load_one_stripe(struct r5l_log *log, set_bit(R5_UPTODATE, &dev->flags); } } - list_add_tail(&sh->r5c, &log->stripe_in_journal_list); - atomic_inc(&log->stripe_in_journal_count); } /* @@ -2070,6 +2065,7 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log, struct stripe_head *sh, *next; struct mddev *mddev = log->rdev->mddev; struct page *page; + sector_t next_checkpoint = MaxSector; page = alloc_page(GFP_KERNEL); if (!page) { @@ -2078,6 +2074,8 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log, return -ENOMEM; } + WARN_ON(list_empty(&ctx->cached_list)); + list_for_each_entry_safe(sh, next, &ctx->cached_list, lru) { struct r5l_meta_block *mb; int i; @@ -2123,12 +2121,15 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log, sync_page_io(log->rdev, ctx->pos, PAGE_SIZE, page, REQ_OP_WRITE, REQ_FUA, false); sh->log_start = ctx->pos; + list_add_tail(&sh->r5c, &log->stripe_in_journal_list); + atomic_inc(&log->stripe_in_journal_count); ctx->pos = write_pos; ctx->seq += 1; - + next_checkpoint = sh->log_start; list_del_init(&sh->lru); raid5_release_stripe(sh); } + log->next_checkpoint = next_checkpoint; __free_page(page); return 0; } @@ -2139,7 +2140,6 @@ static int r5l_recovery_log(struct r5l_log *log) struct r5l_recovery_ctx ctx; int ret; sector_t pos; - struct stripe_head *sh; ctx.pos = log->last_checkpoint; ctx.seq = log->last_cp_seq; @@ -2164,16 +2164,13 @@ static int r5l_recovery_log(struct r5l_log *log) log->next_checkpoint = ctx.pos; r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq++); ctx.pos = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS); - } else { - sh = list_last_entry(&ctx.cached_list, struct stripe_head, lru); - log->next_checkpoint = sh->log_start; } if ((ctx.data_only_stripes == 0) && (ctx.data_parity_stripes == 0)) pr_debug("md/raid:%s: starting from clean shutdown\n", mdname(mddev)); else { - pr_debug("md/raid:%s: recoverying %d data-only stripes and %d data-parity stripes\n", + pr_debug("md/raid:%s: recovering %d data-only stripes and %d data-parity stripes\n", mdname(mddev), ctx.data_only_stripes, ctx.data_parity_stripes); @@ -2418,9 +2415,6 @@ void r5c_finish_stripe_write_out(struct r5conf *conf, if (do_wakeup) wake_up(&conf->wait_for_overlap); - if (conf->log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_THROUGH) - return; - spin_lock_irq(&conf->log->stripe_in_journal_lock); list_del_init(&sh->r5c); spin_unlock_irq(&conf->log->stripe_in_journal_lock); @@ -2639,14 +2633,16 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) spin_lock_init(&log->stripe_in_journal_lock); atomic_set(&log->stripe_in_journal_count, 0); + rcu_assign_pointer(conf->log, log); + if (r5l_load_log(log)) goto error; - rcu_assign_pointer(conf->log, log); set_bit(MD_HAS_JOURNAL, &conf->mddev->flags); return 0; error: + rcu_assign_pointer(conf->log, NULL); md_unregister_thread(&log->reclaim_thread); reclaim_thread: mempool_destroy(log->meta_pool); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 06d7279bdd04..36c13e4be9c9 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -62,6 +62,8 @@ #include "raid0.h" #include "bitmap.h" +#define UNSUPPORTED_MDDEV_FLAGS (1L << MD_FAILFAST_SUPPORTED) + #define cpu_to_group(cpu) cpu_to_node(cpu) #define ANY_GROUP NUMA_NO_NODE @@ -7829,8 +7831,9 @@ static void *raid5_takeover_raid1(struct mddev *mddev) mddev->new_chunk_sectors = chunksect; ret = setup_conf(mddev); - if (!IS_ERR_VALUE(ret)) - clear_bit(MD_FAILFAST_SUPPORTED, &mddev->flags); + if (!IS_ERR(ret)) + mddev_clear_unsupported_flags(mddev, + UNSUPPORTED_MDDEV_FLAGS); return ret; } diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c index b8c293373ecc..a306de4318d7 100644 --- a/drivers/net/appletalk/ipddp.c +++ b/drivers/net/appletalk/ipddp.c @@ -190,7 +190,7 @@ static netdev_tx_t ipddp_xmit(struct sk_buff *skb, struct net_device *dev) */ static int ipddp_create(struct ipddp_route *new_rt) { - struct ipddp_route *rt = kmalloc(sizeof(*rt), GFP_KERNEL); + struct ipddp_route *rt = kzalloc(sizeof(*rt), GFP_KERNEL); if (rt == NULL) return -ENOMEM; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 9ec33b51a0ed..2ce7ae97ac91 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -393,7 +393,7 @@ static int bcm_sf2_sw_mdio_read(struct mii_bus *bus, int addr, int regnum) if (addr == BRCM_PSEUDO_PHY_ADDR && priv->indir_phy_mask & BIT(addr)) return bcm_sf2_sw_indir_rw(priv, 1, addr, regnum, 0); else - return mdiobus_read(priv->master_mii_bus, addr, regnum); + return mdiobus_read_nested(priv->master_mii_bus, addr, regnum); } static int bcm_sf2_sw_mdio_write(struct mii_bus *bus, int addr, int regnum, @@ -407,7 +407,7 @@ static int bcm_sf2_sw_mdio_write(struct mii_bus *bus, int addr, int regnum, if (addr == BRCM_PSEUDO_PHY_ADDR && priv->indir_phy_mask & BIT(addr)) bcm_sf2_sw_indir_rw(priv, 0, addr, regnum, val); else - mdiobus_write(priv->master_mii_bus, addr, regnum, val); + mdiobus_write_nested(priv->master_mii_bus, addr, regnum, val); return 0; } @@ -982,6 +982,7 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) const char *reg_names[BCM_SF2_REGS_NUM] = BCM_SF2_REGS_NAME; struct device_node *dn = pdev->dev.of_node; struct b53_platform_data *pdata; + struct dsa_switch_ops *ops; struct bcm_sf2_priv *priv; struct b53_device *dev; struct dsa_switch *ds; @@ -995,6 +996,10 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; + ops = devm_kzalloc(&pdev->dev, sizeof(*ops), GFP_KERNEL); + if (!ops) + return -ENOMEM; + dev = b53_switch_alloc(&pdev->dev, &bcm_sf2_io_ops, priv); if (!dev) return -ENOMEM; @@ -1014,6 +1019,8 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) ds = dev->ds; /* Override the parts that are non-standard wrt. normal b53 devices */ + memcpy(ops, ds->ops, sizeof(*ops)); + ds->ops = ops; ds->ops->get_tag_protocol = bcm_sf2_sw_get_tag_protocol; ds->ops->setup = bcm_sf2_sw_setup; ds->ops->get_phy_flags = bcm_sf2_sw_get_phy_flags; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 155190db682d..9943629fcbf9 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -539,6 +539,7 @@ static irqreturn_t xgbe_isr(int irq, void *data) } } +isr_done: /* If there is not a separate AN irq, handle it here */ if (pdata->dev_irq == pdata->an_irq) pdata->phy_if.an_isr(irq, pdata); @@ -551,7 +552,6 @@ static irqreturn_t xgbe_isr(int irq, void *data) if (pdata->vdata->i2c_support && (pdata->dev_irq == pdata->i2c_irq)) pdata->i2c_if.i2c_isr(irq, pdata); -isr_done: return IRQ_HANDLED; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 185e9e047aa9..ae42de4fdddf 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -8720,11 +8720,14 @@ static void tg3_free_consistent(struct tg3 *tp) tg3_mem_rx_release(tp); tg3_mem_tx_release(tp); + /* Protect tg3_get_stats64() from reading freed tp->hw_stats. */ + tg3_full_lock(tp, 0); if (tp->hw_stats) { dma_free_coherent(&tp->pdev->dev, sizeof(struct tg3_hw_stats), tp->hw_stats, tp->stats_mapping); tp->hw_stats = NULL; } + tg3_full_unlock(tp); } /* diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 225e9a4877d7..ec010ced6c99 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -275,8 +275,7 @@ static int be_dev_mac_add(struct be_adapter *adapter, u8 *mac) /* Check if mac has already been added as part of uc-list */ for (i = 0; i < adapter->uc_macs; i++) { - if (ether_addr_equal((u8 *)&adapter->uc_list[i * ETH_ALEN], - mac)) { + if (ether_addr_equal(adapter->uc_list[i].mac, mac)) { /* mac already added, skip addition */ adapter->pmac_id[0] = adapter->pmac_id[i + 1]; return 0; @@ -1655,14 +1654,12 @@ static void be_clear_mc_list(struct be_adapter *adapter) static int be_uc_mac_add(struct be_adapter *adapter, int uc_idx) { - if (ether_addr_equal((u8 *)&adapter->uc_list[uc_idx * ETH_ALEN], - adapter->dev_mac)) { + if (ether_addr_equal(adapter->uc_list[uc_idx].mac, adapter->dev_mac)) { adapter->pmac_id[uc_idx + 1] = adapter->pmac_id[0]; return 0; } - return be_cmd_pmac_add(adapter, - (u8 *)&adapter->uc_list[uc_idx * ETH_ALEN], + return be_cmd_pmac_add(adapter, adapter->uc_list[uc_idx].mac, adapter->if_handle, &adapter->pmac_id[uc_idx + 1], 0); } @@ -1698,9 +1695,8 @@ static void be_set_uc_list(struct be_adapter *adapter) } if (adapter->update_uc_list) { - i = 1; /* First slot is claimed by the Primary MAC */ - /* cache the uc-list in adapter array */ + i = 0; netdev_for_each_uc_addr(ha, netdev) { ether_addr_copy(adapter->uc_list[i].mac, ha->addr); i++; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index a761001308dc..1515abaa5ac9 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3962,8 +3962,8 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring) PAGE_SIZE, DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); - __page_frag_drain(buffer_info->page, 0, - buffer_info->pagecnt_bias); + __page_frag_cache_drain(buffer_info->page, + buffer_info->pagecnt_bias); buffer_info->page = NULL; } @@ -6991,7 +6991,7 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, PAGE_SIZE, DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); - __page_frag_drain(page, 0, rx_buffer->pagecnt_bias); + __page_frag_cache_drain(page, rx_buffer->pagecnt_bias); } /* clear contents of rx_buffer */ diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index edbe200ac2fa..4910d9af1933 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2277,7 +2277,7 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) if (priv->tx_ring_num[TX_XDP] && !mlx4_en_check_xdp_mtu(dev, new_mtu)) - return -ENOTSUPP; + return -EOPNOTSUPP; dev->mtu = new_mtu; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 1236b27b1493..2b7dd315020c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3675,14 +3675,8 @@ static void mlx5e_nic_init(struct mlx5_core_dev *mdev, static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) { - struct mlx5_core_dev *mdev = priv->mdev; - struct mlx5_eswitch *esw = mdev->priv.eswitch; - mlx5e_vxlan_cleanup(priv); - if (MLX5_CAP_GEN(mdev, vport_group_manager)) - mlx5_eswitch_unregister_vport_rep(esw, 0); - if (priv->xdp_prog) bpf_prog_put(priv->xdp_prog); } @@ -3807,9 +3801,14 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) static void mlx5e_nic_disable(struct mlx5e_priv *priv) { + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_eswitch *esw = mdev->priv.eswitch; + queue_work(priv->wq, &priv->set_rx_mode_work); + if (MLX5_CAP_GEN(mdev, vport_group_manager)) + mlx5_eswitch_unregister_vport_rep(esw, 0); mlx5e_disable_async_events(priv); - mlx5_lag_remove(priv->mdev); + mlx5_lag_remove(mdev); } static const struct mlx5e_profile mlx5e_nic_profile = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c index 1fffe48a93cc..cbfac06b7ffd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c @@ -109,7 +109,6 @@ static bool mlx5e_am_on_top(struct mlx5e_rx_am *am) switch (am->tune_state) { case MLX5E_AM_PARKING_ON_TOP: case MLX5E_AM_PARKING_TIRED: - WARN_ONCE(true, "mlx5e_am_on_top: PARKING\n"); return true; case MLX5E_AM_GOING_RIGHT: return (am->steps_left > 1) && (am->steps_right == 1); @@ -123,7 +122,6 @@ static void mlx5e_am_turn(struct mlx5e_rx_am *am) switch (am->tune_state) { case MLX5E_AM_PARKING_ON_TOP: case MLX5E_AM_PARKING_TIRED: - WARN_ONCE(true, "mlx5e_am_turn: PARKING\n"); break; case MLX5E_AM_GOING_RIGHT: am->tune_state = MLX5E_AM_GOING_LEFT; @@ -144,7 +142,6 @@ static int mlx5e_am_step(struct mlx5e_rx_am *am) switch (am->tune_state) { case MLX5E_AM_PARKING_ON_TOP: case MLX5E_AM_PARKING_TIRED: - WARN_ONCE(true, "mlx5e_am_step: PARKING\n"); break; case MLX5E_AM_GOING_RIGHT: if (am->profile_ix == (MLX5E_PARAMS_AM_NUM_PROFILES - 1)) @@ -282,10 +279,8 @@ static void mlx5e_am_calc_stats(struct mlx5e_rx_am_sample *start, u32 delta_us = ktime_us_delta(end->time, start->time); unsigned int npkts = end->pkt_ctr - start->pkt_ctr; - if (!delta_us) { - WARN_ONCE(true, "mlx5e_am_calc_stats: delta_us=0\n"); + if (!delta_us) return; - } curr_stats->ppms = (npkts * USEC_PER_MSEC) / delta_us; curr_stats->epms = (MLX5E_AM_NEVENTS * USEC_PER_MSEC) / delta_us; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index f8829b517156..118cea5e5489 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -161,15 +161,21 @@ static void mlx5e_detach_encap(struct mlx5e_priv *priv, } } +/* we get here also when setting rule to the FW failed, etc. It means that the + * flow rule itself might not exist, but some offloading related to the actions + * should be cleaned. + */ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_fc *counter = NULL; - counter = mlx5_flow_rule_counter(flow->rule); - - mlx5_del_flow_rules(flow->rule); + if (!IS_ERR(flow->rule)) { + counter = mlx5_flow_rule_counter(flow->rule); + mlx5_del_flow_rules(flow->rule); + mlx5_fc_destroy(priv->mdev, counter); + } if (esw && esw->mode == SRIOV_OFFLOADS) { mlx5_eswitch_del_vlan_action(esw, flow->attr); @@ -177,8 +183,6 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, mlx5e_detach_encap(priv, flow); } - mlx5_fc_destroy(priv->mdev, counter); - if (!mlx5e_tc_num_filters(priv) && (priv->fs.tc.t)) { mlx5_destroy_flow_table(priv->fs.tc.t); priv->fs.tc.t = NULL; @@ -225,6 +229,11 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers); + struct flow_dissector_key_control *enc_control = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_CONTROL, + f->key); + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) { struct flow_dissector_key_ports *key = skb_flow_dissector_target(f->dissector, @@ -237,28 +246,34 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, /* Full udp dst port must be given */ if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst))) - return -EOPNOTSUPP; - - /* udp src port isn't supported */ - if (memchr_inv(&mask->src, 0, sizeof(mask->src))) - return -EOPNOTSUPP; + goto vxlan_match_offload_err; if (mlx5e_vxlan_lookup_port(priv, be16_to_cpu(key->dst)) && MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) parse_vxlan_attr(spec, f); - else + else { + netdev_warn(priv->netdev, + "%d isn't an offloaded vxlan udp dport\n", be16_to_cpu(key->dst)); return -EOPNOTSUPP; + } MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_dport, ntohs(mask->dst)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_dport, ntohs(key->dst)); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, + udp_sport, ntohs(mask->src)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, + udp_sport, ntohs(key->src)); } else { /* udp dst port must be given */ - return -EOPNOTSUPP; +vxlan_match_offload_err: + netdev_warn(priv->netdev, + "IP tunnel decap offload supported only for vxlan, must set UDP dport\n"); + return -EOPNOTSUPP; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { + if (enc_control->addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { struct flow_dissector_key_ipv4_addrs *key = skb_flow_dissector_target(f->dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, @@ -280,10 +295,10 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, MLX5_SET(fte_match_set_lyr_2_4, headers_v, dst_ipv4_dst_ipv6.ipv4_layout.ipv4, ntohl(key->dst)); - } - MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IP); + MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IP); + } /* Enforce DMAC when offloading incoming tunneled flows. * Flow counters require a match on the DMAC. @@ -346,6 +361,9 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, if (parse_tunnel_attr(priv, spec, f)) return -EOPNOTSUPP; break; + case FLOW_DISSECTOR_KEY_IPV6_ADDRS: + netdev_warn(priv->netdev, + "IPv6 tunnel decap offload isn't supported\n"); default: return -EOPNOTSUPP; } @@ -375,6 +393,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1); MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag, key->flags & FLOW_DIS_IS_FRAGMENT); + + /* the HW doesn't need L3 inline to match on frag=no */ + if (key->flags & FLOW_DIS_IS_FRAGMENT) + *min_inline = MLX5_INLINE_MODE_IP; } } @@ -647,17 +669,14 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, #if IS_ENABLED(CONFIG_INET) rt = ip_route_output_key(dev_net(mirred_dev), fl4); - if (IS_ERR(rt)) { - pr_warn("%s: no route to %pI4\n", __func__, &fl4->daddr); - return -EOPNOTSUPP; - } + if (IS_ERR(rt)) + return PTR_ERR(rt); #else return -EOPNOTSUPP; #endif if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev)) { - pr_warn("%s: Can't offload the flow, netdevices aren't on the same HW e-switch\n", - __func__); + pr_warn("%s: can't offload, devices not on same HW e-switch\n", __func__); ip_rt_put(rt); return -EOPNOTSUPP; } @@ -718,12 +737,12 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, struct net_device **out_dev) { int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); + struct neighbour *n = NULL; struct flowi4 fl4 = {}; - struct neighbour *n; char *encap_header; int encap_size; - __be32 saddr; - int ttl; + __be32 saddr = 0; + int ttl = 0; int err; encap_header = kzalloc(max_encap_size, GFP_KERNEL); @@ -750,7 +769,8 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, e->out_dev = *out_dev; if (!(n->nud_state & NUD_VALID)) { - err = -ENOTSUPP; + pr_warn("%s: can't offload, neighbour to %pI4 invalid\n", __func__, &fl4.daddr); + err = -EOPNOTSUPP; goto out; } @@ -772,6 +792,8 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, err = mlx5_encap_alloc(priv->mdev, e->tunnel_type, encap_size, encap_header, &e->encap_id); out: + if (err && n) + neigh_release(n); kfree(encap_header); return err; } @@ -792,9 +814,17 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, int tunnel_type; int err; - /* udp dst port must be given */ + /* udp dst port must be set */ if (!memchr_inv(&key->tp_dst, 0, sizeof(key->tp_dst))) + goto vxlan_encap_offload_err; + + /* setting udp src port isn't supported */ + if (memchr_inv(&key->tp_src, 0, sizeof(key->tp_src))) { +vxlan_encap_offload_err: + netdev_warn(priv->netdev, + "must set udp dst port and not set udp src port\n"); return -EOPNOTSUPP; + } if (mlx5e_vxlan_lookup_port(priv, be16_to_cpu(key->tp_dst)) && MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) { @@ -802,6 +832,8 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, info.tun_id = tunnel_id_to_key32(key->tun_id); tunnel_type = MLX5_HEADER_TYPE_VXLAN; } else { + netdev_warn(priv->netdev, + "%d isn't an offloaded vxlan udp dport\n", be16_to_cpu(key->tp_dst)); return -EOPNOTSUPP; } @@ -809,6 +841,9 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, case AF_INET: info.daddr = key->u.ipv4.dst; break; + case AF_INET6: + netdev_warn(priv->netdev, + "IPv6 tunnel encap offload isn't supported\n"); default: return -EOPNOTSUPP; } @@ -986,7 +1021,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol, if (IS_ERR(flow->rule)) { err = PTR_ERR(flow->rule); - goto err_free; + goto err_del_rule; } err = rhashtable_insert_fast(&tc->ht, &flow->node, @@ -997,7 +1032,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol, goto out; err_del_rule: - mlx5_del_flow_rules(flow->rule); + mlx5e_tc_del_flow(priv, flow); err_free: kfree(flow); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 6547f22e6b9b..d01e9f21d469 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1195,7 +1195,8 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, { int err = 0; - mlx5_drain_health_wq(dev); + if (cleanup) + mlx5_drain_health_wq(dev); mutex_lock(&dev->intf_state_mutex); if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) { @@ -1359,9 +1360,10 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, mlx5_enter_error_state(dev); mlx5_unload_one(dev, priv, false); - /* In case of kernel call save the pci state */ + /* In case of kernel call save the pci state and drain the health wq */ if (state) { pci_save_state(pdev); + mlx5_drain_health_wq(dev); mlx5_pci_disable_device(dev); } diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 44389c90056a..8f1623bf2134 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -696,7 +696,7 @@ enum rtl_tx_desc_bit_1 { enum rtl_rx_desc_bit { /* Rx private */ PID1 = (1 << 18), /* Protocol ID bit 1/2 */ - PID0 = (1 << 17), /* Protocol ID bit 2/2 */ + PID0 = (1 << 17), /* Protocol ID bit 0/2 */ #define RxProtoUDP (PID1) #define RxProtoTCP (PID0) diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 00fafabab1d0..f729a6b43958 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -574,6 +574,7 @@ static struct sh_eth_cpu_data r8a7740_data = { .rpadir_value = 2 << 16, .no_trimd = 1, .no_ade = 1, + .hw_crc = 1, .tsu = 1, .select_mii = 1, .shift_rd0 = 1, @@ -802,7 +803,7 @@ static struct sh_eth_cpu_data sh7734_data = { .ecsr_value = ECSR_ICD | ECSR_MPD, .ecsipr_value = ECSIPR_LCHNGIP | ECSIPR_ICDIP | ECSIPR_MPDIP, - .eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff, + .eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003f07ff, .tx_check = EESR_TC1 | EESR_FTC, .eesr_err_check = EESR_TWB1 | EESR_TWB | EESR_TABT | EESR_RABT | @@ -832,7 +833,7 @@ static struct sh_eth_cpu_data sh7763_data = { .ecsr_value = ECSR_ICD | ECSR_MPD, .ecsipr_value = ECSIPR_LCHNGIP | ECSIPR_ICDIP | ECSIPR_MPDIP, - .eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff, + .eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003f07ff, .tx_check = EESR_TC1 | EESR_FTC, .eesr_err_check = EESR_TWB1 | EESR_TWB | EESR_TABT | EESR_RABT | diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 39eb7a65bb9f..a276a32d57f2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3319,8 +3319,16 @@ int stmmac_dvr_probe(struct device *device, ndev->max_mtu = JUMBO_LEN; else ndev->max_mtu = SKB_MAX_HEAD(NET_SKB_PAD + NET_IP_ALIGN); - if (priv->plat->maxmtu < ndev->max_mtu) + /* Will not overwrite ndev->max_mtu if plat->maxmtu > ndev->max_mtu + * as well as plat->maxmtu < ndev->min_mtu which is a invalid range. + */ + if ((priv->plat->maxmtu < ndev->max_mtu) && + (priv->plat->maxmtu >= ndev->min_mtu)) ndev->max_mtu = priv->plat->maxmtu; + else if (priv->plat->maxmtu < ndev->min_mtu) + netdev_warn(priv->dev, + "%s: warning: maxmtu having invalid value (%d)\n", + __func__, priv->plat->maxmtu); if (flow_ctrl) priv->flow_ctrl = FLOW_AUTO; /* RX/TX pause on */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index a2831773431a..3da4737620cb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -89,6 +89,9 @@ static void stmmac_default_data(struct plat_stmmacenet_data *plat) /* Set default value for unicast filter entries */ plat->unicast_filter_entries = 1; + + /* Set the maxmtu to a default of JUMBO_LEN */ + plat->maxmtu = JUMBO_LEN; } static int quark_default_data(struct plat_stmmacenet_data *plat, @@ -126,6 +129,9 @@ static int quark_default_data(struct plat_stmmacenet_data *plat, /* Set default value for unicast filter entries */ plat->unicast_filter_entries = 1; + /* Set the maxmtu to a default of JUMBO_LEN */ + plat->maxmtu = JUMBO_LEN; + return 0; } diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index d361835b315d..8dbd59baa34d 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -279,6 +279,7 @@ config MARVELL_PHY config MESON_GXL_PHY tristate "Amlogic Meson GXL Internal PHY" + depends on ARCH_MESON || COMPILE_TEST ---help--- Currently has a driver for the Amlogic Meson GXL Internal PHY diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 1b639242f9e2..e84ae084e259 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -29,6 +29,7 @@ #define MII_DP83867_MICR 0x12 #define MII_DP83867_ISR 0x13 #define DP83867_CTRL 0x1f +#define DP83867_CFG3 0x1e /* Extended Registers */ #define DP83867_RGMIICTL 0x0032 @@ -98,6 +99,8 @@ static int dp83867_config_intr(struct phy_device *phydev) micr_status |= (MII_DP83867_MICR_AN_ERR_INT_EN | MII_DP83867_MICR_SPEED_CHNG_INT_EN | + MII_DP83867_MICR_AUTONEG_COMP_INT_EN | + MII_DP83867_MICR_LINK_STS_CHNG_INT_EN | MII_DP83867_MICR_DUP_MODE_CHNG_INT_EN | MII_DP83867_MICR_SLEEP_MODE_CHNG_INT_EN); @@ -214,6 +217,13 @@ static int dp83867_config_init(struct phy_device *phydev) } } + /* Enable Interrupt output INT_OE in CFG3 register */ + if (phy_interrupt_is_valid(phydev)) { + val = phy_read(phydev, DP83867_CFG3); + val |= BIT(7); + phy_write(phydev, DP83867_CFG3, val); + } + return 0; } diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index e269262471a4..0b78210c0fa7 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -1192,7 +1192,8 @@ static int marvell_read_status(struct phy_device *phydev) int err; /* Check the fiber mode first */ - if (phydev->supported & SUPPORTED_FIBRE) { + if (phydev->supported & SUPPORTED_FIBRE && + phydev->interface != PHY_INTERFACE_MODE_SGMII) { err = phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_M1111_FIBER); if (err < 0) goto error; diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 25f93a98863b..48da6e93c3f7 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -1065,6 +1065,15 @@ void phy_state_machine(struct work_struct *work) if (old_link != phydev->link) phydev->state = PHY_CHANGELINK; } + /* + * Failsafe: check that nobody set phydev->link=0 between two + * poll cycles, otherwise we won't leave RUNNING state as long + * as link remains down. + */ + if (!phydev->link && phydev->state == PHY_RUNNING) { + phydev->state = PHY_CHANGELINK; + phydev_err(phydev, "no link in PHY_RUNNING\n"); + } break; case PHY_CHANGELINK: err = phy_read_status(phydev); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 7dc61228c55b..be418563cb18 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3576,39 +3576,87 @@ static bool delay_autosuspend(struct r8152 *tp) return false; } -static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message) +static int rtl8152_rumtime_suspend(struct r8152 *tp) { - struct r8152 *tp = usb_get_intfdata(intf); struct net_device *netdev = tp->netdev; int ret = 0; - mutex_lock(&tp->control); + if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) { + u32 rcr = 0; - if (PMSG_IS_AUTO(message)) { - if (netif_running(netdev) && delay_autosuspend(tp)) { + if (delay_autosuspend(tp)) { ret = -EBUSY; goto out1; } - set_bit(SELECTIVE_SUSPEND, &tp->flags); - } else { - netif_device_detach(netdev); + if (netif_carrier_ok(netdev)) { + u32 ocp_data; + + rcr = ocp_read_dword(tp, MCU_TYPE_PLA, PLA_RCR); + ocp_data = rcr & ~RCR_ACPT_ALL; + ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, ocp_data); + rxdy_gated_en(tp, true); + ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, + PLA_OOB_CTRL); + if (!(ocp_data & RXFIFO_EMPTY)) { + rxdy_gated_en(tp, false); + ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr); + ret = -EBUSY; + goto out1; + } + } + + clear_bit(WORK_ENABLE, &tp->flags); + usb_kill_urb(tp->intr_urb); + + tp->rtl_ops.autosuspend_en(tp, true); + + if (netif_carrier_ok(netdev)) { + napi_disable(&tp->napi); + rtl_stop_rx(tp); + rxdy_gated_en(tp, false); + ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr); + napi_enable(&tp->napi); + } } + set_bit(SELECTIVE_SUSPEND, &tp->flags); + +out1: + return ret; +} + +static int rtl8152_system_suspend(struct r8152 *tp) +{ + struct net_device *netdev = tp->netdev; + int ret = 0; + + netif_device_detach(netdev); + if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) { clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); napi_disable(&tp->napi); - if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { - rtl_stop_rx(tp); - tp->rtl_ops.autosuspend_en(tp, true); - } else { - cancel_delayed_work_sync(&tp->schedule); - tp->rtl_ops.down(tp); - } + cancel_delayed_work_sync(&tp->schedule); + tp->rtl_ops.down(tp); napi_enable(&tp->napi); } -out1: + + return ret; +} + +static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message) +{ + struct r8152 *tp = usb_get_intfdata(intf); + int ret; + + mutex_lock(&tp->control); + + if (PMSG_IS_AUTO(message)) + ret = rtl8152_rumtime_suspend(tp); + else + ret = rtl8152_system_suspend(tp); + mutex_unlock(&tp->control); return ret; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 23dfb0eac098..454f907d419a 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -263,7 +263,9 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_tos = RT_TOS(ip4h->tos), .flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF, + .flowi4_proto = ip4h->protocol, .daddr = ip4h->daddr, + .saddr = ip4h->saddr, }; struct net *net = dev_net(vrf_dev); struct rtable *rt; @@ -1250,6 +1252,8 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev, return -EINVAL; vrf->tb_id = nla_get_u32(data[IFLA_VRF_TABLE]); + if (vrf->tb_id == RT_TABLE_UNSPEC) + return -EINVAL; dev->priv_flags |= IFF_L3MDEV_MASTER; diff --git a/drivers/net/wireless/intersil/orinoco/mic.c b/drivers/net/wireless/intersil/orinoco/mic.c index bc7397d709d3..08bc7822f820 100644 --- a/drivers/net/wireless/intersil/orinoco/mic.c +++ b/drivers/net/wireless/intersil/orinoco/mic.c @@ -16,7 +16,7 @@ /********************************************************************/ int orinoco_mic_init(struct orinoco_private *priv) { - priv->tx_tfm_mic = crypto_alloc_ahash("michael_mic", 0, + priv->tx_tfm_mic = crypto_alloc_shash("michael_mic", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(priv->tx_tfm_mic)) { printk(KERN_DEBUG "orinoco_mic_init: could not allocate " @@ -25,7 +25,7 @@ int orinoco_mic_init(struct orinoco_private *priv) return -ENOMEM; } - priv->rx_tfm_mic = crypto_alloc_ahash("michael_mic", 0, + priv->rx_tfm_mic = crypto_alloc_shash("michael_mic", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(priv->rx_tfm_mic)) { printk(KERN_DEBUG "orinoco_mic_init: could not allocate " @@ -40,17 +40,16 @@ int orinoco_mic_init(struct orinoco_private *priv) void orinoco_mic_free(struct orinoco_private *priv) { if (priv->tx_tfm_mic) - crypto_free_ahash(priv->tx_tfm_mic); + crypto_free_shash(priv->tx_tfm_mic); if (priv->rx_tfm_mic) - crypto_free_ahash(priv->rx_tfm_mic); + crypto_free_shash(priv->rx_tfm_mic); } -int orinoco_mic(struct crypto_ahash *tfm_michael, u8 *key, +int orinoco_mic(struct crypto_shash *tfm_michael, u8 *key, u8 *da, u8 *sa, u8 priority, u8 *data, size_t data_len, u8 *mic) { - AHASH_REQUEST_ON_STACK(req, tfm_michael); - struct scatterlist sg[2]; + SHASH_DESC_ON_STACK(desc, tfm_michael); u8 hdr[ETH_HLEN + 2]; /* size of header + padding */ int err; @@ -67,18 +66,27 @@ int orinoco_mic(struct crypto_ahash *tfm_michael, u8 *key, hdr[ETH_ALEN * 2 + 2] = 0; hdr[ETH_ALEN * 2 + 3] = 0; - /* Use scatter gather to MIC header and data in one go */ - sg_init_table(sg, 2); - sg_set_buf(&sg[0], hdr, sizeof(hdr)); - sg_set_buf(&sg[1], data, data_len); + desc->tfm = tfm_michael; + desc->flags = 0; - if (crypto_ahash_setkey(tfm_michael, key, MIC_KEYLEN)) - return -1; + err = crypto_shash_setkey(tfm_michael, key, MIC_KEYLEN); + if (err) + return err; + + err = crypto_shash_init(desc); + if (err) + return err; + + err = crypto_shash_update(desc, hdr, sizeof(hdr)); + if (err) + return err; + + err = crypto_shash_update(desc, data, data_len); + if (err) + return err; + + err = crypto_shash_final(desc, mic); + shash_desc_zero(desc); - ahash_request_set_tfm(req, tfm_michael); - ahash_request_set_callback(req, 0, NULL, NULL); - ahash_request_set_crypt(req, sg, mic, data_len + sizeof(hdr)); - err = crypto_ahash_digest(req); - ahash_request_zero(req); return err; } diff --git a/drivers/net/wireless/intersil/orinoco/mic.h b/drivers/net/wireless/intersil/orinoco/mic.h index ce731d05cc98..e8724e889219 100644 --- a/drivers/net/wireless/intersil/orinoco/mic.h +++ b/drivers/net/wireless/intersil/orinoco/mic.h @@ -6,6 +6,7 @@ #define _ORINOCO_MIC_H_ #include <linux/types.h> +#include <crypto/hash.h> #define MICHAEL_MIC_LEN 8 @@ -15,7 +16,7 @@ struct crypto_ahash; int orinoco_mic_init(struct orinoco_private *priv); void orinoco_mic_free(struct orinoco_private *priv); -int orinoco_mic(struct crypto_ahash *tfm_michael, u8 *key, +int orinoco_mic(struct crypto_shash *tfm_michael, u8 *key, u8 *da, u8 *sa, u8 priority, u8 *data, size_t data_len, u8 *mic); diff --git a/drivers/net/wireless/intersil/orinoco/orinoco.h b/drivers/net/wireless/intersil/orinoco/orinoco.h index 2f0c84b1c440..5fa1c3e3713f 100644 --- a/drivers/net/wireless/intersil/orinoco/orinoco.h +++ b/drivers/net/wireless/intersil/orinoco/orinoco.h @@ -152,8 +152,8 @@ struct orinoco_private { u8 *wpa_ie; int wpa_ie_len; - struct crypto_ahash *rx_tfm_mic; - struct crypto_ahash *tx_tfm_mic; + struct crypto_shash *rx_tfm_mic; + struct crypto_shash *tx_tfm_mic; unsigned int wpa_enabled:1; unsigned int tkip_cm_active:1; diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c index 0a508649903d..49015b05f3d1 100644 --- a/drivers/net/wireless/realtek/rtlwifi/usb.c +++ b/drivers/net/wireless/realtek/rtlwifi/usb.c @@ -1063,6 +1063,7 @@ int rtl_usb_probe(struct usb_interface *intf, return -ENOMEM; } rtlpriv = hw->priv; + rtlpriv->hw = hw; rtlpriv->usb_data = kzalloc(RTL_USB_MAX_RX_COUNT * sizeof(u32), GFP_KERNEL); if (!rtlpriv->usb_data) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 2fc86dc7a8df..8a3c3e32a704 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1106,12 +1106,7 @@ int nvme_disable_ctrl(struct nvme_ctrl *ctrl, u64 cap) if (ret) return ret; - /* Checking for ctrl->tagset is a trick to avoid sleeping on module - * load, since we only need the quirk on reset_controller. Notice - * that the HGST device needs this delay only in firmware activation - * procedure; unfortunately we have no (easy) way to verify this. - */ - if ((ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY) && ctrl->tagset) + if (ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY) msleep(NVME_QUIRK_DELAY_AMOUNT); return nvme_wait_ready(ctrl, cap, false); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index aa0bc60810a7..fcc9dcfdf675 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1654,13 +1654,12 @@ nvme_fc_map_data(struct nvme_fc_ctrl *ctrl, struct request *rq, struct nvme_fc_fcp_op *op) { struct nvmefc_fcp_req *freq = &op->fcp_req; - u32 map_len = nvme_map_len(rq); enum dma_data_direction dir; int ret; freq->sg_cnt = 0; - if (!map_len) + if (!blk_rq_payload_bytes(rq)) return 0; freq->sg_table.sgl = freq->first_sgl; @@ -1854,7 +1853,7 @@ nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx, if (ret) return ret; - data_len = nvme_map_len(rq); + data_len = blk_rq_payload_bytes(rq); if (data_len) io_dir = ((rq_data_dir(rq) == WRITE) ? NVMEFC_FCP_WRITE : NVMEFC_FCP_READ); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 6377e14586dc..aead6d08ed2c 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -225,14 +225,6 @@ static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector) return (sector >> (ns->lba_shift - 9)); } -static inline unsigned nvme_map_len(struct request *rq) -{ - if (req_op(rq) == REQ_OP_DISCARD) - return sizeof(struct nvme_dsm_range); - else - return blk_rq_bytes(rq); -} - static inline void nvme_cleanup_cmd(struct request *req) { if (req->rq_flags & RQF_SPECIAL_PAYLOAD) { diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 19beeb7b2ac2..3faefabf339c 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -306,11 +306,11 @@ static __le64 **iod_list(struct request *req) return (__le64 **)(iod->sg + blk_rq_nr_phys_segments(req)); } -static int nvme_init_iod(struct request *rq, unsigned size, - struct nvme_dev *dev) +static int nvme_init_iod(struct request *rq, struct nvme_dev *dev) { struct nvme_iod *iod = blk_mq_rq_to_pdu(rq); int nseg = blk_rq_nr_phys_segments(rq); + unsigned int size = blk_rq_payload_bytes(rq); if (nseg > NVME_INT_PAGES || size > NVME_INT_BYTES(dev)) { iod->sg = kmalloc(nvme_iod_alloc_size(dev, size, nseg), GFP_ATOMIC); @@ -420,12 +420,11 @@ static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi) } #endif -static bool nvme_setup_prps(struct nvme_dev *dev, struct request *req, - int total_len) +static bool nvme_setup_prps(struct nvme_dev *dev, struct request *req) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); struct dma_pool *pool; - int length = total_len; + int length = blk_rq_payload_bytes(req); struct scatterlist *sg = iod->sg; int dma_len = sg_dma_len(sg); u64 dma_addr = sg_dma_address(sg); @@ -501,7 +500,7 @@ static bool nvme_setup_prps(struct nvme_dev *dev, struct request *req, } static int nvme_map_data(struct nvme_dev *dev, struct request *req, - unsigned size, struct nvme_command *cmnd) + struct nvme_command *cmnd) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); struct request_queue *q = req->q; @@ -519,7 +518,7 @@ static int nvme_map_data(struct nvme_dev *dev, struct request *req, DMA_ATTR_NO_WARN)) goto out; - if (!nvme_setup_prps(dev, req, size)) + if (!nvme_setup_prps(dev, req)) goto out_unmap; ret = BLK_MQ_RQ_QUEUE_ERROR; @@ -580,7 +579,6 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx, struct nvme_dev *dev = nvmeq->dev; struct request *req = bd->rq; struct nvme_command cmnd; - unsigned map_len; int ret = BLK_MQ_RQ_QUEUE_OK; /* @@ -600,13 +598,12 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx, if (ret != BLK_MQ_RQ_QUEUE_OK) return ret; - map_len = nvme_map_len(req); - ret = nvme_init_iod(req, map_len, dev); + ret = nvme_init_iod(req, dev); if (ret != BLK_MQ_RQ_QUEUE_OK) goto out_free_cmd; if (blk_rq_nr_phys_segments(req)) - ret = nvme_map_data(dev, req, map_len, &cmnd); + ret = nvme_map_data(dev, req, &cmnd); if (ret != BLK_MQ_RQ_QUEUE_OK) goto out_cleanup_iod; diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index f587af345889..557f29b1f1bb 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -981,8 +981,7 @@ static int nvme_rdma_map_sg_fr(struct nvme_rdma_queue *queue, } static int nvme_rdma_map_data(struct nvme_rdma_queue *queue, - struct request *rq, unsigned int map_len, - struct nvme_command *c) + struct request *rq, struct nvme_command *c) { struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); struct nvme_rdma_device *dev = queue->device; @@ -1014,9 +1013,9 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue, } if (count == 1) { - if (rq_data_dir(rq) == WRITE && - map_len <= nvme_rdma_inline_data_size(queue) && - nvme_rdma_queue_idx(queue)) + if (rq_data_dir(rq) == WRITE && nvme_rdma_queue_idx(queue) && + blk_rq_payload_bytes(rq) <= + nvme_rdma_inline_data_size(queue)) return nvme_rdma_map_sg_inline(queue, req, c); if (dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY) @@ -1422,7 +1421,7 @@ static inline bool nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue, struct request *rq) { if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags))) { - struct nvme_command *cmd = (struct nvme_command *)rq->cmd; + struct nvme_command *cmd = nvme_req(rq)->cmd; if (rq->cmd_type != REQ_TYPE_DRV_PRIV || cmd->common.opcode != nvme_fabrics_command || @@ -1444,7 +1443,6 @@ static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, struct nvme_command *c = sqe->data; bool flush = false; struct ib_device *dev; - unsigned int map_len; int ret; WARN_ON_ONCE(rq->tag < 0); @@ -1462,8 +1460,7 @@ static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, blk_mq_start_request(rq); - map_len = nvme_map_len(rq); - ret = nvme_rdma_map_data(queue, rq, map_len, c); + ret = nvme_rdma_map_data(queue, rq, c); if (ret < 0) { dev_err(queue->ctrl->ctrl.device, "Failed to map data (%d)\n", ret); diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 9a507e77eced..90b05c72186c 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -396,9 +396,6 @@ static int rproc_handle_vdev(struct rproc *rproc, struct fw_rsc_vdev *rsc, goto unwind_vring_allocations; } - /* track the rvdevs list reference */ - kref_get(&rvdev->refcount); - list_add_tail(&rvdev->node, &rproc->rvdevs); rproc_add_subdev(rproc, &rvdev->subdev, @@ -889,13 +886,15 @@ static int rproc_fw_boot(struct rproc *rproc, const struct firmware *fw) /* * Create a copy of the resource table. When a virtio device starts * and calls vring_new_virtqueue() the address of the allocated vring - * will be stored in the table_ptr. Before the device is started, - * table_ptr will be copied into device memory. + * will be stored in the cached_table. Before the device is started, + * cached_table will be copied into device memory. */ - rproc->table_ptr = kmemdup(table, tablesz, GFP_KERNEL); - if (!rproc->table_ptr) + rproc->cached_table = kmemdup(table, tablesz, GFP_KERNEL); + if (!rproc->cached_table) goto clean_up; + rproc->table_ptr = rproc->cached_table; + /* reset max_notifyid */ rproc->max_notifyid = -1; @@ -914,16 +913,18 @@ static int rproc_fw_boot(struct rproc *rproc, const struct firmware *fw) } /* - * The starting device has been given the rproc->table_ptr as the + * The starting device has been given the rproc->cached_table as the * resource table. The address of the vring along with the other - * allocated resources (carveouts etc) is stored in table_ptr. + * allocated resources (carveouts etc) is stored in cached_table. * In order to pass this information to the remote device we must copy * this information to device memory. We also update the table_ptr so * that any subsequent changes will be applied to the loaded version. */ loaded_table = rproc_find_loaded_rsc_table(rproc, fw); - if (loaded_table) - memcpy(loaded_table, rproc->table_ptr, tablesz); + if (loaded_table) { + memcpy(loaded_table, rproc->cached_table, tablesz); + rproc->table_ptr = loaded_table; + } /* power up the remote processor */ ret = rproc->ops->start(rproc); @@ -951,7 +952,8 @@ stop_rproc: clean_up_resources: rproc_resource_cleanup(rproc); clean_up: - kfree(rproc->table_ptr); + kfree(rproc->cached_table); + rproc->cached_table = NULL; rproc->table_ptr = NULL; rproc_disable_iommu(rproc); @@ -1185,7 +1187,8 @@ void rproc_shutdown(struct rproc *rproc) rproc_disable_iommu(rproc); /* Free the copy of the resource table */ - kfree(rproc->table_ptr); + kfree(rproc->cached_table); + rproc->cached_table = NULL; rproc->table_ptr = NULL; /* if in crash state, unlock crash handler */ diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c index a79cb5a9e5f2..1cfb775e8e82 100644 --- a/drivers/rpmsg/rpmsg_core.c +++ b/drivers/rpmsg/rpmsg_core.c @@ -453,8 +453,8 @@ int rpmsg_register_device(struct rpmsg_device *rpdev) struct device *dev = &rpdev->dev; int ret; - dev_set_name(&rpdev->dev, "%s:%s", - dev_name(dev->parent), rpdev->id.name); + dev_set_name(&rpdev->dev, "%s.%s.%d.%d", dev_name(dev->parent), + rpdev->id.name, rpdev->src, rpdev->dst); rpdev->dev.bus = &rpmsg_bus; rpdev->dev.release = rpmsg_release_device; diff --git a/drivers/scsi/bfa/bfad.c b/drivers/scsi/bfa/bfad.c index d9e15210b110..5caf5f3ff642 100644 --- a/drivers/scsi/bfa/bfad.c +++ b/drivers/scsi/bfa/bfad.c @@ -64,9 +64,9 @@ int max_rport_logins = BFA_FCS_MAX_RPORT_LOGINS; u32 bfi_image_cb_size, bfi_image_ct_size, bfi_image_ct2_size; u32 *bfi_image_cb, *bfi_image_ct, *bfi_image_ct2; -#define BFAD_FW_FILE_CB "cbfw-3.2.3.0.bin" -#define BFAD_FW_FILE_CT "ctfw-3.2.3.0.bin" -#define BFAD_FW_FILE_CT2 "ct2fw-3.2.3.0.bin" +#define BFAD_FW_FILE_CB "cbfw-3.2.5.1.bin" +#define BFAD_FW_FILE_CT "ctfw-3.2.5.1.bin" +#define BFAD_FW_FILE_CT2 "ct2fw-3.2.5.1.bin" static u32 *bfad_load_fwimg(struct pci_dev *pdev); static void bfad_free_fwimg(void); diff --git a/drivers/scsi/bfa/bfad_drv.h b/drivers/scsi/bfa/bfad_drv.h index f9e862093a25..cfcfff48e8e1 100644 --- a/drivers/scsi/bfa/bfad_drv.h +++ b/drivers/scsi/bfa/bfad_drv.h @@ -58,7 +58,7 @@ #ifdef BFA_DRIVER_VERSION #define BFAD_DRIVER_VERSION BFA_DRIVER_VERSION #else -#define BFAD_DRIVER_VERSION "3.2.25.0" +#define BFAD_DRIVER_VERSION "3.2.25.1" #endif #define BFAD_PROTO_NAME FCPI_NAME diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h index 9ddc9200e0a4..9e4b7709043e 100644 --- a/drivers/scsi/fnic/fnic.h +++ b/drivers/scsi/fnic/fnic.h @@ -248,6 +248,7 @@ struct fnic { struct completion *remove_wait; /* device remove thread blocks */ atomic_t in_flight; /* io counter */ + bool internal_reset_inprogress; u32 _reserved; /* fill hole */ unsigned long state_flags; /* protected by host lock */ enum fnic_state state; diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c index 2544a37ece0a..adb3d5871e74 100644 --- a/drivers/scsi/fnic/fnic_scsi.c +++ b/drivers/scsi/fnic/fnic_scsi.c @@ -2581,6 +2581,19 @@ int fnic_host_reset(struct scsi_cmnd *sc) unsigned long wait_host_tmo; struct Scsi_Host *shost = sc->device->host; struct fc_lport *lp = shost_priv(shost); + struct fnic *fnic = lport_priv(lp); + unsigned long flags; + + spin_lock_irqsave(&fnic->fnic_lock, flags); + if (fnic->internal_reset_inprogress == 0) { + fnic->internal_reset_inprogress = 1; + } else { + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, + "host reset in progress skipping another host reset\n"); + return SUCCESS; + } + spin_unlock_irqrestore(&fnic->fnic_lock, flags); /* * If fnic_reset is successful, wait for fabric login to complete @@ -2601,6 +2614,9 @@ int fnic_host_reset(struct scsi_cmnd *sc) } } + spin_lock_irqsave(&fnic->fnic_lock, flags); + fnic->internal_reset_inprogress = 0; + spin_unlock_irqrestore(&fnic->fnic_lock, flags); return ret; } diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index 3d3768aaab4f..8fb5c54c7dd3 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -3585,7 +3585,7 @@ static int ibmvscsis_write_pending(struct se_cmd *se_cmd) 1, 1); if (rc) { pr_err("srp_transfer_data() failed: %d\n", rc); - return -EAGAIN; + return -EIO; } /* * We now tell TCM to add this WRITE CDB directly into the TCM storage diff --git a/drivers/scsi/qedi/Kconfig b/drivers/scsi/qedi/Kconfig index 23ca8a274586..21331453db7b 100644 --- a/drivers/scsi/qedi/Kconfig +++ b/drivers/scsi/qedi/Kconfig @@ -1,6 +1,6 @@ config QEDI tristate "QLogic QEDI 25/40/100Gb iSCSI Initiator Driver Support" - depends on PCI && SCSI + depends on PCI && SCSI && UIO depends on QED select SCSI_ISCSI_ATTRS select QED_LL2 diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index c35b6de4ca64..e9e1e141af9c 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1018,7 +1018,7 @@ static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb) count = blk_rq_map_sg(req->q, req, sdb->table.sgl); BUG_ON(count > sdb->table.nents); sdb->table.nents = count; - sdb->length = blk_rq_bytes(req); + sdb->length = blk_rq_payload_bytes(req); return BLKPREP_OK; } @@ -2893,7 +2893,7 @@ scsi_internal_device_block(struct scsi_device *sdev) * request queue. */ if (q->mq_ops) { - blk_mq_stop_hw_queues(q); + blk_mq_quiesce_queue(q); } else { spin_lock_irqsave(q->queue_lock, flags); blk_stop_queue(q); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index b1933041da39..1fbb1ecf49f2 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -836,7 +836,6 @@ static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd) struct bio *bio = rq->bio; sector_t sector = blk_rq_pos(rq); unsigned int nr_sectors = blk_rq_sectors(rq); - unsigned int nr_bytes = blk_rq_bytes(rq); int ret; if (sdkp->device->no_write_same) @@ -869,21 +868,7 @@ static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd) cmd->transfersize = sdp->sector_size; cmd->allowed = SD_MAX_RETRIES; - - /* - * For WRITE_SAME the data transferred in the DATA IN buffer is - * different from the amount of data actually written to the target. - * - * We set up __data_len to the amount of data transferred from the - * DATA IN buffer so that blk_rq_map_sg set up the proper S/G list - * to transfer a single sector of data first, but then reset it to - * the amount of data to be written right after so that the I/O path - * knows how much to actually write. - */ - rq->__data_len = sdp->sector_size; - ret = scsi_init_io(cmd); - rq->__data_len = nr_bytes; - return ret; + return scsi_init_io(cmd); } static int sd_setup_flush_cmnd(struct scsi_cmnd *cmd) diff --git a/drivers/scsi/snic/snic_main.c b/drivers/scsi/snic/snic_main.c index 396b32dca074..7cf70aaec0ba 100644 --- a/drivers/scsi/snic/snic_main.c +++ b/drivers/scsi/snic/snic_main.c @@ -591,6 +591,7 @@ snic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!pool) { SNIC_HOST_ERR(shost, "dflt sgl pool creation failed\n"); + ret = -ENOMEM; goto err_free_res; } @@ -601,6 +602,7 @@ snic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!pool) { SNIC_HOST_ERR(shost, "max sgl pool creation failed\n"); + ret = -ENOMEM; goto err_free_dflt_sgl_pool; } @@ -611,6 +613,7 @@ snic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!pool) { SNIC_HOST_ERR(shost, "snic tmreq info pool creation failed.\n"); + ret = -ENOMEM; goto err_free_max_sgl_pool; } diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 7dfefd66df93..1cadc9eefa21 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1693,6 +1693,10 @@ void transport_generic_request_failure(struct se_cmd *cmd, case TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED: case TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED: case TCM_COPY_TARGET_DEVICE_NOT_REACHABLE: + case TCM_TOO_MANY_TARGET_DESCS: + case TCM_UNSUPPORTED_TARGET_DESC_TYPE_CODE: + case TCM_TOO_MANY_SEGMENT_DESCS: + case TCM_UNSUPPORTED_SEGMENT_DESC_TYPE_CODE: break; case TCM_OUT_OF_RESOURCES: sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; @@ -2808,6 +2812,26 @@ static const struct sense_info sense_info_table[] = { .key = ILLEGAL_REQUEST, .asc = 0x26, /* INVALID FIELD IN PARAMETER LIST */ }, + [TCM_TOO_MANY_TARGET_DESCS] = { + .key = ILLEGAL_REQUEST, + .asc = 0x26, + .ascq = 0x06, /* TOO MANY TARGET DESCRIPTORS */ + }, + [TCM_UNSUPPORTED_TARGET_DESC_TYPE_CODE] = { + .key = ILLEGAL_REQUEST, + .asc = 0x26, + .ascq = 0x07, /* UNSUPPORTED TARGET DESCRIPTOR TYPE CODE */ + }, + [TCM_TOO_MANY_SEGMENT_DESCS] = { + .key = ILLEGAL_REQUEST, + .asc = 0x26, + .ascq = 0x08, /* TOO MANY SEGMENT DESCRIPTORS */ + }, + [TCM_UNSUPPORTED_SEGMENT_DESC_TYPE_CODE] = { + .key = ILLEGAL_REQUEST, + .asc = 0x26, + .ascq = 0x09, /* UNSUPPORTED SEGMENT DESCRIPTOR TYPE CODE */ + }, [TCM_PARAMETER_LIST_LENGTH_ERROR] = { .key = ILLEGAL_REQUEST, .asc = 0x1a, /* PARAMETER LIST LENGTH ERROR */ diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c index 37d5caebffa6..d828b3b5000b 100644 --- a/drivers/target/target_core_xcopy.c +++ b/drivers/target/target_core_xcopy.c @@ -53,18 +53,13 @@ static int target_xcopy_gen_naa_ieee(struct se_device *dev, unsigned char *buf) return 0; } -static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op *xop, - bool src) +static int target_xcopy_locate_se_dev_e4(const unsigned char *dev_wwn, + struct se_device **found_dev) { struct se_device *se_dev; - unsigned char tmp_dev_wwn[XCOPY_NAA_IEEE_REGEX_LEN], *dev_wwn; + unsigned char tmp_dev_wwn[XCOPY_NAA_IEEE_REGEX_LEN]; int rc; - if (src) - dev_wwn = &xop->dst_tid_wwn[0]; - else - dev_wwn = &xop->src_tid_wwn[0]; - mutex_lock(&g_device_mutex); list_for_each_entry(se_dev, &g_device_list, g_dev_node) { @@ -78,15 +73,8 @@ static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op if (rc != 0) continue; - if (src) { - xop->dst_dev = se_dev; - pr_debug("XCOPY 0xe4: Setting xop->dst_dev: %p from located" - " se_dev\n", xop->dst_dev); - } else { - xop->src_dev = se_dev; - pr_debug("XCOPY 0xe4: Setting xop->src_dev: %p from located" - " se_dev\n", xop->src_dev); - } + *found_dev = se_dev; + pr_debug("XCOPY 0xe4: located se_dev: %p\n", se_dev); rc = target_depend_item(&se_dev->dev_group.cg_item); if (rc != 0) { @@ -110,7 +98,7 @@ static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op } static int target_xcopy_parse_tiddesc_e4(struct se_cmd *se_cmd, struct xcopy_op *xop, - unsigned char *p, bool src) + unsigned char *p, unsigned short cscd_index) { unsigned char *desc = p; unsigned short ript; @@ -155,7 +143,13 @@ static int target_xcopy_parse_tiddesc_e4(struct se_cmd *se_cmd, struct xcopy_op return -EINVAL; } - if (src) { + if (cscd_index != xop->stdi && cscd_index != xop->dtdi) { + pr_debug("XCOPY 0xe4: ignoring CSCD entry %d - neither src nor " + "dest\n", cscd_index); + return 0; + } + + if (cscd_index == xop->stdi) { memcpy(&xop->src_tid_wwn[0], &desc[8], XCOPY_NAA_IEEE_REGEX_LEN); /* * Determine if the source designator matches the local device @@ -167,10 +161,15 @@ static int target_xcopy_parse_tiddesc_e4(struct se_cmd *se_cmd, struct xcopy_op pr_debug("XCOPY 0xe4: Set xop->src_dev %p from source" " received xop\n", xop->src_dev); } - } else { + } + + if (cscd_index == xop->dtdi) { memcpy(&xop->dst_tid_wwn[0], &desc[8], XCOPY_NAA_IEEE_REGEX_LEN); /* - * Determine if the destination designator matches the local device + * Determine if the destination designator matches the local + * device. If @cscd_index corresponds to both source (stdi) and + * destination (dtdi), or dtdi comes after stdi, then + * XCOL_DEST_RECV_OP wins. */ if (!memcmp(&xop->local_dev_wwn[0], &xop->dst_tid_wwn[0], XCOPY_NAA_IEEE_REGEX_LEN)) { @@ -190,20 +189,23 @@ static int target_xcopy_parse_target_descriptors(struct se_cmd *se_cmd, { struct se_device *local_dev = se_cmd->se_dev; unsigned char *desc = p; - int offset = tdll % XCOPY_TARGET_DESC_LEN, rc, ret = 0; + int offset = tdll % XCOPY_TARGET_DESC_LEN, rc; + unsigned short cscd_index = 0; unsigned short start = 0; - bool src = true; *sense_ret = TCM_INVALID_PARAMETER_LIST; if (offset != 0) { pr_err("XCOPY target descriptor list length is not" " multiple of %d\n", XCOPY_TARGET_DESC_LEN); + *sense_ret = TCM_UNSUPPORTED_TARGET_DESC_TYPE_CODE; return -EINVAL; } - if (tdll > 64) { + if (tdll > RCR_OP_MAX_TARGET_DESC_COUNT * XCOPY_TARGET_DESC_LEN) { pr_err("XCOPY target descriptor supports a maximum" " two src/dest descriptors, tdll: %hu too large..\n", tdll); + /* spc4r37 6.4.3.4 CSCD DESCRIPTOR LIST LENGTH field */ + *sense_ret = TCM_TOO_MANY_TARGET_DESCS; return -EINVAL; } /* @@ -215,37 +217,43 @@ static int target_xcopy_parse_target_descriptors(struct se_cmd *se_cmd, while (start < tdll) { /* - * Check target descriptor identification with 0xE4 type with - * use VPD 0x83 WWPN matching .. + * Check target descriptor identification with 0xE4 type, and + * compare the current index with the CSCD descriptor IDs in + * the segment descriptor. Use VPD 0x83 WWPN matching .. */ switch (desc[0]) { case 0xe4: rc = target_xcopy_parse_tiddesc_e4(se_cmd, xop, - &desc[0], src); + &desc[0], cscd_index); if (rc != 0) goto out; - /* - * Assume target descriptors are in source -> destination order.. - */ - if (src) - src = false; - else - src = true; start += XCOPY_TARGET_DESC_LEN; desc += XCOPY_TARGET_DESC_LEN; - ret++; + cscd_index++; break; default: pr_err("XCOPY unsupported descriptor type code:" " 0x%02x\n", desc[0]); + *sense_ret = TCM_UNSUPPORTED_TARGET_DESC_TYPE_CODE; goto out; } } - if (xop->op_origin == XCOL_SOURCE_RECV_OP) - rc = target_xcopy_locate_se_dev_e4(se_cmd, xop, true); - else - rc = target_xcopy_locate_se_dev_e4(se_cmd, xop, false); + switch (xop->op_origin) { + case XCOL_SOURCE_RECV_OP: + rc = target_xcopy_locate_se_dev_e4(xop->dst_tid_wwn, + &xop->dst_dev); + break; + case XCOL_DEST_RECV_OP: + rc = target_xcopy_locate_se_dev_e4(xop->src_tid_wwn, + &xop->src_dev); + break; + default: + pr_err("XCOPY CSCD descriptor IDs not found in CSCD list - " + "stdi: %hu dtdi: %hu\n", xop->stdi, xop->dtdi); + rc = -EINVAL; + break; + } /* * If a matching IEEE NAA 0x83 descriptor for the requested device * is not located on this node, return COPY_ABORTED with ASQ/ASQC @@ -262,7 +270,7 @@ static int target_xcopy_parse_target_descriptors(struct se_cmd *se_cmd, pr_debug("XCOPY TGT desc: Dest dev: %p NAA IEEE WWN: 0x%16phN\n", xop->dst_dev, &xop->dst_tid_wwn[0]); - return ret; + return cscd_index; out: return -EINVAL; @@ -284,6 +292,14 @@ static int target_xcopy_parse_segdesc_02(struct se_cmd *se_cmd, struct xcopy_op xop->stdi = get_unaligned_be16(&desc[4]); xop->dtdi = get_unaligned_be16(&desc[6]); + + if (xop->stdi > XCOPY_CSCD_DESC_ID_LIST_OFF_MAX || + xop->dtdi > XCOPY_CSCD_DESC_ID_LIST_OFF_MAX) { + pr_err("XCOPY segment desc 0x02: unsupported CSCD ID > 0x%x; stdi: %hu dtdi: %hu\n", + XCOPY_CSCD_DESC_ID_LIST_OFF_MAX, xop->stdi, xop->dtdi); + return -EINVAL; + } + pr_debug("XCOPY seg desc 0x02: desc_len: %hu stdi: %hu dtdi: %hu, DC: %d\n", desc_len, xop->stdi, xop->dtdi, dc); @@ -306,15 +322,25 @@ static int target_xcopy_parse_segdesc_02(struct se_cmd *se_cmd, struct xcopy_op static int target_xcopy_parse_segment_descriptors(struct se_cmd *se_cmd, struct xcopy_op *xop, unsigned char *p, - unsigned int sdll) + unsigned int sdll, sense_reason_t *sense_ret) { unsigned char *desc = p; unsigned int start = 0; int offset = sdll % XCOPY_SEGMENT_DESC_LEN, rc, ret = 0; + *sense_ret = TCM_INVALID_PARAMETER_LIST; + if (offset != 0) { pr_err("XCOPY segment descriptor list length is not" " multiple of %d\n", XCOPY_SEGMENT_DESC_LEN); + *sense_ret = TCM_UNSUPPORTED_SEGMENT_DESC_TYPE_CODE; + return -EINVAL; + } + if (sdll > RCR_OP_MAX_SG_DESC_COUNT * XCOPY_SEGMENT_DESC_LEN) { + pr_err("XCOPY supports %u segment descriptor(s), sdll: %u too" + " large..\n", RCR_OP_MAX_SG_DESC_COUNT, sdll); + /* spc4r37 6.4.3.5 SEGMENT DESCRIPTOR LIST LENGTH field */ + *sense_ret = TCM_TOO_MANY_SEGMENT_DESCS; return -EINVAL; } @@ -335,6 +361,7 @@ static int target_xcopy_parse_segment_descriptors(struct se_cmd *se_cmd, default: pr_err("XCOPY unsupported segment descriptor" "type: 0x%02x\n", desc[0]); + *sense_ret = TCM_UNSUPPORTED_SEGMENT_DESC_TYPE_CODE; goto out; } } @@ -861,6 +888,16 @@ sense_reason_t target_do_xcopy(struct se_cmd *se_cmd) return TCM_UNSUPPORTED_SCSI_OPCODE; } + if (se_cmd->data_length == 0) { + target_complete_cmd(se_cmd, SAM_STAT_GOOD); + return TCM_NO_SENSE; + } + if (se_cmd->data_length < XCOPY_HDR_LEN) { + pr_err("XCOPY parameter truncation: length %u < hdr_len %u\n", + se_cmd->data_length, XCOPY_HDR_LEN); + return TCM_PARAMETER_LIST_LENGTH_ERROR; + } + xop = kzalloc(sizeof(struct xcopy_op), GFP_KERNEL); if (!xop) { pr_err("Unable to allocate xcopy_op\n"); @@ -883,6 +920,12 @@ sense_reason_t target_do_xcopy(struct se_cmd *se_cmd) */ tdll = get_unaligned_be16(&p[2]); sdll = get_unaligned_be32(&p[8]); + if (tdll + sdll > RCR_OP_MAX_DESC_LIST_LEN) { + pr_err("XCOPY descriptor list length %u exceeds maximum %u\n", + tdll + sdll, RCR_OP_MAX_DESC_LIST_LEN); + ret = TCM_PARAMETER_LIST_LENGTH_ERROR; + goto out; + } inline_dl = get_unaligned_be32(&p[12]); if (inline_dl != 0) { @@ -890,10 +933,32 @@ sense_reason_t target_do_xcopy(struct se_cmd *se_cmd) goto out; } + if (se_cmd->data_length < (XCOPY_HDR_LEN + tdll + sdll + inline_dl)) { + pr_err("XCOPY parameter truncation: data length %u too small " + "for tdll: %hu sdll: %u inline_dl: %u\n", + se_cmd->data_length, tdll, sdll, inline_dl); + ret = TCM_PARAMETER_LIST_LENGTH_ERROR; + goto out; + } + pr_debug("Processing XCOPY with list_id: 0x%02x list_id_usage: 0x%02x" " tdll: %hu sdll: %u inline_dl: %u\n", list_id, list_id_usage, tdll, sdll, inline_dl); + /* + * skip over the target descriptors until segment descriptors + * have been passed - CSCD ids are needed to determine src and dest. + */ + seg_desc = &p[16] + tdll; + + rc = target_xcopy_parse_segment_descriptors(se_cmd, xop, seg_desc, + sdll, &ret); + if (rc <= 0) + goto out; + + pr_debug("XCOPY: Processed %d segment descriptors, length: %u\n", rc, + rc * XCOPY_SEGMENT_DESC_LEN); + rc = target_xcopy_parse_target_descriptors(se_cmd, xop, &p[16], tdll, &ret); if (rc <= 0) goto out; @@ -911,18 +976,8 @@ sense_reason_t target_do_xcopy(struct se_cmd *se_cmd) pr_debug("XCOPY: Processed %d target descriptors, length: %u\n", rc, rc * XCOPY_TARGET_DESC_LEN); - seg_desc = &p[16]; - seg_desc += (rc * XCOPY_TARGET_DESC_LEN); - - rc = target_xcopy_parse_segment_descriptors(se_cmd, xop, seg_desc, sdll); - if (rc <= 0) { - xcopy_pt_undepend_remotedev(xop); - goto out; - } transport_kunmap_data_sg(se_cmd); - pr_debug("XCOPY: Processed %d segment descriptors, length: %u\n", rc, - rc * XCOPY_SEGMENT_DESC_LEN); INIT_WORK(&xop->xop_work, target_xcopy_do_work); queue_work(xcopy_wq, &xop->xop_work); return TCM_NO_SENSE; diff --git a/drivers/target/target_core_xcopy.h b/drivers/target/target_core_xcopy.h index 4d3d4dd060f2..7c0b105cbe1b 100644 --- a/drivers/target/target_core_xcopy.h +++ b/drivers/target/target_core_xcopy.h @@ -1,10 +1,17 @@ #include <target/target_core_base.h> +#define XCOPY_HDR_LEN 16 #define XCOPY_TARGET_DESC_LEN 32 #define XCOPY_SEGMENT_DESC_LEN 28 #define XCOPY_NAA_IEEE_REGEX_LEN 16 #define XCOPY_MAX_SECTORS 1024 +/* + * SPC4r37 6.4.6.1 + * Table 150 — CSCD descriptor ID values + */ +#define XCOPY_CSCD_DESC_ID_LIST_OFF_MAX 0x07FF + enum xcopy_origin_list { XCOL_SOURCE_RECV_OP = 0x01, XCOL_DEST_RECV_OP = 0x02, diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 9266271a787a..b3cc33fa6d26 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -36,7 +36,6 @@ #include <linux/uaccess.h> #include <linux/vfio.h> #include <linux/workqueue.h> -#include <linux/pid_namespace.h> #include <linux/mdev.h> #include <linux/notifier.h> @@ -495,8 +494,7 @@ static int vfio_pin_page_external(struct vfio_dma *dma, unsigned long vaddr, unsigned long *pfn_base, bool do_accounting) { unsigned long limit; - bool lock_cap = ns_capable(task_active_pid_ns(dma->task)->user_ns, - CAP_IPC_LOCK); + bool lock_cap = has_capability(dma->task, CAP_IPC_LOCK); struct mm_struct *mm; int ret; bool rsvd; @@ -1085,7 +1085,8 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2) * Tell lockdep we inherited freeze protection from submission * thread. */ - __sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE); + if (S_ISREG(file_inode(file)->i_mode)) + __sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE); file_end_write(file); } @@ -1525,7 +1526,8 @@ static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored, * by telling it the lock got released so that it doesn't * complain about held lock when we return to userspace. */ - __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE); + if (S_ISREG(file_inode(file)->i_mode)) + __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE); } kfree(iovec); return ret; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 29a02daf08a9..422370293cfd 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -2298,6 +2298,7 @@ static int elf_core_dump(struct coredump_params *cprm) goto end_coredump; } } + dump_truncate(cprm); if (!elf_core_write_extra_data(cprm)) goto end_coredump; diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 63d197724519..ff0b0be92d61 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -273,6 +273,8 @@ static void run_ordered_work(struct __btrfs_workqueue *wq) unsigned long flags; while (1) { + void *wtag; + spin_lock_irqsave(lock, flags); if (list_empty(list)) break; @@ -299,11 +301,13 @@ static void run_ordered_work(struct __btrfs_workqueue *wq) spin_unlock_irqrestore(lock, flags); /* - * we don't want to call the ordered free functions - * with the lock held though + * We don't want to call the ordered free functions with the + * lock held though. Save the work as tag for the trace event, + * because the callback could free the structure. */ + wtag = work; work->ordered_free(work); - trace_btrfs_all_work_done(work); + trace_btrfs_all_work_done(wq->fs_info, wtag); } spin_unlock_irqrestore(lock, flags); } @@ -311,6 +315,7 @@ static void run_ordered_work(struct __btrfs_workqueue *wq) static void normal_work_helper(struct btrfs_work *work) { struct __btrfs_workqueue *wq; + void *wtag; int need_order = 0; /* @@ -324,6 +329,8 @@ static void normal_work_helper(struct btrfs_work *work) if (work->ordered_func) need_order = 1; wq = work->wq; + /* Safe for tracepoints in case work gets freed by the callback */ + wtag = work; trace_btrfs_work_sched(work); thresh_exec_hook(wq); @@ -333,7 +340,7 @@ static void normal_work_helper(struct btrfs_work *work) run_ordered_work(wq); } if (!need_order) - trace_btrfs_all_work_done(work); + trace_btrfs_all_work_done(wq->fs_info, wtag); } void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index e97302f437a1..dcd2e798767e 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2522,11 +2522,11 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, if (ref && ref->seq && btrfs_check_delayed_seq(fs_info, delayed_refs, ref->seq)) { spin_unlock(&locked_ref->lock); - btrfs_delayed_ref_unlock(locked_ref); spin_lock(&delayed_refs->lock); locked_ref->processing = 0; delayed_refs->num_heads_ready++; spin_unlock(&delayed_refs->lock); + btrfs_delayed_ref_unlock(locked_ref); locked_ref = NULL; cond_resched(); count++; @@ -2572,7 +2572,10 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, */ if (must_insert_reserved) locked_ref->must_insert_reserved = 1; + spin_lock(&delayed_refs->lock); locked_ref->processing = 0; + delayed_refs->num_heads_ready++; + spin_unlock(&delayed_refs->lock); btrfs_debug(fs_info, "run_delayed_extent_op returned %d", ret); @@ -7384,7 +7387,8 @@ btrfs_lock_cluster(struct btrfs_block_group_cache *block_group, spin_unlock(&cluster->refill_lock); - down_read(&used_bg->data_rwsem); + /* We should only have one-level nested. */ + down_read_nested(&used_bg->data_rwsem, SINGLE_DEPTH_NESTING); spin_lock(&cluster->refill_lock); if (used_bg == cluster->block_group) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f2b281ad7af6..4e024260ad71 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7059,7 +7059,7 @@ insert: write_unlock(&em_tree->lock); out: - trace_btrfs_get_extent(root, em); + trace_btrfs_get_extent(root, inode, em); btrfs_free_path(path); if (trans) { @@ -7623,11 +7623,18 @@ static void adjust_dio_outstanding_extents(struct inode *inode, * within our reservation, otherwise we need to adjust our inode * counter appropriately. */ - if (dio_data->outstanding_extents) { + if (dio_data->outstanding_extents >= num_extents) { dio_data->outstanding_extents -= num_extents; } else { + /* + * If dio write length has been split due to no large enough + * contiguous space, we need to compensate our inode counter + * appropriately. + */ + u64 num_needed = num_extents - dio_data->outstanding_extents; + spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->outstanding_extents += num_extents; + BTRFS_I(inode)->outstanding_extents += num_needed; spin_unlock(&BTRFS_I(inode)->lock); } } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index f10bf5213ed8..eeffff84f280 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -37,6 +37,7 @@ */ #define LOG_INODE_ALL 0 #define LOG_INODE_EXISTS 1 +#define LOG_OTHER_INODE 2 /* * directory trouble cases @@ -4641,7 +4642,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, if (S_ISDIR(inode->i_mode) || (!test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags) && - inode_only == LOG_INODE_EXISTS)) + inode_only >= LOG_INODE_EXISTS)) max_key.type = BTRFS_XATTR_ITEM_KEY; else max_key.type = (u8)-1; @@ -4665,7 +4666,13 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, return ret; } - mutex_lock(&BTRFS_I(inode)->log_mutex); + if (inode_only == LOG_OTHER_INODE) { + inode_only = LOG_INODE_EXISTS; + mutex_lock_nested(&BTRFS_I(inode)->log_mutex, + SINGLE_DEPTH_NESTING); + } else { + mutex_lock(&BTRFS_I(inode)->log_mutex); + } /* * a brute force approach to making sure we get the most uptodate @@ -4817,7 +4824,7 @@ again: * unpin it. */ err = btrfs_log_inode(trans, root, other_inode, - LOG_INODE_EXISTS, + LOG_OTHER_INODE, 0, LLONG_MAX, ctx); iput(other_inode); if (err) diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c index 161342b73ce5..726f928238d0 100644 --- a/fs/btrfs/uuid-tree.c +++ b/fs/btrfs/uuid-tree.c @@ -352,7 +352,5 @@ skip: out: btrfs_free_path(path); - if (ret) - btrfs_warn(fs_info, "btrfs_uuid_tree_iterate failed %d", ret); - return 0; + return ret; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 9cd0c0ea7cdb..e4b066cd912a 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -502,9 +502,9 @@ static struct ceph_snap_context *get_oldest_context(struct inode *inode, dout(" head snapc %p has %d dirty pages\n", snapc, ci->i_wrbuffer_ref_head); if (truncate_size) - *truncate_size = capsnap->truncate_size; + *truncate_size = ci->i_truncate_size; if (truncate_seq) - *truncate_seq = capsnap->truncate_seq; + *truncate_seq = ci->i_truncate_seq; } spin_unlock(&ci->i_ceph_lock); return snapc; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 4f49253387a0..ec6b35e9f966 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2106,6 +2106,11 @@ static int __do_request(struct ceph_mds_client *mdsc, dout("do_request mdsmap err %d\n", err); goto finish; } + if (mdsc->mdsmap->m_epoch == 0) { + dout("do_request no mdsmap, waiting for map\n"); + list_add(&req->r_wait, &mdsc->waiting_for_map); + goto finish; + } if (!(mdsc->fsc->mount_options->flags & CEPH_MOUNT_OPT_MOUNTWAIT) && !ceph_mdsmap_is_cluster_available(mdsc->mdsmap)) { diff --git a/fs/coredump.c b/fs/coredump.c index e525b6017cdf..ae6b05629ca1 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -833,3 +833,21 @@ int dump_align(struct coredump_params *cprm, int align) return mod ? dump_skip(cprm, align - mod) : 1; } EXPORT_SYMBOL(dump_align); + +/* + * Ensures that file size is big enough to contain the current file + * postion. This prevents gdb from complaining about a truncated file + * if the last "write" to the file was dump_skip. + */ +void dump_truncate(struct coredump_params *cprm) +{ + struct file *file = cprm->file; + loff_t offset; + + if (file->f_op->llseek && file->f_op->llseek != no_llseek) { + offset = file->f_op->llseek(file, 0, SEEK_CUR); + if (i_size_read(file->f_mapping->host) < offset) + do_truncate(file->f_path.dentry, offset, 0, file); + } +} +EXPORT_SYMBOL(dump_truncate); @@ -691,8 +691,8 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping, pgoff_t index, unsigned long pfn) { struct vm_area_struct *vma; - pte_t *ptep; - pte_t pte; + pte_t pte, *ptep = NULL; + pmd_t *pmdp = NULL; spinlock_t *ptl; bool changed; @@ -707,21 +707,42 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping, address = pgoff_address(index, vma); changed = false; - if (follow_pte(vma->vm_mm, address, &ptep, &ptl)) + if (follow_pte_pmd(vma->vm_mm, address, &ptep, &pmdp, &ptl)) continue; - if (pfn != pte_pfn(*ptep)) - goto unlock; - if (!pte_dirty(*ptep) && !pte_write(*ptep)) - goto unlock; - flush_cache_page(vma, address, pfn); - pte = ptep_clear_flush(vma, address, ptep); - pte = pte_wrprotect(pte); - pte = pte_mkclean(pte); - set_pte_at(vma->vm_mm, address, ptep, pte); - changed = true; -unlock: - pte_unmap_unlock(ptep, ptl); + if (pmdp) { +#ifdef CONFIG_FS_DAX_PMD + pmd_t pmd; + + if (pfn != pmd_pfn(*pmdp)) + goto unlock_pmd; + if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp)) + goto unlock_pmd; + + flush_cache_page(vma, address, pfn); + pmd = pmdp_huge_clear_flush(vma, address, pmdp); + pmd = pmd_wrprotect(pmd); + pmd = pmd_mkclean(pmd); + set_pmd_at(vma->vm_mm, address, pmdp, pmd); + changed = true; +unlock_pmd: + spin_unlock(ptl); +#endif + } else { + if (pfn != pte_pfn(*ptep)) + goto unlock_pte; + if (!pte_dirty(*ptep) && !pte_write(*ptep)) + goto unlock_pte; + + flush_cache_page(vma, address, pfn); + pte = ptep_clear_flush(vma, address, ptep); + pte = pte_wrprotect(pte); + pte = pte_mkclean(pte); + set_pte_at(vma->vm_mm, address, ptep, pte); + changed = true; +unlock_pte: + pte_unmap_unlock(ptep, ptl); + } if (changed) mmu_notifier_invalidate_page(vma->vm_mm, address); diff --git a/fs/direct-io.c b/fs/direct-io.c index aeae8c063451..c87bae4376b8 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -906,6 +906,7 @@ static int do_direct_IO(struct dio *dio, struct dio_submit *sdio, struct buffer_head *map_bh) { const unsigned blkbits = sdio->blkbits; + const unsigned i_blkbits = blkbits + sdio->blkfactor; int ret = 0; while (sdio->block_in_file < sdio->final_block_in_request) { @@ -949,7 +950,7 @@ static int do_direct_IO(struct dio *dio, struct dio_submit *sdio, clean_bdev_aliases( map_bh->b_bdev, map_bh->b_blocknr, - map_bh->b_size >> blkbits); + map_bh->b_size >> i_blkbits); } if (!sdio->blkfactor) diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 0738f48293cc..0d8802453758 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -713,8 +713,8 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, } sector = SECTOR_FROM_BLOCK(blkstart); - if (sector & (bdev_zone_size(bdev) - 1) || - nr_sects != bdev_zone_size(bdev)) { + if (sector & (bdev_zone_sectors(bdev) - 1) || + nr_sects != bdev_zone_sectors(bdev)) { f2fs_msg(sbi->sb, KERN_INFO, "(%d) %s: Unaligned discard attempted (block %x + %x)", devi, sbi->s_ndevs ? FDEV(devi).path: "", diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 702638e21c76..46fd30d8af77 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1553,16 +1553,16 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) return 0; if (sbi->blocks_per_blkz && sbi->blocks_per_blkz != - SECTOR_TO_BLOCK(bdev_zone_size(bdev))) + SECTOR_TO_BLOCK(bdev_zone_sectors(bdev))) return -EINVAL; - sbi->blocks_per_blkz = SECTOR_TO_BLOCK(bdev_zone_size(bdev)); + sbi->blocks_per_blkz = SECTOR_TO_BLOCK(bdev_zone_sectors(bdev)); if (sbi->log_blocks_per_blkz && sbi->log_blocks_per_blkz != __ilog2_u32(sbi->blocks_per_blkz)) return -EINVAL; sbi->log_blocks_per_blkz = __ilog2_u32(sbi->blocks_per_blkz); FDEV(devi).nr_blkz = SECTOR_TO_BLOCK(nr_sectors) >> sbi->log_blocks_per_blkz; - if (nr_sectors & (bdev_zone_size(bdev) - 1)) + if (nr_sectors & (bdev_zone_sectors(bdev) - 1)) FDEV(devi).nr_blkz++; FDEV(devi).blkz_type = kmalloc(FDEV(devi).nr_blkz, GFP_KERNEL); diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 83d576f6a287..77d1632e905d 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3303,6 +3303,16 @@ static int ocfs2_downconvert_lock(struct ocfs2_super *osb, mlog(ML_BASTS, "lockres %s, level %d => %d\n", lockres->l_name, lockres->l_level, new_level); + /* + * On DLM_LKF_VALBLK, fsdlm behaves differently with o2cb. It always + * expects DLM_LKF_VALBLK being set if the LKB has LVB, so that + * we can recover correctly from node failure. Otherwise, we may get + * invalid LVB in LKB, but without DLM_SBF_VALNOTVALID being set. + */ + if (!ocfs2_is_o2cb_active() && + lockres->l_ops->flags & LOCK_TYPE_USES_LVB) + lvb = 1; + if (lvb) dlm_flags |= DLM_LKF_VALBLK; diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 52c07346bea3..820359096c7a 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -48,6 +48,12 @@ static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl"; */ static struct ocfs2_stack_plugin *active_stack; +inline int ocfs2_is_o2cb_active(void) +{ + return !strcmp(active_stack->sp_name, OCFS2_STACK_PLUGIN_O2CB); +} +EXPORT_SYMBOL_GPL(ocfs2_is_o2cb_active); + static struct ocfs2_stack_plugin *ocfs2_stack_lookup(const char *name) { struct ocfs2_stack_plugin *p; diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h index f2dce10fae54..e3036e1790e8 100644 --- a/fs/ocfs2/stackglue.h +++ b/fs/ocfs2/stackglue.h @@ -298,6 +298,9 @@ void ocfs2_stack_glue_set_max_proto_version(struct ocfs2_protocol_version *max_p int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin); void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin); +/* In ocfs2_downconvert_lock(), we need to know which stack we are using */ +int ocfs2_is_o2cb_active(void); + extern struct kset *ocfs2_kset; #endif /* STACKGLUE_H */ diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 595522022aca..c9d48dc78495 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -922,11 +922,10 @@ int simple_set_acl(struct inode *inode, struct posix_acl *acl, int type) int error; if (type == ACL_TYPE_ACCESS) { - error = posix_acl_equiv_mode(acl, &inode->i_mode); - if (error < 0) - return 0; - if (error == 0) - acl = NULL; + error = posix_acl_update_mode(inode, + &inode->i_mode, &acl); + if (error) + return error; } inode->i_ctime = current_time(inode); diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 5050056a0b06..9f06a211e157 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -95,10 +95,7 @@ unsigned int xfs_alloc_set_aside( struct xfs_mount *mp) { - unsigned int blocks; - - blocks = 4 + (mp->m_sb.sb_agcount * XFS_ALLOC_AGFL_RESERVE); - return blocks; + return mp->m_sb.sb_agcount * (XFS_ALLOC_AGFL_RESERVE + 4); } /* @@ -365,36 +362,12 @@ xfs_alloc_fix_len( return; ASSERT(rlen >= args->minlen && rlen <= args->maxlen); ASSERT(rlen % args->prod == args->mod); + ASSERT(args->pag->pagf_freeblks + args->pag->pagf_flcount >= + rlen + args->minleft); args->len = rlen; } /* - * Fix up length if there is too little space left in the a.g. - * Return 1 if ok, 0 if too little, should give up. - */ -STATIC int -xfs_alloc_fix_minleft( - xfs_alloc_arg_t *args) /* allocation argument structure */ -{ - xfs_agf_t *agf; /* a.g. freelist header */ - int diff; /* free space difference */ - - if (args->minleft == 0) - return 1; - agf = XFS_BUF_TO_AGF(args->agbp); - diff = be32_to_cpu(agf->agf_freeblks) - - args->len - args->minleft; - if (diff >= 0) - return 1; - args->len += diff; /* shrink the allocated space */ - /* casts to (int) catch length underflows */ - if ((int)args->len >= (int)args->minlen) - return 1; - args->agbno = NULLAGBLOCK; - return 0; -} - -/* * Update the two btrees, logically removing from freespace the extent * starting at rbno, rlen blocks. The extent is contained within the * actual (current) free extent fbno for flen blocks. @@ -689,8 +662,6 @@ xfs_alloc_ag_vextent( xfs_alloc_arg_t *args) /* argument structure for allocation */ { int error=0; - xfs_extlen_t reservation; - xfs_extlen_t oldmax; ASSERT(args->minlen > 0); ASSERT(args->maxlen > 0); @@ -699,20 +670,6 @@ xfs_alloc_ag_vextent( ASSERT(args->alignment > 0); /* - * Clamp maxlen to the amount of free space minus any reservations - * that have been made. - */ - oldmax = args->maxlen; - reservation = xfs_ag_resv_needed(args->pag, args->resv); - if (args->maxlen > args->pag->pagf_freeblks - reservation) - args->maxlen = args->pag->pagf_freeblks - reservation; - if (args->maxlen == 0) { - args->agbno = NULLAGBLOCK; - args->maxlen = oldmax; - return 0; - } - - /* * Branch to correct routine based on the type. */ args->wasfromfl = 0; @@ -731,8 +688,6 @@ xfs_alloc_ag_vextent( /* NOTREACHED */ } - args->maxlen = oldmax; - if (error || args->agbno == NULLAGBLOCK) return error; @@ -841,9 +796,6 @@ xfs_alloc_ag_vextent_exact( args->len = XFS_AGBLOCK_MIN(tend, args->agbno + args->maxlen) - args->agbno; xfs_alloc_fix_len(args); - if (!xfs_alloc_fix_minleft(args)) - goto not_found; - ASSERT(args->agbno + args->len <= tend); /* @@ -1149,12 +1101,7 @@ restart: XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); ASSERT(ltbno + ltlen <= be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_length)); args->len = blen; - if (!xfs_alloc_fix_minleft(args)) { - xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); - trace_xfs_alloc_near_nominleft(args); - return 0; - } - blen = args->len; + /* * We are allocating starting at bnew for blen blocks. */ @@ -1346,12 +1293,6 @@ restart: */ args->len = XFS_EXTLEN_MIN(ltlena, args->maxlen); xfs_alloc_fix_len(args); - if (!xfs_alloc_fix_minleft(args)) { - trace_xfs_alloc_near_nominleft(args); - xfs_btree_del_cursor(bno_cur_lt, XFS_BTREE_NOERROR); - xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); - return 0; - } rlen = args->len; (void)xfs_alloc_compute_diff(args->agbno, rlen, args->alignment, args->datatype, ltbnoa, ltlena, <new); @@ -1553,8 +1494,6 @@ restart: } xfs_alloc_fix_len(args); - if (!xfs_alloc_fix_minleft(args)) - goto out_nominleft; rlen = args->len; XFS_WANT_CORRUPTED_GOTO(args->mp, rlen <= flen, error0); /* @@ -2056,7 +1995,7 @@ xfs_alloc_space_available( int flags) { struct xfs_perag *pag = args->pag; - xfs_extlen_t longest; + xfs_extlen_t alloc_len, longest; xfs_extlen_t reservation; /* blocks that are still reserved */ int available; @@ -2066,17 +2005,28 @@ xfs_alloc_space_available( reservation = xfs_ag_resv_needed(pag, args->resv); /* do we have enough contiguous free space for the allocation? */ + alloc_len = args->minlen + (args->alignment - 1) + args->minalignslop; longest = xfs_alloc_longest_free_extent(args->mp, pag, min_free, reservation); - if ((args->minlen + args->alignment + args->minalignslop - 1) > longest) + if (longest < alloc_len) return false; /* do we have enough free space remaining for the allocation? */ available = (int)(pag->pagf_freeblks + pag->pagf_flcount - - reservation - min_free - args->total); - if (available < (int)args->minleft || available <= 0) + reservation - min_free - args->minleft); + if (available < (int)max(args->total, alloc_len)) return false; + /* + * Clamp maxlen to the amount of free space available for the actual + * extent allocation. + */ + if (available < (int)args->maxlen && !(flags & XFS_ALLOC_FLAG_CHECK)) { + args->maxlen = available; + ASSERT(args->maxlen > 0); + ASSERT(args->maxlen >= args->minlen); + } + return true; } @@ -2122,7 +2072,8 @@ xfs_alloc_fix_freelist( } need = xfs_alloc_min_freelist(mp, pag); - if (!xfs_alloc_space_available(args, need, flags)) + if (!xfs_alloc_space_available(args, need, flags | + XFS_ALLOC_FLAG_CHECK)) goto out_agbp_relse; /* @@ -2638,12 +2589,10 @@ xfs_alloc_vextent( xfs_agblock_t agsize; /* allocation group size */ int error; int flags; /* XFS_ALLOC_FLAG_... locking flags */ - xfs_extlen_t minleft;/* minimum left value, temp copy */ xfs_mount_t *mp; /* mount structure pointer */ xfs_agnumber_t sagno; /* starting allocation group number */ xfs_alloctype_t type; /* input allocation type */ int bump_rotor = 0; - int no_min = 0; xfs_agnumber_t rotorstep = xfs_rotorstep; /* inode32 agf stepper */ mp = args->mp; @@ -2672,7 +2621,6 @@ xfs_alloc_vextent( trace_xfs_alloc_vextent_badargs(args); return 0; } - minleft = args->minleft; switch (type) { case XFS_ALLOCTYPE_THIS_AG: @@ -2683,9 +2631,7 @@ xfs_alloc_vextent( */ args->agno = XFS_FSB_TO_AGNO(mp, args->fsbno); args->pag = xfs_perag_get(mp, args->agno); - args->minleft = 0; error = xfs_alloc_fix_freelist(args, 0); - args->minleft = minleft; if (error) { trace_xfs_alloc_vextent_nofix(args); goto error0; @@ -2750,9 +2696,7 @@ xfs_alloc_vextent( */ for (;;) { args->pag = xfs_perag_get(mp, args->agno); - if (no_min) args->minleft = 0; error = xfs_alloc_fix_freelist(args, flags); - args->minleft = minleft; if (error) { trace_xfs_alloc_vextent_nofix(args); goto error0; @@ -2792,20 +2736,17 @@ xfs_alloc_vextent( * or switch to non-trylock mode. */ if (args->agno == sagno) { - if (no_min == 1) { + if (flags == 0) { args->agbno = NULLAGBLOCK; trace_xfs_alloc_vextent_allfailed(args); break; } - if (flags == 0) { - no_min = 1; - } else { - flags = 0; - if (type == XFS_ALLOCTYPE_START_BNO) { - args->agbno = XFS_FSB_TO_AGBNO(mp, - args->fsbno); - args->type = XFS_ALLOCTYPE_NEAR_BNO; - } + + flags = 0; + if (type == XFS_ALLOCTYPE_START_BNO) { + args->agbno = XFS_FSB_TO_AGBNO(mp, + args->fsbno); + args->type = XFS_ALLOCTYPE_NEAR_BNO; } } xfs_perag_put(args->pag); diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 7c404a6b0ae3..1d0f48a501a3 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -56,7 +56,7 @@ typedef unsigned int xfs_alloctype_t; #define XFS_ALLOC_FLAG_FREEING 0x00000002 /* indicate caller is freeing extents*/ #define XFS_ALLOC_FLAG_NORMAP 0x00000004 /* don't modify the rmapbt */ #define XFS_ALLOC_FLAG_NOSHRINK 0x00000008 /* don't shrink the freelist */ - +#define XFS_ALLOC_FLAG_CHECK 0x00000010 /* test only, don't modify args */ /* * Argument structure for xfs_alloc routines. diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 2760bc3b2536..44773c9eb957 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3812,7 +3812,6 @@ xfs_bmap_btalloc( args.fsbno = 0; args.type = XFS_ALLOCTYPE_FIRST_AG; args.total = ap->minlen; - args.minleft = 0; if ((error = xfs_alloc_vextent(&args))) return error; ap->dfops->dop_low = true; @@ -4344,8 +4343,6 @@ xfs_bmapi_allocate( if (error) return error; - if (bma->dfops->dop_low) - bma->minleft = 0; if (bma->cur) bma->cur->bc_private.b.firstblock = *bma->firstblock; if (bma->blkno == NULLFSBLOCK) diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index d6330c297ca0..d9be241fc86f 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -502,12 +502,11 @@ try_another_ag: if (args.fsbno == NULLFSBLOCK && args.minleft) { /* * Could not find an AG with enough free space to satisfy - * a full btree split. Try again without minleft and if + * a full btree split. Try again and if * successful activate the lowspace algorithm. */ args.fsbno = 0; args.type = XFS_ALLOCTYPE_FIRST_AG; - args.minleft = 0; error = xfs_alloc_vextent(&args); if (error) goto error0; diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 0f56fcd3a5d5..631e7c0e0a29 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1152,19 +1152,22 @@ xfs_vm_releasepage( * block_invalidatepage() can send pages that are still marked dirty * but otherwise have invalidated buffers. * - * We've historically freed buffers on the latter. Instead, quietly - * filter out all dirty pages to avoid spurious buffer state warnings. - * This can likely be removed once shrink_active_list() is fixed. + * We want to release the latter to avoid unnecessary buildup of the + * LRU, skip the former and warn if we've left any lingering + * delalloc/unwritten buffers on clean pages. Skip pages with delalloc + * or unwritten buffers and warn if the page is not dirty. Otherwise + * try to release the buffers. */ - if (PageDirty(page)) - return 0; - xfs_count_page_state(page, &delalloc, &unwritten); - if (WARN_ON_ONCE(delalloc)) + if (delalloc) { + WARN_ON_ONCE(!PageDirty(page)); return 0; - if (WARN_ON_ONCE(unwritten)) + } + if (unwritten) { + WARN_ON_ONCE(!PageDirty(page)); return 0; + } return try_to_free_buffers(page); } diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index c39ac14ff540..b1469f0a91a6 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -3317,12 +3317,8 @@ xfs_log_force( xfs_mount_t *mp, uint flags) { - int error; - trace_xfs_log_force(mp, 0, _RET_IP_); - error = _xfs_log_force(mp, flags, NULL); - if (error) - xfs_warn(mp, "%s: error %d returned.", __func__, error); + _xfs_log_force(mp, flags, NULL); } /* @@ -3466,12 +3462,8 @@ xfs_log_force_lsn( xfs_lsn_t lsn, uint flags) { - int error; - trace_xfs_log_force(mp, lsn, _RET_IP_); - error = _xfs_log_force_lsn(mp, lsn, flags, NULL); - if (error) - xfs_warn(mp, "%s: error %d returned.", __func__, error); + _xfs_log_force_lsn(mp, lsn, flags, NULL); } /* diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 83695641bd5e..1ca8e8fd1078 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -739,7 +739,7 @@ static inline bool blk_queue_is_zoned(struct request_queue *q) } } -static inline unsigned int blk_queue_zone_size(struct request_queue *q) +static inline unsigned int blk_queue_zone_sectors(struct request_queue *q) { return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; } @@ -1000,6 +1000,19 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) return blk_rq_cur_bytes(rq) >> 9; } +/* + * Some commands like WRITE SAME have a payload or data transfer size which + * is different from the size of the request. Any driver that supports such + * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to + * calculate the data transfer size. + */ +static inline unsigned int blk_rq_payload_bytes(struct request *rq) +{ + if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) + return rq->special_vec.bv_len; + return blk_rq_bytes(rq); +} + static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, int op) { @@ -1536,12 +1549,12 @@ static inline bool bdev_is_zoned(struct block_device *bdev) return false; } -static inline unsigned int bdev_zone_size(struct block_device *bdev) +static inline unsigned int bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) - return blk_queue_zone_size(q); + return blk_queue_zone_sectors(q); return 0; } diff --git a/include/linux/coredump.h b/include/linux/coredump.h index d016a121a8c4..28ffa94aed6b 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -14,6 +14,7 @@ struct coredump_params; extern int dump_skip(struct coredump_params *cprm, size_t nr); extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr); extern int dump_align(struct coredump_params *cprm, int align); +extern void dump_truncate(struct coredump_params *cprm); #ifdef CONFIG_COREDUMP extern void do_coredump(const siginfo_t *siginfo); #else diff --git a/include/linux/efi.h b/include/linux/efi.h index a07a476178cd..5b1af30ece55 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -103,6 +103,7 @@ typedef struct { #define EFI_PAGE_SHIFT 12 #define EFI_PAGE_SIZE (1UL << EFI_PAGE_SHIFT) +#define EFI_PAGES_MAX (U64_MAX >> EFI_PAGE_SHIFT) typedef struct { u32 type; @@ -950,6 +951,7 @@ static inline efi_status_t efi_query_variable_store(u32 attributes, #endif extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr); +extern phys_addr_t __init efi_memmap_alloc(unsigned int num_entries); extern int __init efi_memmap_init_early(struct efi_memory_map_data *data); extern int __init efi_memmap_init_late(phys_addr_t addr, unsigned long size); extern void __init efi_memmap_unmap(void); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 4175dca4ac39..0fe0b6295ab5 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -38,9 +38,8 @@ struct vm_area_struct; #define ___GFP_ACCOUNT 0x100000u #define ___GFP_NOTRACK 0x200000u #define ___GFP_DIRECT_RECLAIM 0x400000u -#define ___GFP_OTHER_NODE 0x800000u -#define ___GFP_WRITE 0x1000000u -#define ___GFP_KSWAPD_RECLAIM 0x2000000u +#define ___GFP_WRITE 0x800000u +#define ___GFP_KSWAPD_RECLAIM 0x1000000u /* If the above are modified, __GFP_BITS_SHIFT may need updating */ /* @@ -172,11 +171,6 @@ struct vm_area_struct; * __GFP_NOTRACK_FALSE_POSITIVE is an alias of __GFP_NOTRACK. It's a means of * distinguishing in the source between false positives and allocations that * cannot be supported (e.g. page tables). - * - * __GFP_OTHER_NODE is for allocations that are on a remote node but that - * should not be accounted for as a remote allocation in vmstat. A - * typical user would be khugepaged collapsing a huge page on a remote - * node. */ #define __GFP_COLD ((__force gfp_t)___GFP_COLD) #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) @@ -184,10 +178,9 @@ struct vm_area_struct; #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) #define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK) -#define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT 26 +#define __GFP_BITS_SHIFT 25 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /* @@ -506,11 +499,10 @@ extern void free_hot_cold_page(struct page *page, bool cold); extern void free_hot_cold_page_list(struct list_head *list, bool cold); struct page_frag_cache; -extern void __page_frag_drain(struct page *page, unsigned int order, - unsigned int count); -extern void *__alloc_page_frag(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask); -extern void __free_page_frag(void *addr); +extern void __page_frag_cache_drain(struct page *page, unsigned int count); +extern void *page_frag_alloc(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask); +extern void page_frag_free(void *addr); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) diff --git a/include/linux/jump_label_ratelimit.h b/include/linux/jump_label_ratelimit.h index 089f70f83e97..23da3af459fe 100644 --- a/include/linux/jump_label_ratelimit.h +++ b/include/linux/jump_label_ratelimit.h @@ -14,6 +14,7 @@ struct static_key_deferred { #ifdef HAVE_JUMP_LABEL extern void static_key_slow_dec_deferred(struct static_key_deferred *key); +extern void static_key_deferred_flush(struct static_key_deferred *key); extern void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl); @@ -26,6 +27,10 @@ static inline void static_key_slow_dec_deferred(struct static_key_deferred *key) STATIC_KEY_CHECK_USE(); static_key_slow_dec(&key->key); } +static inline void static_key_deferred_flush(struct static_key_deferred *key) +{ + STATIC_KEY_CHECK_USE(); +} static inline void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 61d20c17f3b7..254698856b8f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -120,7 +120,7 @@ struct mem_cgroup_reclaim_iter { */ struct mem_cgroup_per_node { struct lruvec lruvec; - unsigned long lru_size[NR_LRU_LISTS]; + unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1]; @@ -432,7 +432,7 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg) int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, - int nr_pages); + int zid, int nr_pages); unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, int nid, unsigned int lru_mask); @@ -441,9 +441,23 @@ static inline unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { struct mem_cgroup_per_node *mz; + unsigned long nr_pages = 0; + int zid; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - return mz->lru_size[lru]; + for (zid = 0; zid < MAX_NR_ZONES; zid++) + nr_pages += mz->lru_zone_size[zid][lru]; + return nr_pages; +} + +static inline +unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, + enum lru_list lru, int zone_idx) +{ + struct mem_cgroup_per_node *mz; + + mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + return mz->lru_zone_size[zone_idx][lru]; } void mem_cgroup_handle_over_high(void); @@ -671,6 +685,12 @@ mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { return 0; } +static inline +unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, + enum lru_list lru, int zone_idx) +{ + return 0; +} static inline unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, diff --git a/include/linux/mm.h b/include/linux/mm.h index fe6b4036664a..b84615b0f64c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1210,8 +1210,8 @@ int copy_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); -int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, - spinlock_t **ptlp); +int follow_pte_pmd(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp); int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn); int follow_phys(struct vm_area_struct *vma, unsigned long address, diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 71613e8a720f..41d376e7116d 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -39,7 +39,7 @@ static __always_inline void update_lru_size(struct lruvec *lruvec, { __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG - mem_cgroup_update_lru_size(lruvec, lru, nr_pages); + mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #endif } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 994f7423a74b..9bde9558b596 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2477,14 +2477,19 @@ static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen) return NAPI_GRO_CB(skb)->frag0_len < hlen; } +static inline void skb_gro_frag0_invalidate(struct sk_buff *skb) +{ + NAPI_GRO_CB(skb)->frag0 = NULL; + NAPI_GRO_CB(skb)->frag0_len = 0; +} + static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, unsigned int offset) { if (!pskb_may_pull(skb, hlen)) return NULL; - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; + skb_gro_frag0_invalidate(skb); return skb->data + offset; } diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 4741ecdb9817..78ed8105e64d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1259,6 +1259,7 @@ extern void perf_event_disable(struct perf_event *event); extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_disable_inatomic(struct perf_event *event); extern void perf_event_task_tick(void); +extern int perf_event_account_interrupt(struct perf_event *event); #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index e2f3a3281d8f..8265d351c9f0 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -408,7 +408,8 @@ enum rproc_crash_type { * @crash_comp: completion used to sync crash handler and the rproc reload * @recovery_disabled: flag that state if recovery was disabled * @max_notifyid: largest allocated notify id. - * @table_ptr: our copy of the resource table + * @table_ptr: pointer to the resource table in effect + * @cached_table: copy of the resource table * @has_iommu: flag to indicate if remote processor is behind an MMU */ struct rproc { @@ -440,6 +441,7 @@ struct rproc { bool recovery_disabled; int max_notifyid; struct resource_table *table_ptr; + struct resource_table *cached_table; bool has_iommu; bool auto_boot; }; diff --git a/include/linux/sched.h b/include/linux/sched.h index 4d1905245c7a..ad3ec9ec61f7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -854,6 +854,16 @@ struct signal_struct { #define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */ +#define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \ + SIGNAL_STOP_CONTINUED) + +static inline void signal_set_stop_flags(struct signal_struct *sig, + unsigned int flags) +{ + WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP)); + sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; +} + /* If true, all threads except ->group_exit_task have pending SIGKILL */ static inline int signal_group_exit(const struct signal_struct *sig) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b53c0cfd417e..a410715bbef8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2480,7 +2480,7 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, static inline void skb_free_frag(void *addr) { - __free_page_frag(addr); + page_frag_free(addr); } void *napi_alloc_frag(unsigned int fragsz); diff --git a/include/linux/slab.h b/include/linux/slab.h index 084b12bad198..4c5363566815 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -226,7 +226,7 @@ static inline const char *__check_heap_object(const void *ptr, * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) -#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif @@ -239,7 +239,7 @@ static inline const char *__check_heap_object(const void *ptr, * be allocated from the same page. */ #define KMALLOC_SHIFT_HIGH PAGE_SHIFT -#define KMALLOC_SHIFT_MAX 30 +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif diff --git a/include/linux/swap.h b/include/linux/swap.h index 09f4be179ff3..7f47b7098b1b 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -150,8 +150,9 @@ enum { SWP_FILE = (1 << 7), /* set after swap_activate success */ SWP_AREA_DISCARD = (1 << 8), /* single-time swap area discards */ SWP_PAGE_DISCARD = (1 << 9), /* freed swap page-cluster discards */ + SWP_STABLE_WRITES = (1 << 10), /* no overwrite PG_writeback pages */ /* add others here before... */ - SWP_SCANNING = (1 << 10), /* refcount in scan_swap_map */ + SWP_SCANNING = (1 << 11), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL diff --git a/include/linux/timerfd.h b/include/linux/timerfd.h index bd36ce431e32..bab0b1ad0613 100644 --- a/include/linux/timerfd.h +++ b/include/linux/timerfd.h @@ -8,23 +8,7 @@ #ifndef _LINUX_TIMERFD_H #define _LINUX_TIMERFD_H -/* For O_CLOEXEC and O_NONBLOCK */ -#include <linux/fcntl.h> - -/* For _IO helpers */ -#include <linux/ioctl.h> - -/* - * CAREFUL: Check include/asm-generic/fcntl.h when defining - * new flags, since they might collide with O_* ones. We want - * to re-use O_* flags that couldn't possibly have a meaning - * from eventfd, in order to leave a free define-space for - * shared O_* flags. - */ -#define TFD_TIMER_ABSTIME (1 << 0) -#define TFD_TIMER_CANCEL_ON_SET (1 << 1) -#define TFD_CLOEXEC O_CLOEXEC -#define TFD_NONBLOCK O_NONBLOCK +#include <uapi/linux/timerfd.h> #define TFD_SHARED_FCNTL_FLAGS (TFD_CLOEXEC | TFD_NONBLOCK) /* Flags for timerfd_create. */ @@ -32,6 +16,4 @@ /* Flags for timerfd_settime. */ #define TFD_SETTIME_FLAGS (TFD_TIMER_ABSTIME | TFD_TIMER_CANCEL_ON_SET) -#define TFD_IOC_SET_TICKS _IOW('T', 0, u64) - #endif /* _LINUX_TIMERFD_H */ diff --git a/include/sound/hdmi-codec.h b/include/sound/hdmi-codec.h index 530c57bdefa0..915c4357945c 100644 --- a/include/sound/hdmi-codec.h +++ b/include/sound/hdmi-codec.h @@ -36,10 +36,10 @@ struct hdmi_codec_daifmt { HDMI_AC97, HDMI_SPDIF, } fmt; - int bit_clk_inv:1; - int frame_clk_inv:1; - int bit_clk_master:1; - int frame_clk_master:1; + unsigned int bit_clk_inv:1; + unsigned int frame_clk_inv:1; + unsigned int bit_clk_master:1; + unsigned int frame_clk_master:1; }; /* diff --git a/include/sound/soc.h b/include/sound/soc.h index 2b502f6cc6d0..b86168a21d56 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -813,6 +813,7 @@ struct snd_soc_component { unsigned int suspended:1; /* is in suspend PM state */ struct list_head list; + struct list_head card_aux_list; /* for auxiliary bound components */ struct list_head card_list; struct snd_soc_dai_driver *dai_drv; @@ -1152,6 +1153,7 @@ struct snd_soc_card { */ struct snd_soc_aux_dev *aux_dev; int num_aux_devs; + struct list_head aux_comp_list; const struct snd_kcontrol_new *controls; int num_controls; @@ -1547,6 +1549,7 @@ static inline void snd_soc_initialize_card_lists(struct snd_soc_card *card) INIT_LIST_HEAD(&card->widgets); INIT_LIST_HEAD(&card->paths); INIT_LIST_HEAD(&card->dapm_list); + INIT_LIST_HEAD(&card->aux_comp_list); INIT_LIST_HEAD(&card->component_dev_list); } diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 29e6858bb164..43edf82e54ff 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -174,6 +174,10 @@ enum tcm_sense_reason_table { TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED = R(0x16), TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED = R(0x17), TCM_COPY_TARGET_DEVICE_NOT_REACHABLE = R(0x18), + TCM_TOO_MANY_TARGET_DESCS = R(0x19), + TCM_UNSUPPORTED_TARGET_DESC_TYPE_CODE = R(0x1a), + TCM_TOO_MANY_SEGMENT_DESCS = R(0x1b), + TCM_UNSUPPORTED_SEGMENT_DESC_TYPE_CODE = R(0x1c), #undef R }; diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index c14bed4ab097..88d18a8ceb59 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -130,8 +130,8 @@ DECLARE_EVENT_CLASS(btrfs__inode, BTRFS_I(inode)->root->root_key.objectid; ), - TP_printk_btrfs("root = %llu(%s), gen = %llu, ino = %lu, blocks = %llu, " - "disk_i_size = %llu, last_trans = %llu, logged_trans = %llu", + TP_printk_btrfs("root=%llu(%s) gen=%llu ino=%lu blocks=%llu " + "disk_i_size=%llu last_trans=%llu logged_trans=%llu", show_root_type(__entry->root_objectid), (unsigned long long)__entry->generation, (unsigned long)__entry->ino, @@ -184,14 +184,16 @@ DEFINE_EVENT(btrfs__inode, btrfs_inode_evict, TRACE_EVENT_CONDITION(btrfs_get_extent, - TP_PROTO(struct btrfs_root *root, struct extent_map *map), + TP_PROTO(struct btrfs_root *root, struct inode *inode, + struct extent_map *map), - TP_ARGS(root, map), + TP_ARGS(root, inode, map), TP_CONDITION(map), TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) + __field( u64, ino ) __field( u64, start ) __field( u64, len ) __field( u64, orig_start ) @@ -204,7 +206,8 @@ TRACE_EVENT_CONDITION(btrfs_get_extent, TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; - __entry->start = map->start; + __entry->ino = btrfs_ino(inode); + __entry->start = map->start; __entry->len = map->len; __entry->orig_start = map->orig_start; __entry->block_start = map->block_start; @@ -214,11 +217,12 @@ TRACE_EVENT_CONDITION(btrfs_get_extent, __entry->compress_type = map->compress_type; ), - TP_printk_btrfs("root = %llu(%s), start = %llu, len = %llu, " - "orig_start = %llu, block_start = %llu(%s), " - "block_len = %llu, flags = %s, refs = %u, " - "compress_type = %u", + TP_printk_btrfs("root=%llu(%s) ino=%llu start=%llu len=%llu " + "orig_start=%llu block_start=%llu(%s) " + "block_len=%llu flags=%s refs=%u " + "compress_type=%u", show_root_type(__entry->root_objectid), + (unsigned long long)__entry->ino, (unsigned long long)__entry->start, (unsigned long long)__entry->len, (unsigned long long)__entry->orig_start, @@ -259,6 +263,7 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent, __field( int, compress_type ) __field( int, refs ) __field( u64, root_objectid ) + __field( u64, truncated_len ) ), TP_fast_assign_btrfs(btrfs_sb(inode->i_sb), @@ -273,18 +278,21 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent, __entry->refs = atomic_read(&ordered->refs); __entry->root_objectid = BTRFS_I(inode)->root->root_key.objectid; + __entry->truncated_len = ordered->truncated_len; ), - TP_printk_btrfs("root = %llu(%s), ino = %llu, file_offset = %llu, " - "start = %llu, len = %llu, disk_len = %llu, " - "bytes_left = %llu, flags = %s, compress_type = %d, " - "refs = %d", + TP_printk_btrfs("root=%llu(%s) ino=%llu file_offset=%llu " + "start=%llu len=%llu disk_len=%llu " + "truncated_len=%llu " + "bytes_left=%llu flags=%s compress_type=%d " + "refs=%d", show_root_type(__entry->root_objectid), (unsigned long long)__entry->ino, (unsigned long long)__entry->file_offset, (unsigned long long)__entry->start, (unsigned long long)__entry->len, (unsigned long long)__entry->disk_len, + (unsigned long long)__entry->truncated_len, (unsigned long long)__entry->bytes_left, show_ordered_flags(__entry->flags), __entry->compress_type, __entry->refs) @@ -354,10 +362,10 @@ DECLARE_EVENT_CLASS(btrfs__writepage, BTRFS_I(inode)->root->root_key.objectid; ), - TP_printk_btrfs("root = %llu(%s), ino = %lu, page_index = %lu, " - "nr_to_write = %ld, pages_skipped = %ld, range_start = %llu, " - "range_end = %llu, for_kupdate = %d, " - "for_reclaim = %d, range_cyclic = %d, writeback_index = %lu", + TP_printk_btrfs("root=%llu(%s) ino=%lu page_index=%lu " + "nr_to_write=%ld pages_skipped=%ld range_start=%llu " + "range_end=%llu for_kupdate=%d " + "for_reclaim=%d range_cyclic=%d writeback_index=%lu", show_root_type(__entry->root_objectid), (unsigned long)__entry->ino, __entry->index, __entry->nr_to_write, __entry->pages_skipped, @@ -400,8 +408,8 @@ TRACE_EVENT(btrfs_writepage_end_io_hook, BTRFS_I(page->mapping->host)->root->root_key.objectid; ), - TP_printk_btrfs("root = %llu(%s), ino = %lu, page_index = %lu, start = %llu, " - "end = %llu, uptodate = %d", + TP_printk_btrfs("root=%llu(%s) ino=%lu page_index=%lu start=%llu " + "end=%llu uptodate=%d", show_root_type(__entry->root_objectid), (unsigned long)__entry->ino, (unsigned long)__entry->index, (unsigned long long)__entry->start, @@ -433,7 +441,7 @@ TRACE_EVENT(btrfs_sync_file, BTRFS_I(inode)->root->root_key.objectid; ), - TP_printk_btrfs("root = %llu(%s), ino = %ld, parent = %ld, datasync = %d", + TP_printk_btrfs("root=%llu(%s) ino=%ld parent=%ld datasync=%d", show_root_type(__entry->root_objectid), (unsigned long)__entry->ino, (unsigned long)__entry->parent, __entry->datasync) @@ -484,9 +492,9 @@ TRACE_EVENT(btrfs_add_block_group, __entry->create = create; ), - TP_printk("%pU: block_group offset = %llu, size = %llu, " - "flags = %llu(%s), bytes_used = %llu, bytes_super = %llu, " - "create = %d", __entry->fsid, + TP_printk("%pU: block_group offset=%llu size=%llu " + "flags=%llu(%s) bytes_used=%llu bytes_super=%llu " + "create=%d", __entry->fsid, (unsigned long long)__entry->offset, (unsigned long long)__entry->size, (unsigned long long)__entry->flags, @@ -535,9 +543,9 @@ DECLARE_EVENT_CLASS(btrfs_delayed_tree_ref, __entry->seq = ref->seq; ), - TP_printk_btrfs("bytenr = %llu, num_bytes = %llu, action = %s, " - "parent = %llu(%s), ref_root = %llu(%s), level = %d, " - "type = %s, seq = %llu", + TP_printk_btrfs("bytenr=%llu num_bytes=%llu action=%s " + "parent=%llu(%s) ref_root=%llu(%s) level=%d " + "type=%s seq=%llu", (unsigned long long)__entry->bytenr, (unsigned long long)__entry->num_bytes, show_ref_action(__entry->action), @@ -600,9 +608,9 @@ DECLARE_EVENT_CLASS(btrfs_delayed_data_ref, __entry->seq = ref->seq; ), - TP_printk_btrfs("bytenr = %llu, num_bytes = %llu, action = %s, " - "parent = %llu(%s), ref_root = %llu(%s), owner = %llu, " - "offset = %llu, type = %s, seq = %llu", + TP_printk_btrfs("bytenr=%llu num_bytes=%llu action=%s " + "parent=%llu(%s) ref_root=%llu(%s) owner=%llu " + "offset=%llu type=%s seq=%llu", (unsigned long long)__entry->bytenr, (unsigned long long)__entry->num_bytes, show_ref_action(__entry->action), @@ -657,7 +665,7 @@ DECLARE_EVENT_CLASS(btrfs_delayed_ref_head, __entry->is_data = head_ref->is_data; ), - TP_printk_btrfs("bytenr = %llu, num_bytes = %llu, action = %s, is_data = %d", + TP_printk_btrfs("bytenr=%llu num_bytes=%llu action=%s is_data=%d", (unsigned long long)__entry->bytenr, (unsigned long long)__entry->num_bytes, show_ref_action(__entry->action), @@ -721,8 +729,8 @@ DECLARE_EVENT_CLASS(btrfs__chunk, __entry->root_objectid = fs_info->chunk_root->root_key.objectid; ), - TP_printk_btrfs("root = %llu(%s), offset = %llu, size = %llu, " - "num_stripes = %d, sub_stripes = %d, type = %s", + TP_printk_btrfs("root=%llu(%s) offset=%llu size=%llu " + "num_stripes=%d sub_stripes=%d type=%s", show_root_type(__entry->root_objectid), (unsigned long long)__entry->offset, (unsigned long long)__entry->size, @@ -771,8 +779,8 @@ TRACE_EVENT(btrfs_cow_block, __entry->cow_level = btrfs_header_level(cow); ), - TP_printk_btrfs("root = %llu(%s), refs = %d, orig_buf = %llu " - "(orig_level = %d), cow_buf = %llu (cow_level = %d)", + TP_printk_btrfs("root=%llu(%s) refs=%d orig_buf=%llu " + "(orig_level=%d) cow_buf=%llu (cow_level=%d)", show_root_type(__entry->root_objectid), __entry->refs, (unsigned long long)__entry->buf_start, @@ -836,7 +844,7 @@ TRACE_EVENT(btrfs_trigger_flush, __assign_str(reason, reason) ), - TP_printk("%pU: %s: flush = %d(%s), flags = %llu(%s), bytes = %llu", + TP_printk("%pU: %s: flush=%d(%s) flags=%llu(%s) bytes=%llu", __entry->fsid, __get_str(reason), __entry->flush, show_flush_action(__entry->flush), (unsigned long long)__entry->flags, @@ -879,8 +887,8 @@ TRACE_EVENT(btrfs_flush_space, __entry->ret = ret; ), - TP_printk("%pU: state = %d(%s), flags = %llu(%s), num_bytes = %llu, " - "orig_bytes = %llu, ret = %d", __entry->fsid, __entry->state, + TP_printk("%pU: state=%d(%s) flags=%llu(%s) num_bytes=%llu " + "orig_bytes=%llu ret=%d", __entry->fsid, __entry->state, show_flush_state(__entry->state), (unsigned long long)__entry->flags, __print_flags((unsigned long)__entry->flags, "|", @@ -905,7 +913,7 @@ DECLARE_EVENT_CLASS(btrfs__reserved_extent, __entry->len = len; ), - TP_printk_btrfs("root = %llu(%s), start = %llu, len = %llu", + TP_printk_btrfs("root=%llu(%s) start=%llu len=%llu", show_root_type(BTRFS_EXTENT_TREE_OBJECTID), (unsigned long long)__entry->start, (unsigned long long)__entry->len) @@ -944,7 +952,7 @@ TRACE_EVENT(find_free_extent, __entry->data = data; ), - TP_printk_btrfs("root = %Lu(%s), len = %Lu, empty_size = %Lu, flags = %Lu(%s)", + TP_printk_btrfs("root=%Lu(%s) len=%Lu empty_size=%Lu flags=%Lu(%s)", show_root_type(BTRFS_EXTENT_TREE_OBJECTID), __entry->num_bytes, __entry->empty_size, __entry->data, __print_flags((unsigned long)__entry->data, "|", @@ -973,8 +981,8 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent, __entry->len = len; ), - TP_printk_btrfs("root = %Lu(%s), block_group = %Lu, flags = %Lu(%s), " - "start = %Lu, len = %Lu", + TP_printk_btrfs("root=%Lu(%s) block_group=%Lu flags=%Lu(%s) " + "start=%Lu len=%Lu", show_root_type(BTRFS_EXTENT_TREE_OBJECTID), __entry->bg_objectid, __entry->flags, __print_flags((unsigned long)__entry->flags, @@ -1025,8 +1033,8 @@ TRACE_EVENT(btrfs_find_cluster, __entry->min_bytes = min_bytes; ), - TP_printk_btrfs("block_group = %Lu, flags = %Lu(%s), start = %Lu, len = %Lu," - " empty_size = %Lu, min_bytes = %Lu", __entry->bg_objectid, + TP_printk_btrfs("block_group=%Lu flags=%Lu(%s) start=%Lu len=%Lu " + "empty_size=%Lu min_bytes=%Lu", __entry->bg_objectid, __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS), __entry->start, @@ -1047,7 +1055,7 @@ TRACE_EVENT(btrfs_failed_cluster_setup, __entry->bg_objectid = block_group->key.objectid; ), - TP_printk_btrfs("block_group = %Lu", __entry->bg_objectid) + TP_printk_btrfs("block_group=%Lu", __entry->bg_objectid) ); TRACE_EVENT(btrfs_setup_cluster, @@ -1075,8 +1083,8 @@ TRACE_EVENT(btrfs_setup_cluster, __entry->bitmap = bitmap; ), - TP_printk_btrfs("block_group = %Lu, flags = %Lu(%s), window_start = %Lu, " - "size = %Lu, max_size = %Lu, bitmap = %d", + TP_printk_btrfs("block_group=%Lu flags=%Lu(%s) window_start=%Lu " + "size=%Lu max_size=%Lu bitmap=%d", __entry->bg_objectid, __entry->flags, __print_flags((unsigned long)__entry->flags, "|", @@ -1103,7 +1111,7 @@ TRACE_EVENT(alloc_extent_state, __entry->ip = IP ), - TP_printk("state=%p; mask = %s; caller = %pS", __entry->state, + TP_printk("state=%p mask=%s caller=%pS", __entry->state, show_gfp_flags(__entry->mask), (void *)__entry->ip) ); @@ -1123,7 +1131,7 @@ TRACE_EVENT(free_extent_state, __entry->ip = IP ), - TP_printk(" state=%p; caller = %pS", __entry->state, + TP_printk("state=%p caller=%pS", __entry->state, (void *)__entry->ip) ); @@ -1151,28 +1159,32 @@ DECLARE_EVENT_CLASS(btrfs__work, __entry->normal_work = &work->normal_work; ), - TP_printk_btrfs("work=%p (normal_work=%p), wq=%p, func=%pf, ordered_func=%p," - " ordered_free=%p", + TP_printk_btrfs("work=%p (normal_work=%p) wq=%p func=%pf ordered_func=%p " + "ordered_free=%p", __entry->work, __entry->normal_work, __entry->wq, __entry->func, __entry->ordered_func, __entry->ordered_free) ); -/* For situiations that the work is freed */ +/* + * For situiations when the work is freed, we pass fs_info and a tag that that + * matches address of the work structure so it can be paired with the + * scheduling event. + */ DECLARE_EVENT_CLASS(btrfs__work__done, - TP_PROTO(struct btrfs_work *work), + TP_PROTO(struct btrfs_fs_info *fs_info, void *wtag), - TP_ARGS(work), + TP_ARGS(fs_info, wtag), TP_STRUCT__entry_btrfs( - __field( void *, work ) + __field( void *, wtag ) ), - TP_fast_assign_btrfs(btrfs_work_owner(work), - __entry->work = work; + TP_fast_assign_btrfs(fs_info, + __entry->wtag = wtag; ), - TP_printk_btrfs("work->%p", __entry->work) + TP_printk_btrfs("work->%p", __entry->wtag) ); DEFINE_EVENT(btrfs__work, btrfs_work_queued, @@ -1191,9 +1203,9 @@ DEFINE_EVENT(btrfs__work, btrfs_work_sched, DEFINE_EVENT(btrfs__work__done, btrfs_all_work_done, - TP_PROTO(struct btrfs_work *work), + TP_PROTO(struct btrfs_fs_info *fs_info, void *wtag), - TP_ARGS(work) + TP_ARGS(fs_info, wtag) ); DEFINE_EVENT(btrfs__work, btrfs_ordered_sched, @@ -1221,7 +1233,7 @@ DECLARE_EVENT_CLASS(btrfs__workqueue, __entry->high = high; ), - TP_printk_btrfs("name=%s%s, wq=%p", __get_str(name), + TP_printk_btrfs("name=%s%s wq=%p", __get_str(name), __print_flags(__entry->high, "", {(WQ_HIGHPRI), "-high"}), __entry->wq) @@ -1276,7 +1288,7 @@ DECLARE_EVENT_CLASS(btrfs__qgroup_data_map, __entry->free_reserved = free_reserved; ), - TP_printk_btrfs("rootid=%llu, ino=%lu, free_reserved=%llu", + TP_printk_btrfs("rootid=%llu ino=%lu free_reserved=%llu", __entry->rootid, __entry->ino, __entry->free_reserved) ); @@ -1323,7 +1335,7 @@ DECLARE_EVENT_CLASS(btrfs__qgroup_rsv_data, __entry->op = op; ), - TP_printk_btrfs("root=%llu, ino=%lu, start=%llu, len=%llu, reserved=%llu, op=%s", + TP_printk_btrfs("root=%llu ino=%lu start=%llu len=%llu reserved=%llu op=%s", __entry->rootid, __entry->ino, __entry->start, __entry->len, __entry->reserved, __print_flags((unsigned long)__entry->op, "", @@ -1361,7 +1373,7 @@ DECLARE_EVENT_CLASS(btrfs__qgroup_delayed_ref, __entry->reserved = reserved; ), - TP_printk_btrfs("root=%llu, reserved=%llu, op=free", + TP_printk_btrfs("root=%llu reserved=%llu op=free", __entry->ref_root, __entry->reserved) ); @@ -1388,7 +1400,7 @@ DECLARE_EVENT_CLASS(btrfs_qgroup_extent, __entry->num_bytes = rec->num_bytes; ), - TP_printk_btrfs("bytenr = %llu, num_bytes = %llu", + TP_printk_btrfs("bytenr=%llu num_bytes=%llu", (unsigned long long)__entry->bytenr, (unsigned long long)__entry->num_bytes) ); @@ -1430,8 +1442,8 @@ TRACE_EVENT(btrfs_qgroup_account_extent, __entry->nr_new_roots = nr_new_roots; ), - TP_printk_btrfs("bytenr = %llu, num_bytes = %llu, nr_old_roots = %llu, " - "nr_new_roots = %llu", + TP_printk_btrfs("bytenr=%llu num_bytes=%llu nr_old_roots=%llu " + "nr_new_roots=%llu", __entry->bytenr, __entry->num_bytes, __entry->nr_old_roots, @@ -1457,7 +1469,7 @@ TRACE_EVENT(qgroup_update_counters, __entry->cur_new_count = cur_new_count; ), - TP_printk_btrfs("qgid = %llu, cur_old_count = %llu, cur_new_count = %llu", + TP_printk_btrfs("qgid=%llu cur_old_count=%llu cur_new_count=%llu", __entry->qgid, __entry->cur_old_count, __entry->cur_new_count) diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 9e687ca9a307..15bf875d0e4a 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -47,8 +47,7 @@ {(unsigned long)__GFP_WRITE, "__GFP_WRITE"}, \ {(unsigned long)__GFP_RECLAIM, "__GFP_RECLAIM"}, \ {(unsigned long)__GFP_DIRECT_RECLAIM, "__GFP_DIRECT_RECLAIM"},\ - {(unsigned long)__GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"},\ - {(unsigned long)__GFP_OTHER_NODE, "__GFP_OTHER_NODE"} \ + {(unsigned long)__GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"}\ #define show_gfp_flags(flags) \ (flags) ? __print_flags(flags, "|", \ diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index a8b93e685239..f330ba4547cf 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -414,6 +414,7 @@ header-y += telephony.h header-y += termios.h header-y += thermal.h header-y += time.h +header-y += timerfd.h header-y += times.h header-y += timex.h header-y += tiocl.h diff --git a/include/uapi/linux/timerfd.h b/include/uapi/linux/timerfd.h new file mode 100644 index 000000000000..6fcfaa8da173 --- /dev/null +++ b/include/uapi/linux/timerfd.h @@ -0,0 +1,36 @@ +/* + * include/linux/timerfd.h + * + * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> + * + */ + +#ifndef _UAPI_LINUX_TIMERFD_H +#define _UAPI_LINUX_TIMERFD_H + +#include <linux/types.h> + +/* For O_CLOEXEC and O_NONBLOCK */ +#include <linux/fcntl.h> + +/* For _IO helpers */ +#include <linux/ioctl.h> + +/* + * CAREFUL: Check include/asm-generic/fcntl.h when defining + * new flags, since they might collide with O_* ones. We want + * to re-use O_* flags that couldn't possibly have a meaning + * from eventfd, in order to leave a free define-space for + * shared O_* flags. + * + * Also make sure to update the masks in include/linux/timerfd.h + * when adding new flags. + */ +#define TFD_TIMER_ABSTIME (1 << 0) +#define TFD_TIMER_CANCEL_ON_SET (1 << 1) +#define TFD_CLOEXEC O_CLOEXEC +#define TFD_NONBLOCK O_NONBLOCK + +#define TFD_IOC_SET_TICKS _IOW('T', 0, __u64) + +#endif /* _UAPI_LINUX_TIMERFD_H */ diff --git a/init/Kconfig b/init/Kconfig index 223b734abccd..e1a937348a3e 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1176,6 +1176,10 @@ config CGROUP_DEBUG Say N. +config SOCK_CGROUP_DATA + bool + default n + endif # CGROUPS config CHECKPOINT_RESTORE diff --git a/ipc/sem.c b/ipc/sem.c index e08b94851922..3ec5742b5640 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -1977,7 +1977,7 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, } rcu_read_lock(); - sem_lock(sma, sops, nsops); + locknum = sem_lock(sma, sops, nsops); if (!ipc_valid_object(&sma->sem_perm)) goto out_unlock_free; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index a2ac051c342f..229a5d5df977 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -56,7 +56,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) attr->value_size == 0 || attr->map_flags) return ERR_PTR(-EINVAL); - if (attr->value_size >= 1 << (KMALLOC_SHIFT_MAX - 1)) + if (attr->value_size > KMALLOC_MAX_SIZE) /* if value_size is bigger, the user space won't be able to * access the elements. */ diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 34debc1a9641..3f2bb58952d8 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -274,7 +274,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) */ goto free_htab; - if (htab->map.value_size >= (1 << (KMALLOC_SHIFT_MAX - 1)) - + if (htab->map.value_size >= KMALLOC_MAX_SIZE - MAX_BPF_STACK - sizeof(struct htab_elem)) /* if value_size is bigger, the user space won't be able to * access the elements via bpf syscall. This check also makes diff --git a/kernel/capability.c b/kernel/capability.c index a98e814f216f..f97fe77ceb88 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -318,6 +318,7 @@ bool has_capability(struct task_struct *t, int cap) { return has_ns_capability(t, &init_user_ns, cap); } +EXPORT_SYMBOL(has_capability); /** * has_ns_capability_noaudit - Does a task have a capability (unaudited) diff --git a/kernel/events/core.c b/kernel/events/core.c index ab15509fab8c..110b38a58493 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2249,7 +2249,7 @@ static int __perf_install_in_context(void *info) struct perf_event_context *ctx = event->ctx; struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); struct perf_event_context *task_ctx = cpuctx->task_ctx; - bool activate = true; + bool reprogram = true; int ret = 0; raw_spin_lock(&cpuctx->ctx.lock); @@ -2257,27 +2257,26 @@ static int __perf_install_in_context(void *info) raw_spin_lock(&ctx->lock); task_ctx = ctx; - /* If we're on the wrong CPU, try again */ - if (task_cpu(ctx->task) != smp_processor_id()) { - ret = -ESRCH; - goto unlock; - } + reprogram = (ctx->task == current); /* - * If we're on the right CPU, see if the task we target is - * current, if not we don't have to activate the ctx, a future - * context switch will do that for us. + * If the task is running, it must be running on this CPU, + * otherwise we cannot reprogram things. + * + * If its not running, we don't care, ctx->lock will + * serialize against it becoming runnable. */ - if (ctx->task != current) - activate = false; - else - WARN_ON_ONCE(cpuctx->task_ctx && cpuctx->task_ctx != ctx); + if (task_curr(ctx->task) && !reprogram) { + ret = -ESRCH; + goto unlock; + } + WARN_ON_ONCE(reprogram && cpuctx->task_ctx && cpuctx->task_ctx != ctx); } else if (task_ctx) { raw_spin_lock(&task_ctx->lock); } - if (activate) { + if (reprogram) { ctx_sched_out(ctx, cpuctx, EVENT_TIME); add_event_to_ctx(event, ctx); ctx_resched(cpuctx, task_ctx); @@ -2328,13 +2327,36 @@ perf_install_in_context(struct perf_event_context *ctx, /* * Installing events is tricky because we cannot rely on ctx->is_active * to be set in case this is the nr_events 0 -> 1 transition. + * + * Instead we use task_curr(), which tells us if the task is running. + * However, since we use task_curr() outside of rq::lock, we can race + * against the actual state. This means the result can be wrong. + * + * If we get a false positive, we retry, this is harmless. + * + * If we get a false negative, things are complicated. If we are after + * perf_event_context_sched_in() ctx::lock will serialize us, and the + * value must be correct. If we're before, it doesn't matter since + * perf_event_context_sched_in() will program the counter. + * + * However, this hinges on the remote context switch having observed + * our task->perf_event_ctxp[] store, such that it will in fact take + * ctx::lock in perf_event_context_sched_in(). + * + * We do this by task_function_call(), if the IPI fails to hit the task + * we know any future context switch of task must see the + * perf_event_ctpx[] store. */ -again: + /* - * Cannot use task_function_call() because we need to run on the task's - * CPU regardless of whether its current or not. + * This smp_mb() orders the task->perf_event_ctxp[] store with the + * task_cpu() load, such that if the IPI then does not find the task + * running, a future context switch of that task must observe the + * store. */ - if (!cpu_function_call(task_cpu(task), __perf_install_in_context, event)) + smp_mb(); +again: + if (!task_function_call(task, __perf_install_in_context, event)) return; raw_spin_lock_irq(&ctx->lock); @@ -2348,12 +2370,16 @@ again: raw_spin_unlock_irq(&ctx->lock); return; } - raw_spin_unlock_irq(&ctx->lock); /* - * Since !ctx->is_active doesn't mean anything, we must IPI - * unconditionally. + * If the task is not running, ctx->lock will avoid it becoming so, + * thus we can safely install the event. */ - goto again; + if (task_curr(task)) { + raw_spin_unlock_irq(&ctx->lock); + goto again; + } + add_event_to_ctx(event, ctx); + raw_spin_unlock_irq(&ctx->lock); } /* @@ -7034,25 +7060,12 @@ static void perf_log_itrace_start(struct perf_event *event) perf_output_end(&handle); } -/* - * Generic event overflow handling, sampling. - */ - -static int __perf_event_overflow(struct perf_event *event, - int throttle, struct perf_sample_data *data, - struct pt_regs *regs) +static int +__perf_event_account_interrupt(struct perf_event *event, int throttle) { - int events = atomic_read(&event->event_limit); struct hw_perf_event *hwc = &event->hw; - u64 seq; int ret = 0; - - /* - * Non-sampling counters might still use the PMI to fold short - * hardware counters, ignore those. - */ - if (unlikely(!is_sampling_event(event))) - return 0; + u64 seq; seq = __this_cpu_read(perf_throttled_seq); if (seq != hwc->interrupts_seq) { @@ -7080,6 +7093,34 @@ static int __perf_event_overflow(struct perf_event *event, perf_adjust_period(event, delta, hwc->last_period, true); } + return ret; +} + +int perf_event_account_interrupt(struct perf_event *event) +{ + return __perf_event_account_interrupt(event, 1); +} + +/* + * Generic event overflow handling, sampling. + */ + +static int __perf_event_overflow(struct perf_event *event, + int throttle, struct perf_sample_data *data, + struct pt_regs *regs) +{ + int events = atomic_read(&event->event_limit); + int ret = 0; + + /* + * Non-sampling counters might still use the PMI to fold short + * hardware counters, ignore those. + */ + if (unlikely(!is_sampling_event(event))) + return 0; + + ret = __perf_event_account_interrupt(event, throttle); + /* * XXX event_limit might not quite work as expected on inherited * events @@ -9503,6 +9544,37 @@ static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id) return 0; } +/* + * Variation on perf_event_ctx_lock_nested(), except we take two context + * mutexes. + */ +static struct perf_event_context * +__perf_event_ctx_lock_double(struct perf_event *group_leader, + struct perf_event_context *ctx) +{ + struct perf_event_context *gctx; + +again: + rcu_read_lock(); + gctx = READ_ONCE(group_leader->ctx); + if (!atomic_inc_not_zero(&gctx->refcount)) { + rcu_read_unlock(); + goto again; + } + rcu_read_unlock(); + + mutex_lock_double(&gctx->mutex, &ctx->mutex); + + if (group_leader->ctx != gctx) { + mutex_unlock(&ctx->mutex); + mutex_unlock(&gctx->mutex); + put_ctx(gctx); + goto again; + } + + return gctx; +} + /** * sys_perf_event_open - open a performance event, associate it to a task/cpu * @@ -9746,12 +9818,31 @@ SYSCALL_DEFINE5(perf_event_open, } if (move_group) { - gctx = group_leader->ctx; - mutex_lock_double(&gctx->mutex, &ctx->mutex); + gctx = __perf_event_ctx_lock_double(group_leader, ctx); + if (gctx->task == TASK_TOMBSTONE) { err = -ESRCH; goto err_locked; } + + /* + * Check if we raced against another sys_perf_event_open() call + * moving the software group underneath us. + */ + if (!(group_leader->group_caps & PERF_EV_CAP_SOFTWARE)) { + /* + * If someone moved the group out from under us, check + * if this new event wound up on the same ctx, if so + * its the regular !move_group case, otherwise fail. + */ + if (gctx != ctx) { + err = -EINVAL; + goto err_locked; + } else { + perf_event_ctx_unlock(group_leader, gctx); + move_group = 0; + } + } } else { mutex_lock(&ctx->mutex); } @@ -9853,7 +9944,7 @@ SYSCALL_DEFINE5(perf_event_open, perf_unpin_context(ctx); if (move_group) - mutex_unlock(&gctx->mutex); + perf_event_ctx_unlock(group_leader, gctx); mutex_unlock(&ctx->mutex); if (task) { @@ -9879,7 +9970,7 @@ SYSCALL_DEFINE5(perf_event_open, err_locked: if (move_group) - mutex_unlock(&gctx->mutex); + perf_event_ctx_unlock(group_leader, gctx); mutex_unlock(&ctx->mutex); /* err_file: */ fput(event_file); diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 93ad6c1fb9b6..a9b8cf500591 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -182,6 +182,13 @@ void static_key_slow_dec_deferred(struct static_key_deferred *key) } EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred); +void static_key_deferred_flush(struct static_key_deferred *key) +{ + STATIC_KEY_CHECK_USE(); + flush_delayed_work(&key->work); +} +EXPORT_SYMBOL_GPL(static_key_deferred_flush); + void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) { diff --git a/kernel/memremap.c b/kernel/memremap.c index b501e390bb34..9ecedc28b928 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -246,7 +246,9 @@ static void devm_memremap_pages_release(struct device *dev, void *data) /* pages are dead and unused, undo the arch mapping */ align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(resource_size(res), SECTION_SIZE); + mem_hotplug_begin(); arch_remove_memory(align_start, align_size); + mem_hotplug_done(); untrack_pfn(NULL, PHYS_PFN(align_start), align_size); pgmap_radix_release(res); dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc, @@ -358,7 +360,9 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, if (error) goto err_pfn_remap; + mem_hotplug_begin(); error = arch_add_memory(nid, align_start, align_size, true); + mem_hotplug_done(); if (error) goto err_add_memory; diff --git a/kernel/signal.c b/kernel/signal.c index ff046b73ff2d..3603d93a1968 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -346,7 +346,7 @@ static bool task_participate_group_stop(struct task_struct *task) * fresh group stop. Read comment in do_signal_stop() for details. */ if (!sig->group_stop_count && !(sig->flags & SIGNAL_STOP_STOPPED)) { - sig->flags = SIGNAL_STOP_STOPPED; + signal_set_stop_flags(sig, SIGNAL_STOP_STOPPED); return true; } return false; @@ -843,7 +843,7 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force) * will take ->siglock, notice SIGNAL_CLD_MASK, and * notify its parent. See get_signal_to_deliver(). */ - signal->flags = why | SIGNAL_STOP_CONTINUED; + signal_set_stop_flags(signal, why | SIGNAL_STOP_CONTINUED); signal->group_stop_count = 0; signal->group_exit_code = 0; } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 2c115fdab397..74e0388cc88d 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -767,7 +767,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, tick = expires; /* Skip reprogram of event if its not changed */ - if (ts->tick_stopped && (expires == dev->next_event)) + if (ts->tick_stopped && (expires == ts->next_tick)) goto out; /* @@ -787,6 +787,8 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, trace_tick_stop(1, TICK_DEP_MASK_NONE); } + ts->next_tick = tick; + /* * If the expiration time == KTIME_MAX, then we simply stop * the tick timer. @@ -802,7 +804,10 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, else tick_program_event(tick, 1); out: - /* Update the estimated sleep length */ + /* + * Update the estimated sleep length until the next timer + * (not only the tick). + */ ts->sleep_length = ktime_sub(dev->next_event, now); return tick; } diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index bf38226e5c17..075444e3d48e 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -27,6 +27,7 @@ enum tick_nohz_mode { * timer is modified for nohz sleeps. This is necessary * to resume the tick timer operation in the timeline * when the CPU returns from nohz sleep. + * @next_tick: Next tick to be fired when in dynticks mode. * @tick_stopped: Indicator that the idle tick has been stopped * @idle_jiffies: jiffies at the entry to idle for idle time accounting * @idle_calls: Total number of idle calls @@ -44,6 +45,7 @@ struct tick_sched { unsigned long check_clocks; enum tick_nohz_mode nohz_mode; ktime_t last_tick; + ktime_t next_tick; int inidle; int tick_stopped; unsigned long idle_jiffies; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index b06848a104e6..eb9e9a7870fa 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -164,7 +164,7 @@ config DEBUG_INFO_REDUCED config DEBUG_INFO_SPLIT bool "Produce split debuginfo in .dwo files" - depends on DEBUG_INFO + depends on DEBUG_INFO && !FRV help Generate debug info into separate .dwo files. This significantly reduces the build directory size for builds with DEBUG_INFO, diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 25f572303801..e68604ae3ced 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -730,43 +730,50 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, } EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); +static inline void pipe_truncate(struct iov_iter *i) +{ + struct pipe_inode_info *pipe = i->pipe; + if (pipe->nrbufs) { + size_t off = i->iov_offset; + int idx = i->idx; + int nrbufs = (idx - pipe->curbuf) & (pipe->buffers - 1); + if (off) { + pipe->bufs[idx].len = off - pipe->bufs[idx].offset; + idx = next_idx(idx, pipe); + nrbufs++; + } + while (pipe->nrbufs > nrbufs) { + pipe_buf_release(pipe, &pipe->bufs[idx]); + idx = next_idx(idx, pipe); + pipe->nrbufs--; + } + } +} + static void pipe_advance(struct iov_iter *i, size_t size) { struct pipe_inode_info *pipe = i->pipe; - struct pipe_buffer *buf; - int idx = i->idx; - size_t off = i->iov_offset, orig_sz; - if (unlikely(i->count < size)) size = i->count; - orig_sz = size; - if (size) { + struct pipe_buffer *buf; + size_t off = i->iov_offset, left = size; + int idx = i->idx; if (off) /* make it relative to the beginning of buffer */ - size += off - pipe->bufs[idx].offset; + left += off - pipe->bufs[idx].offset; while (1) { buf = &pipe->bufs[idx]; - if (size <= buf->len) + if (left <= buf->len) break; - size -= buf->len; + left -= buf->len; idx = next_idx(idx, pipe); } - buf->len = size; i->idx = idx; - off = i->iov_offset = buf->offset + size; - } - if (off) - idx = next_idx(idx, pipe); - if (pipe->nrbufs) { - int unused = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1); - /* [curbuf,unused) is in use. Free [idx,unused) */ - while (idx != unused) { - pipe_buf_release(pipe, &pipe->bufs[idx]); - idx = next_idx(idx, pipe); - pipe->nrbufs--; - } + i->iov_offset = buf->offset + left; } - i->count -= orig_sz; + i->count -= size; + /* ... and discard everything past that point */ + pipe_truncate(i); } void iov_iter_advance(struct iov_iter *i, size_t size) @@ -826,6 +833,7 @@ void iov_iter_pipe(struct iov_iter *i, int direction, size_t count) { BUG_ON(direction != ITER_PIPE); + WARN_ON(pipe->nrbufs == pipe->buffers); i->type = direction; i->pipe = pipe; i->idx = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1); diff --git a/mm/filemap.c b/mm/filemap.c index d0e4d1002059..b772a33ef640 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -138,7 +138,7 @@ static int page_cache_tree_insert(struct address_space *mapping, dax_radix_locked_entry(0, RADIX_DAX_EMPTY)); /* Wakeup waiters for exceptional entry lock */ dax_wake_mapping_entry_waiter(mapping, page->index, p, - false); + true); } } __radix_tree_replace(&mapping->page_tree, node, slot, page, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 10eedbf14421..9a6bd6c8d55a 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -883,15 +883,17 @@ void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd) { pmd_t entry; unsigned long haddr; + bool write = vmf->flags & FAULT_FLAG_WRITE; vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) goto unlock; entry = pmd_mkyoung(orig_pmd); + if (write) + entry = pmd_mkdirty(entry); haddr = vmf->address & HPAGE_PMD_MASK; - if (pmdp_set_access_flags(vmf->vma, haddr, vmf->pmd, entry, - vmf->flags & FAULT_FLAG_WRITE)) + if (pmdp_set_access_flags(vmf->vma, haddr, vmf->pmd, entry, write)) update_mmu_cache_pmd(vmf->vma, vmf->address, vmf->pmd); unlock: @@ -919,8 +921,7 @@ static int do_huge_pmd_wp_page_fallback(struct vm_fault *vmf, pmd_t orig_pmd, } for (i = 0; i < HPAGE_PMD_NR; i++) { - pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE | - __GFP_OTHER_NODE, vma, + pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE, vma, vmf->address, page_to_nid(page)); if (unlikely(!pages[i] || mem_cgroup_try_charge(pages[i], vma->vm_mm, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3edb759c5c7d..c7025c132670 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1773,23 +1773,32 @@ free: } /* - * When releasing a hugetlb pool reservation, any surplus pages that were - * allocated to satisfy the reservation must be explicitly freed if they were - * never used. - * Called with hugetlb_lock held. + * This routine has two main purposes: + * 1) Decrement the reservation count (resv_huge_pages) by the value passed + * in unused_resv_pages. This corresponds to the prior adjustments made + * to the associated reservation map. + * 2) Free any unused surplus pages that may have been allocated to satisfy + * the reservation. As many as unused_resv_pages may be freed. + * + * Called with hugetlb_lock held. However, the lock could be dropped (and + * reacquired) during calls to cond_resched_lock. Whenever dropping the lock, + * we must make sure nobody else can claim pages we are in the process of + * freeing. Do this by ensuring resv_huge_page always is greater than the + * number of huge pages we plan to free when dropping the lock. */ static void return_unused_surplus_pages(struct hstate *h, unsigned long unused_resv_pages) { unsigned long nr_pages; - /* Uncommit the reservation */ - h->resv_huge_pages -= unused_resv_pages; - /* Cannot return gigantic pages currently */ if (hstate_is_gigantic(h)) - return; + goto out; + /* + * Part (or even all) of the reservation could have been backed + * by pre-allocated pages. Only free surplus pages. + */ nr_pages = min(unused_resv_pages, h->surplus_huge_pages); /* @@ -1799,12 +1808,22 @@ static void return_unused_surplus_pages(struct hstate *h, * when the nodes with surplus pages have no free pages. * free_pool_huge_page() will balance the the freed pages across the * on-line nodes with memory and will handle the hstate accounting. + * + * Note that we decrement resv_huge_pages as we free the pages. If + * we drop the lock, resv_huge_pages will still be sufficiently large + * to cover subsequent pages we may free. */ while (nr_pages--) { + h->resv_huge_pages--; + unused_resv_pages--; if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1)) - break; + goto out; cond_resched_lock(&hugetlb_lock); } + +out: + /* Fully uncommit the reservation */ + h->resv_huge_pages -= unused_resv_pages; } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index e32389a97030..77ae3239c3de 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -943,7 +943,7 @@ static void collapse_huge_page(struct mm_struct *mm, VM_BUG_ON(address & ~HPAGE_PMD_MASK); /* Only allocate from the target node */ - gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_OTHER_NODE | __GFP_THISNODE; + gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE; /* * Before allocating the hugepage, release the mmap_sem read lock. @@ -1242,7 +1242,6 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) struct vm_area_struct *vma; unsigned long addr; pmd_t *pmd, _pmd; - bool deposited = false; i_mmap_lock_write(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { @@ -1267,26 +1266,10 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) spinlock_t *ptl = pmd_lock(vma->vm_mm, pmd); /* assume page table is clear */ _pmd = pmdp_collapse_flush(vma, addr, pmd); - /* - * now deposit the pgtable for arch that need it - * otherwise free it. - */ - if (arch_needs_pgtable_deposit()) { - /* - * The deposit should be visibile only after - * collapse is seen by others. - */ - smp_wmb(); - pgtable_trans_huge_deposit(vma->vm_mm, pmd, - pmd_pgtable(_pmd)); - deposited = true; - } spin_unlock(ptl); up_write(&vma->vm_mm->mmap_sem); - if (!deposited) { - atomic_long_dec(&vma->vm_mm->nr_ptes); - pte_free(vma->vm_mm, pmd_pgtable(_pmd)); - } + atomic_long_dec(&vma->vm_mm->nr_ptes); + pte_free(vma->vm_mm, pmd_pgtable(_pmd)); } } i_mmap_unlock_write(mapping); @@ -1326,8 +1309,7 @@ static void collapse_shmem(struct mm_struct *mm, VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); /* Only allocate from the target node */ - gfp = alloc_hugepage_khugepaged_gfpmask() | - __GFP_OTHER_NODE | __GFP_THISNODE; + gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE; new_page = khugepaged_alloc_page(hpage, gfp, node); if (!new_page) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4048897e7b01..a63a8f832664 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -625,8 +625,8 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, int nid, unsigned int lru_mask) { + struct lruvec *lruvec = mem_cgroup_lruvec(NODE_DATA(nid), memcg); unsigned long nr = 0; - struct mem_cgroup_per_node *mz; enum lru_list lru; VM_BUG_ON((unsigned)nid >= nr_node_ids); @@ -634,8 +634,7 @@ unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, for_each_lru(lru) { if (!(BIT(lru) & lru_mask)) continue; - mz = mem_cgroup_nodeinfo(memcg, nid); - nr += mz->lru_size[lru]; + nr += mem_cgroup_get_lru_size(lruvec, lru); } return nr; } @@ -1002,6 +1001,7 @@ out: * mem_cgroup_update_lru_size - account for adding or removing an lru page * @lruvec: mem_cgroup per zone lru vector * @lru: index of lru list the page is sitting on + * @zid: zone id of the accounted pages * @nr_pages: positive when adding or negative when removing * * This function must be called under lru_lock, just before a page is added @@ -1009,27 +1009,25 @@ out: * so as to allow it to check that lru_size 0 is consistent with list_empty). */ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, - int nr_pages) + int zid, int nr_pages) { struct mem_cgroup_per_node *mz; unsigned long *lru_size; long size; - bool empty; if (mem_cgroup_disabled()) return; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - lru_size = mz->lru_size + lru; - empty = list_empty(lruvec->lists + lru); + lru_size = &mz->lru_zone_size[zid][lru]; if (nr_pages < 0) *lru_size += nr_pages; size = *lru_size; - if (WARN_ONCE(size < 0 || empty != !size, - "%s(%p, %d, %d): lru_size %ld but %sempty\n", - __func__, lruvec, lru, nr_pages, size, empty ? "" : "not ")) { + if (WARN_ONCE(size < 0, + "%s(%p, %d, %d): lru_size %ld\n", + __func__, lruvec, lru, nr_pages, size)) { VM_BUG_ON(1); *lru_size = 0; } diff --git a/mm/memory.c b/mm/memory.c index 9f2c15cdb32c..6bf2b471e30c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3772,8 +3772,8 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) } #endif /* __PAGETABLE_PMD_FOLDED */ -static int __follow_pte(struct mm_struct *mm, unsigned long address, - pte_t **ptepp, spinlock_t **ptlp) +static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) { pgd_t *pgd; pud_t *pud; @@ -3790,11 +3790,20 @@ static int __follow_pte(struct mm_struct *mm, unsigned long address, pmd = pmd_offset(pud, address); VM_BUG_ON(pmd_trans_huge(*pmd)); - if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) - goto out; - /* We cannot handle huge page PFN maps. Luckily they don't exist. */ - if (pmd_huge(*pmd)) + if (pmd_huge(*pmd)) { + if (!pmdpp) + goto out; + + *ptlp = pmd_lock(mm, pmd); + if (pmd_huge(*pmd)) { + *pmdpp = pmd; + return 0; + } + spin_unlock(*ptlp); + } + + if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) goto out; ptep = pte_offset_map_lock(mm, pmd, address, ptlp); @@ -3810,16 +3819,30 @@ out: return -EINVAL; } -int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, - spinlock_t **ptlp) +static inline int follow_pte(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, spinlock_t **ptlp) +{ + int res; + + /* (void) is needed to make gcc happy */ + (void) __cond_lock(*ptlp, + !(res = __follow_pte_pmd(mm, address, ptepp, NULL, + ptlp))); + return res; +} + +int follow_pte_pmd(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) { int res; /* (void) is needed to make gcc happy */ (void) __cond_lock(*ptlp, - !(res = __follow_pte(mm, address, ptepp, ptlp))); + !(res = __follow_pte_pmd(mm, address, ptepp, pmdpp, + ptlp))); return res; } +EXPORT_SYMBOL(follow_pte_pmd); /** * follow_pfn - look up PFN at a user virtual address diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2c6d5f64feca..d604d2596b7b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1864,14 +1864,14 @@ int move_freepages(struct zone *zone, #endif for (page = start_page; page <= end_page;) { - /* Make sure we are not inadvertently changing nodes */ - VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page); - if (!pfn_valid_within(page_to_pfn(page))) { page++; continue; } + /* Make sure we are not inadvertently changing nodes */ + VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page); + if (!PageBuddy(page)) { page++; continue; @@ -2583,30 +2583,22 @@ int __isolate_free_page(struct page *page, unsigned int order) * Update NUMA hit/miss statistics * * Must be called with interrupts disabled. - * - * When __GFP_OTHER_NODE is set assume the node of the preferred - * zone is the local node. This is useful for daemons who allocate - * memory on behalf of other processes. */ -static inline void zone_statistics(struct zone *preferred_zone, struct zone *z, - gfp_t flags) +static inline void zone_statistics(struct zone *preferred_zone, struct zone *z) { #ifdef CONFIG_NUMA - int local_nid = numa_node_id(); enum zone_stat_item local_stat = NUMA_LOCAL; - if (unlikely(flags & __GFP_OTHER_NODE)) { + if (z->node != numa_node_id()) local_stat = NUMA_OTHER; - local_nid = preferred_zone->node; - } - if (z->node == local_nid) { + if (z->node == preferred_zone->node) __inc_zone_state(z, NUMA_HIT); - __inc_zone_state(z, local_stat); - } else { + else { __inc_zone_state(z, NUMA_MISS); __inc_zone_state(preferred_zone, NUMA_FOREIGN); } + __inc_zone_state(z, local_stat); #endif } @@ -2674,7 +2666,7 @@ struct page *buffered_rmqueue(struct zone *preferred_zone, } __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); - zone_statistics(preferred_zone, zone, gfp_flags); + zone_statistics(preferred_zone, zone); local_irq_restore(flags); VM_BUG_ON_PAGE(bad_range(zone, page), page); @@ -3904,8 +3896,8 @@ EXPORT_SYMBOL(free_pages); * drivers to provide a backing region of memory for use as either an * sk_buff->head, or to be used in the "frags" portion of skb_shared_info. */ -static struct page *__page_frag_refill(struct page_frag_cache *nc, - gfp_t gfp_mask) +static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, + gfp_t gfp_mask) { struct page *page = NULL; gfp_t gfp = gfp_mask; @@ -3925,22 +3917,23 @@ static struct page *__page_frag_refill(struct page_frag_cache *nc, return page; } -void __page_frag_drain(struct page *page, unsigned int order, - unsigned int count) +void __page_frag_cache_drain(struct page *page, unsigned int count) { VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); if (page_ref_sub_and_test(page, count)) { + unsigned int order = compound_order(page); + if (order == 0) free_hot_cold_page(page, false); else __free_pages_ok(page, order); } } -EXPORT_SYMBOL(__page_frag_drain); +EXPORT_SYMBOL(__page_frag_cache_drain); -void *__alloc_page_frag(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask) +void *page_frag_alloc(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask) { unsigned int size = PAGE_SIZE; struct page *page; @@ -3948,7 +3941,7 @@ void *__alloc_page_frag(struct page_frag_cache *nc, if (unlikely(!nc->va)) { refill: - page = __page_frag_refill(nc, gfp_mask); + page = __page_frag_cache_refill(nc, gfp_mask); if (!page) return NULL; @@ -3991,19 +3984,19 @@ refill: return nc->va + offset; } -EXPORT_SYMBOL(__alloc_page_frag); +EXPORT_SYMBOL(page_frag_alloc); /* * Frees a page fragment allocated out of either a compound or order 0 page. */ -void __free_page_frag(void *addr) +void page_frag_free(void *addr) { struct page *page = virt_to_head_page(addr); if (unlikely(put_page_testzero(page))) __free_pages_ok(page, compound_order(page)); } -EXPORT_SYMBOL(__free_page_frag); +EXPORT_SYMBOL(page_frag_free); static void *make_alloc_exact(unsigned long addr, unsigned int order, size_t size) diff --git a/mm/slab.c b/mm/slab.c index 29bc6c0dedd0..4f2ec6bb46eb 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2457,7 +2457,6 @@ union freelist_init_state { unsigned int pos; unsigned int *list; unsigned int count; - unsigned int rand; }; struct rnd_state rnd_state; }; @@ -2483,8 +2482,7 @@ static bool freelist_state_initialize(union freelist_init_state *state, } else { state->list = cachep->random_seq; state->count = count; - state->pos = 0; - state->rand = rand; + state->pos = rand % count; ret = true; } return ret; @@ -2493,7 +2491,9 @@ static bool freelist_state_initialize(union freelist_init_state *state, /* Get the next entry on the list and randomize it using a random shift */ static freelist_idx_t next_random_slot(union freelist_init_state *state) { - return (state->list[state->pos++] + state->rand) % state->count; + if (state->pos >= state->count) + state->pos = 0; + return state->list[state->pos++]; } /* Swap two freelist entries */ diff --git a/mm/swapfile.c b/mm/swapfile.c index 1c6e0321205d..4761701d1721 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -943,11 +943,25 @@ bool reuse_swap_page(struct page *page, int *total_mapcount) count = page_trans_huge_mapcount(page, total_mapcount); if (count <= 1 && PageSwapCache(page)) { count += page_swapcount(page); - if (count == 1 && !PageWriteback(page)) { + if (count != 1) + goto out; + if (!PageWriteback(page)) { delete_from_swap_cache(page); SetPageDirty(page); + } else { + swp_entry_t entry; + struct swap_info_struct *p; + + entry.val = page_private(page); + p = swap_info_get(entry); + if (p->flags & SWP_STABLE_WRITES) { + spin_unlock(&p->lock); + return false; + } + spin_unlock(&p->lock); } } +out: return count <= 1; } @@ -2448,6 +2462,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = -ENOMEM; goto bad_swap; } + + if (bdi_cap_stable_pages_required(inode_to_bdi(inode))) + p->flags |= SWP_STABLE_WRITES; + if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) { int cpu; diff --git a/mm/vmscan.c b/mm/vmscan.c index 6aa5b01d3e75..532a2a750952 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -242,6 +242,16 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru) return node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru); } +unsigned long lruvec_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, + int zone_idx) +{ + if (!mem_cgroup_disabled()) + return mem_cgroup_get_zone_lru_size(lruvec, lru, zone_idx); + + return zone_page_state(&lruvec_pgdat(lruvec)->node_zones[zone_idx], + NR_ZONE_LRU_BASE + lru); +} + /* * Add a shrinker callback to be called from the vm. */ @@ -1382,8 +1392,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode) * be complete before mem_cgroup_update_lru_size due to a santity check. */ static __always_inline void update_lru_sizes(struct lruvec *lruvec, - enum lru_list lru, unsigned long *nr_zone_taken, - unsigned long nr_taken) + enum lru_list lru, unsigned long *nr_zone_taken) { int zid; @@ -1392,11 +1401,11 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec, continue; __update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); - } - #ifdef CONFIG_MEMCG - mem_cgroup_update_lru_size(lruvec, lru, -nr_taken); + mem_cgroup_update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); #endif + } + } /* @@ -1501,7 +1510,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, *nr_scanned = scan; trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan, nr_taken, mode, is_file_lru(lru)); - update_lru_sizes(lruvec, lru, nr_zone_taken, nr_taken); + update_lru_sizes(lruvec, lru, nr_zone_taken); return nr_taken; } @@ -2047,10 +2056,8 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, if (!managed_zone(zone)) continue; - inactive_zone = zone_page_state(zone, - NR_ZONE_LRU_BASE + (file * LRU_FILE)); - active_zone = zone_page_state(zone, - NR_ZONE_LRU_BASE + (file * LRU_FILE) + LRU_ACTIVE); + inactive_zone = lruvec_zone_lru_size(lruvec, file * LRU_FILE, zid); + active_zone = lruvec_zone_lru_size(lruvec, (file * LRU_FILE) + LRU_ACTIVE, zid); inactive -= min(inactive, inactive_zone); active -= min(active, active_zone); diff --git a/net/Kconfig b/net/Kconfig index a1005007224c..a29bb4b41c50 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -258,10 +258,6 @@ config XPS config HWBM bool -config SOCK_CGROUP_DATA - bool - default n - config CGROUP_NET_PRIO bool "Network priority cgroup" depends on CGROUPS diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 8ca6a929bf12..95087e6e8258 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -399,7 +399,7 @@ bridged_dnat: br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL, - br_nf_pre_routing_finish); + br_nf_pre_routing_finish_bridge); return 0; } ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr); diff --git a/net/core/dev.c b/net/core/dev.c index 8db5a0b4b520..07b307b0b414 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4441,7 +4441,9 @@ static void skb_gro_reset_offset(struct sk_buff *skb) pinfo->nr_frags && !PageHighMem(skb_frag_page(frag0))) { NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); - NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0); + NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, + skb_frag_size(frag0), + skb->end - skb->tail); } } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index fe4e1531976c..1b7673aac59d 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -67,8 +67,8 @@ EXPORT_SYMBOL(skb_flow_dissector_init); * The function will try to retrieve a be32 entity at * offset poff */ -__be16 skb_flow_get_be16(const struct sk_buff *skb, int poff, void *data, - int hlen) +static __be16 skb_flow_get_be16(const struct sk_buff *skb, int poff, + void *data, int hlen) { __be16 *u, _u; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5a03730fbc1a..734c71468b01 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -369,7 +369,7 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) local_irq_save(flags); nc = this_cpu_ptr(&netdev_alloc_cache); - data = __alloc_page_frag(nc, fragsz, gfp_mask); + data = page_frag_alloc(nc, fragsz, gfp_mask); local_irq_restore(flags); return data; } @@ -391,7 +391,7 @@ static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); - return __alloc_page_frag(&nc->page, fragsz, gfp_mask); + return page_frag_alloc(&nc->page, fragsz, gfp_mask); } void *napi_alloc_frag(unsigned int fragsz) @@ -441,7 +441,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, local_irq_save(flags); nc = this_cpu_ptr(&netdev_alloc_cache); - data = __alloc_page_frag(nc, len, gfp_mask); + data = page_frag_alloc(nc, len, gfp_mask); pfmemalloc = nc->pfmemalloc; local_irq_restore(flags); @@ -505,7 +505,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; - data = __alloc_page_frag(&nc->page, len, gfp_mask); + data = page_frag_alloc(&nc->page, len, gfp_mask); if (unlikely(!data)) return NULL; diff --git a/net/core/sock.c b/net/core/sock.c index f560e0826009..4eca27dc5c94 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -222,7 +222,7 @@ static const char *const af_family_key_strings[AF_MAX+1] = { "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" , "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" , "sk_lock-AF_NFC" , "sk_lock-AF_VSOCK" , "sk_lock-AF_KCM" , - "sk_lock-AF_MAX" + "sk_lock-AF_QIPCRTR", "sk_lock-AF_MAX" }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" , @@ -239,7 +239,7 @@ static const char *const af_family_slock_key_strings[AF_MAX+1] = { "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" , "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" , "slock-AF_NFC" , "slock-AF_VSOCK" ,"slock-AF_KCM" , - "slock-AF_MAX" + "slock-AF_QIPCRTR", "slock-AF_MAX" }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { "clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" , @@ -256,7 +256,7 @@ static const char *const af_family_clock_key_strings[AF_MAX+1] = { "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" , "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" , "clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_KCM" , - "clock-AF_MAX" + "clock-AF_QIPCRTR", "clock-AF_MAX" }; /* diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 5fff951a0a49..da3862124545 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -394,9 +394,11 @@ static int dsa_dst_apply(struct dsa_switch_tree *dst) return err; } - err = dsa_cpu_port_ethtool_setup(dst->ds[0]); - if (err) - return err; + if (dst->ds[0]) { + err = dsa_cpu_port_ethtool_setup(dst->ds[0]); + if (err) + return err; + } /* If we use a tagging format that doesn't have an ethertype * field, make sure that all packets from this point on get @@ -433,7 +435,8 @@ static void dsa_dst_unapply(struct dsa_switch_tree *dst) dsa_ds_unapply(dst, ds); } - dsa_cpu_port_ethtool_restore(dst->ds[0]); + if (dst->ds[0]) + dsa_cpu_port_ethtool_restore(dst->ds[0]); pr_info("DSA: tree %d unapplied\n", dst->tree); dst->applied = false; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 7a5b4c7d9a87..eba1546b5031 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1618,8 +1618,13 @@ void fib_select_multipath(struct fib_result *res, int hash) void fib_select_path(struct net *net, struct fib_result *res, struct flowi4 *fl4, int mp_hash) { + bool oif_check; + + oif_check = (fl4->flowi4_oif == 0 || + fl4->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF); + #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (res->fi->fib_nhs > 1 && fl4->flowi4_oif == 0) { + if (res->fi->fib_nhs > 1 && oif_check) { if (mp_hash < 0) mp_hash = get_hash_from_flowi4(fl4) >> 1; @@ -1629,7 +1634,7 @@ void fib_select_path(struct net *net, struct fib_result *res, #endif if (!res->prefixlen && res->table->tb_num_default > 1 && - res->type == RTN_UNICAST && !fl4->flowi4_oif) + res->type == RTN_UNICAST && oif_check) fib_select_default(fl4, res); if (!fl4->saddr) diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 21db00d0362b..a6b8c1a4102b 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -144,7 +144,7 @@ clusterip_config_find_get(struct net *net, __be32 clusterip, int entry) rcu_read_lock_bh(); c = __clusterip_config_find(net, clusterip); if (c) { - if (unlikely(!atomic_inc_not_zero(&c->refcount))) + if (!c->pde || unlikely(!atomic_inc_not_zero(&c->refcount))) c = NULL; else if (entry) atomic_inc(&c->entries); @@ -166,14 +166,15 @@ clusterip_config_init_nodelist(struct clusterip_config *c, static struct clusterip_config * clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip, - struct net_device *dev) + struct net_device *dev) { + struct net *net = dev_net(dev); struct clusterip_config *c; - struct clusterip_net *cn = net_generic(dev_net(dev), clusterip_net_id); + struct clusterip_net *cn = net_generic(net, clusterip_net_id); c = kzalloc(sizeof(*c), GFP_ATOMIC); if (!c) - return NULL; + return ERR_PTR(-ENOMEM); c->dev = dev; c->clusterip = ip; @@ -185,6 +186,17 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip, atomic_set(&c->refcount, 1); atomic_set(&c->entries, 1); + spin_lock_bh(&cn->lock); + if (__clusterip_config_find(net, ip)) { + spin_unlock_bh(&cn->lock); + kfree(c); + + return ERR_PTR(-EBUSY); + } + + list_add_rcu(&c->list, &cn->configs); + spin_unlock_bh(&cn->lock); + #ifdef CONFIG_PROC_FS { char buffer[16]; @@ -195,16 +207,16 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip, cn->procdir, &clusterip_proc_fops, c); if (!c->pde) { + spin_lock_bh(&cn->lock); + list_del_rcu(&c->list); + spin_unlock_bh(&cn->lock); kfree(c); - return NULL; + + return ERR_PTR(-ENOMEM); } } #endif - spin_lock_bh(&cn->lock); - list_add_rcu(&c->list, &cn->configs); - spin_unlock_bh(&cn->lock); - return c; } @@ -410,9 +422,9 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) config = clusterip_config_init(cipinfo, e->ip.dst.s_addr, dev); - if (!config) { + if (IS_ERR(config)) { dev_put(dev); - return -ENOMEM; + return PTR_ERR(config); } dev_mc_add(config->dev, config->clustermac); } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 22cbd61079b5..b2fa498b15d1 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -951,7 +951,7 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_tcp_notsent_lowat, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_douintvec, }, { .procname = "tcp_tw_reuse", diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index d46f4d5b1c62..ba8f02d0f283 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -606,7 +606,6 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, return ret; } -EXPORT_SYMBOL_GPL(tcp_peer_is_proven); void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst) { diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 89c59e656f44..fc7b4017ba24 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -191,6 +191,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, ops = rcu_dereference(inet6_offloads[proto]); if (!ops || !ops->callbacks.gro_receive) { __pskb_pull(skb, skb_gro_offset(skb)); + skb_gro_frag0_invalidate(skb); proto = ipv6_gso_pull_exthdrs(skb, proto); skb_gro_pull(skb, -skb_transport_offset(skb)); skb_reset_transport_header(skb); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index f4b4a4a5f4ba..d82042c8d8fd 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -189,12 +189,12 @@ static int vti6_tnl_create2(struct net_device *dev) struct vti6_net *ip6n = net_generic(net, vti6_net_id); int err; + dev->rtnl_link_ops = &vti6_link_ops; err = register_netdevice(dev); if (err < 0) goto out; strcpy(t->parms.name, dev->name); - dev->rtnl_link_ops = &vti6_link_ops; dev_hold(dev); vti6_tnl_link(ip6n, t); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8417c41d8ec8..ce5aaf448c54 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1464,7 +1464,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, struct fib6_node *fn; /* Get the "current" route for this destination and - * check if the redirect has come from approriate router. + * check if the redirect has come from appropriate router. * * RFC 4861 specifies that redirects should only be * accepted if they come from the nexthop to the target. @@ -2768,7 +2768,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) old MTU is the lowest MTU in the path, update the route PMTU to reflect the increase. In this case if the other nodes' MTU also have the lowest MTU, TOO BIG MESSAGE will be lead to - PMTU discouvery. + PMTU discovery. */ if (rt->dst.dev == arg->dev && dst_metric_raw(&rt->dst, RTAX_MTU) && diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index cfb9e5f4e28f..13190b38f22e 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1044,7 +1044,8 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; struct iucv_sock *iucv = iucv_sk(sk); - size_t headroom, linear; + size_t headroom = 0; + size_t linear; struct sk_buff *skb; struct iucv_message txmsg = {0}; struct cmsghdr *cmsg; @@ -1122,18 +1123,20 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, * this is fine for SOCK_SEQPACKET (unless we want to support * segmented records using the MSG_EOR flag), but * for SOCK_STREAM we might want to improve it in future */ - headroom = (iucv->transport == AF_IUCV_TRANS_HIPER) - ? sizeof(struct af_iucv_trans_hdr) + ETH_HLEN : 0; - if (headroom + len < PAGE_SIZE) { + if (iucv->transport == AF_IUCV_TRANS_HIPER) { + headroom = sizeof(struct af_iucv_trans_hdr) + ETH_HLEN; linear = len; } else { - /* In nonlinear "classic" iucv skb, - * reserve space for iucv_array - */ - if (iucv->transport != AF_IUCV_TRANS_HIPER) - headroom += sizeof(struct iucv_array) * - (MAX_SKB_FRAGS + 1); - linear = PAGE_SIZE - headroom; + if (len < PAGE_SIZE) { + linear = len; + } else { + /* In nonlinear "classic" iucv skb, + * reserve space for iucv_array + */ + headroom = sizeof(struct iucv_array) * + (MAX_SKB_FRAGS + 1); + linear = PAGE_SIZE - headroom; + } } skb = sock_alloc_send_pskb(sk, headroom + linear, len - linear, noblock, &err, 0); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a019a87e58ee..0db5f9782265 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2115,7 +2115,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, * is called on error from nf_tables_newrule(). */ expr = nft_expr_first(rule); - while (expr->ops && expr != nft_expr_last(rule)) { + while (expr != nft_expr_last(rule) && expr->ops) { nf_tables_expr_destroy(ctx, expr); expr = nft_expr_next(expr); } diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 36d2b1096546..7d699bbd45b0 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -250,6 +250,22 @@ static int nft_payload_l4csum_update(const struct nft_pktinfo *pkt, return 0; } +static int nft_payload_csum_inet(struct sk_buff *skb, const u32 *src, + __wsum fsum, __wsum tsum, int csum_offset) +{ + __sum16 sum; + + if (skb_copy_bits(skb, csum_offset, &sum, sizeof(sum)) < 0) + return -1; + + nft_csum_replace(&sum, fsum, tsum); + if (!skb_make_writable(skb, csum_offset + sizeof(sum)) || + skb_store_bits(skb, csum_offset, &sum, sizeof(sum)) < 0) + return -1; + + return 0; +} + static void nft_payload_set_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -259,7 +275,6 @@ static void nft_payload_set_eval(const struct nft_expr *expr, const u32 *src = ®s->data[priv->sreg]; int offset, csum_offset; __wsum fsum, tsum; - __sum16 sum; switch (priv->base) { case NFT_PAYLOAD_LL_HEADER: @@ -282,18 +297,14 @@ static void nft_payload_set_eval(const struct nft_expr *expr, csum_offset = offset + priv->csum_offset; offset += priv->offset; - if (priv->csum_type == NFT_PAYLOAD_CSUM_INET && + if ((priv->csum_type == NFT_PAYLOAD_CSUM_INET || priv->csum_flags) && (priv->base != NFT_PAYLOAD_TRANSPORT_HEADER || skb->ip_summed != CHECKSUM_PARTIAL)) { - if (skb_copy_bits(skb, csum_offset, &sum, sizeof(sum)) < 0) - goto err; - fsum = skb_checksum(skb, offset, priv->len, 0); tsum = csum_partial(src, priv->len, 0); - nft_csum_replace(&sum, fsum, tsum); - if (!skb_make_writable(skb, csum_offset + sizeof(sum)) || - skb_store_bits(skb, csum_offset, &sum, sizeof(sum)) < 0) + if (priv->csum_type == NFT_PAYLOAD_CSUM_INET && + nft_payload_csum_inet(skb, src, fsum, tsum, csum_offset)) goto err; if (priv->csum_flags && diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index 3e19fa1230dc..dbb6aaff67ec 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -38,7 +38,7 @@ static void nft_queue_eval(const struct nft_expr *expr, if (priv->queues_total > 1) { if (priv->flags & NFT_QUEUE_FLAG_CPU_FANOUT) { - int cpu = smp_processor_id(); + int cpu = raw_smp_processor_id(); queue = priv->queuenum + cpu % priv->queues_total; } else { diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index bd6efc53f26d..2d6fe3559912 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -110,30 +110,32 @@ static int nft_quota_obj_init(const struct nlattr * const tb[], static int nft_quota_do_dump(struct sk_buff *skb, struct nft_quota *priv, bool reset) { + u64 consumed, consumed_cap; u32 flags = priv->flags; - u64 consumed; - - if (reset) { - consumed = atomic64_xchg(&priv->consumed, 0); - if (test_and_clear_bit(NFT_QUOTA_DEPLETED_BIT, &priv->flags)) - flags |= NFT_QUOTA_F_DEPLETED; - } else { - consumed = atomic64_read(&priv->consumed); - } /* Since we inconditionally increment consumed quota for each packet * that we see, don't go over the quota boundary in what we send to * userspace. */ - if (consumed > priv->quota) - consumed = priv->quota; + consumed = atomic64_read(&priv->consumed); + if (consumed >= priv->quota) { + consumed_cap = priv->quota; + flags |= NFT_QUOTA_F_DEPLETED; + } else { + consumed_cap = consumed; + } if (nla_put_be64(skb, NFTA_QUOTA_BYTES, cpu_to_be64(priv->quota), NFTA_QUOTA_PAD) || - nla_put_be64(skb, NFTA_QUOTA_CONSUMED, cpu_to_be64(consumed), + nla_put_be64(skb, NFTA_QUOTA_CONSUMED, cpu_to_be64(consumed_cap), NFTA_QUOTA_PAD) || nla_put_be32(skb, NFTA_QUOTA_FLAGS, htonl(flags))) goto nla_put_failure; + + if (reset) { + atomic64_sub(consumed, &priv->consumed); + clear_bit(NFT_QUOTA_DEPLETED_BIT, &priv->flags); + } return 0; nla_put_failure: diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 28c56b95fb7f..ea7c67050792 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -1502,10 +1502,7 @@ static int __init netlbl_init(void) printk(KERN_INFO "NetLabel: Initializing\n"); printk(KERN_INFO "NetLabel: domain hash size = %u\n", (1 << NETLBL_DOMHSH_BITSIZE)); - printk(KERN_INFO "NetLabel: protocols =" - " UNLABELED" - " CIPSOv4" - "\n"); + printk(KERN_INFO "NetLabel: protocols = UNLABELED CIPSOv4 CALIPSO\n"); ret_val = netlbl_domhsh_init(NETLBL_DOMHSH_BITSIZE); if (ret_val != 0) diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index c985ecbe9bd6..ae5ac175b2be 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -252,7 +252,7 @@ static struct sk_buff *qrtr_alloc_resume_tx(u32 src_node, const int pkt_len = 20; struct qrtr_hdr *hdr; struct sk_buff *skb; - u32 *buf; + __le32 *buf; skb = alloc_skb(QRTR_HDR_SIZE + pkt_len, GFP_KERNEL); if (!skb) @@ -269,7 +269,7 @@ static struct sk_buff *qrtr_alloc_resume_tx(u32 src_node, hdr->dst_node_id = cpu_to_le32(dst_node); hdr->dst_port_id = cpu_to_le32(QRTR_PORT_CTRL); - buf = (u32 *)skb_put(skb, pkt_len); + buf = (__le32 *)skb_put(skb, pkt_len); memset(buf, 0, pkt_len); buf[0] = cpu_to_le32(QRTR_TYPE_RESUME_TX); buf[1] = cpu_to_le32(src_node); diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index e54082699520..34efaa4ef2f6 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -1048,7 +1048,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) (new_transport->state == SCTP_PF))) new_transport = asoc->peer.active_path; if (new_transport->state == SCTP_UNCONFIRMED) { - WARN_ONCE(1, "Atempt to send packet on unconfirmed path."); + WARN_ONCE(1, "Attempt to send packet on unconfirmed path."); sctp_chunk_fail(chunk, 0); sctp_chunk_free(chunk); continue; diff --git a/net/socket.c b/net/socket.c index a8c2307590b8..0758e13754e2 100644 --- a/net/socket.c +++ b/net/socket.c @@ -533,7 +533,7 @@ static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer, return used; } -int sockfs_setattr(struct dentry *dentry, struct iattr *iattr) +static int sockfs_setattr(struct dentry *dentry, struct iattr *iattr) { int err = simple_setattr(dentry, iattr); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 3df85a751a85..ef5eff93a8b8 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -14502,13 +14502,17 @@ static int nl80211_netlink_notify(struct notifier_block * nb, list_for_each_entry_rcu(rdev, &cfg80211_rdev_list, list) { bool schedule_destroy_work = false; - bool schedule_scan_stop = false; struct cfg80211_sched_scan_request *sched_scan_req = rcu_dereference(rdev->sched_scan_req); if (sched_scan_req && notify->portid && - sched_scan_req->owner_nlportid == notify->portid) - schedule_scan_stop = true; + sched_scan_req->owner_nlportid == notify->portid) { + sched_scan_req->owner_nlportid = 0; + + if (rdev->ops->sched_scan_stop && + rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN) + schedule_work(&rdev->sched_scan_stop_wk); + } list_for_each_entry_rcu(wdev, &rdev->wiphy.wdev_list, list) { cfg80211_mlme_unregister_socket(wdev, notify->portid); @@ -14539,12 +14543,6 @@ static int nl80211_netlink_notify(struct notifier_block * nb, spin_unlock(&rdev->destroy_list_lock); schedule_work(&rdev->destroy_work); } - } else if (schedule_scan_stop) { - sched_scan_req->owner_nlportid = 0; - - if (rdev->ops->sched_scan_stop && - rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN) - schedule_work(&rdev->sched_scan_stop_wk); } } diff --git a/samples/bpf/sock_example.h b/samples/bpf/sock_example.h index 09f7fe7e5fd7..d8014065d479 100644 --- a/samples/bpf/sock_example.h +++ b/samples/bpf/sock_example.h @@ -4,7 +4,7 @@ #include <unistd.h> #include <string.h> #include <errno.h> -#include <net/ethernet.h> +#include <linux/if_ether.h> #include <net/if.h> #include <linux/if_packet.h> #include <arpa/inet.h> diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c index f4fa6af22def..ccca1e348017 100644 --- a/samples/bpf/trace_output_user.c +++ b/samples/bpf/trace_output_user.c @@ -9,7 +9,6 @@ #include <string.h> #include <fcntl.h> #include <poll.h> -#include <sys/ioctl.h> #include <linux/perf_event.h> #include <linux/bpf.h> #include <errno.h> diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c index 1fc57a5093a7..ca495686b9c3 100644 --- a/samples/vfio-mdev/mtty.c +++ b/samples/vfio-mdev/mtty.c @@ -1073,7 +1073,7 @@ int mtty_get_region_info(struct mdev_device *mdev, { unsigned int size = 0; struct mdev_state *mdev_state; - int bar_index; + u32 bar_index; if (!mdev) return -EINVAL; @@ -1082,8 +1082,11 @@ int mtty_get_region_info(struct mdev_device *mdev, if (!mdev_state) return -EINVAL; - mutex_lock(&mdev_state->ops_lock); bar_index = region_info->index; + if (bar_index >= VFIO_PCI_NUM_REGIONS) + return -EINVAL; + + mutex_lock(&mdev_state->ops_lock); switch (bar_index) { case VFIO_PCI_CONFIG_REGION_INDEX: @@ -1180,7 +1183,10 @@ static long mtty_ioctl(struct mdev_device *mdev, unsigned int cmd, memcpy(&mdev_state->dev_info, &info, sizeof(info)); - return copy_to_user((void __user *)arg, &info, minsz); + if (copy_to_user((void __user *)arg, &info, minsz)) + return -EFAULT; + + return 0; } case VFIO_DEVICE_GET_REGION_INFO: { @@ -1201,7 +1207,10 @@ static long mtty_ioctl(struct mdev_device *mdev, unsigned int cmd, if (ret) return ret; - return copy_to_user((void __user *)arg, &info, minsz); + if (copy_to_user((void __user *)arg, &info, minsz)) + return -EFAULT; + + return 0; } case VFIO_DEVICE_GET_IRQ_INFO: @@ -1221,10 +1230,10 @@ static long mtty_ioctl(struct mdev_device *mdev, unsigned int cmd, if (ret) return ret; - if (info.count == -1) - return -EINVAL; + if (copy_to_user((void __user *)arg, &info, minsz)) + return -EFAULT; - return copy_to_user((void __user *)arg, &info, minsz); + return 0; } case VFIO_DEVICE_SET_IRQS: { diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c index efe3a44658d5..4576f987a4a5 100644 --- a/sound/soc/codecs/nau8825.c +++ b/sound/soc/codecs/nau8825.c @@ -561,9 +561,9 @@ static void nau8825_xtalk_prepare(struct nau8825 *nau8825) nau8825_xtalk_backup(nau8825); /* Config IIS as master to output signal by codec */ regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL2, - NAU8825_I2S_MS_MASK | NAU8825_I2S_DRV_MASK | + NAU8825_I2S_MS_MASK | NAU8825_I2S_LRC_DIV_MASK | NAU8825_I2S_BLK_DIV_MASK, NAU8825_I2S_MS_MASTER | - (0x2 << NAU8825_I2S_DRV_SFT) | 0x1); + (0x2 << NAU8825_I2S_LRC_DIV_SFT) | 0x1); /* Ramp up headphone volume to 0dB to get better performance and * avoid pop noise in headphone. */ @@ -657,7 +657,7 @@ static void nau8825_xtalk_clean(struct nau8825 *nau8825) NAU8825_IRQ_RMS_EN, NAU8825_IRQ_RMS_EN); /* Recover default value for IIS */ regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL2, - NAU8825_I2S_MS_MASK | NAU8825_I2S_DRV_MASK | + NAU8825_I2S_MS_MASK | NAU8825_I2S_LRC_DIV_MASK | NAU8825_I2S_BLK_DIV_MASK, NAU8825_I2S_MS_SLAVE); /* Restore value of specific register for cross talk */ nau8825_xtalk_restore(nau8825); @@ -2006,7 +2006,8 @@ static void nau8825_fll_apply(struct nau8825 *nau8825, NAU8825_FLL_INTEGER_MASK, fll_param->fll_int); /* FLL pre-scaler */ regmap_update_bits(nau8825->regmap, NAU8825_REG_FLL4, - NAU8825_FLL_REF_DIV_MASK, fll_param->clk_ref_div); + NAU8825_FLL_REF_DIV_MASK, + fll_param->clk_ref_div << NAU8825_FLL_REF_DIV_SFT); /* select divided VCO input */ regmap_update_bits(nau8825->regmap, NAU8825_REG_FLL5, NAU8825_FLL_CLK_SW_MASK, NAU8825_FLL_CLK_SW_REF); diff --git a/sound/soc/codecs/nau8825.h b/sound/soc/codecs/nau8825.h index 5d1704e73241..514fd13c2f46 100644 --- a/sound/soc/codecs/nau8825.h +++ b/sound/soc/codecs/nau8825.h @@ -137,7 +137,8 @@ #define NAU8825_FLL_CLK_SRC_FS (0x3 << NAU8825_FLL_CLK_SRC_SFT) /* FLL4 (0x07) */ -#define NAU8825_FLL_REF_DIV_MASK (0x3 << 10) +#define NAU8825_FLL_REF_DIV_SFT 10 +#define NAU8825_FLL_REF_DIV_MASK (0x3 << NAU8825_FLL_REF_DIV_SFT) /* FLL5 (0x08) */ #define NAU8825_FLL_PDB_DAC_EN (0x1 << 15) @@ -247,8 +248,8 @@ /* I2S_PCM_CTRL2 (0x1d) */ #define NAU8825_I2S_TRISTATE (1 << 15) /* 0 - normal mode, 1 - Hi-Z output */ -#define NAU8825_I2S_DRV_SFT 12 -#define NAU8825_I2S_DRV_MASK (0x3 << NAU8825_I2S_DRV_SFT) +#define NAU8825_I2S_LRC_DIV_SFT 12 +#define NAU8825_I2S_LRC_DIV_MASK (0x3 << NAU8825_I2S_LRC_DIV_SFT) #define NAU8825_I2S_MS_SFT 3 #define NAU8825_I2S_MS_MASK (1 << NAU8825_I2S_MS_SFT) #define NAU8825_I2S_MS_MASTER (1 << NAU8825_I2S_MS_SFT) diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index 10c2a564a715..1ac96ef9ee20 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -3833,6 +3833,9 @@ static int rt5645_i2c_probe(struct i2c_client *i2c, } } + regmap_update_bits(rt5645->regmap, RT5645_ADDA_CLK1, + RT5645_I2S_PD1_MASK, RT5645_I2S_PD1_2); + if (rt5645->pdata.jd_invert) { regmap_update_bits(rt5645->regmap, RT5645_IRQ_CTRL2, RT5645_JD_1_1_MASK, RT5645_JD_1_1_INV); diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c index 8877b74b0510..bb94d50052d7 100644 --- a/sound/soc/codecs/tlv320aic3x.c +++ b/sound/soc/codecs/tlv320aic3x.c @@ -126,6 +126,16 @@ static const struct reg_default aic3x_reg[] = { { 108, 0x00 }, { 109, 0x00 }, }; +static bool aic3x_volatile_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case AIC3X_RESET: + return true; + default: + return false; + } +} + static const struct regmap_config aic3x_regmap = { .reg_bits = 8, .val_bits = 8, @@ -133,6 +143,9 @@ static const struct regmap_config aic3x_regmap = { .max_register = DAC_ICC_ADJ, .reg_defaults = aic3x_reg, .num_reg_defaults = ARRAY_SIZE(aic3x_reg), + + .volatile_reg = aic3x_volatile_reg, + .cache_type = REGCACHE_RBTREE, }; diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 593b7d1aed46..d72ccef9e238 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -1551,7 +1551,7 @@ static int wm_adsp_load(struct wm_adsp *dsp) const struct wmfw_region *region; const struct wm_adsp_region *mem; const char *region_name; - char *file, *text; + char *file, *text = NULL; struct wm_adsp_buf *buf; unsigned int reg; int regions = 0; @@ -1700,10 +1700,21 @@ static int wm_adsp_load(struct wm_adsp *dsp) regions, le32_to_cpu(region->len), offset, region_name); + if ((pos + le32_to_cpu(region->len) + sizeof(*region)) > + firmware->size) { + adsp_err(dsp, + "%s.%d: %s region len %d bytes exceeds file length %zu\n", + file, regions, region_name, + le32_to_cpu(region->len), firmware->size); + ret = -EINVAL; + goto out_fw; + } + if (text) { memcpy(text, region->data, le32_to_cpu(region->len)); adsp_info(dsp, "%s: %s\n", file, text); kfree(text); + text = NULL; } if (reg) { @@ -1748,6 +1759,7 @@ out_fw: regmap_async_complete(regmap); wm_adsp_buf_free(&buf_list); release_firmware(firmware); + kfree(text); out: kfree(file); @@ -2233,6 +2245,17 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp) } if (reg) { + if ((pos + le32_to_cpu(blk->len) + sizeof(*blk)) > + firmware->size) { + adsp_err(dsp, + "%s.%d: %s region len %d bytes exceeds file length %zu\n", + file, blocks, region_name, + le32_to_cpu(blk->len), + firmware->size); + ret = -EINVAL; + goto out_fw; + } + buf = wm_adsp_buf_alloc(blk->data, le32_to_cpu(blk->len), &buf_list); diff --git a/sound/soc/dwc/designware_i2s.c b/sound/soc/dwc/designware_i2s.c index 2998954a1c74..bdf8398cbc81 100644 --- a/sound/soc/dwc/designware_i2s.c +++ b/sound/soc/dwc/designware_i2s.c @@ -681,22 +681,19 @@ static int dw_i2s_probe(struct platform_device *pdev) } if (!pdata) { - ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0); - if (ret == -EPROBE_DEFER) { - dev_err(&pdev->dev, - "failed to register PCM, deferring probe\n"); - return ret; - } else if (ret) { - dev_err(&pdev->dev, - "Could not register DMA PCM: %d\n" - "falling back to PIO mode\n", ret); + if (irq >= 0) { ret = dw_pcm_register(pdev); - if (ret) { - dev_err(&pdev->dev, - "Could not register PIO PCM: %d\n", + dev->use_pio = true; + } else { + ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, + 0); + dev->use_pio = false; + } + + if (ret) { + dev_err(&pdev->dev, "could not register pcm: %d\n", ret); - goto err_clk_disable; - } + goto err_clk_disable; } } diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c index 50349437d961..fde08660b63b 100644 --- a/sound/soc/fsl/fsl_ssi.c +++ b/sound/soc/fsl/fsl_ssi.c @@ -224,6 +224,12 @@ struct fsl_ssi_soc_data { * @dbg_stats: Debugging statistics * * @soc: SoC specific data + * + * @fifo_watermark: the FIFO watermark setting. Notifies DMA when + * there are @fifo_watermark or fewer words in TX fifo or + * @fifo_watermark or more empty words in RX fifo. + * @dma_maxburst: max number of words to transfer in one go. So far, + * this is always the same as fifo_watermark. */ struct fsl_ssi_private { struct regmap *regs; @@ -263,6 +269,9 @@ struct fsl_ssi_private { const struct fsl_ssi_soc_data *soc; struct device *dev; + + u32 fifo_watermark; + u32 dma_maxburst; }; /* @@ -1051,21 +1060,7 @@ static int _fsl_ssi_set_dai_fmt(struct device *dev, regmap_write(regs, CCSR_SSI_SRCR, srcr); regmap_write(regs, CCSR_SSI_SCR, scr); - /* - * Set the watermark for transmit FIFI 0 and receive FIFO 0. We don't - * use FIFO 1. We program the transmit water to signal a DMA transfer - * if there are only two (or fewer) elements left in the FIFO. Two - * elements equals one frame (left channel, right channel). This value, - * however, depends on the depth of the transmit buffer. - * - * We set the watermark on the same level as the DMA burstsize. For - * fiq it is probably better to use the biggest possible watermark - * size. - */ - if (ssi_private->use_dma) - wm = ssi_private->fifo_depth - 2; - else - wm = ssi_private->fifo_depth; + wm = ssi_private->fifo_watermark; regmap_write(regs, CCSR_SSI_SFCSR, CCSR_SSI_SFCSR_TFWM0(wm) | CCSR_SSI_SFCSR_RFWM0(wm) | @@ -1373,12 +1368,8 @@ static int fsl_ssi_imx_probe(struct platform_device *pdev, dev_dbg(&pdev->dev, "could not get baud clock: %ld\n", PTR_ERR(ssi_private->baudclk)); - /* - * We have burstsize be "fifo_depth - 2" to match the SSI - * watermark setting in fsl_ssi_startup(). - */ - ssi_private->dma_params_tx.maxburst = ssi_private->fifo_depth - 2; - ssi_private->dma_params_rx.maxburst = ssi_private->fifo_depth - 2; + ssi_private->dma_params_tx.maxburst = ssi_private->dma_maxburst; + ssi_private->dma_params_rx.maxburst = ssi_private->dma_maxburst; ssi_private->dma_params_tx.addr = ssi_private->ssi_phys + CCSR_SSI_STX0; ssi_private->dma_params_rx.addr = ssi_private->ssi_phys + CCSR_SSI_SRX0; @@ -1543,6 +1534,47 @@ static int fsl_ssi_probe(struct platform_device *pdev) /* Older 8610 DTs didn't have the fifo-depth property */ ssi_private->fifo_depth = 8; + /* + * Set the watermark for transmit FIFO 0 and receive FIFO 0. We don't + * use FIFO 1 but set the watermark appropriately nontheless. + * We program the transmit water to signal a DMA transfer + * if there are N elements left in the FIFO. For chips with 15-deep + * FIFOs, set watermark to 8. This allows the SSI to operate at a + * high data rate without channel slipping. Behavior is unchanged + * for the older chips with a fifo depth of only 8. A value of 4 + * might be appropriate for the older chips, but is left at + * fifo_depth-2 until sombody has a chance to test. + * + * We set the watermark on the same level as the DMA burstsize. For + * fiq it is probably better to use the biggest possible watermark + * size. + */ + switch (ssi_private->fifo_depth) { + case 15: + /* + * 2 samples is not enough when running at high data + * rates (like 48kHz @ 16 bits/channel, 16 channels) + * 8 seems to split things evenly and leave enough time + * for the DMA to fill the FIFO before it's over/under + * run. + */ + ssi_private->fifo_watermark = 8; + ssi_private->dma_maxburst = 8; + break; + case 8: + default: + /* + * maintain old behavior for older chips. + * Keeping it the same because I don't have an older + * board to test with. + * I suspect this could be changed to be something to + * leave some more space in the fifo. + */ + ssi_private->fifo_watermark = ssi_private->fifo_depth - 2; + ssi_private->dma_maxburst = ssi_private->fifo_depth - 2; + break; + } + dev_set_drvdata(&pdev->dev, ssi_private); if (ssi_private->soc->imx) { diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 507a86a5eafe..8d2fb2d6f532 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -142,7 +142,7 @@ static int platform_clock_control(struct snd_soc_dapm_widget *w, * for Jack detection and button press */ ret = snd_soc_dai_set_sysclk(codec_dai, RT5640_SCLK_S_RCCLK, - 0, + 48000 * 512, SND_SOC_CLOCK_IN); if (!ret) { if ((byt_rt5640_quirk & BYT_RT5640_MCLK_EN) && priv->mclk) @@ -825,10 +825,20 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev) if ((byt_rt5640_quirk & BYT_RT5640_MCLK_EN) && (is_valleyview())) { priv->mclk = devm_clk_get(&pdev->dev, "pmc_plt_clk_3"); if (IS_ERR(priv->mclk)) { + ret_val = PTR_ERR(priv->mclk); + dev_err(&pdev->dev, - "Failed to get MCLK from pmc_plt_clk_3: %ld\n", - PTR_ERR(priv->mclk)); - return PTR_ERR(priv->mclk); + "Failed to get MCLK from pmc_plt_clk_3: %d\n", + ret_val); + + /* + * Fall back to bit clock usage for -ENOENT (clock not + * available likely due to missing dependencies), bail + * for all other errors, including -EPROBE_DEFER + */ + if (ret_val != -ENOENT) + return ret_val; + byt_rt5640_quirk &= ~BYT_RT5640_MCLK_EN; } } diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c index 84b5101e6ca6..6c6b63a6b338 100644 --- a/sound/soc/intel/skylake/skl-pcm.c +++ b/sound/soc/intel/skylake/skl-pcm.c @@ -180,6 +180,9 @@ static int skl_pcm_open(struct snd_pcm_substream *substream, snd_pcm_set_sync(substream); mconfig = skl_tplg_fe_get_cpr_module(dai, substream->stream); + if (!mconfig) + return -EINVAL; + skl_tplg_d0i3_get(skl, mconfig->d0i3_caps); return 0; diff --git a/sound/soc/intel/skylake/skl-sst.c b/sound/soc/intel/skylake/skl-sst.c index 8fc3178bc79c..b30bd384c8d3 100644 --- a/sound/soc/intel/skylake/skl-sst.c +++ b/sound/soc/intel/skylake/skl-sst.c @@ -515,6 +515,9 @@ EXPORT_SYMBOL_GPL(skl_sst_init_fw); void skl_sst_dsp_cleanup(struct device *dev, struct skl_sst *ctx) { + + if (ctx->dsp->fw) + release_firmware(ctx->dsp->fw); skl_clear_module_table(ctx->dsp); skl_freeup_uuid_list(ctx); skl_ipc_free(&ctx->ipc); diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index 4bd68de76130..99b5b0835c1e 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -1030,10 +1030,8 @@ static int __rsnd_kctrl_new(struct rsnd_mod *mod, return -ENOMEM; ret = snd_ctl_add(card, kctrl); - if (ret < 0) { - snd_ctl_free_one(kctrl); + if (ret < 0) return ret; - } cfg->update = update; cfg->card = card; diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index f1901bb1466e..baa1afa41e3d 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1748,6 +1748,7 @@ static int soc_bind_aux_dev(struct snd_soc_card *card, int num) component->init = aux_dev->init; component->auxiliary = 1; + list_add(&component->card_aux_list, &card->aux_comp_list); return 0; @@ -1758,16 +1759,14 @@ err_defer: static int soc_probe_aux_devices(struct snd_soc_card *card) { - struct snd_soc_component *comp; + struct snd_soc_component *comp, *tmp; int order; int ret; for (order = SND_SOC_COMP_ORDER_FIRST; order <= SND_SOC_COMP_ORDER_LAST; order++) { - list_for_each_entry(comp, &card->component_dev_list, card_list) { - if (!comp->auxiliary) - continue; - + list_for_each_entry_safe(comp, tmp, &card->aux_comp_list, + card_aux_list) { if (comp->driver->probe_order == order) { ret = soc_probe_component(card, comp); if (ret < 0) { @@ -1776,6 +1775,7 @@ static int soc_probe_aux_devices(struct snd_soc_card *card) comp->name, ret); return ret; } + list_del(&comp->card_aux_list); } } } diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index e7a1eaa2772f..6aba14009c92 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -2184,9 +2184,11 @@ static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd) break; case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: - case SNDRV_PCM_TRIGGER_PAUSE_PUSH: fe->dpcm[stream].state = SND_SOC_DPCM_STATE_STOP; break; + case SNDRV_PCM_TRIGGER_PAUSE_PUSH: + fe->dpcm[stream].state = SND_SOC_DPCM_STATE_PAUSED; + break; } out: diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 65670b2b408c..fbfb1fab88d5 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -514,13 +514,12 @@ static void remove_widget(struct snd_soc_component *comp, == SND_SOC_TPLG_TYPE_MIXER) kfree(kcontrol->tlv.p); - snd_ctl_remove(card, kcontrol); - /* Private value is used as struct soc_mixer_control * for volume mixers or soc_bytes_ext for bytes * controls. */ kfree((void *)kcontrol->private_value); + snd_ctl_remove(card, kcontrol); } kfree(w->kcontrol_news); } diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index b3fd2382fdd9..eb4b9f7a571e 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1135,6 +1135,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x045E, 0x076F): /* MS Lifecam HD-6000 */ case USB_ID(0x045E, 0x0772): /* MS Lifecam Studio */ case USB_ID(0x045E, 0x0779): /* MS Lifecam HD-3000 */ + case USB_ID(0x047F, 0x02F7): /* Plantronics BT-600 */ case USB_ID(0x047F, 0x0415): /* Plantronics BT-300 */ case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */ case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c index 3284bb14ae78..8aad81151d50 100644 --- a/tools/lib/subcmd/parse-options.c +++ b/tools/lib/subcmd/parse-options.c @@ -213,6 +213,9 @@ static int get_value(struct parse_opt_ctx_t *p, else err = get_arg(p, opt, flags, (const char **)opt->value); + if (opt->set) + *(bool *)opt->set = true; + /* PARSE_OPT_NOEMPTY: Allow NULL but disallow empty string. */ if (opt->flags & PARSE_OPT_NOEMPTY) { const char *val = *(const char **)opt->value; diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h index 8866ac438b34..11c3be3bcce7 100644 --- a/tools/lib/subcmd/parse-options.h +++ b/tools/lib/subcmd/parse-options.h @@ -137,6 +137,11 @@ struct option { { .type = OPTION_STRING, .short_name = (s), .long_name = (l), \ .value = check_vtype(v, const char **), (a), .help = (h), \ .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) } +#define OPT_STRING_OPTARG_SET(s, l, v, os, a, h, d) \ + { .type = OPTION_STRING, .short_name = (s), .long_name = (l), \ + .value = check_vtype(v, const char **), (a), .help = (h), \ + .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d), \ + .set = check_vtype(os, bool *)} #define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY} #define OPT_DATE(s, l, v, h) \ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb } diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c index f1ce60065258..ec30c2fcbac0 100644 --- a/tools/lib/traceevent/plugin_sched_switch.c +++ b/tools/lib/traceevent/plugin_sched_switch.c @@ -111,7 +111,7 @@ static int sched_switch_handler(struct trace_seq *s, trace_seq_printf(s, "%lld ", val); if (pevent_get_field_val(s, event, "prev_prio", record, &val, 0) == 0) - trace_seq_printf(s, "[%lld] ", val); + trace_seq_printf(s, "[%d] ", (int) val); if (pevent_get_field_val(s, event, "prev_state", record, &val, 0) == 0) write_state(s, val); @@ -129,7 +129,7 @@ static int sched_switch_handler(struct trace_seq *s, trace_seq_printf(s, "%lld", val); if (pevent_get_field_val(s, event, "next_prio", record, &val, 0) == 0) - trace_seq_printf(s, " [%lld]", val); + trace_seq_printf(s, " [%d]", (int) val); return 0; } diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 27fc3617c6a4..5054d9147f0f 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -430,6 +430,10 @@ that gets then processed, possibly via a perf script, to decide if that particular perf.data snapshot should be kept or not. Implies --timestamp-filename, --no-buildid and --no-buildid-cache. +The reason for the latter two is to reduce the data file switching +overhead. You can still switch them on with: + + --switch-output --no-no-buildid --no-no-buildid-cache --dry-run:: Parse options then exit. --dry-run can be used to detect errors in cmdline diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 8fc24824705e..8bb16aa9d661 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -704,9 +704,9 @@ install-tests: all install-gtk $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \ $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr' -install-bin: install-tools install-tests +install-bin: install-tools install-tests install-traceevent-plugins -install: install-bin try-install-man install-traceevent-plugins +install: install-bin try-install-man install-python_ext: $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)' diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 35a02f8e5a4a..915869e00d86 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -655,7 +655,6 @@ static const struct { { "__GFP_RECLAIM", "R" }, { "__GFP_DIRECT_RECLAIM", "DR" }, { "__GFP_KSWAPD_RECLAIM", "KR" }, - { "__GFP_OTHER_NODE", "ON" }, }; static size_t max_gfp_len; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 74d6a035133a..4ec10e9427d9 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1405,7 +1405,7 @@ static bool dry_run; * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record', * using pipes, etc. */ -struct option __record_options[] = { +static struct option __record_options[] = { OPT_CALLBACK('e', "event", &record.evlist, "event", "event selector. use 'perf list' to list available events", parse_events_option), @@ -1636,7 +1636,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) * overhead. Still generate buildid if they are required * explicitly using * - * perf record --signal-trigger --no-no-buildid \ + * perf record --switch-output --no-no-buildid \ * --no-no-buildid-cache * * Following code equals to: diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index d53e706a6f17..5b134b0d1ff3 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -209,6 +209,7 @@ struct perf_sched { u64 skipped_samples; const char *time_str; struct perf_time_interval ptime; + struct perf_time_interval hist_time; }; /* per thread run time data */ @@ -2460,6 +2461,11 @@ static int timehist_sched_change_event(struct perf_tool *tool, timehist_print_sample(sched, sample, &al, thread, t); out: + if (sched->hist_time.start == 0 && t >= ptime->start) + sched->hist_time.start = t; + if (ptime->end == 0 || t <= ptime->end) + sched->hist_time.end = t; + if (tr) { /* time of this sched_switch event becomes last time task seen */ tr->last_time = sample->time; @@ -2624,6 +2630,7 @@ static void timehist_print_summary(struct perf_sched *sched, struct thread *t; struct thread_runtime *r; int i; + u64 hist_time = sched->hist_time.end - sched->hist_time.start; memset(&totals, 0, sizeof(totals)); @@ -2665,7 +2672,7 @@ static void timehist_print_summary(struct perf_sched *sched, totals.sched_count += r->run_stats.n; printf(" CPU %2d idle for ", i); print_sched_time(r->total_run_time, 6); - printf(" msec\n"); + printf(" msec (%6.2f%%)\n", 100.0 * r->total_run_time / hist_time); } else printf(" CPU %2d idle entire time window\n", i); } @@ -2701,12 +2708,16 @@ static void timehist_print_summary(struct perf_sched *sched, printf("\n" " Total number of unique tasks: %" PRIu64 "\n" - "Total number of context switches: %" PRIu64 "\n" - " Total run time (msec): ", + "Total number of context switches: %" PRIu64 "\n", totals.task_count, totals.sched_count); + printf(" Total run time (msec): "); print_sched_time(totals.total_run_time, 2); printf("\n"); + + printf(" Total scheduling time (msec): "); + print_sched_time(hist_time, 2); + printf(" (x %d)\n", sched->max_cpu); } typedef int (*sched_handler)(struct perf_tool *tool, diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index d281ae2b54e8..4a57c8a60bd9 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -163,7 +163,7 @@ static struct map *kernel_get_module_map(const char *module) /* A file path -- this is an offline module */ if (module && strchr(module, '/')) - return machine__findnew_module_map(host_machine, 0, module); + return dso__new_map(module); if (!module) module = "kernel"; @@ -173,6 +173,7 @@ static struct map *kernel_get_module_map(const char *module) if (strncmp(pos->dso->short_name + 1, module, pos->dso->short_name_len - 2) == 0 && module[pos->dso->short_name_len - 2] == '\0') { + map__get(pos); return pos; } } @@ -188,15 +189,6 @@ struct map *get_target_map(const char *target, bool user) return kernel_get_module_map(target); } -static void put_target_map(struct map *map, bool user) -{ - if (map && user) { - /* Only the user map needs to be released */ - map__put(map); - } -} - - static int convert_exec_to_group(const char *exec, char **result) { char *ptr1, *ptr2, *exec_copy; @@ -268,21 +260,6 @@ static bool kprobe_warn_out_range(const char *symbol, unsigned long address) } /* - * NOTE: - * '.gnu.linkonce.this_module' section of kernel module elf directly - * maps to 'struct module' from linux/module.h. This section contains - * actual module name which will be used by kernel after loading it. - * But, we cannot use 'struct module' here since linux/module.h is not - * exposed to user-space. Offset of 'name' has remained same from long - * time, so hardcoding it here. - */ -#ifdef __LP64__ -#define MOD_NAME_OFFSET 24 -#else -#define MOD_NAME_OFFSET 12 -#endif - -/* * @module can be module name of module file path. In case of path, * inspect elf and find out what is actual module name. * Caller has to free mod_name after using it. @@ -296,6 +273,7 @@ static char *find_module_name(const char *module) Elf_Data *data; Elf_Scn *sec; char *mod_name = NULL; + int name_offset; fd = open(module, O_RDONLY); if (fd < 0) @@ -317,7 +295,21 @@ static char *find_module_name(const char *module) if (!data || !data->d_buf) goto ret_err; - mod_name = strdup((char *)data->d_buf + MOD_NAME_OFFSET); + /* + * NOTE: + * '.gnu.linkonce.this_module' section of kernel module elf directly + * maps to 'struct module' from linux/module.h. This section contains + * actual module name which will be used by kernel after loading it. + * But, we cannot use 'struct module' here since linux/module.h is not + * exposed to user-space. Offset of 'name' has remained same from long + * time, so hardcoding it here. + */ + if (ehdr.e_ident[EI_CLASS] == ELFCLASS32) + name_offset = 12; + else /* expect ELFCLASS64 by default */ + name_offset = 24; + + mod_name = strdup((char *)data->d_buf + name_offset); ret_err: elf_end(elf); @@ -412,7 +404,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, } out: - put_target_map(map, uprobes); + map__put(map); return ret; } @@ -618,6 +610,51 @@ error: return ret ? : -ENOENT; } +/* + * Rename DWARF symbols to ELF symbols -- gcc sometimes optimizes functions + * and generate new symbols with suffixes such as .constprop.N or .isra.N + * etc. Since those symbols are not recorded in DWARF, we have to find + * correct generated symbols from offline ELF binary. + * For online kernel or uprobes we don't need this because those are + * rebased on _text, or already a section relative address. + */ +static int +post_process_offline_probe_trace_events(struct probe_trace_event *tevs, + int ntevs, const char *pathname) +{ + struct symbol *sym; + struct map *map; + unsigned long stext = 0; + u64 addr; + int i; + + /* Prepare a map for offline binary */ + map = dso__new_map(pathname); + if (!map || get_text_start_address(pathname, &stext) < 0) { + pr_warning("Failed to get ELF symbols for %s\n", pathname); + return -EINVAL; + } + + for (i = 0; i < ntevs; i++) { + addr = tevs[i].point.address + tevs[i].point.offset - stext; + sym = map__find_symbol(map, addr); + if (!sym) + continue; + if (!strcmp(sym->name, tevs[i].point.symbol)) + continue; + /* If we have no realname, use symbol for it */ + if (!tevs[i].point.realname) + tevs[i].point.realname = tevs[i].point.symbol; + else + free(tevs[i].point.symbol); + tevs[i].point.symbol = strdup(sym->name); + tevs[i].point.offset = addr - sym->start; + } + map__put(map); + + return 0; +} + static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, int ntevs, const char *exec) { @@ -679,7 +716,8 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs, /* Skip post process if the target is an offline kernel */ if (symbol_conf.ignore_vmlinux_buildid) - return 0; + return post_process_offline_probe_trace_events(tevs, ntevs, + symbol_conf.vmlinux_name); reloc_sym = kernel_get_ref_reloc_sym(); if (!reloc_sym) { @@ -2869,7 +2907,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, } out: - put_target_map(map, pev->uprobes); + map__put(map); free(syms); return ret; @@ -3362,10 +3400,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter, return ret; /* Get a symbol map */ - if (user) - map = dso__new_map(target); - else - map = kernel_get_module_map(target); + map = get_target_map(target, user); if (!map) { pr_err("Failed to get a map for %s\n", (target) ? : "kernel"); return -EINVAL; @@ -3397,9 +3432,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter, } end: - if (user) { - map__put(map); - } + map__put(map); exit_probe_symbol_maps(); return ret; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 99400b0e8f2a..adbc6c02c3aa 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -537,6 +537,12 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size) break; } else { int n = namesz + descsz; + + if (n > (int)sizeof(bf)) { + n = sizeof(bf); + pr_debug("%s: truncating reading of build id in sysfs file %s: n_namesz=%u, n_descsz=%u.\n", + __func__, filename, nhdr.n_namesz, nhdr.n_descsz); + } if (read(fd, bf, n) != n) break; } diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 71b05891a6a1..831022b12848 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -90,7 +90,7 @@ ifdef INSTALL_PATH done; @# Ask all targets to emit their test scripts - echo "#!/bin/bash" > $(ALL_SCRIPT) + echo "#!/bin/sh" > $(ALL_SCRIPT) echo "cd \$$(dirname \$$0)" >> $(ALL_SCRIPT) echo "ROOT=\$$PWD" >> $(ALL_SCRIPT) diff --git a/tools/testing/selftests/bpf/test_kmod.sh b/tools/testing/selftests/bpf/test_kmod.sh index 92e627adf354..6d58cca8e235 100755 --- a/tools/testing/selftests/bpf/test_kmod.sh +++ b/tools/testing/selftests/bpf/test_kmod.sh @@ -1,4 +1,4 @@ -#!/bin/bash +#!/bin/sh SRC_TREE=../../../../ diff --git a/tools/testing/selftests/net/run_netsocktests b/tools/testing/selftests/net/run_netsocktests index c09a682df56a..16058bbea7a8 100755 --- a/tools/testing/selftests/net/run_netsocktests +++ b/tools/testing/selftests/net/run_netsocktests @@ -1,4 +1,4 @@ -#!/bin/bash +#!/bin/sh echo "--------------------" echo "running socket test" diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c index bdd58c78902e..df9e0a0cdf29 100644 --- a/tools/testing/selftests/x86/protection_keys.c +++ b/tools/testing/selftests/x86/protection_keys.c @@ -1367,7 +1367,7 @@ void run_tests_once(void) tracing_off(); close_test_fds(); - printf("test %2d PASSED (itertation %d)\n", test_nr, iteration_nr); + printf("test %2d PASSED (iteration %d)\n", test_nr, iteration_nr); dprintf1("======================\n\n"); } iteration_nr++; diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c index 52abac4bb6a2..6d2fcd6fcb25 100644 --- a/virt/lib/irqbypass.c +++ b/virt/lib/irqbypass.c @@ -195,7 +195,7 @@ int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer) mutex_lock(&lock); list_for_each_entry(tmp, &consumers, node) { - if (tmp->token == consumer->token) { + if (tmp->token == consumer->token || tmp == consumer) { mutex_unlock(&lock); module_put(THIS_MODULE); return -EBUSY; @@ -245,7 +245,7 @@ void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer) mutex_lock(&lock); list_for_each_entry(tmp, &consumers, node) { - if (tmp->token != consumer->token) + if (tmp != consumer) continue; list_for_each_entry(producer, &producers, node) { |