diff --git a/Makefile b/Makefile index 7fc373c011c0..332dd011b3b9 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 14 -SUBLEVEL = 75 +SUBLEVEL = 76 EXTRAVERSION = NAME = Petit Gorille

diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index 4674541eba3f..8ce6e7235915 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -241,6 +241,26 @@ int copy_thread(unsigned long clone_flags, task_thread_info(current)->thr_ptr; }

+ + /* + * setup usermode thread pointer #1: + * when child is picked by scheduler, __switch_to() uses @c_callee to + * populate usermode callee regs: this works (despite being in a kernel + * function) since special return path for child @ret_from_fork() + * ensures those regs are not clobbered all the way to RTIE to usermode + */ + c_callee->r25 = task_thread_info(p)->thr_ptr; + +#ifdef CONFIG_ARC_CURR_IN_REG + /* + * setup usermode thread pointer #2: + * however for this special use of r25 in kernel, __switch_to() sets + * r25 for kernel needs and only in the final return path is usermode + * r25 setup, from pt_regs->user_r25. So set that up as well + */ + c_regs->user_r25 = c_callee->r25; +#endif + return 0; }

diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index bbcdf929be54..a5e919e34c42 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -9,6 +9,7 @@ extern void ppc_printk_progress(char *s, unsigned short hex);

extern unsigned int rtas_data; extern unsigned long long memory_limit; +extern bool init_mem_is_free; extern unsigned long klimit; extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);

diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index 096d4e4d31e6..882c750dc519 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -22,20 +22,28 @@ #include <asm/page.h> #include <asm/code-patching.h> #include <asm/setup.h> +#include <asm/sections.h>

-static int __patch_instruction(unsigned int *addr, unsigned int instr) +static int __patch_instruction(unsigned int *exec_addr, unsigned int instr, + unsigned int *patch_addr) { int err;

- __put_user_size(instr, addr, 4, err); + __put_user_size(instr, patch_addr, 4, err); if (err) return err;

- asm ("dcbst 0, %0; sync; icbi 0,%0; sync; isync" :: "r" (addr)); + asm ("dcbst 0, %0; sync; icbi 0,%1; sync; isync" :: "r" (patch_addr), + "r" (exec_addr));

return 0; }

+static int raw_patch_instruction(unsigned int *addr, unsigned int instr) +{ + return __patch_instruction(addr, instr, addr); +} + #ifdef CONFIG_STRICT_KERNEL_RWX static DEFINE_PER_CPU(struct vm_struct *, text_poke_area);

@@ -135,10 +143,10 @@ static inline int unmap_patch_area(unsigned long addr) return 0; }

-int patch_instruction(unsigned int *addr, unsigned int instr) +static int do_patch_instruction(unsigned int *addr, unsigned int instr) { int err; - unsigned int *dest = NULL; + unsigned int *patch_addr = NULL; unsigned long flags; unsigned long text_poke_addr; unsigned long kaddr = (unsigned long)addr; @@ -149,7 +157,7 @@ int patch_instruction(unsigned int *addr, unsigned int instr) * to allow patching. We just do the plain old patching */ if (!this_cpu_read(*PTRRELOC(&text_poke_area))) - return __patch_instruction(addr, instr); + return raw_patch_instruction(addr, instr);

local_irq_save(flags);

@@ -159,17 +167,10 @@ int patch_instruction(unsigned int *addr, unsigned int instr) goto out; }

- dest = (unsigned int *)(text_poke_addr) + + patch_addr = (unsigned int *)(text_poke_addr) + ((kaddr & ~PAGE_MASK) / sizeof(unsigned int));

- /* - * We use __put_user_size so that we can handle faults while - * writing to dest and return err to handle faults gracefully - */ - __put_user_size(instr, dest, 4, err); - if (!err) - asm ("dcbst 0, %0; sync; icbi 0,%0; icbi 0,%1; sync; isync" - ::"r" (dest), "r"(addr)); + __patch_instruction(addr, instr, patch_addr);

err = unmap_patch_area(text_poke_addr); if (err) @@ -182,12 +183,22 @@ int patch_instruction(unsigned int *addr, unsigned int instr) } #else /* !CONFIG_STRICT_KERNEL_RWX */

-int patch_instruction(unsigned int *addr, unsigned int instr) +static int do_patch_instruction(unsigned int *addr, unsigned int instr) { - return __patch_instruction(addr, instr); + return raw_patch_instruction(addr, instr); }

#endif /* CONFIG_STRICT_KERNEL_RWX */ + +int patch_instruction(unsigned int *addr, unsigned int instr) +{ + /* Make sure we aren't patching a freed init section */ + if (init_mem_is_free && init_section_contains(addr, 4)) { + pr_debug("Skipping init section patching addr: 0x%px\n", addr); + return 0; + } + return do_patch_instruction(addr, instr); +} NOKPROBE_SYMBOL(patch_instruction);

int patch_branch(unsigned int *addr, unsigned long target, int flags) diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 9c2f83331e5b..30bf13b72e5e 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -63,6 +63,7 @@ #endif

unsigned long long memory_limit; +bool init_mem_is_free;

#ifdef CONFIG_HIGHMEM pte_t *kmap_pte; @@ -405,6 +406,7 @@ void free_initmem(void) { ppc_md.progress = ppc_printk_progress; mark_initmem_nx(); + init_mem_is_free = true; free_initmem_default(POISON_FREE_INITMEM); }

diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index b545bf9d2328..0a550dc5c525 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -74,7 +74,13 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \ -fno-omit-frame-pointer -foptimize-sibling-calls \ - -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO $(RETPOLINE_VDSO_CFLAGS) + -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO + +ifdef CONFIG_RETPOLINE +ifneq ($(RETPOLINE_VDSO_CFLAGS),) + CFL += $(RETPOLINE_VDSO_CFLAGS) +endif +endif

$(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)

@@ -153,7 +159,13 @@ KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector) KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) KBUILD_CFLAGS_32 += -fno-omit-frame-pointer KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING -KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS) + +ifdef CONFIG_RETPOLINE +ifneq ($(RETPOLINE_VDSO_CFLAGS),) + KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS) +endif +endif + $(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)

$(obj)/vdso32.so.dbg: FORCE \ diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index fa8dbfcf7ed3..9c35dc0a9d64 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -43,8 +43,9 @@ extern u8 hvclock_page notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; - asm("syscall" : "=a" (ret) : - "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory"); + asm ("syscall" : "=a" (ret), "=m" (*ts) : + "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : + "memory", "rcx", "r11"); return ret; }

@@ -52,8 +53,9 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) { long ret;

- asm("syscall" : "=a" (ret) : - "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory"); + asm ("syscall" : "=a" (ret), "=m" (*tv), "=m" (*tz) : + "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : + "memory", "rcx", "r11"); return ret; }

@@ -64,13 +66,13 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret;

- asm( + asm ( "mov %%ebx, %%edx \n" - "mov %2, %%ebx \n" + "mov %[clock], %%ebx \n" "call __kernel_vsyscall \n" "mov %%edx, %%ebx \n" - : "=a" (ret) - : "0" (__NR_clock_gettime), "g" (clock), "c" (ts) + : "=a" (ret), "=m" (*ts) + : "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts) : "memory", "edx"); return ret; } @@ -79,13 +81,13 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) { long ret;

- asm( + asm ( "mov %%ebx, %%edx \n" - "mov %2, %%ebx \n" + "mov %[tv], %%ebx \n" "call __kernel_vsyscall \n" "mov %%edx, %%ebx \n" - : "=a" (ret) - : "0" (__NR_gettimeofday), "g" (tv), "c" (tz) + : "=a" (ret), "=m" (*tv), "=m" (*tz) + : "0" (__NR_gettimeofday), [tv] "g" (tv), "c" (tz) : "memory", "edx"); return ret; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 1dfb808abd23..d755e0d44ac1 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -231,6 +231,17 @@ static u64 __read_mostly shadow_nonpresent_or_rsvd_mask; */ static const u64 shadow_nonpresent_or_rsvd_mask_len = 5;

+/* + * In some cases, we need to preserve the GFN of a non-present or reserved + * SPTE when we usurp the upper five bits of the physical address space to + * defend against L1TF, e.g. for MMIO SPTEs. To preserve the GFN, we'll + * shift bits of the GFN that overlap with shadow_nonpresent_or_rsvd_mask + * left into the reserved bits, i.e. the GFN in the SPTE will be split into + * high and low parts. This mask covers the lower bits of the GFN. + */ +static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; + + static void mmu_spte_set(u64 *sptep, u64 spte); static void mmu_free_roots(struct kvm_vcpu *vcpu);

@@ -338,9 +349,7 @@ static bool is_mmio_spte(u64 spte)

static gfn_t get_mmio_spte_gfn(u64 spte) { - u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask | - shadow_nonpresent_or_rsvd_mask; - u64 gpa = spte & ~mask; + u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask;

gpa |= (spte >> shadow_nonpresent_or_rsvd_mask_len) & shadow_nonpresent_or_rsvd_mask; @@ -404,6 +413,8 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);

static void kvm_mmu_reset_all_pte_masks(void) { + u8 low_phys_bits; + shadow_user_mask = 0; shadow_accessed_mask = 0; shadow_dirty_mask = 0; @@ -418,12 +429,17 @@ static void kvm_mmu_reset_all_pte_masks(void) * appropriate mask to guard against L1TF attacks. Otherwise, it is * assumed that the CPU is not vulnerable to L1TF. */ + low_phys_bits = boot_cpu_data.x86_phys_bits; if (boot_cpu_data.x86_phys_bits < - 52 - shadow_nonpresent_or_rsvd_mask_len) + 52 - shadow_nonpresent_or_rsvd_mask_len) { shadow_nonpresent_or_rsvd_mask = rsvd_bits(boot_cpu_data.x86_phys_bits - shadow_nonpresent_or_rsvd_mask_len, boot_cpu_data.x86_phys_bits - 1); + low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len; + } + shadow_nonpresent_or_rsvd_lower_gfn_mask = + GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT); }

static int is_cpuid_PSE36(void) diff --git a/block/blk-mq.c b/block/blk-mq.c index 49979c095f31..eac444804736 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1512,7 +1512,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) BUG_ON(!rq->q); if (rq->mq_ctx != this_ctx) { if (this_ctx) { - trace_block_unplug(this_q, depth, from_schedule); + trace_block_unplug(this_q, depth, !from_schedule); blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list, from_schedule); @@ -1532,7 +1532,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) * on 'ctx_list'. Do those. */ if (this_ctx) { - trace_block_unplug(this_q, depth, from_schedule); + trace_block_unplug(this_q, depth, !from_schedule); blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list, from_schedule); } diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 770b1539a083..d16b40cd26cc 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1462,8 +1462,10 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)

dpm_wait_for_subordinate(dev, async);

- if (async_error) + if (async_error) { + dev->power.direct_complete = false; goto Complete; + }

/* * If a device configured to wake up the system from sleep states @@ -1475,6 +1477,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) pm_wakeup_event(dev, 0);

if (pm_wakeup_pending()) { + dev->power.direct_complete = false; async_error = -EBUSY; goto Complete; } diff --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c index ec8a4376f74f..2fab18fae4fc 100644 --- a/drivers/clocksource/timer-atmel-pit.c +++ b/drivers/clocksource/timer-atmel-pit.c @@ -180,26 +180,29 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node) data->base = of_iomap(node, 0); if (!data->base) { pr_err("Could not map PIT address\n"); - return -ENXIO; + ret = -ENXIO; + goto exit; }

data->mck = of_clk_get(node, 0); if (IS_ERR(data->mck)) { pr_err("Unable to get mck clk\n"); - return PTR_ERR(data->mck); + ret = PTR_ERR(data->mck); + goto exit; }

ret = clk_prepare_enable(data->mck); if (ret) { pr_err("Unable to enable mck\n"); - return ret; + goto exit; }

/* Get the interrupts property */ data->irq = irq_of_parse_and_map(node, 0); if (!data->irq) { pr_err("Unable to get IRQ from DT\n"); - return -EINVAL; + ret = -EINVAL; + goto exit; }

/* @@ -227,7 +230,7 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node) ret = clocksource_register_hz(&data->clksrc, pit_rate); if (ret) { pr_err("Failed to register clocksource\n"); - return ret; + goto exit; }

/* Set up irq handler */ @@ -236,7 +239,8 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node) "at91_tick", data); if (ret) { pr_err("Unable to setup IRQ\n"); - return ret; + clocksource_unregister(&data->clksrc); + goto exit; }

/* Set up and register clockevents */ @@ -254,6 +258,10 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node) clockevents_register_device(&data->clkevt);

return 0; + +exit: + kfree(data); + return ret; } TIMER_OF_DECLARE(at91sam926x_pit, "atmel,at91sam9260-pit", at91sam926x_pit_dt_init); diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c index 0e8160701833..bb7b59fc5c08 100644 --- a/drivers/crypto/chelsio/chcr_algo.c +++ b/drivers/crypto/chelsio/chcr_algo.c @@ -384,7 +384,8 @@ static inline int is_hmac(struct crypto_tfm *tfm)

static void write_phys_cpl(struct cpl_rx_phys_dsgl *phys_cpl, struct scatterlist *sg, - struct phys_sge_parm *sg_param) + struct phys_sge_parm *sg_param, + int pci_chan_id) { struct phys_sge_pairs *to; unsigned int len = 0, left_size = sg_param->obsize; @@ -402,6 +403,7 @@ static void write_phys_cpl(struct cpl_rx_phys_dsgl *phys_cpl, phys_cpl->rss_hdr_int.opcode = CPL_RX_PHYS_ADDR; phys_cpl->rss_hdr_int.qid = htons(sg_param->qid); phys_cpl->rss_hdr_int.hash_val = 0; + phys_cpl->rss_hdr_int.channel = pci_chan_id; to = (struct phys_sge_pairs *)((unsigned char *)phys_cpl + sizeof(struct cpl_rx_phys_dsgl)); for (i = 0; nents && left_size; to++) { @@ -418,7 +420,8 @@ static void write_phys_cpl(struct cpl_rx_phys_dsgl *phys_cpl, static inline int map_writesg_phys_cpl(struct device *dev, struct cpl_rx_phys_dsgl *phys_cpl, struct scatterlist *sg, - struct phys_sge_parm *sg_param) + struct phys_sge_parm *sg_param, + int pci_chan_id) { if (!sg || !sg_param->nents) return -EINVAL; @@ -428,7 +431,7 @@ static inline int map_writesg_phys_cpl(struct device *dev, pr_err("CHCR : DMA mapping failed\n"); return -EINVAL; } - write_phys_cpl(phys_cpl, sg, sg_param); + write_phys_cpl(phys_cpl, sg, sg_param, pci_chan_id); return 0; }

@@ -608,7 +611,7 @@ static inline void create_wreq(struct chcr_context *ctx, is_iv ? iv_loc : IV_NOP, !!lcb, ctx->tx_qidx);

- chcr_req->ulptx.cmd_dest = FILL_ULPTX_CMD_DEST(ctx->dev->tx_channel_id, + chcr_req->ulptx.cmd_dest = FILL_ULPTX_CMD_DEST(ctx->tx_chan_id, qid); chcr_req->ulptx.len = htonl((DIV_ROUND_UP((calc_tx_flits_ofld(skb) * 8), 16) - ((sizeof(chcr_req->wreq)) >> 4))); @@ -698,7 +701,8 @@ static struct sk_buff *create_cipher_wr(struct cipher_wr_param *wrparam) sg_param.obsize = wrparam->bytes; sg_param.qid = wrparam->qid; error = map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, - reqctx->dst, &sg_param); + reqctx->dst, &sg_param, + ctx->pci_chan_id); if (error) goto map_fail1;

@@ -1228,16 +1232,23 @@ static int chcr_device_init(struct chcr_context *ctx) adap->vres.ncrypto_fc); rxq_perchan = u_ctx->lldi.nrxq / u_ctx->lldi.nchan; txq_perchan = ntxq / u_ctx->lldi.nchan; - rxq_idx = ctx->dev->tx_channel_id * rxq_perchan; - rxq_idx += id % rxq_perchan; - txq_idx = ctx->dev->tx_channel_id * txq_perchan; - txq_idx += id % txq_perchan; spin_lock(&ctx->dev->lock_chcr_dev); - ctx->rx_qidx = rxq_idx; - ctx->tx_qidx = txq_idx; + ctx->tx_chan_id = ctx->dev->tx_channel_id; ctx->dev->tx_channel_id = !ctx->dev->tx_channel_id; ctx->dev->rx_channel_id = 0; spin_unlock(&ctx->dev->lock_chcr_dev); + rxq_idx = ctx->tx_chan_id * rxq_perchan; + rxq_idx += id % rxq_perchan; + txq_idx = ctx->tx_chan_id * txq_perchan; + txq_idx += id % txq_perchan; + ctx->rx_qidx = rxq_idx; + ctx->tx_qidx = txq_idx; + /* Channel Id used by SGE to forward packet to Host. + * Same value should be used in cpl_fw6_pld RSS_CH field + * by FW. Driver programs PCI channel ID to be used in fw + * at the time of queue allocation with value "pi->tx_chan" + */ + ctx->pci_chan_id = txq_idx / txq_perchan; } out: return err; @@ -2066,7 +2077,8 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req, sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize); sg_param.qid = qid; error = map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, - reqctx->dst, &sg_param); + reqctx->dst, &sg_param, + ctx->pci_chan_id); if (error) goto dstmap_fail;

@@ -2389,7 +2401,7 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req, sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize); sg_param.qid = qid; error = map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, - reqctx->dst, &sg_param); + reqctx->dst, &sg_param, ctx->pci_chan_id); if (error) goto dstmap_fail;

@@ -2545,7 +2557,8 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req, sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize); sg_param.qid = qid; error = map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, - reqctx->dst, &sg_param); + reqctx->dst, &sg_param, + ctx->pci_chan_id); if (error) goto dstmap_fail;

diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h index 30af1ee17b87..e039d9aeb651 100644 --- a/drivers/crypto/chelsio/chcr_crypto.h +++ b/drivers/crypto/chelsio/chcr_crypto.h @@ -222,6 +222,8 @@ struct chcr_context { struct chcr_dev *dev; unsigned char tx_qidx; unsigned char rx_qidx; + unsigned char tx_chan_id; + unsigned char pci_chan_id; struct __crypto_ctx crypto_ctx[0]; };

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index 9fc3d387eae3..fb36425e21ff 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -231,6 +231,8 @@ int amdgpu_vce_suspend(struct amdgpu_device *adev) { int i;

+ cancel_delayed_work_sync(&adev->vce.idle_work); + if (adev->vce.vcpu_bo == NULL) return 0;

@@ -241,7 +243,6 @@ int amdgpu_vce_suspend(struct amdgpu_device *adev) if (i == AMDGPU_MAX_VCE_HANDLES) return 0;

- cancel_delayed_work_sync(&adev->vce.idle_work); /* TODO: suspending running encoding sessions isn't supported */ return -EINVAL; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 1612d8aa6ad6..fca1b10628a6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -155,11 +155,11 @@ int amdgpu_vcn_suspend(struct amdgpu_device *adev) unsigned size; void *ptr;

+ cancel_delayed_work_sync(&adev->vcn.idle_work); + if (adev->vcn.vcpu_bo == NULL) return 0;

- cancel_delayed_work_sync(&adev->vcn.idle_work); - size = amdgpu_bo_size(adev->vcn.vcpu_bo); ptr = adev->vcn.cpu_addr;

diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index 7bcf5702c91c..889c95d4feec 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -96,6 +96,8 @@ static int drm_syncobj_fence_get_or_add_callback(struct drm_syncobj *syncobj, { int ret;

+ WARN_ON(*fence); + *fence = drm_syncobj_fence_get(syncobj); if (*fence) return 1; @@ -656,6 +658,9 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,

if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) { for (i = 0; i < count; ++i) { + if (entries[i].fence) + continue; + drm_syncobj_fence_get_or_add_callback(syncobjs[i], &entries[i].fence, &entries[i].syncobj_cb, diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 16423d7ab599..17144a781aeb 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1742,6 +1742,8 @@ static int ucma_close(struct inode *inode, struct file *filp) mutex_lock(&mut); if (!ctx->closing) { mutex_unlock(&mut); + ucma_put_ctx(ctx); + wait_for_completion(&ctx->comp); /* rdma_destroy_id ensures that no event handlers are * inflight for that id before releasing it. */ diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 0a5a45f3ec5f..7f1c64c4ad24 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -1454,8 +1454,8 @@ static int __load_mappings(struct dm_cache_metadata *cmd, if (hints_valid) { r = dm_array_cursor_next(&cmd->hint_cursor); if (r) { - DMERR("dm_array_cursor_next for hint failed"); - goto out; + dm_array_cursor_end(&cmd->hint_cursor); + hints_valid = false; } }

diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index a4b7c2698096..e2ea57d5376e 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -3097,8 +3097,13 @@ static dm_cblock_t get_cache_dev_size(struct cache *cache)

static bool can_resize(struct cache *cache, dm_cblock_t new_size) { - if (from_cblock(new_size) > from_cblock(cache->cache_size)) - return true; + if (from_cblock(new_size) > from_cblock(cache->cache_size)) { + if (cache->sized) { + DMERR("%s: unable to extend cache due to missing cache table reload", + cache_device_name(cache)); + return false; + } + }

/* * We can't drop a dirty block when shrinking the cache. diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c index df514507d3f1..22003895f854 100644 --- a/drivers/net/wireless/ath/ath10k/debug.c +++ b/drivers/net/wireless/ath/ath10k/debug.c @@ -1,6 +1,7 @@ /* * Copyright (c) 2005-2011 Atheros Communications Inc. * Copyright (c) 2011-2013 Qualcomm Atheros, Inc. + * Copyright (c) 2018, The Linux Foundation. All rights reserved. * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -163,6 +164,8 @@ void ath10k_debug_print_hwfw_info(struct ath10k *ar) void ath10k_debug_print_board_info(struct ath10k *ar) { char boardinfo[100]; + const struct firmware *board; + u32 crc;

if (ar->id.bmi_ids_valid) scnprintf(boardinfo, sizeof(boardinfo), "%d:%d", @@ -170,11 +173,16 @@ void ath10k_debug_print_board_info(struct ath10k *ar) else scnprintf(boardinfo, sizeof(boardinfo), "N/A");

+ board = ar->normal_mode_fw.board; + if (!IS_ERR_OR_NULL(board)) + crc = crc32_le(0, board->data, board->size); + else + crc = 0; + ath10k_info(ar, "board_file api %d bmi_id %s crc32 %08x", ar->bd_api, boardinfo, - crc32_le(0, ar->normal_mode_fw.board->data, - ar->normal_mode_fw.board->size)); + crc); }

void ath10k_debug_print_boot_info(struct ath10k *ar) diff --git a/drivers/net/wireless/ath/ath10k/trace.h b/drivers/net/wireless/ath/ath10k/trace.h index e0d00cef0bd8..5b974bb76e6c 100644 --- a/drivers/net/wireless/ath/ath10k/trace.h +++ b/drivers/net/wireless/ath/ath10k/trace.h @@ -152,10 +152,9 @@ TRACE_EVENT(ath10k_log_dbg_dump, );

TRACE_EVENT(ath10k_wmi_cmd, - TP_PROTO(struct ath10k *ar, int id, const void *buf, size_t buf_len, - int ret), + TP_PROTO(struct ath10k *ar, int id, const void *buf, size_t buf_len),

- TP_ARGS(ar, id, buf, buf_len, ret), + TP_ARGS(ar, id, buf, buf_len),

TP_STRUCT__entry( __string(device, dev_name(ar->dev)) @@ -163,7 +162,6 @@ TRACE_EVENT(ath10k_wmi_cmd, __field(unsigned int, id) __field(size_t, buf_len) __dynamic_array(u8, buf, buf_len) - __field(int, ret) ),

TP_fast_assign( @@ -171,17 +169,15 @@ TRACE_EVENT(ath10k_wmi_cmd, __assign_str(driver, dev_driver_string(ar->dev)); __entry->id = id; __entry->buf_len = buf_len; - __entry->ret = ret; memcpy(__get_dynamic_array(buf), buf, buf_len); ),

TP_printk( - "%s %s id %d len %zu ret %d", + "%s %s id %d len %zu", __get_str(driver), __get_str(device), __entry->id, - __entry->buf_len, - __entry->ret + __entry->buf_len ) );

diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c index baec856af90f..b54001e97ced 100644 --- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c +++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c @@ -1486,10 +1486,10 @@ ath10k_wmi_tlv_op_gen_start_scan(struct ath10k *ar, bssid_len = arg->n_bssids * sizeof(struct wmi_mac_addr); ie_len = roundup(arg->ie_len, 4); len = (sizeof(*tlv) + sizeof(*cmd)) + - (arg->n_channels ? sizeof(*tlv) + chan_len : 0) + - (arg->n_ssids ? sizeof(*tlv) + ssid_len : 0) + - (arg->n_bssids ? sizeof(*tlv) + bssid_len : 0) + - (arg->ie_len ? sizeof(*tlv) + ie_len : 0); + sizeof(*tlv) + chan_len + + sizeof(*tlv) + ssid_len + + sizeof(*tlv) + bssid_len + + sizeof(*tlv) + ie_len;

skb = ath10k_wmi_alloc_skb(ar, len); if (!skb) diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c index 38a97086708b..2ab5311659ea 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.c +++ b/drivers/net/wireless/ath/ath10k/wmi.c @@ -1741,8 +1741,8 @@ int ath10k_wmi_cmd_send_nowait(struct ath10k *ar, struct sk_buff *skb, cmd_hdr->cmd_id = __cpu_to_le32(cmd);

memset(skb_cb, 0, sizeof(*skb_cb)); + trace_ath10k_wmi_cmd(ar, cmd_id, skb->data, skb->len); ret = ath10k_htc_send(&ar->htc, ar->wmi.eid, skb); - trace_ath10k_wmi_cmd(ar, cmd_id, skb->data, skb->len, ret);

if (ret) goto err_pull; diff --git a/drivers/net/xen-netback/hash.c b/drivers/net/xen-netback/hash.c index 3c4c58b9fe76..3b6fb5b3bdb2 100644 --- a/drivers/net/xen-netback/hash.c +++ b/drivers/net/xen-netback/hash.c @@ -332,20 +332,22 @@ u32 xenvif_set_hash_mapping_size(struct xenvif *vif, u32 size) u32 xenvif_set_hash_mapping(struct xenvif *vif, u32 gref, u32 len, u32 off) { - u32 *mapping = &vif->hash.mapping[off]; + u32 *mapping = vif->hash.mapping; struct gnttab_copy copy_op = { .source.u.ref = gref, .source.domid = vif->domid, - .dest.u.gmfn = virt_to_gfn(mapping), .dest.domid = DOMID_SELF, - .dest.offset = xen_offset_in_page(mapping), - .len = len * sizeof(u32), + .len = len * sizeof(*mapping), .flags = GNTCOPY_source_gref };

- if ((off + len > vif->hash.size) || copy_op.len > XEN_PAGE_SIZE) + if ((off + len < off) || (off + len > vif->hash.size) || + len > XEN_PAGE_SIZE / sizeof(*mapping)) return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;

+ copy_op.dest.u.gmfn = virt_to_gfn(mapping + off); + copy_op.dest.offset = xen_offset_in_page(mapping + off); + while (len-- != 0) if (mapping[off++] >= vif->num_queues) return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 7deb7b5d8683..058d542647dd 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2868,6 +2868,10 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, }

if (ret) { + nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING); + cancel_work_sync(&ctrl->ctrl.reset_work); + cancel_delayed_work_sync(&ctrl->connect_work); + /* couldn't schedule retry - fail out */ dev_err(ctrl->ctrl.device, "NVME-FC{%d}: Connect retry failed\n", ctrl->cnum); diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 985a85f281a8..7c6aff761800 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -614,6 +614,9 @@ static void __init of_unittest_parse_interrupts(void) struct of_phandle_args args; int i, rc;

+ if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC) + return; + np = of_find_node_by_path("/testcase-data/interrupts/interrupts0"); if (!np) { pr_err("missing testcase data\n"); @@ -688,6 +691,9 @@ static void __init of_unittest_parse_interrupts_extended(void) struct of_phandle_args args; int i, rc;

+ if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC) + return; + np = of_find_node_by_path("/testcase-data/interrupts/interrupts-extended0"); if (!np) { pr_err("missing testcase data\n"); @@ -844,15 +850,19 @@ static void __init of_unittest_platform_populate(void) pdev = of_find_device_by_node(np); unittest(pdev, "device 1 creation failed\n");

- irq = platform_get_irq(pdev, 0); - unittest(irq == -EPROBE_DEFER, "device deferred probe failed - %d\n", irq); + if (!(of_irq_workarounds & OF_IMAP_OLDWORLD_MAC)) { + irq = platform_get_irq(pdev, 0); + unittest(irq == -EPROBE_DEFER, + "device deferred probe failed - %d\n", irq);

- /* Test that a parsing failure does not return -EPROBE_DEFER */ - np = of_find_node_by_path("/testcase-data/testcase-device2"); - pdev = of_find_device_by_node(np); - unittest(pdev, "device 2 creation failed\n"); - irq = platform_get_irq(pdev, 0); - unittest(irq < 0 && irq != -EPROBE_DEFER, "device parsing error failed - %d\n", irq); + /* Test that a parsing failure does not return -EPROBE_DEFER */ + np = of_find_node_by_path("/testcase-data/testcase-device2"); + pdev = of_find_device_by_node(np); + unittest(pdev, "device 2 creation failed\n"); + irq = platform_get_irq(pdev, 0); + unittest(irq < 0 && irq != -EPROBE_DEFER, + "device parsing error failed - %d\n", irq); + }

np = of_find_node_by_path("/testcase-data/platform-tests"); unittest(np, "No testcase data in device tree\n"); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 22924629e64a..1af30c881566 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1112,12 +1112,12 @@ int pci_save_state(struct pci_dev *dev) EXPORT_SYMBOL(pci_save_state);

static void pci_restore_config_dword(struct pci_dev *pdev, int offset, - u32 saved_val, int retry) + u32 saved_val, int retry, bool force) { u32 val;

pci_read_config_dword(pdev, offset, &val); - if (val == saved_val) + if (!force && val == saved_val) return;

for (;;) { @@ -1136,25 +1136,36 @@ static void pci_restore_config_dword(struct pci_dev *pdev, int offset, }

static void pci_restore_config_space_range(struct pci_dev *pdev, - int start, int end, int retry) + int start, int end, int retry, + bool force) { int index;

for (index = end; index >= start; index--) pci_restore_config_dword(pdev, 4 * index, pdev->saved_config_space[index], - retry); + retry, force); }

static void pci_restore_config_space(struct pci_dev *pdev) { if (pdev->hdr_type == PCI_HEADER_TYPE_NORMAL) { - pci_restore_config_space_range(pdev, 10, 15, 0); + pci_restore_config_space_range(pdev, 10, 15, 0, false); /* Restore BARs before the command register. */ - pci_restore_config_space_range(pdev, 4, 9, 10); - pci_restore_config_space_range(pdev, 0, 3, 0); + pci_restore_config_space_range(pdev, 4, 9, 10, false); + pci_restore_config_space_range(pdev, 0, 3, 0, false); + } else if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE) { + pci_restore_config_space_range(pdev, 12, 15, 0, false); + + /* + * Force rewriting of prefetch registers to avoid S3 resume + * issues on Intel PCI bridges that occur when these + * registers are not explicitly written. + */ + pci_restore_config_space_range(pdev, 9, 11, 0, true); + pci_restore_config_space_range(pdev, 0, 8, 0, false); } else { - pci_restore_config_space_range(pdev, 0, 15, 0); + pci_restore_config_space_range(pdev, 0, 15, 0, false); } }

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 562d31073f9a..8d65b2f9ee80 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1254,6 +1254,7 @@ static void tty_driver_remove_tty(struct tty_driver *driver, struct tty_struct * static int tty_reopen(struct tty_struct *tty) { struct tty_driver *driver = tty->driver; + int retval;

if (driver->type == TTY_DRIVER_TYPE_PTY && driver->subtype == PTY_TYPE_MASTER) @@ -1267,10 +1268,14 @@ static int tty_reopen(struct tty_struct *tty)

tty->count++;

- if (!tty->ldisc) - return tty_ldisc_reinit(tty, tty->termios.c_line); + if (tty->ldisc) + return 0;

- return 0; + retval = tty_ldisc_reinit(tty, tty->termios.c_line); + if (retval) + tty->count--; + + return retval; }

/** diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index feaa0d8f830a..9f6f402470ac 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1527,6 +1527,7 @@ static void acm_disconnect(struct usb_interface *intf) { struct acm *acm = usb_get_intfdata(intf); struct tty_struct *tty; + int i;

/* sibling interface is already cleaning up */ if (!acm) @@ -1557,6 +1558,11 @@ static void acm_disconnect(struct usb_interface *intf)

tty_unregister_device(acm_tty_driver, acm->minor);

+ usb_free_urb(acm->ctrlurb); + for (i = 0; i < ACM_NW; i++) + usb_free_urb(acm->wb[i].urb); + for (i = 0; i < acm->rx_buflimit; i++) + usb_free_urb(acm->read_urbs[i]); acm_write_buffers_free(acm); usb_free_coherent(acm->dev, acm->ctrlsize, acm->ctrl_buffer, acm->ctrl_dma); acm_read_buffers_free(acm); diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c index 8fb60657ed4f..510d28a9d190 100644 --- a/drivers/usb/host/xhci-mtk.c +++ b/drivers/usb/host/xhci-mtk.c @@ -780,10 +780,10 @@ static int __maybe_unused xhci_mtk_resume(struct device *dev) xhci_mtk_host_enable(mtk);

xhci_dbg(xhci, "%s: restart port polling\n", __func__); - set_bit(HCD_FLAG_POLL_RH, &hcd->flags); - usb_hcd_poll_rh_status(hcd); set_bit(HCD_FLAG_POLL_RH, &xhci->shared_hcd->flags); usb_hcd_poll_rh_status(xhci->shared_hcd); + set_bit(HCD_FLAG_POLL_RH, &hcd->flags); + usb_hcd_poll_rh_status(hcd); return 0; }

diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 838d37e79fa2..9218f506f8e3 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -196,6 +196,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) } if (pdev->vendor == PCI_VENDOR_ID_INTEL && (pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) xhci->quirks |= XHCI_MISSING_CAS; diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c index 2674da40d9cd..6d6acf2c07c3 100644 --- a/drivers/usb/serial/usb-serial-simple.c +++ b/drivers/usb/serial/usb-serial-simple.c @@ -87,7 +87,8 @@ DEVICE(moto_modem, MOTO_IDS);

/* Motorola Tetra driver */ #define MOTOROLA_TETRA_IDS() \ - { USB_DEVICE(0x0cad, 0x9011) } /* Motorola Solutions TETRA PEI */ + { USB_DEVICE(0x0cad, 0x9011) }, /* Motorola Solutions TETRA PEI */ \ + { USB_DEVICE(0x0cad, 0x9012) } /* MTP6550 */ DEVICE(motorola_tetra, MOTOROLA_TETRA_IDS);

/* Novatel Wireless GPS driver */ diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c index ef69273074ba..a3edb20ea4c3 100644 --- a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c +++ b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c @@ -496,6 +496,9 @@ static int omapfb_memory_read(struct fb_info *fbi, if (!access_ok(VERIFY_WRITE, mr->buffer, mr->buffer_size)) return -EFAULT;

+ if (mr->w > 4096 || mr->h > 4096) + return -EINVAL; + if (mr->w * mr->h * 3 > mr->buffer_size) return -EINVAL;

@@ -509,7 +512,7 @@ static int omapfb_memory_read(struct fb_info *fbi, mr->x, mr->y, mr->w, mr->h);

if (r > 0) { - if (copy_to_user(mr->buffer, buf, mr->buffer_size)) + if (copy_to_user(mr->buffer, buf, r)) r = -EFAULT; }

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 36c9fbf70d44..d9873aa014a6 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -143,16 +143,17 @@ static void set_page_pfns(struct virtio_balloon *vb,

static unsigned fill_balloon(struct virtio_balloon *vb, size_t num) { - struct balloon_dev_info *vb_dev_info = &vb->vb_dev_info; unsigned num_allocated_pages; + unsigned num_pfns; + struct page *page; + LIST_HEAD(pages);

/* We can only do one array worth at a time. */ num = min(num, ARRAY_SIZE(vb->pfns));

- mutex_lock(&vb->balloon_lock); - for (vb->num_pfns = 0; vb->num_pfns < num; - vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) { - struct page *page = balloon_page_enqueue(vb_dev_info); + for (num_pfns = 0; num_pfns < num; + num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) { + struct page *page = balloon_page_alloc();

if (!page) { dev_info_ratelimited(&vb->vdev->dev, @@ -162,11 +163,23 @@ static unsigned fill_balloon(struct virtio_balloon *vb, size_t num) msleep(200); break; } + + balloon_page_push(&pages, page); + } + + mutex_lock(&vb->balloon_lock); + + vb->num_pfns = 0; + + while ((page = balloon_page_pop(&pages))) { + balloon_page_enqueue(&vb->vb_dev_info, page); + set_page_pfns(vb, vb->pfns + vb->num_pfns, page); vb->num_pages += VIRTIO_BALLOON_PAGES_PER_PAGE; if (!virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) adjust_managed_page_count(page, -1); + vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE; }

num_allocated_pages = vb->num_pfns; diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index c282e21f5b5e..41fce930f44c 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -708,6 +708,7 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,

crc_offset = le32_to_cpu((*cp_block)->checksum_offset); if (crc_offset > (blk_size - sizeof(__le32))) { + f2fs_put_page(*cp_page, 1); f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc_offset: %zu", crc_offset); return -EINVAL; @@ -715,6 +716,7 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,

crc = cur_cp_crc(*cp_block); if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) { + f2fs_put_page(*cp_page, 1); f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value"); return -EINVAL; } @@ -734,14 +736,14 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi, err = get_checkpoint_version(sbi, cp_addr, &cp_block, &cp_page_1, version); if (err) - goto invalid_cp1; + return NULL; pre_version = *version;

cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1; err = get_checkpoint_version(sbi, cp_addr, &cp_block, &cp_page_2, version); if (err) - goto invalid_cp2; + goto invalid_cp; cur_version = *version;

if (cur_version == pre_version) { @@ -749,9 +751,8 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi, f2fs_put_page(cp_page_2, 1); return cp_page_1; } -invalid_cp2: f2fs_put_page(cp_page_2, 1); -invalid_cp1: +invalid_cp: f2fs_put_page(cp_page_1, 1); return NULL; } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index e1cd3dcf5a03..ad827cf642fe 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1930,6 +1930,9 @@ static struct ubi_volume_desc *open_ubi(const char *name, int mode) int dev, vol; char *endptr;

+ if (!name || !*name) + return ERR_PTR(-EINVAL); + /* First, try to open using the device node path method */ ubi = ubi_open_volume_path(name, mode); if (!IS_ERR(ubi)) diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h index fbbe6da40fed..53051f3d8f25 100644 --- a/include/linux/balloon_compaction.h +++ b/include/linux/balloon_compaction.h @@ -50,6 +50,7 @@ #include <linux/gfp.h> #include <linux/err.h> #include <linux/fs.h> +#include <linux/list.h>

/* * Balloon device information descriptor. @@ -67,7 +68,9 @@ struct balloon_dev_info { struct inode *inode; };

-extern struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info); +extern struct page *balloon_page_alloc(void); +extern void balloon_page_enqueue(struct balloon_dev_info *b_dev_info, + struct page *page); extern struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info);

static inline void balloon_devinfo_init(struct balloon_dev_info *balloon) @@ -193,4 +196,34 @@ static inline gfp_t balloon_mapping_gfp_mask(void) }

#endif /* CONFIG_BALLOON_COMPACTION */ + +/* + * balloon_page_push - insert a page into a page list. + * @head : pointer to list + * @page : page to be added + * + * Caller must ensure the page is private and protect the list. + */ +static inline void balloon_page_push(struct list_head *pages, struct page *page) +{ + list_add(&page->lru, pages); +} + +/* + * balloon_page_pop - remove a page from a page list. + * @head : pointer to list + * @page : page to be added + * + * Caller must ensure the page is private and protect the list. + */ +static inline struct page *balloon_page_pop(struct list_head *pages) +{ + struct page *page = list_first_entry_or_null(pages, struct page, lru); + + if (!page) + return NULL; + + list_del(&page->lru); + return page; +} #endif /* _LINUX_BALLOON_COMPACTION_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 82a25880714a..7aa2de25c09c 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -140,6 +140,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write); struct page *follow_huge_pd(struct vm_area_struct *vma, @@ -169,6 +171,18 @@ static inline unsigned long hugetlb_total_pages(void) return 0; }

+static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, + pte_t *ptep) +{ + return 0; +} + +static inline void adjust_range_if_pmd_sharing_possible( + struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} + #define follow_hugetlb_page(m,v,p,vs,a,b,i,w,n) ({ BUG(); 0; }) #define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL) #define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; }) diff --git a/include/linux/mm.h b/include/linux/mm.h index a26cf767407e..58f2263de4de 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2322,6 +2322,12 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, return vma; }

+static inline bool range_in_vma(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + return (vma && vma->vm_start <= start && end <= vma->vm_end); +} + #ifdef CONFIG_MMU pgprot_t vm_get_page_prot(unsigned long vm_flags); void vma_set_page_prot(struct vm_area_struct *vma); diff --git a/kernel/events/core.c b/kernel/events/core.c index 812ebf1cbb87..4dbce29a9313 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3757,6 +3757,12 @@ int perf_event_read_local(struct perf_event *event, u64 *value) goto out; }

+ /* If this is a pinned event it must be running on this CPU */ + if (event->attr.pinned && event->oncpu != smp_processor_id()) { + ret = -EBUSY; + goto out; + } + /* * If the event is currently on this CPU, its either a per-task event, * or local to this CPU. Furthermore it means its ACTIVE (otherwise diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c index 68d28924ba79..ef858d547e2d 100644 --- a/mm/balloon_compaction.c +++ b/mm/balloon_compaction.c @@ -10,23 +10,38 @@ #include <linux/export.h> #include <linux/balloon_compaction.h>

+/* + * balloon_page_alloc - allocates a new page for insertion into the balloon + * page list. + * + * Driver must call it to properly allocate a new enlisted balloon page. + * Driver must call balloon_page_enqueue before definitively removing it from + * the guest system. This function returns the page address for the recently + * allocated page or NULL in the case we fail to allocate a new page this turn. + */ +struct page *balloon_page_alloc(void) +{ + struct page *page = alloc_page(balloon_mapping_gfp_mask() | + __GFP_NOMEMALLOC | __GFP_NORETRY); + return page; +} +EXPORT_SYMBOL_GPL(balloon_page_alloc); + /* * balloon_page_enqueue - allocates a new page and inserts it into the balloon * page list. * @b_dev_info: balloon device descriptor where we will insert a new page to + * @page: new page to enqueue - allocated using balloon_page_alloc. * - * Driver must call it to properly allocate a new enlisted balloon page + * Driver must call it to properly enqueue a new allocated balloon page * before definitively removing it from the guest system. * This function returns the page address for the recently enqueued page or * NULL in the case we fail to allocate a new page this turn. */ -struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info) +void balloon_page_enqueue(struct balloon_dev_info *b_dev_info, + struct page *page) { unsigned long flags; - struct page *page = alloc_page(balloon_mapping_gfp_mask() | - __GFP_NOMEMALLOC | __GFP_NORETRY); - if (!page) - return NULL;

/* * Block others from accessing the 'page' when we get around to @@ -39,7 +54,6 @@ struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info) __count_vm_event(BALLOON_INFLATE); spin_unlock_irqrestore(&b_dev_info->pages_lock, flags); unlock_page(page); - return page; } EXPORT_SYMBOL_GPL(balloon_page_enqueue);

diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 255469f78217..174612f8339c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2886,7 +2886,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE); page_add_anon_rmap(new, vma, mmun_start, true); set_pmd_at(mm, mmun_start, pvmw->pmd, pmde); - if (vma->vm_flags & VM_LOCKED) + if ((vma->vm_flags & VM_LOCKED) && !PageDoubleMap(new)) mlock_vma_page(new); update_mmu_cache_pmd(vma, address, pvmw->pmd); } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index dfd2947e046e..9801dc0250e2 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4517,12 +4517,40 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr) /* * check on proper vm_flags and page table alignment */ - if (vma->vm_flags & VM_MAYSHARE && - vma->vm_start <= base && end <= vma->vm_end) + if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end)) return true; return false; }

+/* + * Determine if start,end range within vma could be mapped by shared pmd. + * If yes, adjust start and end to cover range associated with possible + * shared pmd mappings. + */ +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ + unsigned long check_addr = *start; + + if (!(vma->vm_flags & VM_MAYSHARE)) + return; + + for (check_addr = *start; check_addr < *end; check_addr += PUD_SIZE) { + unsigned long a_start = check_addr & PUD_MASK; + unsigned long a_end = a_start + PUD_SIZE; + + /* + * If sharing is possible, adjust start/end if necessary. + */ + if (range_in_vma(vma, a_start, a_end)) { + if (a_start < *start) + *start = a_start; + if (a_end > *end) + *end = a_end; + } + } +} + /* * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the @@ -4620,6 +4648,11 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) { return 0; } + +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} #define want_pmd_share() (0) #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */

diff --git a/mm/migrate.c b/mm/migrate.c index 1236449b4777..cbb025239071 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -274,6 +274,9 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new)) mlock_vma_page(new);

+ if (PageTransHuge(page) && PageMlocked(page)) + clear_page_mlock(page); + /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, pvmw.address, pvmw.pte); } diff --git a/mm/rmap.c b/mm/rmap.c index 97edcf44d88c..8bd2ddd8febd 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1358,11 +1358,21 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, }

/* - * We have to assume the worse case ie pmd for invalidation. Note that - * the page can not be free in this function as call of try_to_unmap() - * must hold a reference on the page. + * For THP, we have to assume the worse case ie pmd for invalidation. + * For hugetlb, it could be much worse if we need to do pud + * invalidation in the case of pmd sharing. + * + * Note that the page can not be free in this function as call of + * try_to_unmap() must hold a reference on the page. */ end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page))); + if (PageHuge(page)) { + /* + * If sharing is possible, start and end will be adjusted + * accordingly. + */ + adjust_range_if_pmd_sharing_possible(vma, &start, &end); + } mmu_notifier_invalidate_range_start(vma->vm_mm, start, end);

while (page_vma_mapped_walk(&pvmw)) { @@ -1408,6 +1418,32 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); address = pvmw.address;

+ if (PageHuge(page)) { + if (huge_pmd_unshare(mm, &address, pvmw.pte)) { + /* + * huge_pmd_unshare unmapped an entire PMD + * page. There is no way of knowing exactly + * which PMDs may be cached for this mm, so + * we must flush them all. start/end were + * already adjusted above to cover this range. + */ + flush_cache_range(vma, start, end); + flush_tlb_range(vma, start, end); + mmu_notifier_invalidate_range(mm, start, end); + + /* + * The ref count of the PMD page was dropped + * which is part of the way map counting + * is done for shared PMDs. Return 'true' + * here. When there is no other sharing, + * huge_pmd_unshare returns false and we will + * unmap the actual page and drop map count + * to zero. + */ + page_vma_mapped_walk_done(&pvmw); + break; + } + }

if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && diff --git a/mm/vmstat.c b/mm/vmstat.c index 4bb13e72ac97..2bdc962b2dfe 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1203,6 +1203,9 @@ const char * const vmstat_text[] = { #ifdef CONFIG_SMP "nr_tlb_remote_flush", "nr_tlb_remote_flush_received", +#else + "", /* nr_tlb_remote_flush */ + "", /* nr_tlb_remote_flush_received */ #endif /* CONFIG_SMP */ "nr_tlb_local_flush_all", "nr_tlb_local_flush_one", diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index b456b882a6ea..63558335e41e 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -426,7 +426,7 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: /* Keys without a station are used for TX only */ - if (key->sta && test_sta_flag(key->sta, WLAN_STA_MFP)) + if (sta && test_sta_flag(sta, WLAN_STA_MFP)) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; case NL80211_IFTYPE_ADHOC: diff --git a/net/rds/ib.h b/net/rds/ib.h index 86a8578d95b8..7db93f7f5c61 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -373,7 +373,7 @@ void rds_ib_mr_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc); int rds_ib_recv_init(void); void rds_ib_recv_exit(void); int rds_ib_recv_path(struct rds_conn_path *conn); -int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic); +int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic, gfp_t gfp); void rds_ib_recv_free_caches(struct rds_ib_connection *ic); void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp); void rds_ib_inc_free(struct rds_incoming *inc); diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 6e721c449c4b..e086395a2355 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -946,7 +946,7 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp) if (!ic) return -ENOMEM;

- ret = rds_ib_recv_alloc_caches(ic); + ret = rds_ib_recv_alloc_caches(ic, gfp); if (ret) { kfree(ic); return ret; diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index b4e421aa9727..918d2e676b9b 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -98,12 +98,12 @@ static void rds_ib_cache_xfer_to_ready(struct rds_ib_refill_cache *cache) } }

-static int rds_ib_recv_alloc_cache(struct rds_ib_refill_cache *cache) +static int rds_ib_recv_alloc_cache(struct rds_ib_refill_cache *cache, gfp_t gfp) { struct rds_ib_cache_head *head; int cpu;

- cache->percpu = alloc_percpu(struct rds_ib_cache_head); + cache->percpu = alloc_percpu_gfp(struct rds_ib_cache_head, gfp); if (!cache->percpu) return -ENOMEM;

@@ -118,13 +118,13 @@ static int rds_ib_recv_alloc_cache(struct rds_ib_refill_cache *cache) return 0; }

-int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic) +int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic, gfp_t gfp) { int ret;

- ret = rds_ib_recv_alloc_cache(&ic->i_cache_incs); + ret = rds_ib_recv_alloc_cache(&ic->i_cache_incs, gfp); if (!ret) { - ret = rds_ib_recv_alloc_cache(&ic->i_cache_frags); + ret = rds_ib_recv_alloc_cache(&ic->i_cache_frags, gfp); if (ret) free_percpu(ic->i_cache_incs.percpu); } diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 615fdc63452e..e37653b0f2d0 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -25,6 +25,7 @@ #include "util/string2.h" #include "util/thread-stack.h" #include "util/time-utils.h" +#include "util/path.h" #include "print_binary.h" #include <linux/bitmap.h> #include <linux/kernel.h> @@ -2129,19 +2130,6 @@ static int parse_output_fields(const struct option *opt __maybe_unused, return rc; }

-/* Helper function for filesystems that return a dent->d_type DT_UNKNOWN */ -static int is_directory(const char *base_path, const struct dirent *dent) -{ - char path[PATH_MAX]; - struct stat st; - - sprintf(path, "%s/%s", base_path, dent->d_name); - if (stat(path, &st)) - return 0; - - return S_ISDIR(st.st_mode); -} - #define for_each_lang(scripts_path, scripts_dir, lang_dirent) \ while ((lang_dirent = readdir(scripts_dir)) != NULL) \ if ((lang_dirent->d_type == DT_DIR || \ diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index dac76ac117c1..398d4cc2f0e4 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1432,7 +1432,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map, struct arch **parch, char *cpuid) { struct dso *dso = map->dso; - char command[PATH_MAX * 2]; + char *command; struct arch *arch = NULL; FILE *file; char symfs_filename[PATH_MAX]; @@ -1496,7 +1496,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map, strcpy(symfs_filename, tmp); }

- snprintf(command, sizeof(command), + err = asprintf(&command, "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 " -l -d %s %s -C "%s" 2>/dev/null|grep -v "%s:"|expand", @@ -1509,12 +1509,17 @@ int symbol__disassemble(struct symbol *sym, struct map *map, symbol_conf.annotate_src ? "-S" : "", symfs_filename, symfs_filename);

+ if (err < 0) { + pr_err("Failure allocating memory for the command to run\n"); + goto out_remove_tmp; + } + pr_debug("Executing: %s\n", command);

err = -1; if (pipe(stdout_fd) < 0) { pr_err("Failure creating the pipe to run %s\n", command); - goto out_remove_tmp; + goto out_free_command; }

pid = fork(); @@ -1541,7 +1546,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map, * If we were using debug info should retry with * original binary. */ - goto out_remove_tmp; + goto out_free_command; }

nline = 0; @@ -1570,6 +1575,8 @@ int symbol__disassemble(struct symbol *sym, struct map *map,

fclose(file); err = 0; +out_free_command: + free(command); out_remove_tmp: close(stdout_fd[0]);

@@ -1583,7 +1590,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map,

out_close_stdout: close(stdout_fd[1]); - goto out_remove_tmp; + goto out_free_command; }

static void insert_source_line(struct rb_root *root, struct source_line *src_line) diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c index 933f5c6bffb4..ca56ba2dd3da 100644 --- a/tools/perf/util/path.c +++ b/tools/perf/util/path.c @@ -18,6 +18,7 @@ #include <stdio.h> #include <sys/types.h> #include <sys/stat.h> +#include <dirent.h> #include <unistd.h>

static char bad_path[] = "/bad-path/"; @@ -77,3 +78,16 @@ bool is_regular_file(const char *file)

return S_ISREG(st.st_mode); } + +/* Helper function for filesystems that return a dent->d_type DT_UNKNOWN */ +bool is_directory(const char *base_path, const struct dirent *dent) +{ + char path[PATH_MAX]; + struct stat st; + + sprintf(path, "%s/%s", base_path, dent->d_name); + if (stat(path, &st)) + return false; + + return S_ISDIR(st.st_mode); +} diff --git a/tools/perf/util/path.h b/tools/perf/util/path.h index 14a254ada7eb..f014f905df50 100644 --- a/tools/perf/util/path.h +++ b/tools/perf/util/path.h @@ -2,9 +2,12 @@ #ifndef _PERF_PATH_H #define _PERF_PATH_H

+struct dirent; + int path__join(char *bf, size_t size, const char *path1, const char *path2); int path__join3(char *bf, size_t size, const char *path1, const char *path2, const char *path3);

bool is_regular_file(const char *file); +bool is_directory(const char *base_path, const struct dirent *dent);

#endif /* _PERF_PATH_H */ diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index af415febbc46..da4df7fd43a2 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -28,6 +28,8 @@ class install_lib(_install_lib): cflags = getenv('CFLAGS', '').split() # switch off several checks (need to be at the end of cflags list) cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ] +if cc != "clang": + cflags += ['-Wno-cast-function-type' ]

src_perf = getenv('srctree') + '/tools/perf' build_lib = getenv('PYTHON_EXTBUILD_LIB') diff --git a/tools/testing/selftests/x86/test_vdso.c b/tools/testing/selftests/x86/test_vdso.c index 235259011704..35edd61d1663 100644 --- a/tools/testing/selftests/x86/test_vdso.c +++ b/tools/testing/selftests/x86/test_vdso.c @@ -17,6 +17,7 @@ #include <errno.h> #include <sched.h> #include <stdbool.h> +#include <limits.h>

#ifndef SYS_getcpu # ifdef __x86_64__ @@ -31,6 +32,14 @@

int nerrs = 0;

+typedef int (*vgettime_t)(clockid_t, struct timespec *); + +vgettime_t vdso_clock_gettime; + +typedef long (*vgtod_t)(struct timeval *tv, struct timezone *tz); + +vgtod_t vdso_gettimeofday; + typedef long (*getcpu_t)(unsigned *, unsigned *, void *);

getcpu_t vgetcpu; @@ -95,6 +104,15 @@ static void fill_function_pointers() printf("Warning: failed to find getcpu in vDSO\n");

vgetcpu = (getcpu_t) vsyscall_getcpu(); + + vdso_clock_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime"); + if (!vdso_clock_gettime) + printf("Warning: failed to find clock_gettime in vDSO\n"); + + vdso_gettimeofday = (vgtod_t)dlsym(vdso, "__vdso_gettimeofday"); + if (!vdso_gettimeofday) + printf("Warning: failed to find gettimeofday in vDSO\n"); + }

static long sys_getcpu(unsigned * cpu, unsigned * node, @@ -103,6 +121,16 @@ static long sys_getcpu(unsigned * cpu, unsigned * node, return syscall(__NR_getcpu, cpu, node, cache); }

+static inline int sys_clock_gettime(clockid_t id, struct timespec *ts) +{ + return syscall(__NR_clock_gettime, id, ts); +} + +static inline int sys_gettimeofday(struct timeval *tv, struct timezone *tz) +{ + return syscall(__NR_gettimeofday, tv, tz); +} + static void test_getcpu(void) { printf("[RUN]\tTesting getcpu...\n"); @@ -155,10 +183,154 @@ static void test_getcpu(void) } }

+static bool ts_leq(const struct timespec *a, const struct timespec *b) +{ + if (a->tv_sec != b->tv_sec) + return a->tv_sec < b->tv_sec; + else + return a->tv_nsec <= b->tv_nsec; +} + +static bool tv_leq(const struct timeval *a, const struct timeval *b) +{ + if (a->tv_sec != b->tv_sec) + return a->tv_sec < b->tv_sec; + else + return a->tv_usec <= b->tv_usec; +} + +static char const * const clocknames[] = { + [0] = "CLOCK_REALTIME", + [1] = "CLOCK_MONOTONIC", + [2] = "CLOCK_PROCESS_CPUTIME_ID", + [3] = "CLOCK_THREAD_CPUTIME_ID", + [4] = "CLOCK_MONOTONIC_RAW", + [5] = "CLOCK_REALTIME_COARSE", + [6] = "CLOCK_MONOTONIC_COARSE", + [7] = "CLOCK_BOOTTIME", + [8] = "CLOCK_REALTIME_ALARM", + [9] = "CLOCK_BOOTTIME_ALARM", + [10] = "CLOCK_SGI_CYCLE", + [11] = "CLOCK_TAI", +}; + +static void test_one_clock_gettime(int clock, const char *name) +{ + struct timespec start, vdso, end; + int vdso_ret, end_ret; + + printf("[RUN]\tTesting clock_gettime for clock %s (%d)...\n", name, clock); + + if (sys_clock_gettime(clock, &start) < 0) { + if (errno == EINVAL) { + vdso_ret = vdso_clock_gettime(clock, &vdso); + if (vdso_ret == -EINVAL) { + printf("[OK]\tNo such clock.\n"); + } else { + printf("[FAIL]\tNo such clock, but __vdso_clock_gettime returned %d\n", vdso_ret); + nerrs++; + } + } else { + printf("[WARN]\t clock_gettime(%d) syscall returned error %d\n", clock, errno); + } + return; + } + + vdso_ret = vdso_clock_gettime(clock, &vdso); + end_ret = sys_clock_gettime(clock, &end); + + if (vdso_ret != 0 || end_ret != 0) { + printf("[FAIL]\tvDSO returned %d, syscall errno=%d\n", + vdso_ret, errno); + nerrs++; + return; + } + + printf("\t%llu.%09ld %llu.%09ld %llu.%09ld\n", + (unsigned long long)start.tv_sec, start.tv_nsec, + (unsigned long long)vdso.tv_sec, vdso.tv_nsec, + (unsigned long long)end.tv_sec, end.tv_nsec); + + if (!ts_leq(&start, &vdso) || !ts_leq(&vdso, &end)) { + printf("[FAIL]\tTimes are out of sequence\n"); + nerrs++; + } +} + +static void test_clock_gettime(void) +{ + for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]); + clock++) { + test_one_clock_gettime(clock, clocknames[clock]); + } + + /* Also test some invalid clock ids */ + test_one_clock_gettime(-1, "invalid"); + test_one_clock_gettime(INT_MIN, "invalid"); + test_one_clock_gettime(INT_MAX, "invalid"); +} + +static void test_gettimeofday(void) +{ + struct timeval start, vdso, end; + struct timezone sys_tz, vdso_tz; + int vdso_ret, end_ret; + + if (!vdso_gettimeofday) + return; + + printf("[RUN]\tTesting gettimeofday...\n"); + + if (sys_gettimeofday(&start, &sys_tz) < 0) { + printf("[FAIL]\tsys_gettimeofday failed (%d)\n", errno); + nerrs++; + return; + } + + vdso_ret = vdso_gettimeofday(&vdso, &vdso_tz); + end_ret = sys_gettimeofday(&end, NULL); + + if (vdso_ret != 0 || end_ret != 0) { + printf("[FAIL]\tvDSO returned %d, syscall errno=%d\n", + vdso_ret, errno); + nerrs++; + return; + } + + printf("\t%llu.%06ld %llu.%06ld %llu.%06ld\n", + (unsigned long long)start.tv_sec, start.tv_usec, + (unsigned long long)vdso.tv_sec, vdso.tv_usec, + (unsigned long long)end.tv_sec, end.tv_usec); + + if (!tv_leq(&start, &vdso) || !tv_leq(&vdso, &end)) { + printf("[FAIL]\tTimes are out of sequence\n"); + nerrs++; + } + + if (sys_tz.tz_minuteswest == vdso_tz.tz_minuteswest && + sys_tz.tz_dsttime == vdso_tz.tz_dsttime) { + printf("[OK]\ttimezones match: minuteswest=%d, dsttime=%d\n", + sys_tz.tz_minuteswest, sys_tz.tz_dsttime); + } else { + printf("[FAIL]\ttimezones do not match\n"); + nerrs++; + } + + /* And make sure that passing NULL for tz doesn't crash. */ + vdso_gettimeofday(&vdso, NULL); +} + int main(int argc, char **argv) { fill_function_pointers();

+ test_clock_gettime(); + test_gettimeofday(); + + /* + * Test getcpu() last so that, if something goes wrong setting affinity, + * we still run the other tests. + */ test_getcpu();

return nerrs ? 1 : 0;