diff options
68 files changed, 540 insertions, 212 deletions
diff --git a/Documentation/devicetree/bindings/Makefile b/Documentation/devicetree/bindings/Makefile index 6e5cef0ed6fb..50daa0b3b032 100644 --- a/Documentation/devicetree/bindings/Makefile +++ b/Documentation/devicetree/bindings/Makefile @@ -17,7 +17,11 @@ extra-y += $(DT_TMP_SCHEMA) quiet_cmd_mk_schema = SCHEMA $@ cmd_mk_schema = $(DT_MK_SCHEMA) $(DT_MK_SCHEMA_FLAGS) -o $@ $(filter-out FORCE, $^) -DT_DOCS = $(shell cd $(srctree)/$(src) && find * -name '*.yaml') +DT_DOCS = $(shell \ + cd $(srctree)/$(src) && \ + find * \( -name '*.yaml' ! -name $(DT_TMP_SCHEMA) \) \ + ) + DT_SCHEMA_FILES ?= $(addprefix $(src)/,$(DT_DOCS)) extra-y += $(patsubst $(src)/%.yaml,%.example.dts, $(DT_SCHEMA_FILES)) diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index 33a2c94fed0d..63b4a1705182 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -30,6 +30,7 @@ generic-y += pgalloc.h generic-y += preempt.h generic-y += segment.h generic-y += serial.h +generic-y += shmparam.h generic-y += tlbflush.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/c6x/include/uapi/asm/Kbuild b/arch/c6x/include/uapi/asm/Kbuild index 6c6f6301012e..0febf1a07c30 100644 --- a/arch/c6x/include/uapi/asm/Kbuild +++ b/arch/c6x/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild index cd400d353d18..961c1dc064e1 100644 --- a/arch/h8300/include/asm/Kbuild +++ b/arch/h8300/include/asm/Kbuild @@ -40,6 +40,7 @@ generic-y += preempt.h generic-y += scatterlist.h generic-y += sections.h generic-y += serial.h +generic-y += shmparam.h generic-y += sizes.h generic-y += spinlock.h generic-y += timex.h diff --git a/arch/h8300/include/uapi/asm/Kbuild b/arch/h8300/include/uapi/asm/Kbuild index 6c6f6301012e..0febf1a07c30 100644 --- a/arch/h8300/include/uapi/asm/Kbuild +++ b/arch/h8300/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index 47c4da3d64a4..b25fd42aa0f4 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -30,6 +30,7 @@ generic-y += rwsem.h generic-y += sections.h generic-y += segment.h generic-y += serial.h +generic-y += shmparam.h generic-y += sizes.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/hexagon/include/uapi/asm/Kbuild b/arch/hexagon/include/uapi/asm/Kbuild index 61d955c1747a..c1b06dcf6cf8 100644 --- a/arch/hexagon/include/uapi/asm/Kbuild +++ b/arch/hexagon/include/uapi/asm/Kbuild @@ -1,4 +1,3 @@ include include/uapi/asm-generic/Kbuild.asm -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 9f1dd26903e3..95f8f631c4df 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -20,6 +20,7 @@ generic-y += mm-arch-hooks.h generic-y += percpu.h generic-y += preempt.h generic-y += sections.h +generic-y += shmparam.h generic-y += spinlock.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/m68k/include/uapi/asm/Kbuild b/arch/m68k/include/uapi/asm/Kbuild index b8b3525271fa..960bf1e4be53 100644 --- a/arch/m68k/include/uapi/asm/Kbuild +++ b/arch/m68k/include/uapi/asm/Kbuild @@ -2,4 +2,3 @@ include include/uapi/asm-generic/Kbuild.asm generated-y += unistd_32.h generic-y += kvm_para.h -generic-y += shmparam.h diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 9c7d1d25bf3d..791cc8d54d0a 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -26,6 +26,7 @@ generic-y += parport.h generic-y += percpu.h generic-y += preempt.h generic-y += serial.h +generic-y += shmparam.h generic-y += syscalls.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild index 28823e3db825..97823ec46e97 100644 --- a/arch/microblaze/include/uapi/asm/Kbuild +++ b/arch/microblaze/include/uapi/asm/Kbuild @@ -2,5 +2,4 @@ include include/uapi/asm-generic/Kbuild.asm generated-y += unistd_32.h generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index eb87cd8327c8..1f04844b6b82 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -34,6 +34,7 @@ generic-y += qrwlock_types.h generic-y += qrwlock.h generic-y += sections.h generic-y += segment.h +generic-y += shmparam.h generic-y += string.h generic-y += switch_to.h generic-y += topology.h diff --git a/arch/openrisc/include/uapi/asm/Kbuild b/arch/openrisc/include/uapi/asm/Kbuild index 6c6f6301012e..0febf1a07c30 100644 --- a/arch/openrisc/include/uapi/asm/Kbuild +++ b/arch/openrisc/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index feeeaa60697c..515fc3cc9687 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -103,7 +103,7 @@ choice prompt "Base ISA" default ARCH_RV64I help - This selects the base ISA that this kernel will traget and must match + This selects the base ISA that this kernel will target and must match the target platform. config ARCH_RV32I diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index f399659d3b8d..2fd3461e50ab 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -13,8 +13,6 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_BPF_SYSCALL=y CONFIG_SMP=y -CONFIG_PCI=y -CONFIG_PCIE_XILINX=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_NET=y @@ -28,6 +26,10 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y CONFIG_NETLINK_DIAG=y +CONFIG_PCI=y +CONFIG_PCIEPORTBUS=y +CONFIG_PCI_HOST_GENERIC=y +CONFIG_PCIE_XILINX=y CONFIG_DEVTMPFS=y CONFIG_BLK_DEV_LOOP=y CONFIG_VIRTIO_BLK=y @@ -63,7 +65,6 @@ CONFIG_USB_STORAGE=y CONFIG_USB_UAS=y CONFIG_VIRTIO_MMIO=y CONFIG_SIFIVE_PLIC=y -CONFIG_RAS=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_AUTOFS4_FS=y @@ -77,5 +78,6 @@ CONFIG_NFS_V4_1=y CONFIG_NFS_V4_2=y CONFIG_ROOT_NFS=y CONFIG_CRYPTO_USER_API_HASH=y +CONFIG_CRYPTO_DEV_VIRTIO=y CONFIG_PRINTK_TIME=y # CONFIG_RCU_TRACE is not set diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 06cfbb3aacbb..2a546a52f02a 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -80,7 +80,7 @@ typedef struct page *pgtable_t; #define __pgd(x) ((pgd_t) { (x) }) #define __pgprot(x) ((pgprot_t) { (x) }) -#ifdef CONFIG_64BITS +#ifdef CONFIG_64BIT #define PTE_FMT "%016lx" #else #define PTE_FMT "%08lx" diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index 0531f49af5c3..ce70bceb8872 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -22,7 +22,7 @@ * This decides where the kernel will search for a free chunk of vm * space during mmap's. */ -#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE >> 1) +#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE / 3) #define STACK_TOP TASK_SIZE #define STACK_TOP_MAX STACK_TOP diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index 6a92a2fe198e..dac98348c6a3 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -39,6 +39,7 @@ void asm_offsets(void) OFFSET(TASK_STACK, task_struct, stack); OFFSET(TASK_TI, task_struct, thread_info); OFFSET(TASK_TI_FLAGS, task_struct, thread_info.flags); + OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count); OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp); OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp); OFFSET(TASK_TI_CPU, task_struct, thread_info.cpu); diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 355166f57205..fd9b57c8b4ce 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -144,6 +144,10 @@ _save_context: REG_L x2, PT_SP(sp) .endm +#if !IS_ENABLED(CONFIG_PREEMPT) +.set resume_kernel, restore_all +#endif + ENTRY(handle_exception) SAVE_ALL @@ -228,7 +232,7 @@ ret_from_exception: REG_L s0, PT_SSTATUS(sp) csrc sstatus, SR_SIE andi s0, s0, SR_SPP - bnez s0, restore_all + bnez s0, resume_kernel resume_userspace: /* Interrupts must be disabled here so flags are checked atomically */ @@ -250,6 +254,18 @@ restore_all: RESTORE_ALL sret +#if IS_ENABLED(CONFIG_PREEMPT) +resume_kernel: + REG_L s0, TASK_TI_PREEMPT_COUNT(tp) + bnez s0, restore_all +need_resched: + REG_L s0, TASK_TI_FLAGS(tp) + andi s0, s0, _TIF_NEED_RESCHED + beqz s0, restore_all + call preempt_schedule_irq + j need_resched +#endif + work_pending: /* Enter slow path for supplementary processing */ la ra, ret_from_exception diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 6e079e94b638..77564310235f 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -181,7 +181,7 @@ static void __init setup_bootmem(void) BUG_ON(mem_size == 0); set_max_mapnr(PFN_DOWN(mem_size)); - max_low_pfn = memblock_end_of_DRAM(); + max_low_pfn = PFN_DOWN(memblock_end_of_DRAM()); #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index fc185ecabb0a..18cda0e8cf94 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -57,15 +57,12 @@ void __init setup_smp(void) while ((dn = of_find_node_by_type(dn, "cpu"))) { hart = riscv_of_processor_hartid(dn); - if (hart < 0) { - of_node_put(dn); + if (hart < 0) continue; - } if (hart == cpuid_to_hartid_map(0)) { BUG_ON(found_boot_cpu); found_boot_cpu = 1; - of_node_put(dn); continue; } @@ -73,7 +70,6 @@ void __init setup_smp(void) set_cpu_possible(cpuid, true); set_cpu_present(cpuid, true); cpuid++; - of_node_put(dn); } BUG_ON(!found_boot_cpu); diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 1d9bfaff60bc..658ebf645f42 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -28,7 +28,8 @@ static void __init zone_sizes_init(void) unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, }; #ifdef CONFIG_ZONE_DMA32 - max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, max_low_pfn)); + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, + (unsigned long) PFN_PHYS(max_low_pfn))); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild index 1372553dc0a9..1d1544b6ca74 100644 --- a/arch/unicore32/include/asm/Kbuild +++ b/arch/unicore32/include/asm/Kbuild @@ -28,6 +28,7 @@ generic-y += preempt.h generic-y += sections.h generic-y += segment.h generic-y += serial.h +generic-y += shmparam.h generic-y += sizes.h generic-y += syscalls.h generic-y += topology.h diff --git a/arch/unicore32/include/uapi/asm/Kbuild b/arch/unicore32/include/uapi/asm/Kbuild index 6c6f6301012e..0febf1a07c30 100644 --- a/arch/unicore32/include/uapi/asm/Kbuild +++ b/arch/unicore32/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 8f657286d599..0ce558a8150d 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -7,7 +7,11 @@ #endif #ifdef CONFIG_KASAN +#ifdef CONFIG_KASAN_EXTRA +#define KASAN_STACK_ORDER 2 +#else #define KASAN_STACK_ORDER 1 +#endif #else #define KASAN_STACK_ORDER 0 #endif diff --git a/block/blk-core.c b/block/blk-core.c index 3c5f61ceeb67..6b78ec56a4f2 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -462,6 +462,10 @@ static void blk_rq_timed_out_timer(struct timer_list *t) kblockd_schedule_work(&q->timeout_work); } +static void blk_timeout_work(struct work_struct *work) +{ +} + /** * blk_alloc_queue_node - allocate a request queue * @gfp_mask: memory allocation flags @@ -505,7 +509,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) timer_setup(&q->backing_dev_info->laptop_mode_wb_timer, laptop_mode_timer_fn, 0); timer_setup(&q->timeout, blk_rq_timed_out_timer, 0); - INIT_WORK(&q->timeout_work, NULL); + INIT_WORK(&q->timeout_work, blk_timeout_work); INIT_LIST_HEAD(&q->icq_list); #ifdef CONFIG_BLK_CGROUP INIT_LIST_HEAD(&q->blkg_list); diff --git a/block/blk-flush.c b/block/blk-flush.c index a3fc7191c694..6e0f2d97fc6d 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -335,7 +335,7 @@ static void mq_flush_data_end_io(struct request *rq, blk_status_t error) blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error); spin_unlock_irqrestore(&fq->mq_flush_lock, flags); - blk_mq_run_hw_queue(hctx, true); + blk_mq_sched_restart(hctx); } /** diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c index da58020a144e..33a28cde126c 100644 --- a/drivers/ide/ide-atapi.c +++ b/drivers/ide/ide-atapi.c @@ -235,21 +235,28 @@ EXPORT_SYMBOL_GPL(ide_prep_sense); int ide_queue_sense_rq(ide_drive_t *drive, void *special) { - struct request *sense_rq = drive->sense_rq; + ide_hwif_t *hwif = drive->hwif; + struct request *sense_rq; + unsigned long flags; + + spin_lock_irqsave(&hwif->lock, flags); /* deferred failure from ide_prep_sense() */ if (!drive->sense_rq_armed) { printk(KERN_WARNING PFX "%s: error queuing a sense request\n", drive->name); + spin_unlock_irqrestore(&hwif->lock, flags); return -ENOMEM; } + sense_rq = drive->sense_rq; ide_req(sense_rq)->special = special; drive->sense_rq_armed = false; drive->hwif->rq = NULL; ide_insert_request_head(drive, sense_rq); + spin_unlock_irqrestore(&hwif->lock, flags); return 0; } EXPORT_SYMBOL_GPL(ide_queue_sense_rq); diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 8445b484ae69..b137f27a34d5 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -68,8 +68,10 @@ int ide_end_rq(ide_drive_t *drive, struct request *rq, blk_status_t error, } if (!blk_update_request(rq, error, nr_bytes)) { - if (rq == drive->sense_rq) + if (rq == drive->sense_rq) { drive->sense_rq = NULL; + drive->sense_rq_active = false; + } __blk_mq_end_request(rq, error); return 0; @@ -451,16 +453,11 @@ void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq) blk_mq_delay_run_hw_queue(q->queue_hw_ctx[0], 3); } -/* - * Issue a new request to a device. - */ -blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *hctx, - const struct blk_mq_queue_data *bd) +blk_status_t ide_issue_rq(ide_drive_t *drive, struct request *rq, + bool local_requeue) { - ide_drive_t *drive = hctx->queue->queuedata; - ide_hwif_t *hwif = drive->hwif; + ide_hwif_t *hwif = drive->hwif; struct ide_host *host = hwif->host; - struct request *rq = bd->rq; ide_startstop_t startstop; if (!blk_rq_is_passthrough(rq) && !(rq->rq_flags & RQF_DONTPREP)) { @@ -474,8 +471,6 @@ blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *hctx, if (ide_lock_host(host, hwif)) return BLK_STS_DEV_RESOURCE; - blk_mq_start_request(rq); - spin_lock_irq(&hwif->lock); if (!ide_lock_port(hwif)) { @@ -511,18 +506,6 @@ repeat: drive->dev_flags &= ~(IDE_DFLAG_SLEEPING | IDE_DFLAG_PARKED); /* - * we know that the queue isn't empty, but this can happen - * if ->prep_rq() decides to kill a request - */ - if (!rq) { - rq = bd->rq; - if (!rq) { - ide_unlock_port(hwif); - goto out; - } - } - - /* * Sanity: don't accept a request that isn't a PM request * if we are currently power managed. This is very important as * blk_stop_queue() doesn't prevent the blk_fetch_request() @@ -560,9 +543,12 @@ repeat: } } else { plug_device: + if (local_requeue) + list_add(&rq->queuelist, &drive->rq_list); spin_unlock_irq(&hwif->lock); ide_unlock_host(host); - ide_requeue_and_plug(drive, rq); + if (!local_requeue) + ide_requeue_and_plug(drive, rq); return BLK_STS_OK; } @@ -573,6 +559,26 @@ out: return BLK_STS_OK; } +/* + * Issue a new request to a device. + */ +blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *hctx, + const struct blk_mq_queue_data *bd) +{ + ide_drive_t *drive = hctx->queue->queuedata; + ide_hwif_t *hwif = drive->hwif; + + spin_lock_irq(&hwif->lock); + if (drive->sense_rq_active) { + spin_unlock_irq(&hwif->lock); + return BLK_STS_DEV_RESOURCE; + } + spin_unlock_irq(&hwif->lock); + + blk_mq_start_request(bd->rq); + return ide_issue_rq(drive, bd->rq, false); +} + static int drive_is_ready(ide_drive_t *drive) { ide_hwif_t *hwif = drive->hwif; @@ -893,13 +899,8 @@ EXPORT_SYMBOL_GPL(ide_pad_transfer); void ide_insert_request_head(ide_drive_t *drive, struct request *rq) { - ide_hwif_t *hwif = drive->hwif; - unsigned long flags; - - spin_lock_irqsave(&hwif->lock, flags); + drive->sense_rq_active = true; list_add_tail(&rq->queuelist, &drive->rq_list); - spin_unlock_irqrestore(&hwif->lock, flags); - kblockd_schedule_work(&drive->rq_work); } EXPORT_SYMBOL_GPL(ide_insert_request_head); diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c index 102aa3bc3e7f..8af7af6001eb 100644 --- a/drivers/ide/ide-park.c +++ b/drivers/ide/ide-park.c @@ -54,7 +54,9 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout) scsi_req(rq)->cmd[0] = REQ_UNPARK_HEADS; scsi_req(rq)->cmd_len = 1; ide_req(rq)->type = ATA_PRIV_MISC; + spin_lock_irq(&hwif->lock); ide_insert_request_head(drive, rq); + spin_unlock_irq(&hwif->lock); out: return; diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 63627be0811a..5aeaca24a28f 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -1159,18 +1159,27 @@ static void drive_rq_insert_work(struct work_struct *work) ide_drive_t *drive = container_of(work, ide_drive_t, rq_work); ide_hwif_t *hwif = drive->hwif; struct request *rq; + blk_status_t ret; LIST_HEAD(list); - spin_lock_irq(&hwif->lock); - if (!list_empty(&drive->rq_list)) - list_splice_init(&drive->rq_list, &list); - spin_unlock_irq(&hwif->lock); + blk_mq_quiesce_queue(drive->queue); - while (!list_empty(&list)) { - rq = list_first_entry(&list, struct request, queuelist); + ret = BLK_STS_OK; + spin_lock_irq(&hwif->lock); + while (!list_empty(&drive->rq_list)) { + rq = list_first_entry(&drive->rq_list, struct request, queuelist); list_del_init(&rq->queuelist); - blk_execute_rq_nowait(drive->queue, rq->rq_disk, rq, true, NULL); + + spin_unlock_irq(&hwif->lock); + ret = ide_issue_rq(drive, rq, true); + spin_lock_irq(&hwif->lock); } + spin_unlock_irq(&hwif->lock); + + blk_mq_unquiesce_queue(drive->queue); + + if (ret != BLK_STS_OK) + kblockd_schedule_work(&drive->rq_work); } static const u8 ide_hwif_to_major[] = diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index ec3a5ef7fee0..cbbe6b6535be 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -1935,12 +1935,14 @@ out: } static struct stripe_head * -r5c_recovery_alloc_stripe(struct r5conf *conf, - sector_t stripe_sect) +r5c_recovery_alloc_stripe( + struct r5conf *conf, + sector_t stripe_sect, + int noblock) { struct stripe_head *sh; - sh = raid5_get_active_stripe(conf, stripe_sect, 0, 1, 0); + sh = raid5_get_active_stripe(conf, stripe_sect, 0, noblock, 0); if (!sh) return NULL; /* no more stripe available */ @@ -2150,7 +2152,7 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log, stripe_sect); if (!sh) { - sh = r5c_recovery_alloc_stripe(conf, stripe_sect); + sh = r5c_recovery_alloc_stripe(conf, stripe_sect, 1); /* * cannot get stripe from raid5_get_active_stripe * try replay some stripes @@ -2159,20 +2161,29 @@ 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); + conf, stripe_sect, 1); } if (!sh) { + int new_size = conf->min_nr_stripes * 2; pr_debug("md/raid:%s: Increasing stripe cache size to %d to recovery data on journal.\n", mdname(mddev), - conf->min_nr_stripes * 2); - raid5_set_cache_size(mddev, - conf->min_nr_stripes * 2); - sh = r5c_recovery_alloc_stripe(conf, - stripe_sect); + new_size); + ret = raid5_set_cache_size(mddev, new_size); + if (conf->min_nr_stripes <= new_size / 2) { + pr_err("md/raid:%s: Cannot increase cache size, ret=%d, new_size=%d, min_nr_stripes=%d, max_nr_stripes=%d\n", + mdname(mddev), + ret, + new_size, + conf->min_nr_stripes, + conf->max_nr_stripes); + return -ENOMEM; + } + sh = r5c_recovery_alloc_stripe( + conf, stripe_sect, 0); } if (!sh) { pr_err("md/raid:%s: Cannot get enough stripes due to memory pressure. Recovery failed.\n", - mdname(mddev)); + mdname(mddev)); return -ENOMEM; } list_add_tail(&sh->lru, cached_stripe_list); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 4990f0319f6c..cecea901ab8c 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6369,6 +6369,7 @@ raid5_show_stripe_cache_size(struct mddev *mddev, char *page) int raid5_set_cache_size(struct mddev *mddev, int size) { + int result = 0; struct r5conf *conf = mddev->private; if (size <= 16 || size > 32768) @@ -6385,11 +6386,14 @@ raid5_set_cache_size(struct mddev *mddev, int size) mutex_lock(&conf->cache_size_mutex); while (size > conf->max_nr_stripes) - if (!grow_one_stripe(conf, GFP_KERNEL)) + if (!grow_one_stripe(conf, GFP_KERNEL)) { + conf->min_nr_stripes = conf->max_nr_stripes; + result = -ENOMEM; break; + } mutex_unlock(&conf->cache_size_mutex); - return 0; + return result; } EXPORT_SYMBOL(raid5_set_cache_size); diff --git a/drivers/s390/scsi/zfcp_aux.c b/drivers/s390/scsi/zfcp_aux.c index 9cf30d124b9e..e390f8c6d5f3 100644 --- a/drivers/s390/scsi/zfcp_aux.c +++ b/drivers/s390/scsi/zfcp_aux.c @@ -403,7 +403,6 @@ struct zfcp_adapter *zfcp_adapter_enqueue(struct ccw_device *ccw_device) goto failed; /* report size limit per scatter-gather segment */ - adapter->dma_parms.max_segment_size = ZFCP_QDIO_SBALE_LEN; adapter->ccw_device->dev.dma_parms = &adapter->dma_parms; adapter->stat_read_buf_num = FSF_STATUS_READS_RECOM; diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c index 00acc7144bbc..f4f6a07c5222 100644 --- a/drivers/s390/scsi/zfcp_scsi.c +++ b/drivers/s390/scsi/zfcp_scsi.c @@ -428,6 +428,8 @@ static struct scsi_host_template zfcp_scsi_host_template = { .max_sectors = (((QDIO_MAX_ELEMENTS_PER_BUFFER - 1) * ZFCP_QDIO_MAX_SBALS_PER_REQ) - 2) * 8, /* GCD, adjusted later */ + /* report size limit per scatter-gather segment */ + .max_segment_size = ZFCP_QDIO_SBALE_LEN, .dma_boundary = ZFCP_QDIO_SBALE_LEN - 1, .shost_attrs = zfcp_sysfs_shost_attrs, .sdev_attrs = zfcp_sysfs_sdev_attrs, diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c index 128d658d472a..16957d7ac414 100644 --- a/drivers/scsi/53c700.c +++ b/drivers/scsi/53c700.c @@ -295,7 +295,7 @@ NCR_700_detect(struct scsi_host_template *tpnt, if(tpnt->sdev_attrs == NULL) tpnt->sdev_attrs = NCR_700_dev_attrs; - memory = dma_alloc_attrs(hostdata->dev, TOTAL_MEM_SIZE, &pScript, + memory = dma_alloc_attrs(dev, TOTAL_MEM_SIZE, &pScript, GFP_KERNEL, DMA_ATTR_NON_CONSISTENT); if(memory == NULL) { printk(KERN_ERR "53c700: Failed to allocate memory for driver, detaching\n"); diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c index 350257c13a5b..bc9f2a2365f4 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_io.c +++ b/drivers/scsi/bnx2fc/bnx2fc_io.c @@ -240,6 +240,7 @@ struct bnx2fc_cmd_mgr *bnx2fc_cmd_mgr_alloc(struct bnx2fc_hba *hba) return NULL; } + cmgr->hba = hba; cmgr->free_list = kcalloc(arr_sz, sizeof(*cmgr->free_list), GFP_KERNEL); if (!cmgr->free_list) { @@ -256,7 +257,6 @@ struct bnx2fc_cmd_mgr *bnx2fc_cmd_mgr_alloc(struct bnx2fc_hba *hba) goto mem_err; } - cmgr->hba = hba; cmgr->cmds = (struct bnx2fc_cmd **)(cmgr + 1); for (i = 0; i < arr_sz; i++) { @@ -295,7 +295,7 @@ struct bnx2fc_cmd_mgr *bnx2fc_cmd_mgr_alloc(struct bnx2fc_hba *hba) /* Allocate pool of io_bdts - one for each bnx2fc_cmd */ mem_size = num_ios * sizeof(struct io_bdt *); - cmgr->io_bdt_pool = kmalloc(mem_size, GFP_KERNEL); + cmgr->io_bdt_pool = kzalloc(mem_size, GFP_KERNEL); if (!cmgr->io_bdt_pool) { printk(KERN_ERR PFX "failed to alloc io_bdt_pool\n"); goto mem_err; diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c index be83590ed955..ff943f477d6f 100644 --- a/drivers/scsi/libfc/fc_lport.c +++ b/drivers/scsi/libfc/fc_lport.c @@ -1726,14 +1726,14 @@ void fc_lport_flogi_resp(struct fc_seq *sp, struct fc_frame *fp, fc_frame_payload_op(fp) != ELS_LS_ACC) { FC_LPORT_DBG(lport, "FLOGI not accepted or bad response\n"); fc_lport_error(lport, fp); - goto err; + goto out; } flp = fc_frame_payload_get(fp, sizeof(*flp)); if (!flp) { FC_LPORT_DBG(lport, "FLOGI bad response\n"); fc_lport_error(lport, fp); - goto err; + goto out; } mfs = ntohs(flp->fl_csp.sp_bb_data) & @@ -1743,7 +1743,7 @@ void fc_lport_flogi_resp(struct fc_seq *sp, struct fc_frame *fp, FC_LPORT_DBG(lport, "FLOGI bad mfs:%hu response, " "lport->mfs:%hu\n", mfs, lport->mfs); fc_lport_error(lport, fp); - goto err; + goto out; } if (mfs <= lport->mfs) { diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 661512bec3ac..e27f4df24021 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -62,7 +62,7 @@ /* make sure inq_product_rev string corresponds to this version */ #define SDEBUG_VERSION "0188" /* format to fit INQUIRY revision field */ -static const char *sdebug_version_date = "20180128"; +static const char *sdebug_version_date = "20190125"; #define MY_NAME "scsi_debug" @@ -735,7 +735,7 @@ static inline bool scsi_debug_lbp(void) (sdebug_lbpu || sdebug_lbpws || sdebug_lbpws10); } -static void *fake_store(unsigned long long lba) +static void *lba2fake_store(unsigned long long lba) { lba = do_div(lba, sdebug_store_sectors); @@ -2514,8 +2514,8 @@ static int do_device_access(struct scsi_cmnd *scmd, u32 sg_skip, u64 lba, return ret; } -/* If fake_store(lba,num) compares equal to arr(num), then copy top half of - * arr into fake_store(lba,num) and return true. If comparison fails then +/* If lba2fake_store(lba,num) compares equal to arr(num), then copy top half of + * arr into lba2fake_store(lba,num) and return true. If comparison fails then * return false. */ static bool comp_write_worker(u64 lba, u32 num, const u8 *arr) { @@ -2643,7 +2643,7 @@ static int prot_verify_read(struct scsi_cmnd *SCpnt, sector_t start_sec, if (sdt->app_tag == cpu_to_be16(0xffff)) continue; - ret = dif_verify(sdt, fake_store(sector), sector, ei_lba); + ret = dif_verify(sdt, lba2fake_store(sector), sector, ei_lba); if (ret) { dif_errors++; return ret; @@ -3261,10 +3261,12 @@ err_out: static int resp_write_same(struct scsi_cmnd *scp, u64 lba, u32 num, u32 ei_lba, bool unmap, bool ndob) { + int ret; unsigned long iflags; unsigned long long i; - int ret; - u64 lba_off; + u32 lb_size = sdebug_sector_size; + u64 block, lbaa; + u8 *fs1p; ret = check_device_access_params(scp, lba, num); if (ret) @@ -3276,31 +3278,30 @@ static int resp_write_same(struct scsi_cmnd *scp, u64 lba, u32 num, unmap_region(lba, num); goto out; } - - lba_off = lba * sdebug_sector_size; + lbaa = lba; + block = do_div(lbaa, sdebug_store_sectors); /* if ndob then zero 1 logical block, else fetch 1 logical block */ + fs1p = fake_storep + (block * lb_size); if (ndob) { - memset(fake_storep + lba_off, 0, sdebug_sector_size); + memset(fs1p, 0, lb_size); ret = 0; } else - ret = fetch_to_dev_buffer(scp, fake_storep + lba_off, - sdebug_sector_size); + ret = fetch_to_dev_buffer(scp, fs1p, lb_size); if (-1 == ret) { write_unlock_irqrestore(&atomic_rw, iflags); return DID_ERROR << 16; - } else if (sdebug_verbose && !ndob && (ret < sdebug_sector_size)) + } else if (sdebug_verbose && !ndob && (ret < lb_size)) sdev_printk(KERN_INFO, scp->device, "%s: %s: lb size=%u, IO sent=%d bytes\n", - my_name, "write same", - sdebug_sector_size, ret); + my_name, "write same", lb_size, ret); /* Copy first sector to remaining blocks */ - for (i = 1 ; i < num ; i++) - memcpy(fake_storep + ((lba + i) * sdebug_sector_size), - fake_storep + lba_off, - sdebug_sector_size); - + for (i = 1 ; i < num ; i++) { + lbaa = lba + i; + block = do_div(lbaa, sdebug_store_sectors); + memmove(fake_storep + (block * lb_size), fs1p, lb_size); + } if (scsi_debug_lbp()) map_region(lba, num); out: diff --git a/drivers/tty/serial/earlycon-riscv-sbi.c b/drivers/tty/serial/earlycon-riscv-sbi.c index e1a551aae336..ce81523c3113 100644 --- a/drivers/tty/serial/earlycon-riscv-sbi.c +++ b/drivers/tty/serial/earlycon-riscv-sbi.c @@ -10,13 +10,16 @@ #include <linux/serial_core.h> #include <asm/sbi.h> -static void sbi_console_write(struct console *con, - const char *s, unsigned int n) +static void sbi_putc(struct uart_port *port, int c) { - int i; + sbi_console_putchar(c); +} - for (i = 0; i < n; ++i) - sbi_console_putchar(s[i]); +static void sbi_console_write(struct console *con, + const char *s, unsigned n) +{ + struct earlycon_device *dev = con->data; + uart_console_write(&dev->port, s, n, sbi_putc); } static int __init early_sbi_setup(struct earlycon_device *device, diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c index d441244b79df..28d9c2b1b3bb 100644 --- a/fs/autofs/expire.c +++ b/fs/autofs/expire.c @@ -596,7 +596,6 @@ int autofs_expire_run(struct super_block *sb, pkt.len = dentry->d_name.len; memcpy(pkt.name, dentry->d_name.name, pkt.len); pkt.name[pkt.len] = '\0'; - dput(dentry); if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire))) ret = -EFAULT; @@ -609,6 +608,8 @@ int autofs_expire_run(struct super_block *sb, complete_all(&ino->expire_complete); spin_unlock(&sbi->fs_lock); + dput(dentry); + return ret; } diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index 0e8ea2d9a2bb..078992eee299 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -266,8 +266,10 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) } root_inode = autofs_get_inode(s, S_IFDIR | 0755); root = d_make_root(root_inode); - if (!root) + if (!root) { + ret = -ENOMEM; goto fail_ino; + } pipe = NULL; root->d_fsdata = ino; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index f64aad613727..5a6c39b44c84 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -968,6 +968,48 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, return 0; } +static struct extent_buffer *alloc_tree_block_no_bg_flush( + struct btrfs_trans_handle *trans, + struct btrfs_root *root, + u64 parent_start, + const struct btrfs_disk_key *disk_key, + int level, + u64 hint, + u64 empty_size) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + struct extent_buffer *ret; + + /* + * If we are COWing a node/leaf from the extent, chunk, device or free + * space trees, make sure that we do not finish block group creation of + * pending block groups. We do this to avoid a deadlock. + * COWing can result in allocation of a new chunk, and flushing pending + * block groups (btrfs_create_pending_block_groups()) can be triggered + * when finishing allocation of a new chunk. Creation of a pending block + * group modifies the extent, chunk, device and free space trees, + * therefore we could deadlock with ourselves since we are holding a + * lock on an extent buffer that btrfs_create_pending_block_groups() may + * try to COW later. + * For similar reasons, we also need to delay flushing pending block + * groups when splitting a leaf or node, from one of those trees, since + * we are holding a write lock on it and its parent or when inserting a + * new root node for one of those trees. + */ + if (root == fs_info->extent_root || + root == fs_info->chunk_root || + root == fs_info->dev_root || + root == fs_info->free_space_root) + trans->can_flush_pending_bgs = false; + + ret = btrfs_alloc_tree_block(trans, root, parent_start, + root->root_key.objectid, disk_key, level, + hint, empty_size); + trans->can_flush_pending_bgs = true; + + return ret; +} + /* * does the dirty work in cow of a single block. The parent block (if * supplied) is updated to point to the new cow copy. The new buffer is marked @@ -1015,28 +1057,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, if ((root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && parent) parent_start = parent->start; - /* - * If we are COWing a node/leaf from the extent, chunk, device or free - * space trees, make sure that we do not finish block group creation of - * pending block groups. We do this to avoid a deadlock. - * COWing can result in allocation of a new chunk, and flushing pending - * block groups (btrfs_create_pending_block_groups()) can be triggered - * when finishing allocation of a new chunk. Creation of a pending block - * group modifies the extent, chunk, device and free space trees, - * therefore we could deadlock with ourselves since we are holding a - * lock on an extent buffer that btrfs_create_pending_block_groups() may - * try to COW later. - */ - if (root == fs_info->extent_root || - root == fs_info->chunk_root || - root == fs_info->dev_root || - root == fs_info->free_space_root) - trans->can_flush_pending_bgs = false; - - cow = btrfs_alloc_tree_block(trans, root, parent_start, - root->root_key.objectid, &disk_key, level, - search_start, empty_size); - trans->can_flush_pending_bgs = true; + cow = alloc_tree_block_no_bg_flush(trans, root, parent_start, &disk_key, + level, search_start, empty_size); if (IS_ERR(cow)) return PTR_ERR(cow); @@ -3345,8 +3367,8 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, else btrfs_node_key(lower, &lower_key, 0); - c = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, - &lower_key, level, root->node->start, 0); + c = alloc_tree_block_no_bg_flush(trans, root, 0, &lower_key, level, + root->node->start, 0); if (IS_ERR(c)) return PTR_ERR(c); @@ -3475,8 +3497,8 @@ static noinline int split_node(struct btrfs_trans_handle *trans, mid = (c_nritems + 1) / 2; btrfs_node_key(c, &disk_key, mid); - split = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, - &disk_key, level, c->start, 0); + split = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, level, + c->start, 0); if (IS_ERR(split)) return PTR_ERR(split); @@ -4260,8 +4282,8 @@ again: else btrfs_item_key(l, &disk_key, mid); - right = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, - &disk_key, 0, l->start, 0); + right = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, 0, + l->start, 0); if (IS_ERR(right)) return PTR_ERR(right); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index c5586ffd1426..0a3f122dd61f 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1621,6 +1621,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, flags | SB_RDONLY, device_name, data); if (IS_ERR(mnt_root)) { root = ERR_CAST(mnt_root); + kfree(subvol_name); goto out; } @@ -1630,12 +1631,14 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, if (error < 0) { root = ERR_PTR(error); mntput(mnt_root); + kfree(subvol_name); goto out; } } } if (IS_ERR(mnt_root)) { root = ERR_CAST(mnt_root); + kfree(subvol_name); goto out; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 127fa1535f58..4ec2b660d014 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -850,14 +850,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, btrfs_trans_release_chunk_metadata(trans); - if (lock && should_end_transaction(trans) && - READ_ONCE(cur_trans->state) == TRANS_STATE_RUNNING) { - spin_lock(&info->trans_lock); - if (cur_trans->state == TRANS_STATE_RUNNING) - cur_trans->state = TRANS_STATE_BLOCKED; - spin_unlock(&info->trans_lock); - } - if (lock && READ_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) { if (throttle) return btrfs_commit_transaction(trans); @@ -1879,6 +1871,21 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err) kmem_cache_free(btrfs_trans_handle_cachep, trans); } +/* + * Release reserved delayed ref space of all pending block groups of the + * transaction and remove them from the list + */ +static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_block_group_cache *block_group, *tmp; + + list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) { + btrfs_delayed_refs_rsv_release(fs_info, 1); + list_del_init(&block_group->bg_list); + } +} + static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) { /* @@ -2270,6 +2277,7 @@ scrub_continue: btrfs_scrub_continue(fs_info); cleanup_transaction: btrfs_trans_release_metadata(trans); + btrfs_cleanup_pending_block_groups(trans); btrfs_trans_release_chunk_metadata(trans); trans->block_rsv = NULL; btrfs_warn(fs_info, "Skipping commit of aborted transaction."); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 3e4f8f88353e..15561926ab32 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -957,11 +957,11 @@ static noinline struct btrfs_device *device_list_add(const char *path, else fs_devices = alloc_fs_devices(disk_super->fsid, NULL); - fs_devices->fsid_change = fsid_change_in_progress; - if (IS_ERR(fs_devices)) return ERR_CAST(fs_devices); + fs_devices->fsid_change = fsid_change_in_progress; + mutex_lock(&fs_devices->device_list_mutex); list_add(&fs_devices->fs_list, &fs_uuids); diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 82377017130f..d31b6c72b476 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -21,8 +21,13 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); + /* + * We must skip inodes in unusual state. We may also skip + * inodes without pages but we deliberately won't in case + * we need to reschedule to avoid softlockups. + */ if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || - (inode->i_mapping->nrpages == 0)) { + (inode->i_mapping->nrpages == 0 && !need_resched())) { spin_unlock(&inode->i_lock); continue; } @@ -30,6 +35,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); + cond_resched(); invalidate_mapping_pages(inode->i_mapping, 0, -1); iput(toput_inode); toput_inode = inode; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 8ae109429a88..e39bac94dead 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -256,7 +256,7 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry, inode = proc_get_inode(dir->i_sb, de); if (!inode) return ERR_PTR(-ENOMEM); - d_set_d_op(dentry, &proc_misc_dentry_ops); + d_set_d_op(dentry, de->proc_dops); return d_splice_alias(inode, dentry); } read_unlock(&proc_subdir_lock); @@ -429,6 +429,8 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, INIT_LIST_HEAD(&ent->pde_openers); proc_set_user(ent, (*parent)->uid, (*parent)->gid); + ent->proc_dops = &proc_misc_dentry_ops; + out: return ent; } diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 5185d7f6a51e..95b14196f284 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -44,6 +44,7 @@ struct proc_dir_entry { struct completion *pde_unload_completion; const struct inode_operations *proc_iops; const struct file_operations *proc_fops; + const struct dentry_operations *proc_dops; union { const struct seq_operations *seq_ops; int (*single_show)(struct seq_file *, void *); diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index d5e0fcb3439e..a7b12435519e 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -38,6 +38,22 @@ static struct net *get_proc_net(const struct inode *inode) return maybe_get_net(PDE_NET(PDE(inode))); } +static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + return 0; +} + +static const struct dentry_operations proc_net_dentry_ops = { + .d_revalidate = proc_net_d_revalidate, + .d_delete = always_delete_dentry, +}; + +static void pde_force_lookup(struct proc_dir_entry *pde) +{ + /* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */ + pde->proc_dops = &proc_net_dentry_ops; +} + static int seq_open_net(struct inode *inode, struct file *file) { unsigned int state_size = PDE(inode)->state_size; @@ -90,6 +106,7 @@ struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_seq_fops; p->seq_ops = ops; p->state_size = state_size; @@ -133,6 +150,7 @@ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_seq_fops; p->seq_ops = ops; p->state_size = state_size; @@ -181,6 +199,7 @@ struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_single_fops; p->single_show = show; return proc_register(parent, p); @@ -223,6 +242,7 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_single_fops; p->single_show = show; p->write = write; diff --git a/include/linux/ide.h b/include/linux/ide.h index e7d29ae633cd..971cf76a78a0 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -615,6 +615,7 @@ struct ide_drive_s { /* current sense rq and buffer */ bool sense_rq_armed; + bool sense_rq_active; struct request *sense_rq; struct request_sense sense_data; @@ -1219,6 +1220,7 @@ extern void ide_stall_queue(ide_drive_t *drive, unsigned long timeout); extern void ide_timer_expiry(struct timer_list *t); extern irqreturn_t ide_intr(int irq, void *dev_id); extern blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); +extern blk_status_t ide_issue_rq(ide_drive_t *, struct request *, bool); extern void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq); void ide_init_disk(struct gendisk *, ide_drive_t *); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 07da5c6c5ba0..368267c1b71b 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -21,14 +21,16 @@ struct vmem_altmap; * walkers which rely on the fully initialized page->flags and others * should use this rather than pfn_valid && pfn_to_page */ -#define pfn_to_online_page(pfn) \ -({ \ - struct page *___page = NULL; \ - unsigned long ___nr = pfn_to_section_nr(pfn); \ - \ - if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\ - ___page = pfn_to_page(pfn); \ - ___page; \ +#define pfn_to_online_page(pfn) \ +({ \ + struct page *___page = NULL; \ + unsigned long ___pfn = pfn; \ + unsigned long ___nr = pfn_to_section_nr(___pfn); \ + \ + if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \ + pfn_valid_within(___pfn)) \ + ___page = pfn_to_page(___pfn); \ + ___page; \ }) /* diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index ec912d01126f..ecdc6542070f 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -71,6 +71,7 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ #define MMF_OOM_VICTIM 25 /* mm is the oom victim */ +#define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ diff --git a/init/Kconfig b/init/Kconfig index 513fa544a134..c9386a365eea 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -512,6 +512,17 @@ config PSI_DEFAULT_DISABLED per default but can be enabled through passing psi=1 on the kernel commandline during boot. + This feature adds some code to the task wakeup and sleep + paths of the scheduler. The overhead is too low to affect + common scheduling-intense workloads in practice (such as + webservers, memcache), but it does show up in artificial + scheduler stress tests, such as hackbench. + + If you are paranoid and not sure what the kernel will be + used for, say Y. + + Say N if unsure. + endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION @@ -825,7 +836,7 @@ config CGROUP_PIDS PIDs controller is designed to stop this from happening. It should be noted that organisational operations (such as attaching - to a cgroup hierarchy will *not* be blocked by the PIDs controller), + to a cgroup hierarchy) will *not* be blocked by the PIDs controller, since the PIDs limit only affects a process's ability to fork, not to attach to a cgroup. diff --git a/kernel/exit.c b/kernel/exit.c index 3fb7be001964..2639a30a8aa5 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -558,12 +558,14 @@ static struct task_struct *find_alive_thread(struct task_struct *p) return NULL; } -static struct task_struct *find_child_reaper(struct task_struct *father) +static struct task_struct *find_child_reaper(struct task_struct *father, + struct list_head *dead) __releases(&tasklist_lock) __acquires(&tasklist_lock) { struct pid_namespace *pid_ns = task_active_pid_ns(father); struct task_struct *reaper = pid_ns->child_reaper; + struct task_struct *p, *n; if (likely(reaper != father)) return reaper; @@ -579,6 +581,12 @@ static struct task_struct *find_child_reaper(struct task_struct *father) panic("Attempted to kill init! exitcode=0x%08x\n", father->signal->group_exit_code ?: father->exit_code); } + + list_for_each_entry_safe(p, n, dead, ptrace_entry) { + list_del_init(&p->ptrace_entry); + release_task(p); + } + zap_pid_ns_processes(pid_ns); write_lock_irq(&tasklist_lock); @@ -668,7 +676,7 @@ static void forget_original_parent(struct task_struct *father, exit_ptrace(father, dead); /* Can drop and reacquire tasklist_lock */ - reaper = find_child_reaper(father); + reaper = find_child_reaper(father, dead); if (list_empty(&father->children)) return; diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index fe24de3fbc93..c3484785b179 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -124,6 +124,7 @@ * sampling of the aggregate task states would be. */ +#include "../workqueue_internal.h" #include <linux/sched/loadavg.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> @@ -480,9 +481,6 @@ static void psi_group_change(struct psi_group *group, int cpu, groupc->tasks[t]++; write_seqcount_end(&groupc->seq); - - if (!delayed_work_pending(&group->clock_work)) - schedule_delayed_work(&group->clock_work, PSI_FREQ); } static struct psi_group *iterate_groups(struct task_struct *task, void **iter) @@ -513,6 +511,7 @@ void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); struct psi_group *group; + bool wake_clock = true; void *iter = NULL; if (!task->pid) @@ -530,8 +529,22 @@ void psi_task_change(struct task_struct *task, int clear, int set) task->psi_flags &= ~clear; task->psi_flags |= set; - while ((group = iterate_groups(task, &iter))) + /* + * Periodic aggregation shuts off if there is a period of no + * task changes, so we wake it back up if necessary. However, + * don't do this if the task change is the aggregation worker + * itself going to sleep, or we'll ping-pong forever. + */ + if (unlikely((clear & TSK_RUNNING) && + (task->flags & PF_WQ_WORKER) && + wq_worker_last_func(task) == psi_update_work)) + wake_clock = false; + + while ((group = iterate_groups(task, &iter))) { psi_group_change(group, cpu, clear, set); + if (wake_clock && !delayed_work_pending(&group->clock_work)) + schedule_delayed_work(&group->clock_work, PSI_FREQ); + } } void psi_memstall_tick(struct task_struct *task, int cpu) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 392be4b252f6..fc5d23d752a5 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -910,6 +910,26 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task) } /** + * wq_worker_last_func - retrieve worker's last work function + * + * Determine the last function a worker executed. This is called from + * the scheduler to get a worker's last known identity. + * + * CONTEXT: + * spin_lock_irq(rq->lock) + * + * Return: + * The last work function %current executed as a worker, NULL if it + * hasn't executed any work yet. + */ +work_func_t wq_worker_last_func(struct task_struct *task) +{ + struct worker *worker = kthread_data(task); + + return worker->last_func; +} + +/** * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to set @@ -2184,6 +2204,9 @@ __acquires(&pool->lock) if (unlikely(cpu_intensive)) worker_clr_flags(worker, WORKER_CPU_INTENSIVE); + /* tag the worker for identification in schedule() */ + worker->last_func = worker->current_func; + /* we're done with it, release */ hash_del(&worker->hentry); worker->current_work = NULL; diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index 66fbb5a9e633..cb68b03ca89a 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -53,6 +53,9 @@ struct worker { /* used only by rescuers to point to the target workqueue */ struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ + + /* used by the scheduler to determine a worker's last known identity */ + work_func_t last_func; }; /** @@ -67,9 +70,10 @@ static inline struct worker *current_wq_worker(void) /* * Scheduler hooks for concurrency managed workqueue. Only to be used from - * sched/core.c and workqueue.c. + * sched/ and workqueue.c. */ void wq_worker_waking_up(struct task_struct *task, int cpu); struct task_struct *wq_worker_sleeping(struct task_struct *task); +work_func_t wq_worker_last_func(struct task_struct *task); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ diff --git a/lib/test_kmod.c b/lib/test_kmod.c index d82d022111e0..9cf77628fc91 100644 --- a/lib/test_kmod.c +++ b/lib/test_kmod.c @@ -632,7 +632,7 @@ static void __kmod_config_free(struct test_config *config) config->test_driver = NULL; kfree_const(config->test_fs); - config->test_driver = NULL; + config->test_fs = NULL; } static void kmod_config_free(struct kmod_test_device *test_dev) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index df2e7dd5ff17..afef61656c1e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4268,7 +4268,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, break; } if (ret & VM_FAULT_RETRY) { - if (nonblocking) + if (nonblocking && + !(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *nonblocking = 0; *nr_pages = 0; /* diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile index 0a14fcff70ed..e2bb06c1b45e 100644 --- a/mm/kasan/Makefile +++ b/mm/kasan/Makefile @@ -5,6 +5,7 @@ UBSAN_SANITIZE_generic.o := n UBSAN_SANITIZE_tags.o := n KCOV_INSTRUMENT := n +CFLAGS_REMOVE_common.o = -pg CFLAGS_REMOVE_generic.o = -pg # Function splitter causes unnecessary splits in __asan_load1/__asan_store1 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533 diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 7c72f2a95785..831be5ff5f4d 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -372,7 +372,8 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, if (fail || tk->addr_valid == 0) { pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", pfn, tk->tsk->comm, tk->tsk->pid); - force_sig(SIGKILL, tk->tsk); + do_send_sig_info(SIGKILL, SEND_SIG_PRIV, + tk->tsk, PIDTYPE_PID); } /* diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b9a667d36c55..124e794867c5 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1233,7 +1233,8 @@ static bool is_pageblock_removable_nolock(struct page *page) bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) { struct page *page = pfn_to_page(start_pfn); - struct page *end_page = page + nr_pages; + unsigned long end_pfn = min(start_pfn + nr_pages, zone_end_pfn(page_zone(page))); + struct page *end_page = pfn_to_page(end_pfn); /* Check the starting page of each pageblock within the range */ for (; page < end_page; page = next_active_pageblock(page)) { @@ -1273,6 +1274,9 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, i++; if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn) continue; + /* Check if we got outside of the zone */ + if (zone && !zone_spans_pfn(zone, pfn + i)) + return 0; page = pfn_to_page(pfn + i); if (zone && page_zone(page) != zone) return 0; @@ -1301,23 +1305,27 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, static unsigned long scan_movable_pages(unsigned long start, unsigned long end) { unsigned long pfn; - struct page *page; + for (pfn = start; pfn < end; pfn++) { - if (pfn_valid(pfn)) { - page = pfn_to_page(pfn); - if (PageLRU(page)) - return pfn; - if (__PageMovable(page)) - return pfn; - if (PageHuge(page)) { - if (hugepage_migration_supported(page_hstate(page)) && - page_huge_active(page)) - return pfn; - else - pfn = round_up(pfn + 1, - 1 << compound_order(page)) - 1; - } - } + struct page *page, *head; + unsigned long skip; + + if (!pfn_valid(pfn)) + continue; + page = pfn_to_page(pfn); + if (PageLRU(page)) + return pfn; + if (__PageMovable(page)) + return pfn; + + if (!PageHuge(page)) + continue; + head = compound_head(page); + if (hugepage_migration_supported(page_hstate(head)) && + page_huge_active(head)) + return pfn; + skip = (1 << compound_order(head)) - (page - head); + pfn += skip - 1; } return 0; } @@ -1344,7 +1352,6 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; struct page *page; - int not_managed = 0; int ret = 0; LIST_HEAD(source); @@ -1392,7 +1399,6 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) else ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE); if (!ret) { /* Success */ - put_page(page); list_add_tail(&page->lru, &source); if (!__PageMovable(page)) inc_node_page_state(page, NR_ISOLATED_ANON + @@ -1401,22 +1407,10 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) } else { pr_warn("failed to isolate pfn %lx\n", pfn); dump_page(page, "isolation failed"); - put_page(page); - /* Because we don't have big zone->lock. we should - check this again here. */ - if (page_count(page)) { - not_managed++; - ret = -EBUSY; - break; - } } + put_page(page); } if (!list_empty(&source)) { - if (not_managed) { - putback_movable_pages(&source); - goto out; - } - /* Allocate a new page from the nearest neighbor node */ ret = migrate_pages(&source, new_node_page, NULL, 0, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); @@ -1429,7 +1423,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) putback_movable_pages(&source); } } -out: + return ret; } @@ -1576,7 +1570,6 @@ static int __ref __offline_pages(unsigned long start_pfn, we assume this for now. .*/ if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end)) { - mem_hotplug_done(); ret = -EINVAL; reason = "multizone range"; goto failed_removal; @@ -1591,7 +1584,6 @@ static int __ref __offline_pages(unsigned long start_pfn, MIGRATE_MOVABLE, SKIP_HWPOISON | REPORT_FAILURE); if (ret) { - mem_hotplug_done(); reason = "failure to isolate range"; goto failed_removal; } diff --git a/mm/migrate.c b/mm/migrate.c index a16b15090df3..d4fd680be3b0 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -709,7 +709,6 @@ static bool buffer_migrate_lock_buffers(struct buffer_head *head, /* Simple case, sync compaction */ if (mode != MIGRATE_ASYNC) { do { - get_bh(bh); lock_buffer(bh); bh = bh->b_this_page; @@ -720,18 +719,15 @@ static bool buffer_migrate_lock_buffers(struct buffer_head *head, /* async case, we cannot block on lock_buffer so use trylock_buffer */ do { - get_bh(bh); if (!trylock_buffer(bh)) { /* * We failed to lock the buffer and cannot stall in * async migration. Release the taken locks */ struct buffer_head *failed_bh = bh; - put_bh(failed_bh); bh = head; while (bh != failed_bh) { unlock_buffer(bh); - put_bh(bh); bh = bh->b_this_page; } return false; @@ -818,7 +814,6 @@ unlock_buffers: bh = head; do { unlock_buffer(bh); - put_bh(bh); bh = bh->b_this_page; } while (bh != head); @@ -1135,10 +1130,13 @@ out: * If migration is successful, decrease refcount of the newpage * which will not free the page because new page owner increased * refcounter. As well, if it is LRU page, add the page to LRU - * list in here. + * list in here. Use the old state of the isolated source page to + * determine if we migrated a LRU page. newpage was already unlocked + * and possibly modified by its owner - don't rely on the page + * state. */ if (rc == MIGRATEPAGE_SUCCESS) { - if (unlikely(__PageMovable(newpage))) + if (unlikely(!is_lru)) put_page(newpage); else putback_lru_page(newpage); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index f0e8cd9edb1a..26ea8636758f 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -647,8 +647,8 @@ static int oom_reaper(void *unused) static void wake_oom_reaper(struct task_struct *tsk) { - /* tsk is already queued? */ - if (tsk == oom_reaper_list || tsk->oom_reaper_list) + /* mm is already queued? */ + if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) return; get_task_struct(tsk); @@ -975,6 +975,13 @@ static void oom_kill_process(struct oom_control *oc, const char *message) * still freeing memory. */ read_lock(&tasklist_lock); + + /* + * The task 'p' might have already exited before reaching here. The + * put_task_struct() will free task_struct 'p' while the loop still try + * to access the field of 'p', so, get an extra reference. + */ + get_task_struct(p); for_each_thread(p, t) { list_for_each_entry(child, &t->children, sibling) { unsigned int child_points; @@ -994,6 +1001,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) } } } + put_task_struct(p); read_unlock(&tasklist_lock); /* diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore index 82121a81681f..29bac5ef9a93 100644 --- a/tools/testing/selftests/proc/.gitignore +++ b/tools/testing/selftests/proc/.gitignore @@ -10,4 +10,5 @@ /proc-uptime-002 /read /self +/setns-dcache /thread-self diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftests/proc/Makefile index 1c12c34cf85d..434d033ee067 100644 --- a/tools/testing/selftests/proc/Makefile +++ b/tools/testing/selftests/proc/Makefile @@ -14,6 +14,7 @@ TEST_GEN_PROGS += proc-uptime-001 TEST_GEN_PROGS += proc-uptime-002 TEST_GEN_PROGS += read TEST_GEN_PROGS += self +TEST_GEN_PROGS += setns-dcache TEST_GEN_PROGS += thread-self include ../lib.mk diff --git a/tools/testing/selftests/proc/setns-dcache.c b/tools/testing/selftests/proc/setns-dcache.c new file mode 100644 index 000000000000..60ab197a73fc --- /dev/null +++ b/tools/testing/selftests/proc/setns-dcache.c @@ -0,0 +1,129 @@ +/* + * Copyright © 2019 Alexey Dobriyan <adobriyan@gmail.com> + * + * Permission to use, copy, modify, and distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR + * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ +/* + * Test that setns(CLONE_NEWNET) points to new /proc/net content even + * if old one is in dcache. + * + * FIXME /proc/net/unix is under CONFIG_UNIX which can be disabled. + */ +#undef NDEBUG +#include <assert.h> +#include <errno.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <sys/socket.h> + +static pid_t pid = -1; + +static void f(void) +{ + if (pid > 0) { + kill(pid, SIGTERM); + } +} + +int main(void) +{ + int fd[2]; + char _ = 0; + int nsfd; + + atexit(f); + + /* Check for priviledges and syscall availability straight away. */ + if (unshare(CLONE_NEWNET) == -1) { + if (errno == ENOSYS || errno == EPERM) { + return 4; + } + return 1; + } + /* Distinguisher between two otherwise empty net namespaces. */ + if (socket(AF_UNIX, SOCK_STREAM, 0) == -1) { + return 1; + } + + if (pipe(fd) == -1) { + return 1; + } + + pid = fork(); + if (pid == -1) { + return 1; + } + + if (pid == 0) { + if (unshare(CLONE_NEWNET) == -1) { + return 1; + } + + if (write(fd[1], &_, 1) != 1) { + return 1; + } + + pause(); + + return 0; + } + + if (read(fd[0], &_, 1) != 1) { + return 1; + } + + { + char buf[64]; + snprintf(buf, sizeof(buf), "/proc/%u/ns/net", pid); + nsfd = open(buf, O_RDONLY); + if (nsfd == -1) { + return 1; + } + } + + /* Reliably pin dentry into dcache. */ + (void)open("/proc/net/unix", O_RDONLY); + + if (setns(nsfd, CLONE_NEWNET) == -1) { + return 1; + } + + kill(pid, SIGTERM); + pid = 0; + + { + char buf[4096]; + ssize_t rv; + int fd; + + fd = open("/proc/net/unix", O_RDONLY); + if (fd == -1) { + return 1; + } + +#define S "Num RefCount Protocol Flags Type St Inode Path\n" + rv = read(fd, buf, sizeof(buf)); + + assert(rv == strlen(S)); + assert(memcmp(buf, S, strlen(S)) == 0); + } + + return 0; +} |