diff options
79 files changed, 470 insertions, 262 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 546aa66428c9..6eff4f720c72 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4588,7 +4588,7 @@ B: https://bugzilla.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git F: Documentation/admin-guide/pm/cpuidle.rst F: Documentation/driver-api/pm/cpuidle.rst -F: drivers/cpuidle/* +F: drivers/cpuidle/ F: include/linux/cpuidle.h CPU POWER MONITORING SUBSYSTEM diff --git a/arch/alpha/include/asm/local64.h b/arch/alpha/include/asm/local64.h deleted file mode 100644 index 36c93b5cc239..000000000000 --- a/arch/alpha/include/asm/local64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/local64.h> diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index 81f4edec0c2a..3c1afa524b9c 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 generic-y += extable.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += parport.h generic-y += user.h diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index 4a0848aef207..03657ff8fbe3 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += early_ioremap.h generic-y += extable.h generic-y += flat.h -generic-y += local64.h generic-y += parport.h generated-y += mach-types.h diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index ff9cbb631212..07ac208edc89 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -1,6 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 generic-y += early_ioremap.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += qrwlock.h generic-y += qspinlock.h diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild index 93372255984d..cc24bb8e539f 100644 --- a/arch/csky/include/asm/Kbuild +++ b/arch/csky/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += asm-offsets.h generic-y += gpio.h generic-y += kvm_para.h -generic-y += local64.h generic-y += qrwlock.h generic-y += user.h generic-y += vmlinux.lds.h diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild index ddf04f32b546..60ee7f0d60a8 100644 --- a/arch/h8300/include/asm/Kbuild +++ b/arch/h8300/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += asm-offsets.h generic-y += extable.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += parport.h generic-y += spinlock.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index 373964bb177e..3ece3c93fe08 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -2,5 +2,4 @@ generic-y += extable.h generic-y += iomap.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h diff --git a/arch/ia64/include/asm/local64.h b/arch/ia64/include/asm/local64.h deleted file mode 100644 index 36c93b5cc239..000000000000 --- a/arch/ia64/include/asm/local64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/local64.h> diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 9b5acf8fb092..e76386a3479e 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -536,7 +536,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg) if (map_start < map_end) memmap_init_zone((unsigned long)(map_end - map_start), - args->nid, args->zone, page_to_pfn(map_start), + args->nid, args->zone, page_to_pfn(map_start), page_to_pfn(map_end), MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); return 0; } @@ -546,7 +546,7 @@ memmap_init (unsigned long size, int nid, unsigned long zone, unsigned long start_pfn) { if (!vmem_map) { - memmap_init_zone(size, nid, zone, start_pfn, + memmap_init_zone(size, nid, zone, start_pfn, start_pfn + size, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); } else { struct page *start; diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 1bff55aa2d54..0dbf9c5c6fae 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -2,6 +2,5 @@ generated-y += syscall_table.h generic-y += extable.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += spinlock.h diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 63bce836b9f1..29b0e557aa7c 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -2,7 +2,6 @@ generated-y += syscall_table.h generic-y += extable.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += parport.h generic-y += syscalls.h diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 198b3bafdac9..95b4fa7bd0d1 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -6,7 +6,6 @@ generated-y += syscall_table_64_n64.h generated-y += syscall_table_64_o32.h generic-y += export.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += parport.h generic-y += qrwlock.h diff --git a/arch/nds32/include/asm/Kbuild b/arch/nds32/include/asm/Kbuild index ff1e94299317..82a4453c9c2d 100644 --- a/arch/nds32/include/asm/Kbuild +++ b/arch/nds32/include/asm/Kbuild @@ -4,6 +4,5 @@ generic-y += cmpxchg.h generic-y += export.h generic-y += gpio.h generic-y += kvm_para.h -generic-y += local64.h generic-y += parport.h generic-y += user.h diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index 442f3d3bcd90..ca5987e11053 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 generic-y += extable.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += qspinlock_types.h generic-y += qspinlock.h diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild index f16c4db80116..4406475a2304 100644 --- a/arch/parisc/include/asm/Kbuild +++ b/arch/parisc/include/asm/Kbuild @@ -3,6 +3,5 @@ generated-y += syscall_table_32.h generated-y += syscall_table_64.h generated-y += syscall_table_c32.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += user.h diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 90cd5c53af66..e1f9b4ea1c53 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -5,7 +5,6 @@ generated-y += syscall_table_c32.h generated-y += syscall_table_spu.h generic-y += export.h generic-y += kvm_types.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += qrwlock.h generic-y += vtime.h diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index 59dd7be55005..445ccc97305a 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -3,6 +3,5 @@ generic-y += early_ioremap.h generic-y += extable.h generic-y += flat.h generic-y += kvm_para.h -generic-y += local64.h generic-y += user.h generic-y += vmlinux.lds.h diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 319efa0e6d02..1a18d7b82f86 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -7,5 +7,4 @@ generated-y += unistd_nr.h generic-y += asm-offsets.h generic-y += export.h generic-y += kvm_types.h -generic-y += local64.h generic-y += mcs_spinlock.h diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild index 7435182ef846..fc44d9c88b41 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -1,6 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 generated-y += syscall_table.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += parport.h diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index 5269a704801f..3688fdae50e4 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -6,5 +6,4 @@ generated-y += syscall_table_64.h generated-y += syscall_table_c32.h generic-y += export.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h diff --git a/arch/x86/include/asm/local64.h b/arch/x86/include/asm/local64.h deleted file mode 100644 index 36c93b5cc239..000000000000 --- a/arch/x86/include/asm/local64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/local64.h> diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index 9718e9593564..854c5e07e867 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -2,7 +2,6 @@ generated-y += syscall_table.h generic-y += extable.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += param.h generic-y += qrwlock.h diff --git a/block/blk-core.c b/block/blk-core.c index 96e5fcd7f071..7663a9b94b80 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -18,6 +18,7 @@ #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/blk-mq.h> +#include <linux/blk-pm.h> #include <linux/highmem.h> #include <linux/mm.h> #include <linux/pagemap.h> @@ -424,11 +425,11 @@ EXPORT_SYMBOL(blk_cleanup_queue); /** * blk_queue_enter() - try to increase q->q_usage_counter * @q: request queue pointer - * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PREEMPT + * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PM */ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags) { - const bool pm = flags & BLK_MQ_REQ_PREEMPT; + const bool pm = flags & BLK_MQ_REQ_PM; while (true) { bool success = false; @@ -440,7 +441,8 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags) * responsible for ensuring that that counter is * globally visible before the queue is unfrozen. */ - if (pm || !blk_queue_pm_only(q)) { + if ((pm && queue_rpm_status(q) != RPM_SUSPENDED) || + !blk_queue_pm_only(q)) { success = true; } else { percpu_ref_put(&q->q_usage_counter); @@ -465,8 +467,7 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags) wait_event(q->mq_freeze_wq, (!q->mq_freeze_depth && - (pm || (blk_pm_request_resume(q), - !blk_queue_pm_only(q)))) || + blk_pm_resume_queue(pm, q)) || blk_queue_dying(q)); if (blk_queue_dying(q)) return -ENODEV; @@ -630,7 +631,7 @@ struct request *blk_get_request(struct request_queue *q, unsigned int op, struct request *req; WARN_ON_ONCE(op & REQ_NOWAIT); - WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PREEMPT)); + WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PM)); req = blk_mq_alloc_request(q, op, flags); if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn) diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 3094542e12ae..4d6e83e5b442 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -129,6 +129,7 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(PCI_P2PDMA), QUEUE_FLAG_NAME(ZONE_RESETALL), QUEUE_FLAG_NAME(RQ_ALLOC_TIME), + QUEUE_FLAG_NAME(NOWAIT), }; #undef QUEUE_FLAG_NAME @@ -297,7 +298,6 @@ static const char *const rqf_name[] = { RQF_NAME(MIXED_MERGE), RQF_NAME(MQ_INFLIGHT), RQF_NAME(DONTPREP), - RQF_NAME(PREEMPT), RQF_NAME(FAILED), RQF_NAME(QUIET), RQF_NAME(ELVPRIV), diff --git a/block/blk-mq.c b/block/blk-mq.c index c338c9bc5a2c..f285a9123a8b 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -294,8 +294,8 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, rq->mq_hctx = data->hctx; rq->rq_flags = 0; rq->cmd_flags = data->cmd_flags; - if (data->flags & BLK_MQ_REQ_PREEMPT) - rq->rq_flags |= RQF_PREEMPT; + if (data->flags & BLK_MQ_REQ_PM) + rq->rq_flags |= RQF_PM; if (blk_queue_io_stat(data->q)) rq->rq_flags |= RQF_IO_STAT; INIT_LIST_HEAD(&rq->queuelist); diff --git a/block/blk-pm.c b/block/blk-pm.c index b85234d758f7..17bd020268d4 100644 --- a/block/blk-pm.c +++ b/block/blk-pm.c @@ -67,6 +67,10 @@ int blk_pre_runtime_suspend(struct request_queue *q) WARN_ON_ONCE(q->rpm_status != RPM_ACTIVE); + spin_lock_irq(&q->queue_lock); + q->rpm_status = RPM_SUSPENDING; + spin_unlock_irq(&q->queue_lock); + /* * Increase the pm_only counter before checking whether any * non-PM blk_queue_enter() calls are in progress to avoid that any @@ -89,15 +93,14 @@ int blk_pre_runtime_suspend(struct request_queue *q) /* Switch q_usage_counter back to per-cpu mode. */ blk_mq_unfreeze_queue(q); - spin_lock_irq(&q->queue_lock); - if (ret < 0) + if (ret < 0) { + spin_lock_irq(&q->queue_lock); + q->rpm_status = RPM_ACTIVE; pm_runtime_mark_last_busy(q->dev); - else - q->rpm_status = RPM_SUSPENDING; - spin_unlock_irq(&q->queue_lock); + spin_unlock_irq(&q->queue_lock); - if (ret) blk_clear_pm_only(q); + } return ret; } diff --git a/block/blk-pm.h b/block/blk-pm.h index ea5507d23e75..a2283cc9f716 100644 --- a/block/blk-pm.h +++ b/block/blk-pm.h @@ -6,11 +6,14 @@ #include <linux/pm_runtime.h> #ifdef CONFIG_PM -static inline void blk_pm_request_resume(struct request_queue *q) +static inline int blk_pm_resume_queue(const bool pm, struct request_queue *q) { - if (q->dev && (q->rpm_status == RPM_SUSPENDED || - q->rpm_status == RPM_SUSPENDING)) - pm_request_resume(q->dev); + if (!q->dev || !blk_queue_pm_only(q)) + return 1; /* Nothing to do */ + if (pm && q->rpm_status != RPM_SUSPENDED) + return 1; /* Request allowed */ + pm_request_resume(q->dev); + return 0; } static inline void blk_pm_mark_last_busy(struct request *rq) @@ -44,8 +47,9 @@ static inline void blk_pm_put_request(struct request *rq) --rq->q->nr_pending; } #else -static inline void blk_pm_request_resume(struct request_queue *q) +static inline int blk_pm_resume_queue(const bool pm, struct request_queue *q) { + return 1; } static inline void blk_pm_mark_last_busy(struct request *rq) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 6e23376548ce..1a660466dd75 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -3086,7 +3086,6 @@ static int __init intel_pstate_init(void) intel_pstate.attr = hwp_cpufreq_attrs; intel_cpufreq.attr = hwp_cpufreq_attrs; intel_cpufreq.flags |= CPUFREQ_NEED_UPDATE_LIMITS; - intel_cpufreq.fast_switch = NULL; intel_cpufreq.adjust_perf = intel_cpufreq_adjust_perf; if (!default_driver) default_driver = &intel_pstate; diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c index 2162bc80f09e..013ad33fbbc8 100644 --- a/drivers/ide/ide-atapi.c +++ b/drivers/ide/ide-atapi.c @@ -223,7 +223,6 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq) sense_rq->rq_disk = rq->rq_disk; sense_rq->cmd_flags = REQ_OP_DRV_IN; ide_req(sense_rq)->type = ATA_PRIV_SENSE; - sense_rq->rq_flags |= RQF_PREEMPT; req->cmd[0] = GPCMD_REQUEST_SENSE; req->cmd[4] = cmd_len; diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 1a53c7a75224..4867b67b60d6 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -515,15 +515,10 @@ repeat: * above to return us whatever is in the queue. Since we call * ide_do_request() ourselves, we end up taking requests while * the queue is blocked... - * - * We let requests forced at head of queue with ide-preempt - * though. I hope that doesn't happen too much, hopefully not - * unless the subdriver triggers such a thing in its own PM - * state machine. */ if ((drive->dev_flags & IDE_DFLAG_BLOCKED) && ata_pm_request(rq) == 0 && - (rq->rq_flags & RQF_PREEMPT) == 0) { + (rq->rq_flags & RQF_PM) == 0) { /* there should be no pending command at this point */ ide_unlock_port(hwif); goto plug_device; diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c index 192e6c65d34e..82ab308f1aaf 100644 --- a/drivers/ide/ide-pm.c +++ b/drivers/ide/ide-pm.c @@ -77,7 +77,7 @@ int generic_ide_resume(struct device *dev) } memset(&rqpm, 0, sizeof(rqpm)); - rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, BLK_MQ_REQ_PREEMPT); + rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, BLK_MQ_REQ_PM); ide_req(rq)->type = ATA_PRIV_PM_RESUME; ide_req(rq)->special = &rqpm; rqpm.pm_step = IDE_PM_START_RESUME; diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index d79335506ecd..28f93b9aa51b 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -963,6 +963,39 @@ static struct cpuidle_state dnv_cstates[] __initdata = { .enter = NULL } }; +/* + * Note, depending on HW and FW revision, SnowRidge SoC may or may not support + * C6, and this is indicated in the CPUID mwait leaf. + */ +static struct cpuidle_state snr_cstates[] __initdata = { + { + .name = "C1", + .desc = "MWAIT 0x00", + .flags = MWAIT2flg(0x00), + .exit_latency = 2, + .target_residency = 2, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .name = "C1E", + .desc = "MWAIT 0x01", + .flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE, + .exit_latency = 15, + .target_residency = 25, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .name = "C6", + .desc = "MWAIT 0x20", + .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 130, + .target_residency = 500, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .enter = NULL } +}; + static const struct idle_cpu idle_cpu_nehalem __initconst = { .state_table = nehalem_cstates, .auto_demotion_disable_flags = NHM_C1_AUTO_DEMOTE | NHM_C3_AUTO_DEMOTE, @@ -1084,6 +1117,12 @@ static const struct idle_cpu idle_cpu_dnv __initconst = { .use_acpi = true, }; +static const struct idle_cpu idle_cpu_snr __initconst = { + .state_table = snr_cstates, + .disable_promotion_to_c1e = true, + .use_acpi = true, +}; + static const struct x86_cpu_id intel_idle_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP, &idle_cpu_nhx), X86_MATCH_INTEL_FAM6_MODEL(NEHALEM, &idle_cpu_nehalem), @@ -1122,7 +1161,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, &idle_cpu_bxt), X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS, &idle_cpu_bxt), X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D, &idle_cpu_dnv), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &idle_cpu_dnv), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &idle_cpu_snr), {} }; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 5f9f9b3a226d..53791138d78b 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -3166,12 +3166,11 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) } if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags)) - cc->crypt_queue = alloc_workqueue("kcryptd-%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, + cc->crypt_queue = alloc_workqueue("kcryptd/%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 1, devname); else - cc->crypt_queue = alloc_workqueue("kcryptd-%s", - WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | - WQ_UNBOUND | WQ_SYSFS, + cc->crypt_queue = alloc_workqueue("kcryptd/%s", + WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus(), devname); if (!cc->crypt_queue) { ti->error = "Couldn't create kcryptd queue"; diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 4268eb359915..8c905aabacc0 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -1092,7 +1092,7 @@ static struct opp_table *_allocate_opp_table(struct device *dev, int index) if (IS_ERR(opp_table->clk)) { ret = PTR_ERR(opp_table->clk); if (ret == -EPROBE_DEFER) - goto err; + goto remove_opp_dev; dev_dbg(dev, "%s: Couldn't find clock: %d\n", __func__, ret); } @@ -1101,7 +1101,7 @@ static struct opp_table *_allocate_opp_table(struct device *dev, int index) ret = dev_pm_opp_of_find_icc_paths(dev, opp_table); if (ret) { if (ret == -EPROBE_DEFER) - goto err; + goto put_clk; dev_warn(dev, "%s: Error finding interconnect paths: %d\n", __func__, ret); @@ -1113,6 +1113,11 @@ static struct opp_table *_allocate_opp_table(struct device *dev, int index) return opp_table; +put_clk: + if (!IS_ERR(opp_table->clk)) + clk_put(opp_table->clk); +remove_opp_dev: + _remove_opp_dev(opp_dev, opp_table); err: kfree(opp_table); return ERR_PTR(ret); diff --git a/drivers/scsi/cxgbi/cxgb4i/Kconfig b/drivers/scsi/cxgbi/cxgb4i/Kconfig index b206e266b4e7..8b0deece9758 100644 --- a/drivers/scsi/cxgbi/cxgb4i/Kconfig +++ b/drivers/scsi/cxgbi/cxgb4i/Kconfig @@ -4,6 +4,7 @@ config SCSI_CXGB4_ISCSI depends on PCI && INET && (IPV6 || IPV6=n) depends on THERMAL || !THERMAL depends on ETHERNET + depends on TLS || TLS=n select NET_VENDOR_CHELSIO select CHELSIO_T4 select CHELSIO_LIB diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 969baf4cd3f5..6e23dc3209fe 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -5034,7 +5034,7 @@ _base_check_for_trigger_pages_support(struct MPT3SAS_ADAPTER *ioc) static void _base_get_diag_triggers(struct MPT3SAS_ADAPTER *ioc) { - u16 trigger_flags; + int trigger_flags; /* * Default setting of master trigger. diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 4848ae3c7b56..b3f14f05340a 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -249,7 +249,8 @@ int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, req = blk_get_request(sdev->request_queue, data_direction == DMA_TO_DEVICE ? - REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, BLK_MQ_REQ_PREEMPT); + REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, + rq_flags & RQF_PM ? BLK_MQ_REQ_PM : 0); if (IS_ERR(req)) return ret; rq = scsi_req(req); @@ -1206,6 +1207,8 @@ static blk_status_t scsi_device_state_check(struct scsi_device *sdev, struct request *req) { switch (sdev->sdev_state) { + case SDEV_CREATED: + return BLK_STS_OK; case SDEV_OFFLINE: case SDEV_TRANSPORT_OFFLINE: /* @@ -1232,18 +1235,18 @@ scsi_device_state_check(struct scsi_device *sdev, struct request *req) return BLK_STS_RESOURCE; case SDEV_QUIESCE: /* - * If the devices is blocked we defer normal commands. + * If the device is blocked we only accept power management + * commands. */ - if (req && !(req->rq_flags & RQF_PREEMPT)) + if (req && WARN_ON_ONCE(!(req->rq_flags & RQF_PM))) return BLK_STS_RESOURCE; return BLK_STS_OK; default: /* * For any other not fully online state we only allow - * special commands. In particular any user initiated - * command is not allowed. + * power management commands. */ - if (req && !(req->rq_flags & RQF_PREEMPT)) + if (req && !(req->rq_flags & RQF_PM)) return BLK_STS_IOERR; return BLK_STS_OK; } @@ -2516,15 +2519,13 @@ void sdev_evt_send_simple(struct scsi_device *sdev, EXPORT_SYMBOL_GPL(sdev_evt_send_simple); /** - * scsi_device_quiesce - Block user issued commands. + * scsi_device_quiesce - Block all commands except power management. * @sdev: scsi device to quiesce. * * This works by trying to transition to the SDEV_QUIESCE state * (which must be a legal transition). When the device is in this - * state, only special requests will be accepted, all others will - * be deferred. Since special requests may also be requeued requests, - * a successful return doesn't guarantee the device will be - * totally quiescent. + * state, only power management requests will be accepted, all others will + * be deferred. * * Must be called with user context, may sleep. * @@ -2586,12 +2587,12 @@ void scsi_device_resume(struct scsi_device *sdev) * device deleted during suspend) */ mutex_lock(&sdev->state_mutex); + if (sdev->sdev_state == SDEV_QUIESCE) + scsi_device_set_state(sdev, SDEV_RUNNING); if (sdev->quiesced_by) { sdev->quiesced_by = NULL; blk_clear_pm_only(sdev->request_queue); } - if (sdev->sdev_state == SDEV_QUIESCE) - scsi_device_set_state(sdev, SDEV_RUNNING); mutex_unlock(&sdev->state_mutex); } EXPORT_SYMBOL(scsi_device_resume); diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c index f3d5b1bbd5aa..c37dd15d16d2 100644 --- a/drivers/scsi/scsi_transport_spi.c +++ b/drivers/scsi/scsi_transport_spi.c @@ -117,12 +117,16 @@ static int spi_execute(struct scsi_device *sdev, const void *cmd, sshdr = &sshdr_tmp; for(i = 0; i < DV_RETRIES; i++) { + /* + * The purpose of the RQF_PM flag below is to bypass the + * SDEV_QUIESCE state. + */ result = scsi_execute(sdev, cmd, dir, buffer, bufflen, sense, sshdr, DV_TIMEOUT, /* retries */ 1, REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER, - 0, NULL); + RQF_PM, NULL); if (driver_byte(result) != DRIVER_SENSE || sshdr->sense_key != UNIT_ATTENTION) break; @@ -1005,23 +1009,26 @@ spi_dv_device(struct scsi_device *sdev) */ lock_system_sleep(); + if (scsi_autopm_get_device(sdev)) + goto unlock_system_sleep; + if (unlikely(spi_dv_in_progress(starget))) - goto unlock; + goto put_autopm; if (unlikely(scsi_device_get(sdev))) - goto unlock; + goto put_autopm; spi_dv_in_progress(starget) = 1; buffer = kzalloc(len, GFP_KERNEL); if (unlikely(!buffer)) - goto out_put; + goto put_sdev; /* We need to verify that the actual device will quiesce; the * later target quiesce is just a nice to have */ if (unlikely(scsi_device_quiesce(sdev))) - goto out_free; + goto free_buffer; scsi_target_quiesce(starget); @@ -1041,12 +1048,16 @@ spi_dv_device(struct scsi_device *sdev) spi_initial_dv(starget) = 1; - out_free: +free_buffer: kfree(buffer); - out_put: + +put_sdev: spi_dv_in_progress(starget) = 0; scsi_device_put(sdev); -unlock: +put_autopm: + scsi_autopm_put_device(sdev); + +unlock_system_sleep: unlock_system_sleep(); } EXPORT_SYMBOL(spi_dv_device); diff --git a/drivers/scsi/ufs/ufs-mediatek-trace.h b/drivers/scsi/ufs/ufs-mediatek-trace.h index fd6f84c1b4e2..895e82ea6ece 100644 --- a/drivers/scsi/ufs/ufs-mediatek-trace.h +++ b/drivers/scsi/ufs/ufs-mediatek-trace.h @@ -31,6 +31,6 @@ TRACE_EVENT(ufs_mtk_event, #undef TRACE_INCLUDE_PATH #undef TRACE_INCLUDE_FILE -#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_PATH ../../drivers/scsi/ufs/ #define TRACE_INCLUDE_FILE ufs-mediatek-trace #include <trace/define_trace.h> diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c index 3522458db3bb..80618af7c872 100644 --- a/drivers/scsi/ufs/ufs-mediatek.c +++ b/drivers/scsi/ufs/ufs-mediatek.c @@ -70,6 +70,13 @@ static bool ufs_mtk_is_va09_supported(struct ufs_hba *hba) return !!(host->caps & UFS_MTK_CAP_VA09_PWR_CTRL); } +static bool ufs_mtk_is_broken_vcc(struct ufs_hba *hba) +{ + struct ufs_mtk_host *host = ufshcd_get_variant(hba); + + return !!(host->caps & UFS_MTK_CAP_BROKEN_VCC); +} + static void ufs_mtk_cfg_unipro_cg(struct ufs_hba *hba, bool enable) { u32 tmp; @@ -514,6 +521,9 @@ static void ufs_mtk_init_host_caps(struct ufs_hba *hba) if (of_property_read_bool(np, "mediatek,ufs-disable-ah8")) host->caps |= UFS_MTK_CAP_DISABLE_AH8; + if (of_property_read_bool(np, "mediatek,ufs-broken-vcc")) + host->caps |= UFS_MTK_CAP_BROKEN_VCC; + dev_info(hba->dev, "caps: 0x%x", host->caps); } @@ -1003,6 +1013,17 @@ static int ufs_mtk_apply_dev_quirks(struct ufs_hba *hba) static void ufs_mtk_fixup_dev_quirks(struct ufs_hba *hba) { ufshcd_fixup_dev_quirks(hba, ufs_mtk_dev_fixups); + + if (ufs_mtk_is_broken_vcc(hba) && hba->vreg_info.vcc && + (hba->dev_quirks & UFS_DEVICE_QUIRK_DELAY_AFTER_LPM)) { + hba->vreg_info.vcc->always_on = true; + /* + * VCC will be kept always-on thus we don't + * need any delay during regulator operations + */ + hba->dev_quirks &= ~(UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM | + UFS_DEVICE_QUIRK_DELAY_AFTER_LPM); + } } static void ufs_mtk_event_notify(struct ufs_hba *hba, diff --git a/drivers/scsi/ufs/ufs-mediatek.h b/drivers/scsi/ufs/ufs-mediatek.h index 93d35097dfb0..3f0d3bb769e8 100644 --- a/drivers/scsi/ufs/ufs-mediatek.h +++ b/drivers/scsi/ufs/ufs-mediatek.h @@ -81,6 +81,7 @@ enum ufs_mtk_host_caps { UFS_MTK_CAP_BOOST_CRYPT_ENGINE = 1 << 0, UFS_MTK_CAP_VA09_PWR_CTRL = 1 << 1, UFS_MTK_CAP_DISABLE_AH8 = 1 << 2, + UFS_MTK_CAP_BROKEN_VCC = 1 << 3, }; struct ufs_mtk_crypt_cfg { diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h index d593edb48767..14dfda735adf 100644 --- a/drivers/scsi/ufs/ufs.h +++ b/drivers/scsi/ufs/ufs.h @@ -330,7 +330,6 @@ enum { UFS_DEV_WRITE_BOOSTER_SUP = BIT(8), }; -#define POWER_DESC_MAX_SIZE 0x62 #define POWER_DESC_MAX_ACTV_ICC_LVLS 16 /* Attribute bActiveICCLevel parameter bit masks definitions */ @@ -513,6 +512,7 @@ struct ufs_query_res { struct ufs_vreg { struct regulator *reg; const char *name; + bool always_on; bool enabled; int min_uV; int max_uV; diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c index df3a564c3e33..fadd566025b8 100644 --- a/drivers/scsi/ufs/ufshcd-pci.c +++ b/drivers/scsi/ufs/ufshcd-pci.c @@ -148,6 +148,8 @@ static int ufs_intel_common_init(struct ufs_hba *hba) { struct intel_host *host; + hba->caps |= UFSHCD_CAP_RPM_AUTOSUSPEND; + host = devm_kzalloc(hba->dev, sizeof(*host), GFP_KERNEL); if (!host) return -ENOMEM; @@ -163,6 +165,41 @@ static void ufs_intel_common_exit(struct ufs_hba *hba) intel_ltr_hide(hba->dev); } +static int ufs_intel_resume(struct ufs_hba *hba, enum ufs_pm_op op) +{ + /* + * To support S4 (suspend-to-disk) with spm_lvl other than 5, the base + * address registers must be restored because the restore kernel can + * have used different addresses. + */ + ufshcd_writel(hba, lower_32_bits(hba->utrdl_dma_addr), + REG_UTP_TRANSFER_REQ_LIST_BASE_L); + ufshcd_writel(hba, upper_32_bits(hba->utrdl_dma_addr), + REG_UTP_TRANSFER_REQ_LIST_BASE_H); + ufshcd_writel(hba, lower_32_bits(hba->utmrdl_dma_addr), + REG_UTP_TASK_REQ_LIST_BASE_L); + ufshcd_writel(hba, upper_32_bits(hba->utmrdl_dma_addr), + REG_UTP_TASK_REQ_LIST_BASE_H); + + if (ufshcd_is_link_hibern8(hba)) { + int ret = ufshcd_uic_hibern8_exit(hba); + + if (!ret) { + ufshcd_set_link_active(hba); + } else { + dev_err(hba->dev, "%s: hibern8 exit failed %d\n", + __func__, ret); + /* + * Force reset and restore. Any other actions can lead + * to an unrecoverable state. + */ + ufshcd_set_link_off(hba); + } + } + + return 0; +} + static int ufs_intel_ehl_init(struct ufs_hba *hba) { hba->quirks |= UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8; @@ -174,6 +211,7 @@ static struct ufs_hba_variant_ops ufs_intel_cnl_hba_vops = { .init = ufs_intel_common_init, .exit = ufs_intel_common_exit, .link_startup_notify = ufs_intel_link_startup_notify, + .resume = ufs_intel_resume, }; static struct ufs_hba_variant_ops ufs_intel_ehl_hba_vops = { @@ -181,6 +219,7 @@ static struct ufs_hba_variant_ops ufs_intel_ehl_hba_vops = { .init = ufs_intel_ehl_init, .exit = ufs_intel_common_exit, .link_startup_notify = ufs_intel_link_startup_notify, + .resume = ufs_intel_resume, }; #ifdef CONFIG_PM_SLEEP @@ -207,6 +246,30 @@ static int ufshcd_pci_resume(struct device *dev) { return ufshcd_system_resume(dev_get_drvdata(dev)); } + +/** + * ufshcd_pci_poweroff - suspend-to-disk poweroff function + * @dev: pointer to PCI device handle + * + * Returns 0 if successful + * Returns non-zero otherwise + */ +static int ufshcd_pci_poweroff(struct device *dev) +{ + struct ufs_hba *hba = dev_get_drvdata(dev); + int spm_lvl = hba->spm_lvl; + int ret; + + /* + * For poweroff we need to set the UFS device to PowerDown mode. + * Force spm_lvl to ensure that. + */ + hba->spm_lvl = 5; + ret = ufshcd_system_suspend(hba); + hba->spm_lvl = spm_lvl; + return ret; +} + #endif /* !CONFIG_PM_SLEEP */ #ifdef CONFIG_PM @@ -302,8 +365,14 @@ ufshcd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) } static const struct dev_pm_ops ufshcd_pci_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(ufshcd_pci_suspend, - ufshcd_pci_resume) +#ifdef CONFIG_PM_SLEEP + .suspend = ufshcd_pci_suspend, + .resume = ufshcd_pci_resume, + .freeze = ufshcd_pci_suspend, + .thaw = ufshcd_pci_resume, + .poweroff = ufshcd_pci_poweroff, + .restore = ufshcd_pci_resume, +#endif SET_RUNTIME_PM_OPS(ufshcd_pci_runtime_suspend, ufshcd_pci_runtime_resume, ufshcd_pci_runtime_idle) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 9902b7e3aa4a..82ad31781bc9 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -225,6 +225,7 @@ static int ufshcd_reset_and_restore(struct ufs_hba *hba); static int ufshcd_eh_host_reset_handler(struct scsi_cmnd *cmd); static int ufshcd_clear_tm_cmd(struct ufs_hba *hba, int tag); static void ufshcd_hba_exit(struct ufs_hba *hba); +static int ufshcd_clear_ua_wluns(struct ufs_hba *hba); static int ufshcd_probe_hba(struct ufs_hba *hba, bool async); static int ufshcd_setup_clocks(struct ufs_hba *hba, bool on); static int ufshcd_uic_hibern8_enter(struct ufs_hba *hba); @@ -580,6 +581,23 @@ static void ufshcd_print_pwr_info(struct ufs_hba *hba) hba->pwr_info.hs_rate); } +static void ufshcd_device_reset(struct ufs_hba *hba) +{ + int err; + + err = ufshcd_vops_device_reset(hba); + + if (!err) { + ufshcd_set_ufs_dev_active(hba); + if (ufshcd_is_wb_allowed(hba)) { + hba->wb_enabled = false; + hba->wb_buf_flush_enabled = false; + } + } + if (err != -EOPNOTSUPP) + ufshcd_update_evt_hist(hba, UFS_EVT_DEV_RESET, err); +} + void ufshcd_delay_us(unsigned long us, unsigned long tolerance) { if (!us) @@ -3665,7 +3683,7 @@ static int ufshcd_dme_enable(struct ufs_hba *hba) ret = ufshcd_send_uic_cmd(hba, &uic_cmd); if (ret) dev_err(hba->dev, - "dme-reset: error code %d\n", ret); + "dme-enable: error code %d\n", ret); return ret; } @@ -3964,7 +3982,7 @@ int ufshcd_link_recovery(struct ufs_hba *hba) spin_unlock_irqrestore(hba->host->host_lock, flags); /* Reset the attached device */ - ufshcd_vops_device_reset(hba); + ufshcd_device_reset(hba); ret = ufshcd_host_reset_and_restore(hba); @@ -6930,7 +6948,8 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba) /* Establish the link again and restore the device */ err = ufshcd_probe_hba(hba, false); - + if (!err) + ufshcd_clear_ua_wluns(hba); out: if (err) dev_err(hba->dev, "%s: Host init failed %d\n", __func__, err); @@ -6968,7 +6987,7 @@ static int ufshcd_reset_and_restore(struct ufs_hba *hba) do { /* Reset the attached device */ - ufshcd_vops_device_reset(hba); + ufshcd_device_reset(hba); err = ufshcd_host_reset_and_restore(hba); } while (err && --retries); @@ -8045,7 +8064,7 @@ static int ufshcd_disable_vreg(struct device *dev, struct ufs_vreg *vreg) { int ret = 0; - if (!vreg || !vreg->enabled) + if (!vreg || !vreg->enabled || vreg->always_on) goto out; ret = regulator_disable(vreg->reg); @@ -8414,13 +8433,7 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba, * handling context. */ hba->host->eh_noresume = 1; - if (hba->wlun_dev_clr_ua) { - ret = ufshcd_send_request_sense(hba, sdp); - if (ret) - goto out; - /* Unit attention condition is cleared now */ - hba->wlun_dev_clr_ua = false; - } + ufshcd_clear_ua_wluns(hba); cmd[4] = pwr_mode << 4; @@ -8441,7 +8454,7 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba, if (!ret) hba->curr_dev_pwr_mode = pwr_mode; -out: + scsi_device_put(sdp); hba->host->eh_noresume = 0; return ret; @@ -8747,7 +8760,7 @@ set_link_active: * further below. */ if (ufshcd_is_ufs_dev_deepsleep(hba)) { - ufshcd_vops_device_reset(hba); + ufshcd_device_reset(hba); WARN_ON(!ufshcd_is_link_off(hba)); } if (ufshcd_is_link_hibern8(hba) && !ufshcd_uic_hibern8_exit(hba)) @@ -8757,7 +8770,7 @@ set_link_active: set_dev_active: /* Can also get here needing to exit DeepSleep */ if (ufshcd_is_ufs_dev_deepsleep(hba)) { - ufshcd_vops_device_reset(hba); + ufshcd_device_reset(hba); ufshcd_host_reset_and_restore(hba); } if (!ufshcd_set_dev_pwr_mode(hba, UFS_ACTIVE_PWR_MODE)) @@ -9353,7 +9366,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) } /* Reset the attached device */ - ufshcd_vops_device_reset(hba); + ufshcd_device_reset(hba); ufshcd_init_crypto(hba); diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index f8c2467dc014..aa9ea3552323 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -1218,16 +1218,12 @@ static inline void ufshcd_vops_dbg_register_dump(struct ufs_hba *hba) hba->vops->dbg_register_dump(hba); } -static inline void ufshcd_vops_device_reset(struct ufs_hba *hba) +static inline int ufshcd_vops_device_reset(struct ufs_hba *hba) { - if (hba->vops && hba->vops->device_reset) { - int err = hba->vops->device_reset(hba); - - if (!err) - ufshcd_set_ufs_dev_active(hba); - if (err != -EOPNOTSUPP) - ufshcd_update_evt_hist(hba, UFS_EVT_DEV_RESET, err); - } + if (hba->vops && hba->vops->device_reset) + return hba->vops->device_reset(hba); + + return -EOPNOTSUPP; } static inline void ufshcd_vops_config_scaling_param(struct ufs_hba *hba, diff --git a/fs/block_dev.c b/fs/block_dev.c index 9293045e128c..3e5b02f6606c 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1055,7 +1055,6 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder) /** * bd_abort_claiming - abort claiming of a block device * @bdev: block device of interest - * @whole: whole block device * @holder: holder that has claimed @bdev * * Abort claiming of a block device when the exclusive open failed. This can be @@ -1828,6 +1827,7 @@ const struct file_operations def_blk_fops = { /** * lookup_bdev - lookup a struct block_device by name * @pathname: special file representing the block device + * @dev: return value of the block device's dev_t * * Get a reference to the blockdevice at @pathname in the current * namespace if possible and return it. Return ERR_PTR(error) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 98c15ff2e599..840587037b59 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2475,6 +2475,22 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry, return r; } +static void encode_timestamp_and_gids(void **p, + const struct ceph_mds_request *req) +{ + struct ceph_timespec ts; + int i; + + ceph_encode_timespec64(&ts, &req->r_stamp); + ceph_encode_copy(p, &ts, sizeof(ts)); + + /* gid_list */ + ceph_encode_32(p, req->r_cred->group_info->ngroups); + for (i = 0; i < req->r_cred->group_info->ngroups; i++) + ceph_encode_64(p, from_kgid(&init_user_ns, + req->r_cred->group_info->gid[i])); +} + /* * called under mdsc->mutex */ @@ -2491,7 +2507,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, u64 ino1 = 0, ino2 = 0; int pathlen1 = 0, pathlen2 = 0; bool freepath1 = false, freepath2 = false; - int len, i; + int len; u16 releases; void *p, *end; int ret; @@ -2517,17 +2533,10 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, goto out_free1; } - if (legacy) { - /* Old style */ - len = sizeof(*head); - } else { - /* New style: add gid_list and any later fields */ - len = sizeof(struct ceph_mds_request_head) + sizeof(u32) + - (sizeof(u64) * req->r_cred->group_info->ngroups); - } - + len = legacy ? sizeof(*head) : sizeof(struct ceph_mds_request_head); len += pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) + sizeof(struct ceph_timespec); + len += sizeof(u32) + (sizeof(u64) * req->r_cred->group_info->ngroups); /* calculate (max) length for cap releases */ len += sizeof(struct ceph_mds_request_release) * @@ -2548,7 +2557,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, msg->hdr.tid = cpu_to_le64(req->r_tid); /* - * The old ceph_mds_request_header didn't contain a version field, and + * The old ceph_mds_request_head didn't contain a version field, and * one was added when we moved the message version from 3->4. */ if (legacy) { @@ -2609,20 +2618,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, head->num_releases = cpu_to_le16(releases); - /* time stamp */ - { - struct ceph_timespec ts; - ceph_encode_timespec64(&ts, &req->r_stamp); - ceph_encode_copy(&p, &ts, sizeof(ts)); - } - - /* gid list */ - if (!legacy) { - ceph_encode_32(&p, req->r_cred->group_info->ngroups); - for (i = 0; i < req->r_cred->group_info->ngroups; i++) - ceph_encode_64(&p, from_kgid(&init_user_ns, - req->r_cred->group_info->gid[i])); - } + encode_timestamp_and_gids(&p, req); if (WARN_ON_ONCE(p > end)) { ceph_msg_put(msg); @@ -2730,13 +2726,8 @@ static int __prepare_send_request(struct ceph_mds_session *session, /* remove cap/dentry releases from message */ rhead->num_releases = 0; - /* time stamp */ p = msg->front.iov_base + req->r_request_release_offset; - { - struct ceph_timespec ts; - ceph_encode_timespec64(&ts, &req->r_stamp); - ceph_encode_copy(&p, &ts, sizeof(ts)); - } + encode_timestamp_and_gids(&p, req); msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); diff --git a/fs/file.c b/fs/file.c index c0b60961c672..dab120b71e44 100644 --- a/fs/file.c +++ b/fs/file.c @@ -21,7 +21,6 @@ #include <linux/rcupdate.h> #include <linux/close_range.h> #include <net/sock.h> -#include <linux/io_uring.h> unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; @@ -428,7 +427,6 @@ void exit_files(struct task_struct *tsk) struct files_struct * files = tsk->files; if (files) { - io_uring_files_cancel(files); task_lock(tsk); tsk->files = NULL; task_unlock(tsk); diff --git a/fs/io_uring.c b/fs/io_uring.c index 7e35283fc0b1..ca46f314640b 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -992,6 +992,10 @@ enum io_mem_account { ACCT_PINNED, }; +static void destroy_fixed_file_ref_node(struct fixed_file_ref_node *ref_node); +static struct fixed_file_ref_node *alloc_fixed_file_ref_node( + struct io_ring_ctx *ctx); + static void __io_complete_rw(struct io_kiocb *req, long res, long res2, struct io_comp_state *cs); static void io_cqring_fill_event(struct io_kiocb *req, long res); @@ -1501,6 +1505,13 @@ static bool io_grab_identity(struct io_kiocb *req) spin_unlock_irq(&ctx->inflight_lock); req->work.flags |= IO_WQ_WORK_FILES; } + if (!(req->work.flags & IO_WQ_WORK_MM) && + (def->work_flags & IO_WQ_WORK_MM)) { + if (id->mm != current->mm) + return false; + mmgrab(id->mm); + req->work.flags |= IO_WQ_WORK_MM; + } return true; } @@ -1525,13 +1536,6 @@ static void io_prep_async_work(struct io_kiocb *req) req->work.flags |= IO_WQ_WORK_UNBOUND; } - /* ->mm can never change on us */ - if (!(req->work.flags & IO_WQ_WORK_MM) && - (def->work_flags & IO_WQ_WORK_MM)) { - mmgrab(id->mm); - req->work.flags |= IO_WQ_WORK_MM; - } - /* if we fail grabbing identity, we must COW, regrab, and retry */ if (io_grab_identity(req)) return; @@ -7231,14 +7235,28 @@ static void io_file_ref_kill(struct percpu_ref *ref) complete(&data->done); } +static void io_sqe_files_set_node(struct fixed_file_data *file_data, + struct fixed_file_ref_node *ref_node) +{ + spin_lock_bh(&file_data->lock); + file_data->node = ref_node; + list_add_tail(&ref_node->node, &file_data->ref_list); + spin_unlock_bh(&file_data->lock); + percpu_ref_get(&file_data->refs); +} + static int io_sqe_files_unregister(struct io_ring_ctx *ctx) { struct fixed_file_data *data = ctx->file_data; - struct fixed_file_ref_node *ref_node = NULL; + struct fixed_file_ref_node *backup_node, *ref_node = NULL; unsigned nr_tables, i; + int ret; if (!data) return -ENXIO; + backup_node = alloc_fixed_file_ref_node(ctx); + if (!backup_node) + return -ENOMEM; spin_lock_bh(&data->lock); ref_node = data->node; @@ -7250,7 +7268,18 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) /* wait for all refs nodes to complete */ flush_delayed_work(&ctx->file_put_work); - wait_for_completion(&data->done); + do { + ret = wait_for_completion_interruptible(&data->done); + if (!ret) + break; + ret = io_run_task_work_sig(); + if (ret < 0) { + percpu_ref_resurrect(&data->refs); + reinit_completion(&data->done); + io_sqe_files_set_node(data, backup_node); + return ret; + } + } while (1); __io_sqe_files_unregister(ctx); nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE); @@ -7261,6 +7290,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) kfree(data); ctx->file_data = NULL; ctx->nr_user_files = 0; + destroy_fixed_file_ref_node(backup_node); return 0; } @@ -7758,11 +7788,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, return PTR_ERR(ref_node); } - file_data->node = ref_node; - spin_lock_bh(&file_data->lock); - list_add_tail(&ref_node->node, &file_data->ref_list); - spin_unlock_bh(&file_data->lock); - percpu_ref_get(&file_data->refs); + io_sqe_files_set_node(file_data, ref_node); return ret; out_fput: for (i = 0; i < ctx->nr_user_files; i++) { @@ -7918,11 +7944,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (needs_switch) { percpu_ref_kill(&data->node->refs); - spin_lock_bh(&data->lock); - list_add_tail(&ref_node->node, &data->ref_list); - data->node = ref_node; - spin_unlock_bh(&data->lock); - percpu_ref_get(&ctx->file_data->refs); + io_sqe_files_set_node(data, ref_node); } else destroy_fixed_file_ref_node(ref_node); diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild index 4365b9aa3e3f..267f6dfb8960 100644 --- a/include/asm-generic/Kbuild +++ b/include/asm-generic/Kbuild @@ -34,6 +34,7 @@ mandatory-y += kmap_size.h mandatory-y += kprobes.h mandatory-y += linkage.h mandatory-y += local.h +mandatory-y += local64.h mandatory-y += mm-arch-hooks.h mandatory-y += mmiowb.h mandatory-y += mmu.h diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 47b021952ac7..d705b174d346 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -447,8 +447,8 @@ enum { BLK_MQ_REQ_NOWAIT = (__force blk_mq_req_flags_t)(1 << 0), /* allocate from reserved pool */ BLK_MQ_REQ_RESERVED = (__force blk_mq_req_flags_t)(1 << 1), - /* set RQF_PREEMPT */ - BLK_MQ_REQ_PREEMPT = (__force blk_mq_req_flags_t)(1 << 3), + /* set RQF_PM */ + BLK_MQ_REQ_PM = (__force blk_mq_req_flags_t)(1 << 2), }; struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 070de09425ad..f94ee3089e01 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -79,9 +79,6 @@ typedef __u32 __bitwise req_flags_t; #define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6)) /* don't call prep for this one */ #define RQF_DONTPREP ((__force req_flags_t)(1 << 7)) -/* set for "ide_preempt" requests and also for requests for which the SCSI - "quiesce" state must be ignored. */ -#define RQF_PREEMPT ((__force req_flags_t)(1 << 8)) /* vaguely specified driver internal error. Ignored by the block layer */ #define RQF_FAILED ((__force req_flags_t)(1 << 10)) /* don't warn about errors */ @@ -430,8 +427,7 @@ struct request_queue { unsigned long queue_flags; /* * Number of contexts that have called blk_set_pm_only(). If this - * counter is above zero then only RQF_PM and RQF_PREEMPT requests are - * processed. + * counter is above zero then only RQF_PM requests are processed. */ atomic_t pm_only; @@ -696,6 +692,18 @@ static inline bool queue_is_mq(struct request_queue *q) return q->mq_ops; } +#ifdef CONFIG_PM +static inline enum rpm_status queue_rpm_status(struct request_queue *q) +{ + return q->rpm_status; +} +#else +static inline enum rpm_status queue_rpm_status(struct request_queue *q) +{ + return RPM_ACTIVE; +} +#endif + static inline enum blk_zoned_model blk_queue_zoned_model(struct request_queue *q) { diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h index 7bb66e15b481..e3a0be2c90ad 100644 --- a/include/linux/build_bug.h +++ b/include/linux/build_bug.h @@ -77,9 +77,4 @@ #define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr) #define __static_assert(expr, msg, ...) _Static_assert(expr, msg) -#ifdef __GENKSYMS__ -/* genksyms gets confused by _Static_assert */ -#define _Static_assert(expr, ...) -#endif - #endif /* _LINUX_BUILD_BUG_H */ diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h index f5e02f6c0655..3989dcb94d3d 100644 --- a/include/linux/ceph/msgr.h +++ b/include/linux/ceph/msgr.h @@ -33,8 +33,8 @@ #define CEPH_MSGR2_INCARNATION_1 (0ull) #define DEFINE_MSGR2_FEATURE(bit, incarnation, name) \ - static const uint64_t CEPH_MSGR2_FEATURE_##name = (1ULL << bit); \ - static const uint64_t CEPH_MSGR2_FEATUREMASK_##name = \ + static const uint64_t __maybe_unused CEPH_MSGR2_FEATURE_##name = (1ULL << bit); \ + static const uint64_t __maybe_unused CEPH_MSGR2_FEATUREMASK_##name = \ (1ULL << bit | CEPH_MSGR2_INCARNATION_##incarnation); #define HAVE_MSGR2_FEATURE(x, name) \ diff --git a/include/linux/kdev_t.h b/include/linux/kdev_t.h index 85b5151911cf..4856706fbfeb 100644 --- a/include/linux/kdev_t.h +++ b/include/linux/kdev_t.h @@ -21,61 +21,61 @@ }) /* acceptable for old filesystems */ -static inline bool old_valid_dev(dev_t dev) +static __always_inline bool old_valid_dev(dev_t dev) { return MAJOR(dev) < 256 && MINOR(dev) < 256; } -static inline u16 old_encode_dev(dev_t dev) +static __always_inline u16 old_encode_dev(dev_t dev) { return (MAJOR(dev) << 8) | MINOR(dev); } -static inline dev_t old_decode_dev(u16 val) +static __always_inline dev_t old_decode_dev(u16 val) { return MKDEV((val >> 8) & 255, val & 255); } -static inline u32 new_encode_dev(dev_t dev) +static __always_inline u32 new_encode_dev(dev_t dev) { unsigned major = MAJOR(dev); unsigned minor = MINOR(dev); return (minor & 0xff) | (major << 8) | ((minor & ~0xff) << 12); } -static inline dev_t new_decode_dev(u32 dev) +static __always_inline dev_t new_decode_dev(u32 dev) { unsigned major = (dev & 0xfff00) >> 8; unsigned minor = (dev & 0xff) | ((dev >> 12) & 0xfff00); return MKDEV(major, minor); } -static inline u64 huge_encode_dev(dev_t dev) +static __always_inline u64 huge_encode_dev(dev_t dev) { return new_encode_dev(dev); } -static inline dev_t huge_decode_dev(u64 dev) +static __always_inline dev_t huge_decode_dev(u64 dev) { return new_decode_dev(dev); } -static inline int sysv_valid_dev(dev_t dev) +static __always_inline int sysv_valid_dev(dev_t dev) { return MAJOR(dev) < (1<<14) && MINOR(dev) < (1<<18); } -static inline u32 sysv_encode_dev(dev_t dev) +static __always_inline u32 sysv_encode_dev(dev_t dev) { return MINOR(dev) | (MAJOR(dev) << 18); } -static inline unsigned sysv_major(u32 dev) +static __always_inline unsigned sysv_major(u32 dev) { return (dev >> 18) & 0x3fff; } -static inline unsigned sysv_minor(u32 dev) +static __always_inline unsigned sysv_minor(u32 dev) { return dev & 0x3ffff; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 5299b90a6c40..ecdf8a8cd6ae 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -216,6 +216,13 @@ int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, loff_t *); +/* + * Any attempt to mark this function as static leads to build failure + * when CONFIG_DEBUG_INFO_BTF is enabled because __add_to_page_cache_locked() + * is referred to by BPF code. This must be visible for error injection. + */ +int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, + pgoff_t index, gfp_t gfp, void **shadowp); #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) @@ -2432,8 +2439,9 @@ extern int __meminit early_pfn_to_nid(unsigned long pfn); #endif extern void set_dma_reserve(unsigned long new_dma_reserve); -extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, - enum meminit_context, struct vmem_altmap *, int migratetype); +extern void memmap_init_zone(unsigned long, int, unsigned long, + unsigned long, unsigned long, enum meminit_context, + struct vmem_altmap *, int migratetype); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); diff --git a/include/linux/sizes.h b/include/linux/sizes.h index 9874f6f67537..1ac79bcee2bb 100644 --- a/include/linux/sizes.h +++ b/include/linux/sizes.h @@ -44,6 +44,9 @@ #define SZ_2G 0x80000000 #define SZ_4G _AC(0x100000000, ULL) +#define SZ_8G _AC(0x200000000, ULL) +#define SZ_16G _AC(0x400000000, ULL) +#define SZ_32G _AC(0x800000000, ULL) #define SZ_64T _AC(0x400000000000, ULL) #endif /* __LINUX_SIZES_H__ */ diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 191c329e482a..32596fdbcd5b 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -908,6 +908,8 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) opt = fs_parse(fc, cgroup1_fs_parameters, param, &result); if (opt == -ENOPARAM) { if (strcmp(param->key, "source") == 0) { + if (fc->source) + return invalf(fc, "Multiple sources not supported"); fc->source = param->string; param->string = NULL; return 0; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index fefa21981027..613845769103 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -244,7 +244,7 @@ bool cgroup_ssid_enabled(int ssid) * * The default hierarchy is the v2 interface of cgroup and this function * can be used to test whether a cgroup is on the default hierarchy for - * cases where a subsystem should behave differnetly depending on the + * cases where a subsystem should behave differently depending on the * interface version. * * List of changed behaviors: @@ -262,7 +262,7 @@ bool cgroup_ssid_enabled(int ssid) * "cgroup.procs" instead. * * - "cgroup.procs" is not sorted. pids will be unique unless they got - * recycled inbetween reads. + * recycled in-between reads. * * - "release_agent" and "notify_on_release" are removed. Replacement * notification mechanism will be implemented. @@ -342,7 +342,7 @@ static bool cgroup_is_mixable(struct cgroup *cgrp) return !cgroup_parent(cgrp); } -/* can @cgrp become a thread root? should always be true for a thread root */ +/* can @cgrp become a thread root? Should always be true for a thread root */ static bool cgroup_can_be_thread_root(struct cgroup *cgrp) { /* mixables don't care */ @@ -527,7 +527,7 @@ static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, * the root css is returned, so this function always returns a valid css. * * The returned css is not guaranteed to be online, and therefore it is the - * callers responsiblity to tryget a reference for it. + * callers responsibility to try get a reference for it. */ struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss) @@ -699,7 +699,7 @@ EXPORT_SYMBOL_GPL(of_css); ; \ else -/* walk live descendants in preorder */ +/* walk live descendants in pre order */ #define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) \ css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL)) \ if (({ lockdep_assert_held(&cgroup_mutex); \ @@ -933,7 +933,7 @@ void put_css_set_locked(struct css_set *cset) WARN_ON_ONCE(!list_empty(&cset->threaded_csets)); - /* This css_set is dead. unlink it and release cgroup and css refs */ + /* This css_set is dead. Unlink it and release cgroup and css refs */ for_each_subsys(ss, ssid) { list_del(&cset->e_cset_node[ssid]); css_put(cset->subsys[ssid]); @@ -1058,7 +1058,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset, /* * Build the set of subsystem state objects that we want to see in the - * new css_set. while subsystems can change globally, the entries here + * new css_set. While subsystems can change globally, the entries here * won't change, so no need for locking. */ for_each_subsys(ss, i) { @@ -1148,7 +1148,7 @@ static void link_css_set(struct list_head *tmp_links, struct css_set *cset, /* * Always add links to the tail of the lists so that the lists are - * in choronological order. + * in chronological order. */ list_move_tail(&link->cset_link, &cgrp->cset_links); list_add_tail(&link->cgrp_link, &cset->cgrp_links); @@ -3654,7 +3654,7 @@ static ssize_t cgroup_freeze_write(struct kernfs_open_file *of, static int cgroup_file_open(struct kernfs_open_file *of) { - struct cftype *cft = of->kn->priv; + struct cftype *cft = of_cft(of); if (cft->open) return cft->open(of); @@ -3663,7 +3663,7 @@ static int cgroup_file_open(struct kernfs_open_file *of) static void cgroup_file_release(struct kernfs_open_file *of) { - struct cftype *cft = of->kn->priv; + struct cftype *cft = of_cft(of); if (cft->release) cft->release(of); @@ -3674,7 +3674,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, { struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; struct cgroup *cgrp = of->kn->parent->priv; - struct cftype *cft = of->kn->priv; + struct cftype *cft = of_cft(of); struct cgroup_subsys_state *css; int ret; @@ -3724,7 +3724,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt) { - struct cftype *cft = of->kn->priv; + struct cftype *cft = of_cft(of); if (cft->poll) return cft->poll(of, pt); @@ -4134,7 +4134,7 @@ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, * implies that if we observe !CSS_RELEASED on @pos in this RCU * critical section, the one pointed to by its next pointer is * guaranteed to not have finished its RCU grace period even if we - * have dropped rcu_read_lock() inbetween iterations. + * have dropped rcu_read_lock() in-between iterations. * * If @pos has CSS_RELEASED set, its next pointer can't be * dereferenced; however, as each css is given a monotonically @@ -4382,7 +4382,7 @@ static struct css_set *css_task_iter_next_css_set(struct css_task_iter *it) } /** - * css_task_iter_advance_css_set - advance a task itererator to the next css_set + * css_task_iter_advance_css_set - advance a task iterator to the next css_set * @it: the iterator to advance * * Advance @it to the next css_set to walk. @@ -6308,7 +6308,7 @@ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss) * * Find the cgroup at @path on the default hierarchy, increment its * reference count and return it. Returns pointer to the found cgroup on - * success, ERR_PTR(-ENOENT) if @path doens't exist and ERR_PTR(-ENOTDIR) + * success, ERR_PTR(-ENOENT) if @path doesn't exist and ERR_PTR(-ENOTDIR) * if @path points to a non-directory. */ struct cgroup *cgroup_get_from_path(const char *path) diff --git a/kernel/exit.c b/kernel/exit.c index 3594291a8542..04029e35e69a 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -63,6 +63,7 @@ #include <linux/random.h> #include <linux/rcuwait.h> #include <linux/compat.h> +#include <linux/io_uring.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -776,6 +777,7 @@ void __noreturn do_exit(long code) schedule(); } + io_uring_files_cancel(tsk->files); exit_signals(tsk); /* sets PF_EXITING */ /* sync mm's RSS info before statistics gathering */ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b5295a0b0536..9880b6c0e272 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3731,17 +3731,24 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq) * is updated and visible. */ if (!freezable || !workqueue_freezing) { + bool kick = false; + pwq->max_active = wq->saved_max_active; while (!list_empty(&pwq->delayed_works) && - pwq->nr_active < pwq->max_active) + pwq->nr_active < pwq->max_active) { pwq_activate_first_delayed(pwq); + kick = true; + } /* * Need to kick a worker after thawed or an unbound wq's - * max_active is bumped. It's a slow path. Do it always. + * max_active is bumped. In realtime scenarios, always kicking a + * worker will cause interference on the isolated cpu cores, so + * let's kick iff work items were activated. */ - wake_up_worker(pwq->pool); + if (kick) + wake_up_worker(pwq->pool); } else { pwq->max_active = 0; } diff --git a/lib/genalloc.c b/lib/genalloc.c index 7f1244b5294a..dab97bb69df6 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -81,14 +81,14 @@ static int clear_bits_ll(unsigned long *addr, unsigned long mask_to_clear) * users set the same bit, one user will return remain bits, otherwise * return 0. */ -static int bitmap_set_ll(unsigned long *map, int start, int nr) +static int bitmap_set_ll(unsigned long *map, unsigned long start, unsigned long nr) { unsigned long *p = map + BIT_WORD(start); - const int size = start + nr; + const unsigned long size = start + nr; int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start); - while (nr - bits_to_set >= 0) { + while (nr >= bits_to_set) { if (set_bits_ll(p, mask_to_set)) return nr; nr -= bits_to_set; @@ -116,14 +116,15 @@ static int bitmap_set_ll(unsigned long *map, int start, int nr) * users clear the same bit, one user will return remain bits, * otherwise return 0. */ -static int bitmap_clear_ll(unsigned long *map, int start, int nr) +static unsigned long +bitmap_clear_ll(unsigned long *map, unsigned long start, unsigned long nr) { unsigned long *p = map + BIT_WORD(start); - const int size = start + nr; + const unsigned long size = start + nr; int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start); - while (nr - bits_to_clear >= 0) { + while (nr >= bits_to_clear) { if (clear_bits_ll(p, mask_to_clear)) return nr; nr -= bits_to_clear; @@ -183,8 +184,8 @@ int gen_pool_add_owner(struct gen_pool *pool, unsigned long virt, phys_addr_t ph size_t size, int nid, void *owner) { struct gen_pool_chunk *chunk; - int nbits = size >> pool->min_alloc_order; - int nbytes = sizeof(struct gen_pool_chunk) + + unsigned long nbits = size >> pool->min_alloc_order; + unsigned long nbytes = sizeof(struct gen_pool_chunk) + BITS_TO_LONGS(nbits) * sizeof(long); chunk = vzalloc_node(nbytes, nid); @@ -242,7 +243,7 @@ void gen_pool_destroy(struct gen_pool *pool) struct list_head *_chunk, *_next_chunk; struct gen_pool_chunk *chunk; int order = pool->min_alloc_order; - int bit, end_bit; + unsigned long bit, end_bit; list_for_each_safe(_chunk, _next_chunk, &pool->chunks) { chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk); @@ -278,7 +279,7 @@ unsigned long gen_pool_alloc_algo_owner(struct gen_pool *pool, size_t size, struct gen_pool_chunk *chunk; unsigned long addr = 0; int order = pool->min_alloc_order; - int nbits, start_bit, end_bit, remain; + unsigned long nbits, start_bit, end_bit, remain; #ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG BUG_ON(in_nmi()); @@ -487,7 +488,7 @@ void gen_pool_free_owner(struct gen_pool *pool, unsigned long addr, size_t size, { struct gen_pool_chunk *chunk; int order = pool->min_alloc_order; - int start_bit, nbits, remain; + unsigned long start_bit, nbits, remain; #ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG BUG_ON(in_nmi()); @@ -755,7 +756,7 @@ unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size, index = bitmap_find_next_zero_area(map, size, start, nr, 0); while (index < size) { - int next_bit = find_next_bit(map, size, index + nr); + unsigned long next_bit = find_next_bit(map, size, index + nr); if ((next_bit - index) < len) { len = next_bit - index; start_bit = index; diff --git a/lib/zlib_dfltcc/Makefile b/lib/zlib_dfltcc/Makefile index 8e4d5afbbb10..66e1c96387c4 100644 --- a/lib/zlib_dfltcc/Makefile +++ b/lib/zlib_dfltcc/Makefile @@ -8,4 +8,4 @@ obj-$(CONFIG_ZLIB_DFLTCC) += zlib_dfltcc.o -zlib_dfltcc-objs := dfltcc.o dfltcc_deflate.o dfltcc_inflate.o dfltcc_syms.o +zlib_dfltcc-objs := dfltcc.o dfltcc_deflate.o dfltcc_inflate.o diff --git a/lib/zlib_dfltcc/dfltcc.c b/lib/zlib_dfltcc/dfltcc.c index c30de430b30c..782f76e9d4da 100644 --- a/lib/zlib_dfltcc/dfltcc.c +++ b/lib/zlib_dfltcc/dfltcc.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: Zlib /* dfltcc.c - SystemZ DEFLATE CONVERSION CALL support. */ -#include <linux/zutil.h> +#include <linux/export.h> +#include <linux/module.h> #include "dfltcc_util.h" #include "dfltcc.h" @@ -53,3 +54,6 @@ void dfltcc_reset( dfltcc_state->dht_threshold = DFLTCC_DHT_MIN_SAMPLE_SIZE; dfltcc_state->param.ribm = DFLTCC_RIBM; } +EXPORT_SYMBOL(dfltcc_reset); + +MODULE_LICENSE("GPL"); diff --git a/lib/zlib_dfltcc/dfltcc_deflate.c b/lib/zlib_dfltcc/dfltcc_deflate.c index 00c185101c6d..6c946e8532ee 100644 --- a/lib/zlib_dfltcc/dfltcc_deflate.c +++ b/lib/zlib_dfltcc/dfltcc_deflate.c @@ -4,6 +4,7 @@ #include "dfltcc_util.h" #include "dfltcc.h" #include <asm/setup.h> +#include <linux/export.h> #include <linux/zutil.h> /* @@ -34,6 +35,7 @@ int dfltcc_can_deflate( return 1; } +EXPORT_SYMBOL(dfltcc_can_deflate); static void dfltcc_gdht( z_streamp strm @@ -277,3 +279,4 @@ again: goto again; /* deflate() must use all input or all output */ return 1; } +EXPORT_SYMBOL(dfltcc_deflate); diff --git a/lib/zlib_dfltcc/dfltcc_inflate.c b/lib/zlib_dfltcc/dfltcc_inflate.c index db107016d29b..fb60b5a6a1cb 100644 --- a/lib/zlib_dfltcc/dfltcc_inflate.c +++ b/lib/zlib_dfltcc/dfltcc_inflate.c @@ -125,7 +125,7 @@ dfltcc_inflate_action dfltcc_inflate( param->ho = (state->write - state->whave) & ((1 << HB_BITS) - 1); if (param->hl) param->nt = 0; /* Honor history for the first block */ - param->cv = state->flags ? REVERSE(state->check) : state->check; + param->cv = state->check; /* Inflate */ do { @@ -138,7 +138,7 @@ dfltcc_inflate_action dfltcc_inflate( state->bits = param->sbb; state->whave = param->hl; state->write = (param->ho + param->hl) & ((1 << HB_BITS) - 1); - state->check = state->flags ? REVERSE(param->cv) : param->cv; + state->check = param->cv; if (cc == DFLTCC_CC_OP2_CORRUPT && param->oesc != 0) { /* Report an error if stream is corrupted */ state->mode = BAD; diff --git a/lib/zlib_dfltcc/dfltcc_syms.c b/lib/zlib_dfltcc/dfltcc_syms.c deleted file mode 100644 index 6f23481804c1..000000000000 --- a/lib/zlib_dfltcc/dfltcc_syms.c +++ /dev/null @@ -1,17 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * linux/lib/zlib_dfltcc/dfltcc_syms.c - * - * Exported symbols for the s390 zlib dfltcc support. - * - */ - -#include <linux/init.h> -#include <linux/module.h> -#include <linux/zlib.h> -#include "dfltcc.h" - -EXPORT_SYMBOL(dfltcc_can_deflate); -EXPORT_SYMBOL(dfltcc_deflate); -EXPORT_SYMBOL(dfltcc_reset); -MODULE_LICENSE("GPL"); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index cbf32d2824fd..a2602969873d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4105,10 +4105,30 @@ retry_avoidcopy: * may get SIGKILLed if it later faults. */ if (outside_reserve) { + struct address_space *mapping = vma->vm_file->f_mapping; + pgoff_t idx; + u32 hash; + put_page(old_page); BUG_ON(huge_pte_none(pte)); + /* + * Drop hugetlb_fault_mutex and i_mmap_rwsem before + * unmapping. unmapping needs to hold i_mmap_rwsem + * in write mode. Dropping i_mmap_rwsem in read mode + * here is OK as COW mappings do not interact with + * PMD sharing. + * + * Reacquire both after unmap operation. + */ + idx = vma_hugecache_offset(h, vma, haddr); + hash = hugetlb_fault_mutex_hash(mapping, idx); + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); + unmap_ref_private(mm, vma, old_page, haddr); - BUG_ON(huge_pte_none(pte)); + + i_mmap_lock_read(mapping); + mutex_lock(&hugetlb_fault_mutex_table[hash]); spin_lock(ptl); ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); if (likely(ptep && diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c index 1dd5a0f99372..5106b84b07d4 100644 --- a/mm/kasan/generic.c +++ b/mm/kasan/generic.c @@ -337,6 +337,8 @@ void kasan_record_aux_stack(void *addr) cache = page->slab_cache; object = nearest_obj(cache, page, addr); alloc_meta = kasan_get_alloc_meta(cache, object); + if (!alloc_meta) + return; alloc_meta->aux_stack[1] = alloc_meta->aux_stack[0]; alloc_meta->aux_stack[0] = kasan_save_stack(GFP_NOWAIT); diff --git a/mm/memory.c b/mm/memory.c index 7d608765932b..feff48e1465a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2892,11 +2892,13 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) entry = mk_pte(new_page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); + /* * Clear the pte entry and flush it first, before updating the - * pte with the new entry. This will avoid a race condition - * seen in the presence of one thread doing SMC and another - * thread doing COW. + * pte with the new entry, to keep TLBs on different CPUs in + * sync. This code used to set the new PTE then flush TLBs, but + * that left a window where the new PTE could be loaded into + * some TLBs while the old PTE remains in others. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); page_add_new_anon_rmap(new_page, vma, vmf->address, false); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index af41fb990820..f9d57b9be8c7 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -713,7 +713,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, * expects the zone spans the pfn range. All the pages in the range * are reserved so nobody should be touching them so we should be safe */ - memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn, + memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn, 0, MEMINIT_HOTPLUG, altmap, migratetype); set_zone_contiguous(zone); diff --git a/mm/mremap.c b/mm/mremap.c index c5590afe7165..f554320281cc 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -358,7 +358,9 @@ static unsigned long get_extent(enum pgt_entry entry, unsigned long old_addr, next = (old_addr + size) & mask; /* even if next overflowed, extent below will be ok */ - extent = (next > old_end) ? old_end - old_addr : next - old_addr; + extent = next - old_addr; + if (extent > old_end - old_addr) + extent = old_end - old_addr; next = (new_addr + size) & mask; if (extent > next - new_addr) extent = next - new_addr; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7a2c89b21115..bdbec4c98173 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -423,6 +423,8 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn) if (end_pfn < pgdat_end_pfn(NODE_DATA(nid))) return false; + if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX) + return true; /* * We start only with one section of pages, more pages are added as * needed until the rest of deferred pages are initialized. @@ -6116,7 +6118,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn) * zone stats (e.g., nr_isolate_pageblock) are touched. */ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, - unsigned long start_pfn, + unsigned long start_pfn, unsigned long zone_end_pfn, enum meminit_context context, struct vmem_altmap *altmap, int migratetype) { @@ -6152,7 +6154,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, if (context == MEMINIT_EARLY) { if (overlap_memmap_init(zone, &pfn)) continue; - if (defer_init(nid, pfn, end_pfn)) + if (defer_init(nid, pfn, zone_end_pfn)) break; } @@ -6266,7 +6268,7 @@ void __meminit __weak memmap_init(unsigned long size, int nid, if (end_pfn > start_pfn) { size = end_pfn - start_pfn; - memmap_init_zone(size, nid, zone, start_pfn, + memmap_init_zone(size, nid, zone, start_pfn, range_end_pfn, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); } } diff --git a/mm/slub.c b/mm/slub.c index 0c8b43a5b3b0..dc5b42e700b8 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1619,9 +1619,6 @@ static inline struct page *alloc_slab_page(struct kmem_cache *s, else page = __alloc_pages_node(node, flags, order); - if (page) - account_slab_page(page, order, s); - return page; } @@ -1774,6 +1771,8 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) page->objects = oo_objects(oo); + account_slab_page(page, oo_order(oo), s); + page->slab_cache = s; __SetPageSlab(page); if (page_is_pfmemalloc(page)) diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index c1ebb2aa08b5..c38d8de93836 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -1333,7 +1333,8 @@ static int prepare_auth_signature(struct ceph_connection *con) void *buf; int ret; - buf = alloc_conn_buf(con, head_onwire_len(SHA256_DIGEST_SIZE, false)); + buf = alloc_conn_buf(con, head_onwire_len(SHA256_DIGEST_SIZE, + con_secure(con))); if (!buf) return -ENOMEM; @@ -2032,10 +2033,18 @@ bad: return -EINVAL; } +/* + * Align session_key and con_secret to avoid GFP_ATOMIC allocation + * inside crypto_shash_setkey() and crypto_aead_setkey() called from + * setup_crypto(). __aligned(16) isn't guaranteed to work for stack + * objects, so do it by hand. + */ static int process_auth_done(struct ceph_connection *con, void *p, void *end) { - u8 session_key[CEPH_KEY_LEN]; - u8 con_secret[CEPH_MAX_CON_SECRET_LEN]; + u8 session_key_buf[CEPH_KEY_LEN + 16]; + u8 con_secret_buf[CEPH_MAX_CON_SECRET_LEN + 16]; + u8 *session_key = PTR_ALIGN(&session_key_buf[0], 16); + u8 *con_secret = PTR_ALIGN(&con_secret_buf[0], 16); int session_key_len, con_secret_len; int payload_len; u64 global_id; diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 00085308ed9d..92e888ed939f 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -6646,6 +6646,12 @@ sub process { # } # } +# strlcpy uses that should likely be strscpy + if ($line =~ /\bstrlcpy\s*\(/) { + WARN("STRLCPY", + "Prefer strscpy over strlcpy - see: https://lore.kernel.org/r/CAHk-=wgfRnXz0W3D37d01q3JFkr_i_uTL=V6A6G1oUZcprmknw\@mail.gmail.com/\n" . $herecurr); + } + # typecasts on min/max could be min_t/max_t if ($perl_version_ok && defined $stat && diff --git a/scripts/depmod.sh b/scripts/depmod.sh index e083bcae343f..3643b4f896ed 100755 --- a/scripts/depmod.sh +++ b/scripts/depmod.sh @@ -15,6 +15,8 @@ if ! test -r System.map ; then exit 0 fi +# legacy behavior: "depmod" in /sbin, no /sbin in PATH +PATH="$PATH:/sbin" if [ -z $(command -v $DEPMOD) ]; then echo "Warning: 'make modules_install' requires $DEPMOD. Please install it." >&2 echo "This is probably in the kmod package." >&2 diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 9a25307f6115..d42115e4284d 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -4,7 +4,7 @@ include local_config.mk uname_M := $(shell uname -m 2>/dev/null || echo not) -MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/') +MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') # Without this, failed build products remain, with up-to-date timestamps, # thus tricking Make (and you!) into believing that All Is Well, in subsequent @@ -43,7 +43,7 @@ TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += userfaultfd -ifeq ($(ARCH),x86_64) +ifeq ($(MACHINE),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32) CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_64bit_program.c) CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_program.c -no-pie) @@ -65,13 +65,13 @@ TEST_GEN_FILES += $(BINARIES_64) endif else -ifneq (,$(findstring $(ARCH),powerpc)) +ifneq (,$(findstring $(MACHINE),ppc64)) TEST_GEN_FILES += protection_keys endif endif -ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64)) +ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64)) TEST_GEN_FILES += va_128TBswitch TEST_GEN_FILES += virtual_address_range TEST_GEN_FILES += write_to_hugetlbfs @@ -84,7 +84,7 @@ TEST_FILES := test_vmalloc.sh KSFT_KHDR_INSTALL := 1 include ../lib.mk -ifeq ($(ARCH),x86_64) +ifeq ($(MACHINE),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) |