From 4314f9f4f85832b5082f4e38b07b63b11baa538c Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 8 Jun 2022 10:55:28 +0100 Subject: firmware: arm_scmi: Avoid using extended string-buffers sizes if not necessary Commit b260fccaebdc2 ("firmware: arm_scmi: Add SCMI v3.1 protocol extended names support") moved all the name string buffers to use the extended buffer size of 64 instead of the required 16 bytes. While that should be fine if the firmware terminates the string before 16 bytes, there is possibility of copying random data if the name is not NULL terminated by the firmware. SCMI base protocol agent_name/vendor_id/sub_vendor_id are defined by the specification as NULL-terminated ASCII strings up to 16-bytes in length. The underlying buffers and message descriptors are currently bigger than needed; resize them to fit only the strictly needed 16 bytes to avoid any possible leaks when reading data from the firmware. Change the size argument of strlcpy to use SCMI_SHORT_NAME_MAX_SIZE always when dealing with short domain names, so as to limit the possibility that an ill-formed non-NULL terminated short reply from the SCMI platform firmware can leak stale content laying in the underlying transport shared memory area. While at that, convert all strings handling routines to use the preferred strscpy. Link: https://lore.kernel.org/r/20220608095530.497879-1-cristian.marussi@arm.com Fixes: b260fccaebdc2 ("firmware: arm_scmi: Add SCMI v3.1 protocol extended names support") Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 1c58646ba381..704111f63993 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -13,8 +13,9 @@ #include #include -#define SCMI_MAX_STR_SIZE 64 -#define SCMI_MAX_NUM_RATES 16 +#define SCMI_MAX_STR_SIZE 64 +#define SCMI_SHORT_NAME_MAX_SIZE 16 +#define SCMI_MAX_NUM_RATES 16 /** * struct scmi_revision_info - version information structure @@ -36,8 +37,8 @@ struct scmi_revision_info { u8 num_protocols; u8 num_agents; u32 impl_ver; - char vendor_id[SCMI_MAX_STR_SIZE]; - char sub_vendor_id[SCMI_MAX_STR_SIZE]; + char vendor_id[SCMI_SHORT_NAME_MAX_SIZE]; + char sub_vendor_id[SCMI_SHORT_NAME_MAX_SIZE]; }; struct scmi_clock_info { -- cgit v1.3-15-g9ac1 From 034e5afad921f1c08c001bf147fb1ba76ae33498 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Fri, 10 Jun 2022 16:35:13 -0600 Subject: mm: re-allow pinning of zero pfns The commit referenced below subtly and inadvertently changed the logic to disallow pinning of zero pfns. This breaks device assignment with vfio and potentially various other users of gup. Exclude the zero page test from the negation. Link: https://lkml.kernel.org/r/165490039431.944052.12458624139225785964.stgit@omen Fixes: 1c563432588d ("mm: fix is_pinnable_page against a cma page") Signed-off-by: Alex Williamson Acked-by: Minchan Kim Acked-by: David Hildenbrand Reported-by: Yishai Hadas Cc: Paul E. McKenney Cc: John Hubbard Cc: John Dias Cc: Jason Gunthorpe Cc: Zhangfei Gao Cc: Matthew Wilcox Cc: Joao Martins Cc: Yi Liu Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index bc8f326be0ce..781fae17177d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1600,7 +1600,7 @@ static inline bool is_pinnable_page(struct page *page) if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE) return false; #endif - return !(is_zone_movable_page(page) || is_zero_pfn(page_to_pfn(page))); + return !is_zone_movable_page(page) || is_zero_pfn(page_to_pfn(page)); } #else static inline bool is_pinnable_page(struct page *page) -- cgit v1.3-15-g9ac1 From 67f22ba7750f940bcd7e1b12720896c505c2d63f Mon Sep 17 00:00:00 2001 From: zhenwei pi Date: Wed, 15 Jun 2022 17:32:09 +0800 Subject: mm/memory-failure: disable unpoison once hw error happens Currently unpoison_memory(unsigned long pfn) is designed for soft poison(hwpoison-inject) only. Since 17fae1294ad9d, the KPTE gets cleared on a x86 platform once hardware memory corrupts. Unpoisoning a hardware corrupted page puts page back buddy only, the kernel has a chance to access the page with *NOT PRESENT* KPTE. This leads BUG during accessing on the corrupted KPTE. Suggested by David&Naoya, disable unpoison mechanism when a real HW error happens to avoid BUG like this: Unpoison: Software-unpoisoned page 0x61234 BUG: unable to handle page fault for address: ffff888061234000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 2c01067 P4D 2c01067 PUD 107267063 PMD 10382b063 PTE 800fffff9edcb062 Oops: 0002 [#1] PREEMPT SMP NOPTI CPU: 4 PID: 26551 Comm: stress Kdump: loaded Tainted: G M OE 5.18.0.bm.1-amd64 #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) ... RIP: 0010:clear_page_erms+0x7/0x10 Code: ... RSP: 0000:ffffc90001107bc8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000901 RCX: 0000000000001000 RDX: ffffea0001848d00 RSI: ffffea0001848d40 RDI: ffff888061234000 RBP: ffffea0001848d00 R08: 0000000000000901 R09: 0000000000001276 R10: 0000000000000003 R11: 0000000000000000 R12: 0000000000000001 R13: 0000000000000000 R14: 0000000000140dca R15: 0000000000000001 FS: 00007fd8b2333740(0000) GS:ffff88813fd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff888061234000 CR3: 00000001023d2005 CR4: 0000000000770ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: prep_new_page+0x151/0x170 get_page_from_freelist+0xca0/0xe20 ? sysvec_apic_timer_interrupt+0xab/0xc0 ? asm_sysvec_apic_timer_interrupt+0x1b/0x20 __alloc_pages+0x17e/0x340 __folio_alloc+0x17/0x40 vma_alloc_folio+0x84/0x280 __handle_mm_fault+0x8d4/0xeb0 handle_mm_fault+0xd5/0x2a0 do_user_addr_fault+0x1d0/0x680 ? kvm_read_and_reset_apf_flags+0x3b/0x50 exc_page_fault+0x78/0x170 asm_exc_page_fault+0x27/0x30 Link: https://lkml.kernel.org/r/20220615093209.259374-2-pizhenwei@bytedance.com Fixes: 847ce401df392 ("HWPOISON: Add unpoisoning support") Fixes: 17fae1294ad9d ("x86/{mce,mm}: Unmap the entire page if the whole page is affected and poisoned") Signed-off-by: zhenwei pi Acked-by: David Hildenbrand Acked-by: Naoya Horiguchi Reviewed-by: Miaohe Lin Reviewed-by: Oscar Salvador Cc: Greg Kroah-Hartman Cc: [5.8+] Signed-off-by: Andrew Morton --- Documentation/vm/hwpoison.rst | 3 ++- drivers/base/memory.c | 2 +- include/linux/mm.h | 1 + mm/hwpoison-inject.c | 2 +- mm/madvise.c | 2 +- mm/memory-failure.c | 12 ++++++++++++ 6 files changed, 18 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/Documentation/vm/hwpoison.rst b/Documentation/vm/hwpoison.rst index c742de1769d1..b9d5253c1305 100644 --- a/Documentation/vm/hwpoison.rst +++ b/Documentation/vm/hwpoison.rst @@ -120,7 +120,8 @@ Testing unpoison-pfn Software-unpoison page at PFN echoed into this file. This way a page can be reused again. This only works for Linux - injected failures, not for real memory failures. + injected failures, not for real memory failures. Once any hardware + memory failure happens, this feature is disabled. Note these injection interfaces are not stable and might change between kernel versions diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 084d67fd55cc..bc60c9cd3230 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -558,7 +558,7 @@ static ssize_t hard_offline_page_store(struct device *dev, if (kstrtoull(buf, 0, &pfn) < 0) return -EINVAL; pfn >>= PAGE_SHIFT; - ret = memory_failure(pfn, 0); + ret = memory_failure(pfn, MF_SW_SIMULATED); if (ret == -EOPNOTSUPP) ret = 0; return ret ? ret : count; diff --git a/include/linux/mm.h b/include/linux/mm.h index 781fae17177d..cf3d0d673f6b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3232,6 +3232,7 @@ enum mf_flags { MF_MUST_KILL = 1 << 2, MF_SOFT_OFFLINE = 1 << 3, MF_UNPOISON = 1 << 4, + MF_SW_SIMULATED = 1 << 5, }; extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue(unsigned long pfn, int flags); diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c index 5c0cddd81505..65e242b5a432 100644 --- a/mm/hwpoison-inject.c +++ b/mm/hwpoison-inject.c @@ -48,7 +48,7 @@ static int hwpoison_inject(void *data, u64 val) inject: pr_info("Injecting memory failure at pfn %#lx\n", pfn); - err = memory_failure(pfn, 0); + err = memory_failure(pfn, MF_SW_SIMULATED); return (err == -EOPNOTSUPP) ? 0 : err; } diff --git a/mm/madvise.c b/mm/madvise.c index d7b4f2602949..0316bbc6441b 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -1112,7 +1112,7 @@ static int madvise_inject_error(int behavior, } else { pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n", pfn, start); - ret = memory_failure(pfn, MF_COUNT_INCREASED); + ret = memory_failure(pfn, MF_COUNT_INCREASED | MF_SW_SIMULATED); if (ret == -EOPNOTSUPP) ret = 0; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index b85661cbdc4a..da39ec8afca8 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -69,6 +69,8 @@ int sysctl_memory_failure_recovery __read_mostly = 1; atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0); +static bool hw_memory_failure __read_mostly = false; + static bool __page_handle_poison(struct page *page) { int ret; @@ -1768,6 +1770,9 @@ int memory_failure(unsigned long pfn, int flags) mutex_lock(&mf_mutex); + if (!(flags & MF_SW_SIMULATED)) + hw_memory_failure = true; + p = pfn_to_online_page(pfn); if (!p) { res = arch_memory_failure(pfn, flags); @@ -2103,6 +2108,13 @@ int unpoison_memory(unsigned long pfn) mutex_lock(&mf_mutex); + if (hw_memory_failure) { + unpoison_pr_info("Unpoison: Disabled after HW memory failure %#lx\n", + pfn, &unpoison_rs); + ret = -EOPNOTSUPP; + goto unlock_mutex; + } + if (!PageHWPoison(p)) { unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n", pfn, &unpoison_rs); -- cgit v1.3-15-g9ac1 From 5cf9c91ba927119fc6606b938b1895bb2459d3bc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Jun 2022 09:48:25 +0200 Subject: block: serialize all debugfs operations using q->debugfs_mutex Various places like I/O schedulers or the QOS infrastructure try to register debugfs files on demans, which can race with creating and removing the main queue debugfs directory. Use the existing debugfs_mutex to serialize all debugfs operations that rely on q->debugfs_dir or the directories hanging off it. To make the teardown code a little simpler declare all debugfs dentry pointers and not just the main one uncoditionally in blkdev.h. Move debugfs_mutex next to the dentries that it protects and document what it is used for. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220614074827.458955-3-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-mq-debugfs.c | 25 ++++++++++++++++++++----- block/blk-mq-debugfs.h | 5 ----- block/blk-mq-sched.c | 11 +++++++++++ block/blk-rq-qos.c | 2 ++ block/blk-rq-qos.h | 7 ++++++- block/blk-sysfs.c | 20 +++++++++----------- include/linux/blkdev.h | 8 ++++---- kernel/trace/blktrace.c | 3 --- 8 files changed, 52 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 7e4136a60e1c..f0fcfe1387cb 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -711,11 +711,6 @@ void blk_mq_debugfs_register(struct request_queue *q) } } -void blk_mq_debugfs_unregister(struct request_queue *q) -{ - q->sched_debugfs_dir = NULL; -} - static void blk_mq_debugfs_register_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { @@ -746,6 +741,8 @@ void blk_mq_debugfs_register_hctx(struct request_queue *q, void blk_mq_debugfs_unregister_hctx(struct blk_mq_hw_ctx *hctx) { + if (!hctx->queue->debugfs_dir) + return; debugfs_remove_recursive(hctx->debugfs_dir); hctx->sched_debugfs_dir = NULL; hctx->debugfs_dir = NULL; @@ -773,6 +770,8 @@ void blk_mq_debugfs_register_sched(struct request_queue *q) { struct elevator_type *e = q->elevator->type; + lockdep_assert_held(&q->debugfs_mutex); + /* * If the parent directory has not been created yet, return, we will be * called again later on and the directory/files will be created then. @@ -790,6 +789,8 @@ void blk_mq_debugfs_register_sched(struct request_queue *q) void blk_mq_debugfs_unregister_sched(struct request_queue *q) { + lockdep_assert_held(&q->debugfs_mutex); + debugfs_remove_recursive(q->sched_debugfs_dir); q->sched_debugfs_dir = NULL; } @@ -811,6 +812,10 @@ static const char *rq_qos_id_to_name(enum rq_qos_id id) void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos) { + lockdep_assert_held(&rqos->q->debugfs_mutex); + + if (!rqos->q->debugfs_dir) + return; debugfs_remove_recursive(rqos->debugfs_dir); rqos->debugfs_dir = NULL; } @@ -820,6 +825,8 @@ void blk_mq_debugfs_register_rqos(struct rq_qos *rqos) struct request_queue *q = rqos->q; const char *dir_name = rq_qos_id_to_name(rqos->id); + lockdep_assert_held(&q->debugfs_mutex); + if (rqos->debugfs_dir || !rqos->ops->debugfs_attrs) return; @@ -835,6 +842,8 @@ void blk_mq_debugfs_register_rqos(struct rq_qos *rqos) void blk_mq_debugfs_unregister_queue_rqos(struct request_queue *q) { + lockdep_assert_held(&q->debugfs_mutex); + debugfs_remove_recursive(q->rqos_debugfs_dir); q->rqos_debugfs_dir = NULL; } @@ -844,6 +853,8 @@ void blk_mq_debugfs_register_sched_hctx(struct request_queue *q, { struct elevator_type *e = q->elevator->type; + lockdep_assert_held(&q->debugfs_mutex); + /* * If the parent debugfs directory has not been created yet, return; * We will be called again later on with appropriate parent debugfs @@ -863,6 +874,10 @@ void blk_mq_debugfs_register_sched_hctx(struct request_queue *q, void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx) { + lockdep_assert_held(&hctx->queue->debugfs_mutex); + + if (!hctx->queue->debugfs_dir) + return; debugfs_remove_recursive(hctx->sched_debugfs_dir); hctx->sched_debugfs_dir = NULL; } diff --git a/block/blk-mq-debugfs.h b/block/blk-mq-debugfs.h index 69918f4170d6..771d45832878 100644 --- a/block/blk-mq-debugfs.h +++ b/block/blk-mq-debugfs.h @@ -21,7 +21,6 @@ int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq); int blk_mq_debugfs_rq_show(struct seq_file *m, void *v); void blk_mq_debugfs_register(struct request_queue *q); -void blk_mq_debugfs_unregister(struct request_queue *q); void blk_mq_debugfs_register_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx); void blk_mq_debugfs_unregister_hctx(struct blk_mq_hw_ctx *hctx); @@ -42,10 +41,6 @@ static inline void blk_mq_debugfs_register(struct request_queue *q) { } -static inline void blk_mq_debugfs_unregister(struct request_queue *q) -{ -} - static inline void blk_mq_debugfs_register_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx) { diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index eb3c65a21362..a4f7c101b53b 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -594,7 +594,9 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) if (ret) goto err_free_map_and_rqs; + mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_register_sched(q); + mutex_unlock(&q->debugfs_mutex); queue_for_each_hw_ctx(q, hctx, i) { if (e->ops.init_hctx) { @@ -607,7 +609,9 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) return ret; } } + mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_register_sched_hctx(q, hctx); + mutex_unlock(&q->debugfs_mutex); } return 0; @@ -648,14 +652,21 @@ void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e) unsigned int flags = 0; queue_for_each_hw_ctx(q, hctx, i) { + mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_unregister_sched_hctx(hctx); + mutex_unlock(&q->debugfs_mutex); + if (e->type->ops.exit_hctx && hctx->sched_data) { e->type->ops.exit_hctx(hctx, i); hctx->sched_data = NULL; } flags = hctx->flags; } + + mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_unregister_sched(q); + mutex_unlock(&q->debugfs_mutex); + if (e->type->ops.exit_sched) e->type->ops.exit_sched(e); blk_mq_sched_tags_teardown(q, flags); diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index e83af7bc7591..249a6f05dd3b 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -294,7 +294,9 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, void rq_qos_exit(struct request_queue *q) { + mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_unregister_queue_rqos(q); + mutex_unlock(&q->debugfs_mutex); while (q->rq_qos) { struct rq_qos *rqos = q->rq_qos; diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index 68267007da1c..0e46052b018a 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -104,8 +104,11 @@ static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos) blk_mq_unfreeze_queue(q); - if (rqos->ops->debugfs_attrs) + if (rqos->ops->debugfs_attrs) { + mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_register_rqos(rqos); + mutex_unlock(&q->debugfs_mutex); + } } static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos) @@ -129,7 +132,9 @@ static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos) blk_mq_unfreeze_queue(q); + mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_unregister_rqos(rqos); + mutex_unlock(&q->debugfs_mutex); } typedef bool (acquire_inflight_cb_t)(struct rq_wait *rqw, void *private_data); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 88bd41d4cb59..6e4801b217a7 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -779,14 +779,13 @@ static void blk_release_queue(struct kobject *kobj) if (queue_is_mq(q)) blk_mq_release(q); - blk_trace_shutdown(q); mutex_lock(&q->debugfs_mutex); + blk_trace_shutdown(q); debugfs_remove_recursive(q->debugfs_dir); + q->debugfs_dir = NULL; + q->sched_debugfs_dir = NULL; mutex_unlock(&q->debugfs_mutex); - if (queue_is_mq(q)) - blk_mq_debugfs_unregister(q); - bioset_exit(&q->bio_split); if (blk_queue_has_srcu(q)) @@ -836,17 +835,16 @@ int blk_register_queue(struct gendisk *disk) goto unlock; } + if (queue_is_mq(q)) + __blk_mq_register_dev(dev, q); + mutex_lock(&q->sysfs_lock); + mutex_lock(&q->debugfs_mutex); q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent), blk_debugfs_root); - mutex_unlock(&q->debugfs_mutex); - - if (queue_is_mq(q)) { - __blk_mq_register_dev(dev, q); + if (queue_is_mq(q)) blk_mq_debugfs_register(q); - } - - mutex_lock(&q->sysfs_lock); + mutex_unlock(&q->debugfs_mutex); ret = disk_register_independent_access_ranges(disk, NULL); if (ret) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bb6e3c31b3b7..73c886eba8e1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -482,7 +482,6 @@ struct request_queue { #endif /* CONFIG_BLK_DEV_ZONED */ int node; - struct mutex debugfs_mutex; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace __rcu *blk_trace; #endif @@ -526,11 +525,12 @@ struct request_queue { struct bio_set bio_split; struct dentry *debugfs_dir; - -#ifdef CONFIG_BLK_DEBUG_FS struct dentry *sched_debugfs_dir; struct dentry *rqos_debugfs_dir; -#endif + /* + * Serializes all debugfs metadata operations using the above dentries. + */ + struct mutex debugfs_mutex; bool mq_sysfs_init_done; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 10a32b0f2deb..fe04c6f96ca5 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -770,14 +770,11 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) **/ void blk_trace_shutdown(struct request_queue *q) { - mutex_lock(&q->debugfs_mutex); if (rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex))) { __blk_trace_startstop(q, 0); __blk_trace_remove(q); } - - mutex_unlock(&q->debugfs_mutex); } #ifdef CONFIG_BLK_CGROUP -- cgit v1.3-15-g9ac1 From c01d4d0a82b71857be7449380338bc53dde2da92 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Thu, 16 Jun 2022 15:00:51 +0200 Subject: random: quiet urandom warning ratelimit suppression message random.c ratelimits how much it warns about uninitialized urandom reads using __ratelimit(). When the RNG is finally initialized, it prints the number of missed messages due to ratelimiting. It has been this way since that functionality was introduced back in 2018. Recently, cc1e127bfa95 ("random: remove ratelimiting for in-kernel unseeded randomness") put a bit more stress on the urandom ratelimiting, which teased out a bug in the implementation. Specifically, when under pressure, __ratelimit() will print its own message and reset the count back to 0, making the final message at the end less useful. Secondly, it does so as a pr_warn(), which apparently is undesirable for people's CI. Fortunately, __ratelimit() has the RATELIMIT_MSG_ON_RELEASE flag exactly for this purpose, so we set the flag. Fixes: 4e00b339e264 ("random: rate limit unseeded randomness warnings") Cc: stable@vger.kernel.org Reported-by: Jon Hunter Reported-by: Ron Economos Tested-by: Ron Economos Signed-off-by: Jason A. Donenfeld --- drivers/char/random.c | 2 +- include/linux/ratelimit_types.h | 12 ++++++++---- 2 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/random.c b/drivers/char/random.c index d0e4c89c4fcb..07a022e24057 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -87,7 +87,7 @@ static struct fasync_struct *fasync; /* Control how we warn userspace. */ static struct ratelimit_state urandom_warning = - RATELIMIT_STATE_INIT("warn_urandom_randomness", HZ, 3); + RATELIMIT_STATE_INIT_FLAGS("urandom_warning", HZ, 3, RATELIMIT_MSG_ON_RELEASE); static int ratelimit_disable __read_mostly = IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM); module_param_named(ratelimit_disable, ratelimit_disable, int, 0644); diff --git a/include/linux/ratelimit_types.h b/include/linux/ratelimit_types.h index c21c7f8103e2..002266693e50 100644 --- a/include/linux/ratelimit_types.h +++ b/include/linux/ratelimit_types.h @@ -23,12 +23,16 @@ struct ratelimit_state { unsigned long flags; }; -#define RATELIMIT_STATE_INIT(name, interval_init, burst_init) { \ - .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ - .interval = interval_init, \ - .burst = burst_init, \ +#define RATELIMIT_STATE_INIT_FLAGS(name, interval_init, burst_init, flags_init) { \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ + .interval = interval_init, \ + .burst = burst_init, \ + .flags = flags_init, \ } +#define RATELIMIT_STATE_INIT(name, interval_init, burst_init) \ + RATELIMIT_STATE_INIT_FLAGS(name, interval_init, burst_init, 0) + #define RATELIMIT_STATE_INIT_DISABLED \ RATELIMIT_STATE_INIT(ratelimit_state, 0, DEFAULT_RATELIMIT_BURST) -- cgit v1.3-15-g9ac1 From 9243fc4cd28c8bdddd7fe0abd5bbec3c4fdf5052 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 3 Jun 2022 14:35:29 +0900 Subject: block: remove queue from struct blk_independent_access_range The request queue pointer in struct blk_independent_access_range is unused. Remove it. Signed-off-by: Damien Le Moal Fixes: 41e46b3c2aa2 ("block: Fix potential deadlock in blk_ia_range_sysfs_show()") Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220603053529.76405-1-damien.lemoal@opensource.wdc.com Signed-off-by: Jens Axboe --- block/blk-ia-ranges.c | 1 - include/linux/blkdev.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include/linux') diff --git a/block/blk-ia-ranges.c b/block/blk-ia-ranges.c index 56ed48d2954e..47c89e65b57f 100644 --- a/block/blk-ia-ranges.c +++ b/block/blk-ia-ranges.c @@ -144,7 +144,6 @@ int disk_register_independent_access_ranges(struct gendisk *disk, } for (i = 0; i < iars->nr_ia_ranges; i++) { - iars->ia_range[i].queue = q; ret = kobject_init_and_add(&iars->ia_range[i].kobj, &blk_ia_range_ktype, &iars->kobj, "%d", i); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 73c886eba8e1..2f7b43444c5f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -342,7 +342,6 @@ static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, */ struct blk_independent_access_range { struct kobject kobj; - struct request_queue *queue; sector_t sector; sector_t nr_sectors; }; -- cgit v1.3-15-g9ac1 From 23c9cd56007e90b2c2317c5eab6ab12921b4314a Mon Sep 17 00:00:00 2001 From: Joel Granados Date: Tue, 21 Jun 2022 09:05:00 +0200 Subject: nvme: fix the CRIMS and CRWMS definitions to match the spec Adjust the values of NVME_CAP_CRMS_CRIMS and NVME_CAP_CRMS_CRWMS masks as they are different from the ones in TP4084 - Time-to-ready. Fixes: 354201c53e61 ("nvme: add support for TP4084 - Time-to-Ready Enhancements"). Signed-off-by: Joel Granados Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 29ec3e3481ff..e3934003f239 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -233,8 +233,8 @@ enum { }; enum { - NVME_CAP_CRMS_CRIMS = 1ULL << 59, - NVME_CAP_CRMS_CRWMS = 1ULL << 60, + NVME_CAP_CRMS_CRWMS = 1ULL << 59, + NVME_CAP_CRMS_CRIMS = 1ULL << 60, }; struct nvme_id_power_state { -- cgit v1.3-15-g9ac1 From 20fb0c8272bbb102d15bdd11aa64f828619dd7cc Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Thu, 23 Jun 2022 16:51:52 +0200 Subject: Revert "printk: Wait for the global console lock when the system is going down" This reverts commit b87f02307d3cfbda768520f0687c51ca77e14fc3. The testing of 5.19 release candidates revealed missing synchronization between early and regular console functionality. It would be possible to start the console kthreads later as a workaround. But it is clear that console lock serialized console drivers between each other. It opens a big area of possible problems that were not considered by people involved in the development and review. printk() is crucial for debugging kernel issues and console output is very important part of it. The number of consoles is huge and a proper review would take some time. As a result it need to be reverted for 5.19. Link: https://lore.kernel.org/r/YrBdjVwBOVgLfHyb@alley Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220623145157.21938-2-pmladek@suse.com --- include/linux/printk.h | 5 ----- kernel/panic.c | 2 -- kernel/printk/internal.h | 2 -- kernel/printk/printk.c | 4 ---- kernel/printk/printk_safe.c | 32 -------------------------------- kernel/reboot.c | 2 -- 6 files changed, 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index c1e07c0652c7..cd26aab0ab2a 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -174,7 +174,6 @@ extern void printk_prefer_direct_enter(void); extern void printk_prefer_direct_exit(void); extern bool pr_flush(int timeout_ms, bool reset_on_progress); -extern void try_block_console_kthreads(int timeout_ms); /* * Please don't use printk_ratelimit(), because it shares ratelimiting state @@ -239,10 +238,6 @@ static inline bool pr_flush(int timeout_ms, bool reset_on_progress) return true; } -static inline void try_block_console_kthreads(int timeout_ms) -{ -} - static inline int printk_ratelimit(void) { return 0; diff --git a/kernel/panic.c b/kernel/panic.c index fe73d18ecdf0..6737b2332275 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -273,7 +273,6 @@ void panic(const char *fmt, ...) * unfortunately means it may not be hardened to work in a * panic situation. */ - try_block_console_kthreads(10000); smp_send_stop(); } else { /* @@ -281,7 +280,6 @@ void panic(const char *fmt, ...) * kmsg_dump, we will need architecture dependent extra * works in addition to stopping other CPUs. */ - try_block_console_kthreads(10000); crash_smp_send_stop(); } diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index e7d8578860ad..d947ca6c84f9 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -20,8 +20,6 @@ enum printk_info_flags { LOG_CONT = 8, /* text is a fragment of a continuation line */ }; -extern bool block_console_kthreads; - __printf(4, 0) int vprintk_store(int facility, int level, const struct dev_printk_info *dev_info, diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index b095fb5f5f61..45c6c2b0b104 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -250,9 +250,6 @@ static atomic_t console_kthreads_active = ATOMIC_INIT(0); #define console_kthread_printing_exit() \ atomic_dec(&console_kthreads_active) -/* Block console kthreads to avoid processing new messages. */ -bool block_console_kthreads; - /* * Helper macros to handle lockdep when locking/unlocking console_sem. We use * macros instead of functions so that _RET_IP_ contains useful information. @@ -3733,7 +3730,6 @@ static bool printer_should_wake(struct console *con, u64 seq) if (con->blocked || console_kthreads_atomically_blocked() || - block_console_kthreads || system_state > SYSTEM_RUNNING || oops_in_progress) { return false; diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index caac4de1ea59..ef0f9a2044da 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -8,9 +8,7 @@ #include #include #include -#include #include -#include #include "internal.h" @@ -52,33 +50,3 @@ asmlinkage int vprintk(const char *fmt, va_list args) return vprintk_default(fmt, args); } EXPORT_SYMBOL(vprintk); - -/** - * try_block_console_kthreads() - Try to block console kthreads and - * make the global console_lock() avaialble - * - * @timeout_ms: The maximum time (in ms) to wait. - * - * Prevent console kthreads from starting processing new messages. Wait - * until the global console_lock() become available. - * - * Context: Can be called in any context. - */ -void try_block_console_kthreads(int timeout_ms) -{ - block_console_kthreads = true; - - /* Do not wait when the console lock could not be safely taken. */ - if (this_cpu_read(printk_context) || in_nmi()) - return; - - while (timeout_ms > 0) { - if (console_trylock()) { - console_unlock(); - return; - } - - udelay(1000); - timeout_ms -= 1; - } -} diff --git a/kernel/reboot.c b/kernel/reboot.c index 310363685502..4177645e74d6 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -74,7 +74,6 @@ void kernel_restart_prepare(char *cmd) { blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd); system_state = SYSTEM_RESTART; - try_block_console_kthreads(10000); usermodehelper_disable(); device_shutdown(); } @@ -263,7 +262,6 @@ static void kernel_shutdown_prepare(enum system_states state) blocking_notifier_call_chain(&reboot_notifier_list, (state == SYSTEM_HALT) ? SYS_HALT : SYS_POWER_OFF, NULL); system_state = state; - try_block_console_kthreads(10000); usermodehelper_disable(); device_shutdown(); } -- cgit v1.3-15-g9ac1 From 2d9ef940f89e0ab4fde7ba6f769d82f2a450c35a Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Thu, 23 Jun 2022 16:51:55 +0200 Subject: Revert "printk: extend console_lock for per-console locking" This reverts commit 8e274732115f63c1d09136284431b3555bd5cc56. The testing of 5.19 release candidates revealed missing synchronization between early and regular console functionality. It would be possible to start the console kthreads later as a workaround. But it is clear that console lock serialized console drivers between each other. It opens a big area of possible problems that were not considered by people involved in the development and review. printk() is crucial for debugging kernel issues and console output is very important part of it. The number of consoles is huge and a proper review would take some time. As a result it need to be reverted for 5.19. Link: https://lore.kernel.org/r/YrBdjVwBOVgLfHyb@alley Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220623145157.21938-5-pmladek@suse.com --- include/linux/console.h | 15 --- kernel/printk/printk.c | 261 +++++++++++------------------------------------- 2 files changed, 56 insertions(+), 220 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 143653090c48..9a251e70c090 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -16,7 +16,6 @@ #include #include -#include struct vc_data; struct console_font_op; @@ -155,20 +154,6 @@ struct console { u64 seq; unsigned long dropped; struct task_struct *thread; - bool blocked; - - /* - * The per-console lock is used by printing kthreads to synchronize - * this console with callers of console_lock(). This is necessary in - * order to allow printing kthreads to run in parallel to each other, - * while each safely accessing the @blocked field and synchronizing - * against direct printing via console_lock/console_unlock. - * - * Note: For synchronizing against direct printing via - * console_trylock/console_unlock, see the static global - * variable @console_kthreads_active. - */ - struct mutex lock; void *data; struct console *next; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index dfd1a19b95d6..ae489dc685a1 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -223,33 +223,6 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, /* Number of registered extended console drivers. */ static int nr_ext_console_drivers; -/* - * Used to synchronize printing kthreads against direct printing via - * console_trylock/console_unlock. - * - * Values: - * -1 = console kthreads atomically blocked (via global trylock) - * 0 = no kthread printing, console not locked (via trylock) - * >0 = kthread(s) actively printing - * - * Note: For synchronizing against direct printing via - * console_lock/console_unlock, see the @lock variable in - * struct console. - */ -static atomic_t console_kthreads_active = ATOMIC_INIT(0); - -#define console_kthreads_atomic_tryblock() \ - (atomic_cmpxchg(&console_kthreads_active, 0, -1) == 0) -#define console_kthreads_atomic_unblock() \ - atomic_cmpxchg(&console_kthreads_active, -1, 0) -#define console_kthreads_atomically_blocked() \ - (atomic_read(&console_kthreads_active) == -1) - -#define console_kthread_printing_tryenter() \ - atomic_inc_unless_negative(&console_kthreads_active) -#define console_kthread_printing_exit() \ - atomic_dec(&console_kthreads_active) - /* * Helper macros to handle lockdep when locking/unlocking console_sem. We use * macros instead of functions so that _RET_IP_ contains useful information. @@ -297,49 +270,6 @@ static bool panic_in_progress(void) return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID); } -/* - * Tracks whether kthread printers are all blocked. A value of true implies - * that the console is locked via console_lock() or the console is suspended. - * Writing to this variable requires holding @console_sem. - */ -static bool console_kthreads_blocked; - -/* - * Block all kthread printers from a schedulable context. - * - * Requires holding @console_sem. - */ -static void console_kthreads_block(void) -{ - struct console *con; - - for_each_console(con) { - mutex_lock(&con->lock); - con->blocked = true; - mutex_unlock(&con->lock); - } - - console_kthreads_blocked = true; -} - -/* - * Unblock all kthread printers from a schedulable context. - * - * Requires holding @console_sem. - */ -static void console_kthreads_unblock(void) -{ - struct console *con; - - for_each_console(con) { - mutex_lock(&con->lock); - con->blocked = false; - mutex_unlock(&con->lock); - } - - console_kthreads_blocked = false; -} - /* * This is used for debugging the mess that is the VT code by * keeping track if we have the console semaphore held. It's @@ -2673,6 +2603,13 @@ void resume_console(void) down_console_sem(); console_suspended = 0; console_unlock(); + + /* + * While suspended, new records may have been added to the + * ringbuffer. Wake up the kthread printers to print them. + */ + wake_up_klogd(); + pr_flush(1000, true); } @@ -2691,14 +2628,9 @@ static int console_cpu_notify(unsigned int cpu) /* If trylock fails, someone else is doing the printing */ if (console_trylock()) console_unlock(); - else { - /* - * If a new CPU comes online, the conditions for - * printer_should_wake() may have changed for some - * kthread printer with !CON_ANYTIME. - */ - wake_up_klogd(); - } + + /* Wake kthread printers. Some may have become usable. */ + wake_up_klogd(); } return 0; } @@ -2718,7 +2650,6 @@ void console_lock(void) down_console_sem(); if (console_suspended) return; - console_kthreads_block(); console_locked = 1; console_may_schedule = 1; } @@ -2740,10 +2671,6 @@ int console_trylock(void) up_console_sem(); return 0; } - if (!console_kthreads_atomic_tryblock()) { - up_console_sem(); - return 0; - } console_locked = 1; console_may_schedule = 0; return 1; @@ -2752,7 +2679,7 @@ EXPORT_SYMBOL(console_trylock); int is_console_locked(void) { - return (console_locked || atomic_read(&console_kthreads_active)); + return console_locked; } EXPORT_SYMBOL(is_console_locked); @@ -2796,7 +2723,7 @@ static inline bool __console_is_usable(short flags) * Check if the given console is currently capable and allowed to print * records. * - * Requires holding the console_lock. + * Requires the console_lock. */ static inline bool console_is_usable(struct console *con) { @@ -2809,22 +2736,6 @@ static inline bool console_is_usable(struct console *con) static void __console_unlock(void) { console_locked = 0; - - /* - * Depending on whether console_lock() or console_trylock() was used, - * appropriately allow the kthread printers to continue. - */ - if (console_kthreads_blocked) - console_kthreads_unblock(); - else - console_kthreads_atomic_unblock(); - - /* - * New records may have arrived while the console was locked. - * Wake the kthread printers to print them. - */ - wake_up_klogd(); - up_console_sem(); } @@ -2842,19 +2753,17 @@ static void __console_unlock(void) * * @handover will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding the - * console_lock. Otherwise it is set to false. A NULL pointer may be provided - * to disable allowing the console_lock to be taken over by a printk waiter. + * console_lock. Otherwise it is set to false. * * Returns false if the given console has no next record to print, otherwise * true. * - * Requires the console_lock if @handover is non-NULL. - * Requires con->lock otherwise. + * Requires the console_lock. */ -static bool __console_emit_next_record(struct console *con, char *text, char *ext_text, - char *dropped_text, bool *handover) +static bool console_emit_next_record(struct console *con, char *text, char *ext_text, + char *dropped_text, bool *handover) { - static atomic_t panic_console_dropped = ATOMIC_INIT(0); + static int panic_console_dropped; struct printk_info info; struct printk_record r; unsigned long flags; @@ -2863,8 +2772,7 @@ static bool __console_emit_next_record(struct console *con, char *text, char *ex prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX); - if (handover) - *handover = false; + *handover = false; if (!prb_read_valid(prb, con->seq, &r)) return false; @@ -2872,8 +2780,7 @@ static bool __console_emit_next_record(struct console *con, char *text, char *ex if (con->seq != r.info->seq) { con->dropped += r.info->seq - con->seq; con->seq = r.info->seq; - if (panic_in_progress() && - atomic_fetch_inc_relaxed(&panic_console_dropped) > 10) { + if (panic_in_progress() && panic_console_dropped++ > 10) { suppress_panic_printk = 1; pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n"); } @@ -2895,61 +2802,31 @@ static bool __console_emit_next_record(struct console *con, char *text, char *ex len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time); } - if (handover) { - /* - * While actively printing out messages, if another printk() - * were to occur on another CPU, it may wait for this one to - * finish. This task can not be preempted if there is a - * waiter waiting to take over. - * - * Interrupts are disabled because the hand over to a waiter - * must not be interrupted until the hand over is completed - * (@console_waiter is cleared). - */ - printk_safe_enter_irqsave(flags); - console_lock_spinning_enable(); - - /* don't trace irqsoff print latency */ - stop_critical_timings(); - } + /* + * While actively printing out messages, if another printk() + * were to occur on another CPU, it may wait for this one to + * finish. This task can not be preempted if there is a + * waiter waiting to take over. + * + * Interrupts are disabled because the hand over to a waiter + * must not be interrupted until the hand over is completed + * (@console_waiter is cleared). + */ + printk_safe_enter_irqsave(flags); + console_lock_spinning_enable(); + stop_critical_timings(); /* don't trace print latency */ call_console_driver(con, write_text, len, dropped_text); + start_critical_timings(); con->seq++; - if (handover) { - start_critical_timings(); - *handover = console_lock_spinning_disable_and_check(); - printk_safe_exit_irqrestore(flags); - } + *handover = console_lock_spinning_disable_and_check(); + printk_safe_exit_irqrestore(flags); skip: return true; } -/* - * Print a record for a given console, but allow another printk() caller to - * take over the console_lock and continue printing. - * - * Requires the console_lock, but depending on @handover after the call, the - * caller may no longer have the console_lock. - * - * See __console_emit_next_record() for argument and return details. - */ -static bool console_emit_next_record_transferable(struct console *con, char *text, char *ext_text, - char *dropped_text, bool *handover) -{ - /* - * Handovers are only supported if threaded printers are atomically - * blocked. The context taking over the console_lock may be atomic. - */ - if (!console_kthreads_atomically_blocked()) { - *handover = false; - handover = NULL; - } - - return __console_emit_next_record(con, text, ext_text, dropped_text, handover); -} - /* * Print out all remaining records to all consoles. * @@ -3001,11 +2878,13 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove if (con->flags & CON_EXTENDED) { /* Extended consoles do not print "dropped messages". */ - progress = console_emit_next_record_transferable(con, &text[0], - &ext_text[0], NULL, handover); + progress = console_emit_next_record(con, &text[0], + &ext_text[0], NULL, + handover); } else { - progress = console_emit_next_record_transferable(con, &text[0], - NULL, &dropped_text[0], handover); + progress = console_emit_next_record(con, &text[0], + NULL, &dropped_text[0], + handover); } if (*handover) return false; @@ -3120,10 +2999,6 @@ void console_unblank(void) if (oops_in_progress) { if (down_trylock_console_sem() != 0) return; - if (!console_kthreads_atomic_tryblock()) { - up_console_sem(); - return; - } } else console_lock(); @@ -3206,6 +3081,10 @@ void console_start(struct console *console) console_lock(); console->flags |= CON_ENABLED; console_unlock(); + + /* Wake the newly enabled kthread printer. */ + wake_up_klogd(); + __pr_flush(console, 1000, true); } EXPORT_SYMBOL(console_start); @@ -3407,8 +3286,6 @@ void register_console(struct console *newcon) newcon->dropped = 0; newcon->thread = NULL; - newcon->blocked = true; - mutex_init(&newcon->lock); if (newcon->flags & CON_PRINTBUFFER) { /* Get a consistent copy of @syslog_seq. */ @@ -3709,19 +3586,6 @@ static void printk_fallback_preferred_direct(void) console_unlock(); } -/* - * Print a record for a given console, not allowing another printk() caller - * to take over. This is appropriate for contexts that do not have the - * console_lock. - * - * See __console_emit_next_record() for argument and return details. - */ -static bool console_emit_next_record(struct console *con, char *text, char *ext_text, - char *dropped_text) -{ - return __console_emit_next_record(con, text, ext_text, dropped_text, NULL); -} - static bool printer_should_wake(struct console *con, u64 seq) { short flags; @@ -3729,10 +3593,8 @@ static bool printer_should_wake(struct console *con, u64 seq) if (kthread_should_stop() || !printk_kthreads_available) return true; - if (con->blocked || - console_kthreads_atomically_blocked()) { + if (console_suspended) return false; - } /* * This is an unsafe read from con->flags, but a false positive is @@ -3753,6 +3615,7 @@ static int printk_kthread_func(void *data) struct console *con = data; char *dropped_text = NULL; char *ext_text = NULL; + bool handover; u64 seq = 0; char *text; int error; @@ -3802,27 +3665,15 @@ static int printk_kthread_func(void *data) if (error) continue; - error = mutex_lock_interruptible(&con->lock); - if (error) - continue; + console_lock(); - if (con->blocked || - !console_kthread_printing_tryenter()) { - /* Another context has locked the console_lock. */ - mutex_unlock(&con->lock); + if (console_suspended) { + up_console_sem(); continue; } - /* - * Although this context has not locked the console_lock, it - * is known that the console_lock is not locked and it is not - * possible for any other context to lock the console_lock. - * Therefore it is safe to read con->flags. - */ - - if (!__console_is_usable(con->flags)) { - console_kthread_printing_exit(); - mutex_unlock(&con->lock); + if (!console_is_usable(con)) { + __console_unlock(); continue; } @@ -3835,13 +3686,13 @@ static int printk_kthread_func(void *data) * which can conditionally invoke cond_resched(). */ console_may_schedule = 0; - console_emit_next_record(con, text, ext_text, dropped_text); + console_emit_next_record(con, text, ext_text, dropped_text, &handover); + if (handover) + continue; seq = con->seq; - console_kthread_printing_exit(); - - mutex_unlock(&con->lock); + __console_unlock(); } con_printk(KERN_INFO, con, "printing thread stopped\n"); -- cgit v1.3-15-g9ac1 From 5831788afb17b89c5b531fb60cbd798613ccbb63 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Thu, 23 Jun 2022 16:51:56 +0200 Subject: Revert "printk: add kthread console printers" This reverts commit 09c5ba0aa2fcfdadb17d045c3ee6f86d69270df7. This reverts commit b87f02307d3cfbda768520f0687c51ca77e14fc3. The testing of 5.19 release candidates revealed missing synchronization between early and regular console functionality. It would be possible to start the console kthreads later as a workaround. But it is clear that console lock serialized console drivers between each other. It opens a big area of possible problems that were not considered by people involved in the development and review. printk() is crucial for debugging kernel issues and console output is very important part of it. The number of consoles is huge and a proper review would take some time. As a result it need to be reverted for 5.19. Link: https://lore.kernel.org/r/YrBdjVwBOVgLfHyb@alley Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220623145157.21938-6-pmladek@suse.com --- include/linux/console.h | 2 - kernel/printk/printk.c | 329 ++++-------------------------------------------- 2 files changed, 22 insertions(+), 309 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 9a251e70c090..8c1686e2c233 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -153,8 +153,6 @@ struct console { uint ospeed; u64 seq; unsigned long dropped; - struct task_struct *thread; - void *data; struct console *next; }; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index ae489dc685a1..5a6273e56b4e 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -361,13 +361,6 @@ static int console_msg_format = MSG_FORMAT_DEFAULT; /* syslog_lock protects syslog_* variables and write access to clear_seq. */ static DEFINE_MUTEX(syslog_lock); -/* - * A flag to signify if printk_activate_kthreads() has already started the - * kthread printers. If true, any later registered consoles must start their - * own kthread directly. The flag is write protected by the console_lock. - */ -static bool printk_kthreads_available; - #ifdef CONFIG_PRINTK static atomic_t printk_prefer_direct = ATOMIC_INIT(0); @@ -397,39 +390,6 @@ void printk_prefer_direct_exit(void) WARN_ON(atomic_dec_if_positive(&printk_prefer_direct) < 0); } -/* - * Calling printk() always wakes kthread printers so that they can - * flush the new message to their respective consoles. Also, if direct - * printing is allowed, printk() tries to flush the messages directly. - * - * Direct printing is allowed in situations when the kthreads - * are not available or the system is in a problematic state. - * - * See the implementation about possible races. - */ -static inline bool allow_direct_printing(void) -{ - /* - * Checking kthread availability is a possible race because the - * kthread printers can become permanently disabled during runtime. - * However, doing that requires holding the console_lock, so any - * pending messages will be direct printed by console_unlock(). - */ - if (!printk_kthreads_available) - return true; - - /* - * Prefer direct printing when the system is in a problematic state. - * The context that sets this state will always see the updated value. - * The other contexts do not care. Anyway, direct printing is just a - * best effort. The direct output is only possible when console_lock - * is not already taken and no kthread printers are actively printing. - */ - return (system_state > SYSTEM_RUNNING || - oops_in_progress || - atomic_read(&printk_prefer_direct)); -} - DECLARE_WAIT_QUEUE_HEAD(log_wait); /* All 3 protected by @syslog_lock. */ /* the next printk record to read by syslog(READ) or /proc/kmsg */ @@ -2320,10 +2280,10 @@ asmlinkage int vprintk_emit(int facility, int level, printed_len = vprintk_store(facility, level, dev_info, fmt, args); /* If called from the scheduler, we can not call up(). */ - if (!in_sched && allow_direct_printing()) { + if (!in_sched) { /* * The caller may be holding system-critical or - * timing-sensitive locks. Disable preemption during direct + * timing-sensitive locks. Disable preemption during * printing of all remaining records to all consoles so that * this context can return as soon as possible. Hopefully * another printk() caller will take over the printing. @@ -2366,8 +2326,6 @@ EXPORT_SYMBOL(_printk); static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress); -static void printk_start_kthread(struct console *con); - #else /* CONFIG_PRINTK */ #define CONSOLE_LOG_MAX 0 @@ -2401,8 +2359,6 @@ static void call_console_driver(struct console *con, const char *text, size_t le } static bool suppress_message_printing(int level) { return false; } static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; } -static void printk_start_kthread(struct console *con) { } -static bool allow_direct_printing(void) { return true; } #endif /* CONFIG_PRINTK */ @@ -2603,13 +2559,6 @@ void resume_console(void) down_console_sem(); console_suspended = 0; console_unlock(); - - /* - * While suspended, new records may have been added to the - * ringbuffer. Wake up the kthread printers to print them. - */ - wake_up_klogd(); - pr_flush(1000, true); } @@ -2628,9 +2577,6 @@ static int console_cpu_notify(unsigned int cpu) /* If trylock fails, someone else is doing the printing */ if (console_trylock()) console_unlock(); - - /* Wake kthread printers. Some may have become usable. */ - wake_up_klogd(); } return 0; } @@ -2702,9 +2648,18 @@ static bool abandon_console_lock_in_panic(void) return atomic_read(&panic_cpu) != raw_smp_processor_id(); } -static inline bool __console_is_usable(short flags) +/* + * Check if the given console is currently capable and allowed to print + * records. + * + * Requires the console_lock. + */ +static inline bool console_is_usable(struct console *con) { - if (!(flags & CON_ENABLED)) + if (!(con->flags & CON_ENABLED)) + return false; + + if (!con->write) return false; /* @@ -2713,26 +2668,12 @@ static inline bool __console_is_usable(short flags) * cope (CON_ANYTIME) don't call them until this CPU is officially up. */ if (!cpu_online(raw_smp_processor_id()) && - !(flags & CON_ANYTIME)) + !(con->flags & CON_ANYTIME)) return false; return true; } -/* - * Check if the given console is currently capable and allowed to print - * records. - * - * Requires the console_lock. - */ -static inline bool console_is_usable(struct console *con) -{ - if (!con->write) - return false; - - return __console_is_usable(con->flags); -} - static void __console_unlock(void) { console_locked = 0; @@ -2845,8 +2786,8 @@ skip: * were flushed to all usable consoles. A returned false informs the caller * that everything was not flushed (either there were no usable consoles or * another context has taken over printing or it is a panic situation and this - * is not the panic CPU or direct printing is not preferred). Regardless the - * reason, the caller should assume it is not useful to immediately try again. + * is not the panic CPU). Regardless the reason, the caller should assume it + * is not useful to immediately try again. * * Requires the console_lock. */ @@ -2863,10 +2804,6 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove *handover = false; do { - /* Let the kthread printers do the work if they can. */ - if (!allow_direct_printing()) - return false; - any_progress = false; for_each_console(con) { @@ -3081,10 +3018,6 @@ void console_start(struct console *console) console_lock(); console->flags |= CON_ENABLED; console_unlock(); - - /* Wake the newly enabled kthread printer. */ - wake_up_klogd(); - __pr_flush(console, 1000, true); } EXPORT_SYMBOL(console_start); @@ -3285,8 +3218,6 @@ void register_console(struct console *newcon) nr_ext_console_drivers++; newcon->dropped = 0; - newcon->thread = NULL; - if (newcon->flags & CON_PRINTBUFFER) { /* Get a consistent copy of @syslog_seq. */ mutex_lock(&syslog_lock); @@ -3296,10 +3227,6 @@ void register_console(struct console *newcon) /* Begin with next message. */ newcon->seq = prb_next_seq(prb); } - - if (printk_kthreads_available) - printk_start_kthread(newcon); - console_unlock(); console_sysfs_notify(); @@ -3326,7 +3253,6 @@ EXPORT_SYMBOL(register_console); int unregister_console(struct console *console) { - struct task_struct *thd; struct console *con; int res; @@ -3367,20 +3293,7 @@ int unregister_console(struct console *console) console_drivers->flags |= CON_CONSDEV; console->flags &= ~CON_ENABLED; - - /* - * console->thread can only be cleared under the console lock. But - * stopping the thread must be done without the console lock. The - * task that clears @thread is the task that stops the kthread. - */ - thd = console->thread; - console->thread = NULL; - console_unlock(); - - if (thd) - kthread_stop(thd); - console_sysfs_notify(); if (console->exit) @@ -3476,20 +3389,6 @@ static int __init printk_late_init(void) } late_initcall(printk_late_init); -static int __init printk_activate_kthreads(void) -{ - struct console *con; - - console_lock(); - printk_kthreads_available = true; - for_each_console(con) - printk_start_kthread(con); - console_unlock(); - - return 0; -} -early_initcall(printk_activate_kthreads); - #if defined CONFIG_PRINTK /* If @con is specified, only wait for that console. Otherwise wait for all. */ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) @@ -3564,180 +3463,11 @@ bool pr_flush(int timeout_ms, bool reset_on_progress) } EXPORT_SYMBOL(pr_flush); -static void __printk_fallback_preferred_direct(void) -{ - printk_prefer_direct_enter(); - pr_err("falling back to preferred direct printing\n"); - printk_kthreads_available = false; -} - -/* - * Enter preferred direct printing, but never exit. Mark console threads as - * unavailable. The system is then forever in preferred direct printing and - * any printing threads will exit. - * - * Must *not* be called under console_lock. Use - * __printk_fallback_preferred_direct() if already holding console_lock. - */ -static void printk_fallback_preferred_direct(void) -{ - console_lock(); - __printk_fallback_preferred_direct(); - console_unlock(); -} - -static bool printer_should_wake(struct console *con, u64 seq) -{ - short flags; - - if (kthread_should_stop() || !printk_kthreads_available) - return true; - - if (console_suspended) - return false; - - /* - * This is an unsafe read from con->flags, but a false positive is - * not a problem. Worst case it would allow the printer to wake up - * although it is disabled. But the printer will notice that when - * attempting to print and instead go back to sleep. - */ - flags = data_race(READ_ONCE(con->flags)); - - if (!__console_is_usable(flags)) - return false; - - return prb_read_valid(prb, seq, NULL); -} - -static int printk_kthread_func(void *data) -{ - struct console *con = data; - char *dropped_text = NULL; - char *ext_text = NULL; - bool handover; - u64 seq = 0; - char *text; - int error; - - text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL); - if (!text) { - con_printk(KERN_ERR, con, "failed to allocate text buffer\n"); - printk_fallback_preferred_direct(); - goto out; - } - - if (con->flags & CON_EXTENDED) { - ext_text = kmalloc(CONSOLE_EXT_LOG_MAX, GFP_KERNEL); - if (!ext_text) { - con_printk(KERN_ERR, con, "failed to allocate ext_text buffer\n"); - printk_fallback_preferred_direct(); - goto out; - } - } else { - dropped_text = kmalloc(DROPPED_TEXT_MAX, GFP_KERNEL); - if (!dropped_text) { - con_printk(KERN_ERR, con, "failed to allocate dropped_text buffer\n"); - printk_fallback_preferred_direct(); - goto out; - } - } - - con_printk(KERN_INFO, con, "printing thread started\n"); - - for (;;) { - /* - * Guarantee this task is visible on the waitqueue before - * checking the wake condition. - * - * The full memory barrier within set_current_state() of - * prepare_to_wait_event() pairs with the full memory barrier - * within wq_has_sleeper(). - * - * This pairs with __wake_up_klogd:A. - */ - error = wait_event_interruptible(log_wait, - printer_should_wake(con, seq)); /* LMM(printk_kthread_func:A) */ - - if (kthread_should_stop() || !printk_kthreads_available) - break; - - if (error) - continue; - - console_lock(); - - if (console_suspended) { - up_console_sem(); - continue; - } - - if (!console_is_usable(con)) { - __console_unlock(); - continue; - } - - /* - * Even though the printk kthread is always preemptible, it is - * still not allowed to call cond_resched() from within - * console drivers. The task may become non-preemptible in the - * console driver call chain. For example, vt_console_print() - * takes a spinlock and then can call into fbcon_redraw(), - * which can conditionally invoke cond_resched(). - */ - console_may_schedule = 0; - console_emit_next_record(con, text, ext_text, dropped_text, &handover); - if (handover) - continue; - - seq = con->seq; - - __console_unlock(); - } - - con_printk(KERN_INFO, con, "printing thread stopped\n"); -out: - kfree(dropped_text); - kfree(ext_text); - kfree(text); - - console_lock(); - /* - * If this kthread is being stopped by another task, con->thread will - * already be NULL. That is fine. The important thing is that it is - * NULL after the kthread exits. - */ - con->thread = NULL; - console_unlock(); - - return 0; -} - -/* Must be called under console_lock. */ -static void printk_start_kthread(struct console *con) -{ - /* - * Do not start a kthread if there is no write() callback. The - * kthreads assume the write() callback exists. - */ - if (!con->write) - return; - - con->thread = kthread_run(printk_kthread_func, con, - "pr/%s%d", con->name, con->index); - if (IS_ERR(con->thread)) { - con->thread = NULL; - con_printk(KERN_ERR, con, "unable to start printing thread\n"); - __printk_fallback_preferred_direct(); - return; - } -} - /* * Delayed printk version, for scheduler-internal messages: */ -#define PRINTK_PENDING_WAKEUP 0x01 -#define PRINTK_PENDING_DIRECT_OUTPUT 0x02 +#define PRINTK_PENDING_WAKEUP 0x01 +#define PRINTK_PENDING_OUTPUT 0x02 static DEFINE_PER_CPU(int, printk_pending); @@ -3745,14 +3475,10 @@ static void wake_up_klogd_work_func(struct irq_work *irq_work) { int pending = this_cpu_xchg(printk_pending, 0); - if (pending & PRINTK_PENDING_DIRECT_OUTPUT) { - printk_prefer_direct_enter(); - + if (pending & PRINTK_PENDING_OUTPUT) { /* If trylock fails, someone else is doing the printing */ if (console_trylock()) console_unlock(); - - printk_prefer_direct_exit(); } if (pending & PRINTK_PENDING_WAKEUP) @@ -3777,11 +3503,10 @@ static void __wake_up_klogd(int val) * prepare_to_wait_event(), which is called after ___wait_event() adds * the waiter but before it has checked the wait condition. * - * This pairs with devkmsg_read:A, syslog_print:A, and - * printk_kthread_func:A. + * This pairs with devkmsg_read:A and syslog_print:A. */ if (wq_has_sleeper(&log_wait) || /* LMM(__wake_up_klogd:A) */ - (val & PRINTK_PENDING_DIRECT_OUTPUT)) { + (val & PRINTK_PENDING_OUTPUT)) { this_cpu_or(printk_pending, val); irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); } @@ -3799,17 +3524,7 @@ void defer_console_output(void) * New messages may have been added directly to the ringbuffer * using vprintk_store(), so wake any waiters as well. */ - int val = PRINTK_PENDING_WAKEUP; - - /* - * Make sure that some context will print the messages when direct - * printing is allowed. This happens in situations when the kthreads - * may not be as reliable or perhaps unusable. - */ - if (allow_direct_printing()) - val |= PRINTK_PENDING_DIRECT_OUTPUT; - - __wake_up_klogd(val); + __wake_up_klogd(PRINTK_PENDING_WAKEUP | PRINTK_PENDING_OUTPUT); } void printk_trigger_flush(void) -- cgit v1.3-15-g9ac1 From 07a22b61946f0b80065b0ddcc703b715f84355f5 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Thu, 23 Jun 2022 16:51:57 +0200 Subject: Revert "printk: add functions to prefer direct printing" This reverts commit 2bb2b7b57f81255c13f4395ea911d6bdc70c9fe2. The testing of 5.19 release candidates revealed missing synchronization between early and regular console functionality. It would be possible to start the console kthreads later as a workaround. But it is clear that console lock serialized console drivers between each other. It opens a big area of possible problems that were not considered by people involved in the development and review. printk() is crucial for debugging kernel issues and console output is very important part of it. The number of consoles is huge and a proper review would take some time. As a result it need to be reverted for 5.19. Link: https://lore.kernel.org/r/YrBdjVwBOVgLfHyb@alley Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220623145157.21938-7-pmladek@suse.com --- drivers/tty/sysrq.c | 2 -- include/linux/printk.h | 11 ----------- kernel/hung_task.c | 11 +---------- kernel/panic.c | 4 ---- kernel/printk/printk.c | 28 ---------------------------- kernel/rcu/tree_stall.h | 2 -- kernel/reboot.c | 14 +------------- kernel/watchdog.c | 4 ---- kernel/watchdog_hld.c | 4 ---- 9 files changed, 2 insertions(+), 78 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index 2884cd638d64..bbfd004449b5 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -578,7 +578,6 @@ void __handle_sysrq(int key, bool check_mask) rcu_sysrq_start(); rcu_read_lock(); - printk_prefer_direct_enter(); /* * Raise the apparent loglevel to maximum so that the sysrq header * is shown to provide the user with positive feedback. We do not @@ -620,7 +619,6 @@ void __handle_sysrq(int key, bool check_mask) pr_cont("\n"); console_loglevel = orig_log_level; } - printk_prefer_direct_exit(); rcu_read_unlock(); rcu_sysrq_end(); diff --git a/include/linux/printk.h b/include/linux/printk.h index cd26aab0ab2a..091fba7283e1 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -170,9 +170,6 @@ extern void __printk_safe_exit(void); #define printk_deferred_enter __printk_safe_enter #define printk_deferred_exit __printk_safe_exit -extern void printk_prefer_direct_enter(void); -extern void printk_prefer_direct_exit(void); - extern bool pr_flush(int timeout_ms, bool reset_on_progress); /* @@ -225,14 +222,6 @@ static inline void printk_deferred_exit(void) { } -static inline void printk_prefer_direct_enter(void) -{ -} - -static inline void printk_prefer_direct_exit(void) -{ -} - static inline bool pr_flush(int timeout_ms, bool reset_on_progress) { return true; diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 02a65d554340..52501e5f7655 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -127,8 +127,6 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) * complain: */ if (sysctl_hung_task_warnings) { - printk_prefer_direct_enter(); - if (sysctl_hung_task_warnings > 0) sysctl_hung_task_warnings--; pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n", @@ -144,8 +142,6 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) if (sysctl_hung_task_all_cpu_backtrace) hung_task_show_all_bt = true; - - printk_prefer_direct_exit(); } touch_nmi_watchdog(); @@ -208,17 +204,12 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) } unlock: rcu_read_unlock(); - if (hung_task_show_lock) { - printk_prefer_direct_enter(); + if (hung_task_show_lock) debug_show_all_locks(); - printk_prefer_direct_exit(); - } if (hung_task_show_all_bt) { hung_task_show_all_bt = false; - printk_prefer_direct_enter(); trigger_all_cpu_backtrace(); - printk_prefer_direct_exit(); } if (hung_task_call_panic) diff --git a/kernel/panic.c b/kernel/panic.c index 6737b2332275..8355b19676f8 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -579,8 +579,6 @@ void __warn(const char *file, int line, void *caller, unsigned taint, { disable_trace_on_warning(); - printk_prefer_direct_enter(); - if (file) pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n", raw_smp_processor_id(), current->pid, file, line, @@ -610,8 +608,6 @@ void __warn(const char *file, int line, void *caller, unsigned taint, /* Just a warning, don't kill lockdep. */ add_taint(taint, LOCKDEP_STILL_OK); - - printk_prefer_direct_exit(); } #ifndef __WARN_FLAGS diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 5a6273e56b4e..b49c6ff6dca0 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -362,34 +362,6 @@ static int console_msg_format = MSG_FORMAT_DEFAULT; static DEFINE_MUTEX(syslog_lock); #ifdef CONFIG_PRINTK -static atomic_t printk_prefer_direct = ATOMIC_INIT(0); - -/** - * printk_prefer_direct_enter - cause printk() calls to attempt direct - * printing to all enabled consoles - * - * Since it is not possible to call into the console printing code from any - * context, there is no guarantee that direct printing will occur. - * - * This globally effects all printk() callers. - * - * Context: Any context. - */ -void printk_prefer_direct_enter(void) -{ - atomic_inc(&printk_prefer_direct); -} - -/** - * printk_prefer_direct_exit - restore printk() behavior - * - * Context: Any context. - */ -void printk_prefer_direct_exit(void) -{ - WARN_ON(atomic_dec_if_positive(&printk_prefer_direct) < 0); -} - DECLARE_WAIT_QUEUE_HEAD(log_wait); /* All 3 protected by @syslog_lock. */ /* the next printk record to read by syslog(READ) or /proc/kmsg */ diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 4995c078cff9..a001e1e7a992 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -647,7 +647,6 @@ static void print_cpu_stall(unsigned long gps) * See Documentation/RCU/stallwarn.rst for info on how to debug * RCU CPU stall warnings. */ - printk_prefer_direct_enter(); trace_rcu_stall_warning(rcu_state.name, TPS("SelfDetected")); pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name); raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags); @@ -685,7 +684,6 @@ static void print_cpu_stall(unsigned long gps) */ set_tsk_need_resched(current); set_preempt_need_resched(); - printk_prefer_direct_exit(); } static void check_cpu_stall(struct rcu_data *rdp) diff --git a/kernel/reboot.c b/kernel/reboot.c index 4177645e74d6..6bcc5d6a6572 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -447,11 +447,9 @@ static int __orderly_reboot(void) ret = run_cmd(reboot_cmd); if (ret) { - printk_prefer_direct_enter(); pr_warn("Failed to start orderly reboot: forcing the issue\n"); emergency_sync(); kernel_restart(NULL); - printk_prefer_direct_exit(); } return ret; @@ -464,7 +462,6 @@ static int __orderly_poweroff(bool force) ret = run_cmd(poweroff_cmd); if (ret && force) { - printk_prefer_direct_enter(); pr_warn("Failed to start orderly shutdown: forcing the issue\n"); /* @@ -474,7 +471,6 @@ static int __orderly_poweroff(bool force) */ emergency_sync(); kernel_power_off(); - printk_prefer_direct_exit(); } return ret; @@ -532,8 +528,6 @@ EXPORT_SYMBOL_GPL(orderly_reboot); */ static void hw_failure_emergency_poweroff_func(struct work_struct *work) { - printk_prefer_direct_enter(); - /* * We have reached here after the emergency shutdown waiting period has * expired. This means orderly_poweroff has not been able to shut off @@ -550,8 +544,6 @@ static void hw_failure_emergency_poweroff_func(struct work_struct *work) */ pr_emerg("Hardware protection shutdown failed. Trying emergency restart\n"); emergency_restart(); - - printk_prefer_direct_exit(); } static DECLARE_DELAYED_WORK(hw_failure_emergency_poweroff_work, @@ -590,13 +582,11 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced) { static atomic_t allow_proceed = ATOMIC_INIT(1); - printk_prefer_direct_enter(); - pr_emerg("HARDWARE PROTECTION shutdown (%s)\n", reason); /* Shutdown should be initiated only once. */ if (!atomic_dec_and_test(&allow_proceed)) - goto out; + return; /* * Queue a backup emergency shutdown in the event of @@ -604,8 +594,6 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced) */ hw_failure_emergency_poweroff(ms_until_forced); orderly_poweroff(true); -out: - printk_prefer_direct_exit(); } EXPORT_SYMBOL_GPL(hw_protection_shutdown); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 40024e03d422..9166220457bc 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -424,8 +424,6 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) /* Start period for the next softlockup warning. */ update_report_ts(); - printk_prefer_direct_enter(); - pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); @@ -444,8 +442,6 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); if (softlockup_panic) panic("softlockup: hung tasks"); - - printk_prefer_direct_exit(); } return HRTIMER_RESTART; diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 701f35f0e2d4..247bf0b1582c 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -135,8 +135,6 @@ static void watchdog_overflow_callback(struct perf_event *event, if (__this_cpu_read(hard_watchdog_warn) == true) return; - printk_prefer_direct_enter(); - pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", this_cpu); print_modules(); @@ -157,8 +155,6 @@ static void watchdog_overflow_callback(struct perf_event *event, if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); - printk_prefer_direct_exit(); - __this_cpu_write(hard_watchdog_warn, true); return; } -- cgit v1.3-15-g9ac1 From c7e1c443584ddd7facffca00e9e23b0d084e5bb3 Mon Sep 17 00:00:00 2001 From: Akira Yokosawa Date: Mon, 6 Jun 2022 13:44:24 +0900 Subject: gpio: Fix kernel-doc comments to nested union Commit 48ec13d36d3f ("gpio: Properly document parent data union") is supposed to have fixed a warning from "make htmldocs" regarding kernel-doc comments to union members. However, the same warning still remains [1]. Fix the issue by following the example found in section "Nested structs/unions" of Documentation/doc-guide/kernel-doc.rst. Signed-off-by: Akira Yokosawa Reported-by: Stephen Rothwell Fixes: 48ec13d36d3f ("gpio: Properly document parent data union") Link: https://lore.kernel.org/r/20220606093302.21febee3@canb.auug.org.au/ [1] Cc: Linus Walleij Cc: Bartosz Golaszewski Cc: Joey Gouly Cc: Marc Zyngier Tested-by: Stephen Rothwell Reviewed-by: Mauro Carvalho Chehab Signed-off-by: Bartosz Golaszewski --- include/linux/gpio/driver.h | 29 ++++++++++++++++------------- 1 file changed, 16 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index b1e0f1f8ee2e..54c3c6506503 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -167,21 +167,24 @@ struct gpio_irq_chip { */ irq_flow_handler_t parent_handler; - /** - * @parent_handler_data: - * - * If @per_parent_data is false, @parent_handler_data is a single - * pointer used as the data associated with every parent interrupt. - * - * @parent_handler_data_array: - * - * If @per_parent_data is true, @parent_handler_data_array is - * an array of @num_parents pointers, and is used to associate - * different data for each parent. This cannot be NULL if - * @per_parent_data is true. - */ union { + /** + * @parent_handler_data: + * + * If @per_parent_data is false, @parent_handler_data is a + * single pointer used as the data associated with every + * parent interrupt. + */ void *parent_handler_data; + + /** + * @parent_handler_data_array: + * + * If @per_parent_data is true, @parent_handler_data_array is + * an array of @num_parents pointers, and is used to associate + * different data for each parent. This cannot be NULL if + * @per_parent_data is true. + */ void **parent_handler_data_array; }; -- cgit v1.3-15-g9ac1