From 043f891b70e6197bc181f3b087c2bd04c60fddd2 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Mon, 25 Jun 2018 13:28:06 +0200 Subject: Revert "lib/test_printf.c: call wait_for_random_bytes() before plain %p tests" This reverts commit ee410f15b1418f2f4428e79980674c979081bcb7. It might prevent the machine from boot. It would wait for enough randomness at the very beginning of kernel_init(). But there is basically nothing running in parallel that would help to produce any randomness. Reported-by: Steven Rostedt (VMware) Signed-off-by: Petr Mladek --- lib/test_printf.c | 7 ------- 1 file changed, 7 deletions(-) (limited to 'lib') diff --git a/lib/test_printf.c b/lib/test_printf.c index b2aa8f514844..cea592f402ed 100644 --- a/lib/test_printf.c +++ b/lib/test_printf.c @@ -260,13 +260,6 @@ plain(void) { int err; - /* - * Make sure crng is ready. Otherwise we get "(ptrval)" instead - * of a hashed address when printing '%p' in plain_hash() and - * plain_format(). - */ - wait_for_random_bytes(); - err = plain_hash(); if (err) { pr_warn("plain 'p' does not appear to be hashed\n"); -- cgit v1.2.3 From 4bb6e96ab808f88d746343637f0cc2243b527da5 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 27 Jun 2018 23:26:01 -0700 Subject: lib/percpu_ida.c: don't do alloc from per-CPU list if there is none In commit 804209d8a009 ("lib/percpu_ida.c: use _irqsave() instead of local_irq_save() + spin_lock") I inlined alloc_local_tag() and mixed up the >= check from percpu_ida_alloc() with the one in alloc_local_tag(). Don't alloc from per-CPU freelist if ->nr_free is zero. Link: http://lkml.kernel.org/r/20180613075830.c3zeva52fuj6fxxv@linutronix.de Fixes: 804209d8a009 ("lib/percpu_ida.c: use _irqsave() instead of local_irq_save() + spin_lock") Signed-off-by: Sebastian Andrzej Siewior Reported-by: David Disseldorp Tested-by: David Disseldorp Cc: Thomas Gleixner Cc: Nicholas Bellinger Cc: Shaohua Li Cc: Kent Overstreet Cc: Matthew Wilcox Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/percpu_ida.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c index 9bbd9c5d375a..beb14839b41a 100644 --- a/lib/percpu_ida.c +++ b/lib/percpu_ida.c @@ -141,7 +141,7 @@ int percpu_ida_alloc(struct percpu_ida *pool, int state) spin_lock_irqsave(&tags->lock, flags); /* Fastpath */ - if (likely(tags->nr_free >= 0)) { + if (likely(tags->nr_free)) { tag = tags->freelist[--tags->nr_free]; spin_unlock_irqrestore(&tags->lock, flags); return tag; -- cgit v1.2.3 From dd275caf4a0d9b219fffe49288b6cc33cd564312 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 27 Jun 2018 23:26:20 -0700 Subject: kasan: depend on CONFIG_SLUB_DEBUG KASAN depends on having access to some of the accounting that SLUB_DEBUG does; without it, there are immediate crashes [1]. So, the natural thing to do is to make KASAN select SLUB_DEBUG. [1] http://lkml.kernel.org/r/CAHmME9rtoPwxUSnktxzKso14iuVCWT7BE_-_8PAC=pGw1iJnQg@mail.gmail.com Link: http://lkml.kernel.org/r/20180622154623.25388-1-Jason@zx2c4.com Fixes: f9e13c0a5a33 ("slab, slub: skip unnecessary kasan_cache_shutdown()") Signed-off-by: Jason A. Donenfeld Acked-by: Michal Hocko Reviewed-by: Shakeel Butt Acked-by: Christoph Lameter Cc: Shakeel Butt Cc: David Rientjes Cc: Pekka Enberg Cc: Joonsoo Kim Cc: Andrey Ryabinin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Kconfig.kasan | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index 3d35d062970d..c253c1b46c6b 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -6,6 +6,7 @@ if HAVE_ARCH_KASAN config KASAN bool "KASan: runtime memory debugger" depends on SLUB || (SLAB && !DEBUG_SLAB) + select SLUB_DEBUG if SLUB select CONSTRUCTORS select STACKDEPOT help -- cgit v1.2.3 From 3203c9010060806ff88c9989aeab4dc8d9a474dc Mon Sep 17 00:00:00 2001 From: Kleber Sacilotto de Souza Date: Wed, 27 Jun 2018 17:19:21 +0200 Subject: test_bpf: flag tests that cannot be jited on s390 Flag with FLAG_EXPECTED_FAIL the BPF_MAXINSNS tests that cannot be jited on s390 because they exceed BPF_SIZE_MAX and fail when CONFIG_BPF_JIT_ALWAYS_ON is set. Also set .expected_errcode to -ENOTSUPP so the tests pass in that case. Signed-off-by: Kleber Sacilotto de Souza Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- lib/test_bpf.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'lib') diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 60aedc879361..08d3d59dca17 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -5282,21 +5282,31 @@ static struct bpf_test tests[] = { { /* Mainly checking JIT here. */ "BPF_MAXINSNS: Ctx heavy transformations", { }, +#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390) + CLASSIC | FLAG_EXPECTED_FAIL, +#else CLASSIC, +#endif { }, { { 1, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) }, { 10, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) } }, .fill_helper = bpf_fill_maxinsns6, + .expected_errcode = -ENOTSUPP, }, { /* Mainly checking JIT here. */ "BPF_MAXINSNS: Call heavy transformations", { }, +#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390) + CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, +#else CLASSIC | FLAG_NO_DATA, +#endif { }, { { 1, 0 }, { 10, 0 } }, .fill_helper = bpf_fill_maxinsns7, + .expected_errcode = -ENOTSUPP, }, { /* Mainly checking JIT here. */ "BPF_MAXINSNS: Jump heavy test", @@ -5347,18 +5357,28 @@ static struct bpf_test tests[] = { { "BPF_MAXINSNS: exec all MSH", { }, +#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390) + CLASSIC | FLAG_EXPECTED_FAIL, +#else CLASSIC, +#endif { 0xfa, 0xfb, 0xfc, 0xfd, }, { { 4, 0xababab83 } }, .fill_helper = bpf_fill_maxinsns13, + .expected_errcode = -ENOTSUPP, }, { "BPF_MAXINSNS: ld_abs+get_processor_id", { }, +#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390) + CLASSIC | FLAG_EXPECTED_FAIL, +#else CLASSIC, +#endif { }, { { 1, 0xbee } }, .fill_helper = bpf_fill_ld_abs_get_processor_id, + .expected_errcode = -ENOTSUPP, }, /* * LD_IND / LD_ABS on fragmented SKBs -- cgit v1.2.3 From 9544bc5347207a68eb308cc8aaaed6c3a687cabd Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 29 Jun 2018 08:48:06 -0600 Subject: sg: remove ->sg_magic member This was introduced more than a decade ago when sg chaining was added, but we never really caught anything with it. The scatterlist entry size can be critical, since drivers allocate it, so remove the magic member. Recently it's been triggering allocation stalls and failures in NVMe. Tested-by: Jordan Glover Acked-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/gpu/drm/i915/i915_drv.h | 3 --- include/linux/scatterlist.h | 18 ------------------ lib/scatterlist.c | 6 ------ tools/virtio/linux/scatterlist.h | 18 ------------------ 4 files changed, 45 deletions(-) (limited to 'lib') diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 34c125e2d90c..9180f67746b4 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2238,9 +2238,6 @@ static inline struct scatterlist *____sg_next(struct scatterlist *sg) **/ static inline struct scatterlist *__sg_next(struct scatterlist *sg) { -#ifdef CONFIG_DEBUG_SG - BUG_ON(sg->sg_magic != SG_MAGIC); -#endif return sg_is_last(sg) ? NULL : ____sg_next(sg); } diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 51f52020ad5f..093aa57120b0 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -9,9 +9,6 @@ #include struct scatterlist { -#ifdef CONFIG_DEBUG_SG - unsigned long sg_magic; -#endif unsigned long page_link; unsigned int offset; unsigned int length; @@ -64,7 +61,6 @@ struct sg_table { * */ -#define SG_MAGIC 0x87654321 #define SG_CHAIN 0x01UL #define SG_END 0x02UL @@ -98,7 +94,6 @@ static inline void sg_assign_page(struct scatterlist *sg, struct page *page) */ BUG_ON((unsigned long) page & (SG_CHAIN | SG_END)); #ifdef CONFIG_DEBUG_SG - BUG_ON(sg->sg_magic != SG_MAGIC); BUG_ON(sg_is_chain(sg)); #endif sg->page_link = page_link | (unsigned long) page; @@ -129,7 +124,6 @@ static inline void sg_set_page(struct scatterlist *sg, struct page *page, static inline struct page *sg_page(struct scatterlist *sg) { #ifdef CONFIG_DEBUG_SG - BUG_ON(sg->sg_magic != SG_MAGIC); BUG_ON(sg_is_chain(sg)); #endif return (struct page *)((sg)->page_link & ~(SG_CHAIN | SG_END)); @@ -195,9 +189,6 @@ static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents, **/ static inline void sg_mark_end(struct scatterlist *sg) { -#ifdef CONFIG_DEBUG_SG - BUG_ON(sg->sg_magic != SG_MAGIC); -#endif /* * Set termination bit, clear potential chain bit */ @@ -215,9 +206,6 @@ static inline void sg_mark_end(struct scatterlist *sg) **/ static inline void sg_unmark_end(struct scatterlist *sg) { -#ifdef CONFIG_DEBUG_SG - BUG_ON(sg->sg_magic != SG_MAGIC); -#endif sg->page_link &= ~SG_END; } @@ -260,12 +248,6 @@ static inline void *sg_virt(struct scatterlist *sg) static inline void sg_init_marker(struct scatterlist *sgl, unsigned int nents) { -#ifdef CONFIG_DEBUG_SG - unsigned int i; - - for (i = 0; i < nents; i++) - sgl[i].sg_magic = SG_MAGIC; -#endif sg_mark_end(&sgl[nents - 1]); } diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 06dad7a072fd..d4ae67d6cd1e 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -24,9 +24,6 @@ **/ struct scatterlist *sg_next(struct scatterlist *sg) { -#ifdef CONFIG_DEBUG_SG - BUG_ON(sg->sg_magic != SG_MAGIC); -#endif if (sg_is_last(sg)) return NULL; @@ -111,10 +108,7 @@ struct scatterlist *sg_last(struct scatterlist *sgl, unsigned int nents) for_each_sg(sgl, sg, nents, i) ret = sg; -#ifdef CONFIG_DEBUG_SG - BUG_ON(sgl[0].sg_magic != SG_MAGIC); BUG_ON(!sg_is_last(ret)); -#endif return ret; } EXPORT_SYMBOL(sg_last); diff --git a/tools/virtio/linux/scatterlist.h b/tools/virtio/linux/scatterlist.h index 9a45f90e2d08..369ee308b668 100644 --- a/tools/virtio/linux/scatterlist.h +++ b/tools/virtio/linux/scatterlist.h @@ -36,7 +36,6 @@ static inline void sg_assign_page(struct scatterlist *sg, struct page *page) */ BUG_ON((unsigned long) page & 0x03); #ifdef CONFIG_DEBUG_SG - BUG_ON(sg->sg_magic != SG_MAGIC); BUG_ON(sg_is_chain(sg)); #endif sg->page_link = page_link | (unsigned long) page; @@ -67,7 +66,6 @@ static inline void sg_set_page(struct scatterlist *sg, struct page *page, static inline struct page *sg_page(struct scatterlist *sg) { #ifdef CONFIG_DEBUG_SG - BUG_ON(sg->sg_magic != SG_MAGIC); BUG_ON(sg_is_chain(sg)); #endif return (struct page *)((sg)->page_link & ~0x3); @@ -116,9 +114,6 @@ static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents, **/ static inline void sg_mark_end(struct scatterlist *sg) { -#ifdef CONFIG_DEBUG_SG - BUG_ON(sg->sg_magic != SG_MAGIC); -#endif /* * Set termination bit, clear potential chain bit */ @@ -136,17 +131,11 @@ static inline void sg_mark_end(struct scatterlist *sg) **/ static inline void sg_unmark_end(struct scatterlist *sg) { -#ifdef CONFIG_DEBUG_SG - BUG_ON(sg->sg_magic != SG_MAGIC); -#endif sg->page_link &= ~0x02; } static inline struct scatterlist *sg_next(struct scatterlist *sg) { -#ifdef CONFIG_DEBUG_SG - BUG_ON(sg->sg_magic != SG_MAGIC); -#endif if (sg_is_last(sg)) return NULL; @@ -160,13 +149,6 @@ static inline struct scatterlist *sg_next(struct scatterlist *sg) static inline void sg_init_table(struct scatterlist *sgl, unsigned int nents) { memset(sgl, 0, sizeof(*sgl) * nents); -#ifdef CONFIG_DEBUG_SG - { - unsigned int i; - for (i = 0; i < nents; i++) - sgl[i].sg_magic = SG_MAGIC; - } -#endif sg_mark_end(&sgl[nents - 1]); } -- cgit v1.2.3 From c643ecf354e25ceeae14add9064d4d6253d75577 Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Mon, 2 Jul 2018 09:35:34 -0700 Subject: lib: rhashtable: Correct self-assignment in rhashtable.c In file lib/rhashtable.c line 777, skip variable is assigned to itself. The following error was observed: lib/rhashtable.c:777:41: warning: explicitly assigning value of variable of type 'int' to itself [-Wself-assign] error, forbidden warning: rhashtable.c:777 This error was found when compiling with Clang 6.0. Change it to iter->skip. Signed-off-by: Rishabh Bhatnagar Acked-by: Herbert Xu Reviewed-by: NeilBrown Signed-off-by: David S. Miller --- lib/rhashtable.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 9427b5766134..3109b2e1d552 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -774,7 +774,7 @@ int rhashtable_walk_start_check(struct rhashtable_iter *iter) skip++; if (list == iter->list) { iter->p = p; - skip = skip; + iter->skip = skip; goto found; } } -- cgit v1.2.3 From 0026129c8629265bfe5079c1e017fa8543796d9f Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Sun, 8 Jul 2018 11:55:51 +0900 Subject: rhashtable: add restart routine in rhashtable_free_and_destroy() rhashtable_free_and_destroy() cancels re-hash deferred work then walks and destroys elements. at this moment, some elements can be still in future_tbl. that elements are not destroyed. test case: nft_rhash_destroy() calls rhashtable_free_and_destroy() to destroy all elements of sets before destroying sets and chains. But rhashtable_free_and_destroy() doesn't destroy elements of future_tbl. so that splat occurred. test script: %cat test.nft table ip aa { map map1 { type ipv4_addr : verdict; elements = { 0 : jump a0, 1 : jump a0, 2 : jump a0, 3 : jump a0, 4 : jump a0, 5 : jump a0, 6 : jump a0, 7 : jump a0, 8 : jump a0, 9 : jump a0, } } chain a0 { } } flush ruleset table ip aa { map map1 { type ipv4_addr : verdict; elements = { 0 : jump a0, 1 : jump a0, 2 : jump a0, 3 : jump a0, 4 : jump a0, 5 : jump a0, 6 : jump a0, 7 : jump a0, 8 : jump a0, 9 : jump a0, } } chain a0 { } } flush ruleset %while :; do nft -f test.nft; done Splat looks like: [ 200.795603] kernel BUG at net/netfilter/nf_tables_api.c:1363! [ 200.806944] invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI [ 200.812253] CPU: 1 PID: 1582 Comm: nft Not tainted 4.17.0+ #24 [ 200.820297] Hardware name: To be filled by O.E.M. To be filled by O.E.M./Aptio CRB, BIOS 5.6.5 07/08/2015 [ 200.830309] RIP: 0010:nf_tables_chain_destroy.isra.34+0x62/0x240 [nf_tables] [ 200.838317] Code: 43 50 85 c0 74 26 48 8b 45 00 48 8b 4d 08 ba 54 05 00 00 48 c7 c6 60 6d 29 c0 48 c7 c7 c0 65 29 c0 4c 8b 40 08 e8 58 e5 fd f8 <0f> 0b 48 89 da 48 b8 00 00 00 00 00 fc ff [ 200.860366] RSP: 0000:ffff880118dbf4d0 EFLAGS: 00010282 [ 200.866354] RAX: 0000000000000061 RBX: ffff88010cdeaf08 RCX: 0000000000000000 [ 200.874355] RDX: 0000000000000061 RSI: 0000000000000008 RDI: ffffed00231b7e90 [ 200.882361] RBP: ffff880118dbf4e8 R08: ffffed002373bcfb R09: ffffed002373bcfa [ 200.890354] R10: 0000000000000000 R11: ffffed002373bcfb R12: dead000000000200 [ 200.898356] R13: dead000000000100 R14: ffffffffbb62af38 R15: dffffc0000000000 [ 200.906354] FS: 00007fefc31fd700(0000) GS:ffff88011b800000(0000) knlGS:0000000000000000 [ 200.915533] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 200.922355] CR2: 0000557f1c8e9128 CR3: 0000000106880000 CR4: 00000000001006e0 [ 200.930353] Call Trace: [ 200.932351] ? nf_tables_commit+0x26f6/0x2c60 [nf_tables] [ 200.939525] ? nf_tables_setelem_notify.constprop.49+0x1a0/0x1a0 [nf_tables] [ 200.947525] ? nf_tables_delchain+0x6e0/0x6e0 [nf_tables] [ 200.952383] ? nft_add_set_elem+0x1700/0x1700 [nf_tables] [ 200.959532] ? nla_parse+0xab/0x230 [ 200.963529] ? nfnetlink_rcv_batch+0xd06/0x10d0 [nfnetlink] [ 200.968384] ? nfnetlink_net_init+0x130/0x130 [nfnetlink] [ 200.975525] ? debug_show_all_locks+0x290/0x290 [ 200.980363] ? debug_show_all_locks+0x290/0x290 [ 200.986356] ? sched_clock_cpu+0x132/0x170 [ 200.990352] ? find_held_lock+0x39/0x1b0 [ 200.994355] ? sched_clock_local+0x10d/0x130 [ 200.999531] ? memset+0x1f/0x40 V2: - free all tables requested by Herbert Xu Signed-off-by: Taehee Yoo Acked-by: Herbert Xu Signed-off-by: David S. Miller --- lib/rhashtable.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 3109b2e1d552..0183d07a9b4d 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -1143,13 +1143,14 @@ void rhashtable_free_and_destroy(struct rhashtable *ht, void (*free_fn)(void *ptr, void *arg), void *arg) { - struct bucket_table *tbl; + struct bucket_table *tbl, *next_tbl; unsigned int i; cancel_work_sync(&ht->run_work); mutex_lock(&ht->mutex); tbl = rht_dereference(ht->tbl, ht); +restart: if (free_fn) { for (i = 0; i < tbl->size; i++) { struct rhash_head *pos, *next; @@ -1166,7 +1167,12 @@ void rhashtable_free_and_destroy(struct rhashtable *ht, } } + next_tbl = rht_dereference(tbl->future_tbl, ht); bucket_table_free(tbl); + if (next_tbl) { + tbl = next_tbl; + goto restart; + } mutex_unlock(&ht->mutex); } EXPORT_SYMBOL_GPL(rhashtable_free_and_destroy); -- cgit v1.2.3 From bf3eeb9b5f2a1a05b3a68c6d82112babd58d6a39 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sun, 8 Jul 2018 13:46:02 -0700 Subject: lib/iov_iter: Document _copy_to_iter_mcsafe() Add some theory of operation documentation to _copy_to_iter_mcsafe(). Reported-by: Al Viro Signed-off-by: Dan Williams Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tony Luck Link: http://lkml.kernel.org/r/153108276256.37979.1689794213845539316.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Ingo Molnar --- lib/iov_iter.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'lib') diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 7e43cd54c84c..94fa361be7bb 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -596,6 +596,32 @@ static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset, return ret; } +/** + * _copy_to_iter_mcsafe - copy to user with source-read error exception handling + * @addr: source kernel address + * @bytes: total transfer length + * @iter: destination iterator + * + * The pmem driver arranges for filesystem-dax to use this facility via + * dax_copy_to_iter() for protecting read/write to persistent memory. + * Unless / until an architecture can guarantee identical performance + * between _copy_to_iter_mcsafe() and _copy_to_iter() it would be a + * performance regression to switch more users to the mcsafe version. + * + * Otherwise, the main differences between this and typical _copy_to_iter(). + * + * * Typical tail/residue handling after a fault retries the copy + * byte-by-byte until the fault happens again. Re-triggering machine + * checks is potentially fatal so the implementation uses source + * alignment and poison alignment assumptions to avoid re-triggering + * hardware exceptions. + * + * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies. + * Compare to copy_to_iter() where only ITER_IOVEC attempts might return + * a short copy. + * + * See MCSAFE_TEST for self-test. + */ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i) { const char *from = addr; -- cgit v1.2.3 From abd08d7d245397bcbded8c6c29ff79a36b3875b0 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sun, 8 Jul 2018 13:46:07 -0700 Subject: lib/iov_iter: Document _copy_to_iter_flushcache() Add some theory of operation documentation to _copy_to_iter_flushcache(). Reported-by: Al Viro Signed-off-by: Dan Williams Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tony Luck Link: http://lkml.kernel.org/r/153108276767.37979.9462477994086841699.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Ingo Molnar --- lib/iov_iter.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'lib') diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 94fa361be7bb..09fb73ad9d54 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -727,6 +727,20 @@ size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) EXPORT_SYMBOL(_copy_from_iter_nocache); #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE +/** + * _copy_from_iter_flushcache - write destination through cpu cache + * @addr: destination kernel address + * @bytes: total transfer length + * @iter: source iterator + * + * The pmem driver arranges for filesystem-dax to use this facility via + * dax_copy_from_iter() for ensuring that writes to persistent memory + * are flushed through the CPU cache. It is differentiated from + * _copy_from_iter_nocache() in that guarantees all data is flushed for + * all iterator types. The _copy_from_iter_nocache() only attempts to + * bypass the cache for the ITER_IOVEC case, and on some archs may use + * instructions that strand dirty-data in the cache. + */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; -- cgit v1.2.3 From ca146f6f091e47b3fd18d6a7e76ec0297d202e0f Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sun, 8 Jul 2018 13:46:12 -0700 Subject: lib/iov_iter: Fix pipe handling in _copy_to_iter_mcsafe() By mistake the ITER_PIPE early-exit / warning from copy_from_iter() was cargo-culted in _copy_to_iter_mcsafe() rather than a machine-check-safe version of copy_to_iter_pipe(). Implement copy_pipe_to_iter_mcsafe() being careful to return the indication of short copies due to a CPU exception. Without this regression-fix all splice reads to dax-mode files fail. Reported-by: Ross Zwisler Tested-by: Ross Zwisler Signed-off-by: Dan Williams Acked-by: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tony Luck Fixes: 8780356ef630 ("x86/asm/memcpy_mcsafe: Define copy_to_iter_mcsafe()") Link: http://lkml.kernel.org/r/153108277278.37979.3327916996902264102.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Ingo Molnar --- lib/iov_iter.c | 37 +++++++++++++++++++++++++++++++++---- 1 file changed, 33 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 09fb73ad9d54..8be175df3075 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -596,6 +596,37 @@ static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset, return ret; } +static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes, + struct iov_iter *i) +{ + struct pipe_inode_info *pipe = i->pipe; + size_t n, off, xfer = 0; + int idx; + + if (!sanity(i)) + return 0; + + bytes = n = push_pipe(i, bytes, &idx, &off); + if (unlikely(!n)) + return 0; + for ( ; n; idx = next_idx(idx, pipe), off = 0) { + size_t chunk = min_t(size_t, n, PAGE_SIZE - off); + unsigned long rem; + + rem = memcpy_mcsafe_to_page(pipe->bufs[idx].page, off, addr, + chunk); + i->idx = idx; + i->iov_offset = off + chunk - rem; + xfer += chunk - rem; + if (rem) + break; + n -= chunk; + addr += chunk; + } + i->count -= xfer; + return xfer; +} + /** * _copy_to_iter_mcsafe - copy to user with source-read error exception handling * @addr: source kernel address @@ -627,10 +658,8 @@ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i) const char *from = addr; unsigned long rem, curr_addr, s_addr = (unsigned long) addr; - if (unlikely(i->type & ITER_PIPE)) { - WARN_ON(1); - return 0; - } + if (unlikely(i->type & ITER_PIPE)) + return copy_pipe_to_iter_mcsafe(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); iterate_and_advance(i, bytes, v, -- cgit v1.2.3 From 107d01f5ba10f4162c38109496607eb197059064 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Mon, 16 Jul 2018 13:26:13 -0700 Subject: lib/rhashtable: consider param->min_size when setting initial table size rhashtable_init() currently does not take into account the user-passed min_size parameter unless param->nelem_hint is set as well. As such, the default size (number of buckets) will always be HASH_DEFAULT_SIZE even if the smallest allowed size is larger than that. Remediate this by unconditionally calling into rounded_hashtable_size() and handling things accordingly. Signed-off-by: Davidlohr Bueso Acked-by: Herbert Xu Signed-off-by: David S. Miller --- lib/rhashtable.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 0183d07a9b4d..e5c8586cf717 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -964,8 +964,16 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_stop); static size_t rounded_hashtable_size(const struct rhashtable_params *params) { - return max(roundup_pow_of_two(params->nelem_hint * 4 / 3), - (unsigned long)params->min_size); + size_t retsize; + + if (params->nelem_hint) + retsize = max(roundup_pow_of_two(params->nelem_hint * 4 / 3), + (unsigned long)params->min_size); + else + retsize = max(HASH_DEFAULT_SIZE, + (unsigned long)params->min_size); + + return retsize; } static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed) @@ -1022,8 +1030,6 @@ int rhashtable_init(struct rhashtable *ht, struct bucket_table *tbl; size_t size; - size = HASH_DEFAULT_SIZE; - if ((!params->key_len && !params->obj_hashfn) || (params->obj_hashfn && !params->obj_cmpfn)) return -EINVAL; @@ -1050,8 +1056,7 @@ int rhashtable_init(struct rhashtable *ht, ht->p.min_size = max_t(u16, ht->p.min_size, HASH_MIN_SIZE); - if (params->nelem_hint) - size = rounded_hashtable_size(&ht->p); + size = rounded_hashtable_size(&ht->p); if (params->locks_mul) ht->p.locks_mul = roundup_pow_of_two(params->locks_mul); -- cgit v1.2.3