From 10825410b956dc1ed8c5fbc8bbedaffdadde7f20 Mon Sep 17 00:00:00 2001 From: Laibin Qiu Date: Thu, 27 Jan 2022 18:00:47 +0800 Subject: blk-mq: Fix wrong wakeup batch configuration which will cause hang Commit 180dccb0dba4f ("blk-mq: fix tag_get wait task can't be awakened") will recalculate wake_batch when incrementing or decrementing active_queues to avoid wake_batch > hctx_max_depth. At the same time, in order to not affect performance as much as possible, the minimum wakeup batch is set to 4. But when the QD is small (such as QD=1), if inc or dec active_queues increases wakeup batch, that can lead to a hang: Fix this problem with the following strategies: QD : >= 32 | < 32 --------------------------------- wakeup batch: 8~4 | 3~1 Fixes: 180dccb0dba4f ("blk-mq: fix tag_get wait task can't be awakened") Link: https://lore.kernel.org/linux-block/78cafe94-a787-e006-8851-69906f0c2128@huawei.com/T/#t Reported-by: Alex Xu (Hello71) Signed-off-by: Laibin Qiu Tested-by: Alex Xu (Hello71) Link: https://lore.kernel.org/r/20220127100047.1763746-1-qiulaibin@huawei.com Signed-off-by: Jens Axboe --- lib/sbitmap.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 6220fa67fb7e..09d293c30fd2 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -488,9 +488,13 @@ void sbitmap_queue_recalculate_wake_batch(struct sbitmap_queue *sbq, unsigned int users) { unsigned int wake_batch; + unsigned int min_batch; + unsigned int depth = (sbq->sb.depth + users - 1) / users; - wake_batch = clamp_val((sbq->sb.depth + users - 1) / - users, 4, SBQ_WAKE_BATCH); + min_batch = sbq->sb.depth >= (4 * SBQ_WAIT_QUEUES) ? 4 : 1; + + wake_batch = clamp_val(depth / SBQ_WAIT_QUEUES, + min_batch, SBQ_WAKE_BATCH); __sbitmap_queue_update_wake_batch(sbq, wake_batch); } EXPORT_SYMBOL_GPL(sbitmap_queue_recalculate_wake_batch); -- cgit v1.2.3 From 09c6304e38e440b93a9ebf3f3cf75cd6cb529f91 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Sat, 29 Jan 2022 13:41:11 -0800 Subject: kasan: test: fix compatibility with FORTIFY_SOURCE With CONFIG_FORTIFY_SOURCE enabled, string functions will also perform dynamic checks using __builtin_object_size(ptr), which when failed will panic the kernel. Because the KASAN test deliberately performs out-of-bounds operations, the kernel panics with FORTIFY_SOURCE, for example: | kernel BUG at lib/string_helpers.c:910! | invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI | CPU: 1 PID: 137 Comm: kunit_try_catch Tainted: G B 5.16.0-rc3+ #3 | Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 | RIP: 0010:fortify_panic+0x19/0x1b | ... | Call Trace: | kmalloc_oob_in_memset.cold+0x16/0x16 | ... Fix it by also hiding `ptr` from the optimizer, which will ensure that __builtin_object_size() does not return a valid size, preventing fortified string functions from panicking. Link: https://lkml.kernel.org/r/20220124160744.1244685-1-elver@google.com Signed-off-by: Marco Elver Reported-by: Nico Pache Reviewed-by: Nico Pache Reviewed-by: Andrey Konovalov Reviewed-by: Kees Cook Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Brendan Higgins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_kasan.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'lib') diff --git a/lib/test_kasan.c b/lib/test_kasan.c index 847cdbefab46..26a5c9007653 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -492,6 +492,7 @@ static void kmalloc_oob_in_memset(struct kunit *test) ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr, 0, size + KASAN_GRANULE_SIZE)); @@ -515,6 +516,7 @@ static void kmalloc_memmove_negative_size(struct kunit *test) KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); memset((char *)ptr, 0, 64); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(invalid_size); KUNIT_EXPECT_KASAN_FAIL(test, memmove((char *)ptr, (char *)ptr + 4, invalid_size)); @@ -531,6 +533,7 @@ static void kmalloc_memmove_invalid_size(struct kunit *test) KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); memset((char *)ptr, 0, 64); + OPTIMIZER_HIDE_VAR(ptr); KUNIT_EXPECT_KASAN_FAIL(test, memmove((char *)ptr, (char *)ptr + 4, invalid_size)); kfree(ptr); @@ -893,6 +896,7 @@ static void kasan_memchr(struct kunit *test) ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); KUNIT_EXPECT_KASAN_FAIL(test, kasan_ptr_result = memchr(ptr, '1', size + 1)); @@ -919,6 +923,7 @@ static void kasan_memcmp(struct kunit *test) KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); memset(arr, 0, sizeof(arr)); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = memcmp(ptr, arr, size+1)); -- cgit v1.2.3 From d2a02e3c8bb6b347818518edff5a4b40ff52d6d8 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 19 Jan 2022 14:35:06 +0100 Subject: lib/crypto: blake2s: avoid indirect calls to compression function for Clang CFI blake2s_compress_generic is weakly aliased by blake2s_compress. The current harness for function selection uses a function pointer, which is ordinarily inlined and resolved at compile time. But when Clang's CFI is enabled, CFI still triggers when making an indirect call via a weak symbol. This seems like a bug in Clang's CFI, as though it's bucketing weak symbols and strong symbols differently. It also only seems to trigger when "full LTO" mode is used, rather than "thin LTO". [ 0.000000][ T0] Kernel panic - not syncing: CFI failure (target: blake2s_compress_generic+0x0/0x1444) [ 0.000000][ T0] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.16.0-mainline-06981-g076c855b846e #1 [ 0.000000][ T0] Hardware name: MT6873 (DT) [ 0.000000][ T0] Call trace: [ 0.000000][ T0] dump_backtrace+0xfc/0x1dc [ 0.000000][ T0] dump_stack_lvl+0xa8/0x11c [ 0.000000][ T0] panic+0x194/0x464 [ 0.000000][ T0] __cfi_check_fail+0x54/0x58 [ 0.000000][ T0] __cfi_slowpath_diag+0x354/0x4b0 [ 0.000000][ T0] blake2s_update+0x14c/0x178 [ 0.000000][ T0] _extract_entropy+0xf4/0x29c [ 0.000000][ T0] crng_initialize_primary+0x24/0x94 [ 0.000000][ T0] rand_initialize+0x2c/0x6c [ 0.000000][ T0] start_kernel+0x2f8/0x65c [ 0.000000][ T0] __primary_switched+0xc4/0x7be4 [ 0.000000][ T0] Rebooting in 5 seconds.. Nonetheless, the function pointer method isn't so terrific anyway, so this patch replaces it with a simple boolean, which also gets inlined away. This successfully works around the Clang bug. In general, I'm not too keen on all of the indirection involved here; it clearly does more harm than good. Hopefully the whole thing can get cleaned up down the road when lib/crypto is overhauled more comprehensively. But for now, we go with a simple bandaid. Fixes: 6048fdcc5f26 ("lib/crypto: blake2s: include as built-in") Link: https://github.com/ClangBuiltLinux/linux/issues/1567 Reported-by: Miles Chen Tested-by: Miles Chen Tested-by: Nathan Chancellor Tested-by: John Stultz Acked-by: Nick Desaulniers Reviewed-by: Eric Biggers Signed-off-by: Jason A. Donenfeld --- arch/arm/crypto/blake2s-shash.c | 4 ++-- arch/x86/crypto/blake2s-shash.c | 4 ++-- crypto/blake2s_generic.c | 4 ++-- include/crypto/internal/blake2s.h | 40 ++++++++++++++++++++++++--------------- lib/crypto/blake2s.c | 4 ++-- 5 files changed, 33 insertions(+), 23 deletions(-) (limited to 'lib') diff --git a/arch/arm/crypto/blake2s-shash.c b/arch/arm/crypto/blake2s-shash.c index 17c1c3bfe2f5..763c73beea2d 100644 --- a/arch/arm/crypto/blake2s-shash.c +++ b/arch/arm/crypto/blake2s-shash.c @@ -13,12 +13,12 @@ static int crypto_blake2s_update_arm(struct shash_desc *desc, const u8 *in, unsigned int inlen) { - return crypto_blake2s_update(desc, in, inlen, blake2s_compress); + return crypto_blake2s_update(desc, in, inlen, false); } static int crypto_blake2s_final_arm(struct shash_desc *desc, u8 *out) { - return crypto_blake2s_final(desc, out, blake2s_compress); + return crypto_blake2s_final(desc, out, false); } #define BLAKE2S_ALG(name, driver_name, digest_size) \ diff --git a/arch/x86/crypto/blake2s-shash.c b/arch/x86/crypto/blake2s-shash.c index f9e2fecdb761..59ae28abe35c 100644 --- a/arch/x86/crypto/blake2s-shash.c +++ b/arch/x86/crypto/blake2s-shash.c @@ -18,12 +18,12 @@ static int crypto_blake2s_update_x86(struct shash_desc *desc, const u8 *in, unsigned int inlen) { - return crypto_blake2s_update(desc, in, inlen, blake2s_compress); + return crypto_blake2s_update(desc, in, inlen, false); } static int crypto_blake2s_final_x86(struct shash_desc *desc, u8 *out) { - return crypto_blake2s_final(desc, out, blake2s_compress); + return crypto_blake2s_final(desc, out, false); } #define BLAKE2S_ALG(name, driver_name, digest_size) \ diff --git a/crypto/blake2s_generic.c b/crypto/blake2s_generic.c index 72fe480f9bd6..5f96a21f8788 100644 --- a/crypto/blake2s_generic.c +++ b/crypto/blake2s_generic.c @@ -15,12 +15,12 @@ static int crypto_blake2s_update_generic(struct shash_desc *desc, const u8 *in, unsigned int inlen) { - return crypto_blake2s_update(desc, in, inlen, blake2s_compress_generic); + return crypto_blake2s_update(desc, in, inlen, true); } static int crypto_blake2s_final_generic(struct shash_desc *desc, u8 *out) { - return crypto_blake2s_final(desc, out, blake2s_compress_generic); + return crypto_blake2s_final(desc, out, true); } #define BLAKE2S_ALG(name, driver_name, digest_size) \ diff --git a/include/crypto/internal/blake2s.h b/include/crypto/internal/blake2s.h index d39cfa0d333e..52363eee2b20 100644 --- a/include/crypto/internal/blake2s.h +++ b/include/crypto/internal/blake2s.h @@ -24,14 +24,11 @@ static inline void blake2s_set_lastblock(struct blake2s_state *state) state->f[0] = -1; } -typedef void (*blake2s_compress_t)(struct blake2s_state *state, - const u8 *block, size_t nblocks, u32 inc); - /* Helper functions for BLAKE2s shared by the library and shash APIs */ -static inline void __blake2s_update(struct blake2s_state *state, - const u8 *in, size_t inlen, - blake2s_compress_t compress) +static __always_inline void +__blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen, + bool force_generic) { const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen; @@ -39,7 +36,12 @@ static inline void __blake2s_update(struct blake2s_state *state, return; if (inlen > fill) { memcpy(state->buf + state->buflen, in, fill); - (*compress)(state, state->buf, 1, BLAKE2S_BLOCK_SIZE); + if (force_generic) + blake2s_compress_generic(state, state->buf, 1, + BLAKE2S_BLOCK_SIZE); + else + blake2s_compress(state, state->buf, 1, + BLAKE2S_BLOCK_SIZE); state->buflen = 0; in += fill; inlen -= fill; @@ -47,7 +49,12 @@ static inline void __blake2s_update(struct blake2s_state *state, if (inlen > BLAKE2S_BLOCK_SIZE) { const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); /* Hash one less (full) block than strictly possible */ - (*compress)(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE); + if (force_generic) + blake2s_compress_generic(state, in, nblocks - 1, + BLAKE2S_BLOCK_SIZE); + else + blake2s_compress(state, in, nblocks - 1, + BLAKE2S_BLOCK_SIZE); in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); } @@ -55,13 +62,16 @@ static inline void __blake2s_update(struct blake2s_state *state, state->buflen += inlen; } -static inline void __blake2s_final(struct blake2s_state *state, u8 *out, - blake2s_compress_t compress) +static __always_inline void +__blake2s_final(struct blake2s_state *state, u8 *out, bool force_generic) { blake2s_set_lastblock(state); memset(state->buf + state->buflen, 0, BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */ - (*compress)(state, state->buf, 1, state->buflen); + if (force_generic) + blake2s_compress_generic(state, state->buf, 1, state->buflen); + else + blake2s_compress(state, state->buf, 1, state->buflen); cpu_to_le32_array(state->h, ARRAY_SIZE(state->h)); memcpy(out, state->h, state->outlen); } @@ -99,20 +109,20 @@ static inline int crypto_blake2s_init(struct shash_desc *desc) static inline int crypto_blake2s_update(struct shash_desc *desc, const u8 *in, unsigned int inlen, - blake2s_compress_t compress) + bool force_generic) { struct blake2s_state *state = shash_desc_ctx(desc); - __blake2s_update(state, in, inlen, compress); + __blake2s_update(state, in, inlen, force_generic); return 0; } static inline int crypto_blake2s_final(struct shash_desc *desc, u8 *out, - blake2s_compress_t compress) + bool force_generic) { struct blake2s_state *state = shash_desc_ctx(desc); - __blake2s_final(state, out, compress); + __blake2s_final(state, out, force_generic); return 0; } diff --git a/lib/crypto/blake2s.c b/lib/crypto/blake2s.c index 9364f79937b8..c71c09621c09 100644 --- a/lib/crypto/blake2s.c +++ b/lib/crypto/blake2s.c @@ -18,14 +18,14 @@ void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen) { - __blake2s_update(state, in, inlen, blake2s_compress); + __blake2s_update(state, in, inlen, false); } EXPORT_SYMBOL(blake2s_update); void blake2s_final(struct blake2s_state *state, u8 *out) { WARN_ON(IS_ENABLED(DEBUG) && !out); - __blake2s_final(state, out, blake2s_compress); + __blake2s_final(state, out, false); memzero_explicit(state, sizeof(*state)); } EXPORT_SYMBOL(blake2s_final); -- cgit v1.2.3