From 9ab121d65e03b4dc38f207871070eb353b396b05 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 8 Mar 2024 11:58:56 +0100 Subject: sched/debug: Allow CONFIG_SCHEDSTATS even on !KERNEL_DEBUG kernels All major Linux distributions enable CONFIG_SCHEDSTATS, so make it more widely available. Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20240308105901.1096078-6-mingo@kernel.org --- lib/Kconfig.debug | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 6c596e65de8a..ed2ad1a0cec6 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1250,7 +1250,7 @@ config SCHED_INFO config SCHEDSTATS bool "Collect scheduler statistics" - depends on DEBUG_KERNEL && PROC_FS + depends on PROC_FS select SCHED_INFO help If you say Y here, additional code will be inserted into the -- cgit v1.2.3 From 991e5583647d33ee3a9c89248974ef98b9f539a8 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Wed, 27 Mar 2024 16:23:39 +0100 Subject: lib/test_bitmap: add tests for bitmap_{read,write}() Add basic tests ensuring that values can be added at arbitrary positions of the bitmap, including those spanning into the adjacent unsigned longs. Two new performance tests, test_bitmap_read_perf() and test_bitmap_write_perf(), can be used to assess future performance improvements of bitmap_read() and bitmap_write(): [ 0.431119][ T1] test_bitmap: Time spent in test_bitmap_read_perf: 615253 [ 0.433197][ T1] test_bitmap: Time spent in test_bitmap_write_perf: 916313 (numbers from a Intel(R) Xeon(R) Gold 6154 CPU @ 3.00GHz machine running QEMU). Signed-off-by: Alexander Potapenko Reviewed-by: Andy Shevchenko Acked-by: Yury Norov Signed-off-by: Yury Norov Signed-off-by: Alexander Lobakin Signed-off-by: David S. Miller --- lib/test_bitmap.c | 179 +++++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 172 insertions(+), 7 deletions(-) (limited to 'lib') diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 6b2b33579f56..9198e93b7985 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -60,18 +60,17 @@ static const unsigned long exp3_1_0[] __initconst = { }; static bool __init -__check_eq_uint(const char *srcfile, unsigned int line, - const unsigned int exp_uint, unsigned int x) +__check_eq_ulong(const char *srcfile, unsigned int line, + const unsigned long exp_ulong, unsigned long x) { - if (exp_uint != x) { - pr_err("[%s:%u] expected %u, got %u\n", - srcfile, line, exp_uint, x); + if (exp_ulong != x) { + pr_err("[%s:%u] expected %lu, got %lu\n", + srcfile, line, exp_ulong, x); return false; } return true; } - static bool __init __check_eq_bitmap(const char *srcfile, unsigned int line, const unsigned long *exp_bmap, const unsigned long *bmap, @@ -185,7 +184,8 @@ __check_eq_str(const char *srcfile, unsigned int line, result; \ }) -#define expect_eq_uint(...) __expect_eq(uint, ##__VA_ARGS__) +#define expect_eq_ulong(...) __expect_eq(ulong, ##__VA_ARGS__) +#define expect_eq_uint(x, y) expect_eq_ulong((unsigned int)(x), (unsigned int)(y)) #define expect_eq_bitmap(...) __expect_eq(bitmap, ##__VA_ARGS__) #define expect_eq_pbl(...) __expect_eq(pbl, ##__VA_ARGS__) #define expect_eq_u32_array(...) __expect_eq(u32_array, ##__VA_ARGS__) @@ -1286,6 +1286,168 @@ static void __init test_bitmap_const_eval(void) BUILD_BUG_ON(~var != ~BIT(25)); } +/* + * Test bitmap should be big enough to include the cases when start is not in + * the first word, and start+nbits lands in the following word. + */ +#define TEST_BIT_LEN (1000) + +/* + * Helper function to test bitmap_write() overwriting the chosen byte pattern. + */ +static void __init test_bitmap_write_helper(const char *pattern) +{ + DECLARE_BITMAP(bitmap, TEST_BIT_LEN); + DECLARE_BITMAP(exp_bitmap, TEST_BIT_LEN); + DECLARE_BITMAP(pat_bitmap, TEST_BIT_LEN); + unsigned long w, r, bit; + int i, n, nbits; + + /* + * Only parse the pattern once and store the result in the intermediate + * bitmap. + */ + bitmap_parselist(pattern, pat_bitmap, TEST_BIT_LEN); + + /* + * Check that writing a single bit does not accidentally touch the + * adjacent bits. + */ + for (i = 0; i < TEST_BIT_LEN; i++) { + bitmap_copy(bitmap, pat_bitmap, TEST_BIT_LEN); + bitmap_copy(exp_bitmap, pat_bitmap, TEST_BIT_LEN); + for (bit = 0; bit <= 1; bit++) { + bitmap_write(bitmap, bit, i, 1); + __assign_bit(i, exp_bitmap, bit); + expect_eq_bitmap(exp_bitmap, bitmap, + TEST_BIT_LEN); + } + } + + /* Ensure writing 0 bits does not change anything. */ + bitmap_copy(bitmap, pat_bitmap, TEST_BIT_LEN); + bitmap_copy(exp_bitmap, pat_bitmap, TEST_BIT_LEN); + for (i = 0; i < TEST_BIT_LEN; i++) { + bitmap_write(bitmap, ~0UL, i, 0); + expect_eq_bitmap(exp_bitmap, bitmap, TEST_BIT_LEN); + } + + for (nbits = BITS_PER_LONG; nbits >= 1; nbits--) { + w = IS_ENABLED(CONFIG_64BIT) ? 0xdeadbeefdeadbeefUL + : 0xdeadbeefUL; + w >>= (BITS_PER_LONG - nbits); + for (i = 0; i <= TEST_BIT_LEN - nbits; i++) { + bitmap_copy(bitmap, pat_bitmap, TEST_BIT_LEN); + bitmap_copy(exp_bitmap, pat_bitmap, TEST_BIT_LEN); + for (n = 0; n < nbits; n++) + __assign_bit(i + n, exp_bitmap, w & BIT(n)); + bitmap_write(bitmap, w, i, nbits); + expect_eq_bitmap(exp_bitmap, bitmap, TEST_BIT_LEN); + r = bitmap_read(bitmap, i, nbits); + expect_eq_ulong(r, w); + } + } +} + +static void __init test_bitmap_read_write(void) +{ + unsigned char *pattern[3] = {"", "all:1/2", "all"}; + DECLARE_BITMAP(bitmap, TEST_BIT_LEN); + unsigned long zero_bits = 0, bits_per_long = BITS_PER_LONG; + unsigned long val; + int i, pi; + + /* + * Reading/writing zero bits should not crash the kernel. + * READ_ONCE() prevents constant folding. + */ + bitmap_write(NULL, 0, 0, READ_ONCE(zero_bits)); + /* Return value of bitmap_read() is undefined here. */ + bitmap_read(NULL, 0, READ_ONCE(zero_bits)); + + /* + * Reading/writing more than BITS_PER_LONG bits should not crash the + * kernel. READ_ONCE() prevents constant folding. + */ + bitmap_write(NULL, 0, 0, READ_ONCE(bits_per_long) + 1); + /* Return value of bitmap_read() is undefined here. */ + bitmap_read(NULL, 0, READ_ONCE(bits_per_long) + 1); + + /* + * Ensure that bitmap_read() reads the same value that was previously + * written, and two consequent values are correctly merged. + * The resulting bit pattern is asymmetric to rule out possible issues + * with bit numeration order. + */ + for (i = 0; i < TEST_BIT_LEN - 7; i++) { + bitmap_zero(bitmap, TEST_BIT_LEN); + + bitmap_write(bitmap, 0b10101UL, i, 5); + val = bitmap_read(bitmap, i, 5); + expect_eq_ulong(0b10101UL, val); + + bitmap_write(bitmap, 0b101UL, i + 5, 3); + val = bitmap_read(bitmap, i + 5, 3); + expect_eq_ulong(0b101UL, val); + + val = bitmap_read(bitmap, i, 8); + expect_eq_ulong(0b10110101UL, val); + } + + for (pi = 0; pi < ARRAY_SIZE(pattern); pi++) + test_bitmap_write_helper(pattern[pi]); +} + +static void __init test_bitmap_read_perf(void) +{ + DECLARE_BITMAP(bitmap, TEST_BIT_LEN); + unsigned int cnt, nbits, i; + unsigned long val; + ktime_t time; + + bitmap_fill(bitmap, TEST_BIT_LEN); + time = ktime_get(); + for (cnt = 0; cnt < 5; cnt++) { + for (nbits = 1; nbits <= BITS_PER_LONG; nbits++) { + for (i = 0; i < TEST_BIT_LEN; i++) { + if (i + nbits > TEST_BIT_LEN) + break; + /* + * Prevent the compiler from optimizing away the + * bitmap_read() by using its value. + */ + WRITE_ONCE(val, bitmap_read(bitmap, i, nbits)); + } + } + } + time = ktime_get() - time; + pr_err("Time spent in %s:\t%llu\n", __func__, time); +} + +static void __init test_bitmap_write_perf(void) +{ + DECLARE_BITMAP(bitmap, TEST_BIT_LEN); + unsigned int cnt, nbits, i; + unsigned long val = 0xfeedface; + ktime_t time; + + bitmap_zero(bitmap, TEST_BIT_LEN); + time = ktime_get(); + for (cnt = 0; cnt < 5; cnt++) { + for (nbits = 1; nbits <= BITS_PER_LONG; nbits++) { + for (i = 0; i < TEST_BIT_LEN; i++) { + if (i + nbits > TEST_BIT_LEN) + break; + bitmap_write(bitmap, val, i, nbits); + } + } + } + time = ktime_get() - time; + pr_err("Time spent in %s:\t%llu\n", __func__, time); +} + +#undef TEST_BIT_LEN + static void __init selftest(void) { test_zero_clear(); @@ -1303,6 +1465,9 @@ static void __init selftest(void) test_bitmap_cut(); test_bitmap_print_buf(); test_bitmap_const_eval(); + test_bitmap_read_write(); + test_bitmap_read_perf(); + test_bitmap_write_perf(); test_find_nth_bit(); test_for_each_set_bit(); -- cgit v1.2.3 From f3e28876b6e0b80cc35bf4a7bd854ce1035ea985 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Wed, 27 Mar 2024 16:23:40 +0100 Subject: lib/test_bitmap: use pr_info() for non-error messages pr_err() messages may be treated as errors by some log readers, so let us only use them for test failures. For non-error messages, replace them with pr_info(). Suggested-by: Alexander Lobakin Signed-off-by: Alexander Potapenko Acked-by: Yury Norov Signed-off-by: Yury Norov Signed-off-by: Alexander Lobakin Signed-off-by: David S. Miller --- lib/test_bitmap.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'lib') diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 9198e93b7985..2870373d94d0 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -548,7 +548,7 @@ static void __init test_bitmap_parselist(void) } if (ptest.flags & PARSE_TIME) - pr_err("parselist: %d: input is '%s' OK, Time: %llu\n", + pr_info("parselist: %d: input is '%s' OK, Time: %llu\n", i, ptest.in, time); #undef ptest @@ -587,7 +587,7 @@ static void __init test_bitmap_printlist(void) goto out; } - pr_err("bitmap_print_to_pagebuf: input is '%s', Time: %llu\n", buf, time); + pr_info("bitmap_print_to_pagebuf: input is '%s', Time: %llu\n", buf, time); out: kfree(buf); kfree(bmap); @@ -665,7 +665,7 @@ static void __init test_bitmap_parse(void) } if (test.flags & PARSE_TIME) - pr_err("parse: %d: input is '%s' OK, Time: %llu\n", + pr_info("parse: %d: input is '%s' OK, Time: %llu\n", i, test.in, time); } } @@ -1421,7 +1421,7 @@ static void __init test_bitmap_read_perf(void) } } time = ktime_get() - time; - pr_err("Time spent in %s:\t%llu\n", __func__, time); + pr_info("Time spent in %s:\t%llu\n", __func__, time); } static void __init test_bitmap_write_perf(void) @@ -1443,7 +1443,7 @@ static void __init test_bitmap_write_perf(void) } } time = ktime_get() - time; - pr_err("Time spent in %s:\t%llu\n", __func__, time); + pr_info("Time spent in %s:\t%llu\n", __func__, time); } #undef TEST_BIT_LEN -- cgit v1.2.3 From a37fbe666c016fd89e4460d0ebfcea05baba46dc Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Wed, 27 Mar 2024 16:23:49 +0100 Subject: bitmap: introduce generic optimized bitmap_size() The number of times yet another open coded `BITS_TO_LONGS(nbits) * sizeof(long)` can be spotted is huge. Some generic helper is long overdue. Add one, bitmap_size(), but with one detail. BITS_TO_LONGS() uses DIV_ROUND_UP(). The latter works well when both divident and divisor are compile-time constants or when the divisor is not a pow-of-2. When it is however, the compilers sometimes tend to generate suboptimal code (GCC 13): 48 83 c0 3f add $0x3f,%rax 48 c1 e8 06 shr $0x6,%rax 48 8d 14 c5 00 00 00 00 lea 0x0(,%rax,8),%rdx %BITS_PER_LONG is always a pow-2 (either 32 or 64), but GCC still does full division of `nbits + 63` by it and then multiplication by 8. Instead of BITS_TO_LONGS(), use ALIGN() and then divide by 8. GCC: 8d 50 3f lea 0x3f(%rax),%edx c1 ea 03 shr $0x3,%edx 81 e2 f8 ff ff 1f and $0x1ffffff8,%edx Now it shifts `nbits + 63` by 3 positions (IOW performs fast division by 8) and then masks bits[2:0]. bloat-o-meter: add/remove: 0/0 grow/shrink: 20/133 up/down: 156/-773 (-617) Clang does it better and generates the same code before/after starting from -O1, except that with the ALIGN() approach it uses %edx and thus still saves some bytes: add/remove: 0/0 grow/shrink: 9/133 up/down: 18/-538 (-520) Note that we can't expand DIV_ROUND_UP() by adding a check and using this approach there, as it's used in array declarations where expressions are not allowed. Add this helper to tools/ as well. Reviewed-by: Przemek Kitszel Acked-by: Yury Norov Signed-off-by: Alexander Lobakin Signed-off-by: David S. Miller --- drivers/md/dm-clone-metadata.c | 5 ----- drivers/s390/cio/idset.c | 2 +- include/linux/bitmap.h | 8 +++++--- include/linux/cpumask.h | 2 +- lib/math/prime_numbers.c | 2 -- tools/include/linux/bitmap.h | 7 ++++--- 6 files changed, 11 insertions(+), 15 deletions(-) (limited to 'lib') diff --git a/drivers/md/dm-clone-metadata.c b/drivers/md/dm-clone-metadata.c index c43d55672bce..47c1fa7aad8b 100644 --- a/drivers/md/dm-clone-metadata.c +++ b/drivers/md/dm-clone-metadata.c @@ -465,11 +465,6 @@ static void __destroy_persistent_data_structures(struct dm_clone_metadata *cmd) /*---------------------------------------------------------------------------*/ -static size_t bitmap_size(unsigned long nr_bits) -{ - return BITS_TO_LONGS(nr_bits) * sizeof(long); -} - static int __dirty_map_init(struct dirty_map *dmap, unsigned long nr_words, unsigned long nr_regions) { diff --git a/drivers/s390/cio/idset.c b/drivers/s390/cio/idset.c index 0a1105a483bf..e5f28370a903 100644 --- a/drivers/s390/cio/idset.c +++ b/drivers/s390/cio/idset.c @@ -18,7 +18,7 @@ struct idset { static inline unsigned long idset_bitmap_size(int num_ssid, int num_id) { - return BITS_TO_LONGS(num_ssid * num_id) * sizeof(unsigned long); + return bitmap_size(size_mul(num_ssid, num_id)); } static struct idset *idset_new(int num_ssid, int num_id) diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 914c23e96f26..363e0b184a45 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -226,9 +226,11 @@ void bitmap_fold(unsigned long *dst, const unsigned long *orig, #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) +#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) + static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = 0; @@ -238,7 +240,7 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = ~0UL; @@ -249,7 +251,7 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = *src; diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 1c29947db848..6519f9c77709 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -853,7 +853,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) */ static inline unsigned int cpumask_size(void) { - return BITS_TO_LONGS(large_cpumask_bits) * sizeof(long); + return bitmap_size(large_cpumask_bits); } /* diff --git a/lib/math/prime_numbers.c b/lib/math/prime_numbers.c index d42cebf7407f..d3b64b10da1c 100644 --- a/lib/math/prime_numbers.c +++ b/lib/math/prime_numbers.c @@ -6,8 +6,6 @@ #include #include -#define bitmap_size(nbits) (BITS_TO_LONGS(nbits) * sizeof(unsigned long)) - struct primes { struct rcu_head rcu; unsigned long last, sz; diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index 8c6852dba04f..210c13b1b857 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -26,13 +26,14 @@ bool __bitmap_intersects(const unsigned long *bitmap1, #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) +#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) + static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = 0UL; else { - int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memset(dst, 0, len); + memset(dst, 0, bitmap_size(nbits)); } } @@ -84,7 +85,7 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, */ static inline unsigned long *bitmap_zalloc(int nbits) { - return calloc(1, BITS_TO_LONGS(nbits) * sizeof(unsigned long)); + return calloc(1, bitmap_size(nbits)); } /* -- cgit v1.2.3 From 7adaf37f7f104a7ee5f150af491674ccbbfc4114 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Wed, 27 Mar 2024 16:23:51 +0100 Subject: lib/bitmap: add compile-time test for __assign_bit() optimization Commit dc34d5036692 ("lib: test_bitmap: add compile-time optimization/evaluations assertions") initially missed __assign_bit(), which led to that quite a time passed before I realized it doesn't get optimized at compilation time. Now that it does, add test for that just to make sure nothing will break one day. To make things more interesting, use bitmap_complement() and bitmap_full(), thus checking their compile-time evaluation as well. And remove the misleading comment mentioning the workaround removed recently in favor of adding the whole file to GCov exceptions. Reviewed-by: Przemek Kitszel Signed-off-by: Yury Norov Signed-off-by: Alexander Lobakin Signed-off-by: David S. Miller --- lib/test_bitmap.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'lib') diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 2870373d94d0..83019beabce4 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -1245,14 +1245,7 @@ static void __init test_bitmap_const_eval(void) * in runtime. */ - /* - * Equals to `unsigned long bitmap[1] = { GENMASK(6, 5), }`. - * Clang on s390 optimizes bitops at compile-time as intended, but at - * the same time stops treating @bitmap and @bitopvar as compile-time - * constants after regular test_bit() is executed, thus triggering the - * build bugs below. So, call const_test_bit() there directly until - * the compiler is fixed. - */ + /* Equals to `unsigned long bitmap[1] = { GENMASK(6, 5), }` */ bitmap_clear(bitmap, 0, BITS_PER_LONG); if (!test_bit(7, bitmap)) bitmap_set(bitmap, 5, 2); @@ -1284,6 +1277,15 @@ static void __init test_bitmap_const_eval(void) /* ~BIT(25) */ BUILD_BUG_ON(!__builtin_constant_p(~var)); BUILD_BUG_ON(~var != ~BIT(25)); + + /* ~BIT(25) | BIT(25) == ~0UL */ + bitmap_complement(&var, &var, BITS_PER_LONG); + __assign_bit(25, &var, true); + + /* !(~(~0UL)) == 1 */ + res = bitmap_full(&var, BITS_PER_LONG); + BUILD_BUG_ON(!__builtin_constant_p(res)); + BUILD_BUG_ON(!res); } /* -- cgit v1.2.3 From b1080c667b3b2c8c38a7fa83ca5567124887abae Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 2 Apr 2024 06:38:39 -0700 Subject: mm/slub, kunit: Use inverted data to corrupt kmem cache Two failure patterns are seen randomly when running slub_kunit tests with CONFIG_SLAB_FREELIST_RANDOM and CONFIG_SLAB_FREELIST_HARDENED enabled. Pattern 1: # test_clobber_zone: pass:1 fail:0 skip:0 total:1 ok 1 test_clobber_zone # test_next_pointer: EXPECTATION FAILED at lib/slub_kunit.c:72 Expected 3 == slab_errors, but slab_errors == 0 (0x0) # test_next_pointer: EXPECTATION FAILED at lib/slub_kunit.c:84 Expected 2 == slab_errors, but slab_errors == 0 (0x0) # test_next_pointer: pass:0 fail:1 skip:0 total:1 not ok 2 test_next_pointer In this case, test_next_pointer() overwrites p[s->offset], but the data at p[s->offset] is already 0x12. Pattern 2: ok 1 test_clobber_zone # test_next_pointer: EXPECTATION FAILED at lib/slub_kunit.c:72 Expected 3 == slab_errors, but slab_errors == 2 (0x2) # test_next_pointer: pass:0 fail:1 skip:0 total:1 not ok 2 test_next_pointer In this case, p[s->offset] has a value other than 0x12, but one of the expected failures is nevertheless missing. Invert data instead of writing a fixed value to corrupt the cache data structures to fix the problem. Fixes: 1f9f78b1b376 ("mm/slub, kunit: add a KUnit test for SLUB debugging functionality") Cc: Oliver Glitta Cc: Vlastimil Babka CC: Daniel Latypov Cc: Marco Elver Signed-off-by: Guenter Roeck Signed-off-by: Vlastimil Babka --- lib/slub_kunit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/slub_kunit.c b/lib/slub_kunit.c index d4a3730b08fa..4ce960438806 100644 --- a/lib/slub_kunit.c +++ b/lib/slub_kunit.c @@ -55,7 +55,7 @@ static void test_next_pointer(struct kunit *test) ptr_addr = (unsigned long *)(p + s->offset); tmp = *ptr_addr; - p[s->offset] = 0x12; + p[s->offset] = ~p[s->offset]; /* * Expecting three errors. -- cgit v1.2.3 From 229087f6f1dc2d0c38feba805770f28529980ec0 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 4 Apr 2024 15:03:44 -0700 Subject: bpf, kconfig: Fix DEBUG_INFO_BTF_MODULES Kconfig definition Turns out that due to CONFIG_DEBUG_INFO_BTF_MODULES not having an explicitly specified "menu item name" in Kconfig, it's basically impossible to turn it off (see [0]). This patch fixes the issue by defining menu name for CONFIG_DEBUG_INFO_BTF_MODULES, which makes it actually adjustable and independent of CONFIG_DEBUG_INFO_BTF, in the sense that one can have DEBUG_INFO_BTF=y and DEBUG_INFO_BTF_MODULES=n. We still keep it as defaulting to Y, of course. Fixes: 5f9ae91f7c0d ("kbuild: Build kernel module BTFs if BTF is enabled and pahole supports it") Reported-by: Vincent Li Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/CAK3+h2xiFfzQ9UXf56nrRRP=p1+iUxGoEP5B+aq9MDT5jLXDSg@mail.gmail.com [0] Link: https://lore.kernel.org/bpf/20240404220344.3879270-1-andrii@kernel.org --- lib/Kconfig.debug | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c63a5fbf1f1c..291185f54ee4 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -375,7 +375,7 @@ config DEBUG_INFO_SPLIT Incompatible with older versions of ccache. config DEBUG_INFO_BTF - bool "Generate BTF typeinfo" + bool "Generate BTF type information" depends on !DEBUG_INFO_SPLIT && !DEBUG_INFO_REDUCED depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST depends on BPF_SYSCALL @@ -408,7 +408,8 @@ config PAHOLE_HAS_LANG_EXCLUDE using DEBUG_INFO_BTF_MODULES. config DEBUG_INFO_BTF_MODULES - def_bool y + bool "Generate BTF type information for kernel modules" + default y depends on DEBUG_INFO_BTF && MODULES && PAHOLE_HAS_SPLIT_BTF help Generate compact split BTF type information for kernel modules. -- cgit v1.2.3 From c8e3a8b6f2e62661d838ae222774121ae23777a4 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 25 Mar 2024 08:40:05 +0200 Subject: vdso: Consolidate vdso_calc_delta() Consolidate vdso_calc_delta(), in preparation for further simplification. Suggested-by: Thomas Gleixner Signed-off-by: Adrian Hunter Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20240325064023.2997-2-adrian.hunter@intel.com --- arch/powerpc/include/asm/vdso/gettimeofday.h | 26 +++++++++++--------------- arch/s390/include/asm/vdso/gettimeofday.h | 7 ++----- lib/vdso/gettimeofday.c | 9 ++++++++- 3 files changed, 21 insertions(+), 21 deletions(-) (limited to 'lib') diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h index 78302f6c2580..c6390890a60c 100644 --- a/arch/powerpc/include/asm/vdso/gettimeofday.h +++ b/arch/powerpc/include/asm/vdso/gettimeofday.h @@ -13,6 +13,17 @@ #define VDSO_HAS_TIME 1 +/* + * powerpc specific delta calculation. + * + * This variant removes the masking of the subtraction because the + * clocksource mask of all VDSO capable clocksources on powerpc is U64_MAX + * which would result in a pointless operation. The compiler cannot + * optimize it away as the mask comes from the vdso data and is not compile + * time constant. + */ +#define VDSO_DELTA_NOMASK 1 + static __always_inline int do_syscall_2(const unsigned long _r0, const unsigned long _r3, const unsigned long _r4) { @@ -104,21 +115,6 @@ static inline bool vdso_clocksource_ok(const struct vdso_data *vd) } #define vdso_clocksource_ok vdso_clocksource_ok -/* - * powerpc specific delta calculation. - * - * This variant removes the masking of the subtraction because the - * clocksource mask of all VDSO capable clocksources on powerpc is U64_MAX - * which would result in a pointless operation. The compiler cannot - * optimize it away as the mask comes from the vdso data and is not compile - * time constant. - */ -static __always_inline u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult) -{ - return (cycles - last) * mult; -} -#define vdso_calc_delta vdso_calc_delta - #ifndef __powerpc64__ static __always_inline u64 vdso_shift_ns(u64 ns, unsigned long shift) { diff --git a/arch/s390/include/asm/vdso/gettimeofday.h b/arch/s390/include/asm/vdso/gettimeofday.h index db84942eb78f..7937765ccfa5 100644 --- a/arch/s390/include/asm/vdso/gettimeofday.h +++ b/arch/s390/include/asm/vdso/gettimeofday.h @@ -6,16 +6,13 @@ #define VDSO_HAS_CLOCK_GETRES 1 +#define VDSO_DELTA_NOMASK 1 + #include #include #include #include -#define vdso_calc_delta __arch_vdso_calc_delta -static __always_inline u64 __arch_vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult) -{ - return (cycles - last) * mult; -} static __always_inline const struct vdso_data *__arch_get_vdso_data(void) { diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c index ce2f69552003..faccf12f7c03 100644 --- a/lib/vdso/gettimeofday.c +++ b/lib/vdso/gettimeofday.c @@ -6,6 +6,13 @@ #include #ifndef vdso_calc_delta + +#ifdef VDSO_DELTA_NOMASK +# define VDSO_DELTA_MASK(mask) U64_MAX +#else +# define VDSO_DELTA_MASK(mask) (mask) +#endif + /* * Default implementation which works for all sane clocksources. That * obviously excludes x86/TSC. @@ -13,7 +20,7 @@ static __always_inline u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult) { - return ((cycles - last) & mask) * mult; + return ((cycles - last) & VDSO_DELTA_MASK(mask)) * mult; } #endif -- cgit v1.2.3 From 5b26ef660a690e424d9548fdf0565d4172d5d88f Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 25 Mar 2024 08:40:06 +0200 Subject: vdso: Consolidate nanoseconds calculation Consolidate nanoseconds calculation to simplify and reduce code duplication. Suggested-by: Thomas Gleixner Signed-off-by: Adrian Hunter Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20240325064023.2997-3-adrian.hunter@intel.com --- arch/x86/include/asm/vdso/gettimeofday.h | 17 ++++++------- lib/vdso/gettimeofday.c | 43 ++++++++++++++------------------ 2 files changed, 27 insertions(+), 33 deletions(-) (limited to 'lib') diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h index 8e048ca980df..5727dedd3549 100644 --- a/arch/x86/include/asm/vdso/gettimeofday.h +++ b/arch/x86/include/asm/vdso/gettimeofday.h @@ -300,7 +300,7 @@ static inline bool arch_vdso_cycles_ok(u64 cycles) #define vdso_cycles_ok arch_vdso_cycles_ok /* - * x86 specific delta calculation. + * x86 specific calculation of nanoseconds for the current cycle count * * The regular implementation assumes that clocksource reads are globally * monotonic. The TSC can be slightly off across sockets which can cause @@ -308,8 +308,8 @@ static inline bool arch_vdso_cycles_ok(u64 cycles) * jump. * * Therefore it needs to be verified that @cycles are greater than - * @last. If not then use @last, which is the base time of the current - * conversion period. + * @vd->cycles_last. If not then use @vd->cycles_last, which is the base + * time of the current conversion period. * * This variant also uses a custom mask because while the clocksource mask of * all the VDSO capable clocksources on x86 is U64_MAX, the above code uses @@ -317,25 +317,24 @@ static inline bool arch_vdso_cycles_ok(u64 cycles) * declares everything with the MSB/Sign-bit set as invalid. Therefore the * effective mask is S64_MAX. */ -static __always_inline -u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult) +static __always_inline u64 vdso_calc_ns(const struct vdso_data *vd, u64 cycles, u64 base) { /* * Due to the MSB/Sign-bit being used as invalid marker (see * arch_vdso_cycles_valid() above), the effective mask is S64_MAX. */ - u64 delta = (cycles - last) & S64_MAX; + u64 delta = (cycles - vd->cycle_last) & S64_MAX; /* * Due to the above mentioned TSC wobbles, filter out negative motion. * Per the above masking, the effective sign bit is now bit 62. */ if (unlikely(delta & (1ULL << 62))) - return 0; + return base >> vd->shift; - return delta * mult; + return ((delta * vd->mult) + base) >> vd->shift; } -#define vdso_calc_delta vdso_calc_delta +#define vdso_calc_ns vdso_calc_ns #endif /* !__ASSEMBLY__ */ diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c index faccf12f7c03..9fa90e0794c9 100644 --- a/lib/vdso/gettimeofday.c +++ b/lib/vdso/gettimeofday.c @@ -5,31 +5,32 @@ #include #include -#ifndef vdso_calc_delta +#ifndef vdso_calc_ns #ifdef VDSO_DELTA_NOMASK -# define VDSO_DELTA_MASK(mask) U64_MAX +# define VDSO_DELTA_MASK(vd) U64_MAX #else -# define VDSO_DELTA_MASK(mask) (mask) +# define VDSO_DELTA_MASK(vd) (vd->mask) +#endif + +#ifndef vdso_shift_ns +static __always_inline u64 vdso_shift_ns(u64 ns, u32 shift) +{ + return ns >> shift; +} #endif /* * Default implementation which works for all sane clocksources. That * obviously excludes x86/TSC. */ -static __always_inline -u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult) +static __always_inline u64 vdso_calc_ns(const struct vdso_data *vd, u64 cycles, u64 base) { - return ((cycles - last) & VDSO_DELTA_MASK(mask)) * mult; -} -#endif + u64 delta = (cycles - vd->cycle_last) & VDSO_DELTA_MASK(vd); -#ifndef vdso_shift_ns -static __always_inline u64 vdso_shift_ns(u64 ns, u32 shift) -{ - return ns >> shift; + return vdso_shift_ns((delta * vd->mult) + base, vd->shift); } -#endif +#endif /* vdso_calc_ns */ #ifndef __arch_vdso_hres_capable static inline bool __arch_vdso_hres_capable(void) @@ -56,10 +57,10 @@ static inline bool vdso_cycles_ok(u64 cycles) static __always_inline int do_hres_timens(const struct vdso_data *vdns, clockid_t clk, struct __kernel_timespec *ts) { - const struct vdso_data *vd; const struct timens_offset *offs = &vdns->offset[clk]; const struct vdso_timestamp *vdso_ts; - u64 cycles, last, ns; + const struct vdso_data *vd; + u64 cycles, ns; u32 seq; s64 sec; @@ -80,10 +81,7 @@ static __always_inline int do_hres_timens(const struct vdso_data *vdns, clockid_ cycles = __arch_get_hw_counter(vd->clock_mode, vd); if (unlikely(!vdso_cycles_ok(cycles))) return -1; - ns = vdso_ts->nsec; - last = vd->cycle_last; - ns += vdso_calc_delta(cycles, last, vd->mask, vd->mult); - ns = vdso_shift_ns(ns, vd->shift); + ns = vdso_calc_ns(vd, cycles, vdso_ts->nsec); sec = vdso_ts->sec; } while (unlikely(vdso_read_retry(vd, seq))); @@ -118,7 +116,7 @@ static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk, struct __kernel_timespec *ts) { const struct vdso_timestamp *vdso_ts = &vd->basetime[clk]; - u64 cycles, last, sec, ns; + u64 cycles, sec, ns; u32 seq; /* Allows to compile the high resolution parts out */ @@ -151,10 +149,7 @@ static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk, cycles = __arch_get_hw_counter(vd->clock_mode, vd); if (unlikely(!vdso_cycles_ok(cycles))) return -1; - ns = vdso_ts->nsec; - last = vd->cycle_last; - ns += vdso_calc_delta(cycles, last, vd->mask, vd->mult); - ns = vdso_shift_ns(ns, vd->shift); + ns = vdso_calc_ns(vd, cycles, vdso_ts->nsec); sec = vdso_ts->sec; } while (unlikely(vdso_read_retry(vd, seq))); -- cgit v1.2.3 From 0c68458b0a5878d735572b4f4d91219a1db7c784 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 25 Mar 2024 08:40:07 +0200 Subject: vdso: Add CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT Add CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT in preparation to add multiplication overflow protection to the VDSO time getter functions. Suggested-by: Thomas Gleixner Signed-off-by: Adrian Hunter Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20240325064023.2997-4-adrian.hunter@intel.com --- lib/vdso/Kconfig | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'lib') diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig index d883ac299508..c46c2300517c 100644 --- a/lib/vdso/Kconfig +++ b/lib/vdso/Kconfig @@ -30,4 +30,11 @@ config GENERIC_VDSO_TIME_NS Selected by architectures which support time namespaces in the VDSO +config GENERIC_VDSO_OVERFLOW_PROTECT + bool + help + Select to add multiplication overflow protection to the VDSO + time getter functions for the price of an extra conditional + in the hotpath. + endif -- cgit v1.2.3 From 456e3788bc7164c1c8298045e04068b8e3d8e413 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 25 Mar 2024 08:40:11 +0200 Subject: vdso: Make delta calculation overflow safe Kernel timekeeping is designed to keep the change in cycles (since the last timer interrupt) below max_cycles, which prevents multiplication overflow when converting cycles to nanoseconds. However, if timer interrupts stop, the calculation will eventually overflow. Add protection against that, enabled by config option CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT. Check against max_cycles, falling back to a slower higher precision calculation. Suggested-by: Thomas Gleixner Signed-off-by: Adrian Hunter Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20240325064023.2997-8-adrian.hunter@intel.com --- lib/vdso/gettimeofday.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c index 9fa90e0794c9..9c3a8d2440c9 100644 --- a/lib/vdso/gettimeofday.c +++ b/lib/vdso/gettimeofday.c @@ -13,6 +13,18 @@ # define VDSO_DELTA_MASK(vd) (vd->mask) #endif +#ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT +static __always_inline bool vdso_delta_ok(const struct vdso_data *vd, u64 delta) +{ + return delta < vd->max_cycles; +} +#else +static __always_inline bool vdso_delta_ok(const struct vdso_data *vd, u64 delta) +{ + return true; +} +#endif + #ifndef vdso_shift_ns static __always_inline u64 vdso_shift_ns(u64 ns, u32 shift) { @@ -28,7 +40,10 @@ static __always_inline u64 vdso_calc_ns(const struct vdso_data *vd, u64 cycles, { u64 delta = (cycles - vd->cycle_last) & VDSO_DELTA_MASK(vd); - return vdso_shift_ns((delta * vd->mult) + base, vd->shift); + if (likely(vdso_delta_ok(vd, delta))) + return vdso_shift_ns((delta * vd->mult) + base, vd->shift); + + return mul_u64_u32_add_u64_shr(delta, vd->mult, base, vd->shift); } #endif /* vdso_calc_ns */ -- cgit v1.2.3 From 8ff1e6c5aca5fd908e81c33c460c45f9555e1c22 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 9 Apr 2024 09:26:39 +0300 Subject: vdso: Fix powerpc build U64_MAX undeclared error U64_MAX is not in include/vdso/limits.h, although that isn't noticed on x86 because x86 includes include/linux/limits.h indirectly. However powerpc is more selective, resulting in the following build error: In file included from : lib/vdso/gettimeofday.c: In function 'vdso_calc_ns': lib/vdso/gettimeofday.c:11:33: error: 'U64_MAX' undeclared 11 | # define VDSO_DELTA_MASK(vd) U64_MAX | ^~~~~~~ Use ULLONG_MAX instead which will work just as well and is in include/vdso/limits.h. Fixes: c8e3a8b6f2e6 ("vdso: Consolidate vdso_calc_delta()") Reported-by: Stephen Rothwell Signed-off-by: Adrian Hunter Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20240409062639.3393-1-adrian.hunter@intel.com Closes: https://lore.kernel.org/all/20240409124905.6816db37@canb.auug.org.au/ --- lib/vdso/gettimeofday.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c index 9c3a8d2440c9..899850bd6f0b 100644 --- a/lib/vdso/gettimeofday.c +++ b/lib/vdso/gettimeofday.c @@ -8,7 +8,7 @@ #ifndef vdso_calc_ns #ifdef VDSO_DELTA_NOMASK -# define VDSO_DELTA_MASK(vd) U64_MAX +# define VDSO_DELTA_MASK(vd) ULLONG_MAX #else # define VDSO_DELTA_MASK(vd) (vd->mask) #endif -- cgit v1.2.3 From 779087fe2fecf8b8aa7bdd69982f9c0c8266927b Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Fri, 5 Apr 2024 08:08:12 +0200 Subject: kfifo: drop __kfifo_dma_out_finish_r() It is the same as __kfifo_skip_r(), so: * drop __kfifo_dma_out_finish_r() completely, and * replace its (only) use by __kfifo_skip_r(). Signed-off-by: Jiri Slaby (SUSE) Cc: Stefani Seibold Cc: Andrew Morton Link: https://lore.kernel.org/r/20240405060826.2521-2-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/kfifo.h | 4 +--- lib/kfifo.c | 8 -------- 2 files changed, 1 insertion(+), 11 deletions(-) (limited to 'lib') diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index 0b35a41440ff..bc7a1f5bb0ce 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -797,7 +797,7 @@ __kfifo_int_must_check_helper( \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ if (__recsize) \ - __kfifo_dma_out_finish_r(__kfifo, __recsize); \ + __kfifo_skip_r(__kfifo, __recsize); \ else \ __kfifo->out += __len / sizeof(*__tmp->type); \ }) @@ -879,8 +879,6 @@ extern void __kfifo_dma_in_finish_r(struct __kfifo *fifo, extern unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo, struct scatterlist *sgl, int nents, unsigned int len, size_t recsize); -extern void __kfifo_dma_out_finish_r(struct __kfifo *fifo, size_t recsize); - extern unsigned int __kfifo_len_r(struct __kfifo *fifo, size_t recsize); extern void __kfifo_skip_r(struct __kfifo *fifo, size_t recsize); diff --git a/lib/kfifo.c b/lib/kfifo.c index 12f5a347aa13..958099cc4914 100644 --- a/lib/kfifo.c +++ b/lib/kfifo.c @@ -582,11 +582,3 @@ unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo, } EXPORT_SYMBOL(__kfifo_dma_out_prepare_r); -void __kfifo_dma_out_finish_r(struct __kfifo *fifo, size_t recsize) -{ - unsigned int len; - - len = __kfifo_peek_n(fifo, recsize); - fifo->out += len + recsize; -} -EXPORT_SYMBOL(__kfifo_dma_out_finish_r); -- cgit v1.2.3 From 4edd7e96a1f159f43bd1cb82616f81eaddd54262 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Fri, 5 Apr 2024 08:08:14 +0200 Subject: kfifo: add kfifo_out_linear{,_ptr}() These are helpers which are going to be used in the serial layer. We need a wrapper around kfifo which provides us with a tail (sometimes "tail" offset, sometimes a pointer) to the kfifo data. And which returns count of available data -- but not larger than to the end of the buffer (hence _linear in the names). I.e. something like CIRC_CNT_TO_END() in the legacy circ_buf. This patch adds such two helpers. Signed-off-by: Jiri Slaby (SUSE) Cc: Stefani Seibold Cc: Andrew Morton Link: https://lore.kernel.org/r/20240405060826.2521-4-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/kfifo.h | 63 +++++++++++++++++++++++++++++++++++++++++++++++++++ lib/kfifo.c | 26 +++++++++++++++++++++ 2 files changed, 89 insertions(+) (limited to 'lib') diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index 8f3369ec528b..3def70e1a3e3 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -827,6 +827,63 @@ __kfifo_uint_must_check_helper( \ }) \ ) +/** + * kfifo_out_linear - gets a tail of/offset to available data + * @fifo: address of the fifo to be used + * @tail: pointer to an unsigned int to store the value of tail + * @n: max. number of elements to point at + * + * This macro obtains the offset (tail) to the available data in the fifo + * buffer and returns the + * numbers of elements available. It returns the available count till the end + * of data or till the end of the buffer. So that it can be used for linear + * data processing (like memcpy() of (@fifo->data + @tail) with count + * returned). + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_out_linear(fifo, tail, n) \ +__kfifo_uint_must_check_helper( \ +({ \ + typeof((fifo) + 1) __tmp = (fifo); \ + unsigned int *__tail = (tail); \ + unsigned long __n = (n); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + (__recsize) ? \ + __kfifo_out_linear_r(__kfifo, __tail, __n, __recsize) : \ + __kfifo_out_linear(__kfifo, __tail, __n); \ +}) \ +) + +/** + * kfifo_out_linear_ptr - gets a pointer to the available data + * @fifo: address of the fifo to be used + * @ptr: pointer to data to store the pointer to tail + * @n: max. number of elements to point at + * + * Similarly to kfifo_out_linear(), this macro obtains the pointer to the + * available data in the fifo buffer and returns the numbers of elements + * available. It returns the available count till the end of available data or + * till the end of the buffer. So that it can be used for linear data + * processing (like memcpy() of @ptr with count returned). + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_out_linear_ptr(fifo, ptr, n) \ +__kfifo_uint_must_check_helper( \ +({ \ + typeof((fifo) + 1) ___tmp = (fifo); \ + unsigned int ___tail; \ + unsigned int ___n = kfifo_out_linear(___tmp, &___tail, (n)); \ + *(ptr) = ___tmp->kfifo.data + ___tail * kfifo_esize(___tmp); \ + ___n; \ +}) \ +) + + extern int __kfifo_alloc(struct __kfifo *fifo, unsigned int size, size_t esize, gfp_t gfp_mask); @@ -856,6 +913,9 @@ extern unsigned int __kfifo_dma_out_prepare(struct __kfifo *fifo, extern unsigned int __kfifo_out_peek(struct __kfifo *fifo, void *buf, unsigned int len); +extern unsigned int __kfifo_out_linear(struct __kfifo *fifo, + unsigned int *tail, unsigned int n); + extern unsigned int __kfifo_in_r(struct __kfifo *fifo, const void *buf, unsigned int len, size_t recsize); @@ -885,6 +945,9 @@ extern void __kfifo_skip_r(struct __kfifo *fifo, size_t recsize); extern unsigned int __kfifo_out_peek_r(struct __kfifo *fifo, void *buf, unsigned int len, size_t recsize); +extern unsigned int __kfifo_out_linear_r(struct __kfifo *fifo, + unsigned int *tail, unsigned int n, size_t recsize); + extern unsigned int __kfifo_max_r(unsigned int len, size_t recsize); #endif diff --git a/lib/kfifo.c b/lib/kfifo.c index 958099cc4914..a36bfdbdb17d 100644 --- a/lib/kfifo.c +++ b/lib/kfifo.c @@ -163,6 +163,19 @@ unsigned int __kfifo_out_peek(struct __kfifo *fifo, } EXPORT_SYMBOL(__kfifo_out_peek); +unsigned int __kfifo_out_linear(struct __kfifo *fifo, + unsigned int *tail, unsigned int n) +{ + unsigned int size = fifo->mask + 1; + unsigned int off = fifo->out & fifo->mask; + + if (tail) + *tail = off; + + return min3(n, fifo->in - fifo->out, size - off); +} +EXPORT_SYMBOL(__kfifo_out_linear); + unsigned int __kfifo_out(struct __kfifo *fifo, void *buf, unsigned int len) { @@ -473,6 +486,19 @@ unsigned int __kfifo_out_peek_r(struct __kfifo *fifo, void *buf, } EXPORT_SYMBOL(__kfifo_out_peek_r); +unsigned int __kfifo_out_linear_r(struct __kfifo *fifo, + unsigned int *tail, unsigned int n, size_t recsize) +{ + if (fifo->in == fifo->out) + return 0; + + if (tail) + *tail = fifo->out + recsize; + + return min(n, __kfifo_peek_n(fifo, recsize)); +} +EXPORT_SYMBOL(__kfifo_out_linear_r); + unsigned int __kfifo_out_r(struct __kfifo *fifo, void *buf, unsigned int len, size_t recsize) { -- cgit v1.2.3 From e9d9576de08ac65d2c973ef7ce542338d2da94f9 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Fri, 5 Apr 2024 08:08:15 +0200 Subject: kfifo: remove support for physically non-contiguous memory First, there is no such user. The only user of this interface is caam_rng_fill_async() and that uses kfifo_alloc() -> kmalloc(). Second, the implementation does not allow anything else than direct mapping and kmalloc() (due to virt_to_phys()), anyway. Therefore, there is no point in having this dead (and complex) code in the kernel. Note the setup_sgl_buf() function now boils down to simple sg_set_buf(). That is called twice from setup_sgl() to take care of kfifo buffer wrap-around. setup_sgl_buf() will be extended shortly, so keeping it in place. Signed-off-by: Jiri Slaby (SUSE) Cc: Andrew Morton Cc: Stefani Seibold Link: https://lore.kernel.org/r/20240405060826.2521-5-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- lib/kfifo.c | 38 +++++--------------------------------- 1 file changed, 5 insertions(+), 33 deletions(-) (limited to 'lib') diff --git a/lib/kfifo.c b/lib/kfifo.c index a36bfdbdb17d..d5830960ab87 100644 --- a/lib/kfifo.c +++ b/lib/kfifo.c @@ -305,43 +305,15 @@ int __kfifo_to_user(struct __kfifo *fifo, void __user *to, } EXPORT_SYMBOL(__kfifo_to_user); -static int setup_sgl_buf(struct scatterlist *sgl, void *buf, - int nents, unsigned int len) +static unsigned int setup_sgl_buf(struct scatterlist *sgl, void *buf, + int nents, unsigned int len) { - int n; - unsigned int l; - unsigned int off; - struct page *page; - - if (!nents) + if (!nents || !len) return 0; - if (!len) - return 0; + sg_set_buf(sgl, buf, len); - n = 0; - page = virt_to_page(buf); - off = offset_in_page(buf); - l = 0; - - while (len >= l + PAGE_SIZE - off) { - struct page *npage; - - l += PAGE_SIZE; - buf += PAGE_SIZE; - npage = virt_to_page(buf); - if (page_to_phys(page) != page_to_phys(npage) - l) { - sg_set_page(sgl, page, l - off, off); - sgl = sg_next(sgl); - if (++n == nents || sgl == NULL) - return n; - page = npage; - len -= l - off; - l = off = 0; - } - } - sg_set_page(sgl, page, len, off); - return n + 1; + return 1; } static unsigned int setup_sgl(struct __kfifo *fifo, struct scatterlist *sgl, -- cgit v1.2.3 From ed6d22f5d8672f38d6020c719d5d658a4e3e6be5 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Fri, 5 Apr 2024 08:08:16 +0200 Subject: kfifo: rename l to len_to_end in setup_sgl() So that one can make any sense of the name. Signed-off-by: Jiri Slaby (SUSE) Cc: Stefani Seibold Cc: Andrew Morton Link: https://lore.kernel.org/r/20240405060826.2521-6-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- lib/kfifo.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/kfifo.c b/lib/kfifo.c index d5830960ab87..61e35550aea5 100644 --- a/lib/kfifo.c +++ b/lib/kfifo.c @@ -321,7 +321,7 @@ static unsigned int setup_sgl(struct __kfifo *fifo, struct scatterlist *sgl, { unsigned int size = fifo->mask + 1; unsigned int esize = fifo->esize; - unsigned int l; + unsigned int len_to_end; unsigned int n; off &= fifo->mask; @@ -330,10 +330,10 @@ static unsigned int setup_sgl(struct __kfifo *fifo, struct scatterlist *sgl, size *= esize; len *= esize; } - l = min(len, size - off); + len_to_end = min(len, size - off); - n = setup_sgl_buf(sgl, fifo->data + off, nents, l); - n += setup_sgl_buf(sgl + n, fifo->data, nents - n, len - l); + n = setup_sgl_buf(sgl, fifo->data + off, nents, len_to_end); + n += setup_sgl_buf(sgl + n, fifo->data, nents - n, len - len_to_end); return n; } -- cgit v1.2.3 From fea0dde081621e25bcf7efd40cce6c8272e3aa13 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Fri, 5 Apr 2024 08:08:17 +0200 Subject: kfifo: pass offset to setup_sgl_buf() instead of a pointer As a preparatory for dma addresses filling, we need the data offset instead of virtual pointer in setup_sgl_buf(). So pass the former instead the latter. And pointer to fifo is needed in setup_sgl_buf() now too. Signed-off-by: Jiri Slaby (SUSE) Cc: Stefani Seibold Cc: Andrew Morton Link: https://lore.kernel.org/r/20240405060826.2521-7-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- lib/kfifo.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/kfifo.c b/lib/kfifo.c index 61e35550aea5..3a249ce4f281 100644 --- a/lib/kfifo.c +++ b/lib/kfifo.c @@ -305,9 +305,12 @@ int __kfifo_to_user(struct __kfifo *fifo, void __user *to, } EXPORT_SYMBOL(__kfifo_to_user); -static unsigned int setup_sgl_buf(struct scatterlist *sgl, void *buf, - int nents, unsigned int len) +static unsigned int setup_sgl_buf(struct __kfifo *fifo, struct scatterlist *sgl, + unsigned int data_offset, int nents, + unsigned int len) { + const void *buf = fifo->data + data_offset; + if (!nents || !len) return 0; @@ -332,8 +335,8 @@ static unsigned int setup_sgl(struct __kfifo *fifo, struct scatterlist *sgl, } len_to_end = min(len, size - off); - n = setup_sgl_buf(sgl, fifo->data + off, nents, len_to_end); - n += setup_sgl_buf(sgl + n, fifo->data, nents - n, len - len_to_end); + n = setup_sgl_buf(fifo, sgl, off, nents, len_to_end); + n += setup_sgl_buf(fifo, sgl + n, 0, nents - n, len - len_to_end); return n; } -- cgit v1.2.3 From d52b761e4b1acc897e65bcc8eff42b0537ac0134 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Fri, 5 Apr 2024 08:08:18 +0200 Subject: kfifo: add kfifo_dma_out_prepare_mapped() When the kfifo buffer is already dma-mapped, one cannot use the kfifo API to fill in an SG list. Add kfifo_dma_in_prepare_mapped() which allows exactly this. A mapped dma_addr_t is passed and it is filled into provided sgl too. Including the dma_len. Signed-off-by: Jiri Slaby (SUSE) Cc: Stefani Seibold Cc: Andrew Morton Link: https://lore.kernel.org/r/20240405060826.2521-8-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/kfifo.h | 37 +++++++++++++++++++++++++------------ lib/kfifo.c | 34 ++++++++++++++++++++++------------ 2 files changed, 47 insertions(+), 24 deletions(-) (limited to 'lib') diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index 3def70e1a3e3..c7cc25b2808b 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -36,6 +36,7 @@ * to lock the reader. */ +#include #include #include #include @@ -709,11 +710,12 @@ __kfifo_int_must_check_helper( \ ) /** - * kfifo_dma_in_prepare - setup a scatterlist for DMA input + * kfifo_dma_in_prepare_mapped - setup a scatterlist for DMA input * @fifo: address of the fifo to be used * @sgl: pointer to the scatterlist array * @nents: number of entries in the scatterlist array * @len: number of elements to transfer + * @dma: mapped dma address to fill into @sgl * * This macro fills a scatterlist for DMA input. * It returns the number entries in the scatterlist array. @@ -721,7 +723,7 @@ __kfifo_int_must_check_helper( \ * Note that with only one concurrent reader and one concurrent * writer, you don't need extra locking to use these macros. */ -#define kfifo_dma_in_prepare(fifo, sgl, nents, len) \ +#define kfifo_dma_in_prepare_mapped(fifo, sgl, nents, len, dma) \ ({ \ typeof((fifo) + 1) __tmp = (fifo); \ struct scatterlist *__sgl = (sgl); \ @@ -730,10 +732,14 @@ __kfifo_int_must_check_helper( \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ (__recsize) ? \ - __kfifo_dma_in_prepare_r(__kfifo, __sgl, __nents, __len, __recsize) : \ - __kfifo_dma_in_prepare(__kfifo, __sgl, __nents, __len); \ + __kfifo_dma_in_prepare_r(__kfifo, __sgl, __nents, __len, __recsize, \ + dma) : \ + __kfifo_dma_in_prepare(__kfifo, __sgl, __nents, __len, dma); \ }) +#define kfifo_dma_in_prepare(fifo, sgl, nents, len) \ + kfifo_dma_in_prepare_mapped(fifo, sgl, nents, len, DMA_MAPPING_ERROR) + /** * kfifo_dma_in_finish - finish a DMA IN operation * @fifo: address of the fifo to be used @@ -758,11 +764,12 @@ __kfifo_int_must_check_helper( \ }) /** - * kfifo_dma_out_prepare - setup a scatterlist for DMA output + * kfifo_dma_out_prepare_mapped - setup a scatterlist for DMA output * @fifo: address of the fifo to be used * @sgl: pointer to the scatterlist array * @nents: number of entries in the scatterlist array * @len: number of elements to transfer + * @dma: mapped dma address to fill into @sgl * * This macro fills a scatterlist for DMA output which at most @len bytes * to transfer. @@ -772,7 +779,7 @@ __kfifo_int_must_check_helper( \ * Note that with only one concurrent reader and one concurrent * writer, you don't need extra locking to use these macros. */ -#define kfifo_dma_out_prepare(fifo, sgl, nents, len) \ +#define kfifo_dma_out_prepare_mapped(fifo, sgl, nents, len, dma) \ ({ \ typeof((fifo) + 1) __tmp = (fifo); \ struct scatterlist *__sgl = (sgl); \ @@ -781,10 +788,14 @@ __kfifo_int_must_check_helper( \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ (__recsize) ? \ - __kfifo_dma_out_prepare_r(__kfifo, __sgl, __nents, __len, __recsize) : \ - __kfifo_dma_out_prepare(__kfifo, __sgl, __nents, __len); \ + __kfifo_dma_out_prepare_r(__kfifo, __sgl, __nents, __len, __recsize, \ + dma) : \ + __kfifo_dma_out_prepare(__kfifo, __sgl, __nents, __len, dma); \ }) +#define kfifo_dma_out_prepare(fifo, sgl, nents, len) \ + kfifo_dma_out_prepare_mapped(fifo, sgl, nents, len, DMA_MAPPING_ERROR) + /** * kfifo_dma_out_finish - finish a DMA OUT operation * @fifo: address of the fifo to be used @@ -905,10 +916,10 @@ extern int __kfifo_to_user(struct __kfifo *fifo, void __user *to, unsigned long len, unsigned int *copied); extern unsigned int __kfifo_dma_in_prepare(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len); + struct scatterlist *sgl, int nents, unsigned int len, dma_addr_t dma); extern unsigned int __kfifo_dma_out_prepare(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len); + struct scatterlist *sgl, int nents, unsigned int len, dma_addr_t dma); extern unsigned int __kfifo_out_peek(struct __kfifo *fifo, void *buf, unsigned int len); @@ -930,13 +941,15 @@ extern int __kfifo_to_user_r(struct __kfifo *fifo, void __user *to, unsigned long len, unsigned int *copied, size_t recsize); extern unsigned int __kfifo_dma_in_prepare_r(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len, size_t recsize); + struct scatterlist *sgl, int nents, unsigned int len, size_t recsize, + dma_addr_t dma); extern void __kfifo_dma_in_finish_r(struct __kfifo *fifo, unsigned int len, size_t recsize); extern unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len, size_t recsize); + struct scatterlist *sgl, int nents, unsigned int len, size_t recsize, + dma_addr_t dma); extern unsigned int __kfifo_len_r(struct __kfifo *fifo, size_t recsize); diff --git a/lib/kfifo.c b/lib/kfifo.c index 3a249ce4f281..75ce9225548a 100644 --- a/lib/kfifo.c +++ b/lib/kfifo.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include @@ -307,7 +308,7 @@ EXPORT_SYMBOL(__kfifo_to_user); static unsigned int setup_sgl_buf(struct __kfifo *fifo, struct scatterlist *sgl, unsigned int data_offset, int nents, - unsigned int len) + unsigned int len, dma_addr_t dma) { const void *buf = fifo->data + data_offset; @@ -316,11 +317,16 @@ static unsigned int setup_sgl_buf(struct __kfifo *fifo, struct scatterlist *sgl, sg_set_buf(sgl, buf, len); + if (dma != DMA_MAPPING_ERROR) { + sg_dma_address(sgl) = dma + data_offset; + sg_dma_len(sgl) = len; + } + return 1; } static unsigned int setup_sgl(struct __kfifo *fifo, struct scatterlist *sgl, - int nents, unsigned int len, unsigned int off) + int nents, unsigned int len, unsigned int off, dma_addr_t dma) { unsigned int size = fifo->mask + 1; unsigned int esize = fifo->esize; @@ -335,14 +341,15 @@ static unsigned int setup_sgl(struct __kfifo *fifo, struct scatterlist *sgl, } len_to_end = min(len, size - off); - n = setup_sgl_buf(fifo, sgl, off, nents, len_to_end); - n += setup_sgl_buf(fifo, sgl + n, 0, nents - n, len - len_to_end); + n = setup_sgl_buf(fifo, sgl, off, nents, len_to_end, dma); + n += setup_sgl_buf(fifo, sgl + n, 0, nents - n, len - len_to_end, dma); return n; } unsigned int __kfifo_dma_in_prepare(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len) + struct scatterlist *sgl, int nents, unsigned int len, + dma_addr_t dma) { unsigned int l; @@ -350,12 +357,13 @@ unsigned int __kfifo_dma_in_prepare(struct __kfifo *fifo, if (len > l) len = l; - return setup_sgl(fifo, sgl, nents, len, fifo->in); + return setup_sgl(fifo, sgl, nents, len, fifo->in, dma); } EXPORT_SYMBOL(__kfifo_dma_in_prepare); unsigned int __kfifo_dma_out_prepare(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len) + struct scatterlist *sgl, int nents, unsigned int len, + dma_addr_t dma) { unsigned int l; @@ -363,7 +371,7 @@ unsigned int __kfifo_dma_out_prepare(struct __kfifo *fifo, if (len > l) len = l; - return setup_sgl(fifo, sgl, nents, len, fifo->out); + return setup_sgl(fifo, sgl, nents, len, fifo->out, dma); } EXPORT_SYMBOL(__kfifo_dma_out_prepare); @@ -547,7 +555,8 @@ int __kfifo_to_user_r(struct __kfifo *fifo, void __user *to, EXPORT_SYMBOL(__kfifo_to_user_r); unsigned int __kfifo_dma_in_prepare_r(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len, size_t recsize) + struct scatterlist *sgl, int nents, unsigned int len, size_t recsize, + dma_addr_t dma) { BUG_ON(!nents); @@ -556,7 +565,7 @@ unsigned int __kfifo_dma_in_prepare_r(struct __kfifo *fifo, if (len + recsize > kfifo_unused(fifo)) return 0; - return setup_sgl(fifo, sgl, nents, len, fifo->in + recsize); + return setup_sgl(fifo, sgl, nents, len, fifo->in + recsize, dma); } EXPORT_SYMBOL(__kfifo_dma_in_prepare_r); @@ -570,7 +579,8 @@ void __kfifo_dma_in_finish_r(struct __kfifo *fifo, EXPORT_SYMBOL(__kfifo_dma_in_finish_r); unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len, size_t recsize) + struct scatterlist *sgl, int nents, unsigned int len, size_t recsize, + dma_addr_t dma) { BUG_ON(!nents); @@ -579,7 +589,7 @@ unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo, if (len + recsize > fifo->in - fifo->out) return 0; - return setup_sgl(fifo, sgl, nents, len, fifo->out + recsize); + return setup_sgl(fifo, sgl, nents, len, fifo->out + recsize, dma); } EXPORT_SYMBOL(__kfifo_dma_out_prepare_r); -- cgit v1.2.3 From a88d970c8bb55dc20f319ce3e33c7ce0e9647480 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 17 Mar 2024 14:44:38 -0700 Subject: lib: Add one-byte emulation function Architectures are required to provide four-byte cmpxchg() and 64-bit architectures are additionally required to provide eight-byte cmpxchg(). However, there are cases where one-byte cmpxchg() would be extremely useful. Therefore, provide cmpxchg_emu_u8() that emulates one-byte cmpxchg() in terms of four-byte cmpxchg(). Note that this emulations is fully ordered, and can (for example) cause one-byte cmpxchg_relaxed() to incur the overhead of full ordering. If this causes problems for a given architecture, that architecture is free to provide its own lighter-weight primitives. [ paulmck: Apply Marco Elver feedback. ] [ paulmck: Apply kernel test robot feedback. ] [ paulmck: Drop two-byte support per Arnd Bergmann feedback. ] Link: https://lore.kernel.org/all/0733eb10-5e7a-4450-9b8a-527b97c842ff@paulmck-laptop/ Signed-off-by: Paul E. McKenney Acked-by: Marco Elver Cc: Andrew Morton Cc: Thomas Gleixner Cc: "Peter Zijlstra (Intel)" Cc: Douglas Anderson Cc: Petr Mladek Cc: Arnd Bergmann Cc: --- arch/Kconfig | 3 +++ include/linux/cmpxchg-emu.h | 15 +++++++++++++++ lib/Makefile | 1 + lib/cmpxchg-emu.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 64 insertions(+) create mode 100644 include/linux/cmpxchg-emu.h create mode 100644 lib/cmpxchg-emu.c (limited to 'lib') diff --git a/arch/Kconfig b/arch/Kconfig index 9f066785bb71..284663392eef 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1609,4 +1609,7 @@ config CC_HAS_SANE_FUNCTION_ALIGNMENT # strict alignment always, even with -falign-functions. def_bool CC_HAS_MIN_FUNCTION_ALIGNMENT || CC_IS_CLANG +config ARCH_NEED_CMPXCHG_1_EMU + bool + endmenu diff --git a/include/linux/cmpxchg-emu.h b/include/linux/cmpxchg-emu.h new file mode 100644 index 000000000000..998deec67740 --- /dev/null +++ b/include/linux/cmpxchg-emu.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Emulated 1-byte and 2-byte cmpxchg operations for architectures + * lacking direct support for these sizes. These are implemented in terms + * of 4-byte cmpxchg operations. + * + * Copyright (C) 2024 Paul E. McKenney. + */ + +#ifndef __LINUX_CMPXCHG_EMU_H +#define __LINUX_CMPXCHG_EMU_H + +uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new); + +#endif /* __LINUX_CMPXCHG_EMU_H */ diff --git a/lib/Makefile b/lib/Makefile index ffc6b2341b45..cc3d52fdb477 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -236,6 +236,7 @@ obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o lib-$(CONFIG_GENERIC_BUG) += bug.o obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o +obj-$(CONFIG_ARCH_NEED_CMPXCHG_1_EMU) += cmpxchg-emu.o obj-$(CONFIG_DYNAMIC_DEBUG_CORE) += dynamic_debug.o #ensure exported functions have prototypes diff --git a/lib/cmpxchg-emu.c b/lib/cmpxchg-emu.c new file mode 100644 index 000000000000..27f6f97cb60d --- /dev/null +++ b/lib/cmpxchg-emu.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Emulated 1-byte cmpxchg operation for architectures lacking direct + * support for this size. This is implemented in terms of 4-byte cmpxchg + * operations. + * + * Copyright (C) 2024 Paul E. McKenney. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +union u8_32 { + u8 b[4]; + u32 w; +}; + +/* Emulate one-byte cmpxchg() in terms of 4-byte cmpxchg. */ +uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new) +{ + u32 *p32 = (u32 *)(((uintptr_t)p) & ~0x3); + int i = ((uintptr_t)p) & 0x3; + union u8_32 old32; + union u8_32 new32; + u32 ret; + + ret = READ_ONCE(*p32); + do { + old32.w = ret; + if (old32.b[i] != old) + return old32.b[i]; + new32.w = old32.w; + new32.b[i] = new; + instrument_atomic_read_write(p, 1); + ret = data_race(cmpxchg(p32, old32.w, new32.w)); // Overridden above. + } while (ret != old32.w); + return old; +} +EXPORT_SYMBOL_GPL(cmpxchg_emu_u8); -- cgit v1.2.3 From d7037381d00286aa4beb631c401da761ee564c94 Mon Sep 17 00:00:00 2001 From: Bitao Hu Date: Thu, 11 Apr 2024 15:41:33 +0800 Subject: watchdog/softlockup: Low-overhead detection of interrupt storm The following softlockup is caused by interrupt storm, but it cannot be identified from the call tree. Because the call tree is just a snapshot and doesn't fully capture the behavior of the CPU during the soft lockup. watchdog: BUG: soft lockup - CPU#28 stuck for 23s! [fio:83921] ... Call trace: __do_softirq+0xa0/0x37c __irq_exit_rcu+0x108/0x140 irq_exit+0x14/0x20 __handle_domain_irq+0x84/0xe0 gic_handle_irq+0x80/0x108 el0_irq_naked+0x50/0x58 Therefore, it is necessary to report CPU utilization during the softlockup_threshold period (report once every sample_period, for a total of 5 reportings), like this: watchdog: BUG: soft lockup - CPU#28 stuck for 23s! [fio:83921] CPU#28 Utilization every 4s during lockup: #1: 0% system, 0% softirq, 100% hardirq, 0% idle #2: 0% system, 0% softirq, 100% hardirq, 0% idle #3: 0% system, 0% softirq, 100% hardirq, 0% idle #4: 0% system, 0% softirq, 100% hardirq, 0% idle #5: 0% system, 0% softirq, 100% hardirq, 0% idle ... This is helpful in determining whether an interrupt storm has occurred or in identifying the cause of the softlockup. The criteria for determination are as follows: a. If the hardirq utilization is high, then interrupt storm should be considered and the root cause cannot be determined from the call tree. b. If the softirq utilization is high, then the call might not necessarily point at the root cause. c. If the system utilization is high, then analyzing the root cause from the call tree is possible in most cases. The mechanism requires a considerable amount of global storage space when configured for the maximum number of CPUs. Therefore, adding a SOFTLOCKUP_DETECTOR_INTR_STORM Kconfig knob that defaults to "yes" if the max number of CPUs is <= 128. Signed-off-by: Bitao Hu Signed-off-by: Thomas Gleixner Reviewed-by: Douglas Anderson Reviewed-by: Liu Song Link: https://lore.kernel.org/r/20240411074134.30922-5-yaoma@linux.alibaba.com --- kernel/watchdog.c | 99 ++++++++++++++++++++++++++++++++++++++++++++++++++++++- lib/Kconfig.debug | 14 ++++++++ 2 files changed, 112 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/kernel/watchdog.c b/kernel/watchdog.c index d7b2125503af..ef8ebd31fdab 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -16,6 +16,8 @@ #include #include #include +#include +#include #include #include #include @@ -35,6 +37,8 @@ static DEFINE_MUTEX(watchdog_mutex); # define WATCHDOG_HARDLOCKUP_DEFAULT 0 #endif +#define NUM_SAMPLE_PERIODS 5 + unsigned long __read_mostly watchdog_enabled; int __read_mostly watchdog_user_enabled = 1; static int __read_mostly watchdog_hardlockup_user_enabled = WATCHDOG_HARDLOCKUP_DEFAULT; @@ -333,6 +337,96 @@ __setup("watchdog_thresh=", watchdog_thresh_setup); static void __lockup_detector_cleanup(void); +#ifdef CONFIG_SOFTLOCKUP_DETECTOR_INTR_STORM +enum stats_per_group { + STATS_SYSTEM, + STATS_SOFTIRQ, + STATS_HARDIRQ, + STATS_IDLE, + NUM_STATS_PER_GROUP, +}; + +static const enum cpu_usage_stat tracked_stats[NUM_STATS_PER_GROUP] = { + CPUTIME_SYSTEM, + CPUTIME_SOFTIRQ, + CPUTIME_IRQ, + CPUTIME_IDLE, +}; + +static DEFINE_PER_CPU(u16, cpustat_old[NUM_STATS_PER_GROUP]); +static DEFINE_PER_CPU(u8, cpustat_util[NUM_SAMPLE_PERIODS][NUM_STATS_PER_GROUP]); +static DEFINE_PER_CPU(u8, cpustat_tail); + +/* + * We don't need nanosecond resolution. A granularity of 16ms is + * sufficient for our precision, allowing us to use u16 to store + * cpustats, which will roll over roughly every ~1000 seconds. + * 2^24 ~= 16 * 10^6 + */ +static u16 get_16bit_precision(u64 data_ns) +{ + return data_ns >> 24LL; /* 2^24ns ~= 16.8ms */ +} + +static void update_cpustat(void) +{ + int i; + u8 util; + u16 old_stat, new_stat; + struct kernel_cpustat kcpustat; + u64 *cpustat = kcpustat.cpustat; + u8 tail = __this_cpu_read(cpustat_tail); + u16 sample_period_16 = get_16bit_precision(sample_period); + + kcpustat_cpu_fetch(&kcpustat, smp_processor_id()); + + for (i = 0; i < NUM_STATS_PER_GROUP; i++) { + old_stat = __this_cpu_read(cpustat_old[i]); + new_stat = get_16bit_precision(cpustat[tracked_stats[i]]); + util = DIV_ROUND_UP(100 * (new_stat - old_stat), sample_period_16); + __this_cpu_write(cpustat_util[tail][i], util); + __this_cpu_write(cpustat_old[i], new_stat); + } + + __this_cpu_write(cpustat_tail, (tail + 1) % NUM_SAMPLE_PERIODS); +} + +static void print_cpustat(void) +{ + int i, group; + u8 tail = __this_cpu_read(cpustat_tail); + u64 sample_period_second = sample_period; + + do_div(sample_period_second, NSEC_PER_SEC); + + /* + * Outputting the "watchdog" prefix on every line is redundant and not + * concise, and the original alarm information is sufficient for + * positioning in logs, hence here printk() is used instead of pr_crit(). + */ + printk(KERN_CRIT "CPU#%d Utilization every %llus during lockup:\n", + smp_processor_id(), sample_period_second); + + for (i = 0; i < NUM_SAMPLE_PERIODS; i++) { + group = (tail + i) % NUM_SAMPLE_PERIODS; + printk(KERN_CRIT "\t#%d: %3u%% system,\t%3u%% softirq,\t" + "%3u%% hardirq,\t%3u%% idle\n", i + 1, + __this_cpu_read(cpustat_util[group][STATS_SYSTEM]), + __this_cpu_read(cpustat_util[group][STATS_SOFTIRQ]), + __this_cpu_read(cpustat_util[group][STATS_HARDIRQ]), + __this_cpu_read(cpustat_util[group][STATS_IDLE])); + } +} + +static void report_cpu_status(void) +{ + print_cpustat(); +} +#else +static inline void update_cpustat(void) { } +static inline void report_cpu_status(void) { } +#endif + /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- * lockups can have false positives under extreme conditions. So we generally @@ -364,7 +458,7 @@ static void set_sample_period(void) * and hard thresholds) to increment before the * hardlockup detector generates a warning */ - sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / 5); + sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / NUM_SAMPLE_PERIODS); watchdog_update_hrtimer_threshold(sample_period); } @@ -504,6 +598,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) */ period_ts = READ_ONCE(*this_cpu_ptr(&watchdog_report_ts)); + update_cpustat(); + /* Reset the interval when touched by known problematic code. */ if (period_ts == SOFTLOCKUP_DELAY_REPORT) { if (unlikely(__this_cpu_read(softlockup_touch_sync))) { @@ -539,6 +635,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); + report_cpu_status(); print_modules(); print_irqtrace_events(current); if (regs) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c63a5fbf1f1c..1f0ce712a671 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1029,6 +1029,20 @@ config SOFTLOCKUP_DETECTOR chance to run. The current stack trace is displayed upon detection and the system will stay locked up. +config SOFTLOCKUP_DETECTOR_INTR_STORM + bool "Detect Interrupt Storm in Soft Lockups" + depends on SOFTLOCKUP_DETECTOR && IRQ_TIME_ACCOUNTING + select GENERIC_IRQ_STAT_SNAPSHOT + default y if NR_CPUS <= 128 + help + Say Y here to enable the kernel to detect interrupt storm + during "soft lockups". + + "soft lockups" can be caused by a variety of reasons. If one is + caused by an interrupt storm, then the storming interrupts will not + be on the callstack. To detect this case, it is necessary to report + the CPU stats and the interrupt counts during the "soft lockups". + config BOOTPARAM_SOFTLOCKUP_PANIC bool "Panic (Reboot) On Soft Lockups" depends on SOFTLOCKUP_DETECTOR -- cgit v1.2.3 From 4ba67ef3a1fbb7d8dc5f00de9b93a583d05b38cc Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 11 Apr 2024 12:22:32 -0700 Subject: net: dqs: make struct dql more cache efficient With the previous change, struct dqs->stall_thrs will be in the hot path (at queue side), even if DQS is disabled. The other fields accessed in this function (last_obj_cnt and num_queued) are in the first cache line, let's move this field (stall_thrs) to the very first cache line, since there is a hole there. This does not change the structure size, since it moves an short (2 bytes) to 4-bytes whole in the first cache line. This is the new structure format now: struct dql { unsigned int num_queued; unsigned int last_obj_cnt; ... short unsigned int stall_thrs; /* XXX 2 bytes hole, try to pack */ ... /* --- cacheline 1 boundary (64 bytes) --- */ ... /* Longest stall detected, reported to user */ short unsigned int stall_max; /* XXX 2 bytes hole, try to pack */ }; Also, read the stall_thrs (now in the very first cache line) earlier, together with dql->num_queued (also in the first cache line). Suggested-by: Jakub Kicinski Suggested-by: Eric Dumazet Signed-off-by: Breno Leitao Link: https://lore.kernel.org/r/20240411192241.2498631-5-leitao@debian.org Signed-off-by: Jakub Kicinski --- include/linux/dynamic_queue_limits.h | 5 +++-- lib/dynamic_queue_limits.c | 13 +++++++++---- 2 files changed, 12 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h index 869afb800ea1..281298e77a15 100644 --- a/include/linux/dynamic_queue_limits.h +++ b/include/linux/dynamic_queue_limits.h @@ -50,6 +50,9 @@ struct dql { unsigned int adj_limit; /* limit + num_completed */ unsigned int last_obj_cnt; /* Count at last queuing */ + /* Stall threshold (in jiffies), defined by user */ + unsigned short stall_thrs; + unsigned long history_head; /* top 58 bits of jiffies */ /* stall entries, a bit per entry */ unsigned long history[DQL_HIST_LEN]; @@ -71,8 +74,6 @@ struct dql { unsigned int min_limit; /* Minimum limit */ unsigned int slack_hold_time; /* Time to measure slack */ - /* Stall threshold (in jiffies), defined by user */ - unsigned short stall_thrs; /* Longest stall detected, reported to user */ unsigned short stall_max; unsigned long last_reap; /* Last reap (in jiffies) */ diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c index a1389db1c30a..e49deddd3de9 100644 --- a/lib/dynamic_queue_limits.c +++ b/lib/dynamic_queue_limits.c @@ -15,12 +15,10 @@ #define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0) #define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0) -static void dql_check_stall(struct dql *dql) +static void dql_check_stall(struct dql *dql, unsigned short stall_thrs) { - unsigned short stall_thrs; unsigned long now; - stall_thrs = READ_ONCE(dql->stall_thrs); if (!stall_thrs) return; @@ -86,9 +84,16 @@ void dql_completed(struct dql *dql, unsigned int count) { unsigned int inprogress, prev_inprogress, limit; unsigned int ovlimit, completed, num_queued; + unsigned short stall_thrs; bool all_prev_completed; num_queued = READ_ONCE(dql->num_queued); + /* Read stall_thrs in advance since it belongs to the same (first) + * cache line as ->num_queued. This way, dql_check_stall() does not + * need to touch the first cache line again later, reducing the window + * of possible false sharing. + */ + stall_thrs = READ_ONCE(dql->stall_thrs); /* Can't complete more than what's in queue */ BUG_ON(count > num_queued - dql->num_completed); @@ -178,7 +183,7 @@ void dql_completed(struct dql *dql, unsigned int count) dql->num_completed = completed; dql->prev_num_queued = num_queued; - dql_check_stall(dql); + dql_check_stall(dql, stall_thrs); } EXPORT_SYMBOL(dql_completed); -- cgit v1.2.3 From dac045fc9fa653e250f991ea8350b32cfec690d2 Mon Sep 17 00:00:00 2001 From: Chen Pei Date: Mon, 15 Apr 2024 16:19:28 +0800 Subject: bpf, tests: Fix typos in comments Currently, there are two comments with same name "64-bit ATOMIC magnitudes", the second one should be "32-bit ATOMIC magnitudes" based on the context. Signed-off-by: Chen Pei Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20240415081928.17440-1-cp0613@linux.alibaba.com --- lib/test_bpf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 569e6d2dc55c..207ff87194db 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -13431,7 +13431,7 @@ static struct bpf_test tests[] = { .stack_depth = 8, .nr_testruns = NR_PATTERN_RUNS, }, - /* 64-bit atomic magnitudes */ + /* 32-bit atomic magnitudes */ { "ATOMIC_W_ADD: all operand magnitudes", { }, -- cgit v1.2.3 From 9259a4721699947ceb397037991c0e4acc496b21 Mon Sep 17 00:00:00 2001 From: Ivan Orlov Date: Thu, 18 Apr 2024 00:30:33 +0100 Subject: string_kunit: Add test cases for str*cmp functions Currently, str*cmp functions (strcmp, strncmp, strcasecmp and strncasecmp) are not covered with tests. Extend the `string_kunit.c` test by adding the test cases for them. This patch adds 8 more test cases: 1) strcmp test 2) strcmp test on long strings (2048 chars) 3) strncmp test 4) strncmp test on long strings (2048 chars) 5) strcasecmp test 6) strcasecmp test on long strings 7) strncasecmp test 8) strncasecmp test on long strings These test cases aim at covering as many edge cases as possible, including the tests on empty strings, situations when the different symbol is placed at the end of one of the strings, etc. Signed-off-by: Ivan Orlov Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20240417233033.717596-1-ivan.orlov0322@gmail.com Signed-off-by: Kees Cook --- lib/string_kunit.c | 155 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 155 insertions(+) (limited to 'lib') diff --git a/lib/string_kunit.c b/lib/string_kunit.c index eabf025cf77c..dd19bd7748aa 100644 --- a/lib/string_kunit.c +++ b/lib/string_kunit.c @@ -11,6 +11,12 @@ #include #include +#define STRCMP_LARGE_BUF_LEN 2048 +#define STRCMP_CHANGE_POINT 1337 +#define STRCMP_TEST_EXPECT_EQUAL(test, fn, ...) KUNIT_EXPECT_EQ(test, fn(__VA_ARGS__), 0) +#define STRCMP_TEST_EXPECT_LOWER(test, fn, ...) KUNIT_EXPECT_LT(test, fn(__VA_ARGS__), 0) +#define STRCMP_TEST_EXPECT_GREATER(test, fn, ...) KUNIT_EXPECT_GT(test, fn(__VA_ARGS__), 0) + static void test_memset16(struct kunit *test) { unsigned i, j, k; @@ -179,6 +185,147 @@ static void test_strspn(struct kunit *test) } } +static char strcmp_buffer1[STRCMP_LARGE_BUF_LEN]; +static char strcmp_buffer2[STRCMP_LARGE_BUF_LEN]; + +static void strcmp_fill_buffers(char fill1, char fill2) +{ + memset(strcmp_buffer1, fill1, STRCMP_LARGE_BUF_LEN); + memset(strcmp_buffer2, fill2, STRCMP_LARGE_BUF_LEN); + strcmp_buffer1[STRCMP_LARGE_BUF_LEN - 1] = 0; + strcmp_buffer2[STRCMP_LARGE_BUF_LEN - 1] = 0; +} + +static void test_strcmp(struct kunit *test) +{ + /* Equal strings */ + STRCMP_TEST_EXPECT_EQUAL(test, strcmp, "Hello, Kernel!", "Hello, Kernel!"); + /* First string is lexicographically less than the second */ + STRCMP_TEST_EXPECT_LOWER(test, strcmp, "Hello, KUnit!", "Hello, Kernel!"); + /* First string is lexicographically larger than the second */ + STRCMP_TEST_EXPECT_GREATER(test, strcmp, "Hello, Kernel!", "Hello, KUnit!"); + /* Empty string is always lexicographically less than any non-empty string */ + STRCMP_TEST_EXPECT_LOWER(test, strcmp, "", "Non-empty string"); + /* Two empty strings should be equal */ + STRCMP_TEST_EXPECT_EQUAL(test, strcmp, "", ""); + /* Compare two strings which have only one char difference */ + STRCMP_TEST_EXPECT_LOWER(test, strcmp, "Abacaba", "Abadaba"); + /* Compare two strings which have the same prefix*/ + STRCMP_TEST_EXPECT_LOWER(test, strcmp, "Just a string", "Just a string and something else"); +} + +static void test_strcmp_long_strings(struct kunit *test) +{ + strcmp_fill_buffers('B', 'B'); + STRCMP_TEST_EXPECT_EQUAL(test, strcmp, strcmp_buffer1, strcmp_buffer2); + + strcmp_buffer1[STRCMP_CHANGE_POINT] = 'A'; + STRCMP_TEST_EXPECT_LOWER(test, strcmp, strcmp_buffer1, strcmp_buffer2); + + strcmp_buffer1[STRCMP_CHANGE_POINT] = 'C'; + STRCMP_TEST_EXPECT_GREATER(test, strcmp, strcmp_buffer1, strcmp_buffer2); +} + +static void test_strncmp(struct kunit *test) +{ + /* Equal strings */ + STRCMP_TEST_EXPECT_EQUAL(test, strncmp, "Hello, KUnit!", "Hello, KUnit!", 13); + /* First string is lexicographically less than the second */ + STRCMP_TEST_EXPECT_LOWER(test, strncmp, "Hello, KUnit!", "Hello, Kernel!", 13); + /* Result is always 'equal' when count = 0 */ + STRCMP_TEST_EXPECT_EQUAL(test, strncmp, "Hello, Kernel!", "Hello, KUnit!", 0); + /* Strings with common prefix are equal if count = length of prefix */ + STRCMP_TEST_EXPECT_EQUAL(test, strncmp, "Abacaba", "Abadaba", 3); + /* Strings with common prefix are not equal when count = length of prefix + 1 */ + STRCMP_TEST_EXPECT_LOWER(test, strncmp, "Abacaba", "Abadaba", 4); + /* If one string is a prefix of another, the shorter string is lexicographically smaller */ + STRCMP_TEST_EXPECT_LOWER(test, strncmp, "Just a string", "Just a string and something else", + strlen("Just a string and something else")); + /* + * If one string is a prefix of another, and we check first length + * of prefix chars, the result is 'equal' + */ + STRCMP_TEST_EXPECT_EQUAL(test, strncmp, "Just a string", "Just a string and something else", + strlen("Just a string")); +} + +static void test_strncmp_long_strings(struct kunit *test) +{ + strcmp_fill_buffers('B', 'B'); + STRCMP_TEST_EXPECT_EQUAL(test, strncmp, strcmp_buffer1, + strcmp_buffer2, STRCMP_LARGE_BUF_LEN); + + strcmp_buffer1[STRCMP_CHANGE_POINT] = 'A'; + STRCMP_TEST_EXPECT_LOWER(test, strncmp, strcmp_buffer1, + strcmp_buffer2, STRCMP_LARGE_BUF_LEN); + + strcmp_buffer1[STRCMP_CHANGE_POINT] = 'C'; + STRCMP_TEST_EXPECT_GREATER(test, strncmp, strcmp_buffer1, + strcmp_buffer2, STRCMP_LARGE_BUF_LEN); + /* the strings are equal up to STRCMP_CHANGE_POINT */ + STRCMP_TEST_EXPECT_EQUAL(test, strncmp, strcmp_buffer1, + strcmp_buffer2, STRCMP_CHANGE_POINT); + STRCMP_TEST_EXPECT_GREATER(test, strncmp, strcmp_buffer1, + strcmp_buffer2, STRCMP_CHANGE_POINT + 1); +} + +static void test_strcasecmp(struct kunit *test) +{ + /* Same strings in different case should be equal */ + STRCMP_TEST_EXPECT_EQUAL(test, strcasecmp, "Hello, Kernel!", "HeLLO, KErNeL!"); + /* Empty strings should be equal */ + STRCMP_TEST_EXPECT_EQUAL(test, strcasecmp, "", ""); + /* Despite ascii code for 'a' is larger than ascii code for 'B', 'a' < 'B' */ + STRCMP_TEST_EXPECT_LOWER(test, strcasecmp, "a", "B"); + STRCMP_TEST_EXPECT_GREATER(test, strcasecmp, "B", "a"); + /* Special symbols and numbers should be processed correctly */ + STRCMP_TEST_EXPECT_EQUAL(test, strcasecmp, "-+**.1230ghTTT~^", "-+**.1230Ghttt~^"); +} + +static void test_strcasecmp_long_strings(struct kunit *test) +{ + strcmp_fill_buffers('b', 'B'); + STRCMP_TEST_EXPECT_EQUAL(test, strcasecmp, strcmp_buffer1, strcmp_buffer2); + + strcmp_buffer1[STRCMP_CHANGE_POINT] = 'a'; + STRCMP_TEST_EXPECT_LOWER(test, strcasecmp, strcmp_buffer1, strcmp_buffer2); + + strcmp_buffer1[STRCMP_CHANGE_POINT] = 'C'; + STRCMP_TEST_EXPECT_GREATER(test, strcasecmp, strcmp_buffer1, strcmp_buffer2); +} + +static void test_strncasecmp(struct kunit *test) +{ + /* Same strings in different case should be equal */ + STRCMP_TEST_EXPECT_EQUAL(test, strncasecmp, "AbAcAbA", "Abacaba", strlen("Abacaba")); + /* strncasecmp should check 'count' chars only */ + STRCMP_TEST_EXPECT_EQUAL(test, strncasecmp, "AbaCaBa", "abaCaDa", 5); + STRCMP_TEST_EXPECT_LOWER(test, strncasecmp, "a", "B", 1); + STRCMP_TEST_EXPECT_GREATER(test, strncasecmp, "B", "a", 1); + /* Result is always 'equal' when count = 0 */ + STRCMP_TEST_EXPECT_EQUAL(test, strncasecmp, "Abacaba", "Not abacaba", 0); +} + +static void test_strncasecmp_long_strings(struct kunit *test) +{ + strcmp_fill_buffers('b', 'B'); + STRCMP_TEST_EXPECT_EQUAL(test, strncasecmp, strcmp_buffer1, + strcmp_buffer2, STRCMP_LARGE_BUF_LEN); + + strcmp_buffer1[STRCMP_CHANGE_POINT] = 'a'; + STRCMP_TEST_EXPECT_LOWER(test, strncasecmp, strcmp_buffer1, + strcmp_buffer2, STRCMP_LARGE_BUF_LEN); + + strcmp_buffer1[STRCMP_CHANGE_POINT] = 'C'; + STRCMP_TEST_EXPECT_GREATER(test, strncasecmp, strcmp_buffer1, + strcmp_buffer2, STRCMP_LARGE_BUF_LEN); + + STRCMP_TEST_EXPECT_EQUAL(test, strncasecmp, strcmp_buffer1, + strcmp_buffer2, STRCMP_CHANGE_POINT); + STRCMP_TEST_EXPECT_GREATER(test, strncasecmp, strcmp_buffer1, + strcmp_buffer2, STRCMP_CHANGE_POINT + 1); +} + static struct kunit_case string_test_cases[] = { KUNIT_CASE(test_memset16), KUNIT_CASE(test_memset32), @@ -186,6 +333,14 @@ static struct kunit_case string_test_cases[] = { KUNIT_CASE(test_strchr), KUNIT_CASE(test_strnchr), KUNIT_CASE(test_strspn), + KUNIT_CASE(test_strcmp), + KUNIT_CASE(test_strcmp_long_strings), + KUNIT_CASE(test_strncmp), + KUNIT_CASE(test_strncmp_long_strings), + KUNIT_CASE(test_strcasecmp), + KUNIT_CASE(test_strcasecmp_long_strings), + KUNIT_CASE(test_strncasecmp), + KUNIT_CASE(test_strncasecmp_long_strings), {} }; -- cgit v1.2.3 From b03442f761aae4bbb093a281ad2205bc346188f5 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 19 Apr 2024 07:01:50 -0700 Subject: string: Prepare to merge strscpy_kunit.c into string_kunit.c In preparation for moving the strscpy_kunit.c tests into string_kunit.c, rename "tc" to "strscpy_check" for better readability. Reviewed-by: Andy Shevchenko Tested-by: Ivan Orlov Link: https://lore.kernel.org/r/20240419140155.3028912-1-keescook@chromium.org Signed-off-by: Kees Cook --- lib/strscpy_kunit.c | 51 ++++++++++++++++++++++++++------------------------- 1 file changed, 26 insertions(+), 25 deletions(-) (limited to 'lib') diff --git a/lib/strscpy_kunit.c b/lib/strscpy_kunit.c index a6b6344354ed..b6d1d93a8883 100644 --- a/lib/strscpy_kunit.c +++ b/lib/strscpy_kunit.c @@ -8,22 +8,23 @@ #include #include -/* - * tc() - Run a specific test case. +/** + * strscpy_check() - Run a specific test case. + * @test: KUnit test context pointer * @src: Source string, argument to strscpy_pad() * @count: Size of destination buffer, argument to strscpy_pad() * @expected: Expected return value from call to strscpy_pad() - * @terminator: 1 if there should be a terminating null byte 0 otherwise. * @chars: Number of characters from the src string expected to be * written to the dst buffer. + * @terminator: 1 if there should be a terminating null byte 0 otherwise. * @pad: Number of pad characters expected (in the tail of dst buffer). * (@pad does not include the null terminator byte.) * * Calls strscpy_pad() and verifies the return value and state of the * destination buffer after the call returns. */ -static void tc(struct kunit *test, char *src, int count, int expected, - int chars, int terminator, int pad) +static void strscpy_check(struct kunit *test, char *src, int count, + int expected, int chars, int terminator, int pad) { int nr_bytes_poison; int max_expected; @@ -79,12 +80,12 @@ static void tc(struct kunit *test, char *src, int count, int expected, } } -static void strscpy_test(struct kunit *test) +static void test_strscpy(struct kunit *test) { char dest[8]; /* - * tc() uses a destination buffer of size 6 and needs at + * strscpy_check() uses a destination buffer of size 6 and needs at * least 2 characters spare (one for null and one to check for * overflow). This means we should only call tc() with * strings up to a maximum of 4 characters long and 'count' @@ -92,27 +93,27 @@ static void strscpy_test(struct kunit *test) * the buffer size in tc(). */ - /* tc(test, src, count, expected, chars, terminator, pad) */ - tc(test, "a", 0, -E2BIG, 0, 0, 0); - tc(test, "", 0, -E2BIG, 0, 0, 0); + /* strscpy_check(test, src, count, expected, chars, terminator, pad) */ + strscpy_check(test, "a", 0, -E2BIG, 0, 0, 0); + strscpy_check(test, "", 0, -E2BIG, 0, 0, 0); - tc(test, "a", 1, -E2BIG, 0, 1, 0); - tc(test, "", 1, 0, 0, 1, 0); + strscpy_check(test, "a", 1, -E2BIG, 0, 1, 0); + strscpy_check(test, "", 1, 0, 0, 1, 0); - tc(test, "ab", 2, -E2BIG, 1, 1, 0); - tc(test, "a", 2, 1, 1, 1, 0); - tc(test, "", 2, 0, 0, 1, 1); + strscpy_check(test, "ab", 2, -E2BIG, 1, 1, 0); + strscpy_check(test, "a", 2, 1, 1, 1, 0); + strscpy_check(test, "", 2, 0, 0, 1, 1); - tc(test, "abc", 3, -E2BIG, 2, 1, 0); - tc(test, "ab", 3, 2, 2, 1, 0); - tc(test, "a", 3, 1, 1, 1, 1); - tc(test, "", 3, 0, 0, 1, 2); + strscpy_check(test, "abc", 3, -E2BIG, 2, 1, 0); + strscpy_check(test, "ab", 3, 2, 2, 1, 0); + strscpy_check(test, "a", 3, 1, 1, 1, 1); + strscpy_check(test, "", 3, 0, 0, 1, 2); - tc(test, "abcd", 4, -E2BIG, 3, 1, 0); - tc(test, "abc", 4, 3, 3, 1, 0); - tc(test, "ab", 4, 2, 2, 1, 1); - tc(test, "a", 4, 1, 1, 1, 2); - tc(test, "", 4, 0, 0, 1, 3); + strscpy_check(test, "abcd", 4, -E2BIG, 3, 1, 0); + strscpy_check(test, "abc", 4, 3, 3, 1, 0); + strscpy_check(test, "ab", 4, 2, 2, 1, 1); + strscpy_check(test, "a", 4, 1, 1, 1, 2); + strscpy_check(test, "", 4, 0, 0, 1, 3); /* Compile-time-known source strings. */ KUNIT_EXPECT_EQ(test, strscpy(dest, "", ARRAY_SIZE(dest)), 0); @@ -127,7 +128,7 @@ static void strscpy_test(struct kunit *test) } static struct kunit_case strscpy_test_cases[] = { - KUNIT_CASE(strscpy_test), + KUNIT_CASE(test_strscpy), {} }; -- cgit v1.2.3 From bb8d9b742aa7c576d39b354612224b3c6bfd3cbc Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 19 Apr 2024 07:01:51 -0700 Subject: string: Merge strscpy KUnit tests into string_kunit.c Move the strscpy() tests into string_kunit.c. Remove the separate Kconfig and Makefile rule. Reviewed-by: Andy Shevchenko Tested-by: Ivan Orlov Link: https://lore.kernel.org/r/20240419140155.3028912-2-keescook@chromium.org Signed-off-by: Kees Cook --- MAINTAINERS | 1 - lib/Kconfig.debug | 5 -- lib/Makefile | 1 - lib/string_kunit.c | 120 +++++++++++++++++++++++++++++++++++++++++++ lib/strscpy_kunit.c | 143 ---------------------------------------------------- 5 files changed, 120 insertions(+), 150 deletions(-) delete mode 100644 lib/strscpy_kunit.c (limited to 'lib') diff --git a/MAINTAINERS b/MAINTAINERS index 7c121493f43d..17d079aa15ec 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8442,7 +8442,6 @@ F: include/linux/fortify-string.h F: lib/fortify_kunit.c F: lib/memcpy_kunit.c F: lib/strcat_kunit.c -F: lib/strscpy_kunit.c F: lib/test_fortify/* F: scripts/test_fortify.sh K: \b__NO_FORTIFY\b diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c63a5fbf1f1c..7ffb06eabcd1 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2763,11 +2763,6 @@ config STRCAT_KUNIT_TEST depends on KUNIT default KUNIT_ALL_TESTS -config STRSCPY_KUNIT_TEST - tristate "Test strscpy*() family of functions at runtime" if !KUNIT_ALL_TESTS - depends on KUNIT - default KUNIT_ALL_TESTS - config SIPHASH_KUNIT_TEST tristate "Perform selftest on siphash functions" if !KUNIT_ALL_TESTS depends on KUNIT diff --git a/lib/Makefile b/lib/Makefile index ffc6b2341b45..5f994b963d1a 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -404,7 +404,6 @@ CFLAGS_fortify_kunit.o += $(call cc-disable-warning, stringop-truncation) CFLAGS_fortify_kunit.o += $(DISABLE_STRUCTLEAK_PLUGIN) obj-$(CONFIG_FORTIFY_KUNIT_TEST) += fortify_kunit.o obj-$(CONFIG_STRCAT_KUNIT_TEST) += strcat_kunit.o -obj-$(CONFIG_STRSCPY_KUNIT_TEST) += strscpy_kunit.o obj-$(CONFIG_SIPHASH_KUNIT_TEST) += siphash_kunit.o obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o diff --git a/lib/string_kunit.c b/lib/string_kunit.c index dd19bd7748aa..4af04643f4c2 100644 --- a/lib/string_kunit.c +++ b/lib/string_kunit.c @@ -326,6 +326,125 @@ static void test_strncasecmp_long_strings(struct kunit *test) strcmp_buffer2, STRCMP_CHANGE_POINT + 1); } +/** + * strscpy_check() - Run a specific test case. + * @test: KUnit test context pointer + * @src: Source string, argument to strscpy_pad() + * @count: Size of destination buffer, argument to strscpy_pad() + * @expected: Expected return value from call to strscpy_pad() + * @chars: Number of characters from the src string expected to be + * written to the dst buffer. + * @terminator: 1 if there should be a terminating null byte 0 otherwise. + * @pad: Number of pad characters expected (in the tail of dst buffer). + * (@pad does not include the null terminator byte.) + * + * Calls strscpy_pad() and verifies the return value and state of the + * destination buffer after the call returns. + */ +static void strscpy_check(struct kunit *test, char *src, int count, + int expected, int chars, int terminator, int pad) +{ + int nr_bytes_poison; + int max_expected; + int max_count; + int written; + char buf[6]; + int index, i; + const char POISON = 'z'; + + KUNIT_ASSERT_TRUE_MSG(test, src != NULL, + "null source string not supported"); + + memset(buf, POISON, sizeof(buf)); + /* Future proofing test suite, validate args */ + max_count = sizeof(buf) - 2; /* Space for null and to verify overflow */ + max_expected = count - 1; /* Space for the null */ + + KUNIT_ASSERT_LE_MSG(test, count, max_count, + "count (%d) is too big (%d) ... aborting", count, max_count); + KUNIT_EXPECT_LE_MSG(test, expected, max_expected, + "expected (%d) is bigger than can possibly be returned (%d)", + expected, max_expected); + + written = strscpy_pad(buf, src, count); + KUNIT_ASSERT_EQ(test, written, expected); + + if (count && written == -E2BIG) { + KUNIT_ASSERT_EQ_MSG(test, 0, strncmp(buf, src, count - 1), + "buffer state invalid for -E2BIG"); + KUNIT_ASSERT_EQ_MSG(test, buf[count - 1], '\0', + "too big string is not null terminated correctly"); + } + + for (i = 0; i < chars; i++) + KUNIT_ASSERT_EQ_MSG(test, buf[i], src[i], + "buf[i]==%c != src[i]==%c", buf[i], src[i]); + + if (terminator) + KUNIT_ASSERT_EQ_MSG(test, buf[count - 1], '\0', + "string is not null terminated correctly"); + + for (i = 0; i < pad; i++) { + index = chars + terminator + i; + KUNIT_ASSERT_EQ_MSG(test, buf[index], '\0', + "padding missing at index: %d", i); + } + + nr_bytes_poison = sizeof(buf) - chars - terminator - pad; + for (i = 0; i < nr_bytes_poison; i++) { + index = sizeof(buf) - 1 - i; /* Check from the end back */ + KUNIT_ASSERT_EQ_MSG(test, buf[index], POISON, + "poison value missing at index: %d", i); + } +} + +static void test_strscpy(struct kunit *test) +{ + char dest[8]; + + /* + * strscpy_check() uses a destination buffer of size 6 and needs at + * least 2 characters spare (one for null and one to check for + * overflow). This means we should only call tc() with + * strings up to a maximum of 4 characters long and 'count' + * should not exceed 4. To test with longer strings increase + * the buffer size in tc(). + */ + + /* strscpy_check(test, src, count, expected, chars, terminator, pad) */ + strscpy_check(test, "a", 0, -E2BIG, 0, 0, 0); + strscpy_check(test, "", 0, -E2BIG, 0, 0, 0); + + strscpy_check(test, "a", 1, -E2BIG, 0, 1, 0); + strscpy_check(test, "", 1, 0, 0, 1, 0); + + strscpy_check(test, "ab", 2, -E2BIG, 1, 1, 0); + strscpy_check(test, "a", 2, 1, 1, 1, 0); + strscpy_check(test, "", 2, 0, 0, 1, 1); + + strscpy_check(test, "abc", 3, -E2BIG, 2, 1, 0); + strscpy_check(test, "ab", 3, 2, 2, 1, 0); + strscpy_check(test, "a", 3, 1, 1, 1, 1); + strscpy_check(test, "", 3, 0, 0, 1, 2); + + strscpy_check(test, "abcd", 4, -E2BIG, 3, 1, 0); + strscpy_check(test, "abc", 4, 3, 3, 1, 0); + strscpy_check(test, "ab", 4, 2, 2, 1, 1); + strscpy_check(test, "a", 4, 1, 1, 1, 2); + strscpy_check(test, "", 4, 0, 0, 1, 3); + + /* Compile-time-known source strings. */ + KUNIT_EXPECT_EQ(test, strscpy(dest, "", ARRAY_SIZE(dest)), 0); + KUNIT_EXPECT_EQ(test, strscpy(dest, "", 3), 0); + KUNIT_EXPECT_EQ(test, strscpy(dest, "", 1), 0); + KUNIT_EXPECT_EQ(test, strscpy(dest, "", 0), -E2BIG); + KUNIT_EXPECT_EQ(test, strscpy(dest, "Fixed", ARRAY_SIZE(dest)), 5); + KUNIT_EXPECT_EQ(test, strscpy(dest, "Fixed", 3), -E2BIG); + KUNIT_EXPECT_EQ(test, strscpy(dest, "Fixed", 1), -E2BIG); + KUNIT_EXPECT_EQ(test, strscpy(dest, "Fixed", 0), -E2BIG); + KUNIT_EXPECT_EQ(test, strscpy(dest, "This is too long", ARRAY_SIZE(dest)), -E2BIG); +} + static struct kunit_case string_test_cases[] = { KUNIT_CASE(test_memset16), KUNIT_CASE(test_memset32), @@ -341,6 +460,7 @@ static struct kunit_case string_test_cases[] = { KUNIT_CASE(test_strcasecmp_long_strings), KUNIT_CASE(test_strncasecmp), KUNIT_CASE(test_strncasecmp_long_strings), + KUNIT_CASE(test_strscpy), {} }; diff --git a/lib/strscpy_kunit.c b/lib/strscpy_kunit.c deleted file mode 100644 index b6d1d93a8883..000000000000 --- a/lib/strscpy_kunit.c +++ /dev/null @@ -1,143 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * Kernel module for testing 'strscpy' family of functions. - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include - -/** - * strscpy_check() - Run a specific test case. - * @test: KUnit test context pointer - * @src: Source string, argument to strscpy_pad() - * @count: Size of destination buffer, argument to strscpy_pad() - * @expected: Expected return value from call to strscpy_pad() - * @chars: Number of characters from the src string expected to be - * written to the dst buffer. - * @terminator: 1 if there should be a terminating null byte 0 otherwise. - * @pad: Number of pad characters expected (in the tail of dst buffer). - * (@pad does not include the null terminator byte.) - * - * Calls strscpy_pad() and verifies the return value and state of the - * destination buffer after the call returns. - */ -static void strscpy_check(struct kunit *test, char *src, int count, - int expected, int chars, int terminator, int pad) -{ - int nr_bytes_poison; - int max_expected; - int max_count; - int written; - char buf[6]; - int index, i; - const char POISON = 'z'; - - KUNIT_ASSERT_TRUE_MSG(test, src != NULL, - "null source string not supported"); - - memset(buf, POISON, sizeof(buf)); - /* Future proofing test suite, validate args */ - max_count = sizeof(buf) - 2; /* Space for null and to verify overflow */ - max_expected = count - 1; /* Space for the null */ - - KUNIT_ASSERT_LE_MSG(test, count, max_count, - "count (%d) is too big (%d) ... aborting", count, max_count); - KUNIT_EXPECT_LE_MSG(test, expected, max_expected, - "expected (%d) is bigger than can possibly be returned (%d)", - expected, max_expected); - - written = strscpy_pad(buf, src, count); - KUNIT_ASSERT_EQ(test, written, expected); - - if (count && written == -E2BIG) { - KUNIT_ASSERT_EQ_MSG(test, 0, strncmp(buf, src, count - 1), - "buffer state invalid for -E2BIG"); - KUNIT_ASSERT_EQ_MSG(test, buf[count - 1], '\0', - "too big string is not null terminated correctly"); - } - - for (i = 0; i < chars; i++) - KUNIT_ASSERT_EQ_MSG(test, buf[i], src[i], - "buf[i]==%c != src[i]==%c", buf[i], src[i]); - - if (terminator) - KUNIT_ASSERT_EQ_MSG(test, buf[count - 1], '\0', - "string is not null terminated correctly"); - - for (i = 0; i < pad; i++) { - index = chars + terminator + i; - KUNIT_ASSERT_EQ_MSG(test, buf[index], '\0', - "padding missing at index: %d", i); - } - - nr_bytes_poison = sizeof(buf) - chars - terminator - pad; - for (i = 0; i < nr_bytes_poison; i++) { - index = sizeof(buf) - 1 - i; /* Check from the end back */ - KUNIT_ASSERT_EQ_MSG(test, buf[index], POISON, - "poison value missing at index: %d", i); - } -} - -static void test_strscpy(struct kunit *test) -{ - char dest[8]; - - /* - * strscpy_check() uses a destination buffer of size 6 and needs at - * least 2 characters spare (one for null and one to check for - * overflow). This means we should only call tc() with - * strings up to a maximum of 4 characters long and 'count' - * should not exceed 4. To test with longer strings increase - * the buffer size in tc(). - */ - - /* strscpy_check(test, src, count, expected, chars, terminator, pad) */ - strscpy_check(test, "a", 0, -E2BIG, 0, 0, 0); - strscpy_check(test, "", 0, -E2BIG, 0, 0, 0); - - strscpy_check(test, "a", 1, -E2BIG, 0, 1, 0); - strscpy_check(test, "", 1, 0, 0, 1, 0); - - strscpy_check(test, "ab", 2, -E2BIG, 1, 1, 0); - strscpy_check(test, "a", 2, 1, 1, 1, 0); - strscpy_check(test, "", 2, 0, 0, 1, 1); - - strscpy_check(test, "abc", 3, -E2BIG, 2, 1, 0); - strscpy_check(test, "ab", 3, 2, 2, 1, 0); - strscpy_check(test, "a", 3, 1, 1, 1, 1); - strscpy_check(test, "", 3, 0, 0, 1, 2); - - strscpy_check(test, "abcd", 4, -E2BIG, 3, 1, 0); - strscpy_check(test, "abc", 4, 3, 3, 1, 0); - strscpy_check(test, "ab", 4, 2, 2, 1, 1); - strscpy_check(test, "a", 4, 1, 1, 1, 2); - strscpy_check(test, "", 4, 0, 0, 1, 3); - - /* Compile-time-known source strings. */ - KUNIT_EXPECT_EQ(test, strscpy(dest, "", ARRAY_SIZE(dest)), 0); - KUNIT_EXPECT_EQ(test, strscpy(dest, "", 3), 0); - KUNIT_EXPECT_EQ(test, strscpy(dest, "", 1), 0); - KUNIT_EXPECT_EQ(test, strscpy(dest, "", 0), -E2BIG); - KUNIT_EXPECT_EQ(test, strscpy(dest, "Fixed", ARRAY_SIZE(dest)), 5); - KUNIT_EXPECT_EQ(test, strscpy(dest, "Fixed", 3), -E2BIG); - KUNIT_EXPECT_EQ(test, strscpy(dest, "Fixed", 1), -E2BIG); - KUNIT_EXPECT_EQ(test, strscpy(dest, "Fixed", 0), -E2BIG); - KUNIT_EXPECT_EQ(test, strscpy(dest, "This is too long", ARRAY_SIZE(dest)), -E2BIG); -} - -static struct kunit_case strscpy_test_cases[] = { - KUNIT_CASE(test_strscpy), - {} -}; - -static struct kunit_suite strscpy_test_suite = { - .name = "strscpy", - .test_cases = strscpy_test_cases, -}; - -kunit_test_suite(strscpy_test_suite); - -MODULE_AUTHOR("Tobin C. Harding "); -MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 6e4ef1429f3be236e145c6115b539acdbd2e299c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 19 Apr 2024 07:01:52 -0700 Subject: string: Prepare to merge strcat KUnit tests into string_kunit.c The test naming convention differs between string_kunit.c and strcat_kunit.c. Move "test" to the beginning of the function name. Reviewed-by: Andy Shevchenko Tested-by: Ivan Orlov Link: https://lore.kernel.org/r/20240419140155.3028912-3-keescook@chromium.org Signed-off-by: Kees Cook --- lib/strcat_kunit.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/lib/strcat_kunit.c b/lib/strcat_kunit.c index e21be95514af..ca09f7f0e6a2 100644 --- a/lib/strcat_kunit.c +++ b/lib/strcat_kunit.c @@ -10,7 +10,7 @@ static volatile int unconst; -static void strcat_test(struct kunit *test) +static void test_strcat(struct kunit *test) { char dest[8]; @@ -29,7 +29,7 @@ static void strcat_test(struct kunit *test) KUNIT_EXPECT_STREQ(test, dest, "fourAB"); } -static void strncat_test(struct kunit *test) +static void test_strncat(struct kunit *test) { char dest[8]; @@ -56,7 +56,7 @@ static void strncat_test(struct kunit *test) KUNIT_EXPECT_STREQ(test, dest, "fourAB"); } -static void strlcat_test(struct kunit *test) +static void test_strlcat(struct kunit *test) { char dest[8] = ""; int len = sizeof(dest) + unconst; @@ -88,9 +88,9 @@ static void strlcat_test(struct kunit *test) } static struct kunit_case strcat_test_cases[] = { - KUNIT_CASE(strcat_test), - KUNIT_CASE(strncat_test), - KUNIT_CASE(strlcat_test), + KUNIT_CASE(test_strcat), + KUNIT_CASE(test_strncat), + KUNIT_CASE(test_strlcat), {} }; -- cgit v1.2.3 From bd678f7d9b72ab8b6978dac92b841e46f4b935a3 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 19 Apr 2024 07:01:53 -0700 Subject: string: Merge strcat KUnit tests into string_kunit.c Move the strcat() tests into string_kunit.c. Remove the separate Kconfig and Makefile rule. Reviewed-by: Andy Shevchenko Tested-by: Ivan Orlov Link: https://lore.kernel.org/r/20240419140155.3028912-4-keescook@chromium.org Signed-off-by: Kees Cook --- MAINTAINERS | 1 - lib/Kconfig.debug | 5 --- lib/Makefile | 1 - lib/strcat_kunit.c | 104 ----------------------------------------------------- lib/string_kunit.c | 82 ++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 82 insertions(+), 111 deletions(-) delete mode 100644 lib/strcat_kunit.c (limited to 'lib') diff --git a/MAINTAINERS b/MAINTAINERS index 17d079aa15ec..8974511315c3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8441,7 +8441,6 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/har F: include/linux/fortify-string.h F: lib/fortify_kunit.c F: lib/memcpy_kunit.c -F: lib/strcat_kunit.c F: lib/test_fortify/* F: scripts/test_fortify.sh K: \b__NO_FORTIFY\b diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 7ffb06eabcd1..a384070c74bc 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2758,11 +2758,6 @@ config HW_BREAKPOINT_KUNIT_TEST If unsure, say N. -config STRCAT_KUNIT_TEST - tristate "Test strcat() family of functions at runtime" if !KUNIT_ALL_TESTS - depends on KUNIT - default KUNIT_ALL_TESTS - config SIPHASH_KUNIT_TEST tristate "Perform selftest on siphash functions" if !KUNIT_ALL_TESTS depends on KUNIT diff --git a/lib/Makefile b/lib/Makefile index 5f994b963d1a..b040ad5f8022 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -403,7 +403,6 @@ CFLAGS_fortify_kunit.o += $(call cc-disable-warning, stringop-overread) CFLAGS_fortify_kunit.o += $(call cc-disable-warning, stringop-truncation) CFLAGS_fortify_kunit.o += $(DISABLE_STRUCTLEAK_PLUGIN) obj-$(CONFIG_FORTIFY_KUNIT_TEST) += fortify_kunit.o -obj-$(CONFIG_STRCAT_KUNIT_TEST) += strcat_kunit.o obj-$(CONFIG_SIPHASH_KUNIT_TEST) += siphash_kunit.o obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o diff --git a/lib/strcat_kunit.c b/lib/strcat_kunit.c deleted file mode 100644 index ca09f7f0e6a2..000000000000 --- a/lib/strcat_kunit.c +++ /dev/null @@ -1,104 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Kernel module for testing 'strcat' family of functions. - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include - -static volatile int unconst; - -static void test_strcat(struct kunit *test) -{ - char dest[8]; - - /* Destination is terminated. */ - memset(dest, 0, sizeof(dest)); - KUNIT_EXPECT_EQ(test, strlen(dest), 0); - /* Empty copy does nothing. */ - KUNIT_EXPECT_TRUE(test, strcat(dest, "") == dest); - KUNIT_EXPECT_STREQ(test, dest, ""); - /* 4 characters copied in, stops at %NUL. */ - KUNIT_EXPECT_TRUE(test, strcat(dest, "four\000123") == dest); - KUNIT_EXPECT_STREQ(test, dest, "four"); - KUNIT_EXPECT_EQ(test, dest[5], '\0'); - /* 2 more characters copied in okay. */ - KUNIT_EXPECT_TRUE(test, strcat(dest, "AB") == dest); - KUNIT_EXPECT_STREQ(test, dest, "fourAB"); -} - -static void test_strncat(struct kunit *test) -{ - char dest[8]; - - /* Destination is terminated. */ - memset(dest, 0, sizeof(dest)); - KUNIT_EXPECT_EQ(test, strlen(dest), 0); - /* Empty copy of size 0 does nothing. */ - KUNIT_EXPECT_TRUE(test, strncat(dest, "", 0 + unconst) == dest); - KUNIT_EXPECT_STREQ(test, dest, ""); - /* Empty copy of size 1 does nothing too. */ - KUNIT_EXPECT_TRUE(test, strncat(dest, "", 1 + unconst) == dest); - KUNIT_EXPECT_STREQ(test, dest, ""); - /* Copy of max 0 characters should do nothing. */ - KUNIT_EXPECT_TRUE(test, strncat(dest, "asdf", 0 + unconst) == dest); - KUNIT_EXPECT_STREQ(test, dest, ""); - - /* 4 characters copied in, even if max is 8. */ - KUNIT_EXPECT_TRUE(test, strncat(dest, "four\000123", 8 + unconst) == dest); - KUNIT_EXPECT_STREQ(test, dest, "four"); - KUNIT_EXPECT_EQ(test, dest[5], '\0'); - KUNIT_EXPECT_EQ(test, dest[6], '\0'); - /* 2 characters copied in okay, 2 ignored. */ - KUNIT_EXPECT_TRUE(test, strncat(dest, "ABCD", 2 + unconst) == dest); - KUNIT_EXPECT_STREQ(test, dest, "fourAB"); -} - -static void test_strlcat(struct kunit *test) -{ - char dest[8] = ""; - int len = sizeof(dest) + unconst; - - /* Destination is terminated. */ - KUNIT_EXPECT_EQ(test, strlen(dest), 0); - /* Empty copy is size 0. */ - KUNIT_EXPECT_EQ(test, strlcat(dest, "", len), 0); - KUNIT_EXPECT_STREQ(test, dest, ""); - /* Size 1 should keep buffer terminated, report size of source only. */ - KUNIT_EXPECT_EQ(test, strlcat(dest, "four", 1 + unconst), 4); - KUNIT_EXPECT_STREQ(test, dest, ""); - - /* 4 characters copied in. */ - KUNIT_EXPECT_EQ(test, strlcat(dest, "four", len), 4); - KUNIT_EXPECT_STREQ(test, dest, "four"); - /* 2 characters copied in okay, gets to 6 total. */ - KUNIT_EXPECT_EQ(test, strlcat(dest, "AB", len), 6); - KUNIT_EXPECT_STREQ(test, dest, "fourAB"); - /* 2 characters ignored if max size (7) reached. */ - KUNIT_EXPECT_EQ(test, strlcat(dest, "CD", 7 + unconst), 8); - KUNIT_EXPECT_STREQ(test, dest, "fourAB"); - /* 1 of 2 characters skipped, now at true max size. */ - KUNIT_EXPECT_EQ(test, strlcat(dest, "EFG", len), 9); - KUNIT_EXPECT_STREQ(test, dest, "fourABE"); - /* Everything else ignored, now at full size. */ - KUNIT_EXPECT_EQ(test, strlcat(dest, "1234", len), 11); - KUNIT_EXPECT_STREQ(test, dest, "fourABE"); -} - -static struct kunit_case strcat_test_cases[] = { - KUNIT_CASE(test_strcat), - KUNIT_CASE(test_strncat), - KUNIT_CASE(test_strlcat), - {} -}; - -static struct kunit_suite strcat_test_suite = { - .name = "strcat", - .test_cases = strcat_test_cases, -}; - -kunit_test_suite(strcat_test_suite); - -MODULE_LICENSE("GPL"); diff --git a/lib/string_kunit.c b/lib/string_kunit.c index 4af04643f4c2..48752ed19d56 100644 --- a/lib/string_kunit.c +++ b/lib/string_kunit.c @@ -445,6 +445,85 @@ static void test_strscpy(struct kunit *test) KUNIT_EXPECT_EQ(test, strscpy(dest, "This is too long", ARRAY_SIZE(dest)), -E2BIG); } +static volatile int unconst; + +static void test_strcat(struct kunit *test) +{ + char dest[8]; + + /* Destination is terminated. */ + memset(dest, 0, sizeof(dest)); + KUNIT_EXPECT_EQ(test, strlen(dest), 0); + /* Empty copy does nothing. */ + KUNIT_EXPECT_TRUE(test, strcat(dest, "") == dest); + KUNIT_EXPECT_STREQ(test, dest, ""); + /* 4 characters copied in, stops at %NUL. */ + KUNIT_EXPECT_TRUE(test, strcat(dest, "four\000123") == dest); + KUNIT_EXPECT_STREQ(test, dest, "four"); + KUNIT_EXPECT_EQ(test, dest[5], '\0'); + /* 2 more characters copied in okay. */ + KUNIT_EXPECT_TRUE(test, strcat(dest, "AB") == dest); + KUNIT_EXPECT_STREQ(test, dest, "fourAB"); +} + +static void test_strncat(struct kunit *test) +{ + char dest[8]; + + /* Destination is terminated. */ + memset(dest, 0, sizeof(dest)); + KUNIT_EXPECT_EQ(test, strlen(dest), 0); + /* Empty copy of size 0 does nothing. */ + KUNIT_EXPECT_TRUE(test, strncat(dest, "", 0 + unconst) == dest); + KUNIT_EXPECT_STREQ(test, dest, ""); + /* Empty copy of size 1 does nothing too. */ + KUNIT_EXPECT_TRUE(test, strncat(dest, "", 1 + unconst) == dest); + KUNIT_EXPECT_STREQ(test, dest, ""); + /* Copy of max 0 characters should do nothing. */ + KUNIT_EXPECT_TRUE(test, strncat(dest, "asdf", 0 + unconst) == dest); + KUNIT_EXPECT_STREQ(test, dest, ""); + + /* 4 characters copied in, even if max is 8. */ + KUNIT_EXPECT_TRUE(test, strncat(dest, "four\000123", 8 + unconst) == dest); + KUNIT_EXPECT_STREQ(test, dest, "four"); + KUNIT_EXPECT_EQ(test, dest[5], '\0'); + KUNIT_EXPECT_EQ(test, dest[6], '\0'); + /* 2 characters copied in okay, 2 ignored. */ + KUNIT_EXPECT_TRUE(test, strncat(dest, "ABCD", 2 + unconst) == dest); + KUNIT_EXPECT_STREQ(test, dest, "fourAB"); +} + +static void test_strlcat(struct kunit *test) +{ + char dest[8] = ""; + int len = sizeof(dest) + unconst; + + /* Destination is terminated. */ + KUNIT_EXPECT_EQ(test, strlen(dest), 0); + /* Empty copy is size 0. */ + KUNIT_EXPECT_EQ(test, strlcat(dest, "", len), 0); + KUNIT_EXPECT_STREQ(test, dest, ""); + /* Size 1 should keep buffer terminated, report size of source only. */ + KUNIT_EXPECT_EQ(test, strlcat(dest, "four", 1 + unconst), 4); + KUNIT_EXPECT_STREQ(test, dest, ""); + + /* 4 characters copied in. */ + KUNIT_EXPECT_EQ(test, strlcat(dest, "four", len), 4); + KUNIT_EXPECT_STREQ(test, dest, "four"); + /* 2 characters copied in okay, gets to 6 total. */ + KUNIT_EXPECT_EQ(test, strlcat(dest, "AB", len), 6); + KUNIT_EXPECT_STREQ(test, dest, "fourAB"); + /* 2 characters ignored if max size (7) reached. */ + KUNIT_EXPECT_EQ(test, strlcat(dest, "CD", 7 + unconst), 8); + KUNIT_EXPECT_STREQ(test, dest, "fourAB"); + /* 1 of 2 characters skipped, now at true max size. */ + KUNIT_EXPECT_EQ(test, strlcat(dest, "EFG", len), 9); + KUNIT_EXPECT_STREQ(test, dest, "fourABE"); + /* Everything else ignored, now at full size. */ + KUNIT_EXPECT_EQ(test, strlcat(dest, "1234", len), 11); + KUNIT_EXPECT_STREQ(test, dest, "fourABE"); +} + static struct kunit_case string_test_cases[] = { KUNIT_CASE(test_memset16), KUNIT_CASE(test_memset32), @@ -461,6 +540,9 @@ static struct kunit_case string_test_cases[] = { KUNIT_CASE(test_strncasecmp), KUNIT_CASE(test_strncasecmp_long_strings), KUNIT_CASE(test_strscpy), + KUNIT_CASE(test_strcat), + KUNIT_CASE(test_strncat), + KUNIT_CASE(test_strlcat), {} }; -- cgit v1.2.3 From dde915c5cba1fe49e980efe72662d9bc2a6b7ffd Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 19 Apr 2024 07:01:54 -0700 Subject: string: Convert KUnit test names to standard convention The KUnit convention for test names is AREA_test_WHAT. Adjust the string test names to follow this pattern. Reviewed-by: Andy Shevchenko Tested-by: Ivan Orlov Link: https://lore.kernel.org/r/20240419140155.3028912-5-keescook@chromium.org Signed-off-by: Kees Cook --- lib/string_kunit.c | 72 +++++++++++++++++++++++++++--------------------------- 1 file changed, 36 insertions(+), 36 deletions(-) (limited to 'lib') diff --git a/lib/string_kunit.c b/lib/string_kunit.c index 48752ed19d56..de4eae91403f 100644 --- a/lib/string_kunit.c +++ b/lib/string_kunit.c @@ -17,7 +17,7 @@ #define STRCMP_TEST_EXPECT_LOWER(test, fn, ...) KUNIT_EXPECT_LT(test, fn(__VA_ARGS__), 0) #define STRCMP_TEST_EXPECT_GREATER(test, fn, ...) KUNIT_EXPECT_GT(test, fn(__VA_ARGS__), 0) -static void test_memset16(struct kunit *test) +static void string_test_memset16(struct kunit *test) { unsigned i, j, k; u16 v, *p; @@ -46,7 +46,7 @@ static void test_memset16(struct kunit *test) } } -static void test_memset32(struct kunit *test) +static void string_test_memset32(struct kunit *test) { unsigned i, j, k; u32 v, *p; @@ -75,7 +75,7 @@ static void test_memset32(struct kunit *test) } } -static void test_memset64(struct kunit *test) +static void string_test_memset64(struct kunit *test) { unsigned i, j, k; u64 v, *p; @@ -104,7 +104,7 @@ static void test_memset64(struct kunit *test) } } -static void test_strchr(struct kunit *test) +static void string_test_strchr(struct kunit *test) { const char *test_string = "abcdefghijkl"; const char *empty_string = ""; @@ -127,7 +127,7 @@ static void test_strchr(struct kunit *test) KUNIT_ASSERT_NULL(test, result); } -static void test_strnchr(struct kunit *test) +static void string_test_strnchr(struct kunit *test) { const char *test_string = "abcdefghijkl"; const char *empty_string = ""; @@ -160,7 +160,7 @@ static void test_strnchr(struct kunit *test) KUNIT_ASSERT_NULL(test, result); } -static void test_strspn(struct kunit *test) +static void string_test_strspn(struct kunit *test) { static const struct strspn_test { const char str[16]; @@ -196,7 +196,7 @@ static void strcmp_fill_buffers(char fill1, char fill2) strcmp_buffer2[STRCMP_LARGE_BUF_LEN - 1] = 0; } -static void test_strcmp(struct kunit *test) +static void string_test_strcmp(struct kunit *test) { /* Equal strings */ STRCMP_TEST_EXPECT_EQUAL(test, strcmp, "Hello, Kernel!", "Hello, Kernel!"); @@ -214,7 +214,7 @@ static void test_strcmp(struct kunit *test) STRCMP_TEST_EXPECT_LOWER(test, strcmp, "Just a string", "Just a string and something else"); } -static void test_strcmp_long_strings(struct kunit *test) +static void string_test_strcmp_long_strings(struct kunit *test) { strcmp_fill_buffers('B', 'B'); STRCMP_TEST_EXPECT_EQUAL(test, strcmp, strcmp_buffer1, strcmp_buffer2); @@ -226,7 +226,7 @@ static void test_strcmp_long_strings(struct kunit *test) STRCMP_TEST_EXPECT_GREATER(test, strcmp, strcmp_buffer1, strcmp_buffer2); } -static void test_strncmp(struct kunit *test) +static void string_test_strncmp(struct kunit *test) { /* Equal strings */ STRCMP_TEST_EXPECT_EQUAL(test, strncmp, "Hello, KUnit!", "Hello, KUnit!", 13); @@ -249,7 +249,7 @@ static void test_strncmp(struct kunit *test) strlen("Just a string")); } -static void test_strncmp_long_strings(struct kunit *test) +static void string_test_strncmp_long_strings(struct kunit *test) { strcmp_fill_buffers('B', 'B'); STRCMP_TEST_EXPECT_EQUAL(test, strncmp, strcmp_buffer1, @@ -269,7 +269,7 @@ static void test_strncmp_long_strings(struct kunit *test) strcmp_buffer2, STRCMP_CHANGE_POINT + 1); } -static void test_strcasecmp(struct kunit *test) +static void string_test_strcasecmp(struct kunit *test) { /* Same strings in different case should be equal */ STRCMP_TEST_EXPECT_EQUAL(test, strcasecmp, "Hello, Kernel!", "HeLLO, KErNeL!"); @@ -282,7 +282,7 @@ static void test_strcasecmp(struct kunit *test) STRCMP_TEST_EXPECT_EQUAL(test, strcasecmp, "-+**.1230ghTTT~^", "-+**.1230Ghttt~^"); } -static void test_strcasecmp_long_strings(struct kunit *test) +static void string_test_strcasecmp_long_strings(struct kunit *test) { strcmp_fill_buffers('b', 'B'); STRCMP_TEST_EXPECT_EQUAL(test, strcasecmp, strcmp_buffer1, strcmp_buffer2); @@ -294,7 +294,7 @@ static void test_strcasecmp_long_strings(struct kunit *test) STRCMP_TEST_EXPECT_GREATER(test, strcasecmp, strcmp_buffer1, strcmp_buffer2); } -static void test_strncasecmp(struct kunit *test) +static void string_test_strncasecmp(struct kunit *test) { /* Same strings in different case should be equal */ STRCMP_TEST_EXPECT_EQUAL(test, strncasecmp, "AbAcAbA", "Abacaba", strlen("Abacaba")); @@ -306,7 +306,7 @@ static void test_strncasecmp(struct kunit *test) STRCMP_TEST_EXPECT_EQUAL(test, strncasecmp, "Abacaba", "Not abacaba", 0); } -static void test_strncasecmp_long_strings(struct kunit *test) +static void string_test_strncasecmp_long_strings(struct kunit *test) { strcmp_fill_buffers('b', 'B'); STRCMP_TEST_EXPECT_EQUAL(test, strncasecmp, strcmp_buffer1, @@ -398,7 +398,7 @@ static void strscpy_check(struct kunit *test, char *src, int count, } } -static void test_strscpy(struct kunit *test) +static void string_test_strscpy(struct kunit *test) { char dest[8]; @@ -447,7 +447,7 @@ static void test_strscpy(struct kunit *test) static volatile int unconst; -static void test_strcat(struct kunit *test) +static void string_test_strcat(struct kunit *test) { char dest[8]; @@ -466,7 +466,7 @@ static void test_strcat(struct kunit *test) KUNIT_EXPECT_STREQ(test, dest, "fourAB"); } -static void test_strncat(struct kunit *test) +static void string_test_strncat(struct kunit *test) { char dest[8]; @@ -493,7 +493,7 @@ static void test_strncat(struct kunit *test) KUNIT_EXPECT_STREQ(test, dest, "fourAB"); } -static void test_strlcat(struct kunit *test) +static void string_test_strlcat(struct kunit *test) { char dest[8] = ""; int len = sizeof(dest) + unconst; @@ -525,24 +525,24 @@ static void test_strlcat(struct kunit *test) } static struct kunit_case string_test_cases[] = { - KUNIT_CASE(test_memset16), - KUNIT_CASE(test_memset32), - KUNIT_CASE(test_memset64), - KUNIT_CASE(test_strchr), - KUNIT_CASE(test_strnchr), - KUNIT_CASE(test_strspn), - KUNIT_CASE(test_strcmp), - KUNIT_CASE(test_strcmp_long_strings), - KUNIT_CASE(test_strncmp), - KUNIT_CASE(test_strncmp_long_strings), - KUNIT_CASE(test_strcasecmp), - KUNIT_CASE(test_strcasecmp_long_strings), - KUNIT_CASE(test_strncasecmp), - KUNIT_CASE(test_strncasecmp_long_strings), - KUNIT_CASE(test_strscpy), - KUNIT_CASE(test_strcat), - KUNIT_CASE(test_strncat), - KUNIT_CASE(test_strlcat), + KUNIT_CASE(string_test_memset16), + KUNIT_CASE(string_test_memset32), + KUNIT_CASE(string_test_memset64), + KUNIT_CASE(string_test_strchr), + KUNIT_CASE(string_test_strnchr), + KUNIT_CASE(string_test_strspn), + KUNIT_CASE(string_test_strcmp), + KUNIT_CASE(string_test_strcmp_long_strings), + KUNIT_CASE(string_test_strncmp), + KUNIT_CASE(string_test_strncmp_long_strings), + KUNIT_CASE(string_test_strcasecmp), + KUNIT_CASE(string_test_strcasecmp_long_strings), + KUNIT_CASE(string_test_strncasecmp), + KUNIT_CASE(string_test_strncasecmp_long_strings), + KUNIT_CASE(string_test_strscpy), + KUNIT_CASE(string_test_strcat), + KUNIT_CASE(string_test_strncat), + KUNIT_CASE(string_test_strlcat), {} }; -- cgit v1.2.3 From 20516d6e51dd9994afda8d556507cfbe7853384b Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 11 Apr 2024 13:46:14 -0300 Subject: x86: Stop using weak symbols for __iowrite32_copy() Start switching iomap_copy routines over to use #define and arch provided inline/macro functions instead of weak symbols. Inline functions allow more compiler optimization and this is often a driver hot path. x86 has the only weak implementation for __iowrite32_copy(), so replace it with a static inline containing the same single instruction inline assembly. The compiler will generate the "mov edx,ecx" in a more optimal way. Remove iomap_copy_64.S Link: https://lore.kernel.org/r/1-v3-1893cd8b9369+1925-mlx5_arm_wc_jgg@nvidia.com Acked-by: Arnd Bergmann Signed-off-by: Jason Gunthorpe --- arch/x86/include/asm/io.h | 17 +++++++++++++++++ arch/x86/lib/Makefile | 1 - arch/x86/lib/iomap_copy_64.S | 15 --------------- include/linux/io.h | 5 ++++- lib/iomap_copy.c | 6 +++--- 5 files changed, 24 insertions(+), 20 deletions(-) delete mode 100644 arch/x86/lib/iomap_copy_64.S (limited to 'lib') diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 294cd2a40818..4b99ed326b17 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -209,6 +209,23 @@ void memset_io(volatile void __iomem *, int, size_t); #define memcpy_toio memcpy_toio #define memset_io memset_io +#ifdef CONFIG_X86_64 +/* + * Commit 0f07496144c2 ("[PATCH] Add faster __iowrite32_copy routine for + * x86_64") says that circa 2006 rep movsl is noticeably faster than a copy + * loop. + */ +static inline void __iowrite32_copy(void __iomem *to, const void *from, + size_t count) +{ + asm volatile("rep ; movsl" + : "=&c"(count), "=&D"(to), "=&S"(from) + : "0"(count), "1"(to), "2"(from) + : "memory"); +} +#define __iowrite32_copy __iowrite32_copy +#endif + /* * ISA space is 'always mapped' on a typical x86 system, no need to * explicitly ioremap() it. The fact that the ISA IO space is mapped diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 6da73513f026..98583a9dbab3 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -53,7 +53,6 @@ ifneq ($(CONFIG_X86_CMPXCHG64),y) lib-y += atomic64_386_32.o endif else - obj-y += iomap_copy_64.o ifneq ($(CONFIG_GENERIC_CSUM),y) lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o endif diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S deleted file mode 100644 index 6ff2f56cb0f7..000000000000 --- a/arch/x86/lib/iomap_copy_64.S +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright 2006 PathScale, Inc. All Rights Reserved. - */ - -#include - -/* - * override generic version in lib/iomap_copy.c - */ -SYM_FUNC_START(__iowrite32_copy) - movl %edx,%ecx - rep movsl - RET -SYM_FUNC_END(__iowrite32_copy) diff --git a/include/linux/io.h b/include/linux/io.h index 235ba7d80a8f..ce86120ce9d5 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -16,7 +16,10 @@ struct device; struct resource; -__visible void __iowrite32_copy(void __iomem *to, const void *from, size_t count); +#ifndef __iowrite32_copy +void __iowrite32_copy(void __iomem *to, const void *from, size_t count); +#endif + void __ioread32_copy(void *to, const void __iomem *from, size_t count); void __iowrite64_copy(void __iomem *to, const void *from, size_t count); diff --git a/lib/iomap_copy.c b/lib/iomap_copy.c index 5de7c04e05ef..8ddcbb53507d 100644 --- a/lib/iomap_copy.c +++ b/lib/iomap_copy.c @@ -16,9 +16,8 @@ * time. Order of access is not guaranteed, nor is a memory barrier * performed afterwards. */ -void __attribute__((weak)) __iowrite32_copy(void __iomem *to, - const void *from, - size_t count) +#ifndef __iowrite32_copy +void __iowrite32_copy(void __iomem *to, const void *from, size_t count) { u32 __iomem *dst = to; const u32 *src = from; @@ -28,6 +27,7 @@ void __attribute__((weak)) __iowrite32_copy(void __iomem *to, __raw_writel(*src++, dst++); } EXPORT_SYMBOL_GPL(__iowrite32_copy); +#endif /** * __ioread32_copy - copy data from MMIO space, in 32-bit units -- cgit v1.2.3 From e7bc47b16622d1016b3b77bbdb20fb9e213045f2 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 11 Apr 2024 13:46:16 -0300 Subject: s390: Stop using weak symbols for __iowrite64_copy() Complete switching the __iowriteXX_copy() routines over to use #define and arch provided inline/macro functions instead of weak symbols. S390 has an implementation that simply calls another memcpy function. Inline this so the callers don't have to do two jumps. Link: https://lore.kernel.org/r/3-v3-1893cd8b9369+1925-mlx5_arm_wc_jgg@nvidia.com Acked-by: Niklas Schnelle Acked-by: Arnd Bergmann Signed-off-by: Jason Gunthorpe --- arch/s390/include/asm/io.h | 7 +++++++ arch/s390/pci/pci.c | 6 ------ include/linux/io.h | 3 +++ lib/iomap_copy.c | 7 +++---- 4 files changed, 13 insertions(+), 10 deletions(-) (limited to 'lib') diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index 00704fc8a54b..0fbc992d7a5e 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -81,6 +81,13 @@ static inline void __iowrite32_copy(void __iomem *to, const void *from, } #define __iowrite32_copy __iowrite32_copy +static inline void __iowrite64_copy(void __iomem *to, const void *from, + size_t count) +{ + zpci_memcpy_toio(to, from, count * 8); +} +#define __iowrite64_copy __iowrite64_copy + #endif /* CONFIG_PCI */ #include diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 26afde0d1ed3..0de0f6e405b5 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -250,12 +250,6 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res, return 0; } -/* combine single writes by using store-block insn */ -void __iowrite64_copy(void __iomem *to, const void *from, size_t count) -{ - zpci_memcpy_toio(to, from, count * 8); -} - void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, unsigned long prot) { diff --git a/include/linux/io.h b/include/linux/io.h index ce86120ce9d5..42e132808f00 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -21,7 +21,10 @@ void __iowrite32_copy(void __iomem *to, const void *from, size_t count); #endif void __ioread32_copy(void *to, const void __iomem *from, size_t count); + +#ifndef __iowrite64_copy void __iowrite64_copy(void __iomem *to, const void *from, size_t count); +#endif #ifdef CONFIG_MMU int ioremap_page_range(unsigned long addr, unsigned long end, diff --git a/lib/iomap_copy.c b/lib/iomap_copy.c index 8ddcbb53507d..2fd5712fb7c0 100644 --- a/lib/iomap_copy.c +++ b/lib/iomap_copy.c @@ -60,9 +60,8 @@ EXPORT_SYMBOL_GPL(__ioread32_copy); * time. Order of access is not guaranteed, nor is a memory barrier * performed afterwards. */ -void __attribute__((weak)) __iowrite64_copy(void __iomem *to, - const void *from, - size_t count) +#ifndef __iowrite64_copy +void __iowrite64_copy(void __iomem *to, const void *from, size_t count) { #ifdef CONFIG_64BIT u64 __iomem *dst = to; @@ -75,5 +74,5 @@ void __attribute__((weak)) __iowrite64_copy(void __iomem *to, __iowrite32_copy(to, from, count * 2); #endif } - EXPORT_SYMBOL_GPL(__iowrite64_copy); +#endif -- cgit v1.2.3 From 0efc5990bca540b8d438fda23db3a72efa733eb0 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 9 Apr 2024 19:31:50 -0700 Subject: string.h: Introduce memtostr() and memtostr_pad() Another ambiguous use of strncpy() is to copy from strings that may not be NUL-terminated. These cases depend on having the destination buffer be explicitly larger than the source buffer's maximum size, having the size of the copy exactly match the source buffer's maximum size, and for the destination buffer to get explicitly NUL terminated. This usually happens when parsing protocols or hardware character arrays that are not guaranteed to be NUL-terminated. The code pattern is effectively this: char dest[sizeof(src) + 1]; strncpy(dest, src, sizeof(src)); dest[sizeof(dest) - 1] = '\0'; In practice it usually looks like: struct from_hardware { ... char name[HW_NAME_SIZE] __nonstring; ... }; struct from_hardware *p = ...; char name[HW_NAME_SIZE + 1]; strncpy(name, p->name, HW_NAME_SIZE); name[NW_NAME_SIZE] = '\0'; This cannot be replaced with: strscpy(name, p->name, sizeof(name)); because p->name is smaller and not NUL-terminated, so FORTIFY will trigger when strnlen(p->name, sizeof(name)) is used. And it cannot be replaced with: strscpy(name, p->name, sizeof(p->name)); because then "name" may contain a 1 character early truncation of p->name. Provide an unambiguous interface for converting a maybe not-NUL-terminated string to a NUL-terminated string, with compile-time buffer size checking so that it can never fail at runtime: memtostr() and memtostr_pad(). Also add KUnit tests for both. Link: https://lore.kernel.org/r/20240410023155.2100422-1-keescook@chromium.org Signed-off-by: Kees Cook --- include/linux/string.h | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ lib/string_kunit.c | 26 ++++++++++++++++++++++++++ 2 files changed, 75 insertions(+) (limited to 'lib') diff --git a/include/linux/string.h b/include/linux/string.h index 9ba8b4597009..86aa6cd35167 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -422,6 +422,55 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, memcpy(dest, src, strnlen(src, min(_src_len, _dest_len))); \ } while (0) +/** + * memtostr - Copy a possibly non-NUL-term string to a NUL-term string + * @dest: Pointer to destination NUL-terminates string + * @src: Pointer to character array (likely marked as __nonstring) + * + * This is a replacement for strncpy() uses where the source is not + * a NUL-terminated string. + * + * Note that sizes of @dest and @src must be known at compile-time. + */ +#define memtostr(dest, src) do { \ + const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _src_len = __builtin_object_size(src, 1); \ + const size_t _src_chars = strnlen(src, _src_len); \ + const size_t _copy_len = min(_dest_len - 1, _src_chars); \ + \ + BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ + !__builtin_constant_p(_src_len) || \ + _dest_len == 0 || _dest_len == (size_t)-1 || \ + _src_len == 0 || _src_len == (size_t)-1); \ + memcpy(dest, src, _copy_len); \ + dest[_copy_len] = '\0'; \ +} while (0) + +/** + * memtostr_pad - Copy a possibly non-NUL-term string to a NUL-term string + * with NUL padding in the destination + * @dest: Pointer to destination NUL-terminates string + * @src: Pointer to character array (likely marked as __nonstring) + * + * This is a replacement for strncpy() uses where the source is not + * a NUL-terminated string. + * + * Note that sizes of @dest and @src must be known at compile-time. + */ +#define memtostr_pad(dest, src) do { \ + const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _src_len = __builtin_object_size(src, 1); \ + const size_t _src_chars = strnlen(src, _src_len); \ + const size_t _copy_len = min(_dest_len - 1, _src_chars); \ + \ + BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ + !__builtin_constant_p(_src_len) || \ + _dest_len == 0 || _dest_len == (size_t)-1 || \ + _src_len == 0 || _src_len == (size_t)-1); \ + memcpy(dest, src, _copy_len); \ + memset(&dest[_copy_len], 0, _dest_len - _copy_len); \ +} while (0) + /** * memset_after - Set a value after a struct member to the end of a struct * diff --git a/lib/string_kunit.c b/lib/string_kunit.c index de4eae91403f..fadad46c1b05 100644 --- a/lib/string_kunit.c +++ b/lib/string_kunit.c @@ -524,6 +524,31 @@ static void string_test_strlcat(struct kunit *test) KUNIT_EXPECT_STREQ(test, dest, "fourABE"); } +static void string_test_memtostr(struct kunit *test) +{ + char nonstring[7] = { 'a', 'b', 'c', 'd', 'e', 'f', 'g' }; + char nonstring_small[3] = { 'a', 'b', 'c' }; + char dest[sizeof(nonstring) + 1]; + + /* Copy in a non-NUL-terminated string into exactly right-sized dest. */ + KUNIT_EXPECT_EQ(test, sizeof(dest), sizeof(nonstring) + 1); + memset(dest, 'X', sizeof(dest)); + memtostr(dest, nonstring); + KUNIT_EXPECT_STREQ(test, dest, "abcdefg"); + memset(dest, 'X', sizeof(dest)); + memtostr(dest, nonstring_small); + KUNIT_EXPECT_STREQ(test, dest, "abc"); + KUNIT_EXPECT_EQ(test, dest[7], 'X'); + + memset(dest, 'X', sizeof(dest)); + memtostr_pad(dest, nonstring); + KUNIT_EXPECT_STREQ(test, dest, "abcdefg"); + memset(dest, 'X', sizeof(dest)); + memtostr_pad(dest, nonstring_small); + KUNIT_EXPECT_STREQ(test, dest, "abc"); + KUNIT_EXPECT_EQ(test, dest[7], '\0'); +} + static struct kunit_case string_test_cases[] = { KUNIT_CASE(string_test_memset16), KUNIT_CASE(string_test_memset32), @@ -543,6 +568,7 @@ static struct kunit_case string_test_cases[] = { KUNIT_CASE(string_test_strcat), KUNIT_CASE(string_test_strncat), KUNIT_CASE(string_test_strlcat), + KUNIT_CASE(string_test_memtostr), {} }; -- cgit v1.2.3 From c01c41e5009c04515d81a87f6278c413914920ce Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 24 Apr 2024 09:01:30 -0700 Subject: string_kunit: Move strtomem KUnit test to string_kunit.c It is more logical to have the strtomem() test in string_kunit.c instead of the memcpy() suite. Move it to live with memtostr(). Signed-off-by: Kees Cook --- lib/memcpy_kunit.c | 53 ----------------------------------------------------- lib/string_kunit.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 54 insertions(+), 53 deletions(-) (limited to 'lib') diff --git a/lib/memcpy_kunit.c b/lib/memcpy_kunit.c index fd16e6ce53d1..20ea9038c3ff 100644 --- a/lib/memcpy_kunit.c +++ b/lib/memcpy_kunit.c @@ -493,58 +493,6 @@ static void memmove_overlap_test(struct kunit *test) } } -static void strtomem_test(struct kunit *test) -{ - static const char input[sizeof(unsigned long)] = "hi"; - static const char truncate[] = "this is too long"; - struct { - unsigned long canary1; - unsigned char output[sizeof(unsigned long)] __nonstring; - unsigned long canary2; - } wrap; - - memset(&wrap, 0xFF, sizeof(wrap)); - KUNIT_EXPECT_EQ_MSG(test, wrap.canary1, ULONG_MAX, - "bad initial canary value"); - KUNIT_EXPECT_EQ_MSG(test, wrap.canary2, ULONG_MAX, - "bad initial canary value"); - - /* Check unpadded copy leaves surroundings untouched. */ - strtomem(wrap.output, input); - KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX); - KUNIT_EXPECT_EQ(test, wrap.output[0], input[0]); - KUNIT_EXPECT_EQ(test, wrap.output[1], input[1]); - for (size_t i = 2; i < sizeof(wrap.output); i++) - KUNIT_EXPECT_EQ(test, wrap.output[i], 0xFF); - KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX); - - /* Check truncated copy leaves surroundings untouched. */ - memset(&wrap, 0xFF, sizeof(wrap)); - strtomem(wrap.output, truncate); - KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX); - for (size_t i = 0; i < sizeof(wrap.output); i++) - KUNIT_EXPECT_EQ(test, wrap.output[i], truncate[i]); - KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX); - - /* Check padded copy leaves only string padded. */ - memset(&wrap, 0xFF, sizeof(wrap)); - strtomem_pad(wrap.output, input, 0xAA); - KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX); - KUNIT_EXPECT_EQ(test, wrap.output[0], input[0]); - KUNIT_EXPECT_EQ(test, wrap.output[1], input[1]); - for (size_t i = 2; i < sizeof(wrap.output); i++) - KUNIT_EXPECT_EQ(test, wrap.output[i], 0xAA); - KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX); - - /* Check truncated padded copy has no padding. */ - memset(&wrap, 0xFF, sizeof(wrap)); - strtomem(wrap.output, truncate); - KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX); - for (size_t i = 0; i < sizeof(wrap.output); i++) - KUNIT_EXPECT_EQ(test, wrap.output[i], truncate[i]); - KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX); -} - static struct kunit_case memcpy_test_cases[] = { KUNIT_CASE(memset_test), KUNIT_CASE(memcpy_test), @@ -552,7 +500,6 @@ static struct kunit_case memcpy_test_cases[] = { KUNIT_CASE_SLOW(memmove_test), KUNIT_CASE_SLOW(memmove_large_test), KUNIT_CASE_SLOW(memmove_overlap_test), - KUNIT_CASE(strtomem_test), {} }; diff --git a/lib/string_kunit.c b/lib/string_kunit.c index fadad46c1b05..2a812decf14b 100644 --- a/lib/string_kunit.c +++ b/lib/string_kunit.c @@ -524,6 +524,59 @@ static void string_test_strlcat(struct kunit *test) KUNIT_EXPECT_STREQ(test, dest, "fourABE"); } +static void string_test_strtomem(struct kunit *test) +{ + static const char input[sizeof(unsigned long)] = "hi"; + static const char truncate[] = "this is too long"; + struct { + unsigned long canary1; + unsigned char output[sizeof(unsigned long)] __nonstring; + unsigned long canary2; + } wrap; + + memset(&wrap, 0xFF, sizeof(wrap)); + KUNIT_EXPECT_EQ_MSG(test, wrap.canary1, ULONG_MAX, + "bad initial canary value"); + KUNIT_EXPECT_EQ_MSG(test, wrap.canary2, ULONG_MAX, + "bad initial canary value"); + + /* Check unpadded copy leaves surroundings untouched. */ + strtomem(wrap.output, input); + KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX); + KUNIT_EXPECT_EQ(test, wrap.output[0], input[0]); + KUNIT_EXPECT_EQ(test, wrap.output[1], input[1]); + for (size_t i = 2; i < sizeof(wrap.output); i++) + KUNIT_EXPECT_EQ(test, wrap.output[i], 0xFF); + KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX); + + /* Check truncated copy leaves surroundings untouched. */ + memset(&wrap, 0xFF, sizeof(wrap)); + strtomem(wrap.output, truncate); + KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX); + for (size_t i = 0; i < sizeof(wrap.output); i++) + KUNIT_EXPECT_EQ(test, wrap.output[i], truncate[i]); + KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX); + + /* Check padded copy leaves only string padded. */ + memset(&wrap, 0xFF, sizeof(wrap)); + strtomem_pad(wrap.output, input, 0xAA); + KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX); + KUNIT_EXPECT_EQ(test, wrap.output[0], input[0]); + KUNIT_EXPECT_EQ(test, wrap.output[1], input[1]); + for (size_t i = 2; i < sizeof(wrap.output); i++) + KUNIT_EXPECT_EQ(test, wrap.output[i], 0xAA); + KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX); + + /* Check truncated padded copy has no padding. */ + memset(&wrap, 0xFF, sizeof(wrap)); + strtomem(wrap.output, truncate); + KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX); + for (size_t i = 0; i < sizeof(wrap.output); i++) + KUNIT_EXPECT_EQ(test, wrap.output[i], truncate[i]); + KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX); +} + + static void string_test_memtostr(struct kunit *test) { char nonstring[7] = { 'a', 'b', 'c', 'd', 'e', 'f', 'g' }; @@ -568,6 +621,7 @@ static struct kunit_case string_test_cases[] = { KUNIT_CASE(string_test_strcat), KUNIT_CASE(string_test_strncat), KUNIT_CASE(string_test_strlcat), + KUNIT_CASE(string_test_strtomem), KUNIT_CASE(string_test_memtostr), {} }; -- cgit v1.2.3 From c209826737b733b4ccd38448d7b025bb128aaa8a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 24 Apr 2024 09:27:39 -0700 Subject: ubsan: Remove 1-element array usage in debug reporting The "type_name" character array was still marked as a 1-element array. While we don't validate strings used in format arguments yet, let's fix this before it causes trouble some future day. Link: https://lore.kernel.org/r/20240424162739.work.492-kees@kernel.org Reviewed-by: Gustavo A. R. Silva Signed-off-by: Kees Cook --- lib/ubsan.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/ubsan.h b/lib/ubsan.h index 0abbbac8700d..50ef50811b7c 100644 --- a/lib/ubsan.h +++ b/lib/ubsan.h @@ -43,7 +43,7 @@ enum { struct type_descriptor { u16 type_kind; u16 type_info; - char type_name[1]; + char type_name[]; }; struct source_location { -- cgit v1.2.3 From cdc66553c4130735f0a2db943a5259e54ff1597a Mon Sep 17 00:00:00 2001 From: Dawei Li Date: Tue, 16 Apr 2024 16:54:48 +0800 Subject: cpumask: Introduce cpumask_first_and_and() Introduce cpumask_first_and_and() to get intersection between 3 cpumasks, free of any intermediate cpumask variable. Instead, cpumask_first_and_and() works in-place with all inputs and produces desired output directly. Signed-off-by: Dawei Li Signed-off-by: Thomas Gleixner Acked-by: Yury Norov Link: https://lore.kernel.org/r/20240416085454.3547175-2-dawei.li@shingroup.cn --- include/linux/cpumask.h | 17 +++++++++++++++++ include/linux/find.h | 27 +++++++++++++++++++++++++++ lib/find_bit.c | 12 ++++++++++++ 3 files changed, 56 insertions(+) (limited to 'lib') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 1c29947db848..c46f9e9e1d66 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -187,6 +187,23 @@ unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } +/** + * cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3 + * @srcp1: the first input + * @srcp2: the second input + * @srcp3: the third input + * + * Return: >= nr_cpu_ids if no cpus set in all. + */ +static inline +unsigned int cpumask_first_and_and(const struct cpumask *srcp1, + const struct cpumask *srcp2, + const struct cpumask *srcp3) +{ + return find_first_and_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), + cpumask_bits(srcp3), small_cpumask_bits); +} + /** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer diff --git a/include/linux/find.h b/include/linux/find.h index c69598e383c1..28ec5a03393a 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -29,6 +29,8 @@ unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsign unsigned long n); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); +unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, + const unsigned long *addr3, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); @@ -345,6 +347,31 @@ unsigned long find_first_and_bit(const unsigned long *addr1, } #endif +/** + * find_first_and_and_bit - find the first set bit in 3 memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @addr3: The third address to base the search on + * @size: The bitmap size in bits + * + * Returns the bit number for the first set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_first_and_and_bit(const unsigned long *addr1, + const unsigned long *addr2, + const unsigned long *addr3, + unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr1 & *addr2 & *addr3 & GENMASK(size - 1, 0); + + return val ? __ffs(val) : size; + } + + return _find_first_and_and_bit(addr1, addr2, addr3, size); +} + #ifndef find_first_zero_bit /** * find_first_zero_bit - find the first cleared bit in a memory region diff --git a/lib/find_bit.c b/lib/find_bit.c index 32f99e9a670e..dacadd904250 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -116,6 +116,18 @@ unsigned long _find_first_and_bit(const unsigned long *addr1, EXPORT_SYMBOL(_find_first_and_bit); #endif +/* + * Find the first set bit in three memory regions. + */ +unsigned long _find_first_and_and_bit(const unsigned long *addr1, + const unsigned long *addr2, + const unsigned long *addr3, + unsigned long size) +{ + return FIND_FIRST_BIT(addr1[idx] & addr2[idx] & addr3[idx], /* nop */, size); +} +EXPORT_SYMBOL(_find_first_and_and_bit); + #ifndef find_first_zero_bit /* * Find the first cleared bit in a memory region. -- cgit v1.2.3 From 2e431b23a13ce4459cf484c8f0b3218c7048b515 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 24 Apr 2024 15:40:29 -0700 Subject: ubsan: Avoid i386 UBSAN handler crashes with Clang When generating Runtime Calls, Clang doesn't respect the -mregparm=3 option used on i386. Hopefully this will be fixed correctly in Clang 19: https://github.com/llvm/llvm-project/pull/89707 but we need to fix this for earlier Clang versions today. Force the calling convention to use non-register arguments. Reported-by: Erhard Furtner Closes: https://github.com/KSPP/linux/issues/350 Link: https://lore.kernel.org/r/20240424224026.it.216-kees@kernel.org Acked-by: Nathan Chancellor Acked-by: Justin Stitt Signed-off-by: Kees Cook --- lib/ubsan.h | 41 +++++++++++++++++++++++++++-------------- 1 file changed, 27 insertions(+), 14 deletions(-) (limited to 'lib') diff --git a/lib/ubsan.h b/lib/ubsan.h index 50ef50811b7c..07e37d4429b4 100644 --- a/lib/ubsan.h +++ b/lib/ubsan.h @@ -124,19 +124,32 @@ typedef s64 s_max; typedef u64 u_max; #endif -void __ubsan_handle_add_overflow(void *data, void *lhs, void *rhs); -void __ubsan_handle_sub_overflow(void *data, void *lhs, void *rhs); -void __ubsan_handle_mul_overflow(void *data, void *lhs, void *rhs); -void __ubsan_handle_negate_overflow(void *_data, void *old_val); -void __ubsan_handle_divrem_overflow(void *_data, void *lhs, void *rhs); -void __ubsan_handle_type_mismatch(struct type_mismatch_data *data, void *ptr); -void __ubsan_handle_type_mismatch_v1(void *_data, void *ptr); -void __ubsan_handle_out_of_bounds(void *_data, void *index); -void __ubsan_handle_shift_out_of_bounds(void *_data, void *lhs, void *rhs); -void __ubsan_handle_builtin_unreachable(void *_data); -void __ubsan_handle_load_invalid_value(void *_data, void *val); -void __ubsan_handle_alignment_assumption(void *_data, unsigned long ptr, - unsigned long align, - unsigned long offset); +/* + * When generating Runtime Calls, Clang doesn't respect the -mregparm=3 + * option used on i386: https://github.com/llvm/llvm-project/issues/89670 + * Fix this for earlier Clang versions by forcing the calling convention + * to use non-register arguments. + */ +#if defined(CONFIG_X86_32) && \ + defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 190000 +# define ubsan_linkage asmlinkage +#else +# define ubsan_linkage +#endif + +void ubsan_linkage __ubsan_handle_add_overflow(void *data, void *lhs, void *rhs); +void ubsan_linkage __ubsan_handle_sub_overflow(void *data, void *lhs, void *rhs); +void ubsan_linkage __ubsan_handle_mul_overflow(void *data, void *lhs, void *rhs); +void ubsan_linkage __ubsan_handle_negate_overflow(void *_data, void *old_val); +void ubsan_linkage __ubsan_handle_divrem_overflow(void *_data, void *lhs, void *rhs); +void ubsan_linkage __ubsan_handle_type_mismatch(struct type_mismatch_data *data, void *ptr); +void ubsan_linkage __ubsan_handle_type_mismatch_v1(void *_data, void *ptr); +void ubsan_linkage __ubsan_handle_out_of_bounds(void *_data, void *index); +void ubsan_linkage __ubsan_handle_shift_out_of_bounds(void *_data, void *lhs, void *rhs); +void ubsan_linkage __ubsan_handle_builtin_unreachable(void *_data); +void ubsan_linkage __ubsan_handle_load_invalid_value(void *_data, void *val); +void ubsan_linkage __ubsan_handle_alignment_assumption(void *_data, unsigned long ptr, + unsigned long align, + unsigned long offset); #endif -- cgit v1.2.3 From c2af060d1c18beaec56351cf9c9bcbbc5af341a3 Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Tue, 12 Mar 2024 08:59:05 +0800 Subject: lib/test_hmm.c: handle src_pfns and dst_pfns allocation failure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The kcalloc() in dmirror_device_evict_chunk() will return null if the physical memory has run out. As a result, if src_pfns or dst_pfns is dereferenced, the null pointer dereference bug will happen. Moreover, the device is going away. If the kcalloc() fails, the pages mapping a chunk could not be evicted. So add a __GFP_NOFAIL flag in kcalloc(). Finally, as there is no need to have physically contiguous memory, Switch kcalloc() to kvcalloc() in order to avoid failing allocations. Link: https://lkml.kernel.org/r/20240312005905.9939-1-duoming@zju.edu.cn Fixes: b2ef9f5a5cb3 ("mm/hmm/test: add selftest driver for HMM") Signed-off-by: Duoming Zhou Cc: Jérôme Glisse Signed-off-by: Andrew Morton --- lib/test_hmm.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 717dcb830127..b823ba7cb6a1 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -1226,8 +1226,8 @@ static void dmirror_device_evict_chunk(struct dmirror_chunk *chunk) unsigned long *src_pfns; unsigned long *dst_pfns; - src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL); - dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL); + src_pfns = kvcalloc(npages, sizeof(*src_pfns), GFP_KERNEL | __GFP_NOFAIL); + dst_pfns = kvcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL | __GFP_NOFAIL); migrate_device_range(src_pfns, start_pfn, npages); for (i = 0; i < npages; i++) { @@ -1250,8 +1250,8 @@ static void dmirror_device_evict_chunk(struct dmirror_chunk *chunk) } migrate_device_pages(src_pfns, dst_pfns, npages); migrate_device_finalize(src_pfns, dst_pfns, npages); - kfree(src_pfns); - kfree(dst_pfns); + kvfree(src_pfns); + kvfree(dst_pfns); } /* Removes free pages from the free list so they can't be re-allocated */ -- cgit v1.2.3 From 916cc5167cc6f81651f4460d9a35c939ad18ecff Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 21 Mar 2024 09:36:32 -0700 Subject: lib: code tagging framework MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add basic infrastructure to support code tagging which stores tag common information consisting of the module name, function, file name and line number. Provide functions to register a new code tag type and navigate between code tags. Link: https://lkml.kernel.org/r/20240321163705.3067592-11-surenb@google.com Co-developed-by: Kent Overstreet Signed-off-by: Kent Overstreet Signed-off-by: Suren Baghdasaryan Tested-by: Kees Cook Cc: Alexander Viro Cc: Alex Gaynor Cc: Alice Ryhl Cc: Andreas Hindborg Cc: Benno Lossin Cc: "Björn Roy Baron" Cc: Boqun Feng Cc: Christoph Lameter Cc: Dennis Zhou Cc: Gary Guo Cc: Miguel Ojeda Cc: Pasha Tatashin Cc: Peter Zijlstra Cc: Tejun Heo Cc: Vlastimil Babka Cc: Wedson Almeida Filho Signed-off-by: Andrew Morton --- include/linux/codetag.h | 68 +++++++++++++++ lib/Kconfig.debug | 4 + lib/Makefile | 1 + lib/codetag.c | 219 ++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 292 insertions(+) create mode 100644 include/linux/codetag.h create mode 100644 lib/codetag.c (limited to 'lib') diff --git a/include/linux/codetag.h b/include/linux/codetag.h new file mode 100644 index 000000000000..7734269cdb63 --- /dev/null +++ b/include/linux/codetag.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * code tagging framework + */ +#ifndef _LINUX_CODETAG_H +#define _LINUX_CODETAG_H + +#include + +struct codetag_iterator; +struct codetag_type; +struct codetag_module; +struct seq_buf; +struct module; + +/* + * An instance of this structure is created in a special ELF section at every + * code location being tagged. At runtime, the special section is treated as + * an array of these. + */ +struct codetag { + unsigned int flags; /* used in later patches */ + unsigned int lineno; + const char *modname; + const char *function; + const char *filename; +} __aligned(8); + +union codetag_ref { + struct codetag *ct; +}; + +struct codetag_type_desc { + const char *section; + size_t tag_size; +}; + +struct codetag_iterator { + struct codetag_type *cttype; + struct codetag_module *cmod; + unsigned long mod_id; + struct codetag *ct; +}; + +#ifdef MODULE +#define CT_MODULE_NAME KBUILD_MODNAME +#else +#define CT_MODULE_NAME NULL +#endif + +#define CODE_TAG_INIT { \ + .modname = CT_MODULE_NAME, \ + .function = __func__, \ + .filename = __FILE__, \ + .lineno = __LINE__, \ + .flags = 0, \ +} + +void codetag_lock_module_list(struct codetag_type *cttype, bool lock); +struct codetag_iterator codetag_get_ct_iter(struct codetag_type *cttype); +struct codetag *codetag_next_ct(struct codetag_iterator *iter); + +void codetag_to_text(struct seq_buf *out, struct codetag *ct); + +struct codetag_type * +codetag_register_type(const struct codetag_type_desc *desc); + +#endif /* _LINUX_CODETAG_H */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c63a5fbf1f1c..015fc6ee9849 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -968,6 +968,10 @@ config DEBUG_STACKOVERFLOW If in doubt, say "N". +config CODE_TAGGING + bool + select KALLSYMS + source "lib/Kconfig.kasan" source "lib/Kconfig.kfence" source "lib/Kconfig.kmsan" diff --git a/lib/Makefile b/lib/Makefile index ffc6b2341b45..910335da8f13 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -233,6 +233,7 @@ obj-$(CONFIG_OF_RECONFIG_NOTIFIER_ERROR_INJECT) += \ of-reconfig-notifier-error-inject.o obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o +obj-$(CONFIG_CODE_TAGGING) += codetag.o lib-$(CONFIG_GENERIC_BUG) += bug.o obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o diff --git a/lib/codetag.c b/lib/codetag.c new file mode 100644 index 000000000000..8b5b89ad508d --- /dev/null +++ b/lib/codetag.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include +#include +#include + +struct codetag_type { + struct list_head link; + unsigned int count; + struct idr mod_idr; + struct rw_semaphore mod_lock; /* protects mod_idr */ + struct codetag_type_desc desc; +}; + +struct codetag_range { + struct codetag *start; + struct codetag *stop; +}; + +struct codetag_module { + struct module *mod; + struct codetag_range range; +}; + +static DEFINE_MUTEX(codetag_lock); +static LIST_HEAD(codetag_types); + +void codetag_lock_module_list(struct codetag_type *cttype, bool lock) +{ + if (lock) + down_read(&cttype->mod_lock); + else + up_read(&cttype->mod_lock); +} + +struct codetag_iterator codetag_get_ct_iter(struct codetag_type *cttype) +{ + struct codetag_iterator iter = { + .cttype = cttype, + .cmod = NULL, + .mod_id = 0, + .ct = NULL, + }; + + return iter; +} + +static inline struct codetag *get_first_module_ct(struct codetag_module *cmod) +{ + return cmod->range.start < cmod->range.stop ? cmod->range.start : NULL; +} + +static inline +struct codetag *get_next_module_ct(struct codetag_iterator *iter) +{ + struct codetag *res = (struct codetag *) + ((char *)iter->ct + iter->cttype->desc.tag_size); + + return res < iter->cmod->range.stop ? res : NULL; +} + +struct codetag *codetag_next_ct(struct codetag_iterator *iter) +{ + struct codetag_type *cttype = iter->cttype; + struct codetag_module *cmod; + struct codetag *ct; + + lockdep_assert_held(&cttype->mod_lock); + + if (unlikely(idr_is_empty(&cttype->mod_idr))) + return NULL; + + ct = NULL; + while (true) { + cmod = idr_find(&cttype->mod_idr, iter->mod_id); + + /* If module was removed move to the next one */ + if (!cmod) + cmod = idr_get_next_ul(&cttype->mod_idr, + &iter->mod_id); + + /* Exit if no more modules */ + if (!cmod) + break; + + if (cmod != iter->cmod) { + iter->cmod = cmod; + ct = get_first_module_ct(cmod); + } else + ct = get_next_module_ct(iter); + + if (ct) + break; + + iter->mod_id++; + } + + iter->ct = ct; + return ct; +} + +void codetag_to_text(struct seq_buf *out, struct codetag *ct) +{ + if (ct->modname) + seq_buf_printf(out, "%s:%u [%s] func:%s", + ct->filename, ct->lineno, + ct->modname, ct->function); + else + seq_buf_printf(out, "%s:%u func:%s", + ct->filename, ct->lineno, ct->function); +} + +static inline size_t range_size(const struct codetag_type *cttype, + const struct codetag_range *range) +{ + return ((char *)range->stop - (char *)range->start) / + cttype->desc.tag_size; +} + +#ifdef CONFIG_MODULES +static void *get_symbol(struct module *mod, const char *prefix, const char *name) +{ + DECLARE_SEQ_BUF(sb, KSYM_NAME_LEN); + const char *buf; + + seq_buf_printf(&sb, "%s%s", prefix, name); + if (seq_buf_has_overflowed(&sb)) + return NULL; + + buf = seq_buf_str(&sb); + return mod ? + (void *)find_kallsyms_symbol_value(mod, buf) : + (void *)kallsyms_lookup_name(buf); +} + +static struct codetag_range get_section_range(struct module *mod, + const char *section) +{ + return (struct codetag_range) { + get_symbol(mod, "__start_", section), + get_symbol(mod, "__stop_", section), + }; +} + +static int codetag_module_init(struct codetag_type *cttype, struct module *mod) +{ + struct codetag_range range; + struct codetag_module *cmod; + int err; + + range = get_section_range(mod, cttype->desc.section); + if (!range.start || !range.stop) { + pr_warn("Failed to load code tags of type %s from the module %s\n", + cttype->desc.section, + mod ? mod->name : "(built-in)"); + return -EINVAL; + } + + /* Ignore empty ranges */ + if (range.start == range.stop) + return 0; + + BUG_ON(range.start > range.stop); + + cmod = kmalloc(sizeof(*cmod), GFP_KERNEL); + if (unlikely(!cmod)) + return -ENOMEM; + + cmod->mod = mod; + cmod->range = range; + + down_write(&cttype->mod_lock); + err = idr_alloc(&cttype->mod_idr, cmod, 0, 0, GFP_KERNEL); + if (err >= 0) + cttype->count += range_size(cttype, &range); + up_write(&cttype->mod_lock); + + if (err < 0) { + kfree(cmod); + return err; + } + + return 0; +} + +#else /* CONFIG_MODULES */ +static int codetag_module_init(struct codetag_type *cttype, struct module *mod) { return 0; } +#endif /* CONFIG_MODULES */ + +struct codetag_type * +codetag_register_type(const struct codetag_type_desc *desc) +{ + struct codetag_type *cttype; + int err; + + BUG_ON(desc->tag_size <= 0); + + cttype = kzalloc(sizeof(*cttype), GFP_KERNEL); + if (unlikely(!cttype)) + return ERR_PTR(-ENOMEM); + + cttype->desc = *desc; + idr_init(&cttype->mod_idr); + init_rwsem(&cttype->mod_lock); + + err = codetag_module_init(cttype, NULL); + if (unlikely(err)) { + kfree(cttype); + return ERR_PTR(err); + } + + mutex_lock(&codetag_lock); + list_add_tail(&cttype->link, &codetag_types); + mutex_unlock(&codetag_lock); + + return cttype; +} -- cgit v1.2.3 From a473573964e51dcb6efc182f773cd3924be4a184 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 21 Mar 2024 09:36:33 -0700 Subject: lib: code tagging module support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support for code tagging from dynamically loaded modules. Link: https://lkml.kernel.org/r/20240321163705.3067592-12-surenb@google.com Signed-off-by: Suren Baghdasaryan Co-developed-by: Kent Overstreet Signed-off-by: Kent Overstreet Tested-by: Kees Cook Cc: Alexander Viro Cc: Alex Gaynor Cc: Alice Ryhl Cc: Andreas Hindborg Cc: Benno Lossin Cc: "Björn Roy Baron" Cc: Boqun Feng Cc: Christoph Lameter Cc: Dennis Zhou Cc: Gary Guo Cc: Miguel Ojeda Cc: Pasha Tatashin Cc: Peter Zijlstra Cc: Tejun Heo Cc: Vlastimil Babka Cc: Wedson Almeida Filho Signed-off-by: Andrew Morton --- include/linux/codetag.h | 12 ++++++++++ kernel/module/main.c | 4 ++++ lib/codetag.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 72 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/include/linux/codetag.h b/include/linux/codetag.h index 7734269cdb63..c44f5b83f24d 100644 --- a/include/linux/codetag.h +++ b/include/linux/codetag.h @@ -33,6 +33,10 @@ union codetag_ref { struct codetag_type_desc { const char *section; size_t tag_size; + void (*module_load)(struct codetag_type *cttype, + struct codetag_module *cmod); + void (*module_unload)(struct codetag_type *cttype, + struct codetag_module *cmod); }; struct codetag_iterator { @@ -65,4 +69,12 @@ void codetag_to_text(struct seq_buf *out, struct codetag *ct); struct codetag_type * codetag_register_type(const struct codetag_type_desc *desc); +#if defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) +void codetag_load_module(struct module *mod); +void codetag_unload_module(struct module *mod); +#else +static inline void codetag_load_module(struct module *mod) {} +static inline void codetag_unload_module(struct module *mod) {} +#endif + #endif /* _LINUX_CODETAG_H */ diff --git a/kernel/module/main.c b/kernel/module/main.c index e1e8a7a9d6c1..ffa6b3e9cb43 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -56,6 +56,7 @@ #include #include #include +#include #include #include #include "internal.h" @@ -1242,6 +1243,7 @@ static void free_module(struct module *mod) { trace_module_free(mod); + codetag_unload_module(mod); mod_sysfs_teardown(mod); /* @@ -2995,6 +2997,8 @@ static int load_module(struct load_info *info, const char __user *uargs, /* Get rid of temporary copy. */ free_copy(info, flags); + codetag_load_module(mod); + /* Done! */ trace_module_load(mod); diff --git a/lib/codetag.c b/lib/codetag.c index 8b5b89ad508d..54d2828eba25 100644 --- a/lib/codetag.c +++ b/lib/codetag.c @@ -124,15 +124,20 @@ static void *get_symbol(struct module *mod, const char *prefix, const char *name { DECLARE_SEQ_BUF(sb, KSYM_NAME_LEN); const char *buf; + void *ret; seq_buf_printf(&sb, "%s%s", prefix, name); if (seq_buf_has_overflowed(&sb)) return NULL; buf = seq_buf_str(&sb); - return mod ? + preempt_disable(); + ret = mod ? (void *)find_kallsyms_symbol_value(mod, buf) : (void *)kallsyms_lookup_name(buf); + preempt_enable(); + + return ret; } static struct codetag_range get_section_range(struct module *mod, @@ -173,8 +178,11 @@ static int codetag_module_init(struct codetag_type *cttype, struct module *mod) down_write(&cttype->mod_lock); err = idr_alloc(&cttype->mod_idr, cmod, 0, 0, GFP_KERNEL); - if (err >= 0) + if (err >= 0) { cttype->count += range_size(cttype, &range); + if (cttype->desc.module_load) + cttype->desc.module_load(cttype, cmod); + } up_write(&cttype->mod_lock); if (err < 0) { @@ -185,6 +193,52 @@ static int codetag_module_init(struct codetag_type *cttype, struct module *mod) return 0; } +void codetag_load_module(struct module *mod) +{ + struct codetag_type *cttype; + + if (!mod) + return; + + mutex_lock(&codetag_lock); + list_for_each_entry(cttype, &codetag_types, link) + codetag_module_init(cttype, mod); + mutex_unlock(&codetag_lock); +} + +void codetag_unload_module(struct module *mod) +{ + struct codetag_type *cttype; + + if (!mod) + return; + + mutex_lock(&codetag_lock); + list_for_each_entry(cttype, &codetag_types, link) { + struct codetag_module *found = NULL; + struct codetag_module *cmod; + unsigned long mod_id, tmp; + + down_write(&cttype->mod_lock); + idr_for_each_entry_ul(&cttype->mod_idr, cmod, tmp, mod_id) { + if (cmod->mod && cmod->mod == mod) { + found = cmod; + break; + } + } + if (found) { + if (cttype->desc.module_unload) + cttype->desc.module_unload(cttype, cmod); + + cttype->count -= range_size(cttype, &cmod->range); + idr_remove(&cttype->mod_idr, mod_id); + kfree(cmod); + } + up_write(&cttype->mod_lock); + } + mutex_unlock(&codetag_lock); +} + #else /* CONFIG_MODULES */ static int codetag_module_init(struct codetag_type *cttype, struct module *mod) { return 0; } #endif /* CONFIG_MODULES */ -- cgit v1.2.3 From 47a92dfbe01f41bcbf359250ccb3caa589763abf Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 21 Mar 2024 09:36:34 -0700 Subject: lib: prevent module unloading if memory is not freed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Skip freeing module's data section if there are non-zero allocation tags because otherwise, once these allocations are freed, the access to their code tag would cause UAF. Link: https://lkml.kernel.org/r/20240321163705.3067592-13-surenb@google.com Signed-off-by: Suren Baghdasaryan Tested-by: Kees Cook Cc: Alexander Viro Cc: Alex Gaynor Cc: Alice Ryhl Cc: Andreas Hindborg Cc: Benno Lossin Cc: "Björn Roy Baron" Cc: Boqun Feng Cc: Christoph Lameter Cc: Dennis Zhou Cc: Gary Guo Cc: Kent Overstreet Cc: Miguel Ojeda Cc: Pasha Tatashin Cc: Peter Zijlstra Cc: Tejun Heo Cc: Vlastimil Babka Cc: Wedson Almeida Filho Signed-off-by: Andrew Morton --- include/linux/codetag.h | 6 +++--- kernel/module/main.c | 27 +++++++++++++++++++-------- lib/codetag.c | 11 ++++++++--- 3 files changed, 30 insertions(+), 14 deletions(-) (limited to 'lib') diff --git a/include/linux/codetag.h b/include/linux/codetag.h index c44f5b83f24d..bfd0ba5c4185 100644 --- a/include/linux/codetag.h +++ b/include/linux/codetag.h @@ -35,7 +35,7 @@ struct codetag_type_desc { size_t tag_size; void (*module_load)(struct codetag_type *cttype, struct codetag_module *cmod); - void (*module_unload)(struct codetag_type *cttype, + bool (*module_unload)(struct codetag_type *cttype, struct codetag_module *cmod); }; @@ -71,10 +71,10 @@ codetag_register_type(const struct codetag_type_desc *desc); #if defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) void codetag_load_module(struct module *mod); -void codetag_unload_module(struct module *mod); +bool codetag_unload_module(struct module *mod); #else static inline void codetag_load_module(struct module *mod) {} -static inline void codetag_unload_module(struct module *mod) {} +static inline bool codetag_unload_module(struct module *mod) { return true; } #endif #endif /* _LINUX_CODETAG_H */ diff --git a/kernel/module/main.c b/kernel/module/main.c index ffa6b3e9cb43..2d25eebc549d 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1211,15 +1211,19 @@ static void *module_memory_alloc(unsigned int size, enum mod_mem_type type) return module_alloc(size); } -static void module_memory_free(void *ptr, enum mod_mem_type type) +static void module_memory_free(void *ptr, enum mod_mem_type type, + bool unload_codetags) { + if (!unload_codetags && mod_mem_type_is_core_data(type)) + return; + if (mod_mem_use_vmalloc(type)) vfree(ptr); else module_memfree(ptr); } -static void free_mod_mem(struct module *mod) +static void free_mod_mem(struct module *mod, bool unload_codetags) { for_each_mod_mem_type(type) { struct module_memory *mod_mem = &mod->mem[type]; @@ -1230,20 +1234,27 @@ static void free_mod_mem(struct module *mod) /* Free lock-classes; relies on the preceding sync_rcu(). */ lockdep_free_key_range(mod_mem->base, mod_mem->size); if (mod_mem->size) - module_memory_free(mod_mem->base, type); + module_memory_free(mod_mem->base, type, + unload_codetags); } /* MOD_DATA hosts mod, so free it at last */ lockdep_free_key_range(mod->mem[MOD_DATA].base, mod->mem[MOD_DATA].size); - module_memory_free(mod->mem[MOD_DATA].base, MOD_DATA); + module_memory_free(mod->mem[MOD_DATA].base, MOD_DATA, unload_codetags); } /* Free a module, remove from lists, etc. */ static void free_module(struct module *mod) { + bool unload_codetags; + trace_module_free(mod); - codetag_unload_module(mod); + unload_codetags = codetag_unload_module(mod); + if (!unload_codetags) + pr_warn("%s: memory allocation(s) from the module still alive, cannot unload cleanly\n", + mod->name); + mod_sysfs_teardown(mod); /* @@ -1285,7 +1296,7 @@ static void free_module(struct module *mod) kfree(mod->args); percpu_modfree(mod); - free_mod_mem(mod); + free_mod_mem(mod, unload_codetags); } void *__symbol_get(const char *symbol) @@ -2298,7 +2309,7 @@ static int move_module(struct module *mod, struct load_info *info) return 0; out_enomem: for (t--; t >= 0; t--) - module_memory_free(mod->mem[t].base, t); + module_memory_free(mod->mem[t].base, t, true); return ret; } @@ -2428,7 +2439,7 @@ static void module_deallocate(struct module *mod, struct load_info *info) percpu_modfree(mod); module_arch_freeing_init(mod); - free_mod_mem(mod); + free_mod_mem(mod, true); } int __weak module_finalize(const Elf_Ehdr *hdr, diff --git a/lib/codetag.c b/lib/codetag.c index 54d2828eba25..408062f722ce 100644 --- a/lib/codetag.c +++ b/lib/codetag.c @@ -5,6 +5,7 @@ #include #include #include +#include struct codetag_type { struct list_head link; @@ -206,12 +207,13 @@ void codetag_load_module(struct module *mod) mutex_unlock(&codetag_lock); } -void codetag_unload_module(struct module *mod) +bool codetag_unload_module(struct module *mod) { struct codetag_type *cttype; + bool unload_ok = true; if (!mod) - return; + return true; mutex_lock(&codetag_lock); list_for_each_entry(cttype, &codetag_types, link) { @@ -228,7 +230,8 @@ void codetag_unload_module(struct module *mod) } if (found) { if (cttype->desc.module_unload) - cttype->desc.module_unload(cttype, cmod); + if (!cttype->desc.module_unload(cttype, cmod)) + unload_ok = false; cttype->count -= range_size(cttype, &cmod->range); idr_remove(&cttype->mod_idr, mod_id); @@ -237,6 +240,8 @@ void codetag_unload_module(struct module *mod) up_write(&cttype->mod_lock); } mutex_unlock(&codetag_lock); + + return unload_ok; } #else /* CONFIG_MODULES */ -- cgit v1.2.3 From 22d407b164ff79de42d21f37d99f9ee7abdd51c8 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 21 Mar 2024 09:36:35 -0700 Subject: lib: add allocation tagging support for memory allocation profiling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce CONFIG_MEM_ALLOC_PROFILING which provides definitions to easily instrument memory allocators. It registers an "alloc_tags" codetag type with /proc/allocinfo interface to output allocation tag information when the feature is enabled. CONFIG_MEM_ALLOC_PROFILING_DEBUG is provided for debugging the memory allocation profiling instrumentation. Memory allocation profiling can be enabled or disabled at runtime using /proc/sys/vm/mem_profiling sysctl when CONFIG_MEM_ALLOC_PROFILING_DEBUG=n. CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT enables memory allocation profiling by default. [surenb@google.com: Documentation/filesystems/proc.rst: fix allocinfo title] Link: https://lkml.kernel.org/r/20240326073813.727090-1-surenb@google.com [surenb@google.com: do limited memory accounting for modules with ARCH_NEEDS_WEAK_PER_CPU] Link: https://lkml.kernel.org/r/20240402180933.1663992-2-surenb@google.com [klarasmodin@gmail.com: explicitly include irqflags.h in alloc_tag.h] Link: https://lkml.kernel.org/r/20240407133252.173636-1-klarasmodin@gmail.com [surenb@google.com: fix alloc_tag_init() to prevent passing NULL to PTR_ERR()] Link: https://lkml.kernel.org/r/20240417003349.2520094-1-surenb@google.com Link: https://lkml.kernel.org/r/20240321163705.3067592-14-surenb@google.com Signed-off-by: Suren Baghdasaryan Co-developed-by: Kent Overstreet Signed-off-by: Kent Overstreet Signed-off-by: Klara Modin Tested-by: Kees Cook Cc: Alexander Viro Cc: Alex Gaynor Cc: Alice Ryhl Cc: Andreas Hindborg Cc: Benno Lossin Cc: "Björn Roy Baron" Cc: Boqun Feng Cc: Christoph Lameter Cc: Dennis Zhou Cc: Gary Guo Cc: Miguel Ojeda Cc: Pasha Tatashin Cc: Peter Zijlstra Cc: Tejun Heo Cc: Vlastimil Babka Cc: Wedson Almeida Filho Signed-off-by: Andrew Morton --- Documentation/admin-guide/sysctl/vm.rst | 16 ++++ Documentation/filesystems/proc.rst | 29 ++++++ include/asm-generic/codetag.lds.h | 14 +++ include/asm-generic/vmlinux.lds.h | 3 + include/linux/alloc_tag.h | 156 ++++++++++++++++++++++++++++++++ include/linux/sched.h | 24 +++++ lib/Kconfig.debug | 25 +++++ lib/Makefile | 2 + lib/alloc_tag.c | 152 +++++++++++++++++++++++++++++++ scripts/module.lds.S | 7 ++ 10 files changed, 428 insertions(+) create mode 100644 include/asm-generic/codetag.lds.h create mode 100644 include/linux/alloc_tag.h create mode 100644 lib/alloc_tag.c (limited to 'lib') diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index c59889de122b..e86c968a7a0e 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -43,6 +43,7 @@ Currently, these files are in /proc/sys/vm: - legacy_va_layout - lowmem_reserve_ratio - max_map_count +- mem_profiling (only if CONFIG_MEM_ALLOC_PROFILING=y) - memory_failure_early_kill - memory_failure_recovery - min_free_kbytes @@ -425,6 +426,21 @@ e.g., up to one or two maps per allocation. The default value is 65530. +mem_profiling +============== + +Enable memory profiling (when CONFIG_MEM_ALLOC_PROFILING=y) + +1: Enable memory profiling. + +0: Disable memory profiling. + +Enabling memory profiling introduces a small performance overhead for all +memory allocations. + +The default value depends on CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT. + + memory_failure_early_kill: ========================== diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index c6a6b9df2104..245269dd6e02 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -688,6 +688,7 @@ files are there, and which are missing. ============ =============================================================== File Content ============ =============================================================== + allocinfo Memory allocations profiling information apm Advanced power management info bootconfig Kernel command line obtained from boot config, and, if there were kernel parameters from the @@ -953,6 +954,34 @@ also be allocatable although a lot of filesystem metadata may have to be reclaimed to achieve this. +allocinfo +~~~~~~~~~ + +Provides information about memory allocations at all locations in the code +base. Each allocation in the code is identified by its source file, line +number, module (if originates from a loadable module) and the function calling +the allocation. The number of bytes allocated and number of calls at each +location are reported. + +Example output. + +:: + + > sort -rn /proc/allocinfo + 127664128 31168 mm/page_ext.c:270 func:alloc_page_ext + 56373248 4737 mm/slub.c:2259 func:alloc_slab_page + 14880768 3633 mm/readahead.c:247 func:page_cache_ra_unbounded + 14417920 3520 mm/mm_init.c:2530 func:alloc_large_system_hash + 13377536 234 block/blk-mq.c:3421 func:blk_mq_alloc_rqs + 11718656 2861 mm/filemap.c:1919 func:__filemap_get_folio + 9192960 2800 kernel/fork.c:307 func:alloc_thread_stack_node + 4206592 4 net/netfilter/nf_conntrack_core.c:2567 func:nf_ct_alloc_hashtable + 4136960 1010 drivers/staging/ctagmod/ctagmod.c:20 [ctagmod] func:ctagmod_start + 3940352 962 mm/memory.c:4214 func:alloc_anon_folio + 2894464 22613 fs/kernfs/dir.c:615 func:__kernfs_new_node + ... + + meminfo ~~~~~~~ diff --git a/include/asm-generic/codetag.lds.h b/include/asm-generic/codetag.lds.h new file mode 100644 index 000000000000..64f536b80380 --- /dev/null +++ b/include/asm-generic/codetag.lds.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_GENERIC_CODETAG_LDS_H +#define __ASM_GENERIC_CODETAG_LDS_H + +#define SECTION_WITH_BOUNDARIES(_name) \ + . = ALIGN(8); \ + __start_##_name = .; \ + KEEP(*(_name)) \ + __stop_##_name = .; + +#define CODETAG_SECTIONS() \ + SECTION_WITH_BOUNDARIES(alloc_tags) + +#endif /* __ASM_GENERIC_CODETAG_LDS_H */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index f7749d0f2562..3e4497b5135a 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -50,6 +50,8 @@ * [__nosave_begin, __nosave_end] for the nosave data */ +#include + #ifndef LOAD_OFFSET #define LOAD_OFFSET 0 #endif @@ -366,6 +368,7 @@ . = ALIGN(8); \ BOUNDED_SECTION_BY(__dyndbg_classes, ___dyndbg_classes) \ BOUNDED_SECTION_BY(__dyndbg, ___dyndbg) \ + CODETAG_SECTIONS() \ LIKELY_PROFILE() \ BRANCH_PROFILE() \ TRACE_PRINTKS() \ diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h new file mode 100644 index 000000000000..13561223fdab --- /dev/null +++ b/include/linux/alloc_tag.h @@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * allocation tagging + */ +#ifndef _LINUX_ALLOC_TAG_H +#define _LINUX_ALLOC_TAG_H + +#include +#include +#include +#include +#include +#include +#include +#include + +struct alloc_tag_counters { + u64 bytes; + u64 calls; +}; + +/* + * An instance of this structure is created in a special ELF section at every + * allocation callsite. At runtime, the special section is treated as + * an array of these. Embedded codetag utilizes codetag framework. + */ +struct alloc_tag { + struct codetag ct; + struct alloc_tag_counters __percpu *counters; +} __aligned(8); + +#ifdef CONFIG_MEM_ALLOC_PROFILING + +static inline struct alloc_tag *ct_to_alloc_tag(struct codetag *ct) +{ + return container_of(ct, struct alloc_tag, ct); +} + +#ifdef ARCH_NEEDS_WEAK_PER_CPU +/* + * When percpu variables are required to be defined as weak, static percpu + * variables can't be used inside a function (see comments for DECLARE_PER_CPU_SECTION). + * Instead we will accound all module allocations to a single counter. + */ +DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag); + +#define DEFINE_ALLOC_TAG(_alloc_tag) \ + static struct alloc_tag _alloc_tag __used __aligned(8) \ + __section("alloc_tags") = { \ + .ct = CODE_TAG_INIT, \ + .counters = &_shared_alloc_tag }; + +#else /* ARCH_NEEDS_WEAK_PER_CPU */ + +#define DEFINE_ALLOC_TAG(_alloc_tag) \ + static DEFINE_PER_CPU(struct alloc_tag_counters, _alloc_tag_cntr); \ + static struct alloc_tag _alloc_tag __used __aligned(8) \ + __section("alloc_tags") = { \ + .ct = CODE_TAG_INIT, \ + .counters = &_alloc_tag_cntr }; + +#endif /* ARCH_NEEDS_WEAK_PER_CPU */ + +DECLARE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, + mem_alloc_profiling_key); + +static inline bool mem_alloc_profiling_enabled(void) +{ + return static_branch_maybe(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, + &mem_alloc_profiling_key); +} + +static inline struct alloc_tag_counters alloc_tag_read(struct alloc_tag *tag) +{ + struct alloc_tag_counters v = { 0, 0 }; + struct alloc_tag_counters *counter; + int cpu; + + for_each_possible_cpu(cpu) { + counter = per_cpu_ptr(tag->counters, cpu); + v.bytes += counter->bytes; + v.calls += counter->calls; + } + + return v; +} + +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG +static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag *tag) +{ + WARN_ONCE(ref && ref->ct, + "alloc_tag was not cleared (got tag for %s:%u)\n", + ref->ct->filename, ref->ct->lineno); + + WARN_ONCE(!tag, "current->alloc_tag not set"); +} + +static inline void alloc_tag_sub_check(union codetag_ref *ref) +{ + WARN_ONCE(ref && !ref->ct, "alloc_tag was not set\n"); +} +#else +static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag *tag) {} +static inline void alloc_tag_sub_check(union codetag_ref *ref) {} +#endif + +/* Caller should verify both ref and tag to be valid */ +static inline void __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +{ + ref->ct = &tag->ct; + /* + * We need in increment the call counter every time we have a new + * allocation or when we split a large allocation into smaller ones. + * Each new reference for every sub-allocation needs to increment call + * counter because when we free each part the counter will be decremented. + */ + this_cpu_inc(tag->counters->calls); +} + +static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) +{ + alloc_tag_add_check(ref, tag); + if (!ref || !tag) + return; + + __alloc_tag_ref_set(ref, tag); + this_cpu_add(tag->counters->bytes, bytes); +} + +static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) +{ + struct alloc_tag *tag; + + alloc_tag_sub_check(ref); + if (!ref || !ref->ct) + return; + + tag = ct_to_alloc_tag(ref->ct); + + this_cpu_sub(tag->counters->bytes, bytes); + this_cpu_dec(tag->counters->calls); + + ref->ct = NULL; +} + +#else /* CONFIG_MEM_ALLOC_PROFILING */ + +#define DEFINE_ALLOC_TAG(_alloc_tag) +static inline bool mem_alloc_profiling_enabled(void) { return false; } +static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, + size_t bytes) {} +static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) {} + +#endif /* CONFIG_MEM_ALLOC_PROFILING */ + +#endif /* _LINUX_ALLOC_TAG_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 3c2abbc587b4..4118b3f959c3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -770,6 +770,10 @@ struct task_struct { unsigned int flags; unsigned int ptrace; +#ifdef CONFIG_MEM_ALLOC_PROFILING + struct alloc_tag *alloc_tag; +#endif + #ifdef CONFIG_SMP int on_cpu; struct __call_single_node wake_entry; @@ -810,6 +814,7 @@ struct task_struct { struct task_group *sched_task_group; #endif + #ifdef CONFIG_UCLAMP_TASK /* * Clamp values requested for a scheduling entity. @@ -2187,4 +2192,23 @@ static inline int sched_core_idle_cpu(int cpu) { return idle_cpu(cpu); } extern void sched_set_stop_task(int cpu, struct task_struct *stop); +#ifdef CONFIG_MEM_ALLOC_PROFILING +static inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag) +{ + swap(current->alloc_tag, tag); + return tag; +} + +static inline void alloc_tag_restore(struct alloc_tag *tag, struct alloc_tag *old) +{ +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG + WARN(current->alloc_tag != tag, "current->alloc_tag was changed:\n"); +#endif + current->alloc_tag = old; +} +#else +#define alloc_tag_save(_tag) NULL +#define alloc_tag_restore(_tag, _old) do {} while (0) +#endif + #endif diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 015fc6ee9849..fa7aa32ba11a 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -972,6 +972,31 @@ config CODE_TAGGING bool select KALLSYMS +config MEM_ALLOC_PROFILING + bool "Enable memory allocation profiling" + default n + depends on PROC_FS + depends on !DEBUG_FORCE_WEAK_PER_CPU + select CODE_TAGGING + help + Track allocation source code and record total allocation size + initiated at that code location. The mechanism can be used to track + memory leaks with a low performance and memory impact. + +config MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT + bool "Enable memory allocation profiling by default" + default y + depends on MEM_ALLOC_PROFILING + +config MEM_ALLOC_PROFILING_DEBUG + bool "Memory allocation profiler debugging" + default n + depends on MEM_ALLOC_PROFILING + select MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT + help + Adds warnings with helpful error messages for memory allocation + profiling. + source "lib/Kconfig.kasan" source "lib/Kconfig.kfence" source "lib/Kconfig.kmsan" diff --git a/lib/Makefile b/lib/Makefile index 910335da8f13..2f4e17bfb299 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -234,6 +234,8 @@ obj-$(CONFIG_OF_RECONFIG_NOTIFIER_ERROR_INJECT) += \ obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o obj-$(CONFIG_CODE_TAGGING) += codetag.o +obj-$(CONFIG_MEM_ALLOC_PROFILING) += alloc_tag.o + lib-$(CONFIG_GENERIC_BUG) += bug.o obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c new file mode 100644 index 000000000000..331dd17650f3 --- /dev/null +++ b/lib/alloc_tag.c @@ -0,0 +1,152 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include +#include +#include +#include + +static struct codetag_type *alloc_tag_cttype; + +DEFINE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag); +EXPORT_SYMBOL(_shared_alloc_tag); + +DEFINE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, + mem_alloc_profiling_key); + +static void *allocinfo_start(struct seq_file *m, loff_t *pos) +{ + struct codetag_iterator *iter; + struct codetag *ct; + loff_t node = *pos; + + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + m->private = iter; + if (!iter) + return NULL; + + codetag_lock_module_list(alloc_tag_cttype, true); + *iter = codetag_get_ct_iter(alloc_tag_cttype); + while ((ct = codetag_next_ct(iter)) != NULL && node) + node--; + + return ct ? iter : NULL; +} + +static void *allocinfo_next(struct seq_file *m, void *arg, loff_t *pos) +{ + struct codetag_iterator *iter = (struct codetag_iterator *)arg; + struct codetag *ct = codetag_next_ct(iter); + + (*pos)++; + if (!ct) + return NULL; + + return iter; +} + +static void allocinfo_stop(struct seq_file *m, void *arg) +{ + struct codetag_iterator *iter = (struct codetag_iterator *)m->private; + + if (iter) { + codetag_lock_module_list(alloc_tag_cttype, false); + kfree(iter); + } +} + +static void alloc_tag_to_text(struct seq_buf *out, struct codetag *ct) +{ + struct alloc_tag *tag = ct_to_alloc_tag(ct); + struct alloc_tag_counters counter = alloc_tag_read(tag); + s64 bytes = counter.bytes; + + seq_buf_printf(out, "%12lli %8llu ", bytes, counter.calls); + codetag_to_text(out, ct); + seq_buf_putc(out, ' '); + seq_buf_putc(out, '\n'); +} + +static int allocinfo_show(struct seq_file *m, void *arg) +{ + struct codetag_iterator *iter = (struct codetag_iterator *)arg; + char *bufp; + size_t n = seq_get_buf(m, &bufp); + struct seq_buf buf; + + seq_buf_init(&buf, bufp, n); + alloc_tag_to_text(&buf, iter->ct); + seq_commit(m, seq_buf_used(&buf)); + return 0; +} + +static const struct seq_operations allocinfo_seq_op = { + .start = allocinfo_start, + .next = allocinfo_next, + .stop = allocinfo_stop, + .show = allocinfo_show, +}; + +static void __init procfs_init(void) +{ + proc_create_seq("allocinfo", 0444, NULL, &allocinfo_seq_op); +} + +static bool alloc_tag_module_unload(struct codetag_type *cttype, + struct codetag_module *cmod) +{ + struct codetag_iterator iter = codetag_get_ct_iter(cttype); + struct alloc_tag_counters counter; + bool module_unused = true; + struct alloc_tag *tag; + struct codetag *ct; + + for (ct = codetag_next_ct(&iter); ct; ct = codetag_next_ct(&iter)) { + if (iter.cmod != cmod) + continue; + + tag = ct_to_alloc_tag(ct); + counter = alloc_tag_read(tag); + + if (WARN(counter.bytes, + "%s:%u module %s func:%s has %llu allocated at module unload", + ct->filename, ct->lineno, ct->modname, ct->function, counter.bytes)) + module_unused = false; + } + + return module_unused; +} + +static struct ctl_table memory_allocation_profiling_sysctls[] = { + { + .procname = "mem_profiling", + .data = &mem_alloc_profiling_key, +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG + .mode = 0444, +#else + .mode = 0644, +#endif + .proc_handler = proc_do_static_key, + }, + { } +}; + +static int __init alloc_tag_init(void) +{ + const struct codetag_type_desc desc = { + .section = "alloc_tags", + .tag_size = sizeof(struct alloc_tag), + .module_unload = alloc_tag_module_unload, + }; + + alloc_tag_cttype = codetag_register_type(&desc); + if (IS_ERR(alloc_tag_cttype)) + return PTR_ERR(alloc_tag_cttype); + + register_sysctl_init("vm", memory_allocation_profiling_sysctls); + procfs_init(); + + return 0; +} +module_init(alloc_tag_init); diff --git a/scripts/module.lds.S b/scripts/module.lds.S index bf5bcf2836d8..45c67a0994f3 100644 --- a/scripts/module.lds.S +++ b/scripts/module.lds.S @@ -9,6 +9,8 @@ #define DISCARD_EH_FRAME *(.eh_frame) #endif +#include + SECTIONS { /DISCARD/ : { *(.discard) @@ -47,12 +49,17 @@ SECTIONS { .data : { *(.data .data.[0-9a-zA-Z_]*) *(.data..L*) + CODETAG_SECTIONS() } .rodata : { *(.rodata .rodata.[0-9a-zA-Z_]*) *(.rodata..L*) } +#else + .data : { + CODETAG_SECTIONS() + } #endif } -- cgit v1.2.3 From dcfe378c81f72f146890ce1dcfdcc742d3b66924 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 21 Mar 2024 09:36:36 -0700 Subject: lib: introduce support for page allocation tagging MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce helper functions to easily instrument page allocators by storing a pointer to the allocation tag associated with the code that allocated the page in a page_ext field. Link: https://lkml.kernel.org/r/20240321163705.3067592-15-surenb@google.com Signed-off-by: Suren Baghdasaryan Co-developed-by: Kent Overstreet Signed-off-by: Kent Overstreet Reviewed-by: Vlastimil Babka Tested-by: Kees Cook Cc: Alexander Viro Cc: Alex Gaynor Cc: Alice Ryhl Cc: Andreas Hindborg Cc: Benno Lossin Cc: "Björn Roy Baron" Cc: Boqun Feng Cc: Christoph Lameter Cc: Dennis Zhou Cc: Gary Guo Cc: Miguel Ojeda Cc: Pasha Tatashin Cc: Peter Zijlstra Cc: Tejun Heo Cc: Wedson Almeida Filho Signed-off-by: Andrew Morton --- include/linux/page_ext.h | 1 - include/linux/pgalloc_tag.h | 78 +++++++++++++++++++++++++++++++++++++++++++++ lib/Kconfig.debug | 1 + lib/alloc_tag.c | 17 ++++++++++ mm/mm_init.c | 1 + mm/page_alloc.c | 4 +++ mm/page_ext.c | 4 +++ 7 files changed, 105 insertions(+), 1 deletion(-) create mode 100644 include/linux/pgalloc_tag.h (limited to 'lib') diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index be98564191e6..07e0656898f9 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -4,7 +4,6 @@ #include #include -#include struct pglist_data; diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h new file mode 100644 index 000000000000..66bd021eb46e --- /dev/null +++ b/include/linux/pgalloc_tag.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * page allocation tagging + */ +#ifndef _LINUX_PGALLOC_TAG_H +#define _LINUX_PGALLOC_TAG_H + +#include + +#ifdef CONFIG_MEM_ALLOC_PROFILING + +#include + +extern struct page_ext_operations page_alloc_tagging_ops; +extern struct page_ext *page_ext_get(struct page *page); +extern void page_ext_put(struct page_ext *page_ext); + +static inline union codetag_ref *codetag_ref_from_page_ext(struct page_ext *page_ext) +{ + return (void *)page_ext + page_alloc_tagging_ops.offset; +} + +static inline struct page_ext *page_ext_from_codetag_ref(union codetag_ref *ref) +{ + return (void *)ref - page_alloc_tagging_ops.offset; +} + +/* Should be called only if mem_alloc_profiling_enabled() */ +static inline union codetag_ref *get_page_tag_ref(struct page *page) +{ + if (page) { + struct page_ext *page_ext = page_ext_get(page); + + if (page_ext) + return codetag_ref_from_page_ext(page_ext); + } + return NULL; +} + +static inline void put_page_tag_ref(union codetag_ref *ref) +{ + page_ext_put(page_ext_from_codetag_ref(ref)); +} + +static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + alloc_tag_add(ref, task->alloc_tag, PAGE_SIZE * nr); + put_page_tag_ref(ref); + } + } +} + +static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + alloc_tag_sub(ref, PAGE_SIZE * nr); + put_page_tag_ref(ref); + } + } +} + +#else /* CONFIG_MEM_ALLOC_PROFILING */ + +static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) {} +static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} + +#endif /* CONFIG_MEM_ALLOC_PROFILING */ + +#endif /* _LINUX_PGALLOC_TAG_H */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index fa7aa32ba11a..a8f77de5e8ea 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -978,6 +978,7 @@ config MEM_ALLOC_PROFILING depends on PROC_FS depends on !DEBUG_FORCE_WEAK_PER_CPU select CODE_TAGGING + select PAGE_EXTENSION help Track allocation source code and record total allocation size initiated at that code location. The mechanism can be used to track diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 331dd17650f3..59bb71036837 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include #include @@ -118,6 +119,22 @@ static bool alloc_tag_module_unload(struct codetag_type *cttype, return module_unused; } +static __init bool need_page_alloc_tagging(void) +{ + return true; +} + +static __init void init_page_alloc_tagging(void) +{ +} + +struct page_ext_operations page_alloc_tagging_ops = { + .size = sizeof(union codetag_ref), + .need = need_page_alloc_tagging, + .init = init_page_alloc_tagging, +}; +EXPORT_SYMBOL(page_alloc_tagging_ops); + static struct ctl_table memory_allocation_profiling_sysctls[] = { { .procname = "mem_profiling", diff --git a/mm/mm_init.c b/mm/mm_init.c index 549e76af8f82..2fd9bf044a79 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5083ac034d26..3fd273c22749 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #include "internal.h" #include "shuffle.h" @@ -1101,6 +1102,7 @@ __always_inline bool free_pages_prepare(struct page *page, /* Do not let hwpoison pages hit pcplists/buddy */ reset_page_owner(page, order); page_table_check_free(page, order); + pgalloc_tag_sub(page, 1 << order); return false; } @@ -1140,6 +1142,7 @@ __always_inline bool free_pages_prepare(struct page *page, page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; reset_page_owner(page, order); page_table_check_free(page, order); + pgalloc_tag_sub(page, 1 << order); if (!PageHighMem(page)) { debug_check_no_locks_freed(page_address(page), @@ -1533,6 +1536,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order, set_page_owner(page, order, gfp_flags); page_table_check_alloc(page, order); + pgalloc_tag_add(page, current, 1 << order); } static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, diff --git a/mm/page_ext.c b/mm/page_ext.c index 4548fcc66d74..3c58fe8a24df 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -10,6 +10,7 @@ #include #include #include +#include /* * struct page extension @@ -82,6 +83,9 @@ static struct page_ext_operations *page_ext_ops[] __initdata = { #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) &page_idle_ops, #endif +#ifdef CONFIG_MEM_ALLOC_PROFILING + &page_alloc_tagging_ops, +#endif #ifdef CONFIG_PAGE_TABLE_CHECK &page_table_check_ops, #endif -- cgit v1.2.3 From 8d469d0bee74d3f2d02f0b232933a3f084d9cbf7 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 21 Mar 2024 09:36:37 -0700 Subject: lib: introduce early boot parameter to avoid page_ext memory overhead MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The highest memory overhead from memory allocation profiling comes from page_ext objects. This overhead exists even if the feature is disabled but compiled-in. To avoid it, introduce an early boot parameter that prevents page_ext object creation. The new boot parameter is a tri-state with possible values of 0|1|never. When it is set to "never" the memory allocation profiling support is disabled, and overhead is minimized (currently no page_ext objects are allocated, in the future more overhead might be eliminated). As a result we also lose ability to enable memory allocation profiling at runtime (because there is no space to store alloctag references). Runtime sysctrl becomes read-only if the early boot parameter was set to "never". Note that the default value of this boot parameter depends on the CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT configuration. When CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT=n the boot parameter is set to "never", therefore eliminating any overhead. CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT=y results in boot parameter being set to 1 (enabled). This allows distributions to avoid any overhead by setting CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT=n config and with no changes to the kernel command line. We reuse sysctl.vm.mem_profiling boot parameter name in order to avoid introducing yet another control. This change turns it into a tri-state early boot parameter. Link: https://lkml.kernel.org/r/20240321163705.3067592-16-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Vlastimil Babka Tested-by: Kees Cook Cc: Alexander Viro Cc: Alex Gaynor Cc: Alice Ryhl Cc: Andreas Hindborg Cc: Benno Lossin Cc: "Björn Roy Baron" Cc: Boqun Feng Cc: Christoph Lameter Cc: Dennis Zhou Cc: Gary Guo Cc: Kent Overstreet Cc: Miguel Ojeda Cc: Pasha Tatashin Cc: Peter Zijlstra Cc: Tejun Heo Cc: Wedson Almeida Filho Signed-off-by: Andrew Morton --- lib/alloc_tag.c | 41 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 40 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 59bb71036837..6bd8e85beaf7 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -119,9 +119,46 @@ static bool alloc_tag_module_unload(struct codetag_type *cttype, return module_unused; } +#ifdef CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT +static bool mem_profiling_support __meminitdata = true; +#else +static bool mem_profiling_support __meminitdata; +#endif + +static int __init setup_early_mem_profiling(char *str) +{ + bool enable; + + if (!str || !str[0]) + return -EINVAL; + + if (!strncmp(str, "never", 5)) { + enable = false; + mem_profiling_support = false; + } else { + int res; + + res = kstrtobool(str, &enable); + if (res) + return res; + + mem_profiling_support = true; + } + + if (enable != static_key_enabled(&mem_alloc_profiling_key)) { + if (enable) + static_branch_enable(&mem_alloc_profiling_key); + else + static_branch_disable(&mem_alloc_profiling_key); + } + + return 0; +} +early_param("sysctl.vm.mem_profiling", setup_early_mem_profiling); + static __init bool need_page_alloc_tagging(void) { - return true; + return mem_profiling_support; } static __init void init_page_alloc_tagging(void) @@ -161,6 +198,8 @@ static int __init alloc_tag_init(void) if (IS_ERR(alloc_tag_cttype)) return PTR_ERR(alloc_tag_cttype); + if (!mem_profiling_support) + memory_allocation_profiling_sysctls[0].mode = 0444; register_sysctl_init("vm", memory_allocation_profiling_sysctls); procfs_init(); -- cgit v1.2.3 From c789b5fe38f386bbdec8c9c41e9af52d3775e16c Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 21 Mar 2024 09:36:44 -0700 Subject: lib: add codetag reference into slabobj_ext MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To store code tag for every slab object, a codetag reference is embedded into slabobj_ext when CONFIG_MEM_ALLOC_PROFILING=y. Link: https://lkml.kernel.org/r/20240321163705.3067592-23-surenb@google.com Signed-off-by: Suren Baghdasaryan Co-developed-by: Kent Overstreet Signed-off-by: Kent Overstreet Reviewed-by: Vlastimil Babka Tested-by: Kees Cook Cc: Alexander Viro Cc: Alex Gaynor Cc: Alice Ryhl Cc: Andreas Hindborg Cc: Benno Lossin Cc: "Björn Roy Baron" Cc: Boqun Feng Cc: Christoph Lameter Cc: Dennis Zhou Cc: Gary Guo Cc: Miguel Ojeda Cc: Pasha Tatashin Cc: Peter Zijlstra Cc: Tejun Heo Cc: Wedson Almeida Filho Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 5 +++++ lib/Kconfig.debug | 1 + 2 files changed, 6 insertions(+) (limited to 'lib') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 12afc2647cf0..24a6df30be49 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1653,7 +1653,12 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, * if MEMCG_DATA_OBJEXTS is set. */ struct slabobj_ext { +#ifdef CONFIG_MEMCG_KMEM struct obj_cgroup *objcg; +#endif +#ifdef CONFIG_MEM_ALLOC_PROFILING + union codetag_ref ref; +#endif } __aligned(8); static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index a8f77de5e8ea..9d2685ec4592 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -979,6 +979,7 @@ config MEM_ALLOC_PROFILING depends on !DEBUG_FORCE_WEAK_PER_CPU select CODE_TAGGING select PAGE_EXTENSION + select SLAB_OBJ_EXT help Track allocation source code and record total allocation size initiated at that code location. The mechanism can be used to track -- cgit v1.2.3 From 9e54dd8b64dccdf5336172bf905017a6f97ee18d Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Thu, 21 Mar 2024 09:36:53 -0700 Subject: rhashtable: plumb through alloc tag MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This gives better memory allocation profiling results; rhashtable allocations will be accounted to the code that initialized the rhashtable. [surenb@google.com: undo _noprof additions in the documentation] Link: https://lkml.kernel.org/r/20240326231453.1206227-1-surenb@google.com Link: https://lkml.kernel.org/r/20240321163705.3067592-32-surenb@google.com Signed-off-by: Kent Overstreet Signed-off-by: Suren Baghdasaryan Tested-by: Kees Cook Cc: Alexander Viro Cc: Alex Gaynor Cc: Alice Ryhl Cc: Andreas Hindborg Cc: Benno Lossin Cc: "Björn Roy Baron" Cc: Boqun Feng Cc: Christoph Lameter Cc: Dennis Zhou Cc: Gary Guo Cc: Miguel Ojeda Cc: Pasha Tatashin Cc: Peter Zijlstra Cc: Tejun Heo Cc: Vlastimil Babka Cc: Wedson Almeida Filho Signed-off-by: Andrew Morton --- include/linux/alloc_tag.h | 3 +++ include/linux/rhashtable-types.h | 11 +++++++++-- lib/rhashtable.c | 22 ++++++++++++++-------- 3 files changed, 26 insertions(+), 10 deletions(-) (limited to 'lib') diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 2aea7afa1fab..0567766e50bd 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -152,6 +152,8 @@ static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) ref->ct = NULL; } +#define alloc_tag_record(p) ((p) = current->alloc_tag) + #else /* CONFIG_MEM_ALLOC_PROFILING */ #define DEFINE_ALLOC_TAG(_alloc_tag) @@ -159,6 +161,7 @@ static inline bool mem_alloc_profiling_enabled(void) { return false; } static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) {} static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) {} +#define alloc_tag_record(p) do {} while (0) #endif /* CONFIG_MEM_ALLOC_PROFILING */ diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h index b6f3797277ff..015c8298bebc 100644 --- a/include/linux/rhashtable-types.h +++ b/include/linux/rhashtable-types.h @@ -9,6 +9,7 @@ #ifndef _LINUX_RHASHTABLE_TYPES_H #define _LINUX_RHASHTABLE_TYPES_H +#include #include #include #include @@ -88,6 +89,9 @@ struct rhashtable { struct mutex mutex; spinlock_t lock; atomic_t nelems; +#ifdef CONFIG_MEM_ALLOC_PROFILING + struct alloc_tag *alloc_tag; +#endif }; /** @@ -127,9 +131,12 @@ struct rhashtable_iter { bool end_of_table; }; -int rhashtable_init(struct rhashtable *ht, +int rhashtable_init_noprof(struct rhashtable *ht, const struct rhashtable_params *params); -int rhltable_init(struct rhltable *hlt, +#define rhashtable_init(...) alloc_hooks(rhashtable_init_noprof(__VA_ARGS__)) + +int rhltable_init_noprof(struct rhltable *hlt, const struct rhashtable_params *params); +#define rhltable_init(...) alloc_hooks(rhltable_init_noprof(__VA_ARGS__)) #endif /* _LINUX_RHASHTABLE_TYPES_H */ diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 6ae2ba8e06a2..dbbed19f8fff 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -130,7 +130,8 @@ static union nested_table *nested_table_alloc(struct rhashtable *ht, if (ntbl) return ntbl; - ntbl = kzalloc(PAGE_SIZE, GFP_ATOMIC); + ntbl = alloc_hooks_tag(ht->alloc_tag, + kmalloc_noprof(PAGE_SIZE, GFP_ATOMIC|__GFP_ZERO)); if (ntbl && leaf) { for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0]); i++) @@ -157,7 +158,8 @@ static struct bucket_table *nested_bucket_table_alloc(struct rhashtable *ht, size = sizeof(*tbl) + sizeof(tbl->buckets[0]); - tbl = kzalloc(size, gfp); + tbl = alloc_hooks_tag(ht->alloc_tag, + kmalloc_noprof(size, gfp|__GFP_ZERO)); if (!tbl) return NULL; @@ -181,7 +183,9 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, int i; static struct lock_class_key __key; - tbl = kvzalloc(struct_size(tbl, buckets, nbuckets), gfp); + tbl = alloc_hooks_tag(ht->alloc_tag, + kvmalloc_node_noprof(struct_size(tbl, buckets, nbuckets), + gfp|__GFP_ZERO, NUMA_NO_NODE)); size = nbuckets; @@ -1016,7 +1020,7 @@ static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed) * .obj_hashfn = my_hash_fn, * }; */ -int rhashtable_init(struct rhashtable *ht, +int rhashtable_init_noprof(struct rhashtable *ht, const struct rhashtable_params *params) { struct bucket_table *tbl; @@ -1031,6 +1035,8 @@ int rhashtable_init(struct rhashtable *ht, spin_lock_init(&ht->lock); memcpy(&ht->p, params, sizeof(*params)); + alloc_tag_record(ht->alloc_tag); + if (params->min_size) ht->p.min_size = roundup_pow_of_two(params->min_size); @@ -1076,7 +1082,7 @@ int rhashtable_init(struct rhashtable *ht, return 0; } -EXPORT_SYMBOL_GPL(rhashtable_init); +EXPORT_SYMBOL_GPL(rhashtable_init_noprof); /** * rhltable_init - initialize a new hash list table @@ -1087,15 +1093,15 @@ EXPORT_SYMBOL_GPL(rhashtable_init); * * See documentation for rhashtable_init. */ -int rhltable_init(struct rhltable *hlt, const struct rhashtable_params *params) +int rhltable_init_noprof(struct rhltable *hlt, const struct rhashtable_params *params) { int err; - err = rhashtable_init(&hlt->ht, params); + err = rhashtable_init_noprof(&hlt->ht, params); hlt->ht.rhlist = true; return err; } -EXPORT_SYMBOL_GPL(rhltable_init); +EXPORT_SYMBOL_GPL(rhltable_init_noprof); static void rhashtable_free_one(struct rhashtable *ht, struct rhash_head *obj, void (*free_fn)(void *ptr, void *arg), -- cgit v1.2.3 From 1438d349d16b78d88f9e978a4a5496f078c8191b Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 21 Mar 2024 09:36:54 -0700 Subject: lib: add memory allocations report in show_mem() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Include allocations in show_mem reports. Link: https://lkml.kernel.org/r/20240321163705.3067592-33-surenb@google.com Signed-off-by: Kent Overstreet Signed-off-by: Suren Baghdasaryan Reviewed-by: Vlastimil Babka Tested-by: Kees Cook Cc: Alexander Viro Cc: Alex Gaynor Cc: Alice Ryhl Cc: Andreas Hindborg Cc: Benno Lossin Cc: "Björn Roy Baron" Cc: Boqun Feng Cc: Christoph Lameter Cc: Dennis Zhou Cc: Gary Guo Cc: Miguel Ojeda Cc: Pasha Tatashin Cc: Peter Zijlstra Cc: Tejun Heo Cc: Wedson Almeida Filho Signed-off-by: Andrew Morton --- include/linux/alloc_tag.h | 7 +++++++ include/linux/codetag.h | 1 + lib/alloc_tag.c | 38 ++++++++++++++++++++++++++++++++++++++ lib/codetag.c | 5 +++++ mm/show_mem.c | 26 ++++++++++++++++++++++++++ 5 files changed, 77 insertions(+) (limited to 'lib') diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 0567766e50bd..d18388c0e9e1 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -31,6 +31,13 @@ struct alloc_tag { #ifdef CONFIG_MEM_ALLOC_PROFILING +struct codetag_bytes { + struct codetag *ct; + s64 bytes; +}; + +size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sleep); + static inline struct alloc_tag *ct_to_alloc_tag(struct codetag *ct) { return container_of(ct, struct alloc_tag, ct); diff --git a/include/linux/codetag.h b/include/linux/codetag.h index bfd0ba5c4185..c2a579ccd455 100644 --- a/include/linux/codetag.h +++ b/include/linux/codetag.h @@ -61,6 +61,7 @@ struct codetag_iterator { } void codetag_lock_module_list(struct codetag_type *cttype, bool lock); +bool codetag_trylock_module_list(struct codetag_type *cttype); struct codetag_iterator codetag_get_ct_iter(struct codetag_type *cttype); struct codetag *codetag_next_ct(struct codetag_iterator *iter); diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 6bd8e85beaf7..26af9982ddc4 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -89,6 +89,44 @@ static const struct seq_operations allocinfo_seq_op = { .show = allocinfo_show, }; +size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sleep) +{ + struct codetag_iterator iter; + struct codetag *ct; + struct codetag_bytes n; + unsigned int i, nr = 0; + + if (can_sleep) + codetag_lock_module_list(alloc_tag_cttype, true); + else if (!codetag_trylock_module_list(alloc_tag_cttype)) + return 0; + + iter = codetag_get_ct_iter(alloc_tag_cttype); + while ((ct = codetag_next_ct(&iter))) { + struct alloc_tag_counters counter = alloc_tag_read(ct_to_alloc_tag(ct)); + + n.ct = ct; + n.bytes = counter.bytes; + + for (i = 0; i < nr; i++) + if (n.bytes > tags[i].bytes) + break; + + if (i < count) { + nr -= nr == count; + memmove(&tags[i + 1], + &tags[i], + sizeof(tags[0]) * (nr - i)); + nr++; + tags[i] = n; + } + } + + codetag_lock_module_list(alloc_tag_cttype, false); + + return nr; +} + static void __init procfs_init(void) { proc_create_seq("allocinfo", 0444, NULL, &allocinfo_seq_op); diff --git a/lib/codetag.c b/lib/codetag.c index 408062f722ce..5ace625f2328 100644 --- a/lib/codetag.c +++ b/lib/codetag.c @@ -36,6 +36,11 @@ void codetag_lock_module_list(struct codetag_type *cttype, bool lock) up_read(&cttype->mod_lock); } +bool codetag_trylock_module_list(struct codetag_type *cttype) +{ + return down_read_trylock(&cttype->mod_lock) != 0; +} + struct codetag_iterator codetag_get_ct_iter(struct codetag_type *cttype) { struct codetag_iterator iter = { diff --git a/mm/show_mem.c b/mm/show_mem.c index 8dcfafbd283c..bdb439551eef 100644 --- a/mm/show_mem.c +++ b/mm/show_mem.c @@ -423,4 +423,30 @@ void __show_mem(unsigned int filter, nodemask_t *nodemask, int max_zone_idx) #ifdef CONFIG_MEMORY_FAILURE printk("%lu pages hwpoisoned\n", atomic_long_read(&num_poisoned_pages)); #endif +#ifdef CONFIG_MEM_ALLOC_PROFILING + { + struct codetag_bytes tags[10]; + size_t i, nr; + + nr = alloc_tag_top_users(tags, ARRAY_SIZE(tags), false); + if (nr) { + pr_notice("Memory allocations:\n"); + for (i = 0; i < nr; i++) { + struct codetag *ct = tags[i].ct; + struct alloc_tag *tag = ct_to_alloc_tag(ct); + struct alloc_tag_counters counter = alloc_tag_read(tag); + + /* Same as alloc_tag_to_text() but w/o intermediate buffer */ + if (ct->modname) + pr_notice("%12lli %8llu %s:%u [%s] func:%s\n", + counter.bytes, counter.calls, ct->filename, + ct->lineno, ct->modname, ct->function); + else + pr_notice("%12lli %8llu %s:%u func:%s\n", + counter.bytes, counter.calls, ct->filename, + ct->lineno, ct->function); + } + } + } +#endif } -- cgit v1.2.3 From e13106952faad91c6e492bf23b7cbdf1b1c269ce Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 25 Apr 2024 13:08:50 -0700 Subject: alloc_tag: Tighten file permissions on /proc/allocinfo The /proc/allocinfo file exposes a tremendous about of information about kernel build details, memory allocations (obviously), and potentially even image layout (due to ordering). As this is intended to be consumed by system owners (like /proc/slabinfo), use the same file permissions as there: 0400. Link: https://lkml.kernel.org/r/20240425200844.work.184-kees@kernel.org Signed-off-by: Kees Cook Cc: Kent Overstreet Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- lib/alloc_tag.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 26af9982ddc4..531dbe2f5456 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -129,7 +129,7 @@ size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sl static void __init procfs_init(void) { - proc_create_seq("allocinfo", 0444, NULL, &allocinfo_seq_op); + proc_create_seq("allocinfo", 0400, NULL, &allocinfo_seq_op); } static bool alloc_tag_module_unload(struct codetag_type *cttype, -- cgit v1.2.3 From a4864671ca0bf51c8e78242951741df52c06766f Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Tue, 16 Apr 2024 01:18:55 +0800 Subject: lib/xarray: introduce a new helper xas_get_order It can be used after xas_load to check the order of loaded entries. Compared to xa_get_order, it saves an XA_STATE and avoid a rewalk. Added new test for xas_get_order, to make the test work, we have to export xas_get_order with EXPORT_SYMBOL_GPL. Also fix a sparse warning by checking the slot value with xa_entry instead of accessing it directly, as suggested by Matthew Wilcox. [kasong@tencent.com: simplify comment, sparse warning fix, per Matthew Wilcox] Link: https://lkml.kernel.org/r/20240416071722.45997-4-ryncsn@gmail.com Link: https://lkml.kernel.org/r/20240415171857.19244-4-ryncsn@gmail.com Signed-off-by: Kairui Song Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/xarray.h | 6 ++++++ lib/test_xarray.c | 34 ++++++++++++++++++++++++++++++++++ lib/xarray.c | 49 +++++++++++++++++++++++++++++++------------------ 3 files changed, 71 insertions(+), 18 deletions(-) (limited to 'lib') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index cb571dfcf4b1..d9d479334c9e 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -1548,6 +1548,7 @@ void xas_create_range(struct xa_state *); #ifdef CONFIG_XARRAY_MULTI int xa_get_order(struct xarray *, unsigned long index); +int xas_get_order(struct xa_state *xas); void xas_split(struct xa_state *, void *entry, unsigned int order); void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t); #else @@ -1556,6 +1557,11 @@ static inline int xa_get_order(struct xarray *xa, unsigned long index) return 0; } +static inline int xas_get_order(struct xa_state *xas) +{ + return 0; +} + static inline void xas_split(struct xa_state *xas, void *entry, unsigned int order) { diff --git a/lib/test_xarray.c b/lib/test_xarray.c index ebe2af2e072d..0efde8f93490 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -1984,6 +1984,39 @@ static noinline void check_get_order(struct xarray *xa) } } +static noinline void check_xas_get_order(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + + unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1; + unsigned int order; + unsigned long i, j; + + for (order = 0; order < max_order; order++) { + for (i = 0; i < 10; i++) { + xas_set_order(&xas, i << order, order); + do { + xas_lock(&xas); + xas_store(&xas, xa_mk_value(i)); + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + for (j = i << order; j < (i + 1) << order; j++) { + xas_set_order(&xas, j, 0); + rcu_read_lock(); + xas_load(&xas); + XA_BUG_ON(xa, xas_get_order(&xas) != order); + rcu_read_unlock(); + } + + xas_lock(&xas); + xas_set_order(&xas, i << order, order); + xas_store(&xas, NULL); + xas_unlock(&xas); + } + } +} + static noinline void check_destroy(struct xarray *xa) { unsigned long index; @@ -2035,6 +2068,7 @@ static int xarray_checks(void) check_multi_store(&array); check_multi_store_advanced(&array); check_get_order(&array); + check_xas_get_order(&array); check_xa_alloc(); check_find(&array); check_find_entry(&array); diff --git a/lib/xarray.c b/lib/xarray.c index 39f07bfc4dcc..da79128ad754 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1750,39 +1750,52 @@ unlock: EXPORT_SYMBOL(xa_store_range); /** - * xa_get_order() - Get the order of an entry. - * @xa: XArray. - * @index: Index of the entry. + * xas_get_order() - Get the order of an entry. + * @xas: XArray operation state. + * + * Called after xas_load, the xas should not be in an error state. * * Return: A number between 0 and 63 indicating the order of the entry. */ -int xa_get_order(struct xarray *xa, unsigned long index) +int xas_get_order(struct xa_state *xas) { - XA_STATE(xas, xa, index); - void *entry; int order = 0; - rcu_read_lock(); - entry = xas_load(&xas); - - if (!entry) - goto unlock; - - if (!xas.xa_node) - goto unlock; + if (!xas->xa_node) + return 0; for (;;) { - unsigned int slot = xas.xa_offset + (1 << order); + unsigned int slot = xas->xa_offset + (1 << order); if (slot >= XA_CHUNK_SIZE) break; - if (!xa_is_sibling(xas.xa_node->slots[slot])) + if (!xa_is_sibling(xa_entry(xas->xa, xas->xa_node, slot))) break; order++; } - order += xas.xa_node->shift; -unlock: + order += xas->xa_node->shift; + return order; +} +EXPORT_SYMBOL_GPL(xas_get_order); + +/** + * xa_get_order() - Get the order of an entry. + * @xa: XArray. + * @index: Index of the entry. + * + * Return: A number between 0 and 63 indicating the order of the entry. + */ +int xa_get_order(struct xarray *xa, unsigned long index) +{ + XA_STATE(xas, xa, index); + int order = 0; + void *entry; + + rcu_read_lock(); + entry = xas_load(&xas); + if (entry) + order = xas_get_order(&xas); rcu_read_unlock(); return order; -- cgit v1.2.3 From 6758c1128ceb45d1a35298912b974eb4895b7dd9 Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Tue, 16 Apr 2024 01:18:56 +0800 Subject: mm/filemap: optimize filemap folio adding MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead of doing multiple tree walks, do one optimism range check with lock hold, and exit if raced with another insertion. If a shadow exists, check it with a new xas_get_order helper before releasing the lock to avoid redundant tree walks for getting its order. Drop the lock and do the allocation only if a split is needed. In the best case, it only need to walk the tree once. If it needs to alloc and split, 3 walks are issued (One for first ranged conflict check and order retrieving, one for the second check after allocation, one for the insert after split). Testing with 4K pages, in an 8G cgroup, with 16G brd as block device: echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap --rw=randread --time_based \ --ramp_time=30s --runtime=5m --group_reporting Before: bw ( MiB/s): min= 1027, max= 3520, per=100.00%, avg=2445.02, stdev=18.90, samples=8691 iops : min=263001, max=901288, avg=625924.36, stdev=4837.28, samples=8691 After (+7.3%): bw ( MiB/s): min= 493, max= 3947, per=100.00%, avg=2625.56, stdev=25.74, samples=8651 iops : min=126454, max=1010681, avg=672142.61, stdev=6590.48, samples=8651 Test result with THP (do a THP randread then switch to 4K page in hope it issues a lot of splitting): echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap -thp=1 --readonly \ --rw=randread --time_based --ramp_time=30s --runtime=10m \ --group_reporting fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap \ --rw=randread --time_based --runtime=5s --group_reporting Before: bw ( KiB/s): min= 4141, max=14202, per=100.00%, avg=7935.51, stdev=96.85, samples=18976 iops : min= 1029, max= 3548, avg=1979.52, stdev=24.23, samples=18976· READ: bw=4545B/s (4545B/s), 4545B/s-4545B/s (4545B/s-4545B/s), io=64.0KiB (65.5kB), run=14419-14419msec After (+12.5%): bw ( KiB/s): min= 4611, max=15370, per=100.00%, avg=8928.74, stdev=105.17, samples=19146 iops : min= 1151, max= 3842, avg=2231.27, stdev=26.29, samples=19146 READ: bw=4635B/s (4635B/s), 4635B/s-4635B/s (4635B/s-4635B/s), io=64.0KiB (65.5kB), run=14137-14137msec The performance is better for both 4K (+7.5%) and THP (+12.5%) cached read. Link: https://lkml.kernel.org/r/20240415171857.19244-5-ryncsn@gmail.com Signed-off-by: Kairui Song Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- lib/test_xarray.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ mm/filemap.c | 56 ++++++++++++++++++++++++++++++++++++++-------------- 2 files changed, 100 insertions(+), 15 deletions(-) (limited to 'lib') diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 0efde8f93490..8732a311f613 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -2017,6 +2017,64 @@ static noinline void check_xas_get_order(struct xarray *xa) } } +static noinline void check_xas_conflict_get_order(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + + void *entry; + int only_once; + unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1; + unsigned int order; + unsigned long i, j, k; + + for (order = 0; order < max_order; order++) { + for (i = 0; i < 10; i++) { + xas_set_order(&xas, i << order, order); + do { + xas_lock(&xas); + xas_store(&xas, xa_mk_value(i)); + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + /* + * Ensure xas_get_order works with xas_for_each_conflict. + */ + j = i << order; + for (k = 0; k < order; k++) { + only_once = 0; + xas_set_order(&xas, j + (1 << k), k); + xas_lock(&xas); + xas_for_each_conflict(&xas, entry) { + XA_BUG_ON(xa, entry != xa_mk_value(i)); + XA_BUG_ON(xa, xas_get_order(&xas) != order); + only_once++; + } + XA_BUG_ON(xa, only_once != 1); + xas_unlock(&xas); + } + + if (order < max_order - 1) { + only_once = 0; + xas_set_order(&xas, (i & ~1UL) << order, order + 1); + xas_lock(&xas); + xas_for_each_conflict(&xas, entry) { + XA_BUG_ON(xa, entry != xa_mk_value(i)); + XA_BUG_ON(xa, xas_get_order(&xas) != order); + only_once++; + } + XA_BUG_ON(xa, only_once != 1); + xas_unlock(&xas); + } + + xas_set_order(&xas, i << order, order); + xas_lock(&xas); + xas_store(&xas, NULL); + xas_unlock(&xas); + } + } +} + + static noinline void check_destroy(struct xarray *xa) { unsigned long index; @@ -2069,6 +2127,7 @@ static int xarray_checks(void) check_multi_store_advanced(&array); check_get_order(&array); check_xas_get_order(&array); + check_xas_conflict_get_order(&array); check_xa_alloc(); check_find(&array); check_find_entry(&array); diff --git a/mm/filemap.c b/mm/filemap.c index 17a66ea544e7..7b0b2229d4ed 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -852,7 +852,9 @@ noinline int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp) { XA_STATE(xas, &mapping->i_pages, index); - bool huge = folio_test_hugetlb(folio); + void *alloced_shadow = NULL; + int alloced_order = 0; + bool huge; long nr; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); @@ -861,6 +863,7 @@ noinline int __filemap_add_folio(struct address_space *mapping, VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); xas_set_order(&xas, index, folio_order(folio)); + huge = folio_test_hugetlb(folio); nr = folio_nr_pages(folio); gfp &= GFP_RECLAIM_MASK; @@ -868,16 +871,10 @@ noinline int __filemap_add_folio(struct address_space *mapping, folio->mapping = mapping; folio->index = xas.xa_index; - do { - unsigned int order = xa_get_order(xas.xa, xas.xa_index); + for (;;) { + int order = -1, split_order = 0; void *entry, *old = NULL; - if (order > folio_order(folio)) { - xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index), - order, gfp); - if (xas_error(&xas)) - goto error; - } xas_lock_irq(&xas); xas_for_each_conflict(&xas, entry) { old = entry; @@ -885,19 +882,33 @@ noinline int __filemap_add_folio(struct address_space *mapping, xas_set_err(&xas, -EEXIST); goto unlock; } + /* + * If a larger entry exists, + * it will be the first and only entry iterated. + */ + if (order == -1) + order = xas_get_order(&xas); + } + + /* entry may have changed before we re-acquire the lock */ + if (alloced_order && (old != alloced_shadow || order != alloced_order)) { + xas_destroy(&xas); + alloced_order = 0; } if (old) { - if (shadowp) - *shadowp = old; - /* entry may have been split before we acquired lock */ - order = xa_get_order(xas.xa, xas.xa_index); - if (order > folio_order(folio)) { + if (order > 0 && order > folio_order(folio)) { /* How to handle large swap entries? */ BUG_ON(shmem_mapping(mapping)); + if (!alloced_order) { + split_order = order; + goto unlock; + } xas_split(&xas, old, order); xas_reset(&xas); } + if (shadowp) + *shadowp = old; } xas_store(&xas, folio); @@ -913,9 +924,24 @@ noinline int __filemap_add_folio(struct address_space *mapping, __lruvec_stat_mod_folio(folio, NR_FILE_THPS, nr); } + unlock: xas_unlock_irq(&xas); - } while (xas_nomem(&xas, gfp)); + + /* split needed, alloc here and retry. */ + if (split_order) { + xas_split_alloc(&xas, old, split_order, gfp); + if (xas_error(&xas)) + goto error; + alloced_shadow = old; + alloced_order = split_order; + xas_reset(&xas); + continue; + } + + if (!xas_nomem(&xas, gfp)) + break; + } if (xas_error(&xas)) goto error; -- cgit v1.2.3 From 5ef6dc08cfde240b8c748733759185646e654570 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Wed, 13 Mar 2024 22:19:56 +0100 Subject: lib/build_OID_registry: don't mention the full path of the script in output MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This change strips the full path of the script generating lib/oid_registry_data.c to just lib/build_OID_registry. The motivation for this change is Yocto emitting a build warning File /usr/src/debug/linux-lxatac/6.7-r0/lib/oid_registry_data.c in package linux-lxatac-src contains reference to TMPDIR [buildpaths] So this change brings us one step closer to make the build result reproducible independent of the build path. Link: https://lkml.kernel.org/r/20240313211957.884561-2-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Cc: Masahiro Yamada Reviewed-by: Nicolas Schier Signed-off-by: Andrew Morton --- lib/build_OID_registry | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/build_OID_registry b/lib/build_OID_registry index d7fc32ea8ac2..56d8bafeb848 100755 --- a/lib/build_OID_registry +++ b/lib/build_OID_registry @@ -8,6 +8,7 @@ # use strict; +use Cwd qw(abs_path); my @names = (); my @oids = (); @@ -17,6 +18,8 @@ if ($#ARGV != 1) { exit(2); } +my $abs_srctree = abs_path($ENV{'srctree'}); + # # Open the file to read from # @@ -35,7 +38,7 @@ close IN_FILE || die; # open C_FILE, ">$ARGV[1]" or die; print C_FILE "/*\n"; -print C_FILE " * Automatically generated by ", $0, ". Do not edit\n"; +print C_FILE " * Automatically generated by ", $0 =~ s#^\Q$abs_srctree/\E##r, ". Do not edit\n"; print C_FILE " */\n"; # -- cgit v1.2.3 From b157f0e97e3ed6158cde4f247da4c537c3f6a0f9 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Wed, 3 Apr 2024 15:25:47 +0200 Subject: kgdb: add HAS_IOPORT dependency In a future patch HAS_IOPORT=n will disable inb()/outb() and friends at compile time. We thus need to add HAS_IOPORT as dependency for those drivers using them. Link: https://lkml.kernel.org/r/20240403132547.762429-2-schnelle@linux.ibm.com Co-developed-by: Arnd Bergmann Signed-off-by: Arnd Bergmann Signed-off-by: Niklas Schnelle Signed-off-by: Andrew Morton --- lib/Kconfig.kgdb | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb index b5c0e6576749..537e1b3f5734 100644 --- a/lib/Kconfig.kgdb +++ b/lib/Kconfig.kgdb @@ -122,6 +122,7 @@ config KDB_DEFAULT_ENABLE config KDB_KEYBOARD bool "KGDB_KDB: keyboard as input device" depends on VT && KGDB_KDB && !PARISC + depends on HAS_IOPORT default n help KDB can use a PS/2 type keyboard for an input device -- cgit v1.2.3 From f36c54f3ce3d69aadccc56bc7dc2cf6c464f3522 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 3 Apr 2024 13:46:56 +0300 Subject: devres: switch to use dev_err_probe() for unification Patch series "devres: A couple of cleanups". A couple of ad-hoc cleanups. No functional changes intended. This patch (of 2): The devm_*() APIs are supposed to be called during the ->probe() stage. Many drivers (especially new ones) have switched to use dev_err_probe() for error messaging for the sake of unification. Let's do the same in the devres APIs. Link: https://lkml.kernel.org/r/20240403104820.557487-1-andriy.shevchenko@linux.intel.com Link: https://lkml.kernel.org/r/20240403104820.557487-2-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Reviewed-by: Philipp Stanner Signed-off-by: Andrew Morton --- lib/devres.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'lib') diff --git a/lib/devres.c b/lib/devres.c index fe0c63caeb68..27f280a39dca 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -125,12 +125,13 @@ __devm_ioremap_resource(struct device *dev, const struct resource *res, resource_size_t size; void __iomem *dest_ptr; char *pretty_name; + int ret; BUG_ON(!dev); if (!res || resource_type(res) != IORESOURCE_MEM) { - dev_err(dev, "invalid resource %pR\n", res); - return IOMEM_ERR_PTR(-EINVAL); + ret = dev_err_probe(dev, -EINVAL, "invalid resource %pR\n", res); + return IOMEM_ERR_PTR(ret); } if (type == DEVM_IOREMAP && res->flags & IORESOURCE_MEM_NONPOSTED) @@ -144,20 +145,20 @@ __devm_ioremap_resource(struct device *dev, const struct resource *res, else pretty_name = devm_kstrdup(dev, dev_name(dev), GFP_KERNEL); if (!pretty_name) { - dev_err(dev, "can't generate pretty name for resource %pR\n", res); - return IOMEM_ERR_PTR(-ENOMEM); + ret = dev_err_probe(dev, -ENOMEM, "can't generate pretty name for resource %pR\n", res); + return IOMEM_ERR_PTR(ret); } if (!devm_request_mem_region(dev, res->start, size, pretty_name)) { - dev_err(dev, "can't request region for resource %pR\n", res); - return IOMEM_ERR_PTR(-EBUSY); + ret = dev_err_probe(dev, -EBUSY, "can't request region for resource %pR\n", res); + return IOMEM_ERR_PTR(ret); } dest_ptr = __devm_ioremap(dev, res->start, size, type); if (!dest_ptr) { - dev_err(dev, "ioremap failed for resource %pR\n", res); devm_release_mem_region(dev, res->start, size); - dest_ptr = IOMEM_ERR_PTR(-ENOMEM); + ret = dev_err_probe(dev, -ENOMEM, "ioremap failed for resource %pR\n", res); + return IOMEM_ERR_PTR(ret); } return dest_ptr; -- cgit v1.2.3 From 3cc98aa11ec4c3b9b55fa185c8882e4ae20cbd6a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 3 Apr 2024 13:46:57 +0300 Subject: devres: don't use "proxy" headers Update header inclusions to follow IWYU (Include What You Use) principle. Link: https://lkml.kernel.org/r/20240403104820.557487-3-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Reviewed-by: Philipp Stanner Signed-off-by: Andrew Morton --- lib/devres.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/lib/devres.c b/lib/devres.c index 27f280a39dca..4fc152de6d8b 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -1,10 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include -#include -#include -#include +#include #include +#include +#include +#include #include +#include enum devm_ioremap_type { DEVM_IOREMAP = 0, -- cgit v1.2.3 From 3ef3a05ba6ac52998a52dc1eca90853dda771316 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 9 Apr 2024 16:00:54 +0200 Subject: test_hexdump: avoid string truncation warning gcc can warn when a string is too long to fit into the strncpy() destination buffer, as it is here depending on the function arguments: inlined from 'test_hexdump_prepare_test.constprop' at /home/arnd/arm-soc/lib/test_hexdump.c:116:3: include/linux/fortify-string.h:108:33: error: '__builtin_strncpy' output truncated copying between 0 and 32 bytes from a string of length 32 [-Werror=stringop-truncation] 108 | #define __underlying_strncpy __builtin_strncpy | ^ include/linux/fortify-string.h:187:16: note: in expansion of macro '__underlying_strncpy' 187 | return __underlying_strncpy(p, q, size); | ^~~~~~~~~~~~~~~~~~~~ The intention here is to copy exactly 'l' bytes without any padding or NUL-termination, so the most logical change is to use memcpy(), just as a previous change adapted the other output from strncpy() to memcpy(). Link: https://lkml.kernel.org/r/20240409140059.3806717-2-arnd@kernel.org Signed-off-by: Arnd Bergmann Acked-by: Justin Stitt Cc: Alexey Starikovskiy Cc: Bob Moore Cc: Jens Axboe Cc: Len Brown Cc: Lin Ming Cc: Masahiro Yamada Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Nathan Chancellor Cc: Nicolas Schier Cc: Rafael J. Wysocki Cc: "Richard Russon (FlatCap)" Cc: Steven Rostedt Signed-off-by: Andrew Morton --- lib/test_hexdump.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/test_hexdump.c b/lib/test_hexdump.c index b916801f23a8..fe2682bb21e6 100644 --- a/lib/test_hexdump.c +++ b/lib/test_hexdump.c @@ -113,7 +113,7 @@ static void __init test_hexdump_prepare_test(size_t len, int rowsize, *p++ = ' '; } while (p < test + rs * 2 + rs / gs + 1); - strncpy(p, data_a, l); + memcpy(p, data_a, l); p += l; } -- cgit v1.2.3 From 6ad0d7e0f4b68f87a98ea2b239123b7d865df86b Mon Sep 17 00:00:00 2001 From: linke li Date: Fri, 26 Apr 2024 18:34:44 +0800 Subject: sbitmap: use READ_ONCE to access map->word In __sbitmap_queue_get_batch(), map->word is read several times, and update atomically using atomic_long_try_cmpxchg(). But the first two read of map->word is not protected. This patch moves the statement val = READ_ONCE(map->word) forward, eliminating unprotected accesses to map->word within the function. It is aimed at reducing the number of benign races reported by KCSAN in order to focus future debugging effort on harmful races. Signed-off-by: linke li Link: https://lore.kernel.org/r/tencent_0B517C25E519D3D002194E8445E86C04AD0A@qq.com Signed-off-by: Jens Axboe --- lib/sbitmap.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 92c6b1fd8989..1e453f825c05 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -494,18 +494,18 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags, struct sbitmap_word *map = &sb->map[index]; unsigned long get_mask; unsigned int map_depth = __map_depth(sb, index); + unsigned long val; sbitmap_deferred_clear(map); - if (map->word == (1UL << (map_depth - 1)) - 1) + val = READ_ONCE(map->word); + if (val == (1UL << (map_depth - 1)) - 1) goto next; - nr = find_first_zero_bit(&map->word, map_depth); + nr = find_first_zero_bit(&val, map_depth); if (nr + nr_tags <= map_depth) { atomic_long_t *ptr = (atomic_long_t *) &map->word; - unsigned long val; get_mask = ((1UL << nr_tags) - 1) << nr; - val = READ_ONCE(map->word); while (!atomic_long_try_cmpxchg(ptr, &val, get_mask | val)) ; -- cgit v1.2.3 From 6a30653b604aaad1bf0f2e74b068ceb8b6fc7aea Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 25 Apr 2024 09:39:32 +0100 Subject: Fix a potential infinite loop in extract_user_to_sg() Fix extract_user_to_sg() so that it will break out of the loop if iov_iter_extract_pages() returns 0 rather than looping around forever. [Note that I've included two fixes lines as the function got moved to a different file and renamed] Fixes: 85dd2c8ff368 ("netfs: Add a function to extract a UBUF or IOVEC into a BVEC iterator") Fixes: f5f82cd18732 ("Move netfs_extract_iter_to_sg() to lib/scatterlist.c") Signed-off-by: David Howells cc: Jeff Layton cc: Steve French cc: Herbert Xu cc: netfs@lists.linux.dev Link: https://lore.kernel.org/r/1967121.1714034372@warthog.procyon.org.uk Signed-off-by: Jakub Kicinski --- lib/scatterlist.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 68b45c82c37a..7bc2220fea80 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -1124,7 +1124,7 @@ static ssize_t extract_user_to_sg(struct iov_iter *iter, do { res = iov_iter_extract_pages(iter, &pages, maxsize, sg_max, extraction_flags, &off); - if (res < 0) + if (res <= 0) goto failed; len = res; -- cgit v1.2.3 From 998b18072ceb0613629c256b409f4d299829c7ec Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 25 Apr 2024 16:06:22 -0700 Subject: kunit/fortify: Fix mismatched kvalloc()/vfree() usage The kv*() family of tests were accidentally freeing with vfree() instead of kvfree(). Use kvfree() instead. Fixes: 9124a2640148 ("kunit/fortify: Validate __alloc_size attribute results") Link: https://lore.kernel.org/r/20240425230619.work.299-kees@kernel.org Signed-off-by: Kees Cook --- lib/fortify_kunit.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'lib') diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index 493ec02dd5b3..86c1b1a6e2c8 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -267,28 +267,28 @@ DEFINE_ALLOC_SIZE_TEST_PAIR(vmalloc) \ checker((expected_pages) * PAGE_SIZE, \ kvmalloc((alloc_pages) * PAGE_SIZE, gfp), \ - vfree(p)); \ + kvfree(p)); \ checker((expected_pages) * PAGE_SIZE, \ kvmalloc_node((alloc_pages) * PAGE_SIZE, gfp, NUMA_NO_NODE), \ - vfree(p)); \ + kvfree(p)); \ checker((expected_pages) * PAGE_SIZE, \ kvzalloc((alloc_pages) * PAGE_SIZE, gfp), \ - vfree(p)); \ + kvfree(p)); \ checker((expected_pages) * PAGE_SIZE, \ kvzalloc_node((alloc_pages) * PAGE_SIZE, gfp, NUMA_NO_NODE), \ - vfree(p)); \ + kvfree(p)); \ checker((expected_pages) * PAGE_SIZE, \ kvcalloc(1, (alloc_pages) * PAGE_SIZE, gfp), \ - vfree(p)); \ + kvfree(p)); \ checker((expected_pages) * PAGE_SIZE, \ kvcalloc((alloc_pages) * PAGE_SIZE, 1, gfp), \ - vfree(p)); \ + kvfree(p)); \ checker((expected_pages) * PAGE_SIZE, \ kvmalloc_array(1, (alloc_pages) * PAGE_SIZE, gfp), \ - vfree(p)); \ + kvfree(p)); \ checker((expected_pages) * PAGE_SIZE, \ kvmalloc_array((alloc_pages) * PAGE_SIZE, 1, gfp), \ - vfree(p)); \ + kvfree(p)); \ \ prev_size = (expected_pages) * PAGE_SIZE; \ orig = kvmalloc(prev_size, gfp); \ -- cgit v1.2.3 From 00e7d3bea2ce7dac7bee1cf501fb071fd0ea8f6c Mon Sep 17 00:00:00 2001 From: Jim Cromie Date: Mon, 29 Apr 2024 13:31:11 -0600 Subject: dyndbg: fix old BUG_ON in >control parser Fix a BUG_ON from 2009. Even if it looks "unreachable" (I didn't really look), lets make sure by removing it, doing pr_err and return -EINVAL instead. Cc: stable Signed-off-by: Jim Cromie Link: https://lore.kernel.org/r/20240429193145.66543-2-jim.cromie@gmail.com Signed-off-by: Greg Kroah-Hartman --- lib/dynamic_debug.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index c78f335fa981..f2c5e7910bb1 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -302,7 +302,11 @@ static int ddebug_tokenize(char *buf, char *words[], int maxwords) } else { for (end = buf; *end && !isspace(*end); end++) ; - BUG_ON(end == buf); + if (end == buf) { + pr_err("parse err after word:%d=%s\n", nwords, + nwords ? words[nwords - 1] : ""); + return -EINVAL; + } } /* `buf' is start of word, `end' is one past its end */ -- cgit v1.2.3 From a0d6677ec3f1da894cad9df6a962821429828917 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 29 Apr 2024 12:43:39 -0700 Subject: kunit/fortify: Rename tests to use recommended conventions The recommended conventions for KUnit tests is ${module}_test_${what}. Adjust the fortify tests to match. Link: https://lore.kernel.org/r/20240429194342.2421639-1-keescook@chromium.org Signed-off-by: Kees Cook --- lib/fortify_kunit.c | 80 ++++++++++++++++++++++++++--------------------------- 1 file changed, 40 insertions(+), 40 deletions(-) (limited to 'lib') diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index 86c1b1a6e2c8..5d706529c464 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -64,7 +64,7 @@ void fortify_add_kunit_error(int write) kunit_put_resource(resource); } -static void known_sizes_test(struct kunit *test) +static void fortify_test_known_sizes(struct kunit *test) { KUNIT_EXPECT_EQ(test, __compiletime_strlen("88888888"), 8); KUNIT_EXPECT_EQ(test, __compiletime_strlen(array_of_10), 10); @@ -97,7 +97,7 @@ static noinline size_t want_minus_one(int pick) return __compiletime_strlen(str); } -static void control_flow_split_test(struct kunit *test) +static void fortify_test_control_flow_split(struct kunit *test) { KUNIT_EXPECT_EQ(test, want_minus_one(pick), SIZE_MAX); } @@ -173,11 +173,11 @@ static volatile size_t unknown_size = 50; #endif #define DEFINE_ALLOC_SIZE_TEST_PAIR(allocator) \ -static void alloc_size_##allocator##_const_test(struct kunit *test) \ +static void fortify_test_alloc_size_##allocator##_const(struct kunit *test) \ { \ CONST_TEST_BODY(TEST_##allocator); \ } \ -static void alloc_size_##allocator##_dynamic_test(struct kunit *test) \ +static void fortify_test_alloc_size_##allocator##_dynamic(struct kunit *test) \ { \ DYNAMIC_TEST_BODY(TEST_##allocator); \ } @@ -361,7 +361,7 @@ struct fortify_padding { /* Force compiler into not being able to resolve size at compile-time. */ static volatile int unconst; -static void strlen_test(struct kunit *test) +static void fortify_test_strlen(struct kunit *test) { struct fortify_padding pad = { }; int i, end = sizeof(pad.buf) - 1; @@ -384,7 +384,7 @@ static void strlen_test(struct kunit *test) KUNIT_EXPECT_EQ(test, fortify_read_overflows, 1); } -static void strnlen_test(struct kunit *test) +static void fortify_test_strnlen(struct kunit *test) { struct fortify_padding pad = { }; int i, end = sizeof(pad.buf) - 1; @@ -422,7 +422,7 @@ static void strnlen_test(struct kunit *test) KUNIT_EXPECT_EQ(test, fortify_read_overflows, 2); } -static void strcpy_test(struct kunit *test) +static void fortify_test_strcpy(struct kunit *test) { struct fortify_padding pad = { }; char src[sizeof(pad.buf) + 1] = { }; @@ -480,7 +480,7 @@ static void strcpy_test(struct kunit *test) KUNIT_EXPECT_EQ(test, pad.bytes_after, 0); } -static void strncpy_test(struct kunit *test) +static void fortify_test_strncpy(struct kunit *test) { struct fortify_padding pad = { }; char src[] = "Copy me fully into a small buffer and I will overflow!"; @@ -539,7 +539,7 @@ static void strncpy_test(struct kunit *test) KUNIT_EXPECT_EQ(test, pad.bytes_after, 0); } -static void strscpy_test(struct kunit *test) +static void fortify_test_strscpy(struct kunit *test) { struct fortify_padding pad = { }; char src[] = "Copy me fully into a small buffer and I will overflow!"; @@ -596,7 +596,7 @@ static void strscpy_test(struct kunit *test) KUNIT_EXPECT_EQ(test, pad.bytes_after, 0); } -static void strcat_test(struct kunit *test) +static void fortify_test_strcat(struct kunit *test) { struct fortify_padding pad = { }; char src[sizeof(pad.buf) / 2] = { }; @@ -653,7 +653,7 @@ static void strcat_test(struct kunit *test) KUNIT_EXPECT_EQ(test, pad.bytes_after, 0); } -static void strncat_test(struct kunit *test) +static void fortify_test_strncat(struct kunit *test) { struct fortify_padding pad = { }; char src[sizeof(pad.buf)] = { }; @@ -726,7 +726,7 @@ static void strncat_test(struct kunit *test) KUNIT_EXPECT_EQ(test, pad.bytes_after, 0); } -static void strlcat_test(struct kunit *test) +static void fortify_test_strlcat(struct kunit *test) { struct fortify_padding pad = { }; char src[sizeof(pad.buf)] = { }; @@ -811,7 +811,7 @@ static void strlcat_test(struct kunit *test) KUNIT_EXPECT_EQ(test, pad.bytes_after, 0); } -static void memscan_test(struct kunit *test) +static void fortify_test_memscan(struct kunit *test) { char haystack[] = "Where oh where is my memory range?"; char *mem = haystack + strlen("Where oh where is "); @@ -830,7 +830,7 @@ static void memscan_test(struct kunit *test) KUNIT_EXPECT_EQ(test, fortify_read_overflows, 2); } -static void memchr_test(struct kunit *test) +static void fortify_test_memchr(struct kunit *test) { char haystack[] = "Where oh where is my memory range?"; char *mem = haystack + strlen("Where oh where is "); @@ -849,7 +849,7 @@ static void memchr_test(struct kunit *test) KUNIT_EXPECT_EQ(test, fortify_read_overflows, 2); } -static void memchr_inv_test(struct kunit *test) +static void fortify_test_memchr_inv(struct kunit *test) { char haystack[] = "Where oh where is my memory range?"; char *mem = haystack + 1; @@ -869,7 +869,7 @@ static void memchr_inv_test(struct kunit *test) KUNIT_EXPECT_EQ(test, fortify_read_overflows, 2); } -static void memcmp_test(struct kunit *test) +static void fortify_test_memcmp(struct kunit *test) { char one[] = "My mind is going ..."; char two[] = "My mind is going ... I can feel it."; @@ -891,7 +891,7 @@ static void memcmp_test(struct kunit *test) KUNIT_EXPECT_EQ(test, fortify_read_overflows, 2); } -static void kmemdup_test(struct kunit *test) +static void fortify_test_kmemdup(struct kunit *test) { char src[] = "I got Doom running on it!"; char *copy; @@ -951,31 +951,31 @@ static int fortify_test_init(struct kunit *test) } static struct kunit_case fortify_test_cases[] = { - KUNIT_CASE(known_sizes_test), - KUNIT_CASE(control_flow_split_test), - KUNIT_CASE(alloc_size_kmalloc_const_test), - KUNIT_CASE(alloc_size_kmalloc_dynamic_test), - KUNIT_CASE(alloc_size_vmalloc_const_test), - KUNIT_CASE(alloc_size_vmalloc_dynamic_test), - KUNIT_CASE(alloc_size_kvmalloc_const_test), - KUNIT_CASE(alloc_size_kvmalloc_dynamic_test), - KUNIT_CASE(alloc_size_devm_kmalloc_const_test), - KUNIT_CASE(alloc_size_devm_kmalloc_dynamic_test), - KUNIT_CASE(strlen_test), - KUNIT_CASE(strnlen_test), - KUNIT_CASE(strcpy_test), - KUNIT_CASE(strncpy_test), - KUNIT_CASE(strscpy_test), - KUNIT_CASE(strcat_test), - KUNIT_CASE(strncat_test), - KUNIT_CASE(strlcat_test), + KUNIT_CASE(fortify_test_known_sizes), + KUNIT_CASE(fortify_test_control_flow_split), + KUNIT_CASE(fortify_test_alloc_size_kmalloc_const), + KUNIT_CASE(fortify_test_alloc_size_kmalloc_dynamic), + KUNIT_CASE(fortify_test_alloc_size_vmalloc_const), + KUNIT_CASE(fortify_test_alloc_size_vmalloc_dynamic), + KUNIT_CASE(fortify_test_alloc_size_kvmalloc_const), + KUNIT_CASE(fortify_test_alloc_size_kvmalloc_dynamic), + KUNIT_CASE(fortify_test_alloc_size_devm_kmalloc_const), + KUNIT_CASE(fortify_test_alloc_size_devm_kmalloc_dynamic), + KUNIT_CASE(fortify_test_strlen), + KUNIT_CASE(fortify_test_strnlen), + KUNIT_CASE(fortify_test_strcpy), + KUNIT_CASE(fortify_test_strncpy), + KUNIT_CASE(fortify_test_strscpy), + KUNIT_CASE(fortify_test_strcat), + KUNIT_CASE(fortify_test_strncat), + KUNIT_CASE(fortify_test_strlcat), /* skip memset: performs bounds checking on whole structs */ /* skip memcpy: still using warn-and-overwrite instead of hard-fail */ - KUNIT_CASE(memscan_test), - KUNIT_CASE(memchr_test), - KUNIT_CASE(memchr_inv_test), - KUNIT_CASE(memcmp_test), - KUNIT_CASE(kmemdup_test), + KUNIT_CASE(fortify_test_memscan), + KUNIT_CASE(fortify_test_memchr), + KUNIT_CASE(fortify_test_memchr_inv), + KUNIT_CASE(fortify_test_memcmp), + KUNIT_CASE(fortify_test_kmemdup), {} }; -- cgit v1.2.3 From 091f79e8de44736a1e677701d67334bba5b749e3 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 29 Apr 2024 12:43:40 -0700 Subject: kunit/fortify: Do not spam logs with fortify WARNs When running KUnit fortify tests, we're already doing precise tracking of which warnings are getting hit. Don't fill the logs with WARNs unless we've been explicitly built with DEBUG enabled. Link: https://lore.kernel.org/r/20240429194342.2421639-2-keescook@chromium.org Signed-off-by: Kees Cook --- lib/fortify_kunit.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index 5d706529c464..601fa327c5b7 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -15,10 +15,17 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +/* We don't need to fill dmesg with the fortify WARNs during testing. */ +#ifdef DEBUG +# define FORTIFY_REPORT_KUNIT(x...) __fortify_report(x) +#else +# define FORTIFY_REPORT_KUNIT(x...) do { } while (0) +#endif + /* Redefine fortify_panic() to track failures. */ void fortify_add_kunit_error(int write); #define fortify_panic(func, write, avail, size, retfail) do { \ - __fortify_report(FORTIFY_REASON(func, write), avail, size); \ + FORTIFY_REPORT_KUNIT(FORTIFY_REASON(func, write), avail, size); \ fortify_add_kunit_error(write); \ return (retfail); \ } while (0) -- cgit v1.2.3 From 26f812ba75890c48644a31e3cfe3dd9762138968 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 29 Apr 2024 12:43:41 -0700 Subject: kunit/fortify: Add memcpy() tests Add fortify tests for memcpy() and memmove(). This can use a similar method to the fortify_panic() replacement, only we can do it for what was the WARN_ONCE(), which can be redefined. Since this is primarily testing the fortify behaviors of the memcpy() and memmove() defenses, the tests for memcpy() and memmove() are identical. Link: https://lore.kernel.org/r/20240429194342.2421639-3-keescook@chromium.org Signed-off-by: Kees Cook --- include/linux/fortify-string.h | 6 ++- lib/fortify_kunit.c | 85 ++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 87 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 6aeebe0a6777..a0bb13825109 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -15,10 +15,14 @@ #define FORTIFY_REASON(func, write) (FIELD_PREP(BIT(0), write) | \ FIELD_PREP(GENMASK(7, 1), func)) +/* Overridden by KUnit tests. */ #ifndef fortify_panic # define fortify_panic(func, write, avail, size, retfail) \ __fortify_panic(FORTIFY_REASON(func, write), avail, size) #endif +#ifndef fortify_warn_once +# define fortify_warn_once(x...) WARN_ONCE(x) +#endif #define FORTIFY_READ 0 #define FORTIFY_WRITE 1 @@ -609,7 +613,7 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, const size_t __q_size = (q_size); \ const size_t __p_size_field = (p_size_field); \ const size_t __q_size_field = (q_size_field); \ - WARN_ONCE(fortify_memcpy_chk(__fortify_size, __p_size, \ + fortify_warn_once(fortify_memcpy_chk(__fortify_size, __p_size, \ __q_size, __p_size_field, \ __q_size_field, FORTIFY_FUNC_ ##op), \ #op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \ diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index 601fa327c5b7..ef3e4c68b759 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Runtime test cases for CONFIG_FORTIFY_SOURCE. For testing memcpy(), - * see FORTIFY_MEM_* tests in LKDTM (drivers/misc/lkdtm/fortify.c). + * Runtime test cases for CONFIG_FORTIFY_SOURCE. For additional memcpy() + * testing see FORTIFY_MEM_* tests in LKDTM (drivers/misc/lkdtm/fortify.c). * * For corner cases with UBSAN, try testing with: * @@ -18,8 +18,10 @@ /* We don't need to fill dmesg with the fortify WARNs during testing. */ #ifdef DEBUG # define FORTIFY_REPORT_KUNIT(x...) __fortify_report(x) +# define FORTIFY_WARN_KUNIT(x...) WARN_ONCE(x) #else # define FORTIFY_REPORT_KUNIT(x...) do { } while (0) +# define FORTIFY_WARN_KUNIT(x...) do { } while (0) #endif /* Redefine fortify_panic() to track failures. */ @@ -30,6 +32,14 @@ void fortify_add_kunit_error(int write); return (retfail); \ } while (0) +/* Redefine fortify_warn_once() to track memcpy() failures. */ +#define fortify_warn_once(chk_func, x...) do { \ + bool __result = chk_func; \ + FORTIFY_WARN_KUNIT(__result, x); \ + if (__result) \ + fortify_add_kunit_error(1); \ +} while (0) + #include #include #include @@ -818,6 +828,74 @@ static void fortify_test_strlcat(struct kunit *test) KUNIT_EXPECT_EQ(test, pad.bytes_after, 0); } +/* Check for 0-sized arrays... */ +struct fortify_zero_sized { + unsigned long bytes_before; + char buf[0]; + unsigned long bytes_after; +}; + +#define __fortify_test(memfunc) \ +static void fortify_test_##memfunc(struct kunit *test) \ +{ \ + struct fortify_zero_sized zero = { }; \ + struct fortify_padding pad = { }; \ + char srcA[sizeof(pad.buf) + 2]; \ + char srcB[sizeof(pad.buf) + 2]; \ + size_t len = sizeof(pad.buf) + unconst; \ + \ + memset(srcA, 'A', sizeof(srcA)); \ + KUNIT_ASSERT_EQ(test, srcA[0], 'A'); \ + memset(srcB, 'B', sizeof(srcB)); \ + KUNIT_ASSERT_EQ(test, srcB[0], 'B'); \ + \ + memfunc(pad.buf, srcA, 0 + unconst); \ + KUNIT_EXPECT_EQ(test, pad.buf[0], '\0'); \ + KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); \ + KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0); \ + memfunc(pad.buf + 1, srcB, 1 + unconst); \ + KUNIT_EXPECT_EQ(test, pad.buf[0], '\0'); \ + KUNIT_EXPECT_EQ(test, pad.buf[1], 'B'); \ + KUNIT_EXPECT_EQ(test, pad.buf[2], '\0'); \ + KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); \ + KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0); \ + memfunc(pad.buf, srcA, 1 + unconst); \ + KUNIT_EXPECT_EQ(test, pad.buf[0], 'A'); \ + KUNIT_EXPECT_EQ(test, pad.buf[1], 'B'); \ + KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); \ + KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0); \ + memfunc(pad.buf, srcA, len - 1); \ + KUNIT_EXPECT_EQ(test, pad.buf[1], 'A'); \ + KUNIT_EXPECT_EQ(test, pad.buf[len - 1], '\0'); \ + KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); \ + KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0); \ + memfunc(pad.buf, srcA, len); \ + KUNIT_EXPECT_EQ(test, pad.buf[1], 'A'); \ + KUNIT_EXPECT_EQ(test, pad.buf[len - 1], 'A'); \ + KUNIT_EXPECT_EQ(test, pad.bytes_after, 0); \ + KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); \ + KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0); \ + memfunc(pad.buf, srcA, len + 1); \ + KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); \ + KUNIT_EXPECT_EQ(test, fortify_write_overflows, 1); \ + memfunc(pad.buf + 1, srcB, len); \ + KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); \ + KUNIT_EXPECT_EQ(test, fortify_write_overflows, 2); \ + \ + /* Reset error counter. */ \ + fortify_write_overflows = 0; \ + /* Copy nothing into nothing: no errors. */ \ + memfunc(zero.buf, srcB, 0 + unconst); \ + KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); \ + KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0); \ + /* We currently explicitly ignore zero-sized dests. */ \ + memfunc(zero.buf, srcB, 1 + unconst); \ + KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); \ + KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0); \ +} +__fortify_test(memcpy) +__fortify_test(memmove) + static void fortify_test_memscan(struct kunit *test) { char haystack[] = "Where oh where is my memory range?"; @@ -977,7 +1055,8 @@ static struct kunit_case fortify_test_cases[] = { KUNIT_CASE(fortify_test_strncat), KUNIT_CASE(fortify_test_strlcat), /* skip memset: performs bounds checking on whole structs */ - /* skip memcpy: still using warn-and-overwrite instead of hard-fail */ + KUNIT_CASE(fortify_test_memcpy), + KUNIT_CASE(fortify_test_memmove), KUNIT_CASE(fortify_test_memscan), KUNIT_CASE(fortify_test_memchr), KUNIT_CASE(fortify_test_memchr_inv), -- cgit v1.2.3 From a3b00f10da808bd4a354f890b551cba471082d0e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 24 Apr 2024 14:52:13 -0700 Subject: objpool: enable inlining objpool_push() and objpool_pop() operations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit objpool_push() and objpool_pop() are very performance-critical functions and can be called very frequently in kretprobe triggering path. As such, it makes sense to allow compiler to inline them completely to eliminate function calls overhead. Luckily, their logic is quite well isolated and doesn't have any sprawling dependencies. This patch moves both objpool_push() and objpool_pop() into include/linux/objpool.h and marks them as static inline functions, enabling inlining. To avoid anyone using internal helpers (objpool_try_get_slot, objpool_try_add_slot), rename them to use leading underscores. We used kretprobe microbenchmark from BPF selftests (bench trig-kprobe and trig-kprobe-multi benchmarks) running no-op BPF kretprobe/kretprobe.multi programs in a tight loop to evaluate the effect. BPF own overhead in this case is minimal and it mostly stresses the rest of in-kernel kretprobe infrastructure overhead. Results are in millions of calls per second. This is not super scientific, but shows the trend nevertheless. BEFORE ====== kretprobe : 9.794 ± 0.086M/s kretprobe-multi: 10.219 ± 0.032M/s AFTER ===== kretprobe : 9.937 ± 0.174M/s (+1.5%) kretprobe-multi: 10.440 ± 0.108M/s (+2.2%) Link: https://lore.kernel.org/all/20240424215214.3956041-2-andrii@kernel.org/ Cc: Matt (Qiang) Wu Signed-off-by: Andrii Nakryiko Signed-off-by: Masami Hiramatsu (Google) --- include/linux/objpool.h | 101 +++++++++++++++++++++++++++++++++++++++++++++++- lib/objpool.c | 100 ----------------------------------------------- 2 files changed, 99 insertions(+), 102 deletions(-) (limited to 'lib') diff --git a/include/linux/objpool.h b/include/linux/objpool.h index 15aff4a17f0c..d8b1f7b91128 100644 --- a/include/linux/objpool.h +++ b/include/linux/objpool.h @@ -5,6 +5,10 @@ #include #include +#include +#include +#include +#include /* * objpool: ring-array based lockless MPMC queue @@ -118,13 +122,94 @@ int objpool_init(struct objpool_head *pool, int nr_objs, int object_size, gfp_t gfp, void *context, objpool_init_obj_cb objinit, objpool_fini_cb release); +/* try to retrieve object from slot */ +static inline void *__objpool_try_get_slot(struct objpool_head *pool, int cpu) +{ + struct objpool_slot *slot = pool->cpu_slots[cpu]; + /* load head snapshot, other cpus may change it */ + uint32_t head = smp_load_acquire(&slot->head); + + while (head != READ_ONCE(slot->last)) { + void *obj; + + /* + * data visibility of 'last' and 'head' could be out of + * order since memory updating of 'last' and 'head' are + * performed in push() and pop() independently + * + * before any retrieving attempts, pop() must guarantee + * 'last' is behind 'head', that is to say, there must + * be available objects in slot, which could be ensured + * by condition 'last != head && last - head <= nr_objs' + * that is equivalent to 'last - head - 1 < nr_objs' as + * 'last' and 'head' are both unsigned int32 + */ + if (READ_ONCE(slot->last) - head - 1 >= pool->nr_objs) { + head = READ_ONCE(slot->head); + continue; + } + + /* obj must be retrieved before moving forward head */ + obj = READ_ONCE(slot->entries[head & slot->mask]); + + /* move head forward to mark it's consumption */ + if (try_cmpxchg_release(&slot->head, &head, head + 1)) + return obj; + } + + return NULL; +} + /** * objpool_pop() - allocate an object from objpool * @pool: object pool * * return value: object ptr or NULL if failed */ -void *objpool_pop(struct objpool_head *pool); +static inline void *objpool_pop(struct objpool_head *pool) +{ + void *obj = NULL; + unsigned long flags; + int i, cpu; + + /* disable local irq to avoid preemption & interruption */ + raw_local_irq_save(flags); + + cpu = raw_smp_processor_id(); + for (i = 0; i < num_possible_cpus(); i++) { + obj = __objpool_try_get_slot(pool, cpu); + if (obj) + break; + cpu = cpumask_next_wrap(cpu, cpu_possible_mask, -1, 1); + } + raw_local_irq_restore(flags); + + return obj; +} + +/* adding object to slot, abort if the slot was already full */ +static inline int +__objpool_try_add_slot(void *obj, struct objpool_head *pool, int cpu) +{ + struct objpool_slot *slot = pool->cpu_slots[cpu]; + uint32_t head, tail; + + /* loading tail and head as a local snapshot, tail first */ + tail = READ_ONCE(slot->tail); + + do { + head = READ_ONCE(slot->head); + /* fault caught: something must be wrong */ + WARN_ON_ONCE(tail - head > pool->nr_objs); + } while (!try_cmpxchg_acquire(&slot->tail, &tail, tail + 1)); + + /* now the tail position is reserved for the given obj */ + WRITE_ONCE(slot->entries[tail & slot->mask], obj); + /* update sequence to make this obj available for pop() */ + smp_store_release(&slot->last, tail + 1); + + return 0; +} /** * objpool_push() - reclaim the object and return back to objpool @@ -134,7 +219,19 @@ void *objpool_pop(struct objpool_head *pool); * return: 0 or error code (it fails only when user tries to push * the same object multiple times or wrong "objects" into objpool) */ -int objpool_push(void *obj, struct objpool_head *pool); +static inline int objpool_push(void *obj, struct objpool_head *pool) +{ + unsigned long flags; + int rc; + + /* disable local irq to avoid preemption & interruption */ + raw_local_irq_save(flags); + rc = __objpool_try_add_slot(obj, pool, raw_smp_processor_id()); + raw_local_irq_restore(flags); + + return rc; +} + /** * objpool_drop() - discard the object and deref objpool diff --git a/lib/objpool.c b/lib/objpool.c index cfdc02420884..f696308fc026 100644 --- a/lib/objpool.c +++ b/lib/objpool.c @@ -152,106 +152,6 @@ int objpool_init(struct objpool_head *pool, int nr_objs, int object_size, } EXPORT_SYMBOL_GPL(objpool_init); -/* adding object to slot, abort if the slot was already full */ -static inline int -objpool_try_add_slot(void *obj, struct objpool_head *pool, int cpu) -{ - struct objpool_slot *slot = pool->cpu_slots[cpu]; - uint32_t head, tail; - - /* loading tail and head as a local snapshot, tail first */ - tail = READ_ONCE(slot->tail); - - do { - head = READ_ONCE(slot->head); - /* fault caught: something must be wrong */ - WARN_ON_ONCE(tail - head > pool->nr_objs); - } while (!try_cmpxchg_acquire(&slot->tail, &tail, tail + 1)); - - /* now the tail position is reserved for the given obj */ - WRITE_ONCE(slot->entries[tail & slot->mask], obj); - /* update sequence to make this obj available for pop() */ - smp_store_release(&slot->last, tail + 1); - - return 0; -} - -/* reclaim an object to object pool */ -int objpool_push(void *obj, struct objpool_head *pool) -{ - unsigned long flags; - int rc; - - /* disable local irq to avoid preemption & interruption */ - raw_local_irq_save(flags); - rc = objpool_try_add_slot(obj, pool, raw_smp_processor_id()); - raw_local_irq_restore(flags); - - return rc; -} -EXPORT_SYMBOL_GPL(objpool_push); - -/* try to retrieve object from slot */ -static inline void *objpool_try_get_slot(struct objpool_head *pool, int cpu) -{ - struct objpool_slot *slot = pool->cpu_slots[cpu]; - /* load head snapshot, other cpus may change it */ - uint32_t head = smp_load_acquire(&slot->head); - - while (head != READ_ONCE(slot->last)) { - void *obj; - - /* - * data visibility of 'last' and 'head' could be out of - * order since memory updating of 'last' and 'head' are - * performed in push() and pop() independently - * - * before any retrieving attempts, pop() must guarantee - * 'last' is behind 'head', that is to say, there must - * be available objects in slot, which could be ensured - * by condition 'last != head && last - head <= nr_objs' - * that is equivalent to 'last - head - 1 < nr_objs' as - * 'last' and 'head' are both unsigned int32 - */ - if (READ_ONCE(slot->last) - head - 1 >= pool->nr_objs) { - head = READ_ONCE(slot->head); - continue; - } - - /* obj must be retrieved before moving forward head */ - obj = READ_ONCE(slot->entries[head & slot->mask]); - - /* move head forward to mark it's consumption */ - if (try_cmpxchg_release(&slot->head, &head, head + 1)) - return obj; - } - - return NULL; -} - -/* allocate an object from object pool */ -void *objpool_pop(struct objpool_head *pool) -{ - void *obj = NULL; - unsigned long flags; - int i, cpu; - - /* disable local irq to avoid preemption & interruption */ - raw_local_irq_save(flags); - - cpu = raw_smp_processor_id(); - for (i = 0; i < num_possible_cpus(); i++) { - obj = objpool_try_get_slot(pool, cpu); - if (obj) - break; - cpu = cpumask_next_wrap(cpu, cpu_possible_mask, -1, 1); - } - raw_local_irq_restore(flags); - - return obj; -} -EXPORT_SYMBOL_GPL(objpool_pop); - /* release whole objpool forcely */ void objpool_free(struct objpool_head *pool) { -- cgit v1.2.3 From 78d0b16127daa26d016c215a089ae330878291f7 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 24 Apr 2024 14:52:14 -0700 Subject: objpool: cache nr_possible_cpus() and avoid caching nr_cpu_ids MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Profiling shows that calling nr_possible_cpus() in objpool_pop() takes a noticeable amount of CPU (when profiled on 80-core machine), as we need to recalculate number of set bits in a CPU bit mask. This number can't change, so there is no point in paying the price for recalculating it. As such, cache this value in struct objpool_head and use it in objpool_pop(). On the other hand, cached pool->nr_cpus isn't necessary, as it's not used in hot path and is also a pretty trivial value to retrieve. So drop pool->nr_cpus in favor of using nr_cpu_ids everywhere. This way the size of struct objpool_head remains the same, which is a nice bonus. Same BPF selftests benchmarks were used to evaluate the effect. Using changes in previous patch (inlining of objpool_pop/objpool_push) as baseline, here are the differences: BASELINE ======== kretprobe : 9.937 ± 0.174M/s kretprobe-multi: 10.440 ± 0.108M/s AFTER ===== kretprobe : 10.106 ± 0.120M/s (+1.7%) kretprobe-multi: 10.515 ± 0.180M/s (+0.7%) Link: https://lore.kernel.org/all/20240424215214.3956041-3-andrii@kernel.org/ Cc: Matt (Qiang) Wu Signed-off-by: Andrii Nakryiko Signed-off-by: Masami Hiramatsu (Google) --- include/linux/objpool.h | 6 +++--- lib/objpool.c | 12 ++++++------ 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'lib') diff --git a/include/linux/objpool.h b/include/linux/objpool.h index d8b1f7b91128..cb1758eaa2d3 100644 --- a/include/linux/objpool.h +++ b/include/linux/objpool.h @@ -73,7 +73,7 @@ typedef int (*objpool_fini_cb)(struct objpool_head *head, void *context); * struct objpool_head - object pooling metadata * @obj_size: object size, aligned to sizeof(void *) * @nr_objs: total objs (to be pre-allocated with objpool) - * @nr_cpus: local copy of nr_cpu_ids + * @nr_possible_cpus: cached value of num_possible_cpus() * @capacity: max objs can be managed by one objpool_slot * @gfp: gfp flags for kmalloc & vmalloc * @ref: refcount of objpool @@ -85,7 +85,7 @@ typedef int (*objpool_fini_cb)(struct objpool_head *head, void *context); struct objpool_head { int obj_size; int nr_objs; - int nr_cpus; + int nr_possible_cpus; int capacity; gfp_t gfp; refcount_t ref; @@ -176,7 +176,7 @@ static inline void *objpool_pop(struct objpool_head *pool) raw_local_irq_save(flags); cpu = raw_smp_processor_id(); - for (i = 0; i < num_possible_cpus(); i++) { + for (i = 0; i < pool->nr_possible_cpus; i++) { obj = __objpool_try_get_slot(pool, cpu); if (obj) break; diff --git a/lib/objpool.c b/lib/objpool.c index f696308fc026..234f9d0bd081 100644 --- a/lib/objpool.c +++ b/lib/objpool.c @@ -50,7 +50,7 @@ objpool_init_percpu_slots(struct objpool_head *pool, int nr_objs, { int i, cpu_count = 0; - for (i = 0; i < pool->nr_cpus; i++) { + for (i = 0; i < nr_cpu_ids; i++) { struct objpool_slot *slot; int nodes, size, rc; @@ -60,8 +60,8 @@ objpool_init_percpu_slots(struct objpool_head *pool, int nr_objs, continue; /* compute how many objects to be allocated with this slot */ - nodes = nr_objs / num_possible_cpus(); - if (cpu_count < (nr_objs % num_possible_cpus())) + nodes = nr_objs / pool->nr_possible_cpus; + if (cpu_count < (nr_objs % pool->nr_possible_cpus)) nodes++; cpu_count++; @@ -103,7 +103,7 @@ static void objpool_fini_percpu_slots(struct objpool_head *pool) if (!pool->cpu_slots) return; - for (i = 0; i < pool->nr_cpus; i++) + for (i = 0; i < nr_cpu_ids; i++) kvfree(pool->cpu_slots[i]); kfree(pool->cpu_slots); } @@ -130,13 +130,13 @@ int objpool_init(struct objpool_head *pool, int nr_objs, int object_size, /* initialize objpool pool */ memset(pool, 0, sizeof(struct objpool_head)); - pool->nr_cpus = nr_cpu_ids; + pool->nr_possible_cpus = num_possible_cpus(); pool->obj_size = object_size; pool->capacity = capacity; pool->gfp = gfp & ~__GFP_ZERO; pool->context = context; pool->release = release; - slot_size = pool->nr_cpus * sizeof(struct objpool_slot); + slot_size = nr_cpu_ids * sizeof(struct objpool_slot); pool->cpu_slots = kzalloc(slot_size, pool->gfp); if (!pool->cpu_slots) return -ENOMEM; -- cgit v1.2.3 From 74df22453c51392476117d7330bf02cee6e987cf Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 1 May 2024 16:29:48 -0700 Subject: kunit/fortify: Fix replaced failure path to unbreak __alloc_size The __alloc_size annotation for kmemdup() was getting disabled under KUnit testing because the replaced fortify_panic macro implementation was using "return NULL" as a way to survive the sanity checking. But having the chance to return NULL invalidated __alloc_size, so kmemdup was not passing the __builtin_dynamic_object_size() tests any more: [23:26:18] [PASSED] fortify_test_alloc_size_kmalloc_const [23:26:19] # fortify_test_alloc_size_kmalloc_dynamic: EXPECTATION FAILED at lib/fortify_kunit.c:265 [23:26:19] Expected __builtin_dynamic_object_size(p, 1) == expected, but [23:26:19] __builtin_dynamic_object_size(p, 1) == -1 (0xffffffffffffffff) [23:26:19] expected == 11 (0xb) [23:26:19] __alloc_size() not working with __bdos on kmemdup("hello there", len, gfp) [23:26:19] [FAILED] fortify_test_alloc_size_kmalloc_dynamic Normal builds were not affected: __alloc_size continued to work there. Use a zero-sized allocation instead, which allows __alloc_size to behave. Fixes: 4ce615e798a7 ("fortify: Provide KUnit counters for failure testing") Fixes: fa4a3f86d498 ("fortify: Add KUnit tests for runtime overflows") Link: https://lore.kernel.org/r/20240501232937.work.532-kees@kernel.org Signed-off-by: Kees Cook --- include/linux/fortify-string.h | 3 ++- lib/fortify_kunit.c | 6 +++--- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index a0bb13825109..85fc0e6f0f7f 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -738,7 +738,8 @@ __FORTIFY_INLINE void *kmemdup(const void * const POS0 p, size_t size, gfp_t gfp if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) - fortify_panic(FORTIFY_FUNC_kmemdup, FORTIFY_READ, p_size, size, NULL); + fortify_panic(FORTIFY_FUNC_kmemdup, FORTIFY_READ, p_size, size, + __real_kmemdup(p, 0, gfp)); return __real_kmemdup(p, size, gfp); } diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index ef3e4c68b759..306522fd0aa2 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -1002,19 +1002,19 @@ static void fortify_test_kmemdup(struct kunit *test) /* Out of bounds by 1 byte. */ copy = kmemdup(src, len + 1, GFP_KERNEL); - KUNIT_EXPECT_NULL(test, copy); + KUNIT_EXPECT_PTR_EQ(test, copy, ZERO_SIZE_PTR); KUNIT_EXPECT_EQ(test, fortify_read_overflows, 1); kfree(copy); /* Way out of bounds. */ copy = kmemdup(src, len * 2, GFP_KERNEL); - KUNIT_EXPECT_NULL(test, copy); + KUNIT_EXPECT_PTR_EQ(test, copy, ZERO_SIZE_PTR); KUNIT_EXPECT_EQ(test, fortify_read_overflows, 2); kfree(copy); /* Starting offset causing out of bounds. */ copy = kmemdup(src + 1, len, GFP_KERNEL); - KUNIT_EXPECT_NULL(test, copy); + KUNIT_EXPECT_PTR_EQ(test, copy, ZERO_SIZE_PTR); KUNIT_EXPECT_EQ(test, fortify_read_overflows, 3); kfree(copy); } -- cgit v1.2.3 From 377d9095117c084b835e38c020faf5a78e386f01 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 15 Apr 2024 18:20:44 +0200 Subject: vmlinux: Avoid weak reference to notes section Weak references are references that are permitted to remain unsatisfied in the final link. This means they cannot be implemented using place relative relocations, resulting in GOT entries when using position independent code generation. The notes section should always exist, so the weak annotations can be omitted. Acked-by: Arnd Bergmann Signed-off-by: Ard Biesheuvel Signed-off-by: Masahiro Yamada --- kernel/ksysfs.c | 4 ++-- lib/buildid.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 495b69a71a5d..07fb5987b42b 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -228,8 +228,8 @@ KERNEL_ATTR_RW(rcu_normal); /* * Make /sys/kernel/notes give the raw contents of our kernel .notes section. */ -extern const void __start_notes __weak; -extern const void __stop_notes __weak; +extern const void __start_notes; +extern const void __stop_notes; #define notes_size (&__stop_notes - &__start_notes) static ssize_t notes_read(struct file *filp, struct kobject *kobj, diff --git a/lib/buildid.c b/lib/buildid.c index 898301b49eb6..7954dd92e36c 100644 --- a/lib/buildid.c +++ b/lib/buildid.c @@ -182,8 +182,8 @@ unsigned char vmlinux_build_id[BUILD_ID_SIZE_MAX] __ro_after_init; */ void __init init_vmlinux_build_id(void) { - extern const void __start_notes __weak; - extern const void __stop_notes __weak; + extern const void __start_notes; + extern const void __stop_notes; unsigned int size = &__stop_notes - &__start_notes; build_id_parse_buf(&__start_notes, vmlinux_build_id, size); -- cgit v1.2.3 From 7d78a77733552092361239b1d8afaf8412f5dffd Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 1 May 2024 16:32:02 -0700 Subject: string: Add additional __realloc_size() annotations for "dup" helpers Several other "dup"-style interfaces could use the __realloc_size() attribute. (As a reminder to myself and others: "realloc" is used here instead of "alloc" because the "alloc_size" attribute implies that the memory contents are uninitialized. Since we're copying contents into the resulting allocation, it must use "realloc_size" to avoid confusing the compiler's optimization passes.) Add KUnit test coverage where possible. (KUnit still does not have the ability to manipulate userspace memory.) Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20240502145218.it.729-kees@kernel.org Signed-off-by: Kees Cook --- include/linux/string.h | 13 ++++++++----- lib/fortify_kunit.c | 26 ++++++++++++++++++++++++++ 2 files changed, 34 insertions(+), 5 deletions(-) (limited to 'lib') diff --git a/include/linux/string.h b/include/linux/string.h index 86aa6cd35167..10e5177bb49c 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -14,8 +14,8 @@ #include extern char *strndup_user(const char __user *, long); -extern void *memdup_user(const void __user *, size_t); -extern void *vmemdup_user(const void __user *, size_t); +extern void *memdup_user(const void __user *, size_t) __realloc_size(2); +extern void *vmemdup_user(const void __user *, size_t) __realloc_size(2); extern void *memdup_user_nul(const void __user *, size_t); /** @@ -27,7 +27,8 @@ extern void *memdup_user_nul(const void __user *, size_t); * Return: an ERR_PTR() on failure. Result is physically * contiguous, to be freed by kfree(). */ -static inline void *memdup_array_user(const void __user *src, size_t n, size_t size) +static inline __realloc_size(2, 3) +void *memdup_array_user(const void __user *src, size_t n, size_t size) { size_t nbytes; @@ -46,7 +47,8 @@ static inline void *memdup_array_user(const void __user *src, size_t n, size_t s * Return: an ERR_PTR() on failure. Result may be not * physically contiguous. Use kvfree() to free. */ -static inline void *vmemdup_array_user(const void __user *src, size_t n, size_t size) +static inline __realloc_size(2, 3) +void *vmemdup_array_user(const void __user *src, size_t n, size_t size) { size_t nbytes; @@ -285,7 +287,8 @@ extern char *kstrndup(const char *s, size_t len, gfp_t gfp); extern void *kmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2); extern void *kvmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2); extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp); -extern void *kmemdup_array(const void *src, size_t element_size, size_t count, gfp_t gfp); +extern void *kmemdup_array(const void *src, size_t element_size, size_t count, gfp_t gfp) + __realloc_size(2, 3); /* lib/argv_split.c */ extern char **argv_split(gfp_t gfp, const char *str, int *argcp); diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index 306522fd0aa2..d2377e00caab 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -363,6 +363,31 @@ DEFINE_ALLOC_SIZE_TEST_PAIR(kvmalloc) } while (0) DEFINE_ALLOC_SIZE_TEST_PAIR(devm_kmalloc) +static const char * const test_strs[] = { + "", + "Hello there", + "A longer string, just for variety", +}; + +#define TEST_realloc(checker) do { \ + gfp_t gfp = GFP_KERNEL; \ + size_t len; \ + int i; \ + \ + for (i = 0; i < ARRAY_SIZE(test_strs); i++) { \ + len = strlen(test_strs[i]); \ + KUNIT_EXPECT_EQ(test, __builtin_constant_p(len), 0); \ + checker(len, kmemdup_array(test_strs[i], len, 1, gfp), \ + kfree(p)); \ + checker(len, kmemdup(test_strs[i], len, gfp), \ + kfree(p)); \ + } \ +} while (0) +static void fortify_test_realloc_size(struct kunit *test) +{ + TEST_realloc(check_dynamic); +} + /* * We can't have an array at the end of a structure or else * builds without -fstrict-flex-arrays=3 will report them as @@ -1046,6 +1071,7 @@ static struct kunit_case fortify_test_cases[] = { KUNIT_CASE(fortify_test_alloc_size_kvmalloc_dynamic), KUNIT_CASE(fortify_test_alloc_size_devm_kmalloc_const), KUNIT_CASE(fortify_test_alloc_size_devm_kmalloc_dynamic), + KUNIT_CASE(fortify_test_realloc_size), KUNIT_CASE(fortify_test_strlen), KUNIT_CASE(fortify_test_strnlen), KUNIT_CASE(fortify_test_strcpy), -- cgit v1.2.3 From 3f9b8fb46e5d20eac314f56747e24e1a4e74539d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 12 Apr 2024 00:54:19 -0400 Subject: Use bdev_is_paritition() instead of open-coding it Reviewed-by: Christoph Hellwig Signed-off-by: Al Viro --- block/blk-core.c | 5 +++-- block/blk-mq.c | 2 +- include/linux/part_stat.h | 2 +- lib/vsprintf.c | 2 +- 4 files changed, 6 insertions(+), 5 deletions(-) (limited to 'lib') diff --git a/block/blk-core.c b/block/blk-core.c index a16b5abdbbf5..20322abc6082 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -759,7 +759,8 @@ void submit_bio_noacct(struct bio *bio) if (!bio_flagged(bio, BIO_REMAPPED)) { if (unlikely(bio_check_eod(bio))) goto end_io; - if (bdev->bd_partno && unlikely(blk_partition_remap(bio))) + if (bdev_is_partition(bdev) && + unlikely(blk_partition_remap(bio))) goto end_io; } @@ -989,7 +990,7 @@ again: if (likely(try_cmpxchg(&part->bd_stamp, &stamp, now))) __part_stat_add(part, io_ticks, end ? now - stamp : 1); } - if (part->bd_partno) { + if (bdev_is_partition(part)) { part = bdev_whole(part); goto again; } diff --git a/block/blk-mq.c b/block/blk-mq.c index 32afb87efbd0..43bb8f50a07c 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -92,7 +92,7 @@ static bool blk_mq_check_inflight(struct request *rq, void *priv) struct mq_inflight *mi = priv; if (rq->part && blk_do_io_stat(rq) && - (!mi->part->bd_partno || rq->part == mi->part) && + (!bdev_is_partition(mi->part) || rq->part == mi->part) && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) mi->inflight[rq_data_dir(rq)]++; diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index abeba356bc3f..ac8c44dd8237 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -59,7 +59,7 @@ static inline void part_stat_set_all(struct block_device *part, int value) #define part_stat_add(part, field, addnd) do { \ __part_stat_add((part), field, addnd); \ - if ((part)->bd_partno) \ + if (bdev_is_partition(part)) \ __part_stat_add(bdev_whole(part), field, addnd); \ } while (0) diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 552738f14275..3f9f1b959ef0 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -966,7 +966,7 @@ char *bdev_name(char *buf, char *end, struct block_device *bdev, hd = bdev->bd_disk; buf = string(buf, end, hd->disk_name, spec); - if (bdev->bd_partno) { + if (bdev_is_partition(bdev)) { if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) { if (buf < end) *buf = 'p'; -- cgit v1.2.3 From b8c873edbf35570b93edfeddad9e85da54defa52 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 12 Apr 2024 01:01:36 -0400 Subject: wrapper for access to ->bd_partno On the next step it's going to get folded into a field where flags will go. Signed-off-by: Al Viro --- block/early-lookup.c | 2 +- block/partitions/core.c | 12 ++++++------ include/linux/blkdev.h | 7 ++++++- lib/vsprintf.c | 2 +- 4 files changed, 14 insertions(+), 9 deletions(-) (limited to 'lib') diff --git a/block/early-lookup.c b/block/early-lookup.c index 3effbd0d35e9..3fb57f7d2b12 100644 --- a/block/early-lookup.c +++ b/block/early-lookup.c @@ -78,7 +78,7 @@ static int __init devt_from_partuuid(const char *uuid_str, dev_t *devt) * to the partition number found by UUID. */ *devt = part_devt(dev_to_disk(dev), - dev_to_bdev(dev)->bd_partno + offset); + bdev_partno(dev_to_bdev(dev)) + offset); } else { *devt = dev->devt; } diff --git a/block/partitions/core.c b/block/partitions/core.c index b11e88c82c8c..edd5309dc4ba 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -173,7 +173,7 @@ static struct parsed_partitions *check_partition(struct gendisk *hd) static ssize_t part_partition_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", dev_to_bdev(dev)->bd_partno); + return sprintf(buf, "%d\n", bdev_partno(dev_to_bdev(dev))); } static ssize_t part_start_show(struct device *dev, @@ -250,7 +250,7 @@ static int part_uevent(const struct device *dev, struct kobj_uevent_env *env) { const struct block_device *part = dev_to_bdev(dev); - add_uevent_var(env, "PARTN=%u", part->bd_partno); + add_uevent_var(env, "PARTN=%u", bdev_partno(part)); if (part->bd_meta_info && part->bd_meta_info->volname[0]) add_uevent_var(env, "PARTNAME=%s", part->bd_meta_info->volname); return 0; @@ -267,7 +267,7 @@ void drop_partition(struct block_device *part) { lockdep_assert_held(&part->bd_disk->open_mutex); - xa_erase(&part->bd_disk->part_tbl, part->bd_partno); + xa_erase(&part->bd_disk->part_tbl, bdev_partno(part)); kobject_put(part->bd_holder_dir); device_del(&part->bd_device); @@ -338,8 +338,8 @@ static struct block_device *add_partition(struct gendisk *disk, int partno, pdev->parent = ddev; /* in consecutive minor range? */ - if (bdev->bd_partno < disk->minors) { - devt = MKDEV(disk->major, disk->first_minor + bdev->bd_partno); + if (bdev_partno(bdev) < disk->minors) { + devt = MKDEV(disk->major, disk->first_minor + bdev_partno(bdev)); } else { err = blk_alloc_ext_minor(); if (err < 0) @@ -404,7 +404,7 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start, rcu_read_lock(); xa_for_each_start(&disk->part_tbl, idx, part, 1) { - if (part->bd_partno != skip_partno && + if (bdev_partno(part) != skip_partno && start < part->bd_start_sect + bdev_nr_sectors(part) && start + length > part->bd_start_sect) { overlap = true; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c3e8f7cf96be..32549d675955 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -720,6 +720,11 @@ void invalidate_disk(struct gendisk *disk); void set_disk_ro(struct gendisk *disk, bool read_only); void disk_uevent(struct gendisk *disk, enum kobject_action action); +static inline u8 bdev_partno(const struct block_device *bdev) +{ + return bdev->bd_partno; +} + static inline int get_disk_ro(struct gendisk *disk) { return disk->part0->bd_read_only || @@ -1095,7 +1100,7 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, static inline bool bdev_is_partition(struct block_device *bdev) { - return bdev->bd_partno; + return bdev_partno(bdev) != 0; } enum blk_default_limits { diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 3f9f1b959ef0..cdd4e2314bfc 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -972,7 +972,7 @@ char *bdev_name(char *buf, char *end, struct block_device *bdev, *buf = 'p'; buf++; } - buf = number(buf, end, bdev->bd_partno, spec); + buf = number(buf, end, bdev_partno(bdev), spec); } return buf; } -- cgit v1.2.3 From 955a923d2809803980ff574270f81510112be9cf Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Mon, 22 Apr 2024 16:33:49 -0400 Subject: maple_tree: fix mas_empty_area_rev() null pointer dereference Currently the code calls mas_start() followed by mas_data_end() if the maple state is MA_START, but mas_start() may return with the maple state node == NULL. This will lead to a null pointer dereference when checking information in the NULL node, which is done in mas_data_end(). Avoid setting the offset if there is no node by waiting until after the maple state is checked for an empty or single entry state. A user could trigger the events to cause a kernel oops by unmapping all vmas to produce an empty maple tree, then mapping a vma that would cause the scenario described above. Link: https://lkml.kernel.org/r/20240422203349.2418465-1-Liam.Howlett@oracle.com Fixes: 54a611b60590 ("Maple Tree: add new data structure") Signed-off-by: Liam R. Howlett Reported-by: Marius Fleischer Closes: https://lore.kernel.org/lkml/CAJg=8jyuSxDL6XvqEXY_66M20psRK2J53oBTP+fjV5xpW2-R6w@mail.gmail.com/ Link: https://lore.kernel.org/lkml/CAJg=8jyuSxDL6XvqEXY_66M20psRK2J53oBTP+fjV5xpW2-R6w@mail.gmail.com/ Tested-by: Marius Fleischer Tested-by: Sidhartha Kumar Cc: Signed-off-by: Andrew Morton --- lib/maple_tree.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'lib') diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 55e1b35bf877..2d7d27e6ae3c 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5109,18 +5109,18 @@ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, if (size == 0 || max - min < size - 1) return -EINVAL; - if (mas_is_start(mas)) { + if (mas_is_start(mas)) mas_start(mas); - mas->offset = mas_data_end(mas); - } else if (mas->offset >= 2) { - mas->offset -= 2; - } else if (!mas_rewind_node(mas)) { + else if ((mas->offset < 2) && (!mas_rewind_node(mas))) return -EBUSY; - } - /* Empty set. */ - if (mas_is_none(mas) || mas_is_ptr(mas)) + if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) return mas_sparse_area(mas, min, max, size, false); + else if (mas->offset >= 2) + mas->offset -= 2; + else + mas->offset = mas_data_end(mas); + /* The start of the window can only be within these values. */ mas->index = min; -- cgit v1.2.3 From 2aaba39e783a10fd1368626bce6f618a6a2a78b0 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Tue, 23 Apr 2024 12:22:21 -0700 Subject: lib/test_xarray.c: fix error assumptions on check_xa_multi_store_adv_add() While testing lib/test_xarray in userspace I've noticed we can fail with: make -C tools/testing/radix-tree ./tools/testing/radix-tree/xarray BUG at check_xa_multi_store_adv_add:749 xarray: 0x55905fb21a00x head 0x55905fa1d8e0x flags 0 marks 0 0 0 0: 0x55905fa1d8e0x xarray: ../../../lib/test_xarray.c:749: check_xa_multi_store_adv_add: Assertion `0' failed. Aborted We get a failure with a BUG_ON(), and that is because we actually can fail due to -ENOMEM, the check in xas_nomem() will fix this for us so it makes no sense to expect no failure inside the loop. So modify the check and since this is also useful for instructional purposes clarify the situation. The check for XA_BUG_ON(xa, xa_load(xa, index) != p) is already done at the end of the loop so just remove the bogus on inside the loop. With this we now pass the test in both kernel and userspace: In userspace: ./tools/testing/radix-tree/xarray XArray: 149092856 of 149092856 tests passed In kernel space: XArray: 148257077 of 148257077 tests passed Link: https://lkml.kernel.org/r/20240423192221.301095-3-mcgrof@kernel.org Fixes: a60cc288a1a2 ("test_xarray: add tests for advanced multi-index use") Signed-off-by: Luis Chamberlain Cc: Daniel Gomez Cc: Darrick J. Wong Cc: Dave Chinner Cc: "Liam R. Howlett" Cc: Matthew Wilcox (Oracle) Cc: Pankaj Raghav Signed-off-by: Andrew Morton --- lib/test_xarray.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/test_xarray.c b/lib/test_xarray.c index ebe2af2e072d..5ab35190aae3 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -744,15 +744,20 @@ static noinline void check_xa_multi_store_adv_add(struct xarray *xa, do { xas_lock_irq(&xas); - xas_store(&xas, p); - XA_BUG_ON(xa, xas_error(&xas)); - XA_BUG_ON(xa, xa_load(xa, index) != p); - xas_unlock_irq(&xas); + /* + * In our selftest case the only failure we can expect is for + * there not to be enough memory as we're not mimicking the + * entire page cache, so verify that's the only error we can run + * into here. The xas_nomem() which follows will ensure to fix + * that condition for us so to chug on on the loop. + */ + XA_BUG_ON(xa, xas_error(&xas) && xas_error(&xas) != -ENOMEM); } while (xas_nomem(&xas, GFP_KERNEL)); XA_BUG_ON(xa, xas_error(&xas)); + XA_BUG_ON(xa, xa_load(xa, index) != p); } /* mimics page_cache_delete() */ -- cgit v1.2.3 From 2a0774c2886d25f4d2987cd3e3813d16bf96f34f Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 1 May 2024 16:31:18 +0100 Subject: XArray: set the marks correctly when splitting an entry If we created a new node to replace an entry which had search marks set, we were setting the search mark on every entry in that node. That works fine when we're splitting to order 0, but when splitting to a larger order, we must not set the search marks on the sibling entries. Link: https://lkml.kernel.org/r/20240501153120.4094530-1-willy@infradead.org Fixes: c010d47f107f ("mm: thp: split huge page to any lower order pages") Signed-off-by: Matthew Wilcox (Oracle) Reported-by: Luis Chamberlain Link: https://lore.kernel.org/r/ZjFGCOYk3FK_zVy3@bombadil.infradead.org Tested-by: Luis Chamberlain Cc: Zi Yan Signed-off-by: Andrew Morton --- lib/test_xarray.c | 14 +++++++++++++- lib/xarray.c | 23 +++++++++++++++++++---- 2 files changed, 32 insertions(+), 5 deletions(-) (limited to 'lib') diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 5ab35190aae3..928fc20337e6 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -1788,9 +1788,11 @@ static void check_split_1(struct xarray *xa, unsigned long index, unsigned int order, unsigned int new_order) { XA_STATE_ORDER(xas, xa, index, new_order); - unsigned int i; + unsigned int i, found; + void *entry; xa_store_order(xa, index, order, xa, GFP_KERNEL); + xa_set_mark(xa, index, XA_MARK_1); xas_split_alloc(&xas, xa, order, GFP_KERNEL); xas_lock(&xas); @@ -1807,6 +1809,16 @@ static void check_split_1(struct xarray *xa, unsigned long index, xa_set_mark(xa, index, XA_MARK_0); XA_BUG_ON(xa, !xa_get_mark(xa, index, XA_MARK_0)); + xas_set_order(&xas, index, 0); + found = 0; + rcu_read_lock(); + xas_for_each_marked(&xas, entry, ULONG_MAX, XA_MARK_1) { + found++; + XA_BUG_ON(xa, xa_is_internal(entry)); + } + rcu_read_unlock(); + XA_BUG_ON(xa, found != 1 << (order - new_order)); + xa_destroy(xa); } diff --git a/lib/xarray.c b/lib/xarray.c index 39f07bfc4dcc..5e7d6334d70d 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -969,8 +969,22 @@ static unsigned int node_get_marks(struct xa_node *node, unsigned int offset) return marks; } +static inline void node_mark_slots(struct xa_node *node, unsigned int sibs, + xa_mark_t mark) +{ + int i; + + if (sibs == 0) + node_mark_all(node, mark); + else { + for (i = 0; i < XA_CHUNK_SIZE; i += sibs + 1) + node_set_mark(node, i, mark); + } +} + static void node_set_marks(struct xa_node *node, unsigned int offset, - struct xa_node *child, unsigned int marks) + struct xa_node *child, unsigned int sibs, + unsigned int marks) { xa_mark_t mark = XA_MARK_0; @@ -978,7 +992,7 @@ static void node_set_marks(struct xa_node *node, unsigned int offset, if (marks & (1 << (__force unsigned int)mark)) { node_set_mark(node, offset, mark); if (child) - node_mark_all(child, mark); + node_mark_slots(child, sibs, mark); } if (mark == XA_MARK_MAX) break; @@ -1077,7 +1091,8 @@ void xas_split(struct xa_state *xas, void *entry, unsigned int order) child->nr_values = xa_is_value(entry) ? XA_CHUNK_SIZE : 0; RCU_INIT_POINTER(child->parent, node); - node_set_marks(node, offset, child, marks); + node_set_marks(node, offset, child, xas->xa_sibs, + marks); rcu_assign_pointer(node->slots[offset], xa_mk_node(child)); if (xa_is_value(curr)) @@ -1086,7 +1101,7 @@ void xas_split(struct xa_state *xas, void *entry, unsigned int order) } else { unsigned int canon = offset - xas->xa_sibs; - node_set_marks(node, canon, NULL, marks); + node_set_marks(node, canon, NULL, 0, marks); rcu_assign_pointer(node->slots[canon], entry); while (offset > canon) rcu_assign_pointer(node->slots[offset--], -- cgit v1.2.3 From ba591801a3df861b3b327f6122b9de4ef213aae6 Mon Sep 17 00:00:00 2001 From: Long Li Date: Tue, 16 Apr 2024 14:16:28 +0800 Subject: xarray: inline xas_descend to improve performance The commit 63b1898fffcd ("XArray: Disallow sibling entries of nodes") modified the xas_descend function in such a way that it was no longer being compiled as an inline function, because it increased the size of xas_descend(), and the compiler no longer optimizes it as inline. This had a negative impact on performance, xas_descend is called frequently to traverse downwards in the xarray tree, making it a hot function. Inlining xas_descend has been shown to significantly improve performance by approximately 4.95% in the iozone write test. Machine: Intel(R) Xeon(R) Gold 6240 CPU @ 2.60GHz #iozone i 0 -i 1 -s 64g -r 16m -f /test/tmptest Before this patch: kB reclen write rewrite read reread 67108864 16384 2230080 3637689 6315197 5496027 After this patch: kB reclen write rewrite read reread 67108864 16384 2340360 3666175 6272401 5460782 Percentage change: 4.95% 0.78% -0.68% -0.64% This patch introduces inlining to the xas_descend function. While this change increases the size of lib/xarray.o, the performance gains in critical workloads make this an acceptable trade-off. Size comparison before and after patch: .text .data .bss file 0x3502 0 0 lib/xarray.o.before 0x3602 0 0 lib/xarray.o.after Link: https://lkml.kernel.org/r/20240416061628.3768901-1-leo.lilong@huawei.com Signed-off-by: Long Li Cc: Hou Tao Cc: Matthew Wilcox (Oracle) Cc: yangerkun Cc: Zhang Yi Signed-off-by: Andrew Morton --- lib/xarray.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/xarray.c b/lib/xarray.c index da79128ad754..1c87d871cacf 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -200,7 +200,8 @@ static void *xas_start(struct xa_state *xas) return entry; } -static void *xas_descend(struct xa_state *xas, struct xa_node *node) +static __always_inline void *xas_descend(struct xa_state *xas, + struct xa_node *node) { unsigned int offset = get_offset(xas->xa_index, node); void *entry = xa_entry(xas->xa, node, offset); -- cgit v1.2.3 From cde5e1b4a90486b4ac731ee43e4e0152cc16887b Mon Sep 17 00:00:00 2001 From: Mickaël Salaün Date: Mon, 8 Apr 2024 09:46:19 +0200 Subject: kunit: Handle thread creation error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Previously, if a thread creation failed (e.g. -ENOMEM), the function was called (kunit_catch_run_case or kunit_catch_run_case_cleanup) without marking the test as failed. Instead, fill try_result with the error code returned by kthread_run(), which will mark the test as failed and print "internal error occurred...". Cc: Brendan Higgins Cc: Shuah Khan Reviewed-by: Kees Cook Reviewed-by: Rae Moar Reviewed-by: David Gow Signed-off-by: Mickaël Salaün Link: https://lore.kernel.org/r/20240408074625.65017-2-mic@digikod.net Signed-off-by: Shuah Khan --- lib/kunit/try-catch.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/kunit/try-catch.c b/lib/kunit/try-catch.c index f7825991d576..a5cb2ef70a25 100644 --- a/lib/kunit/try-catch.c +++ b/lib/kunit/try-catch.c @@ -69,6 +69,7 @@ void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context) try_catch, "kunit_try_catch_thread"); if (IS_ERR(task_struct)) { + try_catch->try_result = PTR_ERR(task_struct); try_catch->catch(try_catch->context); return; } -- cgit v1.2.3 From f8aa1b98ce40184521ed95ec26cc115a255183b2 Mon Sep 17 00:00:00 2001 From: Mickaël Salaün Date: Mon, 8 Apr 2024 09:46:20 +0200 Subject: kunit: Fix kthread reference MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a race condition when a kthread finishes after the deadline and before the call to kthread_stop(), which may lead to use after free. Cc: Brendan Higgins Cc: Shuah Khan Reviewed-by: Kees Cook Fixes: adf505457032 ("kunit: fix UAF when run kfence test case test_gfpzero") Reviewed-by: David Gow Reviewed-by: Rae Moar Signed-off-by: Mickaël Salaün Link: https://lore.kernel.org/r/20240408074625.65017-3-mic@digikod.net Signed-off-by: Shuah Khan --- lib/kunit/try-catch.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/lib/kunit/try-catch.c b/lib/kunit/try-catch.c index a5cb2ef70a25..73f5007f20ea 100644 --- a/lib/kunit/try-catch.c +++ b/lib/kunit/try-catch.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "try-catch-impl.h" @@ -65,14 +66,15 @@ void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context) try_catch->context = context; try_catch->try_completion = &try_completion; try_catch->try_result = 0; - task_struct = kthread_run(kunit_generic_run_threadfn_adapter, - try_catch, - "kunit_try_catch_thread"); + task_struct = kthread_create(kunit_generic_run_threadfn_adapter, + try_catch, "kunit_try_catch_thread"); if (IS_ERR(task_struct)) { try_catch->try_result = PTR_ERR(task_struct); try_catch->catch(try_catch->context); return; } + get_task_struct(task_struct); + wake_up_process(task_struct); time_remaining = wait_for_completion_timeout(&try_completion, kunit_test_timeout()); @@ -82,6 +84,7 @@ void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context) kthread_stop(task_struct); } + put_task_struct(task_struct); exit_code = try_catch->try_result; if (!exit_code) -- cgit v1.2.3 From 53026ff63bb07c04a0e962a74723eb10ff6f9dc7 Mon Sep 17 00:00:00 2001 From: Mickaël Salaün Date: Mon, 8 Apr 2024 09:46:21 +0200 Subject: kunit: Fix timeout message MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The exit code is always checked, so let's properly handle the -ETIMEDOUT error code. Cc: Brendan Higgins Cc: Shuah Khan Reviewed-by: Kees Cook Reviewed-by: David Gow Reviewed-by: Rae Moar Signed-off-by: Mickaël Salaün Link: https://lore.kernel.org/r/20240408074625.65017-4-mic@digikod.net Signed-off-by: Shuah Khan --- lib/kunit/try-catch.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/kunit/try-catch.c b/lib/kunit/try-catch.c index 73f5007f20ea..cab8b24b5d5a 100644 --- a/lib/kunit/try-catch.c +++ b/lib/kunit/try-catch.c @@ -79,7 +79,6 @@ void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context) time_remaining = wait_for_completion_timeout(&try_completion, kunit_test_timeout()); if (time_remaining == 0) { - kunit_err(test, "try timed out\n"); try_catch->try_result = -ETIMEDOUT; kthread_stop(task_struct); } @@ -94,6 +93,8 @@ void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context) try_catch->try_result = 0; else if (exit_code == -EINTR) kunit_err(test, "wake_up_process() was never called\n"); + else if (exit_code == -ETIMEDOUT) + kunit_err(test, "try timed out\n"); else if (exit_code) kunit_err(test, "Unknown error: %d\n", exit_code); -- cgit v1.2.3 From 3a35c13007dea132a65f07de05c26b87837fadc2 Mon Sep 17 00:00:00 2001 From: Mickaël Salaün Date: Mon, 8 Apr 2024 09:46:22 +0200 Subject: kunit: Handle test faults MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Previously, when a kernel test thread crashed (e.g. NULL pointer dereference, general protection fault), the KUnit test hanged for 30 seconds and exited with a timeout error. Fix this issue by waiting on task_struct->vfork_done instead of the custom kunit_try_catch.try_completion, and track the execution state by initially setting try_result with -EINTR and only setting it to 0 if the test passed. Fix kunit_generic_run_threadfn_adapter() signature by returning 0 instead of calling kthread_complete_and_exit(). Because thread's exit code is never checked, always set it to 0 to make it clear. To make this explicit, export kthread_exit() for KUnit tests built as module. Fix the -EINTR error message, which couldn't be reached until now. This is tested with a following patch. Cc: Brendan Higgins Cc: Eric W. Biederman Cc: Shuah Khan Reviewed-by: Kees Cook Reviewed-by: David Gow Tested-by: Rae Moar Signed-off-by: Mickaël Salaün Link: https://lore.kernel.org/r/20240408074625.65017-5-mic@digikod.net Signed-off-by: Shuah Khan --- include/kunit/try-catch.h | 3 --- kernel/kthread.c | 1 + lib/kunit/try-catch.c | 19 ++++++++++++------- 3 files changed, 13 insertions(+), 10 deletions(-) (limited to 'lib') diff --git a/include/kunit/try-catch.h b/include/kunit/try-catch.h index c507dd43119d..7c966a1adbd3 100644 --- a/include/kunit/try-catch.h +++ b/include/kunit/try-catch.h @@ -14,13 +14,11 @@ typedef void (*kunit_try_catch_func_t)(void *); -struct completion; struct kunit; /** * struct kunit_try_catch - provides a generic way to run code which might fail. * @test: The test case that is currently being executed. - * @try_completion: Completion that the control thread waits on while test runs. * @try_result: Contains any errno obtained while running test case. * @try: The function, the test case, to attempt to run. * @catch: The function called if @try bails out. @@ -46,7 +44,6 @@ struct kunit; struct kunit_try_catch { /* private: internal use only. */ struct kunit *test; - struct completion *try_completion; int try_result; kunit_try_catch_func_t try; kunit_try_catch_func_t catch; diff --git a/kernel/kthread.c b/kernel/kthread.c index c5e40830c1f2..f7be976ff88a 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -315,6 +315,7 @@ void __noreturn kthread_exit(long result) kthread->result = result; do_exit(0); } +EXPORT_SYMBOL(kthread_exit); /** * kthread_complete_and_exit - Exit the current kthread. diff --git a/lib/kunit/try-catch.c b/lib/kunit/try-catch.c index cab8b24b5d5a..7a3910dd78a6 100644 --- a/lib/kunit/try-catch.c +++ b/lib/kunit/try-catch.c @@ -18,7 +18,7 @@ void __noreturn kunit_try_catch_throw(struct kunit_try_catch *try_catch) { try_catch->try_result = -EFAULT; - kthread_complete_and_exit(try_catch->try_completion, -EFAULT); + kthread_exit(0); } EXPORT_SYMBOL_GPL(kunit_try_catch_throw); @@ -26,9 +26,12 @@ static int kunit_generic_run_threadfn_adapter(void *data) { struct kunit_try_catch *try_catch = data; + try_catch->try_result = -EINTR; try_catch->try(try_catch->context); + if (try_catch->try_result == -EINTR) + try_catch->try_result = 0; - kthread_complete_and_exit(try_catch->try_completion, 0); + return 0; } static unsigned long kunit_test_timeout(void) @@ -58,13 +61,11 @@ static unsigned long kunit_test_timeout(void) void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context) { - DECLARE_COMPLETION_ONSTACK(try_completion); struct kunit *test = try_catch->test; struct task_struct *task_struct; int exit_code, time_remaining; try_catch->context = context; - try_catch->try_completion = &try_completion; try_catch->try_result = 0; task_struct = kthread_create(kunit_generic_run_threadfn_adapter, try_catch, "kunit_try_catch_thread"); @@ -75,8 +76,12 @@ void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context) } get_task_struct(task_struct); wake_up_process(task_struct); - - time_remaining = wait_for_completion_timeout(&try_completion, + /* + * As for a vfork(2), task_struct->vfork_done (pointing to the + * underlying kthread->exited) can be used to wait for the end of a + * kernel thread. + */ + time_remaining = wait_for_completion_timeout(task_struct->vfork_done, kunit_test_timeout()); if (time_remaining == 0) { try_catch->try_result = -ETIMEDOUT; @@ -92,7 +97,7 @@ void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context) if (exit_code == -EFAULT) try_catch->try_result = 0; else if (exit_code == -EINTR) - kunit_err(test, "wake_up_process() was never called\n"); + kunit_err(test, "try faulted\n"); else if (exit_code == -ETIMEDOUT) kunit_err(test, "try timed out\n"); else if (exit_code) -- cgit v1.2.3 From 70585f05fbd2bfc25289ff8d95189fa2ed80b9a4 Mon Sep 17 00:00:00 2001 From: Mickaël Salaün Date: Mon, 8 Apr 2024 09:46:23 +0200 Subject: kunit: Fix KUNIT_SUCCESS() calls in iov_iter tests MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix KUNIT_SUCCESS() calls to pass a test argument. This is a no-op for now because this macro does nothing, but it will be required for the next commit. Cc: Brendan Higgins Cc: Rae Moar Cc: Shuah Khan Reviewed-by: Kees Cook Reviewed-by: David Gow Signed-off-by: Mickaël Salaün Link: https://lore.kernel.org/r/20240408074625.65017-6-mic@digikod.net Signed-off-by: Shuah Khan --- lib/kunit_iov_iter.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'lib') diff --git a/lib/kunit_iov_iter.c b/lib/kunit_iov_iter.c index 859b67c4d697..27e0c8ee71d8 100644 --- a/lib/kunit_iov_iter.c +++ b/lib/kunit_iov_iter.c @@ -139,7 +139,7 @@ static void __init iov_kunit_copy_to_kvec(struct kunit *test) return; } - KUNIT_SUCCEED(); + KUNIT_SUCCEED(test); } /* @@ -194,7 +194,7 @@ stop: return; } - KUNIT_SUCCEED(); + KUNIT_SUCCEED(test); } struct bvec_test_range { @@ -302,7 +302,7 @@ static void __init iov_kunit_copy_to_bvec(struct kunit *test) return; } - KUNIT_SUCCEED(); + KUNIT_SUCCEED(test); } /* @@ -359,7 +359,7 @@ stop: return; } - KUNIT_SUCCEED(); + KUNIT_SUCCEED(test); } static void iov_kunit_destroy_xarray(void *data) @@ -453,7 +453,7 @@ static void __init iov_kunit_copy_to_xarray(struct kunit *test) return; } - KUNIT_SUCCEED(); + KUNIT_SUCCEED(test); } /* @@ -516,7 +516,7 @@ stop: return; } - KUNIT_SUCCEED(); + KUNIT_SUCCEED(test); } /* @@ -596,7 +596,7 @@ static void __init iov_kunit_extract_pages_kvec(struct kunit *test) stop: KUNIT_EXPECT_EQ(test, size, 0); KUNIT_EXPECT_EQ(test, iter.count, 0); - KUNIT_SUCCEED(); + KUNIT_SUCCEED(test); } /* @@ -674,7 +674,7 @@ static void __init iov_kunit_extract_pages_bvec(struct kunit *test) stop: KUNIT_EXPECT_EQ(test, size, 0); KUNIT_EXPECT_EQ(test, iter.count, 0); - KUNIT_SUCCEED(); + KUNIT_SUCCEED(test); } /* @@ -753,7 +753,7 @@ static void __init iov_kunit_extract_pages_xarray(struct kunit *test) } stop: - KUNIT_SUCCEED(); + KUNIT_SUCCEED(test); } static struct kunit_case __refdata iov_kunit_cases[] = { -- cgit v1.2.3 From 8bd5d74babc92558da67497918210e053515b2c4 Mon Sep 17 00:00:00 2001 From: Mickaël Salaün Date: Mon, 8 Apr 2024 09:46:24 +0200 Subject: kunit: Print last test location on fault MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This helps identify the location of test faults with opportunistic calls to _KUNIT_SAVE_LOC(). This can be useful while writing tests or debugging them. It is possible to call KUNIT_SUCCESS() to explicit save last location. Cc: Brendan Higgins Cc: David Gow Cc: Rae Moar Cc: Shuah Khan Reviewed-by: Kees Cook Signed-off-by: Mickaël Salaün Link: https://lore.kernel.org/r/20240408074625.65017-7-mic@digikod.net Signed-off-by: Shuah Khan --- include/kunit/test.h | 24 +++++++++++++++++++++--- lib/kunit/try-catch.c | 10 +++++++--- 2 files changed, 28 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/include/kunit/test.h b/include/kunit/test.h index 61637ef32302..e32b4cb7afa2 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -301,6 +301,8 @@ struct kunit { struct list_head resources; /* Protected by lock. */ char status_comment[KUNIT_STATUS_COMMENT_SIZE]; + /* Saves the last seen test. Useful to help with faults. */ + struct kunit_loc last_seen; }; static inline void kunit_set_failure(struct kunit *test) @@ -567,6 +569,15 @@ void __printf(2, 3) kunit_log_append(struct string_stream *log, const char *fmt, #define kunit_err(test, fmt, ...) \ kunit_printk(KERN_ERR, test, fmt, ##__VA_ARGS__) +/* + * Must be called at the beginning of each KUNIT_*_ASSERTION(). + * Cf. KUNIT_CURRENT_LOC. + */ +#define _KUNIT_SAVE_LOC(test) do { \ + WRITE_ONCE(test->last_seen.file, __FILE__); \ + WRITE_ONCE(test->last_seen.line, __LINE__); \ +} while (0) + /** * KUNIT_SUCCEED() - A no-op expectation. Only exists for code clarity. * @test: The test context object. @@ -575,7 +586,7 @@ void __printf(2, 3) kunit_log_append(struct string_stream *log, const char *fmt, * words, it does nothing and only exists for code clarity. See * KUNIT_EXPECT_TRUE() for more information. */ -#define KUNIT_SUCCEED(test) do {} while (0) +#define KUNIT_SUCCEED(test) _KUNIT_SAVE_LOC(test) void __noreturn __kunit_abort(struct kunit *test); @@ -601,14 +612,16 @@ void __printf(6, 7) __kunit_do_failed_assertion(struct kunit *test, } while (0) -#define KUNIT_FAIL_ASSERTION(test, assert_type, fmt, ...) \ +#define KUNIT_FAIL_ASSERTION(test, assert_type, fmt, ...) do { \ + _KUNIT_SAVE_LOC(test); \ _KUNIT_FAILED(test, \ assert_type, \ kunit_fail_assert, \ kunit_fail_assert_format, \ {}, \ fmt, \ - ##__VA_ARGS__) + ##__VA_ARGS__); \ +} while (0) /** * KUNIT_FAIL() - Always causes a test to fail when evaluated. @@ -637,6 +650,7 @@ void __printf(6, 7) __kunit_do_failed_assertion(struct kunit *test, fmt, \ ...) \ do { \ + _KUNIT_SAVE_LOC(test); \ if (likely(!!(condition_) == !!expected_true_)) \ break; \ \ @@ -698,6 +712,7 @@ do { \ .right_text = #right, \ }; \ \ + _KUNIT_SAVE_LOC(test); \ if (likely(__left op __right)) \ break; \ \ @@ -758,6 +773,7 @@ do { \ .right_text = #right, \ }; \ \ + _KUNIT_SAVE_LOC(test); \ if (likely((__left) && (__right) && (strcmp(__left, __right) op 0))) \ break; \ \ @@ -791,6 +807,7 @@ do { \ .right_text = #right, \ }; \ \ + _KUNIT_SAVE_LOC(test); \ if (likely(__left && __right)) \ if (likely(memcmp(__left, __right, __size) op 0)) \ break; \ @@ -815,6 +832,7 @@ do { \ do { \ const typeof(ptr) __ptr = (ptr); \ \ + _KUNIT_SAVE_LOC(test); \ if (!IS_ERR_OR_NULL(__ptr)) \ break; \ \ diff --git a/lib/kunit/try-catch.c b/lib/kunit/try-catch.c index 7a3910dd78a6..fa687278ccc9 100644 --- a/lib/kunit/try-catch.c +++ b/lib/kunit/try-catch.c @@ -96,9 +96,13 @@ void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context) if (exit_code == -EFAULT) try_catch->try_result = 0; - else if (exit_code == -EINTR) - kunit_err(test, "try faulted\n"); - else if (exit_code == -ETIMEDOUT) + else if (exit_code == -EINTR) { + if (test->last_seen.file) + kunit_err(test, "try faulted: last line seen %s:%d\n", + test->last_seen.file, test->last_seen.line); + else + kunit_err(test, "try faulted\n"); + } else if (exit_code == -ETIMEDOUT) kunit_err(test, "try timed out\n"); else if (exit_code) kunit_err(test, "Unknown error: %d\n", exit_code); -- cgit v1.2.3 From 170c31737cf31770916c6cbadab04c5134f0d961 Mon Sep 17 00:00:00 2001 From: Mickaël Salaün Date: Mon, 8 Apr 2024 09:46:25 +0200 Subject: kunit: Add tests for fault MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a test case to check NULL pointer dereference and make sure it would result as a failed test. The full kunit_fault test suite is marked as skipped when run on UML because it would result to a kernel panic. Tested with: ./tools/testing/kunit/kunit.py run --arch x86_64 kunit_fault ./tools/testing/kunit/kunit.py run --arch arm64 \ --cross_compile=aarch64-linux-gnu- kunit_fault Cc: Brendan Higgins Cc: Rae Moar Cc: Shuah Khan Reviewed-by: David Gow Signed-off-by: Mickaël Salaün Link: https://lore.kernel.org/r/20240408074625.65017-8-mic@digikod.net Signed-off-by: Shuah Khan --- lib/kunit/kunit-test.c | 45 ++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 44 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c index f7980ef236a3..0fdca5fffaec 100644 --- a/lib/kunit/kunit-test.c +++ b/lib/kunit/kunit-test.c @@ -109,6 +109,48 @@ static struct kunit_suite kunit_try_catch_test_suite = { .test_cases = kunit_try_catch_test_cases, }; +#ifndef CONFIG_UML + +static void kunit_test_null_dereference(void *data) +{ + struct kunit *test = data; + int *null = NULL; + + *null = 0; + + KUNIT_FAIL(test, "This line should never be reached\n"); +} + +static void kunit_test_fault_null_dereference(struct kunit *test) +{ + struct kunit_try_catch_test_context *ctx = test->priv; + struct kunit_try_catch *try_catch = ctx->try_catch; + + kunit_try_catch_init(try_catch, + test, + kunit_test_null_dereference, + kunit_test_catch); + kunit_try_catch_run(try_catch, test); + + KUNIT_EXPECT_EQ(test, try_catch->try_result, -EINTR); + KUNIT_EXPECT_TRUE(test, ctx->function_called); +} + +#endif /* !CONFIG_UML */ + +static struct kunit_case kunit_fault_test_cases[] = { +#ifndef CONFIG_UML + KUNIT_CASE(kunit_test_fault_null_dereference), +#endif /* !CONFIG_UML */ + {} +}; + +static struct kunit_suite kunit_fault_test_suite = { + .name = "kunit_fault", + .init = kunit_try_catch_test_init, + .test_cases = kunit_fault_test_cases, +}; + /* * Context for testing test managed resources * is_resource_initialized is used to test arbitrary resources @@ -826,6 +868,7 @@ static struct kunit_suite kunit_current_test_suite = { kunit_test_suites(&kunit_try_catch_test_suite, &kunit_resource_test_suite, &kunit_log_test_suite, &kunit_status_test_suite, - &kunit_current_test_suite, &kunit_device_test_suite); + &kunit_current_test_suite, &kunit_device_test_suite, + &kunit_fault_test_suite); MODULE_LICENSE("GPL v2"); -- cgit v1.2.3 From 1eb69ded805103ce3ddc8b1a207abd8c24ca9e63 Mon Sep 17 00:00:00 2001 From: David Gow Date: Fri, 12 Apr 2024 10:59:01 +0800 Subject: kunit: Fix race condition in try-catch completion MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit KUnit's try-catch infrastructure now uses vfork_done, which is always set to a valid completion when a kthread is created, but which is set to NULL once the thread terminates. This creates a race condition, where the kthread exits before we can wait on it. Keep a copy of vfork_done, which is taken before we wake_up_process() and so valid, and wait on that instead. Fixes: 93533996100c ("kunit: Handle test faults") Reported-by: Linux Kernel Functional Testing Closes: https://lore.kernel.org/lkml/20240410102710.35911-1-naresh.kamboju@linaro.org/ Tested-by: Linux Kernel Functional Testing Acked-by: Mickaël Salaün Signed-off-by: David Gow Reviewed-by: Rae Moar Tested-by: Miguel Ojeda Signed-off-by: Shuah Khan --- lib/kunit/try-catch.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/lib/kunit/try-catch.c b/lib/kunit/try-catch.c index fa687278ccc9..6bbe0025b079 100644 --- a/lib/kunit/try-catch.c +++ b/lib/kunit/try-catch.c @@ -63,6 +63,7 @@ void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context) { struct kunit *test = try_catch->test; struct task_struct *task_struct; + struct completion *task_done; int exit_code, time_remaining; try_catch->context = context; @@ -75,13 +76,16 @@ void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context) return; } get_task_struct(task_struct); - wake_up_process(task_struct); /* * As for a vfork(2), task_struct->vfork_done (pointing to the * underlying kthread->exited) can be used to wait for the end of a - * kernel thread. + * kernel thread. It is set to NULL when the thread exits, so we + * keep a copy here. */ - time_remaining = wait_for_completion_timeout(task_struct->vfork_done, + task_done = task_struct->vfork_done; + wake_up_process(task_struct); + + time_remaining = wait_for_completion_timeout(task_done, kunit_test_timeout()); if (time_remaining == 0) { try_catch->try_result = -ETIMEDOUT; -- cgit v1.2.3 From fabd480b721eb30aa4e2c89507b53933069f9f6e Mon Sep 17 00:00:00 2001 From: Wander Lairson Costa Date: Fri, 19 Apr 2024 10:25:01 -0300 Subject: kunit: unregister the device on error kunit_init_device() should unregister the device on bus register error, but mistakenly it tries to unregister the bus. Unregister the device instead of the bus. Signed-off-by: Wander Lairson Costa Fixes: d03c720e03bd ("kunit: Add APIs for managing devices") Reviewed-by: Greg Kroah-Hartman Signed-off-by: Shuah Khan --- lib/kunit/device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/kunit/device.c b/lib/kunit/device.c index abc603730b8e..25c81ed465fb 100644 --- a/lib/kunit/device.c +++ b/lib/kunit/device.c @@ -51,7 +51,7 @@ int kunit_bus_init(void) error = bus_register(&kunit_bus_type); if (error) - bus_unregister(&kunit_bus_type); + root_device_unregister(kunit_bus_device); return error; } -- cgit v1.2.3 From 4b513a02fd052ad65566db31ba64ea5ee2ba1ce9 Mon Sep 17 00:00:00 2001 From: David Gow Date: Tue, 23 Apr 2024 17:08:06 +0800 Subject: kunit: test: Move fault tests behind KUNIT_FAULT_TEST Kconfig option MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The NULL dereference tests in kunit_fault deliberately trigger a kernel BUG(), and therefore print the associated stack trace, even when the test passes. This is both annoying (as it bloats the test output), and can confuse some test harnesses, which assume any BUG() is a failure. Allow these tests to be specifically disabled (without disabling all of KUnit's other tests), by placing them behind the CONFIG_KUNIT_FAULT_TEST Kconfig option. This is enabled by default, but can be set to 'n' to disable the test. An empty 'kunit_fault' suite is left behind, which will automatically be marked 'skipped'. As the fault tests already were disabled under UML (as they weren't compatible with its fault handling), we can simply adapt those conditions, and add a dependency on !UML for our new option. Suggested-by: Guenter Roeck Link: https://lore.kernel.org/all/928249cc-e027-4f7f-b43f-502f99a1ea63@roeck-us.net/ Fixes: 82b0beff3497 ("kunit: Add tests for fault") Signed-off-by: David Gow Reviewed-by: Mickaël Salaün Reviewed-by: Rae Moar Signed-off-by: Shuah Khan --- lib/kunit/Kconfig | 11 +++++++++++ lib/kunit/kunit-test.c | 8 ++++---- 2 files changed, 15 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/kunit/Kconfig b/lib/kunit/Kconfig index 68a6daec0aef..34d7242d526d 100644 --- a/lib/kunit/Kconfig +++ b/lib/kunit/Kconfig @@ -24,6 +24,17 @@ config KUNIT_DEBUGFS test suite, which allow users to see results of the last test suite run that occurred. +config KUNIT_FAULT_TEST + bool "Enable KUnit tests which print BUG stacktraces" + depends on KUNIT_TEST + depends on !UML + default y + help + Enables fault handling tests for the KUnit framework. These tests may + trigger a kernel BUG(), and the associated stack trace, even when they + pass. If this conflicts with your test infrastrcture (or is confusing + or annoying), they can be disabled by setting this to N. + config KUNIT_TEST tristate "KUnit test for KUnit" if !KUNIT_ALL_TESTS default KUNIT_ALL_TESTS diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c index 0fdca5fffaec..e3412e0ca399 100644 --- a/lib/kunit/kunit-test.c +++ b/lib/kunit/kunit-test.c @@ -109,7 +109,7 @@ static struct kunit_suite kunit_try_catch_test_suite = { .test_cases = kunit_try_catch_test_cases, }; -#ifndef CONFIG_UML +#if IS_ENABLED(CONFIG_KUNIT_FAULT_TEST) static void kunit_test_null_dereference(void *data) { @@ -136,12 +136,12 @@ static void kunit_test_fault_null_dereference(struct kunit *test) KUNIT_EXPECT_TRUE(test, ctx->function_called); } -#endif /* !CONFIG_UML */ +#endif /* CONFIG_KUNIT_FAULT_TEST */ static struct kunit_case kunit_fault_test_cases[] = { -#ifndef CONFIG_UML +#if IS_ENABLED(CONFIG_KUNIT_FAULT_TEST) KUNIT_CASE(kunit_test_fault_null_dereference), -#endif /* !CONFIG_UML */ +#endif /* CONFIG_KUNIT_FAULT_TEST */ {} }; -- cgit v1.2.3 From a96a39457705018ad1aac79e7a8453ee52b512ba Mon Sep 17 00:00:00 2001 From: Ivan Orlov Date: Tue, 23 Apr 2024 19:27:01 +0100 Subject: kunit: string-stream-test: use KUNIT_DEFINE_ACTION_WRAPPER Use KUNIT_DEFINE_ACTION_WRAPPER macro to define the 'kfree' and 'string_stream_destroy' wrappers for kunit_add_action. Signed-off-by: Ivan Orlov Reviewed-by: Rae Moar Acked-by: David Gow Signed-off-by: Shuah Khan --- lib/kunit/string-stream-test.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'lib') diff --git a/lib/kunit/string-stream-test.c b/lib/kunit/string-stream-test.c index 03fb511826f7..7511442ea98f 100644 --- a/lib/kunit/string-stream-test.c +++ b/lib/kunit/string-stream-test.c @@ -22,18 +22,10 @@ struct string_stream_test_priv { }; /* Avoids a cast warning if kfree() is passed direct to kunit_add_action(). */ -static void kfree_wrapper(void *p) -{ - kfree(p); -} +KUNIT_DEFINE_ACTION_WRAPPER(kfree_wrapper, kfree, const void *); /* Avoids a cast warning if string_stream_destroy() is passed direct to kunit_add_action(). */ -static void cleanup_raw_stream(void *p) -{ - struct string_stream *stream = p; - - string_stream_destroy(stream); -} +KUNIT_DEFINE_ACTION_WRAPPER(cleanup_raw_stream, string_stream_destroy, struct string_stream *); static char *get_concatenated_string(struct kunit *test, struct string_stream *stream) { -- cgit v1.2.3 From 5496b9b77d7420652202b73cf036e69760be5deb Mon Sep 17 00:00:00 2001 From: Scott Mayhew Date: Thu, 21 Mar 2024 10:32:00 -0400 Subject: kunit: bail out early in __kunit_test_suites_init() if there are no suites to test Commit c72a870926c2 added a mutex to prevent kunit tests from running concurrently. Unfortunately that mutex gets locked during module load regardless of whether the module actually has any kunit tests. This causes a problem for kunit tests that might need to load other kernel modules (e.g. gss_krb5_test loading the camellia module). So check to see if there are actually any tests to run before locking the kunit_run_lock mutex. Fixes: c72a870926c2 ("kunit: add ability to run tests after boot using debugfs") Reported-by: Nico Pache Signed-off-by: Scott Mayhew Reviewed-by: Rae Moar Reviewed-by: David Gow Signed-off-by: Shuah Khan --- lib/kunit/test.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'lib') diff --git a/lib/kunit/test.c b/lib/kunit/test.c index 1d1475578515..b8514dbb337c 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -712,6 +712,9 @@ int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_ { unsigned int i; + if (num_suites == 0) + return 0; + if (!kunit_enabled() && num_suites > 0) { pr_info("kunit: disabled\n"); return 0; -- cgit v1.2.3 From 0d5044b4e7749099b12da5f2c8618f04bb4fa82f Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 6 May 2024 10:50:40 -0700 Subject: lib: Allow for the DIM library to be modular Allow the Dynamic Interrupt Moderation (DIM) library to be built as a module. This is particularly useful in an Android GKI (Google Kernel Image) configuration where everything is built as a module, including Ethernet controller drivers. Having to build DIMLIB into the kernel image with potentially no user is wasteful. Signed-off-by: Florian Fainelli Reviewed-by: Alexander Lobakin Link: https://lore.kernel.org/r/20240506175040.410446-1-florian.fainelli@broadcom.com Signed-off-by: Jakub Kicinski --- lib/Kconfig | 2 +- lib/dim/Makefile | 4 ++-- lib/dim/dim.c | 3 +++ 3 files changed, 6 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/lib/Kconfig b/lib/Kconfig index 4557bb8a5256..d33a268bc256 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -628,7 +628,7 @@ config SIGNATURE Implementation is done using GnuPG MPI library config DIMLIB - bool + tristate help Dynamic Interrupt Moderation library. Implements an algorithm for dynamically changing CQ moderation values diff --git a/lib/dim/Makefile b/lib/dim/Makefile index 1d6858a108cb..c4cc4026c451 100644 --- a/lib/dim/Makefile +++ b/lib/dim/Makefile @@ -2,6 +2,6 @@ # DIM Dynamic Interrupt Moderation library # -obj-$(CONFIG_DIMLIB) += dim.o +obj-$(CONFIG_DIMLIB) += dimlib.o -dim-y := dim.o net_dim.o rdma_dim.o +dimlib-objs := dim.o net_dim.o rdma_dim.o diff --git a/lib/dim/dim.c b/lib/dim/dim.c index e89aaf07bde5..83b65ac74d73 100644 --- a/lib/dim/dim.c +++ b/lib/dim/dim.c @@ -82,3 +82,6 @@ bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end, return true; } EXPORT_SYMBOL(dim_calc_stats); + +MODULE_DESCRIPTION("Dynamic Interrupt Moderation (DIM) library"); +MODULE_LICENSE("Dual BSD/GPL"); -- cgit v1.2.3 From 22bcc915ae910bc823d8351542f6d9e7623fff24 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 23 Apr 2024 22:23:10 +0300 Subject: kfifo: don't use "proxy" headers Update header inclusions to follow IWYU (Include What You Use) principle. Link: https://lkml.kernel.org/r/20240423192529.3249134-4-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Alain Volmat Cc: AngeloGioacchino Del Regno Cc: Chen-Yu Tsai Cc: Hans Verkuil Cc: Jernej Skrabec Cc: Matthias Brugger Cc: Mauro Carvalho Chehab Cc: Patrice Chotard Cc: Rob Herring Cc: Samuel Holland Cc: Sean Wang Cc: Sean Young Cc: Stefani Seibold Signed-off-by: Andrew Morton --- include/linux/kfifo.h | 9 +++++++-- lib/kfifo.c | 8 ++++---- samples/kfifo/dma-example.c | 3 ++- 3 files changed, 13 insertions(+), 7 deletions(-) (limited to 'lib') diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index 0b35a41440ff..6b28d642f332 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -36,10 +36,15 @@ * to lock the reader. */ -#include +#include #include #include -#include +#include + +#include +#include + +struct scatterlist; struct __kfifo { unsigned int in; diff --git a/lib/kfifo.c b/lib/kfifo.c index 12f5a347aa13..15acdee4a8f3 100644 --- a/lib/kfifo.c +++ b/lib/kfifo.c @@ -5,13 +5,13 @@ * Copyright (C) 2009/2010 Stefani Seibold */ -#include -#include -#include #include +#include +#include #include +#include +#include #include -#include /* * internal helper to calculate the unused elements in a fifo diff --git a/samples/kfifo/dma-example.c b/samples/kfifo/dma-example.c index 0cf27483cb36..74fe915b7ffe 100644 --- a/samples/kfifo/dma-example.c +++ b/samples/kfifo/dma-example.c @@ -6,8 +6,9 @@ */ #include -#include #include +#include +#include /* * This module shows how to handle fifo dma operations. -- cgit v1.2.3 From 4c5b7294dedbdfae46f77262c0744879bb9b7221 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 3 May 2024 14:43:54 -0400 Subject: closures: closure_sync_timeout() Add a new variant of closure_sync_timeout() that takes a timeout. Note that when this returns -ETIME the closure will still be waiting on something, i.e. it's not safe to return if you've got a stack allocated closure. Signed-off-by: Kent Overstreet --- include/linux/closure.h | 12 ++++++++++++ lib/closure.c | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+) (limited to 'lib') diff --git a/include/linux/closure.h b/include/linux/closure.h index c554c6a08768..99155df162d0 100644 --- a/include/linux/closure.h +++ b/include/linux/closure.h @@ -194,6 +194,18 @@ static inline void closure_sync(struct closure *cl) __closure_sync(cl); } +int __closure_sync_timeout(struct closure *cl, unsigned long timeout); + +static inline int closure_sync_timeout(struct closure *cl, unsigned long timeout) +{ +#ifdef CONFIG_DEBUG_CLOSURES + BUG_ON(closure_nr_remaining(cl) != 1 && !cl->closure_get_happened); +#endif + return cl->closure_get_happened + ? __closure_sync_timeout(cl, timeout) + : 0; +} + #ifdef CONFIG_DEBUG_CLOSURES void closure_debug_create(struct closure *cl); diff --git a/lib/closure.c b/lib/closure.c index c16540552d61..07409e9e35a5 100644 --- a/lib/closure.c +++ b/lib/closure.c @@ -139,6 +139,43 @@ void __sched __closure_sync(struct closure *cl) } EXPORT_SYMBOL(__closure_sync); +int __sched __closure_sync_timeout(struct closure *cl, unsigned long timeout) +{ + struct closure_syncer s = { .task = current }; + int ret = 0; + + cl->s = &s; + continue_at(cl, closure_sync_fn, NULL); + + while (1) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (s.done) + break; + if (!timeout) { + /* + * Carefully undo the continue_at() - but only if it + * hasn't completed, i.e. the final closure_put() hasn't + * happened yet: + */ + unsigned old, new, v = atomic_read(&cl->remaining); + do { + old = v; + if (!old || (old & CLOSURE_RUNNING)) + goto success; + + new = old + CLOSURE_REMAINING_INITIALIZER; + } while ((v = atomic_cmpxchg(&cl->remaining, old, new)) != old); + ret = -ETIME; + } + + timeout = schedule_timeout(timeout); + } +success: + __set_current_state(TASK_RUNNING); + return ret; +} +EXPORT_SYMBOL(__closure_sync_timeout); + #ifdef CONFIG_DEBUG_CLOSURES static LIST_HEAD(closure_list); -- cgit v1.2.3 From 0a2c6664e56f0dff7535c3d3d9a6174279e18acc Mon Sep 17 00:00:00 2001 From: Kuan-Wei Chiu Date: Thu, 2 May 2024 17:24:42 +0800 Subject: lib/test_bitops: Add benchmark test for fns() Introduce a benchmark test for the fns(). It measures the total time taken by fns() to process 10,000 test data generated using get_random_bytes() for each n in the range [0, BITS_PER_LONG). example: test_bitops: fns: 7637268 ns CC: Andrew Morton CC: Rasmus Villemoes CC: David Laight Signed-off-by: Kuan-Wei Chiu Suggested-by: Yury Norov Signed-off-by: Yury Norov --- lib/test_bitops.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'lib') diff --git a/lib/test_bitops.c b/lib/test_bitops.c index 3b7bcbee84db..55669624bb28 100644 --- a/lib/test_bitops.c +++ b/lib/test_bitops.c @@ -5,9 +5,11 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include +#include /* a tiny module only meant to test * @@ -50,6 +52,30 @@ static unsigned long order_comb_long[][2] = { }; #endif +static int __init test_fns(void) +{ + static volatile __always_used unsigned long tmp __initdata; + unsigned long *buf __free(kfree) = NULL; + unsigned int i, n; + ktime_t time; + + buf = kmalloc_array(10000, sizeof(unsigned long), GFP_KERNEL); + if (!buf) + return -ENOMEM; + + get_random_bytes(buf, 10000 * sizeof(unsigned long)); + time = ktime_get(); + + for (n = 0; n < BITS_PER_LONG; n++) + for (i = 0; i < 10000; i++) + tmp = fns(buf[i], n); + + time = ktime_get() - time; + pr_err("fns: %18llu ns\n", time); + + return 0; +} + static int __init test_bitops_startup(void) { int i, bit_set; @@ -94,6 +120,8 @@ static int __init test_bitops_startup(void) if (bit_set != BITOPS_LAST) pr_err("ERROR: FOUND SET BIT %d\n", bit_set); + test_fns(); + pr_info("Completed bitops test\n"); return 0; -- cgit v1.2.3 From 77db1920a88103e8ef9ee58130df7c970aea3d17 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 2 May 2024 09:56:33 -0700 Subject: lib: make test_bitops compilable into the kernel image The test now is limited to be compiled as a module. There's no technical reason for it. Now that the test bears some performance benchmarks, it would be reasonable to run it at kernel load time, before userspace starts, to reduce possible jitter. Reviewed-by: Kuan-Wei Chiu Signed-off-by: Yury Norov --- lib/Kconfig.debug | 1 - 1 file changed, 1 deletion(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c63a5fbf1f1c..fc8fe1ea5b49 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2436,7 +2436,6 @@ config TEST_LKM config TEST_BITOPS tristate "Test module for compilation of bitops operations" - depends on m help This builds the "test_bitops" module that is much like the TEST_LKM module except that it does a basic exercise of the -- cgit v1.2.3 From 0b2811ba11b04353033237359c9d042eb0cdc1c1 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 2 May 2024 10:12:56 -0700 Subject: bitmap: relax find_nth_bit() limitation on return value The function claims to return the bitmap size, if Nth bit doesn't exist. This rule is violated in inline case because the fns() that is used there doesn't know anything about size of the bitmap. So, relax this requirement to '>= size', and make the outline implementation a bit cheaper. All in-tree kernel users of find_nth_bit() are safe against that. Reported-by: Rasmus Villemoes Closes: https://lore.kernel.org/all/Zi50cAgR8nZvgLa3@yury-ThinkPad/T/#m6da806a0525e74dcc91f35e5f20766ed4e853e8a Signed-off-by: Yury Norov --- include/linux/find.h | 2 +- lib/find_bit.c | 2 +- lib/test_bitmap.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/include/linux/find.h b/include/linux/find.h index c69598e383c1..02751e43d448 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -220,7 +220,7 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) * idx = find_first_bit(addr, size); * * Returns the bit number of the N'th set bit. - * If no such, returns @size. + * If no such, returns >= @size. */ static inline unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) diff --git a/lib/find_bit.c b/lib/find_bit.c index 32f99e9a670e..0bddfc3ff248 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -87,7 +87,7 @@ out: \ if (sz % BITS_PER_LONG) \ tmp = (FETCH) & BITMAP_LAST_WORD_MASK(sz); \ found: \ - sz = min(idx * BITS_PER_LONG + fns(tmp, nr), sz); \ + sz = idx * BITS_PER_LONG + fns(tmp, nr); \ out: \ sz; \ }) diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 6b2b33579f56..088838f829c9 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -244,7 +244,7 @@ static void __init test_find_nth_bit(void) expect_eq_uint(60, find_nth_bit(bmap, 64 * 3, 5)); expect_eq_uint(80, find_nth_bit(bmap, 64 * 3, 6)); expect_eq_uint(123, find_nth_bit(bmap, 64 * 3, 7)); - expect_eq_uint(64 * 3, find_nth_bit(bmap, 64 * 3, 8)); + expect_eq_uint(0, !!(find_nth_bit(bmap, 64 * 3, 8) < 64 * 3)); expect_eq_uint(10, find_nth_bit(bmap, 64 * 3 - 1, 0)); expect_eq_uint(20, find_nth_bit(bmap, 64 * 3 - 1, 1)); @@ -254,7 +254,7 @@ static void __init test_find_nth_bit(void) expect_eq_uint(60, find_nth_bit(bmap, 64 * 3 - 1, 5)); expect_eq_uint(80, find_nth_bit(bmap, 64 * 3 - 1, 6)); expect_eq_uint(123, find_nth_bit(bmap, 64 * 3 - 1, 7)); - expect_eq_uint(64 * 3 - 1, find_nth_bit(bmap, 64 * 3 - 1, 8)); + expect_eq_uint(0, !!(find_nth_bit(bmap, 64 * 3 - 1, 8) < 64 * 3 - 1)); for_each_set_bit(bit, exp1, EXP1_IN_BITS) { b = find_nth_bit(exp1, EXP1_IN_BITS, cnt++); -- cgit v1.2.3 From f135440447af5156de91272ee52ccedcf0796e94 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 29 Apr 2024 16:27:58 -0400 Subject: crypto: lib - implement library version of AES in CFB mode Implement AES in CFB mode using the existing, mostly constant-time generic AES library implementation. This will be used by the TPM code to encrypt communications with TPM hardware, which is often a discrete component connected using sniffable wires or traces. While a CFB template does exist, using a skcipher is a major pain for non-performance critical synchronous crypto where the algorithm is known at compile time and the data is in contiguous buffers with valid kernel virtual addresses. Tested-by: James Bottomley Reviewed-by: James Bottomley Reviewed-by: Jarkko Sakkinen Link: https://lore.kernel.org/all/20230216201410.15010-1-James.Bottomley@HansenPartnership.com/ Signed-off-by: Ard Biesheuvel Signed-off-by: James Bottomley Tested-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- include/crypto/aes.h | 5 + lib/crypto/Kconfig | 5 + lib/crypto/Makefile | 3 + lib/crypto/aescfb.c | 257 +++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 270 insertions(+) create mode 100644 lib/crypto/aescfb.c (limited to 'lib') diff --git a/include/crypto/aes.h b/include/crypto/aes.h index 2090729701ab..9339da7c20a8 100644 --- a/include/crypto/aes.h +++ b/include/crypto/aes.h @@ -87,4 +87,9 @@ void aes_decrypt(const struct crypto_aes_ctx *ctx, u8 *out, const u8 *in); extern const u8 crypto_aes_sbox[]; extern const u8 crypto_aes_inv_sbox[]; +void aescfb_encrypt(const struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src, + int len, const u8 iv[AES_BLOCK_SIZE]); +void aescfb_decrypt(const struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src, + int len, const u8 iv[AES_BLOCK_SIZE]); + #endif diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig index 45436bfc6dff..b01253cac70a 100644 --- a/lib/crypto/Kconfig +++ b/lib/crypto/Kconfig @@ -8,6 +8,11 @@ config CRYPTO_LIB_UTILS config CRYPTO_LIB_AES tristate +config CRYPTO_LIB_AESCFB + tristate + select CRYPTO_LIB_AES + select CRYPTO_LIB_UTILS + config CRYPTO_LIB_AESGCM tristate select CRYPTO_LIB_AES diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile index 8d1446c2be71..969baab8c805 100644 --- a/lib/crypto/Makefile +++ b/lib/crypto/Makefile @@ -10,6 +10,9 @@ obj-$(CONFIG_CRYPTO_LIB_CHACHA_GENERIC) += libchacha.o obj-$(CONFIG_CRYPTO_LIB_AES) += libaes.o libaes-y := aes.o +obj-$(CONFIG_CRYPTO_LIB_AESCFB) += libaescfb.o +libaescfb-y := aescfb.o + obj-$(CONFIG_CRYPTO_LIB_AESGCM) += libaesgcm.o libaesgcm-y := aesgcm.o diff --git a/lib/crypto/aescfb.c b/lib/crypto/aescfb.c new file mode 100644 index 000000000000..749dc1258a44 --- /dev/null +++ b/lib/crypto/aescfb.c @@ -0,0 +1,257 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Minimal library implementation of AES in CFB mode + * + * Copyright 2023 Google LLC + */ + +#include + +#include +#include + +#include + +static void aescfb_encrypt_block(const struct crypto_aes_ctx *ctx, void *dst, + const void *src) +{ + unsigned long flags; + + /* + * In AES-CFB, the AES encryption operates on known 'plaintext' (the IV + * and ciphertext), making it susceptible to timing attacks on the + * encryption key. The AES library already mitigates this risk to some + * extent by pulling the entire S-box into the caches before doing any + * substitutions, but this strategy is more effective when running with + * interrupts disabled. + */ + local_irq_save(flags); + aes_encrypt(ctx, dst, src); + local_irq_restore(flags); +} + +/** + * aescfb_encrypt - Perform AES-CFB encryption on a block of data + * + * @ctx: The AES-CFB key schedule + * @dst: Pointer to the ciphertext output buffer + * @src: Pointer the plaintext (may equal @dst for encryption in place) + * @len: The size in bytes of the plaintext and ciphertext. + * @iv: The initialization vector (IV) to use for this block of data + */ +void aescfb_encrypt(const struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src, + int len, const u8 iv[AES_BLOCK_SIZE]) +{ + u8 ks[AES_BLOCK_SIZE]; + const u8 *v = iv; + + while (len > 0) { + aescfb_encrypt_block(ctx, ks, v); + crypto_xor_cpy(dst, src, ks, min(len, AES_BLOCK_SIZE)); + v = dst; + + dst += AES_BLOCK_SIZE; + src += AES_BLOCK_SIZE; + len -= AES_BLOCK_SIZE; + } + + memzero_explicit(ks, sizeof(ks)); +} +EXPORT_SYMBOL(aescfb_encrypt); + +/** + * aescfb_decrypt - Perform AES-CFB decryption on a block of data + * + * @ctx: The AES-CFB key schedule + * @dst: Pointer to the plaintext output buffer + * @src: Pointer the ciphertext (may equal @dst for decryption in place) + * @len: The size in bytes of the plaintext and ciphertext. + * @iv: The initialization vector (IV) to use for this block of data + */ +void aescfb_decrypt(const struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src, + int len, const u8 iv[AES_BLOCK_SIZE]) +{ + u8 ks[2][AES_BLOCK_SIZE]; + + aescfb_encrypt_block(ctx, ks[0], iv); + + for (int i = 0; len > 0; i ^= 1) { + if (len > AES_BLOCK_SIZE) + /* + * Generate the keystream for the next block before + * performing the XOR, as that may update in place and + * overwrite the ciphertext. + */ + aescfb_encrypt_block(ctx, ks[!i], src); + + crypto_xor_cpy(dst, src, ks[i], min(len, AES_BLOCK_SIZE)); + + dst += AES_BLOCK_SIZE; + src += AES_BLOCK_SIZE; + len -= AES_BLOCK_SIZE; + } + + memzero_explicit(ks, sizeof(ks)); +} +EXPORT_SYMBOL(aescfb_decrypt); + +MODULE_DESCRIPTION("Generic AES-CFB library"); +MODULE_AUTHOR("Ard Biesheuvel "); +MODULE_LICENSE("GPL"); + +#ifndef CONFIG_CRYPTO_MANAGER_DISABLE_TESTS + +/* + * Test code below. Vectors taken from crypto/testmgr.h + */ + +static struct { + u8 ptext[64]; + u8 ctext[64]; + + u8 key[AES_MAX_KEY_SIZE]; + u8 iv[AES_BLOCK_SIZE]; + + int klen; + int len; +} const aescfb_tv[] __initconst = { + { /* From NIST SP800-38A */ + .key = "\x2b\x7e\x15\x16\x28\xae\xd2\xa6" + "\xab\xf7\x15\x88\x09\xcf\x4f\x3c", + .klen = 16, + .iv = "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f", + .ptext = "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96" + "\xe9\x3d\x7e\x11\x73\x93\x17\x2a" + "\xae\x2d\x8a\x57\x1e\x03\xac\x9c" + "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51" + "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11" + "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef" + "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17" + "\xad\x2b\x41\x7b\xe6\x6c\x37\x10", + .ctext = "\x3b\x3f\xd9\x2e\xb7\x2d\xad\x20" + "\x33\x34\x49\xf8\xe8\x3c\xfb\x4a" + "\xc8\xa6\x45\x37\xa0\xb3\xa9\x3f" + "\xcd\xe3\xcd\xad\x9f\x1c\xe5\x8b" + "\x26\x75\x1f\x67\xa3\xcb\xb1\x40" + "\xb1\x80\x8c\xf1\x87\xa4\xf4\xdf" + "\xc0\x4b\x05\x35\x7c\x5d\x1c\x0e" + "\xea\xc4\xc6\x6f\x9f\xf7\xf2\xe6", + .len = 64, + }, { + .key = "\x8e\x73\xb0\xf7\xda\x0e\x64\x52" + "\xc8\x10\xf3\x2b\x80\x90\x79\xe5" + "\x62\xf8\xea\xd2\x52\x2c\x6b\x7b", + .klen = 24, + .iv = "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f", + .ptext = "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96" + "\xe9\x3d\x7e\x11\x73\x93\x17\x2a" + "\xae\x2d\x8a\x57\x1e\x03\xac\x9c" + "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51" + "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11" + "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef" + "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17" + "\xad\x2b\x41\x7b\xe6\x6c\x37\x10", + .ctext = "\xcd\xc8\x0d\x6f\xdd\xf1\x8c\xab" + "\x34\xc2\x59\x09\xc9\x9a\x41\x74" + "\x67\xce\x7f\x7f\x81\x17\x36\x21" + "\x96\x1a\x2b\x70\x17\x1d\x3d\x7a" + "\x2e\x1e\x8a\x1d\xd5\x9b\x88\xb1" + "\xc8\xe6\x0f\xed\x1e\xfa\xc4\xc9" + "\xc0\x5f\x9f\x9c\xa9\x83\x4f\xa0" + "\x42\xae\x8f\xba\x58\x4b\x09\xff", + .len = 64, + }, { + .key = "\x60\x3d\xeb\x10\x15\xca\x71\xbe" + "\x2b\x73\xae\xf0\x85\x7d\x77\x81" + "\x1f\x35\x2c\x07\x3b\x61\x08\xd7" + "\x2d\x98\x10\xa3\x09\x14\xdf\xf4", + .klen = 32, + .iv = "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f", + .ptext = "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96" + "\xe9\x3d\x7e\x11\x73\x93\x17\x2a" + "\xae\x2d\x8a\x57\x1e\x03\xac\x9c" + "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51" + "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11" + "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef" + "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17" + "\xad\x2b\x41\x7b\xe6\x6c\x37\x10", + .ctext = "\xdc\x7e\x84\xbf\xda\x79\x16\x4b" + "\x7e\xcd\x84\x86\x98\x5d\x38\x60" + "\x39\xff\xed\x14\x3b\x28\xb1\xc8" + "\x32\x11\x3c\x63\x31\xe5\x40\x7b" + "\xdf\x10\x13\x24\x15\xe5\x4b\x92" + "\xa1\x3e\xd0\xa8\x26\x7a\xe2\xf9" + "\x75\xa3\x85\x74\x1a\xb9\xce\xf8" + "\x20\x31\x62\x3d\x55\xb1\xe4\x71", + .len = 64, + }, { /* > 16 bytes, not a multiple of 16 bytes */ + .key = "\x2b\x7e\x15\x16\x28\xae\xd2\xa6" + "\xab\xf7\x15\x88\x09\xcf\x4f\x3c", + .klen = 16, + .iv = "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f", + .ptext = "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96" + "\xe9\x3d\x7e\x11\x73\x93\x17\x2a" + "\xae", + .ctext = "\x3b\x3f\xd9\x2e\xb7\x2d\xad\x20" + "\x33\x34\x49\xf8\xe8\x3c\xfb\x4a" + "\xc8", + .len = 17, + }, { /* < 16 bytes */ + .key = "\x2b\x7e\x15\x16\x28\xae\xd2\xa6" + "\xab\xf7\x15\x88\x09\xcf\x4f\x3c", + .klen = 16, + .iv = "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f", + .ptext = "\x6b\xc1\xbe\xe2\x2e\x40\x9f", + .ctext = "\x3b\x3f\xd9\x2e\xb7\x2d\xad", + .len = 7, + }, +}; + +static int __init libaescfb_init(void) +{ + for (int i = 0; i < ARRAY_SIZE(aescfb_tv); i++) { + struct crypto_aes_ctx ctx; + u8 buf[64]; + + if (aes_expandkey(&ctx, aescfb_tv[i].key, aescfb_tv[i].klen)) { + pr_err("aes_expandkey() failed on vector %d\n", i); + return -ENODEV; + } + + aescfb_encrypt(&ctx, buf, aescfb_tv[i].ptext, aescfb_tv[i].len, + aescfb_tv[i].iv); + if (memcmp(buf, aescfb_tv[i].ctext, aescfb_tv[i].len)) { + pr_err("aescfb_encrypt() #1 failed on vector %d\n", i); + return -ENODEV; + } + + /* decrypt in place */ + aescfb_decrypt(&ctx, buf, buf, aescfb_tv[i].len, aescfb_tv[i].iv); + if (memcmp(buf, aescfb_tv[i].ptext, aescfb_tv[i].len)) { + pr_err("aescfb_decrypt() failed on vector %d\n", i); + return -ENODEV; + } + + /* encrypt in place */ + aescfb_encrypt(&ctx, buf, buf, aescfb_tv[i].len, aescfb_tv[i].iv); + if (memcmp(buf, aescfb_tv[i].ctext, aescfb_tv[i].len)) { + pr_err("aescfb_encrypt() #2 failed on vector %d\n", i); + + return -ENODEV; + } + + } + return 0; +} +module_init(libaescfb_init); + +static void __exit libaescfb_exit(void) +{ +} +module_exit(libaescfb_exit); +#endif -- cgit v1.2.3 From b1992c3772e69a6fd0e3fc81cd4d2820c8b6eca0 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 27 Apr 2024 23:55:02 +0900 Subject: kbuild: use $(src) instead of $(srctree)/$(src) for source directory Kbuild conventionally uses $(obj)/ for generated files, and $(src)/ for checked-in source files. It is merely a convention without any functional difference. In fact, $(obj) and $(src) are exactly the same, as defined in scripts/Makefile.build: src := $(obj) When the kernel is built in a separate output directory, $(src) does not accurately reflect the source directory location. While Kbuild resolves this discrepancy by specifying VPATH=$(srctree) to search for source files, it does not cover all cases. For example, when adding a header search path for local headers, -I$(srctree)/$(src) is typically passed to the compiler. This introduces inconsistency between upstream and downstream Makefiles because $(src) is used instead of $(srctree)/$(src) for the latter. To address this inconsistency, this commit changes the semantics of $(src) so that it always points to the directory in the source tree. Going forward, the variables used in Makefiles will have the following meanings: $(obj) - directory in the object tree $(src) - directory in the source tree (changed by this commit) $(objtree) - the top of the kernel object tree $(srctree) - the top of the kernel source tree Consequently, $(srctree)/$(src) in upstream Makefiles need to be replaced with $(src). Signed-off-by: Masahiro Yamada Reviewed-by: Nicolas Schier --- Documentation/Makefile | 8 ++++---- Documentation/devicetree/bindings/Makefile | 6 +++--- Documentation/kbuild/makefiles.rst | 12 ++++++------ Makefile | 7 +++++++ arch/arc/boot/dts/Makefile | 3 +-- arch/arm/Kbuild | 2 +- arch/arm/boot/Makefile | 3 +-- arch/arm/mach-s3c/Makefile | 2 +- arch/arm/plat-orion/Makefile | 2 +- arch/arm/tools/Makefile | 2 +- arch/arm64/kernel/vdso/Makefile | 2 +- arch/arm64/kvm/Makefile | 4 ++-- arch/arm64/kvm/hyp/Makefile | 2 +- arch/csky/boot/dts/Makefile | 4 +--- arch/csky/kernel/vdso/Makefile | 2 +- arch/loongarch/kvm/Makefile | 2 +- arch/loongarch/vdso/Makefile | 2 +- arch/mips/kernel/syscalls/Makefile | 2 +- arch/mips/vdso/Makefile | 4 ++-- arch/nios2/boot/dts/Makefile | 3 +-- arch/parisc/kernel/vdso32/Makefile | 2 +- arch/parisc/kernel/vdso64/Makefile | 2 +- arch/powerpc/boot/Makefile | 6 +++--- arch/powerpc/boot/dts/Makefile | 3 +-- arch/powerpc/boot/dts/fsl/Makefile | 3 +-- arch/powerpc/kernel/vdso/Makefile | 4 ++-- arch/riscv/kernel/compat_vdso/Makefile | 2 +- arch/riscv/kernel/vdso/Makefile | 2 +- arch/riscv/kvm/Makefile | 2 +- arch/s390/kernel/syscalls/Makefile | 4 ++-- arch/s390/kernel/vdso32/Makefile | 2 +- arch/s390/kernel/vdso64/Makefile | 2 +- arch/sparc/vdso/Makefile | 2 +- arch/um/kernel/Makefile | 2 +- arch/x86/boot/Makefile | 2 +- arch/x86/entry/vdso/Makefile | 2 +- arch/x86/kernel/Makefile | 2 +- arch/x86/kernel/cpu/Makefile | 2 +- arch/x86/mm/Makefile | 2 +- arch/x86/um/vdso/Makefile | 2 +- arch/xtensa/boot/dts/Makefile | 3 +-- certs/Makefile | 4 ++-- drivers/Makefile | 5 ----- drivers/crypto/intel/qat/qat_420xx/Makefile | 2 +- drivers/crypto/intel/qat/qat_4xxx/Makefile | 2 +- drivers/crypto/intel/qat/qat_c3xxx/Makefile | 2 +- drivers/crypto/intel/qat/qat_c3xxxvf/Makefile | 2 +- drivers/crypto/intel/qat/qat_c62x/Makefile | 2 +- drivers/crypto/intel/qat/qat_c62xvf/Makefile | 2 +- drivers/crypto/intel/qat/qat_dh895xcc/Makefile | 2 +- drivers/crypto/intel/qat/qat_dh895xccvf/Makefile | 2 +- drivers/gpu/drm/amd/amdgpu/Makefile | 2 +- drivers/gpu/drm/arm/display/komeda/Makefile | 4 ++-- drivers/gpu/drm/i915/Makefile | 4 ++-- drivers/gpu/drm/imagination/Makefile | 2 +- drivers/gpu/drm/msm/Makefile | 8 ++++---- drivers/gpu/drm/nouveau/Kbuild | 10 ++++------ drivers/gpu/drm/xe/Makefile | 10 +++++----- drivers/hid/amd-sfh-hid/Makefile | 2 +- drivers/hid/intel-ish-hid/Makefile | 2 +- drivers/md/dm-vdo/Makefile | 2 +- drivers/net/ethernet/aquantia/atlantic/Makefile | 2 +- drivers/net/ethernet/chelsio/libcxgb/Makefile | 2 +- drivers/net/ethernet/fungible/funeth/Makefile | 2 +- drivers/net/ethernet/hisilicon/hns3/Makefile | 2 +- drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile | 4 ++-- .../net/wireless/broadcom/brcm80211/brcmfmac/bca/Makefile | 6 +++--- .../net/wireless/broadcom/brcm80211/brcmfmac/cyw/Makefile | 6 +++--- .../net/wireless/broadcom/brcm80211/brcmfmac/wcc/Makefile | 6 +++--- drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile | 6 +++--- drivers/net/wireless/broadcom/brcm80211/brcmutil/Makefile | 2 +- drivers/net/wireless/intel/iwlwifi/dvm/Makefile | 2 +- drivers/net/wireless/intel/iwlwifi/mei/Makefile | 2 +- drivers/net/wireless/intel/iwlwifi/mvm/Makefile | 2 +- drivers/net/wireless/intel/iwlwifi/tests/Makefile | 2 +- drivers/net/wireless/realtek/rtl818x/rtl8180/Makefile | 2 +- drivers/net/wireless/realtek/rtl818x/rtl8187/Makefile | 2 +- drivers/scsi/aic7xxx/Makefile | 12 ++++++------ drivers/staging/rtl8723bs/Makefile | 2 +- fs/iomap/Makefile | 2 +- fs/unicode/Makefile | 14 +++++++------- fs/xfs/Makefile | 4 ++-- init/Makefile | 2 +- lib/Makefile | 6 +++--- lib/raid6/Makefile | 2 +- net/wireless/Makefile | 2 +- rust/Makefile | 6 +++--- samples/bpf/Makefile | 2 +- samples/hid/Makefile | 2 +- scripts/Kbuild.include | 3 +-- scripts/Makefile.asm-generic | 6 +++--- scripts/Makefile.build | 2 +- scripts/Makefile.clean | 2 +- scripts/Makefile.lib | 10 +++++----- scripts/Makefile.modpost | 2 +- scripts/dtc/Makefile | 6 +++--- scripts/gdb/linux/Makefile | 2 +- scripts/genksyms/Makefile | 4 ++-- scripts/kconfig/Makefile | 8 ++++---- security/tomoyo/Makefile | 2 +- usr/Makefile | 2 +- usr/include/Makefile | 2 +- 102 files changed, 173 insertions(+), 182 deletions(-) (limited to 'lib') diff --git a/Documentation/Makefile b/Documentation/Makefile index b68f8c816897..66d15fff2089 100644 --- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -76,22 +76,22 @@ loop_cmd = $(echo-cmd) $(cmd_$(1)) || exit; # * dest folder relative to $(BUILDDIR) and # * cache folder relative to $(BUILDDIR)/.doctrees # $4 dest subfolder e.g. "man" for man pages at userspace-api/media/man -# $5 reST source folder relative to $(srctree)/$(src), +# $5 reST source folder relative to $(src), # e.g. "userspace-api/media" for the linux-tv book-set at ./Documentation/userspace-api/media quiet_cmd_sphinx = SPHINX $@ --> file://$(abspath $(BUILDDIR)/$3/$4) cmd_sphinx = $(MAKE) BUILDDIR=$(abspath $(BUILDDIR)) $(build)=Documentation/userspace-api/media $2 && \ PYTHONDONTWRITEBYTECODE=1 \ - BUILDDIR=$(abspath $(BUILDDIR)) SPHINX_CONF=$(abspath $(srctree)/$(src)/$5/$(SPHINX_CONF)) \ + BUILDDIR=$(abspath $(BUILDDIR)) SPHINX_CONF=$(abspath $(src)/$5/$(SPHINX_CONF)) \ $(PYTHON3) $(srctree)/scripts/jobserver-exec \ $(CONFIG_SHELL) $(srctree)/Documentation/sphinx/parallel-wrapper.sh \ $(SPHINXBUILD) \ -b $2 \ - -c $(abspath $(srctree)/$(src)) \ + -c $(abspath $(src)) \ -d $(abspath $(BUILDDIR)/.doctrees/$3) \ -D version=$(KERNELVERSION) -D release=$(KERNELRELEASE) \ $(ALLSPHINXOPTS) \ - $(abspath $(srctree)/$(src)/$5) \ + $(abspath $(src)/$5) \ $(abspath $(BUILDDIR)/$3/$4) && \ if [ "x$(DOCS_CSS)" != "x" ]; then \ cp $(if $(patsubst /%,,$(DOCS_CSS)),$(abspath $(srctree)/$(DOCS_CSS)),$(DOCS_CSS)) $(BUILDDIR)/$3/_static/; \ diff --git a/Documentation/devicetree/bindings/Makefile b/Documentation/devicetree/bindings/Makefile index 8cdda477987f..bf7d64632e20 100644 --- a/Documentation/devicetree/bindings/Makefile +++ b/Documentation/devicetree/bindings/Makefile @@ -25,7 +25,7 @@ quiet_cmd_extract_ex = DTEX $@ $(obj)/%.example.dts: $(src)/%.yaml check_dtschema_version FORCE $(call if_changed,extract_ex) -find_all_cmd = find $(srctree)/$(src) \( -name '*.yaml' ! \ +find_all_cmd = find $(src) \( -name '*.yaml' ! \ -name 'processed-schema*' \) find_cmd = $(find_all_cmd) | \ @@ -37,12 +37,12 @@ CHK_DT_EXAMPLES := $(patsubst $(srctree)/%.yaml,%.example.dtb, $(shell $(find_cm quiet_cmd_yamllint = LINT $(src) cmd_yamllint = ($(find_cmd) | \ xargs -n200 -P$$(nproc) \ - $(DT_SCHEMA_LINT) -f parsable -c $(srctree)/$(src)/.yamllint >&2) \ + $(DT_SCHEMA_LINT) -f parsable -c $(src)/.yamllint >&2) \ && touch $@ || true quiet_cmd_chk_bindings = CHKDT $(src) cmd_chk_bindings = ($(find_cmd) | \ - xargs -n200 -P$$(nproc) $(DT_DOC_CHECKER) -u $(srctree)/$(src)) \ + xargs -n200 -P$$(nproc) $(DT_DOC_CHECKER) -u $(src)) \ && touch $@ || true quiet_cmd_mk_schema = SCHEMA $@ diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst index ad118b7a1806..991ce6081e35 100644 --- a/Documentation/kbuild/makefiles.rst +++ b/Documentation/kbuild/makefiles.rst @@ -346,7 +346,7 @@ ccflags-y, asflags-y and ldflags-y Example:: #arch/cris/boot/compressed/Makefile - ldflags-y += -T $(srctree)/$(src)/decompress_$(arch-y).lds + ldflags-y += -T $(src)/decompress_$(arch-y).lds subdir-ccflags-y, subdir-asflags-y The two flags listed above are similar to ccflags-y and asflags-y. @@ -426,14 +426,14 @@ path to prerequisite files and target files. Two variables are used when defining custom rules: $(src) - $(src) is a relative path which points to the directory - where the Makefile is located. Always use $(src) when + $(src) is the directory where the Makefile is located. Always use $(src) when referring to files located in the src tree. $(obj) - $(obj) is a relative path which points to the directory - where the target is saved. Always use $(obj) when - referring to generated files. + $(obj) is the directory where the target is saved. Always use $(obj) when + referring to generated files. Use $(obj) for pattern rules that need to work + for both generated files and real sources (VPATH will help to find the + prerequisites not only in the object tree but also in the source tree). Example:: diff --git a/Makefile b/Makefile index 12e1a792b8de..c97c8d96061c 100644 --- a/Makefile +++ b/Makefile @@ -263,7 +263,14 @@ srctree := $(abs_srctree) endif objtree := . + +VPATH := + +ifeq ($(KBUILD_EXTMOD),) +ifdef building_out_of_srctree VPATH := $(srctree) +endif +endif export building_out_of_srctree srctree objtree VPATH diff --git a/arch/arc/boot/dts/Makefile b/arch/arc/boot/dts/Makefile index 4237aa5de3a3..48704dfdf75c 100644 --- a/arch/arc/boot/dts/Makefile +++ b/arch/arc/boot/dts/Makefile @@ -10,8 +10,7 @@ obj-y += $(builtindtb-y).dtb.o dtb-y := $(builtindtb-y).dtb # for CONFIG_OF_ALL_DTBS test -dtstree := $(srctree)/$(src) -dtb- := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts)) +dtb- := $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts)) # board-specific dtc flags DTC_FLAGS_hsdk += --pad 20 diff --git a/arch/arm/Kbuild b/arch/arm/Kbuild index b506622e7e23..69de6b6243c7 100644 --- a/arch/arm/Kbuild +++ b/arch/arm/Kbuild @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_FPE_NWFPE) += nwfpe/ # Put arch/arm/fastfpe/ to use this. -obj-$(CONFIG_FPE_FASTFPE) += $(patsubst $(srctree)/$(src)/%,%,$(wildcard $(srctree)/$(src)/fastfpe/)) +obj-$(CONFIG_FPE_FASTFPE) += $(patsubst $(src)/%,%,$(wildcard $(src)/fastfpe/)) obj-$(CONFIG_VFP) += vfp/ obj-$(CONFIG_XEN) += xen/ obj-$(CONFIG_VDSO) += vdso/ diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile index abd6a2889fd0..ba9b9a802469 100644 --- a/arch/arm/boot/Makefile +++ b/arch/arm/boot/Makefile @@ -25,8 +25,7 @@ targets := Image zImage xipImage bootpImage uImage ifeq ($(CONFIG_XIP_KERNEL),y) -cmd_deflate_xip_data = $(CONFIG_SHELL) -c \ - '$(srctree)/$(src)/deflate_xip_data.sh $< $@' +cmd_deflate_xip_data = $(CONFIG_SHELL) -c '$(src)/deflate_xip_data.sh $< $@' ifeq ($(CONFIG_XIP_DEFLATED_DATA),y) quiet_cmd_mkxip = XIPZ $@ diff --git a/arch/arm/mach-s3c/Makefile b/arch/arm/mach-s3c/Makefile index 713827bef831..988c49672715 100644 --- a/arch/arm/mach-s3c/Makefile +++ b/arch/arm/mach-s3c/Makefile @@ -2,7 +2,7 @@ # # Copyright 2009 Simtec Electronics -include $(srctree)/$(src)/Makefile.s3c64xx +include $(src)/Makefile.s3c64xx # Objects we always build independent of SoC choice diff --git a/arch/arm/plat-orion/Makefile b/arch/arm/plat-orion/Makefile index 830b0be038c6..e8c7580df8ca 100644 --- a/arch/arm/plat-orion/Makefile +++ b/arch/arm/plat-orion/Makefile @@ -2,7 +2,7 @@ # # Makefile for the linux kernel. # -ccflags-y := -I$(srctree)/$(src)/include +ccflags-y := -I$(src)/include orion-gpio-$(CONFIG_GPIOLIB) += gpio.o obj-$(CONFIG_PLAT_ORION_LEGACY) += irq.o pcie.o time.o common.o mpp.o diff --git a/arch/arm/tools/Makefile b/arch/arm/tools/Makefile index 81f13bdf32f2..28b6da8ac5f6 100644 --- a/arch/arm/tools/Makefile +++ b/arch/arm/tools/Makefile @@ -9,7 +9,7 @@ gen := arch/$(ARCH)/include/generated kapi := $(gen)/asm uapi := $(gen)/uapi/asm syshdr := $(srctree)/scripts/syscallhdr.sh -sysnr := $(srctree)/$(src)/syscallnr.sh +sysnr := $(src)/syscallnr.sh systbl := $(srctree)/scripts/syscalltbl.sh syscall := $(src)/syscall.tbl diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 8818287f1095..53e86d3bc159 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -68,7 +68,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # Generate VDSO offsets using helper script -gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh +gen-vdsosym := $(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index c0c050e53157..ab474d444cef 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -3,7 +3,7 @@ # Makefile for Kernel-based Virtual Machine module # -ccflags-y += -I $(srctree)/$(src) +ccflags-y += -I $(src) include $(srctree)/virt/kvm/Makefile.kvm @@ -30,7 +30,7 @@ define rule_gen_hyp_constants $(call filechk,offsets,__HYP_CONSTANTS_H__) endef -CFLAGS_hyp-constants.o = -I $(srctree)/$(src)/hyp/include +CFLAGS_hyp-constants.o = -I $(src)/hyp/include $(obj)/hyp-constants.s: $(src)/hyp/hyp-constants.c FORCE $(call if_changed_dep,cc_s_c) diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile index a38dea6186c9..d61e44642f98 100644 --- a/arch/arm64/kvm/hyp/Makefile +++ b/arch/arm64/kvm/hyp/Makefile @@ -3,7 +3,7 @@ # Makefile for Kernel-based Virtual Machine module, HYP part # -incdir := $(srctree)/$(src)/include +incdir := $(src)/include subdir-asflags-y := -I$(incdir) subdir-ccflags-y := -I$(incdir) diff --git a/arch/csky/boot/dts/Makefile b/arch/csky/boot/dts/Makefile index 5f1f55e911ad..aabffc1912e8 100644 --- a/arch/csky/boot/dts/Makefile +++ b/arch/csky/boot/dts/Makefile @@ -1,4 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -dtstree := $(srctree)/$(src) - -dtb-y := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts)) +dtb-y := $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts)) diff --git a/arch/csky/kernel/vdso/Makefile b/arch/csky/kernel/vdso/Makefile index 24a01c22293e..e79a725f5075 100644 --- a/arch/csky/kernel/vdso/Makefile +++ b/arch/csky/kernel/vdso/Makefile @@ -57,4 +57,4 @@ quiet_cmd_vdsold = VDSOLD $@ # Extracts symbol offsets from the VDSO, converting them into an assembly file # that contains the same symbols at the same offsets. quiet_cmd_so2s = SO2S $@ - cmd_so2s = $(NM) -D $< | $(srctree)/$(src)/so2s.sh > $@ + cmd_so2s = $(NM) -D $< | $(src)/so2s.sh > $@ diff --git a/arch/loongarch/kvm/Makefile b/arch/loongarch/kvm/Makefile index 244467d7792a..b2f4cbe01ae8 100644 --- a/arch/loongarch/kvm/Makefile +++ b/arch/loongarch/kvm/Makefile @@ -3,7 +3,7 @@ # Makefile for LoongArch KVM support # -ccflags-y += -I $(srctree)/$(src) +ccflags-y += -I $(src) include $(srctree)/virt/kvm/Makefile.kvm diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile index 75c6726382c3..cdfc4c793e2c 100644 --- a/arch/loongarch/vdso/Makefile +++ b/arch/loongarch/vdso/Makefile @@ -52,7 +52,7 @@ quiet_cmd_vdsoas_o_S = AS $@ cmd_vdsoas_o_S = $(CC) $(a_flags) -c -o $@ $< # Generate VDSO offsets using helper script -gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh +gen-vdsosym := $(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ diff --git a/arch/mips/kernel/syscalls/Makefile b/arch/mips/kernel/syscalls/Makefile index e6b21de65cca..56f6f093bb88 100644 --- a/arch/mips/kernel/syscalls/Makefile +++ b/arch/mips/kernel/syscalls/Makefile @@ -5,7 +5,7 @@ uapi := arch/$(SRCARCH)/include/generated/uapi/asm $(shell mkdir -p $(uapi) $(kapi)) syshdr := $(srctree)/scripts/syscallhdr.sh -sysnr := $(srctree)/$(src)/syscallnr.sh +sysnr := $(src)/syscallnr.sh systbl := $(srctree)/scripts/syscalltbl.sh quiet_cmd_syshdr = SYSHDR $@ diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index eb56581f6d73..40b839e91806 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -43,8 +43,8 @@ CFLAGS_vgettimeofday.o = -include $(c-gettimeofday-y) # config-n32-o32-env.c prepares the environment to build a 32bit vDSO # library on a 64bit kernel. # Note: Needs to be included before than the generic library. -CFLAGS_vgettimeofday-o32.o = -include $(srctree)/$(src)/config-n32-o32-env.c -include $(c-gettimeofday-y) -CFLAGS_vgettimeofday-n32.o = -include $(srctree)/$(src)/config-n32-o32-env.c -include $(c-gettimeofday-y) +CFLAGS_vgettimeofday-o32.o = -include $(src)/config-n32-o32-env.c -include $(c-gettimeofday-y) +CFLAGS_vgettimeofday-n32.o = -include $(src)/config-n32-o32-env.c -include $(c-gettimeofday-y) endif CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) diff --git a/arch/nios2/boot/dts/Makefile b/arch/nios2/boot/dts/Makefile index e9e31bb40df8..1a2e8996bec7 100644 --- a/arch/nios2/boot/dts/Makefile +++ b/arch/nios2/boot/dts/Makefile @@ -2,5 +2,4 @@ obj-y := $(patsubst %.dts,%.dtb.o,$(CONFIG_NIOS2_DTB_SOURCE)) -dtstree := $(srctree)/$(src) -dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts)) +dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts)) diff --git a/arch/parisc/kernel/vdso32/Makefile b/arch/parisc/kernel/vdso32/Makefile index 60dc708a0f80..1350d50c6306 100644 --- a/arch/parisc/kernel/vdso32/Makefile +++ b/arch/parisc/kernel/vdso32/Makefile @@ -40,7 +40,7 @@ quiet_cmd_vdso32as = VDSO32A $@ cmd_vdso32as = $(CROSS32CC) $(a_flags) -c -o $@ $< # Generate VDSO offsets using helper script -gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh +gen-vdsosym := $(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ diff --git a/arch/parisc/kernel/vdso64/Makefile b/arch/parisc/kernel/vdso64/Makefile index 0982f3099ae2..0b1c1cc4c2c7 100644 --- a/arch/parisc/kernel/vdso64/Makefile +++ b/arch/parisc/kernel/vdso64/Makefile @@ -40,7 +40,7 @@ quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< # Generate VDSO offsets using helper script -gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh +gen-vdsosym := $(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 968aee2025b8..a0b3b5cc14cd 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -218,7 +218,7 @@ $(addprefix $(obj)/,$(libfdt) $(libfdtheader)): $(obj)/%: $(srctree)/scripts/dtc $(obj)/empty.c: $(Q)touch $@ -$(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds : $(obj)/%: $(srctree)/$(src)/%.S +$(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds : $(obj)/%: $(src)/%.S $(Q)cp $< $@ clean-files := $(zlib-) $(zlibheader-) $(zliblinuxheader-) \ @@ -252,9 +252,9 @@ targets += $(patsubst $(obj)/%,%,$(obj-boot) wrapper.a) zImage.lds extra-y := $(obj)/wrapper.a $(obj-plat) $(obj)/empty.o \ $(obj)/zImage.lds $(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds -dtstree := $(srctree)/$(src)/dts +dtstree := $(src)/dts -wrapper :=$(srctree)/$(src)/wrapper +wrapper := $(src)/wrapper wrapperbits := $(extra-y) $(addprefix $(obj)/,addnote hack-coff mktree) \ $(wrapper) FORCE diff --git a/arch/powerpc/boot/dts/Makefile b/arch/powerpc/boot/dts/Makefile index fb335d05aae8..0cd0d8558b47 100644 --- a/arch/powerpc/boot/dts/Makefile +++ b/arch/powerpc/boot/dts/Makefile @@ -2,5 +2,4 @@ subdir-y += fsl -dtstree := $(srctree)/$(src) -dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts)) +dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts)) diff --git a/arch/powerpc/boot/dts/fsl/Makefile b/arch/powerpc/boot/dts/fsl/Makefile index 3bae982641e9..d3ecdf14bc42 100644 --- a/arch/powerpc/boot/dts/fsl/Makefile +++ b/arch/powerpc/boot/dts/fsl/Makefile @@ -1,4 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -dtstree := $(srctree)/$(src) -dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts)) +dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts)) diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile index a14eab366993..7d66b6e07993 100644 --- a/arch/powerpc/kernel/vdso/Makefile +++ b/arch/powerpc/kernel/vdso/Makefile @@ -90,10 +90,10 @@ $(obj)/vgettimeofday-64.o: %-64.o: %.c FORCE $(call if_changed_dep,cc_o_c) # Generate VDSO offsets using helper script -gen-vdso32sym := $(srctree)/$(src)/gen_vdso32_offsets.sh +gen-vdso32sym := $(src)/gen_vdso32_offsets.sh quiet_cmd_vdso32sym = VDSO32SYM $@ cmd_vdso32sym = $(NM) $< | $(gen-vdso32sym) | LC_ALL=C sort > $@ -gen-vdso64sym := $(srctree)/$(src)/gen_vdso64_offsets.sh +gen-vdso64sym := $(src)/gen_vdso64_offsets.sh quiet_cmd_vdso64sym = VDSO64SYM $@ cmd_vdso64sym = $(NM) $< | $(gen-vdso64sym) | LC_ALL=C sort > $@ diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile index 3df4cb788c1f..362208dfa7ee 100644 --- a/arch/riscv/kernel/compat_vdso/Makefile +++ b/arch/riscv/kernel/compat_vdso/Makefile @@ -58,7 +58,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # Generate VDSO offsets using helper script -gen-compat_vdsosym := $(srctree)/$(src)/gen_compat_vdso_offsets.sh +gen-compat_vdsosym := $(src)/gen_compat_vdso_offsets.sh quiet_cmd_compat_vdsosym = VDSOSYM $@ cmd_compat_vdsosym = $(NM) $< | $(gen-compat_vdsosym) | LC_ALL=C sort > $@ diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 272c431ac5b9..25f0ee629971 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -60,7 +60,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # Generate VDSO offsets using helper script -gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh +gen-vdsosym := $(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index c9646521f113..c2cacfbc06a0 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -3,7 +3,7 @@ # Makefile for RISC-V KVM support # -ccflags-y += -I $(srctree)/$(src) +ccflags-y += -I $(src) include $(srctree)/virt/kvm/Makefile.kvm diff --git a/arch/s390/kernel/syscalls/Makefile b/arch/s390/kernel/syscalls/Makefile index fb85e797946d..1bb78b9468e8 100644 --- a/arch/s390/kernel/syscalls/Makefile +++ b/arch/s390/kernel/syscalls/Makefile @@ -4,8 +4,8 @@ gen := arch/$(ARCH)/include/generated kapi := $(gen)/asm uapi := $(gen)/uapi/asm -syscall := $(srctree)/$(src)/syscall.tbl -systbl := $(srctree)/$(src)/syscalltbl +syscall := $(src)/syscall.tbl +systbl := $(src)/syscalltbl gen-y := $(kapi)/syscall_table.h kapi-hdrs-y := $(kapi)/unistd_nr.h diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index 70e9949c2612..c263b91adfb1 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -62,7 +62,7 @@ quiet_cmd_vdso32cc = VDSO32C $@ cmd_vdso32cc = $(CC) $(c_flags) -c -o $@ $< # Generate VDSO offsets using helper script -gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh +gen-vdsosym := $(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index 2b3617b6d162..9566bed7d5b2 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -72,7 +72,7 @@ quiet_cmd_vdso64cc = VDSO64C $@ cmd_vdso64cc = $(CC) $(c_flags) -c -o $@ $< # Generate VDSO offsets using helper script -gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh +gen-vdsosym := $(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile index e8aef2c8ae99..0fe134abbcf1 100644 --- a/arch/sparc/vdso/Makefile +++ b/arch/sparc/vdso/Makefile @@ -103,7 +103,7 @@ quiet_cmd_vdso = VDSO $@ cmd_vdso = $(LD) -nostdlib -o $@ \ $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ -T $(filter %.lds,$^) $(filter %.o,$^) && \ - sh $(srctree)/$(src)/checkundef.sh '$(OBJDUMP)' '$@' + sh $(src)/checkundef.sh '$(OBJDUMP)' '$@' VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 -Bsymbolic GCOV_PROFILE := n diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile index 811188be954c..f8567b933ffa 100644 --- a/arch/um/kernel/Makefile +++ b/arch/um/kernel/Makefile @@ -47,7 +47,7 @@ $(obj)/config.c: $(src)/config.c.in $(obj)/config.tmp FORCE $(call if_changed,quote2) quiet_cmd_mkcapflags = MKCAP $@ - cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/../../x86/kernel/cpu/mkcapflags.sh $@ $^ + cmd_mkcapflags = $(CONFIG_SHELL) $(src)/../../x86/kernel/cpu/mkcapflags.sh $@ $^ cpufeature = $(src)/../../x86/include/asm/cpufeatures.h vmxfeature = $(src)/../../x86/include/asm/vmxfeatures.h diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 3cece19b7473..29cda98c65f8 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -129,7 +129,7 @@ targets += mtools.conf # genimage.sh requires bash, but it also has a bunch of other # external dependencies. quiet_cmd_genimage = GENIMAGE $3 -cmd_genimage = $(BASH) $(srctree)/$(src)/genimage.sh $2 $3 $(obj)/bzImage \ + cmd_genimage = $(BASH) $(src)/genimage.sh $2 $3 $(obj)/bzImage \ $(obj)/mtools.conf '$(FDARGS)' $(FDINITRD) PHONY += bzdisk fdimage fdimage144 fdimage288 hdimage isoimage diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 3d64bcc403cf..c003452dba8c 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -176,7 +176,7 @@ quiet_cmd_vdso = VDSO $@ cmd_vdso = $(LD) -o $@ \ $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ -T $(filter %.lds,$^) $(filter %.o,$^) && \ - sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' + sh $(src)/checkundef.sh '$(NM)' '$@' VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 \ $(call ld-option, --eh-frame-hdr) -Bsymbolic -z noexecstack diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 74077694da7d..8a9fc9ec69d3 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -40,7 +40,7 @@ KMSAN_SANITIZE_sev.o := n KCOV_INSTRUMENT_head$(BITS).o := n KCOV_INSTRUMENT_sev.o := n -CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace +CFLAGS_irq.o := -I $(src)/../include/asm/trace obj-y += head_$(BITS).o obj-y += head$(BITS).o diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index eb4dbcdf41f1..a02bba0ed6b9 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -60,7 +60,7 @@ obj-$(CONFIG_ACRN_GUEST) += acrn.o obj-$(CONFIG_DEBUG_FS) += debugfs.o quiet_cmd_mkcapflags = MKCAP $@ - cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $@ $^ + cmd_mkcapflags = $(CONFIG_SHELL) $(src)/mkcapflags.sh $@ $^ cpufeature = $(src)/../../include/asm/cpufeatures.h vmxfeature = $(src)/../../include/asm/vmxfeatures.h diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 428048e73bd2..8d3a00e5c528 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -34,7 +34,7 @@ obj-y += pat/ CFLAGS_physaddr.o := -fno-stack-protector CFLAGS_mem_encrypt_identity.o := -fno-stack-protector -CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace +CFLAGS_fault.o := -I $(src)/../include/asm/trace obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index b86d634730b2..2303fa59971c 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -63,7 +63,7 @@ quiet_cmd_vdso = VDSO $@ cmd_vdso = $(CC) -nostdlib -o $@ \ $(CC_FLAGS_LTO) $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ - sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' + sh $(src)/checkundef.sh '$(NM)' '$@' VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv -z noexecstack GCOV_PROFILE := n diff --git a/arch/xtensa/boot/dts/Makefile b/arch/xtensa/boot/dts/Makefile index 720628c0d8b9..d6408c16d74e 100644 --- a/arch/xtensa/boot/dts/Makefile +++ b/arch/xtensa/boot/dts/Makefile @@ -10,5 +10,4 @@ obj-$(CONFIG_OF) += $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_SOURCE)) # for CONFIG_OF_ALL_DTBS test -dtstree := $(srctree)/$(src) -dtb- := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts)) +dtb- := $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts)) diff --git a/certs/Makefile b/certs/Makefile index 799ad7b9e68a..1094e3860c2a 100644 --- a/certs/Makefile +++ b/certs/Makefile @@ -13,7 +13,7 @@ CFLAGS_blacklist_hashes.o := -I $(obj) quiet_cmd_check_and_copy_blacklist_hash_list = GEN $@ cmd_check_and_copy_blacklist_hash_list = \ $(if $(CONFIG_SYSTEM_BLACKLIST_HASH_LIST), \ - $(AWK) -f $(srctree)/$(src)/check-blacklist-hashes.awk $(CONFIG_SYSTEM_BLACKLIST_HASH_LIST) >&2; \ + $(AWK) -f $(src)/check-blacklist-hashes.awk $(CONFIG_SYSTEM_BLACKLIST_HASH_LIST) >&2; \ { cat $(CONFIG_SYSTEM_BLACKLIST_HASH_LIST); echo $(comma) NULL; } > $@, \ echo NULL > $@) @@ -55,7 +55,7 @@ $(obj)/signing_key.pem: $(obj)/x509.genkey FORCE targets += signing_key.pem quiet_cmd_copy_x509_config = COPY $@ - cmd_copy_x509_config = cat $(srctree)/$(src)/default_x509.genkey > $@ + cmd_copy_x509_config = cat $(src)/default_x509.genkey > $@ # You can provide your own config file. If not present, copy the default one. $(obj)/x509.genkey: diff --git a/drivers/Makefile b/drivers/Makefile index 3bf5cab4b451..fe9ceb0d2288 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -6,11 +6,6 @@ # Rewritten to use lists instead of if-statements. # -# Some driver Makefiles miss $(srctree)/ for include directive. -ifdef building_out_of_srctree -MAKEFLAGS += --include-dir=$(srctree) -endif - obj-y += cache/ obj-y += irqchip/ obj-y += bus/ diff --git a/drivers/crypto/intel/qat/qat_420xx/Makefile b/drivers/crypto/intel/qat/qat_420xx/Makefile index a90fbe00b3c8..45728659fbc4 100644 --- a/drivers/crypto/intel/qat/qat_420xx/Makefile +++ b/drivers/crypto/intel/qat/qat_420xx/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -ccflags-y := -I $(srctree)/$(src)/../qat_common +ccflags-y := -I $(src)/../qat_common obj-$(CONFIG_CRYPTO_DEV_QAT_420XX) += qat_420xx.o qat_420xx-objs := adf_drv.o adf_420xx_hw_data.o diff --git a/drivers/crypto/intel/qat/qat_4xxx/Makefile b/drivers/crypto/intel/qat/qat_4xxx/Makefile index ff9c8b5897ea..9ba202079a22 100644 --- a/drivers/crypto/intel/qat/qat_4xxx/Makefile +++ b/drivers/crypto/intel/qat/qat_4xxx/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: (BSD-3-Clause OR GPL-2.0-only) -ccflags-y := -I $(srctree)/$(src)/../qat_common +ccflags-y := -I $(src)/../qat_common obj-$(CONFIG_CRYPTO_DEV_QAT_4XXX) += qat_4xxx.o qat_4xxx-objs := adf_drv.o adf_4xxx_hw_data.o diff --git a/drivers/crypto/intel/qat/qat_c3xxx/Makefile b/drivers/crypto/intel/qat/qat_c3xxx/Makefile index 92ef416ccc78..7a06ad519bfc 100644 --- a/drivers/crypto/intel/qat/qat_c3xxx/Makefile +++ b/drivers/crypto/intel/qat/qat_c3xxx/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -ccflags-y := -I $(srctree)/$(src)/../qat_common +ccflags-y := -I $(src)/../qat_common obj-$(CONFIG_CRYPTO_DEV_QAT_C3XXX) += qat_c3xxx.o qat_c3xxx-objs := adf_drv.o adf_c3xxx_hw_data.o diff --git a/drivers/crypto/intel/qat/qat_c3xxxvf/Makefile b/drivers/crypto/intel/qat/qat_c3xxxvf/Makefile index b6d76825a92c..7ef633058c4f 100644 --- a/drivers/crypto/intel/qat/qat_c3xxxvf/Makefile +++ b/drivers/crypto/intel/qat/qat_c3xxxvf/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -ccflags-y := -I $(srctree)/$(src)/../qat_common +ccflags-y := -I $(src)/../qat_common obj-$(CONFIG_CRYPTO_DEV_QAT_C3XXXVF) += qat_c3xxxvf.o qat_c3xxxvf-objs := adf_drv.o adf_c3xxxvf_hw_data.o diff --git a/drivers/crypto/intel/qat/qat_c62x/Makefile b/drivers/crypto/intel/qat/qat_c62x/Makefile index d581f7c87d6c..cc9255b3b198 100644 --- a/drivers/crypto/intel/qat/qat_c62x/Makefile +++ b/drivers/crypto/intel/qat/qat_c62x/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -ccflags-y := -I $(srctree)/$(src)/../qat_common +ccflags-y := -I $(src)/../qat_common obj-$(CONFIG_CRYPTO_DEV_QAT_C62X) += qat_c62x.o qat_c62x-objs := adf_drv.o adf_c62x_hw_data.o diff --git a/drivers/crypto/intel/qat/qat_c62xvf/Makefile b/drivers/crypto/intel/qat/qat_c62xvf/Makefile index 446c3d638605..256786662d60 100644 --- a/drivers/crypto/intel/qat/qat_c62xvf/Makefile +++ b/drivers/crypto/intel/qat/qat_c62xvf/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -ccflags-y := -I $(srctree)/$(src)/../qat_common +ccflags-y := -I $(src)/../qat_common obj-$(CONFIG_CRYPTO_DEV_QAT_C62XVF) += qat_c62xvf.o qat_c62xvf-objs := adf_drv.o adf_c62xvf_hw_data.o diff --git a/drivers/crypto/intel/qat/qat_dh895xcc/Makefile b/drivers/crypto/intel/qat/qat_dh895xcc/Makefile index 38d6f8e1624a..cfd3bd757715 100644 --- a/drivers/crypto/intel/qat/qat_dh895xcc/Makefile +++ b/drivers/crypto/intel/qat/qat_dh895xcc/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -ccflags-y := -I $(srctree)/$(src)/../qat_common +ccflags-y := -I $(src)/../qat_common obj-$(CONFIG_CRYPTO_DEV_QAT_DH895xCC) += qat_dh895xcc.o qat_dh895xcc-objs := adf_drv.o adf_dh895xcc_hw_data.o diff --git a/drivers/crypto/intel/qat/qat_dh895xccvf/Makefile b/drivers/crypto/intel/qat/qat_dh895xccvf/Makefile index 0153c85ce743..64b54e92b2b4 100644 --- a/drivers/crypto/intel/qat/qat_dh895xccvf/Makefile +++ b/drivers/crypto/intel/qat/qat_dh895xccvf/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -ccflags-y := -I $(srctree)/$(src)/../qat_common +ccflags-y := -I $(src)/../qat_common obj-$(CONFIG_CRYPTO_DEV_QAT_DH895xCCVF) += qat_dh895xccvf.o qat_dh895xccvf-objs := adf_drv.o adf_dh895xccvf_hw_data.o diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile index 4536c8ad0e11..e568e89283c0 100644 --- a/drivers/gpu/drm/amd/amdgpu/Makefile +++ b/drivers/gpu/drm/amd/amdgpu/Makefile @@ -23,7 +23,7 @@ # Makefile for the drm device driver. This driver provides support for the # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher. -FULL_AMD_PATH=$(srctree)/$(src)/.. +FULL_AMD_PATH=$(src)/.. DISPLAY_FOLDER_NAME=display FULL_AMD_DISPLAY_PATH = $(FULL_AMD_PATH)/$(DISPLAY_FOLDER_NAME) diff --git a/drivers/gpu/drm/arm/display/komeda/Makefile b/drivers/gpu/drm/arm/display/komeda/Makefile index 1931a7fa1a14..cf5287fcbbc2 100644 --- a/drivers/gpu/drm/arm/display/komeda/Makefile +++ b/drivers/gpu/drm/arm/display/komeda/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 ccflags-y := \ - -I $(srctree)/$(src)/../include \ - -I $(srctree)/$(src) + -I $(src)/../include \ + -I $(src) komeda-y := \ komeda_drv.o \ diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index fba73c38e235..2220448ed07f 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -41,7 +41,7 @@ CFLAGS_display/intel_fbdev.o = -Wno-override-init # drivers. Define I915 when building i915. subdir-ccflags-y += -DI915 -subdir-ccflags-y += -I$(srctree)/$(src) +subdir-ccflags-y += -I$(src) # Please keep these build lists sorted! @@ -434,7 +434,7 @@ no-header-test := \ always-$(CONFIG_DRM_I915_WERROR) += \ $(patsubst %.h,%.hdrtest, $(filter-out $(no-header-test), \ - $(shell cd $(srctree)/$(src) && find * -name '*.h'))) + $(shell cd $(src) && find * -name '*.h'))) quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@) cmd_hdrtest = $(CC) $(filter-out $(CFLAGS_GCOV), $(c_flags)) -S -o /dev/null -x c /dev/null -include $<; \ diff --git a/drivers/gpu/drm/imagination/Makefile b/drivers/gpu/drm/imagination/Makefile index ec6db8e9b403..9bc6a3884c22 100644 --- a/drivers/gpu/drm/imagination/Makefile +++ b/drivers/gpu/drm/imagination/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only OR MIT # Copyright (c) 2023 Imagination Technologies Ltd. -subdir-ccflags-y := -I$(srctree)/$(src) +subdir-ccflags-y := -I$(src) powervr-y := \ pvr_ccb.o \ diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index b21ae2880c71..b8cc007fc1b9 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 -ccflags-y := -I $(srctree)/$(src) -ccflags-y += -I $(srctree)/$(src)/disp/dpu1 -ccflags-$(CONFIG_DRM_MSM_DSI) += -I $(srctree)/$(src)/dsi -ccflags-$(CONFIG_DRM_MSM_DP) += -I $(srctree)/$(src)/dp +ccflags-y := -I $(src) +ccflags-y += -I $(src)/disp/dpu1 +ccflags-$(CONFIG_DRM_MSM_DSI) += -I $(src)/dsi +ccflags-$(CONFIG_DRM_MSM_DP) += -I $(src)/dp msm-y := \ adreno/adreno_device.o \ diff --git a/drivers/gpu/drm/nouveau/Kbuild b/drivers/gpu/drm/nouveau/Kbuild index cf6b3a80c0c8..c32c01827c1d 100644 --- a/drivers/gpu/drm/nouveau/Kbuild +++ b/drivers/gpu/drm/nouveau/Kbuild @@ -1,10 +1,8 @@ -NOUVEAU_PATH ?= $(srctree) - # SPDX-License-Identifier: MIT -ccflags-y += -I $(NOUVEAU_PATH)/$(src)/include -ccflags-y += -I $(NOUVEAU_PATH)/$(src)/include/nvkm -ccflags-y += -I $(NOUVEAU_PATH)/$(src)/nvkm -ccflags-y += -I $(NOUVEAU_PATH)/$(src) +ccflags-y += -I $(src)/include +ccflags-y += -I $(src)/include/nvkm +ccflags-y += -I $(src)/nvkm +ccflags-y += -I $(src) # NVKM - HW resource manager #- code also used by various userspace tools/tests diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index c29a850859ad..8162a522222b 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -32,7 +32,7 @@ endif # Enable -Werror in CI and development subdir-ccflags-$(CONFIG_DRM_XE_WERROR) += -Werror -subdir-ccflags-y += -I$(obj) -I$(srctree)/$(src) +subdir-ccflags-y += -I$(obj) -I$(src) # generated sources hostprogs := xe_gen_wa_oob @@ -43,7 +43,7 @@ quiet_cmd_wa_oob = GEN $(notdir $(generated_oob)) cmd_wa_oob = mkdir -p $(@D); $^ $(generated_oob) $(obj)/generated/%_wa_oob.c $(obj)/generated/%_wa_oob.h: $(obj)/xe_gen_wa_oob \ - $(srctree)/$(src)/xe_wa_oob.rules + $(src)/xe_wa_oob.rules $(call cmd,wa_oob) uses_generated_oob := \ @@ -166,8 +166,8 @@ endif # i915 Display compat #defines and #includes subdir-ccflags-$(CONFIG_DRM_XE_DISPLAY) += \ - -I$(srctree)/$(src)/display/ext \ - -I$(srctree)/$(src)/compat-i915-headers \ + -I$(src)/display/ext \ + -I$(src)/compat-i915-headers \ -I$(srctree)/drivers/gpu/drm/i915/display/ \ -Ddrm_i915_gem_object=xe_bo \ -Ddrm_i915_private=xe_device @@ -310,7 +310,7 @@ ifneq ($(CONFIG_DRM_XE_DISPLAY),y) endif always-$(CONFIG_DRM_XE_WERROR) += \ - $(patsubst %.h,%.hdrtest, $(shell cd $(srctree)/$(src) && find * -name '*.h' $(hdrtest_find_args))) + $(patsubst %.h,%.hdrtest, $(shell cd $(src) && find * -name '*.h' $(hdrtest_find_args))) quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@) cmd_hdrtest = $(CC) -DHDRTEST $(filter-out $(CFLAGS_GCOV), $(c_flags)) -S -o /dev/null -x c /dev/null -include $<; touch $@ diff --git a/drivers/hid/amd-sfh-hid/Makefile b/drivers/hid/amd-sfh-hid/Makefile index 0222170ab7ad..106514b54d16 100644 --- a/drivers/hid/amd-sfh-hid/Makefile +++ b/drivers/hid/amd-sfh-hid/Makefile @@ -13,4 +13,4 @@ amd_sfh-objs += sfh1_1/amd_sfh_init.o amd_sfh-objs += sfh1_1/amd_sfh_interface.o amd_sfh-objs += sfh1_1/amd_sfh_desc.o -ccflags-y += -I $(srctree)/$(src)/ +ccflags-y += -I $(src)/ diff --git a/drivers/hid/intel-ish-hid/Makefile b/drivers/hid/intel-ish-hid/Makefile index f0a82b1c7cb9..db4974c43431 100644 --- a/drivers/hid/intel-ish-hid/Makefile +++ b/drivers/hid/intel-ish-hid/Makefile @@ -23,4 +23,4 @@ intel-ishtp-hid-objs += ishtp-hid-client.o obj-$(CONFIG_INTEL_ISH_FIRMWARE_DOWNLOADER) += intel-ishtp-loader.o intel-ishtp-loader-objs += ishtp-fw-loader.o -ccflags-y += -I $(srctree)/$(src)/ishtp +ccflags-y += -I $(src)/ishtp diff --git a/drivers/md/dm-vdo/Makefile b/drivers/md/dm-vdo/Makefile index 33e09abc6acd..9476957bfbf4 100644 --- a/drivers/md/dm-vdo/Makefile +++ b/drivers/md/dm-vdo/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only -ccflags-y := -I$(srctree)/$(src) -I$(srctree)/$(src)/indexer +ccflags-y := -I$(src) -I$(src)/indexer obj-$(CONFIG_DM_VDO) += dm-vdo.o diff --git a/drivers/net/ethernet/aquantia/atlantic/Makefile b/drivers/net/ethernet/aquantia/atlantic/Makefile index 8ebcc68e807f..f6a96931c89a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/Makefile +++ b/drivers/net/ethernet/aquantia/atlantic/Makefile @@ -8,7 +8,7 @@ obj-$(CONFIG_AQTION) += atlantic.o -ccflags-y += -I$(srctree)/$(src) +ccflags-y += -I$(src) atlantic-objs := aq_main.o \ aq_nic.o \ diff --git a/drivers/net/ethernet/chelsio/libcxgb/Makefile b/drivers/net/ethernet/chelsio/libcxgb/Makefile index aa79264e72ba..fbedc31674b3 100644 --- a/drivers/net/ethernet/chelsio/libcxgb/Makefile +++ b/drivers/net/ethernet/chelsio/libcxgb/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -ccflags-y := -I $(srctree)/$(src)/../cxgb4 +ccflags-y := -I $(src)/../cxgb4 obj-$(CONFIG_CHELSIO_LIB) += libcxgb.o diff --git a/drivers/net/ethernet/fungible/funeth/Makefile b/drivers/net/ethernet/fungible/funeth/Makefile index 646d69595b4f..d51e4c2b4a1a 100644 --- a/drivers/net/ethernet/fungible/funeth/Makefile +++ b/drivers/net/ethernet/fungible/funeth/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) -ccflags-y += -I$(srctree)/$(src)/../funcore -I$(srctree)/$(src) +ccflags-y += -I$(src)/../funcore -I$(src) obj-$(CONFIG_FUN_ETH) += funeth.o diff --git a/drivers/net/ethernet/hisilicon/hns3/Makefile b/drivers/net/ethernet/hisilicon/hns3/Makefile index e214bfaece1f..8e9293e57bfd 100644 --- a/drivers/net/ethernet/hisilicon/hns3/Makefile +++ b/drivers/net/ethernet/hisilicon/hns3/Makefile @@ -3,7 +3,7 @@ # Makefile for the HISILICON network device drivers. # -ccflags-y += -I$(srctree)/$(src) +ccflags-y += -I$(src) ccflags-y += -I$(srctree)/drivers/net/ethernet/hisilicon/hns3/hns3pf ccflags-y += -I$(srctree)/drivers/net/ethernet/hisilicon/hns3/hns3vf ccflags-y += -I$(srctree)/drivers/net/ethernet/hisilicon/hns3/hns3_common diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile index dc6d27a36faa..e5ca0f511822 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile @@ -6,8 +6,8 @@ # ccflags-y += \ - -I $(srctree)/$(src) \ - -I $(srctree)/$(src)/../include + -I $(src) \ + -I $(src)/../include obj-$(CONFIG_BRCMFMAC) += brcmfmac.o brcmfmac-objs += \ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/Makefile b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/Makefile index 46098705e236..5e37c638f966 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/Makefile +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/Makefile @@ -3,9 +3,9 @@ # Copyright (c) 2022 Broadcom Corporation ccflags-y += \ - -I $(srctree)/$(src) \ - -I $(srctree)/$(src)/.. \ - -I $(srctree)/$(src)/../../include + -I $(src) \ + -I $(src)/.. \ + -I $(src)/../../include obj-m += brcmfmac-bca.o brcmfmac-bca-objs += \ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/Makefile b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/Makefile index 5e1fddaff79e..33e86724ba14 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/Makefile +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/Makefile @@ -3,9 +3,9 @@ # Copyright (c) 2022 Broadcom Corporation ccflags-y += \ - -I $(srctree)/$(src) \ - -I $(srctree)/$(src)/.. \ - -I $(srctree)/$(src)/../../include + -I $(src) \ + -I $(src)/.. \ + -I $(src)/../../include obj-m += brcmfmac-cyw.o brcmfmac-cyw-objs += \ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/Makefile b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/Makefile index 7f455a19a2b1..3db4cce44f42 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/Makefile +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/Makefile @@ -3,9 +3,9 @@ # Copyright (c) 2022 Broadcom Corporation ccflags-y += \ - -I $(srctree)/$(src) \ - -I $(srctree)/$(src)/.. \ - -I $(srctree)/$(src)/../../include + -I $(src) \ + -I $(src)/.. \ + -I $(src)/../../include obj-m += brcmfmac-wcc.o brcmfmac-wcc-objs += \ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile index 090757730ba6..ffdd17eabe1d 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile @@ -16,9 +16,9 @@ # CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ccflags-y := \ - -I $(srctree)/$(src) \ - -I $(srctree)/$(src)/phy \ - -I $(srctree)/$(src)/../include + -I $(src) \ + -I $(src)/phy \ + -I $(src)/../include brcmsmac-y := \ mac80211_if.o \ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmutil/Makefile b/drivers/net/wireless/broadcom/brcm80211/brcmutil/Makefile index 7a82d615ba2a..f9b40cab766c 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmutil/Makefile +++ b/drivers/net/wireless/broadcom/brcm80211/brcmutil/Makefile @@ -4,7 +4,7 @@ # # Copyright (c) 2011 Broadcom Corporation # -ccflags-y := -I $(srctree)/$(src)/../include +ccflags-y := -I $(src)/../include obj-$(CONFIG_BRCMUTIL) += brcmutil.o brcmutil-objs = utils.o d11.o diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/Makefile b/drivers/net/wireless/intel/iwlwifi/dvm/Makefile index 0486b17d7c41..6109d64006db 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/Makefile +++ b/drivers/net/wireless/intel/iwlwifi/dvm/Makefile @@ -11,4 +11,4 @@ iwldvm-objs += rxon.o devices.o iwldvm-$(CONFIG_IWLWIFI_LEDS) += led.o iwldvm-$(CONFIG_IWLWIFI_DEBUGFS) += debugfs.o -ccflags-y += -I $(srctree)/$(src)/../ +ccflags-y += -I $(src)/../ diff --git a/drivers/net/wireless/intel/iwlwifi/mei/Makefile b/drivers/net/wireless/intel/iwlwifi/mei/Makefile index 8e3ef0347db7..e05f9421be4a 100644 --- a/drivers/net/wireless/intel/iwlwifi/mei/Makefile +++ b/drivers/net/wireless/intel/iwlwifi/mei/Makefile @@ -5,4 +5,4 @@ iwlmei-y += net.o iwlmei-$(CONFIG_IWLWIFI_DEVICE_TRACING) += trace.o CFLAGS_trace.o := -I$(src) -ccflags-y += -I $(srctree)/$(src)/../ +ccflags-y += -I $(src)/../ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/Makefile b/drivers/net/wireless/intel/iwlwifi/mvm/Makefile index 593fe28d89cf..764ba73cde1e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/Makefile +++ b/drivers/net/wireless/intel/iwlwifi/mvm/Makefile @@ -15,4 +15,4 @@ iwlmvm-$(CONFIG_IWLWIFI_LEDS) += led.o iwlmvm-$(CONFIG_PM) += d3.o iwlmvm-$(CONFIG_IWLMEI) += vendor-cmd.o -ccflags-y += -I $(srctree)/$(src)/../ +ccflags-y += -I $(src)/../ diff --git a/drivers/net/wireless/intel/iwlwifi/tests/Makefile b/drivers/net/wireless/intel/iwlwifi/tests/Makefile index 5658471bdf0a..84491488f589 100644 --- a/drivers/net/wireless/intel/iwlwifi/tests/Makefile +++ b/drivers/net/wireless/intel/iwlwifi/tests/Makefile @@ -2,6 +2,6 @@ iwlwifi-tests-y += module.o devinfo.o -ccflags-y += -I$(srctree)/$(src)/../ +ccflags-y += -I$(src)/../ obj-$(CONFIG_IWLWIFI_KUNIT_TESTS) += iwlwifi-tests.o diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8180/Makefile b/drivers/net/wireless/realtek/rtl818x/rtl8180/Makefile index 565a9a114134..1044105c2557 100644 --- a/drivers/net/wireless/realtek/rtl818x/rtl8180/Makefile +++ b/drivers/net/wireless/realtek/rtl818x/rtl8180/Makefile @@ -3,4 +3,4 @@ rtl818x_pci-objs := dev.o rtl8225.o sa2400.o max2820.o grf5101.o rtl8225se.o obj-$(CONFIG_RTL8180) += rtl818x_pci.o -ccflags-y += -I $(srctree)/$(src)/.. +ccflags-y += -I $(src)/.. diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8187/Makefile b/drivers/net/wireless/realtek/rtl818x/rtl8187/Makefile index 0bf64dfb233a..3deded2c05b6 100644 --- a/drivers/net/wireless/realtek/rtl818x/rtl8187/Makefile +++ b/drivers/net/wireless/realtek/rtl818x/rtl8187/Makefile @@ -3,4 +3,4 @@ rtl8187-objs := dev.o rtl8225.o leds.o rfkill.o obj-$(CONFIG_RTL8187) += rtl8187.o -ccflags-y += -I $(srctree)/$(src)/.. +ccflags-y += -I $(src)/.. diff --git a/drivers/scsi/aic7xxx/Makefile b/drivers/scsi/aic7xxx/Makefile index e0188ecd85b2..853c72a81ae0 100644 --- a/drivers/scsi/aic7xxx/Makefile +++ b/drivers/scsi/aic7xxx/Makefile @@ -55,9 +55,9 @@ aicasm-7xxx-opts-$(CONFIG_AIC7XXX_REG_PRETTY_PRINT) := \ ifeq ($(CONFIG_AIC7XXX_BUILD_FIRMWARE),y) $(obj)/aic7xxx_seq.h: $(src)/aic7xxx.seq $(src)/aic7xxx.reg $(obj)/aicasm/aicasm - $(obj)/aicasm/aicasm -I$(srctree)/$(src) -r $(obj)/aic7xxx_reg.h \ + $(obj)/aicasm/aicasm -I $(src) -r $(obj)/aic7xxx_reg.h \ $(aicasm-7xxx-opts-y) -o $(obj)/aic7xxx_seq.h \ - $(srctree)/$(src)/aic7xxx.seq + $(src)/aic7xxx.seq $(aic7xxx-gen-y): $(objtree)/$(obj)/aic7xxx_seq.h @true @@ -73,9 +73,9 @@ aicasm-79xx-opts-$(CONFIG_AIC79XX_REG_PRETTY_PRINT) := \ ifeq ($(CONFIG_AIC79XX_BUILD_FIRMWARE),y) $(obj)/aic79xx_seq.h: $(src)/aic79xx.seq $(src)/aic79xx.reg $(obj)/aicasm/aicasm - $(obj)/aicasm/aicasm -I$(srctree)/$(src) -r $(obj)/aic79xx_reg.h \ + $(obj)/aicasm/aicasm -I $(src) -r $(obj)/aic79xx_reg.h \ $(aicasm-79xx-opts-y) -o $(obj)/aic79xx_seq.h \ - $(srctree)/$(src)/aic79xx.seq + $(src)/aic79xx.seq $(aic79xx-gen-y): $(objtree)/$(obj)/aic79xx_seq.h @true @@ -83,5 +83,5 @@ else $(obj)/aic79xx_reg_print.c: $(src)/aic79xx_reg_print.c_shipped endif -$(obj)/aicasm/aicasm: $(srctree)/$(src)/aicasm/*.[chyl] - $(MAKE) -C $(srctree)/$(src)/aicasm OUTDIR=$(shell pwd)/$(obj)/aicasm/ +$(obj)/aicasm/aicasm: $(src)/aicasm/*.[chyl] + $(MAKE) -C $(src)/aicasm OUTDIR=$(shell pwd)/$(obj)/aicasm/ diff --git a/drivers/staging/rtl8723bs/Makefile b/drivers/staging/rtl8723bs/Makefile index 590bde02058c..7f5067e89295 100644 --- a/drivers/staging/rtl8723bs/Makefile +++ b/drivers/staging/rtl8723bs/Makefile @@ -62,4 +62,4 @@ r8723bs-y = \ obj-$(CONFIG_RTL8723BS) := r8723bs.o -ccflags-y += -I$(srctree)/$(src)/include -I$(srctree)/$(src)/hal +ccflags-y += -I$(src)/include -I$(src)/hal diff --git a/fs/iomap/Makefile b/fs/iomap/Makefile index fc070184b7fa..381d76c5c232 100644 --- a/fs/iomap/Makefile +++ b/fs/iomap/Makefile @@ -4,7 +4,7 @@ # All Rights Reserved. # -ccflags-y += -I $(srctree)/$(src) # needed for trace events +ccflags-y += -I $(src) # needed for trace events obj-$(CONFIG_FS_IOMAP) += iomap.o diff --git a/fs/unicode/Makefile b/fs/unicode/Makefile index 0e51c0025a16..e309afe2b2bb 100644 --- a/fs/unicode/Makefile +++ b/fs/unicode/Makefile @@ -18,13 +18,13 @@ ifdef REGENERATE_UTF8DATA quiet_cmd_utf8data = GEN $@ cmd_utf8data = $< \ - -a $(srctree)/$(src)/DerivedAge.txt \ - -c $(srctree)/$(src)/DerivedCombiningClass.txt \ - -p $(srctree)/$(src)/DerivedCoreProperties.txt \ - -d $(srctree)/$(src)/UnicodeData.txt \ - -f $(srctree)/$(src)/CaseFolding.txt \ - -n $(srctree)/$(src)/NormalizationCorrections.txt \ - -t $(srctree)/$(src)/NormalizationTest.txt \ + -a $(src)/DerivedAge.txt \ + -c $(src)/DerivedCombiningClass.txt \ + -p $(src)/DerivedCoreProperties.txt \ + -d $(src)/UnicodeData.txt \ + -f $(src)/CaseFolding.txt \ + -n $(src)/NormalizationCorrections.txt \ + -t $(src)/NormalizationTest.txt \ -o $@ $(obj)/utf8data.c: $(obj)/mkutf8data $(filter %.txt, $(cmd_utf8data)) FORCE diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 76674ad5833e..c5a35e32adf0 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -4,8 +4,8 @@ # All Rights Reserved. # -ccflags-y += -I $(srctree)/$(src) # needed for trace events -ccflags-y += -I $(srctree)/$(src)/libxfs +ccflags-y += -I $(src) # needed for trace events +ccflags-y += -I $(src)/libxfs obj-$(CONFIG_XFS_FS) += xfs.o diff --git a/init/Makefile b/init/Makefile index cbac576c57d6..3c48d97538c1 100644 --- a/init/Makefile +++ b/init/Makefile @@ -52,7 +52,7 @@ CFLAGS_version.o := -include $(obj)/utsversion-tmp.h # Build version-timestamp.c with final UTS_VERSION # -include/generated/utsversion.h: build-version-auto = $(shell $(srctree)/$(src)/build-version) +include/generated/utsversion.h: build-version-auto = $(shell $(src)/build-version) include/generated/utsversion.h: build-timestamp-auto = $(shell LC_ALL=C date) include/generated/utsversion.h: FORCE $(call filechk,uts_version) diff --git a/lib/Makefile b/lib/Makefile index ffc6b2341b45..27baa6e6daa8 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -352,7 +352,7 @@ $(obj)/oid_registry_data.c: $(srctree)/include/linux/oid_registry.h \ $(call cmd,build_OID_registry) quiet_cmd_build_OID_registry = GEN $@ - cmd_build_OID_registry = perl $(srctree)/$(src)/build_OID_registry $< $@ + cmd_build_OID_registry = perl $(src)/build_OID_registry $< $@ clean-files += oid_registry_data.c @@ -412,8 +412,8 @@ obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o obj-$(CONFIG_FIRMWARE_TABLE) += fw_table.o # FORTIFY_SOURCE compile-time behavior tests -TEST_FORTIFY_SRCS = $(wildcard $(srctree)/$(src)/test_fortify/*-*.c) -TEST_FORTIFY_LOGS = $(patsubst $(srctree)/$(src)/%.c, %.log, $(TEST_FORTIFY_SRCS)) +TEST_FORTIFY_SRCS = $(wildcard $(src)/test_fortify/*-*.c) +TEST_FORTIFY_LOGS = $(patsubst $(src)/%.c, %.log, $(TEST_FORTIFY_SRCS)) TEST_FORTIFY_LOG = test_fortify.log quiet_cmd_test_fortify = TEST $@ diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile index 385a94aa0b99..8785353c6140 100644 --- a/lib/raid6/Makefile +++ b/lib/raid6/Makefile @@ -53,7 +53,7 @@ endif endif quiet_cmd_unroll = UNROLL $@ - cmd_unroll = $(AWK) -v N=$* -f $(srctree)/$(src)/unroll.awk < $< > $@ + cmd_unroll = $(AWK) -v N=$* -f $(src)/unroll.awk < $< > $@ targets += int1.c int2.c int4.c int8.c $(obj)/int%.c: $(src)/int.uc $(src)/unroll.awk FORCE diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 72074fd36df4..1d49cc8b6da1 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -25,7 +25,7 @@ ifneq ($(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR),) cfg80211-y += extra-certs.o endif -$(obj)/shipped-certs.c: $(sort $(wildcard $(srctree)/$(src)/certs/*.hex)) +$(obj)/shipped-certs.c: $(sort $(wildcard $(src)/certs/*.hex)) @$(kecho) " GEN $@" $(Q)(echo '#include "reg.h"'; \ echo 'const u8 shipped_regdb_certs[] = {'; \ diff --git a/rust/Makefile b/rust/Makefile index 846e6ab9d5a9..85e46dde2a5b 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -239,7 +239,7 @@ quiet_cmd_rustsysroot = RUSTSYSROOT rm -rf $(objtree)/$(obj)/test; \ mkdir -p $(objtree)/$(obj)/test; \ cp -a $(rustc_sysroot) $(objtree)/$(obj)/test/sysroot; \ - cp -r $(srctree)/$(src)/alloc/* \ + cp -r $(src)/alloc/* \ $(objtree)/$(obj)/test/sysroot/lib/rustlib/src/rust/library/alloc/src; \ echo '\#!/bin/sh' > $(objtree)/$(obj)/test/rustc_sysroot; \ echo "$(RUSTC) --sysroot=$(abspath $(objtree)/$(obj)/test/sysroot) \"\$$@\"" \ @@ -340,7 +340,7 @@ quiet_cmd_bindgen = BINDGEN $@ $(bindgen_target_cflags) $(bindgen_target_extra) $(obj)/bindings/bindings_generated.rs: private bindgen_target_flags = \ - $(shell grep -Ev '^#|^$$' $(srctree)/$(src)/bindgen_parameters) + $(shell grep -Ev '^#|^$$' $(src)/bindgen_parameters) $(obj)/bindings/bindings_generated.rs: private bindgen_target_extra = ; \ sed -Ei 's/pub const RUST_CONST_HELPER_([a-zA-Z0-9_]*)/pub const \1/g' $@ $(obj)/bindings/bindings_generated.rs: $(src)/bindings/bindings_helper.h \ @@ -348,7 +348,7 @@ $(obj)/bindings/bindings_generated.rs: $(src)/bindings/bindings_helper.h \ $(call if_changed_dep,bindgen) $(obj)/uapi/uapi_generated.rs: private bindgen_target_flags = \ - $(shell grep -Ev '^#|^$$' $(srctree)/$(src)/bindgen_parameters) + $(shell grep -Ev '^#|^$$' $(src)/bindgen_parameters) $(obj)/uapi/uapi_generated.rs: $(src)/uapi/uapi_helper.h \ $(src)/bindgen_parameters FORCE $(call if_changed_dep,bindgen) diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 933f6c3fe6b0..f054e0828f13 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -BPF_SAMPLES_PATH ?= $(abspath $(srctree)/$(src)) +BPF_SAMPLES_PATH ?= $(abspath $(src)) TOOLS_PATH := $(BPF_SAMPLES_PATH)/../../tools pound := \# diff --git a/samples/hid/Makefile b/samples/hid/Makefile index 9f7fe29dd749..c128ccd49974 100644 --- a/samples/hid/Makefile +++ b/samples/hid/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -HID_SAMPLES_PATH ?= $(abspath $(srctree)/$(src)) +HID_SAMPLES_PATH ?= $(abspath $(src)) TOOLS_PATH := $(HID_SAMPLES_PATH)/../../tools pound := \# diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include index 2f331879816b..faf37bafa3f8 100644 --- a/scripts/Kbuild.include +++ b/scripts/Kbuild.include @@ -62,8 +62,7 @@ stringify = $(squote)$(quote)$1$(quote)$(squote) ### # The path to Kbuild or Makefile. Kbuild has precedence over Makefile. -kbuild-dir = $(if $(filter /%,$(src)),$(src),$(srctree)/$(src)) -kbuild-file = $(or $(wildcard $(kbuild-dir)/Kbuild),$(kbuild-dir)/Makefile) +kbuild-file = $(or $(wildcard $(src)/Kbuild),$(src)/Makefile) ### # Read a file, replacing newlines with spaces diff --git a/scripts/Makefile.asm-generic b/scripts/Makefile.asm-generic index 8d01b37b7677..1486abf34c7c 100644 --- a/scripts/Makefile.asm-generic +++ b/scripts/Makefile.asm-generic @@ -9,7 +9,7 @@ PHONY := all all: -src := $(subst /generated,,$(obj)) +src := $(srctree)/$(subst /generated,,$(obj)) include $(srctree)/scripts/Kbuild.include -include $(kbuild-file) @@ -20,14 +20,14 @@ include $(srctree)/$(generic)/Kbuild endif redundant := $(filter $(mandatory-y) $(generated-y), $(generic-y)) -redundant += $(foreach f, $(generic-y), $(if $(wildcard $(srctree)/$(src)/$(f)),$(f))) +redundant += $(foreach f, $(generic-y), $(if $(wildcard $(src)/$(f)),$(f))) redundant := $(sort $(redundant)) $(if $(redundant),\ $(warning redundant generic-y found in $(src)/Kbuild: $(redundant))) # If arch does not implement mandatory headers, fallback to asm-generic ones. mandatory-y := $(filter-out $(generated-y), $(mandatory-y)) -generic-y += $(foreach f, $(mandatory-y), $(if $(wildcard $(srctree)/$(src)/$(f)),,$(f))) +generic-y += $(foreach f, $(mandatory-y), $(if $(wildcard $(src)/$(f)),,$(f))) generic-y := $(addprefix $(obj)/, $(generic-y)) generated-y := $(addprefix $(obj)/, $(generated-y)) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 41138346afb0..43b71c3d0ff6 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -3,7 +3,7 @@ # Building # ========================================================================== -src := $(obj) +src := $(if $(VPATH),$(VPATH)/)$(obj) PHONY := $(obj)/ $(obj)/: diff --git a/scripts/Makefile.clean b/scripts/Makefile.clean index f2cb4d7ffd96..4fcfab40ed61 100644 --- a/scripts/Makefile.clean +++ b/scripts/Makefile.clean @@ -3,7 +3,7 @@ # Cleaning up # ========================================================================== -src := $(obj) +src := $(if $(VPATH),$(VPATH)/)$(obj) PHONY := __clean __clean: diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 42d3c772c8e0..08d42e93bea0 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -209,13 +209,13 @@ _c_flags += $(if $(patsubst n%,, \ -D__KCSAN_INSTRUMENT_BARRIERS__) endif -# $(srctree)/$(src) for including checkin headers from generated source files -# $(objtree)/$(obj) for including generated headers from checkin source files +# $(src) for including checkin headers from generated source files +# $(obj) for including generated headers from checkin source files ifeq ($(KBUILD_EXTMOD),) ifdef building_out_of_srctree -_c_flags += $(addprefix -I $(srctree)/,$(src)) $(addprefix -I $(objtree)/,$(obj)) -_a_flags += $(addprefix -I $(srctree)/,$(src)) $(addprefix -I $(objtree)/,$(obj)) -_cpp_flags += $(addprefix -I $(srctree)/,$(src)) $(addprefix -I $(objtree)/,$(obj)) +_c_flags += $(addprefix -I, $(src) $(obj)) +_a_flags += $(addprefix -I, $(src) $(obj)) +_cpp_flags += $(addprefix -I, $(src) $(obj)) endif endif diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index 739402f45509..68c4f9ee0c90 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -112,7 +112,7 @@ else # set src + obj - they may be used in the modules's Makefile obj := $(KBUILD_EXTMOD) -src := $(obj) +src := $(if $(VPATH),$(VPATH)/)$(obj) # Include the module's Makefile to find KBUILD_EXTRA_SYMBOLS include $(kbuild-file) diff --git a/scripts/dtc/Makefile b/scripts/dtc/Makefile index 4d32b9497da9..a18657072541 100644 --- a/scripts/dtc/Makefile +++ b/scripts/dtc/Makefile @@ -16,12 +16,12 @@ libfdt = $(addprefix libfdt/,$(libfdt-objs)) fdtoverlay-objs := $(libfdt) fdtoverlay.o util.o # Source files need to get at the userspace version of libfdt_env.h to compile -HOST_EXTRACFLAGS += -I $(srctree)/$(src)/libfdt +HOST_EXTRACFLAGS += -I $(src)/libfdt HOST_EXTRACFLAGS += -DNO_YAML # Generated files need one more search path to include headers in source tree -HOSTCFLAGS_dtc-lexer.lex.o := -I $(srctree)/$(src) -HOSTCFLAGS_dtc-parser.tab.o := -I $(srctree)/$(src) +HOSTCFLAGS_dtc-lexer.lex.o := -I $(src) +HOSTCFLAGS_dtc-parser.tab.o := -I $(src) # dependencies on generated files need to be listed explicitly $(obj)/dtc-lexer.lex.o: $(obj)/dtc-parser.tab.h diff --git a/scripts/gdb/linux/Makefile b/scripts/gdb/linux/Makefile index 48941faa6ea6..d77ad9079d0f 100644 --- a/scripts/gdb/linux/Makefile +++ b/scripts/gdb/linux/Makefile @@ -2,7 +2,7 @@ ifdef building_out_of_srctree -symlinks := $(patsubst $(srctree)/$(src)/%,%,$(wildcard $(srctree)/$(src)/*.py)) +symlinks := $(patsubst $(src)/%,%,$(wildcard $(src)/*.py)) quiet_cmd_symlink = SYMLINK $@ cmd_symlink = ln -fsn $(patsubst $(obj)/%,$(abspath $(srctree))/$(src)/%,$@) $@ diff --git a/scripts/genksyms/Makefile b/scripts/genksyms/Makefile index d6a422a63b6a..312edccda736 100644 --- a/scripts/genksyms/Makefile +++ b/scripts/genksyms/Makefile @@ -23,8 +23,8 @@ $(obj)/pars%.tab.c $(obj)/pars%.tab.h: $(src)/pars%.y FORCE endif # -I needed for generated C source to include headers in source tree -HOSTCFLAGS_parse.tab.o := -I $(srctree)/$(src) -HOSTCFLAGS_lex.lex.o := -I $(srctree)/$(src) +HOSTCFLAGS_parse.tab.o := -I $(src) +HOSTCFLAGS_lex.lex.o := -I $(src) # dependencies on generated files need to be listed explicitly $(obj)/lex.lex.o: $(obj)/parse.tab.h diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index ea1bf3b3dbde..a0a0be38cbdc 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -57,7 +57,7 @@ $(foreach c, config menuconfig nconfig gconfig xconfig, $(eval $(call config_rul PHONY += localmodconfig localyesconfig localyesconfig localmodconfig: $(obj)/conf - $(Q)$(PERL) $(srctree)/$(src)/streamline_config.pl --$@ $(srctree) $(Kconfig) > .tmp.config + $(Q)$(PERL) $(src)/streamline_config.pl --$@ $(srctree) $(Kconfig) > .tmp.config $(Q)if [ -f .config ]; then \ cmp -s .tmp.config .config || \ (mv -f .config .config.old.1; \ @@ -118,7 +118,7 @@ tinyconfig: # CHECK: -o cache_dir= working? PHONY += testconfig testconfig: $(obj)/conf - $(Q)$(PYTHON3) -B -m pytest $(srctree)/$(src)/tests \ + $(Q)$(PYTHON3) -B -m pytest $(src)/tests \ -o cache_dir=$(abspath $(obj)/tests/.cache) \ $(if $(findstring 1,$(KBUILD_VERBOSE)),--capture=no) clean-files += tests/.cache @@ -165,8 +165,8 @@ common-objs := confdata.o expr.o lexer.lex.o menu.o parser.tab.o \ preprocess.o symbol.o util.o $(obj)/lexer.lex.o: $(obj)/parser.tab.h -HOSTCFLAGS_lexer.lex.o := -I $(srctree)/$(src) -HOSTCFLAGS_parser.tab.o := -I $(srctree)/$(src) +HOSTCFLAGS_lexer.lex.o := -I $(src) +HOSTCFLAGS_parser.tab.o := -I $(src) # conf: Used for defconfig, oldconfig and related targets hostprogs += conf diff --git a/security/tomoyo/Makefile b/security/tomoyo/Makefile index 884ff155edc3..55c67b9846a9 100644 --- a/security/tomoyo/Makefile +++ b/security/tomoyo/Makefile @@ -11,7 +11,7 @@ quiet_cmd_policy = POLICY $@ printf '\t"";\n';) \ } > $@ -$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(srctree)/$(src)/policy/*.conf.default) FORCE +$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(src)/policy/*.conf.default) FORCE $(call if_changed,policy) ifndef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING diff --git a/usr/Makefile b/usr/Makefile index f8e1ad19e05c..132ef7e96e6d 100644 --- a/usr/Makefile +++ b/usr/Makefile @@ -22,7 +22,7 @@ cpio-data := # If CONFIG_INITRAMFS_SOURCE is empty, generate a small initramfs with the # default contents. ifeq ($(ramfs-input),) -ramfs-input := $(srctree)/$(src)/default_cpio_list +ramfs-input := $(src)/default_cpio_list endif ifeq ($(words $(ramfs-input)),1) diff --git a/usr/include/Makefile b/usr/include/Makefile index 338c81f1fcf3..771e32872b2a 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -78,7 +78,7 @@ quiet_cmd_hdrtest = HDRTEST $< cmd_hdrtest = \ $(CC) $(c_flags) -fsyntax-only -x c /dev/null \ $(if $(filter-out $(no-header-test), $*.h), -include $< -include $<); \ - $(PERL) $(srctree)/$(src)/headers_check.pl $(obj) $(SRCARCH) $<; \ + $(PERL) $(src)/headers_check.pl $(obj) $(SRCARCH) $<; \ touch $@ $(obj)/%.hdrtest: $(obj)/%.h FORCE -- cgit v1.2.3 From 890a64810d59b1a58ed26efc28cfd821fc068e84 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 14 May 2024 16:37:48 -0700 Subject: ubsan: Restore dependency on ARCH_HAS_UBSAN While removing CONFIG_UBSAN_SANITIZE_ALL, ARCH_HAS_UBSAN wasn't correctly depended on. Restore this, as we do not want to attempt UBSAN builds unless it's actually been tested on a given architecture. Reported-by: Masahiro Yamada Closes: https://lore.kernel.org/all/20240514095427.541201-1-masahiroy@kernel.org Fixes: 918327e9b7ff ("ubsan: Remove CONFIG_UBSAN_SANITIZE_ALL") Link: https://lore.kernel.org/r/20240514233747.work.441-kees@kernel.org Signed-off-by: Kees Cook --- lib/Kconfig.ubsan | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index e81e1ac4a919..bdda600f8dfb 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -4,6 +4,7 @@ config ARCH_HAS_UBSAN menuconfig UBSAN bool "Undefined behaviour sanity checker" + depends on ARCH_HAS_UBSAN help This option enables the Undefined Behaviour sanity checker. Compile-time instrumentation is used to detect various undefined -- cgit v1.2.3 From ae1a863bcdbd6ea2abc93519a82ab5d715d5dcbc Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sat, 18 May 2024 11:40:23 -0700 Subject: kunit/fortify: Fix memcmp() test to be amplitude agnostic When memcmp() returns a non-zero value, only the signed bit has any meaning. The actual value may differ between implementations. Reported-by: Nathan Chancellor Closes: https://github.com/ClangBuiltLinux/linux/issues/2025 Tested-by: Nathan Chancellor Link: https://lore.kernel.org/r/20240518184020.work.604-kees@kernel.org Signed-off-by: Kees Cook --- lib/fortify_kunit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index d2377e00caab..39da5b3bc649 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -990,7 +990,7 @@ static void fortify_test_memcmp(struct kunit *test) KUNIT_ASSERT_EQ(test, memcmp(one, two, one_len), 0); KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); /* Still in bounds, but no longer matching. */ - KUNIT_ASSERT_EQ(test, memcmp(one, two, one_len + 1), -32); + KUNIT_ASSERT_LT(test, memcmp(one, two, one_len + 1), 0); KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); /* Catch too-large ranges. */ -- cgit v1.2.3 From 4be073931cd831fa19bf8b612b9a1521385aa53e Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Fri, 29 Mar 2024 00:18:21 -0700 Subject: lib/raid6: use CC_FLAGS_FPU for NEON CFLAGS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that CC_FLAGS_FPU is exported and can be used anywhere in the source tree, use it instead of duplicating the flags here. Link: https://lkml.kernel.org/r/20240329072441.591471-7-samuel.holland@sifive.com Signed-off-by: Samuel Holland Reviewed-by: Christoph Hellwig Acked-by: Christian König Cc: Alex Deucher Cc: Borislav Petkov (AMD) Cc: Catalin Marinas Cc: Dave Hansen Cc: Huacai Chen Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Masahiro Yamada Cc: Michael Ellerman Cc: Nathan Chancellor Cc: Nicolas Schier Cc: Palmer Dabbelt Cc: Russell King Cc: Thomas Gleixner Cc: WANG Xuerui Cc: Will Deacon Signed-off-by: Andrew Morton --- lib/raid6/Makefile | 33 ++++++++++----------------------- 1 file changed, 10 insertions(+), 23 deletions(-) (limited to 'lib') diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile index 8785353c6140..29127dd05d63 100644 --- a/lib/raid6/Makefile +++ b/lib/raid6/Makefile @@ -33,25 +33,6 @@ CFLAGS_REMOVE_vpermxor8.o += -msoft-float endif endif -# The GCC option -ffreestanding is required in order to compile code containing -# ARM/NEON intrinsics in a non C99-compliant environment (such as the kernel) -ifeq ($(CONFIG_KERNEL_MODE_NEON),y) -NEON_FLAGS := -ffreestanding -# Enable -NEON_FLAGS += -isystem $(shell $(CC) -print-file-name=include) -ifeq ($(ARCH),arm) -NEON_FLAGS += -march=armv7-a -mfloat-abi=softfp -mfpu=neon -endif -CFLAGS_recov_neon_inner.o += $(NEON_FLAGS) -ifeq ($(ARCH),arm64) -CFLAGS_REMOVE_recov_neon_inner.o += -mgeneral-regs-only -CFLAGS_REMOVE_neon1.o += -mgeneral-regs-only -CFLAGS_REMOVE_neon2.o += -mgeneral-regs-only -CFLAGS_REMOVE_neon4.o += -mgeneral-regs-only -CFLAGS_REMOVE_neon8.o += -mgeneral-regs-only -endif -endif - quiet_cmd_unroll = UNROLL $@ cmd_unroll = $(AWK) -v N=$* -f $(src)/unroll.awk < $< > $@ @@ -75,10 +56,16 @@ targets += vpermxor1.c vpermxor2.c vpermxor4.c vpermxor8.c $(obj)/vpermxor%.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) -CFLAGS_neon1.o += $(NEON_FLAGS) -CFLAGS_neon2.o += $(NEON_FLAGS) -CFLAGS_neon4.o += $(NEON_FLAGS) -CFLAGS_neon8.o += $(NEON_FLAGS) +CFLAGS_neon1.o += $(CC_FLAGS_FPU) +CFLAGS_neon2.o += $(CC_FLAGS_FPU) +CFLAGS_neon4.o += $(CC_FLAGS_FPU) +CFLAGS_neon8.o += $(CC_FLAGS_FPU) +CFLAGS_recov_neon_inner.o += $(CC_FLAGS_FPU) +CFLAGS_REMOVE_neon1.o += $(CC_FLAGS_NO_FPU) +CFLAGS_REMOVE_neon2.o += $(CC_FLAGS_NO_FPU) +CFLAGS_REMOVE_neon4.o += $(CC_FLAGS_NO_FPU) +CFLAGS_REMOVE_neon8.o += $(CC_FLAGS_NO_FPU) +CFLAGS_REMOVE_recov_neon_inner.o += $(CC_FLAGS_NO_FPU) targets += neon1.c neon2.c neon4.c neon8.c $(obj)/neon%.c: $(src)/neon.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) -- cgit v1.2.3 From 9613736d852dce2376a848e6e9af091c422a947e Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Fri, 29 Mar 2024 00:18:29 -0700 Subject: selftests/fpu: move FP code to a separate translation unit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This ensures no compiler-generated floating-point code can appear outside kernel_fpu_{begin,end}() sections, and some architectures enforce this separation. Link: https://lkml.kernel.org/r/20240329072441.591471-15-samuel.holland@sifive.com Signed-off-by: Samuel Holland Reviewed-by: Christoph Hellwig Acked-by: Christian König Cc: Alex Deucher Cc: Borislav Petkov (AMD) Cc: Catalin Marinas Cc: Dave Hansen Cc: Huacai Chen Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Masahiro Yamada Cc: Michael Ellerman Cc: Nathan Chancellor Cc: Nicolas Schier Cc: Palmer Dabbelt Cc: Russell King Cc: Thomas Gleixner Cc: WANG Xuerui Cc: Will Deacon Signed-off-by: Andrew Morton --- lib/Makefile | 3 +- lib/test_fpu.c | 89 ----------------------------------------------------- lib/test_fpu.h | 8 +++++ lib/test_fpu_glue.c | 59 +++++++++++++++++++++++++++++++++++ lib/test_fpu_impl.c | 37 ++++++++++++++++++++++ 5 files changed, 106 insertions(+), 90 deletions(-) delete mode 100644 lib/test_fpu.c create mode 100644 lib/test_fpu.h create mode 100644 lib/test_fpu_glue.c create mode 100644 lib/test_fpu_impl.c (limited to 'lib') diff --git a/lib/Makefile b/lib/Makefile index 7a1fdd1cce7a..87f8803587ae 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -133,7 +133,8 @@ FPU_CFLAGS += $(call cc-option,-msse -mpreferred-stack-boundary=3,-mpreferred-st endif obj-$(CONFIG_TEST_FPU) += test_fpu.o -CFLAGS_test_fpu.o += $(FPU_CFLAGS) +test_fpu-y := test_fpu_glue.o test_fpu_impl.o +CFLAGS_test_fpu_impl.o += $(FPU_CFLAGS) # Some KUnit files (hooks.o) need to be built-in even when KUnit is a module, # so we can't just use obj-$(CONFIG_KUNIT). diff --git a/lib/test_fpu.c b/lib/test_fpu.c deleted file mode 100644 index e82db19fed84..000000000000 --- a/lib/test_fpu.c +++ /dev/null @@ -1,89 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * Test cases for using floating point operations inside a kernel module. - * - * This tests kernel_fpu_begin() and kernel_fpu_end() functions, especially - * when userland has modified the floating point control registers. The kernel - * state might depend on the state set by the userland thread that was active - * before a syscall. - * - * To facilitate the test, this module registers file - * /sys/kernel/debug/selftest_helpers/test_fpu, which when read causes a - * sequence of floating point operations. If the operations fail, either the - * read returns error status or the kernel crashes. - * If the operations succeed, the read returns "1\n". - */ - -#include -#include -#include -#include - -static int test_fpu(void) -{ - /* - * This sequence of operations tests that rounding mode is - * to nearest and that denormal numbers are supported. - * Volatile variables are used to avoid compiler optimizing - * the calculations away. - */ - volatile double a, b, c, d, e, f, g; - - a = 4.0; - b = 1e-15; - c = 1e-310; - - /* Sets precision flag */ - d = a + b; - - /* Result depends on rounding mode */ - e = a + b / 2; - - /* Denormal and very large values */ - f = b / c; - - /* Depends on denormal support */ - g = a + c * f; - - if (d > a && e > a && g > a) - return 0; - else - return -EINVAL; -} - -static int test_fpu_get(void *data, u64 *val) -{ - int status = -EINVAL; - - kernel_fpu_begin(); - status = test_fpu(); - kernel_fpu_end(); - - *val = 1; - return status; -} - -DEFINE_DEBUGFS_ATTRIBUTE(test_fpu_fops, test_fpu_get, NULL, "%lld\n"); -static struct dentry *selftest_dir; - -static int __init test_fpu_init(void) -{ - selftest_dir = debugfs_create_dir("selftest_helpers", NULL); - if (!selftest_dir) - return -ENOMEM; - - debugfs_create_file_unsafe("test_fpu", 0444, selftest_dir, NULL, - &test_fpu_fops); - - return 0; -} - -static void __exit test_fpu_exit(void) -{ - debugfs_remove(selftest_dir); -} - -module_init(test_fpu_init); -module_exit(test_fpu_exit); - -MODULE_LICENSE("GPL"); diff --git a/lib/test_fpu.h b/lib/test_fpu.h new file mode 100644 index 000000000000..4459807084bc --- /dev/null +++ b/lib/test_fpu.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef _LIB_TEST_FPU_H +#define _LIB_TEST_FPU_H + +int test_fpu(void); + +#endif diff --git a/lib/test_fpu_glue.c b/lib/test_fpu_glue.c new file mode 100644 index 000000000000..85963d7be826 --- /dev/null +++ b/lib/test_fpu_glue.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Test cases for using floating point operations inside a kernel module. + * + * This tests kernel_fpu_begin() and kernel_fpu_end() functions, especially + * when userland has modified the floating point control registers. The kernel + * state might depend on the state set by the userland thread that was active + * before a syscall. + * + * To facilitate the test, this module registers file + * /sys/kernel/debug/selftest_helpers/test_fpu, which when read causes a + * sequence of floating point operations. If the operations fail, either the + * read returns error status or the kernel crashes. + * If the operations succeed, the read returns "1\n". + */ + +#include +#include +#include +#include + +#include "test_fpu.h" + +static int test_fpu_get(void *data, u64 *val) +{ + int status = -EINVAL; + + kernel_fpu_begin(); + status = test_fpu(); + kernel_fpu_end(); + + *val = 1; + return status; +} + +DEFINE_DEBUGFS_ATTRIBUTE(test_fpu_fops, test_fpu_get, NULL, "%lld\n"); +static struct dentry *selftest_dir; + +static int __init test_fpu_init(void) +{ + selftest_dir = debugfs_create_dir("selftest_helpers", NULL); + if (!selftest_dir) + return -ENOMEM; + + debugfs_create_file_unsafe("test_fpu", 0444, selftest_dir, NULL, + &test_fpu_fops); + + return 0; +} + +static void __exit test_fpu_exit(void) +{ + debugfs_remove(selftest_dir); +} + +module_init(test_fpu_init); +module_exit(test_fpu_exit); + +MODULE_LICENSE("GPL"); diff --git a/lib/test_fpu_impl.c b/lib/test_fpu_impl.c new file mode 100644 index 000000000000..777894dbbe86 --- /dev/null +++ b/lib/test_fpu_impl.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include + +#include "test_fpu.h" + +int test_fpu(void) +{ + /* + * This sequence of operations tests that rounding mode is + * to nearest and that denormal numbers are supported. + * Volatile variables are used to avoid compiler optimizing + * the calculations away. + */ + volatile double a, b, c, d, e, f, g; + + a = 4.0; + b = 1e-15; + c = 1e-310; + + /* Sets precision flag */ + d = a + b; + + /* Result depends on rounding mode */ + e = a + b / 2; + + /* Denormal and very large values */ + f = b / c; + + /* Depends on denormal support */ + g = a + c * f; + + if (d > a && e > a && g > a) + return 0; + else + return -EINVAL; +} -- cgit v1.2.3 From 790a4a3dd1039ee07e7bb5854dcc7ccfbb40c876 Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Fri, 29 Mar 2024 00:18:30 -0700 Subject: selftests/fpu: allow building on other architectures MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that ARCH_HAS_KERNEL_FPU_SUPPORT provides a common way to compile and run floating-point code, this test is no longer x86-specific. Link: https://lkml.kernel.org/r/20240329072441.591471-16-samuel.holland@sifive.com Signed-off-by: Samuel Holland Reviewed-by: Christoph Hellwig Acked-by: Christian König Cc: Alex Deucher Cc: Borislav Petkov (AMD) Cc: Catalin Marinas Cc: Dave Hansen Cc: Huacai Chen Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Masahiro Yamada Cc: Michael Ellerman Cc: Nathan Chancellor Cc: Nicolas Schier Cc: Palmer Dabbelt Cc: Russell King Cc: Thomas Gleixner Cc: WANG Xuerui Cc: Will Deacon Signed-off-by: Andrew Morton --- lib/Kconfig.debug | 2 +- lib/Makefile | 25 ++----------------------- lib/test_fpu_glue.c | 5 ++++- 3 files changed, 7 insertions(+), 25 deletions(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c1c1b19525a5..f4384fd60a76 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2926,7 +2926,7 @@ config TEST_FREE_PAGES config TEST_FPU tristate "Test floating point operations in kernel space" - depends on X86 && !KCOV_INSTRUMENT_ALL + depends on ARCH_HAS_KERNEL_FPU_SUPPORT && !KCOV_INSTRUMENT_ALL help Enable this option to add /sys/kernel/debug/selftest_helpers/test_fpu which will trigger a sequence of floating point operations. This is used diff --git a/lib/Makefile b/lib/Makefile index 87f8803587ae..3b1769045651 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -110,31 +110,10 @@ CFLAGS_test_fprobe.o += $(CC_FLAGS_FTRACE) obj-$(CONFIG_FPROBE_SANITY_TEST) += test_fprobe.o obj-$(CONFIG_TEST_OBJPOOL) += test_objpool.o -# -# CFLAGS for compiling floating point code inside the kernel. x86/Makefile turns -# off the generation of FPU/SSE* instructions for kernel proper but FPU_FLAGS -# get appended last to CFLAGS and thus override those previous compiler options. -# -FPU_CFLAGS := -msse -msse2 -ifdef CONFIG_CC_IS_GCC -# Stack alignment mismatch, proceed with caution. -# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 -# (8B stack alignment). -# See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383 -# -# The "-msse" in the first argument is there so that the -# -mpreferred-stack-boundary=3 build error: -# -# -mpreferred-stack-boundary=3 is not between 4 and 12 -# -# can be triggered. Otherwise gcc doesn't complain. -FPU_CFLAGS += -mhard-float -FPU_CFLAGS += $(call cc-option,-msse -mpreferred-stack-boundary=3,-mpreferred-stack-boundary=4) -endif - obj-$(CONFIG_TEST_FPU) += test_fpu.o test_fpu-y := test_fpu_glue.o test_fpu_impl.o -CFLAGS_test_fpu_impl.o += $(FPU_CFLAGS) +CFLAGS_test_fpu_impl.o += $(CC_FLAGS_FPU) +CFLAGS_REMOVE_test_fpu_impl.o += $(CC_FLAGS_NO_FPU) # Some KUnit files (hooks.o) need to be built-in even when KUnit is a module, # so we can't just use obj-$(CONFIG_KUNIT). diff --git a/lib/test_fpu_glue.c b/lib/test_fpu_glue.c index 85963d7be826..eef282a2715f 100644 --- a/lib/test_fpu_glue.c +++ b/lib/test_fpu_glue.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include "test_fpu.h" @@ -38,6 +38,9 @@ static struct dentry *selftest_dir; static int __init test_fpu_init(void) { + if (!kernel_fpu_available()) + return -EINVAL; + selftest_dir = debugfs_create_dir("selftest_helpers", NULL); if (!selftest_dir) return -ENOMEM; -- cgit v1.2.3 From 70c435ca8dcb64e3d7983a30a14484aa163bb2d2 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 30 Apr 2024 15:28:24 +1000 Subject: stackdepot: use gfp_nested_mask() instead of open coded masking The stackdepot code is used by KASAN and lockdep for recoding stack traces. Both of these track allocation context information, and so their internal allocations must obey the caller allocation contexts to avoid generating their own false positive warnings that have nothing to do with the code they are instrumenting/tracking. We also don't want recording stack traces to deplete emergency memory reserves - debug code is useless if it creates new issues that can't be replicated when the debug code is disabled. Switch the stackdepot allocation masking to use gfp_nested_mask() to address these issues. gfp_nested_mask() also strips GFP_ZONEMASK naturally, so that greatly simplifies this code. Link: https://lkml.kernel.org/r/20240430054604.4169568-3-david@fromorbit.com Signed-off-by: Dave Chinner Reviewed-by: Marco Elver Reviewed-by: Christoph Hellwig Reviewed-by: Vlastimil Babka Reviewed-by: Oscar Salvador Cc: Andrey Konovalov Signed-off-by: Andrew Morton --- lib/stackdepot.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'lib') diff --git a/lib/stackdepot.c b/lib/stackdepot.c index cd8f23455285..5ed34cc963fc 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -624,15 +624,8 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries, * we won't be able to do that under the lock. */ if (unlikely(can_alloc && !READ_ONCE(new_pool))) { - /* - * Zero out zone modifiers, as we don't have specific zone - * requirements. Keep the flags related to allocation in atomic - * contexts, I/O, nolockdep. - */ - alloc_flags &= ~GFP_ZONEMASK; - alloc_flags &= (GFP_ATOMIC | GFP_KERNEL | __GFP_NOLOCKDEP); - alloc_flags |= __GFP_NOWARN; - page = alloc_pages(alloc_flags, DEPOT_POOL_ORDER); + page = alloc_pages(gfp_nested_mask(alloc_flags), + DEPOT_POOL_ORDER); if (page) prealloc = page_address(page); } -- cgit v1.2.3 From 9f2c2d6ba13da08643c65b948ce5e3d616864c47 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 7 May 2024 23:01:31 +0300 Subject: bitops: Move aligned_byte_mask() to wordpart.h The bitops.h is for bit related operations. The aligned_byte_mask() is about byte (or part of the machine word) operations, for which we have a separate header, move the mentioned macro to wordpart.h to consolidate similar operations. Signed-off-by: Andy Shevchenko Signed-off-by: Yury Norov --- include/linux/bitops.h | 7 ------- include/linux/wordpart.h | 7 +++++++ lib/usercopy.c | 1 + 3 files changed, 8 insertions(+), 7 deletions(-) (limited to 'lib') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 57ecef354f47..3313d2c04e6d 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -8,13 +8,6 @@ #include -/* Set bits in the first 'n' bytes when loaded from memory */ -#ifdef __LITTLE_ENDIAN -# define aligned_byte_mask(n) ((1UL << 8*(n))-1) -#else -# define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n))) -#endif - #define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) #define BITS_TO_LONGS(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(long)) #define BITS_TO_U64(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u64)) diff --git a/include/linux/wordpart.h b/include/linux/wordpart.h index f6f8f83b15b0..4ca1ba66d2f0 100644 --- a/include/linux/wordpart.h +++ b/include/linux/wordpart.h @@ -39,4 +39,11 @@ */ #define REPEAT_BYTE(x) ((~0ul / 0xff) * (x)) +/* Set bits in the first 'n' bytes when loaded from memory */ +#ifdef __LITTLE_ENDIAN +# define aligned_byte_mask(n) ((1UL << 8*(n))-1) +#else +# define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n))) +#endif + #endif // _LINUX_WORDPART_H diff --git a/lib/usercopy.c b/lib/usercopy.c index d29fe29c6849..4b62e6299cc8 100644 --- a/lib/usercopy.c +++ b/lib/usercopy.c @@ -3,6 +3,7 @@ #include #include #include +#include #include /* out-of-line parts */ -- cgit v1.2.3 From 5671dca241b9a2f4ecf88d8e992041cfb580e0a5 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 7 May 2024 23:01:32 +0300 Subject: usercopy: Don't use "proxy" headers Update header inclusions to follow IWYU (Include What You Use) principle. Signed-off-by: Andy Shevchenko Signed-off-by: Yury Norov --- lib/usercopy.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/usercopy.c b/lib/usercopy.c index 4b62e6299cc8..499a7a7d54db 100644 --- a/lib/usercopy.c +++ b/lib/usercopy.c @@ -1,10 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 -#include +#include +#include +#include #include #include +#include +#include +#include #include #include -#include /* out-of-line parts */ -- cgit v1.2.3 From a38568a0b46d4a0dbe48f4642cbe2f885c525643 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Tue, 14 May 2024 09:31:28 -0700 Subject: lib: add version into /proc/allocinfo output Add version string and a header at the beginning of /proc/allocinfo to allow later format changes. Example output: > head /proc/allocinfo allocinfo - version: 1.0 # 0 0 init/main.c:1314 func:do_initcalls 0 0 init/do_mounts.c:353 func:mount_nodev_root 0 0 init/do_mounts.c:187 func:mount_root_generic 0 0 init/do_mounts.c:158 func:do_mount_root 0 0 init/initramfs.c:493 func:unpack_to_rootfs 0 0 init/initramfs.c:492 func:unpack_to_rootfs 0 0 init/initramfs.c:491 func:unpack_to_rootfs 512 1 arch/x86/events/rapl.c:681 func:init_rapl_pmus 128 1 arch/x86/events/rapl.c:571 func:rapl_cpu_online [akpm@linux-foundation.org: remove stray newline from struct allocinfo_private] Link: https://lkml.kernel.org/r/20240514163128.3662251-1-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Pasha Tatashin Reviewed-by: Kees Cook Cc: Kent Overstreet Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- Documentation/filesystems/proc.rst | 5 ++-- lib/alloc_tag.c | 47 ++++++++++++++++++++++++++------------ 2 files changed, 35 insertions(+), 17 deletions(-) (limited to 'lib') diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 4d97258a7954..7c3a565ffbef 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -961,13 +961,14 @@ Provides information about memory allocations at all locations in the code base. Each allocation in the code is identified by its source file, line number, module (if originates from a loadable module) and the function calling the allocation. The number of bytes allocated and number of calls at each -location are reported. +location are reported. The first line indicates the version of the file, the +second line is the header listing fields in the file. Example output. :: - > sort -rn /proc/allocinfo + > tail -n +3 /proc/allocinfo | sort -rn 127664128 31168 mm/page_ext.c:270 func:alloc_page_ext 56373248 4737 mm/slub.c:2259 func:alloc_slab_page 14880768 3633 mm/readahead.c:247 func:page_cache_ra_unbounded diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 531dbe2f5456..11ed973ac359 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -16,47 +16,60 @@ EXPORT_SYMBOL(_shared_alloc_tag); DEFINE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, mem_alloc_profiling_key); +struct allocinfo_private { + struct codetag_iterator iter; + bool print_header; +}; + static void *allocinfo_start(struct seq_file *m, loff_t *pos) { - struct codetag_iterator *iter; + struct allocinfo_private *priv; struct codetag *ct; loff_t node = *pos; - iter = kzalloc(sizeof(*iter), GFP_KERNEL); - m->private = iter; - if (!iter) + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + m->private = priv; + if (!priv) return NULL; + priv->print_header = (node == 0); codetag_lock_module_list(alloc_tag_cttype, true); - *iter = codetag_get_ct_iter(alloc_tag_cttype); - while ((ct = codetag_next_ct(iter)) != NULL && node) + priv->iter = codetag_get_ct_iter(alloc_tag_cttype); + while ((ct = codetag_next_ct(&priv->iter)) != NULL && node) node--; - return ct ? iter : NULL; + return ct ? priv : NULL; } static void *allocinfo_next(struct seq_file *m, void *arg, loff_t *pos) { - struct codetag_iterator *iter = (struct codetag_iterator *)arg; - struct codetag *ct = codetag_next_ct(iter); + struct allocinfo_private *priv = (struct allocinfo_private *)arg; + struct codetag *ct = codetag_next_ct(&priv->iter); (*pos)++; if (!ct) return NULL; - return iter; + return priv; } static void allocinfo_stop(struct seq_file *m, void *arg) { - struct codetag_iterator *iter = (struct codetag_iterator *)m->private; + struct allocinfo_private *priv = (struct allocinfo_private *)m->private; - if (iter) { + if (priv) { codetag_lock_module_list(alloc_tag_cttype, false); - kfree(iter); + kfree(priv); } } +static void print_allocinfo_header(struct seq_buf *buf) +{ + /* Output format version, so we can change it. */ + seq_buf_printf(buf, "allocinfo - version: 1.0\n"); + seq_buf_printf(buf, "# \n"); +} + static void alloc_tag_to_text(struct seq_buf *out, struct codetag *ct) { struct alloc_tag *tag = ct_to_alloc_tag(ct); @@ -71,13 +84,17 @@ static void alloc_tag_to_text(struct seq_buf *out, struct codetag *ct) static int allocinfo_show(struct seq_file *m, void *arg) { - struct codetag_iterator *iter = (struct codetag_iterator *)arg; + struct allocinfo_private *priv = (struct allocinfo_private *)arg; char *bufp; size_t n = seq_get_buf(m, &bufp); struct seq_buf buf; seq_buf_init(&buf, bufp, n); - alloc_tag_to_text(&buf, iter->ct); + if (priv->print_header) { + print_allocinfo_header(&buf); + priv->print_header = false; + } + alloc_tag_to_text(&buf, priv->iter.ct); seq_commit(m, seq_buf_used(&buf)); return 0; } -- cgit v1.2.3