From b94605a3889b9084d88f1fe06b043e082bc6b075 Mon Sep 17 00:00:00 2001 From: Jocelyn Falempe Date: Fri, 19 Apr 2024 15:20:19 +0200 Subject: lib/fonts: Allow to select fonts for drm_panic drm_panic has been introduced recently, and uses the same fonts as FRAMEBUFFER_CONSOLE. Signed-off-by: Jocelyn Falempe Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20240419132243.154466-1-jfalempe@redhat.com --- lib/fonts/Kconfig | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'lib') diff --git a/lib/fonts/Kconfig b/lib/fonts/Kconfig index 7e945fdcbf11..befcb463f738 100644 --- a/lib/fonts/Kconfig +++ b/lib/fonts/Kconfig @@ -10,7 +10,7 @@ if FONT_SUPPORT config FONTS bool "Select compiled-in fonts" - depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE + depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE || DRM_PANIC help Say Y here if you would like to use fonts other than the default your frame buffer console usually use. @@ -23,7 +23,7 @@ config FONTS config FONT_8x8 bool "VGA 8x8 font" if FONTS - depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE + depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE || DRM_PANIC default y if !SPARC && !FONTS help This is the "high resolution" font for the VGA frame buffer (the one @@ -46,7 +46,7 @@ config FONT_8x16 config FONT_6x11 bool "Mac console 6x11 font (not supported by all drivers)" if FONTS - depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE + depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE || DRM_PANIC default y if !SPARC && !FONTS && MAC help Small console font with Macintosh-style high-half glyphs. Some Mac @@ -54,7 +54,7 @@ config FONT_6x11 config FONT_7x14 bool "console 7x14 font (not supported by all drivers)" if FONTS - depends on FRAMEBUFFER_CONSOLE + depends on FRAMEBUFFER_CONSOLE || DRM_PANIC help Console font with characters just a bit smaller than the default. If the standard 8x16 font is a little too big for you, say Y. @@ -62,7 +62,7 @@ config FONT_7x14 config FONT_PEARL_8x8 bool "Pearl (old m68k) console 8x8 font" if FONTS - depends on FRAMEBUFFER_CONSOLE + depends on FRAMEBUFFER_CONSOLE || DRM_PANIC default y if !SPARC && !FONTS && AMIGA help Small console font with PC-style control-character and high-half @@ -70,7 +70,7 @@ config FONT_PEARL_8x8 config FONT_ACORN_8x8 bool "Acorn console 8x8 font" if FONTS - depends on FRAMEBUFFER_CONSOLE + depends on FRAMEBUFFER_CONSOLE || DRM_PANIC default y if !SPARC && !FONTS && ARM && ARCH_ACORN help Small console font with PC-style control characters and high-half @@ -90,7 +90,7 @@ config FONT_6x10 config FONT_10x18 bool "console 10x18 font (not supported by all drivers)" if FONTS - depends on FRAMEBUFFER_CONSOLE + depends on FRAMEBUFFER_CONSOLE || DRM_PANIC help This is a high resolution console font for machines with very big letters. It fits between the sun 12x22 and the normal 8x16 font. @@ -105,7 +105,7 @@ config FONT_SUN8x16 config FONT_SUN12x22 bool "Sparc console 12x22 font (not supported by all drivers)" - depends on FRAMEBUFFER_CONSOLE && (!SPARC && FONTS || SPARC) + depends on (FRAMEBUFFER_CONSOLE && (!SPARC && FONTS || SPARC)) || DRM_PANIC help This is the high resolution console font for Sun machines with very big letters (like the letters used in the SPARC PROM). If the @@ -113,7 +113,7 @@ config FONT_SUN12x22 config FONT_TER16x32 bool "Terminus 16x32 font (not supported by all drivers)" - depends on FRAMEBUFFER_CONSOLE && (!SPARC && FONTS || SPARC) + depends on (FRAMEBUFFER_CONSOLE && (!SPARC && FONTS || SPARC)) || DRM_PANIC help Terminus Font is a clean, fixed width bitmap font, designed for long (8 and more hours per day) work with computers. @@ -122,7 +122,7 @@ config FONT_TER16x32 config FONT_6x8 bool "OLED 6x8 font" if FONTS - depends on FRAMEBUFFER_CONSOLE + depends on FRAMEBUFFER_CONSOLE || DRM_PANIC help This font is useful for small displays (OLED). -- cgit v1.2.3 From a0a44d9175b349df2462089140fb7f292100bd7c Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Mon, 27 May 2024 11:01:28 +0200 Subject: mm, slab: don't wrap internal functions with alloc_hooks() The functions __kmalloc_noprof(), kmalloc_large_noprof(), kmalloc_trace_noprof() and their _node variants are all internal to the implementations of kmalloc_noprof() and kmalloc_node_noprof() and are only declared in the "public" slab.h and exported so that those implementations can be static inline and distinguish the build-time constant size variants. The only other users for some of the internal functions are slub_kunit and fortify_kunit tests which make very short-lived allocations. Therefore we can stop wrapping them with the alloc_hooks() macro. Instead add a __ prefix to all of them and a comment documenting these as internal. Also rename __kmalloc_trace() to __kmalloc_cache() which is more descriptive - it is a variant of __kmalloc() where the exact kmalloc cache has been already determined. The usage in fortify_kunit can be removed completely, as the internal functions should be tested already through kmalloc() tests in the test variant that passes non-constant allocation size. Reported-by: Kent Overstreet Cc: Suren Baghdasaryan Cc: Kees Cook Reviewed-by: Kent Overstreet Acked-by: David Rientjes Signed-off-by: Vlastimil Babka --- include/linux/slab.h | 48 ++++++++++++++++++++++++------------------------ lib/fortify_kunit.c | 5 ----- lib/slub_kunit.c | 2 +- mm/slub.c | 26 +++++++++++++------------- 4 files changed, 38 insertions(+), 43 deletions(-) (limited to 'lib') diff --git a/include/linux/slab.h b/include/linux/slab.h index 7247e217e21b..ed6bee5ec2b6 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -528,9 +528,6 @@ static_assert(PAGE_SHIFT <= 20); #include -void *__kmalloc_noprof(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); -#define __kmalloc(...) alloc_hooks(__kmalloc_noprof(__VA_ARGS__)) - /** * kmem_cache_alloc - Allocate an object * @cachep: The cache to allocate from. @@ -568,31 +565,34 @@ static __always_inline void kfree_bulk(size_t size, void **p) kmem_cache_free_bulk(NULL, size, p); } -void *__kmalloc_node_noprof(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment - __alloc_size(1); -#define __kmalloc_node(...) alloc_hooks(__kmalloc_node_noprof(__VA_ARGS__)) - void *kmem_cache_alloc_node_noprof(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment __malloc; #define kmem_cache_alloc_node(...) alloc_hooks(kmem_cache_alloc_node_noprof(__VA_ARGS__)) -void *kmalloc_trace_noprof(struct kmem_cache *s, gfp_t flags, size_t size) - __assume_kmalloc_alignment __alloc_size(3); +/* + * The following functions are not to be used directly and are intended only + * for internal use from kmalloc() and kmalloc_node() + * with the exception of kunit tests + */ + +void *__kmalloc_noprof(size_t size, gfp_t flags) + __assume_kmalloc_alignment __alloc_size(1); + +void *__kmalloc_node_noprof(size_t size, gfp_t flags, int node) + __assume_kmalloc_alignment __alloc_size(1); -void *kmalloc_node_trace_noprof(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size) __assume_kmalloc_alignment - __alloc_size(4); -#define kmalloc_trace(...) alloc_hooks(kmalloc_trace_noprof(__VA_ARGS__)) +void *__kmalloc_cache_noprof(struct kmem_cache *s, gfp_t flags, size_t size) + __assume_kmalloc_alignment __alloc_size(3); -#define kmalloc_node_trace(...) alloc_hooks(kmalloc_node_trace_noprof(__VA_ARGS__)) +void *__kmalloc_cache_node_noprof(struct kmem_cache *s, gfp_t gfpflags, + int node, size_t size) + __assume_kmalloc_alignment __alloc_size(4); -void *kmalloc_large_noprof(size_t size, gfp_t flags) __assume_page_alignment - __alloc_size(1); -#define kmalloc_large(...) alloc_hooks(kmalloc_large_noprof(__VA_ARGS__)) +void *__kmalloc_large_noprof(size_t size, gfp_t flags) + __assume_page_alignment __alloc_size(1); -void *kmalloc_large_node_noprof(size_t size, gfp_t flags, int node) __assume_page_alignment - __alloc_size(1); -#define kmalloc_large_node(...) alloc_hooks(kmalloc_large_node_noprof(__VA_ARGS__)) +void *__kmalloc_large_node_noprof(size_t size, gfp_t flags, int node) + __assume_page_alignment __alloc_size(1); /** * kmalloc - allocate kernel memory @@ -654,10 +654,10 @@ static __always_inline __alloc_size(1) void *kmalloc_noprof(size_t size, gfp_t f unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) - return kmalloc_large_noprof(size, flags); + return __kmalloc_large_noprof(size, flags); index = kmalloc_index(size); - return kmalloc_trace_noprof( + return __kmalloc_cache_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, size); } @@ -671,10 +671,10 @@ static __always_inline __alloc_size(1) void *kmalloc_node_noprof(size_t size, gf unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) - return kmalloc_large_node_noprof(size, flags, node); + return __kmalloc_large_node_noprof(size, flags, node); index = kmalloc_index(size); - return kmalloc_node_trace_noprof( + return __kmalloc_cache_node_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, node, size); } diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index 39da5b3bc649..044f409ef856 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -233,11 +233,6 @@ static void fortify_test_alloc_size_##allocator##_dynamic(struct kunit *test) \ kfree(p)); \ checker(expected_size, \ kmalloc_array_node(alloc_size, 1, gfp, NUMA_NO_NODE), \ - kfree(p)); \ - checker(expected_size, __kmalloc(alloc_size, gfp), \ - kfree(p)); \ - checker(expected_size, \ - __kmalloc_node(alloc_size, gfp, NUMA_NO_NODE), \ kfree(p)); \ \ orig = kmalloc(alloc_size, gfp); \ diff --git a/lib/slub_kunit.c b/lib/slub_kunit.c index 4ce960438806..e6667a28c014 100644 --- a/lib/slub_kunit.c +++ b/lib/slub_kunit.c @@ -140,7 +140,7 @@ static void test_kmalloc_redzone_access(struct kunit *test) { struct kmem_cache *s = test_kmem_cache_create("TestSlub_RZ_kmalloc", 32, SLAB_KMALLOC|SLAB_STORE_USER|SLAB_RED_ZONE); - u8 *p = kmalloc_trace(s, GFP_KERNEL, 18); + u8 *p = __kmalloc_cache_noprof(s, GFP_KERNEL, 18); kasan_disable_current(); diff --git a/mm/slub.c b/mm/slub.c index 0809760cf789..95e0a3332c44 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4053,7 +4053,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_node_noprof); * directly to the page allocator. We use __GFP_COMP, because we will need to * know the allocation order to free the pages properly in kfree. */ -static void *__kmalloc_large_node(size_t size, gfp_t flags, int node) +static void *___kmalloc_large_node(size_t size, gfp_t flags, int node) { struct folio *folio; void *ptr = NULL; @@ -4078,25 +4078,25 @@ static void *__kmalloc_large_node(size_t size, gfp_t flags, int node) return ptr; } -void *kmalloc_large_noprof(size_t size, gfp_t flags) +void *__kmalloc_large_noprof(size_t size, gfp_t flags) { - void *ret = __kmalloc_large_node(size, flags, NUMA_NO_NODE); + void *ret = ___kmalloc_large_node(size, flags, NUMA_NO_NODE); trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << get_order(size), flags, NUMA_NO_NODE); return ret; } -EXPORT_SYMBOL(kmalloc_large_noprof); +EXPORT_SYMBOL(__kmalloc_large_noprof); -void *kmalloc_large_node_noprof(size_t size, gfp_t flags, int node) +void *__kmalloc_large_node_noprof(size_t size, gfp_t flags, int node) { - void *ret = __kmalloc_large_node(size, flags, node); + void *ret = ___kmalloc_large_node(size, flags, node); trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << get_order(size), flags, node); return ret; } -EXPORT_SYMBOL(kmalloc_large_node_noprof); +EXPORT_SYMBOL(__kmalloc_large_node_noprof); static __always_inline void *__do_kmalloc_node(size_t size, gfp_t flags, int node, @@ -4106,7 +4106,7 @@ void *__do_kmalloc_node(size_t size, gfp_t flags, int node, void *ret; if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) { - ret = __kmalloc_large_node(size, flags, node); + ret = __kmalloc_large_node_noprof(size, flags, node); trace_kmalloc(caller, ret, size, PAGE_SIZE << get_order(size), flags, node); return ret; @@ -4142,7 +4142,7 @@ void *kmalloc_node_track_caller_noprof(size_t size, gfp_t flags, } EXPORT_SYMBOL(kmalloc_node_track_caller_noprof); -void *kmalloc_trace_noprof(struct kmem_cache *s, gfp_t gfpflags, size_t size) +void *__kmalloc_cache_noprof(struct kmem_cache *s, gfp_t gfpflags, size_t size) { void *ret = slab_alloc_node(s, NULL, gfpflags, NUMA_NO_NODE, _RET_IP_, size); @@ -4152,10 +4152,10 @@ void *kmalloc_trace_noprof(struct kmem_cache *s, gfp_t gfpflags, size_t size) ret = kasan_kmalloc(s, ret, size, gfpflags); return ret; } -EXPORT_SYMBOL(kmalloc_trace_noprof); +EXPORT_SYMBOL(__kmalloc_cache_noprof); -void *kmalloc_node_trace_noprof(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size) +void *__kmalloc_cache_node_noprof(struct kmem_cache *s, gfp_t gfpflags, + int node, size_t size) { void *ret = slab_alloc_node(s, NULL, gfpflags, node, _RET_IP_, size); @@ -4164,7 +4164,7 @@ void *kmalloc_node_trace_noprof(struct kmem_cache *s, gfp_t gfpflags, ret = kasan_kmalloc(s, ret, size, gfpflags); return ret; } -EXPORT_SYMBOL(kmalloc_node_trace_noprof); +EXPORT_SYMBOL(__kmalloc_cache_node_noprof); static noinline void free_to_partial_list( struct kmem_cache *s, struct slab *slab, -- cgit v1.2.3 From 2c7afc2a880cd4899f9dd6bfa62f10f84773148b Mon Sep 17 00:00:00 2001 From: Ivan Orlov Date: Thu, 16 May 2024 22:17:31 +0100 Subject: kunit: Cover 'assert.c' with tests There are multiple assertion formatting functions in the `assert.c` file, which are not covered with tests yet. Implement the KUnit test for these functions. The test consists of 11 test cases for the following functions: 1) 'is_literal' 2) 'is_str_literal' 3) 'kunit_assert_prologue', test case for multiple assert types 4) 'kunit_assert_print_msg' 5) 'kunit_unary_assert_format' 6) 'kunit_ptr_not_err_assert_format' 7) 'kunit_binary_assert_format' 8) 'kunit_binary_ptr_assert_format' 9) 'kunit_binary_str_assert_format' 10) 'kunit_assert_hexdump' 11) 'kunit_mem_assert_format' The test aims at maximizing the branch coverage for the assertion formatting functions. As you can see, it covers some of the static helper functions as well, so mark the static functions in `assert.c` as 'VISIBLE_IF_KUNIT' and conditionally export them with EXPORT_SYMBOL_IF_KUNIT. Add the corresponding definitions to `assert.h`. Build the assert test when CONFIG_KUNIT_TEST is enabled, similar to how it is done for the string stream test. Signed-off-by: Ivan Orlov Reviewed-by: Rae Moar Acked-by: David Gow Signed-off-by: Shuah Khan --- include/kunit/assert.h | 11 ++ lib/kunit/Makefile | 1 + lib/kunit/assert.c | 19 ++- lib/kunit/assert_test.c | 388 ++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 411 insertions(+), 8 deletions(-) create mode 100644 lib/kunit/assert_test.c (limited to 'lib') diff --git a/include/kunit/assert.h b/include/kunit/assert.h index 24c2b9fa61e8..7e7490a74b13 100644 --- a/include/kunit/assert.h +++ b/include/kunit/assert.h @@ -218,4 +218,15 @@ void kunit_mem_assert_format(const struct kunit_assert *assert, const struct va_format *message, struct string_stream *stream); +#if IS_ENABLED(CONFIG_KUNIT) +void kunit_assert_print_msg(const struct va_format *message, + struct string_stream *stream); +bool is_literal(const char *text, long long value); +bool is_str_literal(const char *text, const char *value); +void kunit_assert_hexdump(struct string_stream *stream, + const void *buf, + const void *compared_buf, + const size_t len); +#endif + #endif /* _KUNIT_ASSERT_H */ diff --git a/lib/kunit/Makefile b/lib/kunit/Makefile index 309659a32a78..900e6447c8e8 100644 --- a/lib/kunit/Makefile +++ b/lib/kunit/Makefile @@ -22,6 +22,7 @@ obj-$(CONFIG_KUNIT_TEST) += kunit-test.o # string-stream-test compiles built-in only. ifeq ($(CONFIG_KUNIT_TEST),y) obj-$(CONFIG_KUNIT_TEST) += string-stream-test.o +obj-$(CONFIG_KUNIT_TEST) += assert_test.o endif obj-$(CONFIG_KUNIT_EXAMPLE_TEST) += kunit-example-test.o diff --git a/lib/kunit/assert.c b/lib/kunit/assert.c index dd1d633d0fe2..867aa5c4bccf 100644 --- a/lib/kunit/assert.c +++ b/lib/kunit/assert.c @@ -7,6 +7,7 @@ */ #include #include +#include #include "string-stream.h" @@ -30,8 +31,9 @@ void kunit_assert_prologue(const struct kunit_loc *loc, } EXPORT_SYMBOL_GPL(kunit_assert_prologue); -static void kunit_assert_print_msg(const struct va_format *message, - struct string_stream *stream) +VISIBLE_IF_KUNIT +void kunit_assert_print_msg(const struct va_format *message, + struct string_stream *stream) { if (message->fmt) string_stream_add(stream, "\n%pV", message); @@ -89,7 +91,7 @@ void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert, EXPORT_SYMBOL_GPL(kunit_ptr_not_err_assert_format); /* Checks if `text` is a literal representing `value`, e.g. "5" and 5 */ -static bool is_literal(const char *text, long long value) +VISIBLE_IF_KUNIT bool is_literal(const char *text, long long value) { char *buffer; int len; @@ -166,7 +168,7 @@ EXPORT_SYMBOL_GPL(kunit_binary_ptr_assert_format); /* Checks if KUNIT_EXPECT_STREQ() args were string literals. * Note: `text` will have ""s where as `value` will not. */ -static bool is_str_literal(const char *text, const char *value) +VISIBLE_IF_KUNIT bool is_str_literal(const char *text, const char *value) { int len; @@ -208,10 +210,11 @@ EXPORT_SYMBOL_GPL(kunit_binary_str_assert_format); /* Adds a hexdump of a buffer to a string_stream comparing it with * a second buffer. The different bytes are marked with <>. */ -static void kunit_assert_hexdump(struct string_stream *stream, - const void *buf, - const void *compared_buf, - const size_t len) +VISIBLE_IF_KUNIT +void kunit_assert_hexdump(struct string_stream *stream, + const void *buf, + const void *compared_buf, + const size_t len) { size_t i; const u8 *buf1 = buf; diff --git a/lib/kunit/assert_test.c b/lib/kunit/assert_test.c new file mode 100644 index 000000000000..4a5967712186 --- /dev/null +++ b/lib/kunit/assert_test.c @@ -0,0 +1,388 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * KUnit test for the assertion formatting functions. + * Author: Ivan Orlov + */ +#include +#include "string-stream.h" + +#define TEST_PTR_EXPECTED_BUF_SIZE 32 +#define HEXDUMP_TEST_BUF_LEN 5 +#define ASSERT_TEST_EXPECT_CONTAIN(test, str, substr) KUNIT_EXPECT_TRUE(test, strstr(str, substr)) +#define ASSERT_TEST_EXPECT_NCONTAIN(test, str, substr) KUNIT_EXPECT_FALSE(test, strstr(str, substr)) + +static void kunit_test_is_literal(struct kunit *test) +{ + KUNIT_EXPECT_TRUE(test, is_literal("5", 5)); + KUNIT_EXPECT_TRUE(test, is_literal("0", 0)); + KUNIT_EXPECT_TRUE(test, is_literal("1234567890", 1234567890)); + KUNIT_EXPECT_TRUE(test, is_literal("-1234567890", -1234567890)); + KUNIT_EXPECT_FALSE(test, is_literal("05", 5)); + KUNIT_EXPECT_FALSE(test, is_literal("", 0)); + KUNIT_EXPECT_FALSE(test, is_literal("-0", 0)); + KUNIT_EXPECT_FALSE(test, is_literal("12#45", 1245)); +} + +static void kunit_test_is_str_literal(struct kunit *test) +{ + KUNIT_EXPECT_TRUE(test, is_str_literal("\"Hello, World!\"", "Hello, World!")); + KUNIT_EXPECT_TRUE(test, is_str_literal("\"\"", "")); + KUNIT_EXPECT_TRUE(test, is_str_literal("\"\"\"", "\"")); + KUNIT_EXPECT_FALSE(test, is_str_literal("", "")); + KUNIT_EXPECT_FALSE(test, is_str_literal("\"", "\"")); + KUNIT_EXPECT_FALSE(test, is_str_literal("\"Abacaba", "Abacaba")); + KUNIT_EXPECT_FALSE(test, is_str_literal("Abacaba\"", "Abacaba")); + KUNIT_EXPECT_FALSE(test, is_str_literal("\"Abacaba\"", "\"Abacaba\"")); +} + +KUNIT_DEFINE_ACTION_WRAPPER(kfree_wrapper, kfree, const void *); + +/* this function is used to get a "char *" string from the string stream and defer its cleanup */ +static char *get_str_from_stream(struct kunit *test, struct string_stream *stream) +{ + char *str = string_stream_get_string(stream); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, str); + kunit_add_action(test, kfree_wrapper, (void *)str); + + return str; +} + +static void kunit_test_assert_prologue(struct kunit *test) +{ + struct string_stream *stream; + char *str; + const struct kunit_loc location = { + .file = "testfile.c", + .line = 1337, + }; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + /* Test an expectation fail prologue */ + kunit_assert_prologue(&location, KUNIT_EXPECTATION, stream); + str = get_str_from_stream(test, stream); + ASSERT_TEST_EXPECT_CONTAIN(test, str, "EXPECTATION"); + ASSERT_TEST_EXPECT_CONTAIN(test, str, "testfile.c"); + ASSERT_TEST_EXPECT_CONTAIN(test, str, "1337"); + + /* Test an assertion fail prologue */ + string_stream_clear(stream); + kunit_assert_prologue(&location, KUNIT_ASSERTION, stream); + str = get_str_from_stream(test, stream); + ASSERT_TEST_EXPECT_CONTAIN(test, str, "ASSERTION"); + ASSERT_TEST_EXPECT_CONTAIN(test, str, "testfile.c"); + ASSERT_TEST_EXPECT_CONTAIN(test, str, "1337"); +} + +/* + * This function accepts an arbitrary count of parameters and generates a va_format struct, + * which can be used to validate kunit_assert_print_msg function + */ +static void verify_assert_print_msg(struct kunit *test, + struct string_stream *stream, + char *expected, const char *format, ...) +{ + va_list list; + const struct va_format vformat = { + .fmt = format, + .va = &list, + }; + + va_start(list, format); + string_stream_clear(stream); + kunit_assert_print_msg(&vformat, stream); + KUNIT_EXPECT_STREQ(test, get_str_from_stream(test, stream), expected); +} + +static void kunit_test_assert_print_msg(struct kunit *test) +{ + struct string_stream *stream; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + verify_assert_print_msg(test, stream, "\nTest", "Test"); + verify_assert_print_msg(test, stream, "\nAbacaba -123 234", "%s %d %u", + "Abacaba", -123, 234U); + verify_assert_print_msg(test, stream, "", NULL); +} + +/* + * Further code contains the tests for different assert format functions. + * This helper function accepts the assert format function, executes it and + * validates the result string from the stream by checking that all of the + * substrings exist in the output. + */ +static void validate_assert(assert_format_t format_func, struct kunit *test, + const struct kunit_assert *assert, + struct string_stream *stream, int num_checks, ...) +{ + size_t i; + va_list checks; + char *cur_substr_exp; + struct va_format message = { NULL, NULL }; + + va_start(checks, num_checks); + string_stream_clear(stream); + format_func(assert, &message, stream); + + for (i = 0; i < num_checks; i++) { + cur_substr_exp = va_arg(checks, char *); + ASSERT_TEST_EXPECT_CONTAIN(test, get_str_from_stream(test, stream), cur_substr_exp); + } +} + +static void kunit_test_unary_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct kunit_assert assert = {}; + struct kunit_unary_assert un_assert = { + .assert = assert, + .condition = "expr", + .expected_true = true, + }; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + validate_assert(kunit_unary_assert_format, test, &un_assert.assert, + stream, 2, "true", "is false"); + + un_assert.expected_true = false; + validate_assert(kunit_unary_assert_format, test, &un_assert.assert, + stream, 2, "false", "is true"); +} + +static void kunit_test_ptr_not_err_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct kunit_assert assert = {}; + struct kunit_ptr_not_err_assert not_err_assert = { + .assert = assert, + .text = "expr", + .value = NULL, + }; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + /* Value is NULL. The corresponding message should be printed out */ + validate_assert(kunit_ptr_not_err_assert_format, test, + ¬_err_assert.assert, + stream, 1, "null"); + + /* Value is not NULL, but looks like an error pointer. Error should be printed out */ + not_err_assert.value = (void *)-12; + validate_assert(kunit_ptr_not_err_assert_format, test, + ¬_err_assert.assert, stream, 2, + "error", "-12"); +} + +static void kunit_test_binary_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct kunit_assert assert = {}; + struct kunit_binary_assert_text text = { + .left_text = "1 + 2", + .operation = "==", + .right_text = "2", + }; + const struct kunit_binary_assert binary_assert = { + .assert = assert, + .text = &text, + .left_value = 3, + .right_value = 2, + }; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + /* + * Printed values should depend on the input we provide: the left text, right text, left + * value and the right value. + */ + validate_assert(kunit_binary_assert_format, test, &binary_assert.assert, + stream, 4, "1 + 2", "2", "3", "=="); + + text.right_text = "4 - 2"; + validate_assert(kunit_binary_assert_format, test, &binary_assert.assert, + stream, 3, "==", "1 + 2", "4 - 2"); + + text.left_text = "3"; + validate_assert(kunit_binary_assert_format, test, &binary_assert.assert, + stream, 4, "3", "4 - 2", "2", "=="); + + text.right_text = "2"; + validate_assert(kunit_binary_assert_format, test, &binary_assert.assert, + stream, 3, "3", "2", "=="); +} + +static void kunit_test_binary_ptr_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct kunit_assert assert = {}; + char *addr_var_a, *addr_var_b; + static const void *var_a = (void *)0xDEADBEEF; + static const void *var_b = (void *)0xBADDCAFE; + struct kunit_binary_assert_text text = { + .left_text = "var_a", + .operation = "==", + .right_text = "var_b", + }; + struct kunit_binary_ptr_assert binary_ptr_assert = { + .assert = assert, + .text = &text, + .left_value = var_a, + .right_value = var_b, + }; + + addr_var_a = kunit_kzalloc(test, TEST_PTR_EXPECTED_BUF_SIZE, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, addr_var_a); + addr_var_b = kunit_kzalloc(test, TEST_PTR_EXPECTED_BUF_SIZE, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, addr_var_b); + /* + * Print the addresses to the buffers first. + * This is necessary as we may have different count of leading zeros in the pointer + * on different architectures. + */ + snprintf(addr_var_a, TEST_PTR_EXPECTED_BUF_SIZE, "%px", var_a); + snprintf(addr_var_b, TEST_PTR_EXPECTED_BUF_SIZE, "%px", var_b); + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + validate_assert(kunit_binary_ptr_assert_format, test, &binary_ptr_assert.assert, + stream, 3, addr_var_a, addr_var_b, "=="); +} + +static void kunit_test_binary_str_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct kunit_assert assert = {}; + static const char *var_a = "abacaba"; + static const char *var_b = "kernel"; + struct kunit_binary_assert_text text = { + .left_text = "var_a", + .operation = "==", + .right_text = "var_b", + }; + struct kunit_binary_str_assert binary_str_assert = { + .assert = assert, + .text = &text, + .left_value = var_a, + .right_value = var_b, + }; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + validate_assert(kunit_binary_str_assert_format, test, + &binary_str_assert.assert, + stream, 5, "var_a", "var_b", "\"abacaba\"", + "\"kernel\"", "=="); + + text.left_text = "\"abacaba\""; + validate_assert(kunit_binary_str_assert_format, test, &binary_str_assert.assert, + stream, 4, "\"abacaba\"", "var_b", "\"kernel\"", "=="); + + text.right_text = "\"kernel\""; + validate_assert(kunit_binary_str_assert_format, test, &binary_str_assert.assert, + stream, 3, "\"abacaba\"", "\"kernel\"", "=="); +} + +static const u8 hex_testbuf1[] = { 0x26, 0x74, 0x6b, 0x9c, 0x55, + 0x45, 0x9d, 0x47, 0xd6, 0x47, + 0x2, 0x89, 0x8c, 0x81, 0x94, + 0x12, 0xfe, 0x01 }; +static const u8 hex_testbuf2[] = { 0x26, 0x74, 0x6b, 0x9c, 0x55, + 0x45, 0x9d, 0x47, 0x21, 0x47, + 0xcd, 0x89, 0x24, 0x50, 0x94, + 0x12, 0xba, 0x01 }; +static void kunit_test_assert_hexdump(struct kunit *test) +{ + struct string_stream *stream; + char *str; + size_t i; + char buf[HEXDUMP_TEST_BUF_LEN]; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + /* Check that we are getting output like for non-matching numbers. */ + kunit_assert_hexdump(stream, hex_testbuf1, hex_testbuf2, sizeof(hex_testbuf1)); + str = get_str_from_stream(test, stream); + for (i = 0; i < sizeof(hex_testbuf1); i++) { + snprintf(buf, HEXDUMP_TEST_BUF_LEN, "<%02x>", hex_testbuf1[i]); + if (hex_testbuf1[i] != hex_testbuf2[i]) + ASSERT_TEST_EXPECT_CONTAIN(test, str, buf); + } + /* We shouldn't get any numbers when comparing the buffer with itself. */ + string_stream_clear(stream); + kunit_assert_hexdump(stream, hex_testbuf1, hex_testbuf1, sizeof(hex_testbuf1)); + str = get_str_from_stream(test, stream); + ASSERT_TEST_EXPECT_NCONTAIN(test, str, "<"); + ASSERT_TEST_EXPECT_NCONTAIN(test, str, ">"); +} + +static void kunit_test_mem_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct string_stream *expected_stream; + struct kunit_assert assert = {}; + static const struct kunit_binary_assert_text text = { + .left_text = "hex_testbuf1", + .operation = "==", + .right_text = "hex_testbuf2", + }; + struct kunit_mem_assert mem_assert = { + .assert = assert, + .text = &text, + .left_value = NULL, + .right_value = hex_testbuf2, + .size = sizeof(hex_testbuf1), + }; + + expected_stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, expected_stream); + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + /* The left value is NULL */ + validate_assert(kunit_mem_assert_format, test, &mem_assert.assert, + stream, 2, "hex_testbuf1", "is not null"); + + /* The right value is NULL, the left value is not NULL */ + mem_assert.left_value = hex_testbuf1; + mem_assert.right_value = NULL; + validate_assert(kunit_mem_assert_format, test, &mem_assert.assert, + stream, 2, "hex_testbuf2", "is not null"); + + /* Both arguments are not null */ + mem_assert.left_value = hex_testbuf1; + mem_assert.right_value = hex_testbuf2; + + validate_assert(kunit_mem_assert_format, test, &mem_assert.assert, + stream, 3, "hex_testbuf1", "hex_testbuf2", "=="); +} + +static struct kunit_case assert_test_cases[] = { + KUNIT_CASE(kunit_test_is_literal), + KUNIT_CASE(kunit_test_is_str_literal), + KUNIT_CASE(kunit_test_assert_prologue), + KUNIT_CASE(kunit_test_assert_print_msg), + KUNIT_CASE(kunit_test_unary_assert_format), + KUNIT_CASE(kunit_test_ptr_not_err_assert_format), + KUNIT_CASE(kunit_test_binary_assert_format), + KUNIT_CASE(kunit_test_binary_ptr_assert_format), + KUNIT_CASE(kunit_test_binary_str_assert_format), + KUNIT_CASE(kunit_test_assert_hexdump), + KUNIT_CASE(kunit_test_mem_assert_format), + {} +}; + +static struct kunit_suite assert_test_suite = { + .name = "kunit-assert", + .test_cases = assert_test_cases, +}; + +kunit_test_suites(&assert_test_suite); -- cgit v1.2.3 From ec1249d3278183d419276b9a7fe73591cd3dd505 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 09:28:43 -0700 Subject: test_bpf: Add missing MODULE_DESCRIPTION() make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_bpf.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Signed-off-by: Jeff Johnson Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240531-md-lib-test_bpf-v1-1-868e4bd2f9ed@quicinc.com --- lib/test_bpf.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 207ff87194db..ce5716c3999a 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -15706,4 +15706,5 @@ static void __exit test_bpf_exit(void) module_init(test_bpf_init); module_exit(test_bpf_exit); +MODULE_DESCRIPTION("Testsuite for BPF interpreter and BPF JIT compiler"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 8031042cc531cc855926f76b0ea20db2da48f804 Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Fri, 31 May 2024 16:18:01 +0100 Subject: list: test: remove unused struct 'klist_test_struct' 'klist_test_struct' has been unused since the original commit 57b4f760f94d ("list: test: Test the klist structure"). Remove it. Signed-off-by: Dr. David Alan Gilbert Reviewed-by: David Gow Signed-off-by: Shuah Khan --- lib/list-test.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'lib') diff --git a/lib/list-test.c b/lib/list-test.c index 0cc27de9cec8..383ee0ad582e 100644 --- a/lib/list-test.c +++ b/lib/list-test.c @@ -1201,12 +1201,6 @@ static struct kunit_suite hlist_test_module = { }; -struct klist_test_struct { - int data; - struct klist klist; - struct klist_node klist_node; -}; - static int node_count; static struct klist_node *last_node; -- cgit v1.2.3 From 5a71c0d1180e76d223a8266799d1ee4ba3a8e697 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 15:01:14 -0700 Subject: dyndbg: add missing MODULE_DESCRIPTION() macro make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_dynamic_debug.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Signed-off-by: Jeff Johnson Link: https://lore.kernel.org/r/20240531-md-test_dynamic_debug-v1-1-2194b477f55e@quicinc.com Signed-off-by: Greg Kroah-Hartman --- lib/test_dynamic_debug.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/test_dynamic_debug.c b/lib/test_dynamic_debug.c index 8dd250ad022b..77c2a669b6af 100644 --- a/lib/test_dynamic_debug.c +++ b/lib/test_dynamic_debug.c @@ -162,4 +162,5 @@ module_init(test_dynamic_debug_init); module_exit(test_dynamic_debug_exit); MODULE_AUTHOR("Jim Cromie "); +MODULE_DESCRIPTION("Kernel module for testing dynamic_debug"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 0d618e39763e0e2b88586cd7d40ce8419735412f Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 22:21:38 -0700 Subject: lib/math: add missing MODULE_DESCRIPTION() macros make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/math/prime_numbers.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/math/rational-test.o Add the missing invocations of the MODULE_DESCRIPTION() macro. Signed-off-by: Jeff Johnson Link: https://lore.kernel.org/r/20240531-md-lib-math-v1-1-11a3bec51ebb@quicinc.com Signed-off-by: Greg Kroah-Hartman --- lib/math/prime_numbers.c | 1 + lib/math/rational-test.c | 1 + 2 files changed, 2 insertions(+) (limited to 'lib') diff --git a/lib/math/prime_numbers.c b/lib/math/prime_numbers.c index d3b64b10da1c..9a17ee9af93a 100644 --- a/lib/math/prime_numbers.c +++ b/lib/math/prime_numbers.c @@ -311,4 +311,5 @@ module_exit(primes_exit); module_param_named(selftest, selftest_max, ulong, 0400); MODULE_AUTHOR("Intel Corporation"); +MODULE_DESCRIPTION("Prime number library"); MODULE_LICENSE("GPL"); diff --git a/lib/math/rational-test.c b/lib/math/rational-test.c index 01611ddff420..47486a95f088 100644 --- a/lib/math/rational-test.c +++ b/lib/math/rational-test.c @@ -53,4 +53,5 @@ static struct kunit_suite rational_test_suite = { kunit_test_suites(&rational_test_suite); +MODULE_DESCRIPTION("Rational fractions unit test"); MODULE_LICENSE("GPL v2"); -- cgit v1.2.3 From 0ee14725471cea66e03e3cd4f4c582d759de502c Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Thu, 6 Jun 2024 15:46:09 +0100 Subject: mm/util: Swap kmemdup_array() arguments GCC 14.1 complains about the argument usage of kmemdup_array(): drivers/soc/tegra/fuse/fuse-tegra.c:130:65: error: 'kmemdup_array' sizes specified with 'sizeof' in the earlier argument and not in the later argument [-Werror=calloc-transposed-args] 130 | fuse->lookups = kmemdup_array(fuse->soc->lookups, sizeof(*fuse->lookups), | ^ drivers/soc/tegra/fuse/fuse-tegra.c:130:65: note: earlier argument should specify number of elements, later size of each element The annotation introduced by commit 7d78a7773355 ("string: Add additional __realloc_size() annotations for "dup" helpers") lets the compiler think that kmemdup_array() follows the same format as calloc(), with the number of elements preceding the size of one element. So we could simply swap the arguments to __realloc_size() to get rid of that warning, but it seems cleaner to instead have kmemdup_array() follow the same format as krealloc_array(), memdup_array_user(), calloc() etc. Fixes: 7d78a7773355 ("string: Add additional __realloc_size() annotations for "dup" helpers") Signed-off-by: Jean-Philippe Brucker Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20240606144608.97817-2-jean-philippe@linaro.org Signed-off-by: Kees Cook --- drivers/soc/tegra/fuse/fuse-tegra.c | 4 ++-- include/linux/string.h | 2 +- lib/fortify_kunit.c | 2 +- mm/util.c | 4 ++-- 4 files changed, 6 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/drivers/soc/tegra/fuse/fuse-tegra.c b/drivers/soc/tegra/fuse/fuse-tegra.c index b6bfd6729df3..d27667283846 100644 --- a/drivers/soc/tegra/fuse/fuse-tegra.c +++ b/drivers/soc/tegra/fuse/fuse-tegra.c @@ -127,8 +127,8 @@ static void tegra_fuse_print_sku_info(struct tegra_sku_info *tegra_sku_info) static int tegra_fuse_add_lookups(struct tegra_fuse *fuse) { - fuse->lookups = kmemdup_array(fuse->soc->lookups, sizeof(*fuse->lookups), - fuse->soc->num_lookups, GFP_KERNEL); + fuse->lookups = kmemdup_array(fuse->soc->lookups, fuse->soc->num_lookups, + sizeof(*fuse->lookups), GFP_KERNEL); if (!fuse->lookups) return -ENOMEM; diff --git a/include/linux/string.h b/include/linux/string.h index 60168aa2af07..9edace076ddb 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -289,7 +289,7 @@ extern void *kmemdup_noprof(const void *src, size_t len, gfp_t gfp) __realloc_si 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 count, size_t element_size, gfp_t gfp) __realloc_size(2, 3); /* lib/argv_split.c */ diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index f9cc467334ce..e17d520f532c 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -374,7 +374,7 @@ static const char * const test_strs[] = { 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), \ + checker(len, kmemdup_array(test_strs[i], 1, len, gfp), \ kfree(p)); \ checker(len, kmemdup(test_strs[i], len, gfp), \ kfree(p)); \ diff --git a/mm/util.c b/mm/util.c index c9e519e6811f..6682097372ef 100644 --- a/mm/util.c +++ b/mm/util.c @@ -139,14 +139,14 @@ EXPORT_SYMBOL(kmemdup_noprof); * kmemdup_array - duplicate a given array. * * @src: array to duplicate. - * @element_size: size of each element of array. * @count: number of elements to duplicate from array. + * @element_size: size of each element of array. * @gfp: GFP mask to use. * * Return: duplicated array of @src or %NULL in case of error, * result is physically contiguous. Use kfree() to free. */ -void *kmemdup_array(const void *src, size_t element_size, size_t count, gfp_t gfp) +void *kmemdup_array(const void *src, size_t count, size_t element_size, gfp_t gfp) { return kmemdup(src, size_mul(element_size, count), gfp); } -- cgit v1.2.3 From 645211db1394f0607935dd43d907af7a12631907 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Tue, 28 May 2024 16:49:23 -0700 Subject: crypto: lib - add missing MODULE_DESCRIPTION() macros Fix the allmodconfig 'make W=1' warnings: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/crypto/libchacha.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/crypto/libarc4.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/crypto/libdes.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/crypto/libpoly1305.o Signed-off-by: Jeff Johnson Signed-off-by: Herbert Xu --- lib/crypto/arc4.c | 1 + lib/crypto/des.c | 1 + lib/crypto/libchacha.c | 1 + lib/crypto/poly1305.c | 1 + 4 files changed, 4 insertions(+) (limited to 'lib') diff --git a/lib/crypto/arc4.c b/lib/crypto/arc4.c index c2020f19c652..838812d18216 100644 --- a/lib/crypto/arc4.c +++ b/lib/crypto/arc4.c @@ -71,4 +71,5 @@ void arc4_crypt(struct arc4_ctx *ctx, u8 *out, const u8 *in, unsigned int len) } EXPORT_SYMBOL(arc4_crypt); +MODULE_DESCRIPTION("ARC4 Cipher Algorithm"); MODULE_LICENSE("GPL"); diff --git a/lib/crypto/des.c b/lib/crypto/des.c index ef5bb8822aba..9518658b97cf 100644 --- a/lib/crypto/des.c +++ b/lib/crypto/des.c @@ -899,4 +899,5 @@ void des3_ede_decrypt(const struct des3_ede_ctx *dctx, u8 *dst, const u8 *src) } EXPORT_SYMBOL_GPL(des3_ede_decrypt); +MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms"); MODULE_LICENSE("GPL"); diff --git a/lib/crypto/libchacha.c b/lib/crypto/libchacha.c index dabc3accae05..cc1be0496eb9 100644 --- a/lib/crypto/libchacha.c +++ b/lib/crypto/libchacha.c @@ -32,4 +32,5 @@ void chacha_crypt_generic(u32 *state, u8 *dst, const u8 *src, } EXPORT_SYMBOL(chacha_crypt_generic); +MODULE_DESCRIPTION("ChaCha stream cipher (RFC7539)"); MODULE_LICENSE("GPL"); diff --git a/lib/crypto/poly1305.c b/lib/crypto/poly1305.c index 26d87fc3823e..5d8378d23e95 100644 --- a/lib/crypto/poly1305.c +++ b/lib/crypto/poly1305.c @@ -76,3 +76,4 @@ EXPORT_SYMBOL_GPL(poly1305_final_generic); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Martin Willi "); +MODULE_DESCRIPTION("Poly1305 authenticator algorithm, RFC7539"); -- cgit v1.2.3 From a5217468214c228b89da37291de604cd756914ab Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Sat, 1 Jun 2024 10:19:11 -0700 Subject: kunit: add missing MODULE_DESCRIPTION() macros to core modules make allmodconfig && make W=1 C=1 reports in lib/kunit: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/kunit/kunit.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/kunit/kunit-test.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/kunit/kunit-example-test.o Add the missing invocations of the MODULE_DESCRIPTION() macro. Signed-off-by: Jeff Johnson Reviewed-by: Rae Moar Reviewed-by: David Gow Signed-off-by: Shuah Khan --- lib/kunit/kunit-example-test.c | 1 + lib/kunit/kunit-test.c | 1 + lib/kunit/test.c | 1 + 3 files changed, 3 insertions(+) (limited to 'lib') diff --git a/lib/kunit/kunit-example-test.c b/lib/kunit/kunit-example-test.c index 798924f7cc86..3056d6bc705d 100644 --- a/lib/kunit/kunit-example-test.c +++ b/lib/kunit/kunit-example-test.c @@ -374,4 +374,5 @@ static struct kunit_suite example_init_test_suite = { */ kunit_test_init_section_suites(&example_init_test_suite); +MODULE_DESCRIPTION("Example KUnit test suite"); MODULE_LICENSE("GPL v2"); diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c index e3412e0ca399..37e02be1e710 100644 --- a/lib/kunit/kunit-test.c +++ b/lib/kunit/kunit-test.c @@ -871,4 +871,5 @@ kunit_test_suites(&kunit_try_catch_test_suite, &kunit_resource_test_suite, &kunit_current_test_suite, &kunit_device_test_suite, &kunit_fault_test_suite); +MODULE_DESCRIPTION("KUnit test for core test infrastructure"); MODULE_LICENSE("GPL v2"); diff --git a/lib/kunit/test.c b/lib/kunit/test.c index b8514dbb337c..e8b1b52a19ab 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -938,4 +938,5 @@ static void __exit kunit_exit(void) } module_exit(kunit_exit); +MODULE_DESCRIPTION("Base unit test (KUnit) API"); MODULE_LICENSE("GPL v2"); -- cgit v1.2.3 From 425ae3ab5a1fa744a00680f059cf1accaaaecb28 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 16:58:42 -0700 Subject: list: test: add the missing MODULE_DESCRIPTION() macro make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/list-test.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Signed-off-by: Jeff Johnson Reviewed-by: David Gow Signed-off-by: Shuah Khan --- lib/list-test.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/list-test.c b/lib/list-test.c index 383ee0ad582e..37cbc33e9fdb 100644 --- a/lib/list-test.c +++ b/lib/list-test.c @@ -1493,4 +1493,5 @@ static struct kunit_suite klist_test_module = { kunit_test_suites(&list_test_module, &hlist_test_module, &klist_test_module); +MODULE_DESCRIPTION("KUnit test for the Kernel Linked-list structures"); MODULE_LICENSE("GPL v2"); -- cgit v1.2.3 From c1e156ae50ee520baf4e560b1284677ddfcea974 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 6 Jun 2024 16:49:38 +0200 Subject: lib: objagg: Fix spelling Fixes: 0a020d416d0a ("lib: introduce initial implementation of object aggregation manager") Signed-off-by: Ido Schimmel Reviewed-by: Amit Cohen Tested-by: Alexander Zubkov Signed-off-by: Petr Machata Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- lib/objagg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/objagg.c b/lib/objagg.c index 1e248629ed64..955538c90223 100644 --- a/lib/objagg.c +++ b/lib/objagg.c @@ -421,7 +421,7 @@ static struct objagg_obj *__objagg_obj_get(struct objagg *objagg, void *obj) * * There are 3 main options this function wraps: * 1) The object according to "obj" already exist. In that case - * the reference counter is incrementes and the object is returned. + * the reference counter is incremented and the object is returned. * 2) The object does not exist, but it can be aggregated within * another object. In that case, user ops->delta_create() is called * to obtain delta data and a new object is created with returned -- cgit v1.2.3 From 2aad28ec4543f4c3154f904bcd817e649ffb0ba6 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 6 Jun 2024 16:49:39 +0200 Subject: lib: test_objagg: Fix spelling Fixes: 0a020d416d0a ("lib: introduce initial implementation of object aggregation manager") Signed-off-by: Ido Schimmel Reviewed-by: Amit Cohen Tested-by: Alexander Zubkov Signed-off-by: Petr Machata Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- lib/test_objagg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/test_objagg.c b/lib/test_objagg.c index c0c957c50635..d34df4306b87 100644 --- a/lib/test_objagg.c +++ b/lib/test_objagg.c @@ -60,7 +60,7 @@ static struct objagg_obj *world_obj_get(struct world *world, if (!world->key_refs[key_id_index(key_id)]) { world->objagg_objs[key_id_index(key_id)] = objagg_obj; } else if (world->objagg_objs[key_id_index(key_id)] != objagg_obj) { - pr_err("Key %u: God another object for the same key.\n", + pr_err("Key %u: Got another object for the same key.\n", key_id); err = -EINVAL; goto err_key_id_check; -- cgit v1.2.3 From b4a3a89fffcdf09702b1f161b914e52abca1894d Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 6 Jun 2024 16:49:41 +0200 Subject: lib: objagg: Fix general protection fault The library supports aggregation of objects into other objects only if the parent object does not have a parent itself. That is, nesting is not supported. Aggregation happens in two cases: Without and with hints, where hints are a pre-computed recommendation on how to aggregate the provided objects. Nesting is not possible in the first case due to a check that prevents it, but in the second case there is no check because the assumption is that nesting cannot happen when creating objects based on hints. The violation of this assumption leads to various warnings and eventually to a general protection fault [1]. Before fixing the root cause, error out when nesting happens and warn. [1] general protection fault, probably for non-canonical address 0xdead000000000d90: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 1083 Comm: kworker/1:9 Tainted: G W 6.9.0-rc6-custom-gd9b4f1cca7fb #7 Hardware name: Mellanox Technologies Ltd. MSN3700/VMOD0005, BIOS 5.11 01/06/2019 Workqueue: mlxsw_core mlxsw_sp_acl_tcam_vregion_rehash_work RIP: 0010:mlxsw_sp_acl_erp_bf_insert+0x25/0x80 [...] Call Trace: mlxsw_sp_acl_atcam_entry_add+0x256/0x3c0 mlxsw_sp_acl_tcam_entry_create+0x5e/0xa0 mlxsw_sp_acl_tcam_vchunk_migrate_one+0x16b/0x270 mlxsw_sp_acl_tcam_vregion_rehash_work+0xbe/0x510 process_one_work+0x151/0x370 worker_thread+0x2cb/0x3e0 kthread+0xd0/0x100 ret_from_fork+0x34/0x50 ret_from_fork_asm+0x1a/0x30 Fixes: 9069a3817d82 ("lib: objagg: implement optimization hints assembly and use hints for object creation") Reported-by: Alexander Zubkov Signed-off-by: Ido Schimmel Reviewed-by: Amit Cohen Tested-by: Alexander Zubkov Signed-off-by: Petr Machata Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- lib/objagg.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'lib') diff --git a/lib/objagg.c b/lib/objagg.c index 955538c90223..0f99ea5f5371 100644 --- a/lib/objagg.c +++ b/lib/objagg.c @@ -167,6 +167,9 @@ static int objagg_obj_parent_assign(struct objagg *objagg, { void *delta_priv; + if (WARN_ON(!objagg_obj_is_root(parent))) + return -EINVAL; + delta_priv = objagg->ops->delta_create(objagg->priv, parent->obj, objagg_obj->obj); if (IS_ERR(delta_priv)) -- cgit v1.2.3 From 97d833ceb27dc19f8777d63f90be4a27b5daeedf Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 6 Jun 2024 16:49:42 +0200 Subject: mlxsw: spectrum_acl_erp: Fix object nesting warning ACLs in Spectrum-2 and newer ASICs can reside in the algorithmic TCAM (A-TCAM) or in the ordinary circuit TCAM (C-TCAM). The former can contain more ACLs (i.e., tc filters), but the number of masks in each region (i.e., tc chain) is limited. In order to mitigate the effects of the above limitation, the device allows filters to share a single mask if their masks only differ in up to 8 consecutive bits. For example, dst_ip/25 can be represented using dst_ip/24 with a delta of 1 bit. The C-TCAM does not have a limit on the number of masks being used (and therefore does not support mask aggregation), but can contain a limited number of filters. The driver uses the "objagg" library to perform the mask aggregation by passing it objects that consist of the filter's mask and whether the filter is to be inserted into the A-TCAM or the C-TCAM since filters in different TCAMs cannot share a mask. The set of created objects is dependent on the insertion order of the filters and is not necessarily optimal. Therefore, the driver will periodically ask the library to compute a more optimal set ("hints") by looking at all the existing objects. When the library asks the driver whether two objects can be aggregated the driver only compares the provided masks and ignores the A-TCAM / C-TCAM indication. This is the right thing to do since the goal is to move as many filters as possible to the A-TCAM. The driver also forbids two identical masks from being aggregated since this can only happen if one was intentionally put in the C-TCAM to avoid a conflict in the A-TCAM. The above can result in the following set of hints: H1: {mask X, A-TCAM} -> H2: {mask Y, A-TCAM} // X is Y + delta H3: {mask Y, C-TCAM} -> H4: {mask Z, A-TCAM} // Y is Z + delta After getting the hints from the library the driver will start migrating filters from one region to another while consulting the computed hints and instructing the device to perform a lookup in both regions during the transition. Assuming a filter with mask X is being migrated into the A-TCAM in the new region, the hints lookup will return H1. Since H2 is the parent of H1, the library will try to find the object associated with it and create it if necessary in which case another hints lookup (recursive) will be performed. This hints lookup for {mask Y, A-TCAM} will either return H2 or H3 since the driver passes the library an object comparison function that ignores the A-TCAM / C-TCAM indication. This can eventually lead to nested objects which are not supported by the library [1]. Fix by removing the object comparison function from both the driver and the library as the driver was the only user. That way the lookup will only return exact matches. I do not have a reliable reproducer that can reproduce the issue in a timely manner, but before the fix the issue would reproduce in several minutes and with the fix it does not reproduce in over an hour. Note that the current usefulness of the hints is limited because they include the C-TCAM indication and represent aggregation that cannot actually happen. This will be addressed in net-next. [1] WARNING: CPU: 0 PID: 153 at lib/objagg.c:170 objagg_obj_parent_assign+0xb5/0xd0 Modules linked in: CPU: 0 PID: 153 Comm: kworker/0:18 Not tainted 6.9.0-rc6-custom-g70fbc2c1c38b #42 Hardware name: Mellanox Technologies Ltd. MSN3700C/VMOD0008, BIOS 5.11 10/10/2018 Workqueue: mlxsw_core mlxsw_sp_acl_tcam_vregion_rehash_work RIP: 0010:objagg_obj_parent_assign+0xb5/0xd0 [...] Call Trace: __objagg_obj_get+0x2bb/0x580 objagg_obj_get+0xe/0x80 mlxsw_sp_acl_erp_mask_get+0xb5/0xf0 mlxsw_sp_acl_atcam_entry_add+0xe8/0x3c0 mlxsw_sp_acl_tcam_entry_create+0x5e/0xa0 mlxsw_sp_acl_tcam_vchunk_migrate_one+0x16b/0x270 mlxsw_sp_acl_tcam_vregion_rehash_work+0xbe/0x510 process_one_work+0x151/0x370 Fixes: 9069a3817d82 ("lib: objagg: implement optimization hints assembly and use hints for object creation") Signed-off-by: Ido Schimmel Reviewed-by: Amit Cohen Tested-by: Alexander Zubkov Signed-off-by: Petr Machata Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 13 ------------- include/linux/objagg.h | 1 - lib/objagg.c | 15 --------------- 3 files changed, 29 deletions(-) (limited to 'lib') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c index d231f4d2888b..9eee229303cc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c @@ -1217,18 +1217,6 @@ static bool mlxsw_sp_acl_erp_delta_check(void *priv, const void *parent_obj, return err ? false : true; } -static int mlxsw_sp_acl_erp_hints_obj_cmp(const void *obj1, const void *obj2) -{ - const struct mlxsw_sp_acl_erp_key *key1 = obj1; - const struct mlxsw_sp_acl_erp_key *key2 = obj2; - - /* For hints purposes, two objects are considered equal - * in case the masks are the same. Does not matter what - * the "ctcam" value is. - */ - return memcmp(key1->mask, key2->mask, sizeof(key1->mask)); -} - static void *mlxsw_sp_acl_erp_delta_create(void *priv, void *parent_obj, void *obj) { @@ -1308,7 +1296,6 @@ static void mlxsw_sp_acl_erp_root_destroy(void *priv, void *root_priv) static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = { .obj_size = sizeof(struct mlxsw_sp_acl_erp_key), .delta_check = mlxsw_sp_acl_erp_delta_check, - .hints_obj_cmp = mlxsw_sp_acl_erp_hints_obj_cmp, .delta_create = mlxsw_sp_acl_erp_delta_create, .delta_destroy = mlxsw_sp_acl_erp_delta_destroy, .root_create = mlxsw_sp_acl_erp_root_create, diff --git a/include/linux/objagg.h b/include/linux/objagg.h index 78021777df46..6df5b887dc54 100644 --- a/include/linux/objagg.h +++ b/include/linux/objagg.h @@ -8,7 +8,6 @@ struct objagg_ops { size_t obj_size; bool (*delta_check)(void *priv, const void *parent_obj, const void *obj); - int (*hints_obj_cmp)(const void *obj1, const void *obj2); void * (*delta_create)(void *priv, void *parent_obj, void *obj); void (*delta_destroy)(void *priv, void *delta_priv); void * (*root_create)(void *priv, void *obj, unsigned int root_id); diff --git a/lib/objagg.c b/lib/objagg.c index 0f99ea5f5371..363e43e849ac 100644 --- a/lib/objagg.c +++ b/lib/objagg.c @@ -906,20 +906,6 @@ static const struct objagg_opt_algo *objagg_opt_algos[] = { [OBJAGG_OPT_ALGO_SIMPLE_GREEDY] = &objagg_opt_simple_greedy, }; -static int objagg_hints_obj_cmp(struct rhashtable_compare_arg *arg, - const void *obj) -{ - struct rhashtable *ht = arg->ht; - struct objagg_hints *objagg_hints = - container_of(ht, struct objagg_hints, node_ht); - const struct objagg_ops *ops = objagg_hints->ops; - const char *ptr = obj; - - ptr += ht->p.key_offset; - return ops->hints_obj_cmp ? ops->hints_obj_cmp(ptr, arg->key) : - memcmp(ptr, arg->key, ht->p.key_len); -} - /** * objagg_hints_get - obtains hints instance * @objagg: objagg instance @@ -958,7 +944,6 @@ struct objagg_hints *objagg_hints_get(struct objagg *objagg, offsetof(struct objagg_hints_node, obj); objagg_hints->ht_params.head_offset = offsetof(struct objagg_hints_node, ht_node); - objagg_hints->ht_params.obj_cmpfn = objagg_hints_obj_cmp; err = rhashtable_init(&objagg_hints->node_ht, &objagg_hints->ht_params); if (err) -- cgit v1.2.3 From 9dd5134c61580ba4c219296c37e08ff64c109a74 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 10 Jun 2024 11:23:05 -0700 Subject: kunit/overflow: Adjust for __counted_by with DEFINE_RAW_FLEX() When a flexible array structure has a __counted_by annotation, its use with DEFINE_RAW_FLEX() will result in the count being zero-initialized. This is expected since one doesn't want to use RAW with a counted_by struct. Adjust the tests to check for the condition and for compiler support. Reported-by: Christian Schrefl Closes: https://lore.kernel.org/all/0bfc6b38-8bc5-4971-b6fb-dc642a73fbfe@gmail.com/ Suggested-by: Nathan Chancellor Reviewed-by: Nathan Chancellor Link: https://lore.kernel.org/r/20240610182301.work.272-kees@kernel.org Tested-by: Christian Schrefl Reviewed-by: Christian Schrefl Signed-off-by: Kees Cook --- lib/overflow_kunit.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/lib/overflow_kunit.c b/lib/overflow_kunit.c index 4ef31b0bb74d..d305b0c054bb 100644 --- a/lib/overflow_kunit.c +++ b/lib/overflow_kunit.c @@ -1178,14 +1178,28 @@ struct foo { s16 array[] __counted_by(counter); }; +struct bar { + int a; + u32 counter; + s16 array[]; +}; + static void DEFINE_FLEX_test(struct kunit *test) { - DEFINE_RAW_FLEX(struct foo, two, array, 2); + /* Using _RAW_ on a __counted_by struct will initialize "counter" to zero */ + DEFINE_RAW_FLEX(struct foo, two_but_zero, array, 2); +#if __has_attribute(__counted_by__) + int expected_raw_size = sizeof(struct foo); +#else + int expected_raw_size = sizeof(struct foo) + 2 * sizeof(s16); +#endif + /* Without annotation, it will always be on-stack size. */ + DEFINE_RAW_FLEX(struct bar, two, array, 2); DEFINE_FLEX(struct foo, eight, array, counter, 8); DEFINE_FLEX(struct foo, empty, array, counter, 0); - KUNIT_EXPECT_EQ(test, __struct_size(two), - sizeof(struct foo) + sizeof(s16) + sizeof(s16)); + KUNIT_EXPECT_EQ(test, __struct_size(two_but_zero), expected_raw_size); + KUNIT_EXPECT_EQ(test, __struct_size(two), sizeof(struct bar) + 2 * sizeof(s16)); KUNIT_EXPECT_EQ(test, __struct_size(eight), 24); KUNIT_EXPECT_EQ(test, __struct_size(empty), sizeof(struct foo)); } -- cgit v1.2.3 From dd6e9894b451e7c85cceb8e9dc5432679a70e7dc Mon Sep 17 00:00:00 2001 From: Zijun Hu Date: Thu, 30 May 2024 21:14:37 +0800 Subject: kobject_uevent: Fix OOB access within zap_modalias_env() zap_modalias_env() wrongly calculates size of memory block to move, so will cause OOB memory access issue if variable MODALIAS is not the last one within its @env parameter, fixed by correcting size to memmove. Fixes: 9b3fa47d4a76 ("kobject: fix suppressing modalias in uevents delivered over netlink") Cc: stable@vger.kernel.org Signed-off-by: Zijun Hu Reviewed-by: Lk Sii Link: https://lore.kernel.org/r/1717074877-11352-1-git-send-email-quic_zijuhu@quicinc.com Signed-off-by: Greg Kroah-Hartman --- lib/kobject_uevent.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 03b427e2707e..b7f2fa08d9c8 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -433,8 +433,23 @@ static void zap_modalias_env(struct kobj_uevent_env *env) len = strlen(env->envp[i]) + 1; if (i != env->envp_idx - 1) { + /* @env->envp[] contains pointers to @env->buf[] + * with @env->buflen chars, and we are removing + * variable MODALIAS here pointed by @env->envp[i] + * with length @len as shown below: + * + * 0 @env->buf[] @env->buflen + * --------------------------------------------- + * ^ ^ ^ ^ + * | |-> @len <-| target block | + * @env->envp[0] @env->envp[i] @env->envp[i + 1] + * + * so the "target block" indicated above is moved + * backward by @len, and its right size is + * @env->buflen - (@env->envp[i + 1] - @env->envp[0]). + */ memmove(env->envp[i], env->envp[i + 1], - env->buflen - len); + env->buflen - (env->envp[i + 1] - env->envp[0])); for (j = i; j < env->envp_idx - 1; j++) env->envp[j] = env->envp[j + 1] - len; -- cgit v1.2.3 From a930fde94ae5fbcb178c1330268f15f2c893c507 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 19:42:25 -0700 Subject: vsprintf: add missing MODULE_DESCRIPTION() macro make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_printf.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_scanf.o Add the missing invocations of the MODULE_DESCRIPTION() macro. Signed-off-by: Jeff Johnson Link: https://lore.kernel.org/r/20240531-md-vsprintf-v1-1-d8bc7e21539a@quicinc.com Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek --- lib/test_printf.c | 1 + lib/test_scanf.c | 1 + 2 files changed, 2 insertions(+) (limited to 'lib') diff --git a/lib/test_printf.c b/lib/test_printf.c index 69b6a5e177f2..965cb6f28527 100644 --- a/lib/test_printf.c +++ b/lib/test_printf.c @@ -824,4 +824,5 @@ static void __init selftest(void) KSTM_MODULE_LOADERS(test_printf); MODULE_AUTHOR("Rasmus Villemoes "); +MODULE_DESCRIPTION("Test cases for printf facility"); MODULE_LICENSE("GPL"); diff --git a/lib/test_scanf.c b/lib/test_scanf.c index a2707af2951a..7257b1768545 100644 --- a/lib/test_scanf.c +++ b/lib/test_scanf.c @@ -810,4 +810,5 @@ static void __init selftest(void) KSTM_MODULE_LOADERS(test_scanf); MODULE_AUTHOR("Richard Fitzgerald "); +MODULE_DESCRIPTION("Test cases for sscanf facility"); MODULE_LICENSE("GPL v2"); -- cgit v1.2.3 From e2a6c472de7a5e5a1455a9fff1cfc55a1dd888af Mon Sep 17 00:00:00 2001 From: Joel Granados Date: Tue, 4 Jun 2024 08:29:20 +0200 Subject: mm profiling: Remove superfluous sentinel element from ctl_table This commit is part of a greater effort to remove all empty elements at the end of the ctl_table arrays (sentinels) which will reduce the overall build time size of the kernel and run time memory bloat by ~64 bytes per sentinel (further information Link : https://lore.kernel.org/all/ZO5Yx5JFogGi%2FcBo@bombadil.infradead.org/) Removed sentinel from memory_allocation_profiling_sysctls Signed-off-by: Joel Granados --- lib/alloc_tag.c | 1 - 1 file changed, 1 deletion(-) (limited to 'lib') diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 11ed973ac359..7293cd54d1b1 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -238,7 +238,6 @@ static struct ctl_table memory_allocation_profiling_sysctls[] = { #endif .proc_handler = proc_do_static_key, }, - { } }; static int __init alloc_tag_init(void) -- cgit v1.2.3 From 51104c19d8570eb23208e08eac0e9ae09ced1c15 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jun 2024 12:59:18 -0700 Subject: kunit: test: Add vm_mmap() allocation resource manager For tests that need to allocate using vm_mmap() (e.g. usercopy and execve), provide the interface to have the allocation tracked by KUnit itself. This requires bringing up a placeholder userspace mm. This combines my earlier attempt at this with Mark Rutland's version[1]. Normally alloc_mm() and arch_pick_mmap_layout() aren't exported for modules, so export these only for KUnit testing. Link: https://lore.kernel.org/lkml/20230321122514.1743889-2-mark.rutland@arm.com/ [1] Co-developed-by: Mark Rutland Signed-off-by: Mark Rutland Reviewed-by: David Gow Signed-off-by: Kees Cook Signed-off-by: Shuah Khan --- include/kunit/test.h | 17 ++++++++ kernel/fork.c | 3 ++ lib/kunit/Makefile | 1 + lib/kunit/user_alloc.c | 113 +++++++++++++++++++++++++++++++++++++++++++++++++ mm/util.c | 3 ++ 5 files changed, 137 insertions(+) create mode 100644 lib/kunit/user_alloc.c (limited to 'lib') diff --git a/include/kunit/test.h b/include/kunit/test.h index e32b4cb7afa2..ec61cad6b71d 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -480,6 +480,23 @@ static inline void *kunit_kcalloc(struct kunit *test, size_t n, size_t size, gfp return kunit_kmalloc_array(test, n, size, gfp | __GFP_ZERO); } +/** + * kunit_vm_mmap() - Allocate KUnit-tracked vm_mmap() area + * @test: The test context object. + * @file: struct file pointer to map from, if any + * @addr: desired address, if any + * @len: how many bytes to allocate + * @prot: mmap PROT_* bits + * @flag: mmap flags + * @offset: offset into @file to start mapping from. + * + * See vm_mmap() for more information. + */ +unsigned long kunit_vm_mmap(struct kunit *test, struct file *file, + unsigned long addr, unsigned long len, + unsigned long prot, unsigned long flag, + unsigned long offset); + void kunit_cleanup(struct kunit *test); void __printf(2, 3) kunit_log_append(struct string_stream *log, const char *fmt, ...); diff --git a/kernel/fork.c b/kernel/fork.c index 99076dbe27d8..cea203197136 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -115,6 +115,8 @@ #define CREATE_TRACE_POINTS #include +#include + /* * Minimum number of threads to boot the kernel */ @@ -1334,6 +1336,7 @@ struct mm_struct *mm_alloc(void) memset(mm, 0, sizeof(*mm)); return mm_init(mm, current, current_user_ns()); } +EXPORT_SYMBOL_IF_KUNIT(mm_alloc); static inline void __mmput(struct mm_struct *mm) { diff --git a/lib/kunit/Makefile b/lib/kunit/Makefile index 900e6447c8e8..30f6bbf04a4a 100644 --- a/lib/kunit/Makefile +++ b/lib/kunit/Makefile @@ -2,6 +2,7 @@ obj-$(CONFIG_KUNIT) += kunit.o kunit-objs += test.o \ resource.o \ + user_alloc.o \ static_stub.o \ string-stream.o \ assert.o \ diff --git a/lib/kunit/user_alloc.c b/lib/kunit/user_alloc.c new file mode 100644 index 000000000000..76d3d1345ed7 --- /dev/null +++ b/lib/kunit/user_alloc.c @@ -0,0 +1,113 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KUnit userspace memory allocation resource management. + */ +#include +#include +#include +#include + +struct kunit_vm_mmap_resource { + unsigned long addr; + size_t size; +}; + +/* vm_mmap() arguments */ +struct kunit_vm_mmap_params { + struct file *file; + unsigned long addr; + unsigned long len; + unsigned long prot; + unsigned long flag; + unsigned long offset; +}; + +/* Create and attach a new mm if it doesn't already exist. */ +static int kunit_attach_mm(void) +{ + struct mm_struct *mm; + + if (current->mm) + return 0; + + mm = mm_alloc(); + if (!mm) + return -ENOMEM; + + /* Define the task size. */ + mm->task_size = TASK_SIZE; + + /* Make sure we can allocate new VMAs. */ + arch_pick_mmap_layout(mm, ¤t->signal->rlim[RLIMIT_STACK]); + + /* Attach the mm. It will be cleaned up when the process dies. */ + kthread_use_mm(mm); + + return 0; +} + +static int kunit_vm_mmap_init(struct kunit_resource *res, void *context) +{ + struct kunit_vm_mmap_params *p = context; + struct kunit_vm_mmap_resource vres; + int ret; + + ret = kunit_attach_mm(); + if (ret) + return ret; + + vres.size = p->len; + vres.addr = vm_mmap(p->file, p->addr, p->len, p->prot, p->flag, p->offset); + if (!vres.addr) + return -ENOMEM; + res->data = kmemdup(&vres, sizeof(vres), GFP_KERNEL); + if (!res->data) { + vm_munmap(vres.addr, vres.size); + return -ENOMEM; + } + + return 0; +} + +static void kunit_vm_mmap_free(struct kunit_resource *res) +{ + struct kunit_vm_mmap_resource *vres = res->data; + + /* + * Since this is executed from the test monitoring process, + * the test's mm has already been torn down. We don't need + * to run vm_munmap(vres->addr, vres->size), only clean up + * the vres. + */ + + kfree(vres); + res->data = NULL; +} + +unsigned long kunit_vm_mmap(struct kunit *test, struct file *file, + unsigned long addr, unsigned long len, + unsigned long prot, unsigned long flag, + unsigned long offset) +{ + struct kunit_vm_mmap_params params = { + .file = file, + .addr = addr, + .len = len, + .prot = prot, + .flag = flag, + .offset = offset, + }; + struct kunit_vm_mmap_resource *vres; + + vres = kunit_alloc_resource(test, + kunit_vm_mmap_init, + kunit_vm_mmap_free, + GFP_KERNEL, + ¶ms); + if (vres) + return vres->addr; + return 0; +} +EXPORT_SYMBOL_GPL(kunit_vm_mmap); + +MODULE_IMPORT_NS(EXPORTED_FOR_KUNIT_TESTING); diff --git a/mm/util.c b/mm/util.c index c9e519e6811f..df37c47d9374 100644 --- a/mm/util.c +++ b/mm/util.c @@ -26,6 +26,8 @@ #include +#include + #include "internal.h" #include "swap.h" @@ -482,6 +484,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) clear_bit(MMF_TOPDOWN, &mm->flags); } #endif +EXPORT_SYMBOL_IF_KUNIT(arch_pick_mmap_layout); /** * __account_locked_vm - account locked pages to an mm's locked_vm -- cgit v1.2.3 From cf6219ee889fb304cf8192c707ad280d93baafc7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jun 2024 12:59:19 -0700 Subject: usercopy: Convert test_user_copy to KUnit test Convert the runtime tests of hardened usercopy to standard KUnit tests. Additionally disable usercopy_test_invalid() for systems with separate address spaces (or no MMU) since it's not sensible to test for address confusion there (e.g. m68k). Co-developed-by: Vitor Massaru Iha Signed-off-by: Vitor Massaru Iha Link: https://lore.kernel.org/r/20200721174654.72132-1-vitor@massaru.org Tested-by: Ivan Orlov Reviewed-by: David Gow Signed-off-by: Kees Cook Signed-off-by: Shuah Khan --- MAINTAINERS | 1 + lib/Kconfig.debug | 21 ++-- lib/Makefile | 2 +- lib/test_user_copy.c | 331 --------------------------------------------------- lib/usercopy_kunit.c | 329 ++++++++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 340 insertions(+), 344 deletions(-) delete mode 100644 lib/test_user_copy.c create mode 100644 lib/usercopy_kunit.c (limited to 'lib') diff --git a/MAINTAINERS b/MAINTAINERS index d6c90161c7bf..9a4883f78853 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11962,6 +11962,7 @@ F: arch/*/configs/hardening.config F: include/linux/overflow.h F: include/linux/randomize_kstack.h F: kernel/configs/hardening.config +F: lib/usercopy_kunit.c F: mm/usercopy.c K: \b(add|choose)_random_kstack_offset\b K: \b__check_(object_size|heap_object)\b diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 59b6765d86b8..561e346f5cb0 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2505,18 +2505,6 @@ config TEST_VMALLOC If unsure, say N. -config TEST_USER_COPY - tristate "Test user/kernel boundary protections" - depends on m - help - This builds the "test_user_copy" module that runs sanity checks - on the copy_to/from_user infrastructure, making sure basic - user/kernel boundary testing is working. If it fails to load, - a regression has been detected in the user/kernel memory boundary - protections. - - If unsure, say N. - config TEST_BPF tristate "Test BPF filter functionality" depends on m && NET @@ -2814,6 +2802,15 @@ config SIPHASH_KUNIT_TEST This is intended to help people writing architecture-specific optimized versions. If unsure, say N. +config USERCOPY_KUNIT_TEST + tristate "KUnit Test for user/kernel boundary protections" + depends on KUNIT + default KUNIT_ALL_TESTS + help + This builds the "usercopy_kunit" module that runs sanity checks + on the copy_to/from_user infrastructure, making sure basic + user/kernel boundary testing is working. + config TEST_UDELAY tristate "udelay test driver" help diff --git a/lib/Makefile b/lib/Makefile index 3b1769045651..fae5cc67b95a 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -78,7 +78,6 @@ obj-$(CONFIG_TEST_LKM) += test_module.o obj-$(CONFIG_TEST_VMALLOC) += test_vmalloc.o obj-$(CONFIG_TEST_RHASHTABLE) += test_rhashtable.o obj-$(CONFIG_TEST_SORT) += test_sort.o -obj-$(CONFIG_TEST_USER_COPY) += test_user_copy.o obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_keys.o obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_key_base.o obj-$(CONFIG_TEST_DYNAMIC_DEBUG) += test_dynamic_debug.o @@ -388,6 +387,7 @@ 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-$(CONFIG_SIPHASH_KUNIT_TEST) += siphash_kunit.o +obj-$(CONFIG_USERCOPY_KUNIT_TEST) += usercopy_kunit.o obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c deleted file mode 100644 index 5ff04d8fe971..000000000000 --- a/lib/test_user_copy.c +++ /dev/null @@ -1,331 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Kernel module for testing copy_to/from_user infrastructure. - * - * Copyright 2013 Google Inc. All Rights Reserved - * - * Authors: - * Kees Cook - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include -#include - -/* - * Several 32-bit architectures support 64-bit {get,put}_user() calls. - * As there doesn't appear to be anything that can safely determine - * their capability at compile-time, we just have to opt-out certain archs. - */ -#if BITS_PER_LONG == 64 || (!(defined(CONFIG_ARM) && !defined(MMU)) && \ - !defined(CONFIG_M68K) && \ - !defined(CONFIG_MICROBLAZE) && \ - !defined(CONFIG_NIOS2) && \ - !defined(CONFIG_PPC32) && \ - !defined(CONFIG_SUPERH)) -# define TEST_U64 -#endif - -#define test(condition, msg, ...) \ -({ \ - int cond = (condition); \ - if (cond) \ - pr_warn("[%d] " msg "\n", __LINE__, ##__VA_ARGS__); \ - cond; \ -}) - -static bool is_zeroed(void *from, size_t size) -{ - return memchr_inv(from, 0x0, size) == NULL; -} - -static int test_check_nonzero_user(char *kmem, char __user *umem, size_t size) -{ - int ret = 0; - size_t start, end, i, zero_start, zero_end; - - if (test(size < 2 * PAGE_SIZE, "buffer too small")) - return -EINVAL; - - /* - * We want to cross a page boundary to exercise the code more - * effectively. We also don't want to make the size we scan too large, - * otherwise the test can take a long time and cause soft lockups. So - * scan a 1024 byte region across the page boundary. - */ - size = 1024; - start = PAGE_SIZE - (size / 2); - - kmem += start; - umem += start; - - zero_start = size / 4; - zero_end = size - zero_start; - - /* - * We conduct a series of check_nonzero_user() tests on a block of - * memory with the following byte-pattern (trying every possible - * [start,end] pair): - * - * [ 00 ff 00 ff ... 00 00 00 00 ... ff 00 ff 00 ] - * - * And we verify that check_nonzero_user() acts identically to - * memchr_inv(). - */ - - memset(kmem, 0x0, size); - for (i = 1; i < zero_start; i += 2) - kmem[i] = 0xff; - for (i = zero_end; i < size; i += 2) - kmem[i] = 0xff; - - ret |= test(copy_to_user(umem, kmem, size), - "legitimate copy_to_user failed"); - - for (start = 0; start <= size; start++) { - for (end = start; end <= size; end++) { - size_t len = end - start; - int retval = check_zeroed_user(umem + start, len); - int expected = is_zeroed(kmem + start, len); - - ret |= test(retval != expected, - "check_nonzero_user(=%d) != memchr_inv(=%d) mismatch (start=%zu, end=%zu)", - retval, expected, start, end); - } - } - - return ret; -} - -static int test_copy_struct_from_user(char *kmem, char __user *umem, - size_t size) -{ - int ret = 0; - char *umem_src = NULL, *expected = NULL; - size_t ksize, usize; - - umem_src = kmalloc(size, GFP_KERNEL); - ret = test(umem_src == NULL, "kmalloc failed"); - if (ret) - goto out_free; - - expected = kmalloc(size, GFP_KERNEL); - ret = test(expected == NULL, "kmalloc failed"); - if (ret) - goto out_free; - - /* Fill umem with a fixed byte pattern. */ - memset(umem_src, 0x3e, size); - ret |= test(copy_to_user(umem, umem_src, size), - "legitimate copy_to_user failed"); - - /* Check basic case -- (usize == ksize). */ - ksize = size; - usize = size; - - memcpy(expected, umem_src, ksize); - - memset(kmem, 0x0, size); - ret |= test(copy_struct_from_user(kmem, ksize, umem, usize), - "copy_struct_from_user(usize == ksize) failed"); - ret |= test(memcmp(kmem, expected, ksize), - "copy_struct_from_user(usize == ksize) gives unexpected copy"); - - /* Old userspace case -- (usize < ksize). */ - ksize = size; - usize = size / 2; - - memcpy(expected, umem_src, usize); - memset(expected + usize, 0x0, ksize - usize); - - memset(kmem, 0x0, size); - ret |= test(copy_struct_from_user(kmem, ksize, umem, usize), - "copy_struct_from_user(usize < ksize) failed"); - ret |= test(memcmp(kmem, expected, ksize), - "copy_struct_from_user(usize < ksize) gives unexpected copy"); - - /* New userspace (-E2BIG) case -- (usize > ksize). */ - ksize = size / 2; - usize = size; - - memset(kmem, 0x0, size); - ret |= test(copy_struct_from_user(kmem, ksize, umem, usize) != -E2BIG, - "copy_struct_from_user(usize > ksize) didn't give E2BIG"); - - /* New userspace (success) case -- (usize > ksize). */ - ksize = size / 2; - usize = size; - - memcpy(expected, umem_src, ksize); - ret |= test(clear_user(umem + ksize, usize - ksize), - "legitimate clear_user failed"); - - memset(kmem, 0x0, size); - ret |= test(copy_struct_from_user(kmem, ksize, umem, usize), - "copy_struct_from_user(usize > ksize) failed"); - ret |= test(memcmp(kmem, expected, ksize), - "copy_struct_from_user(usize > ksize) gives unexpected copy"); - -out_free: - kfree(expected); - kfree(umem_src); - return ret; -} - -static int __init test_user_copy_init(void) -{ - int ret = 0; - char *kmem; - char __user *usermem; - char *bad_usermem; - unsigned long user_addr; - u8 val_u8; - u16 val_u16; - u32 val_u32; -#ifdef TEST_U64 - u64 val_u64; -#endif - - kmem = kmalloc(PAGE_SIZE * 2, GFP_KERNEL); - if (!kmem) - return -ENOMEM; - - user_addr = vm_mmap(NULL, 0, PAGE_SIZE * 2, - PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_ANONYMOUS | MAP_PRIVATE, 0); - if (user_addr >= (unsigned long)(TASK_SIZE)) { - pr_warn("Failed to allocate user memory\n"); - kfree(kmem); - return -ENOMEM; - } - - usermem = (char __user *)user_addr; - bad_usermem = (char *)user_addr; - - /* - * Legitimate usage: none of these copies should fail. - */ - memset(kmem, 0x3a, PAGE_SIZE * 2); - ret |= test(copy_to_user(usermem, kmem, PAGE_SIZE), - "legitimate copy_to_user failed"); - memset(kmem, 0x0, PAGE_SIZE); - ret |= test(copy_from_user(kmem, usermem, PAGE_SIZE), - "legitimate copy_from_user failed"); - ret |= test(memcmp(kmem, kmem + PAGE_SIZE, PAGE_SIZE), - "legitimate usercopy failed to copy data"); - -#define test_legit(size, check) \ - do { \ - val_##size = check; \ - ret |= test(put_user(val_##size, (size __user *)usermem), \ - "legitimate put_user (" #size ") failed"); \ - val_##size = 0; \ - ret |= test(get_user(val_##size, (size __user *)usermem), \ - "legitimate get_user (" #size ") failed"); \ - ret |= test(val_##size != check, \ - "legitimate get_user (" #size ") failed to do copy"); \ - if (val_##size != check) { \ - pr_info("0x%llx != 0x%llx\n", \ - (unsigned long long)val_##size, \ - (unsigned long long)check); \ - } \ - } while (0) - - test_legit(u8, 0x5a); - test_legit(u16, 0x5a5b); - test_legit(u32, 0x5a5b5c5d); -#ifdef TEST_U64 - test_legit(u64, 0x5a5b5c5d6a6b6c6d); -#endif -#undef test_legit - - /* Test usage of check_nonzero_user(). */ - ret |= test_check_nonzero_user(kmem, usermem, 2 * PAGE_SIZE); - /* Test usage of copy_struct_from_user(). */ - ret |= test_copy_struct_from_user(kmem, usermem, 2 * PAGE_SIZE); - - /* - * Invalid usage: none of these copies should succeed. - */ - - /* Prepare kernel memory with check values. */ - memset(kmem, 0x5a, PAGE_SIZE); - memset(kmem + PAGE_SIZE, 0, PAGE_SIZE); - - /* Reject kernel-to-kernel copies through copy_from_user(). */ - ret |= test(!copy_from_user(kmem, (char __user *)(kmem + PAGE_SIZE), - PAGE_SIZE), - "illegal all-kernel copy_from_user passed"); - - /* Destination half of buffer should have been zeroed. */ - ret |= test(memcmp(kmem + PAGE_SIZE, kmem, PAGE_SIZE), - "zeroing failure for illegal all-kernel copy_from_user"); - -#if 0 - /* - * When running with SMAP/PAN/etc, this will Oops the kernel - * due to the zeroing of userspace memory on failure. This needs - * to be tested in LKDTM instead, since this test module does not - * expect to explode. - */ - ret |= test(!copy_from_user(bad_usermem, (char __user *)kmem, - PAGE_SIZE), - "illegal reversed copy_from_user passed"); -#endif - ret |= test(!copy_to_user((char __user *)kmem, kmem + PAGE_SIZE, - PAGE_SIZE), - "illegal all-kernel copy_to_user passed"); - ret |= test(!copy_to_user((char __user *)kmem, bad_usermem, - PAGE_SIZE), - "illegal reversed copy_to_user passed"); - -#define test_illegal(size, check) \ - do { \ - val_##size = (check); \ - ret |= test(!get_user(val_##size, (size __user *)kmem), \ - "illegal get_user (" #size ") passed"); \ - ret |= test(val_##size != (size)0, \ - "zeroing failure for illegal get_user (" #size ")"); \ - if (val_##size != (size)0) { \ - pr_info("0x%llx != 0\n", \ - (unsigned long long)val_##size); \ - } \ - ret |= test(!put_user(val_##size, (size __user *)kmem), \ - "illegal put_user (" #size ") passed"); \ - } while (0) - - test_illegal(u8, 0x5a); - test_illegal(u16, 0x5a5b); - test_illegal(u32, 0x5a5b5c5d); -#ifdef TEST_U64 - test_illegal(u64, 0x5a5b5c5d6a6b6c6d); -#endif -#undef test_illegal - - vm_munmap(user_addr, PAGE_SIZE * 2); - kfree(kmem); - - if (ret == 0) { - pr_info("tests passed.\n"); - return 0; - } - - return -EINVAL; -} - -module_init(test_user_copy_init); - -static void __exit test_user_copy_exit(void) -{ - pr_info("unloaded.\n"); -} - -module_exit(test_user_copy_exit); - -MODULE_AUTHOR("Kees Cook "); -MODULE_LICENSE("GPL"); diff --git a/lib/usercopy_kunit.c b/lib/usercopy_kunit.c new file mode 100644 index 000000000000..45f1e558c464 --- /dev/null +++ b/lib/usercopy_kunit.c @@ -0,0 +1,329 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Kernel module for testing copy_to/from_user infrastructure. + * + * Copyright 2013 Google Inc. All Rights Reserved + * + * Authors: + * Kees Cook + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include + +/* + * Several 32-bit architectures support 64-bit {get,put}_user() calls. + * As there doesn't appear to be anything that can safely determine + * their capability at compile-time, we just have to opt-out certain archs. + */ +#if BITS_PER_LONG == 64 || (!(defined(CONFIG_ARM) && !defined(MMU)) && \ + !defined(CONFIG_M68K) && \ + !defined(CONFIG_MICROBLAZE) && \ + !defined(CONFIG_NIOS2) && \ + !defined(CONFIG_PPC32) && \ + !defined(CONFIG_SUPERH)) +# define TEST_U64 +#endif + +struct usercopy_test_priv { + char *kmem; + char __user *umem; + size_t size; +}; + +static bool is_zeroed(void *from, size_t size) +{ + return memchr_inv(from, 0x0, size) == NULL; +} + +/* Test usage of check_nonzero_user(). */ +static void usercopy_test_check_nonzero_user(struct kunit *test) +{ + size_t start, end, i, zero_start, zero_end; + struct usercopy_test_priv *priv = test->priv; + char __user *umem = priv->umem; + char *kmem = priv->kmem; + size_t size = priv->size; + + KUNIT_ASSERT_GE_MSG(test, size, 2 * PAGE_SIZE, "buffer too small"); + + /* + * We want to cross a page boundary to exercise the code more + * effectively. We also don't want to make the size we scan too large, + * otherwise the test can take a long time and cause soft lockups. So + * scan a 1024 byte region across the page boundary. + */ + size = 1024; + start = PAGE_SIZE - (size / 2); + + kmem += start; + umem += start; + + zero_start = size / 4; + zero_end = size - zero_start; + + /* + * We conduct a series of check_nonzero_user() tests on a block of + * memory with the following byte-pattern (trying every possible + * [start,end] pair): + * + * [ 00 ff 00 ff ... 00 00 00 00 ... ff 00 ff 00 ] + * + * And we verify that check_nonzero_user() acts identically to + * memchr_inv(). + */ + + memset(kmem, 0x0, size); + for (i = 1; i < zero_start; i += 2) + kmem[i] = 0xff; + for (i = zero_end; i < size; i += 2) + kmem[i] = 0xff; + + KUNIT_EXPECT_EQ_MSG(test, copy_to_user(umem, kmem, size), 0, + "legitimate copy_to_user failed"); + + for (start = 0; start <= size; start++) { + for (end = start; end <= size; end++) { + size_t len = end - start; + int retval = check_zeroed_user(umem + start, len); + int expected = is_zeroed(kmem + start, len); + + KUNIT_ASSERT_EQ_MSG(test, retval, expected, + "check_nonzero_user(=%d) != memchr_inv(=%d) mismatch (start=%zu, end=%zu)", + retval, expected, start, end); + } + } +} + +/* Test usage of copy_struct_from_user(). */ +static void usercopy_test_copy_struct_from_user(struct kunit *test) +{ + char *umem_src = NULL, *expected = NULL; + struct usercopy_test_priv *priv = test->priv; + char __user *umem = priv->umem; + char *kmem = priv->kmem; + size_t size = priv->size; + size_t ksize, usize; + + umem_src = kunit_kmalloc(test, size, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, umem_src); + + expected = kunit_kmalloc(test, size, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, expected); + + /* Fill umem with a fixed byte pattern. */ + memset(umem_src, 0x3e, size); + KUNIT_ASSERT_EQ_MSG(test, copy_to_user(umem, umem_src, size), 0, + "legitimate copy_to_user failed"); + + /* Check basic case -- (usize == ksize). */ + ksize = size; + usize = size; + + memcpy(expected, umem_src, ksize); + + memset(kmem, 0x0, size); + KUNIT_EXPECT_EQ_MSG(test, copy_struct_from_user(kmem, ksize, umem, usize), 0, + "copy_struct_from_user(usize == ksize) failed"); + KUNIT_EXPECT_MEMEQ_MSG(test, kmem, expected, ksize, + "copy_struct_from_user(usize == ksize) gives unexpected copy"); + + /* Old userspace case -- (usize < ksize). */ + ksize = size; + usize = size / 2; + + memcpy(expected, umem_src, usize); + memset(expected + usize, 0x0, ksize - usize); + + memset(kmem, 0x0, size); + KUNIT_EXPECT_EQ_MSG(test, copy_struct_from_user(kmem, ksize, umem, usize), 0, + "copy_struct_from_user(usize < ksize) failed"); + KUNIT_EXPECT_MEMEQ_MSG(test, kmem, expected, ksize, + "copy_struct_from_user(usize < ksize) gives unexpected copy"); + + /* New userspace (-E2BIG) case -- (usize > ksize). */ + ksize = size / 2; + usize = size; + + memset(kmem, 0x0, size); + KUNIT_EXPECT_EQ_MSG(test, copy_struct_from_user(kmem, ksize, umem, usize), -E2BIG, + "copy_struct_from_user(usize > ksize) didn't give E2BIG"); + + /* New userspace (success) case -- (usize > ksize). */ + ksize = size / 2; + usize = size; + + memcpy(expected, umem_src, ksize); + KUNIT_EXPECT_EQ_MSG(test, clear_user(umem + ksize, usize - ksize), 0, + "legitimate clear_user failed"); + + memset(kmem, 0x0, size); + KUNIT_EXPECT_EQ_MSG(test, copy_struct_from_user(kmem, ksize, umem, usize), 0, + "copy_struct_from_user(usize > ksize) failed"); + KUNIT_EXPECT_MEMEQ_MSG(test, kmem, expected, ksize, + "copy_struct_from_user(usize > ksize) gives unexpected copy"); +} + +/* + * Legitimate usage: none of these copies should fail. + */ +static void usercopy_test_valid(struct kunit *test) +{ + struct usercopy_test_priv *priv = test->priv; + char __user *usermem = priv->umem; + char *kmem = priv->kmem; + + memset(kmem, 0x3a, PAGE_SIZE * 2); + KUNIT_EXPECT_EQ_MSG(test, 0, copy_to_user(usermem, kmem, PAGE_SIZE), + "legitimate copy_to_user failed"); + memset(kmem, 0x0, PAGE_SIZE); + KUNIT_EXPECT_EQ_MSG(test, 0, copy_from_user(kmem, usermem, PAGE_SIZE), + "legitimate copy_from_user failed"); + KUNIT_EXPECT_MEMEQ_MSG(test, kmem, kmem + PAGE_SIZE, PAGE_SIZE, + "legitimate usercopy failed to copy data"); + +#define test_legit(size, check) \ + do { \ + size val_##size = (check); \ + KUNIT_EXPECT_EQ_MSG(test, 0, \ + put_user(val_##size, (size __user *)usermem), \ + "legitimate put_user (" #size ") failed"); \ + val_##size = 0; \ + KUNIT_EXPECT_EQ_MSG(test, 0, \ + get_user(val_##size, (size __user *)usermem), \ + "legitimate get_user (" #size ") failed"); \ + KUNIT_EXPECT_EQ_MSG(test, val_##size, check, \ + "legitimate get_user (" #size ") failed to do copy"); \ + } while (0) + + test_legit(u8, 0x5a); + test_legit(u16, 0x5a5b); + test_legit(u32, 0x5a5b5c5d); +#ifdef TEST_U64 + test_legit(u64, 0x5a5b5c5d6a6b6c6d); +#endif +#undef test_legit +} + +/* + * Invalid usage: none of these copies should succeed. + */ +static void usercopy_test_invalid(struct kunit *test) +{ + struct usercopy_test_priv *priv = test->priv; + char __user *usermem = priv->umem; + char *bad_usermem = (char *)usermem; + char *kmem = priv->kmem; + u64 *kmem_u64 = (u64 *)kmem; + + if (IS_ENABLED(CONFIG_ALTERNATE_USER_ADDRESS_SPACE) || + !IS_ENABLED(CONFIG_MMU)) { + kunit_skip(test, "Testing for kernel/userspace address confusion is only sensible on architectures with a shared address space"); + return; + } + + /* Prepare kernel memory with check values. */ + memset(kmem, 0x5a, PAGE_SIZE); + memset(kmem + PAGE_SIZE, 0, PAGE_SIZE); + + /* Reject kernel-to-kernel copies through copy_from_user(). */ + KUNIT_EXPECT_NE_MSG(test, copy_from_user(kmem, (char __user *)(kmem + PAGE_SIZE), + PAGE_SIZE), 0, + "illegal all-kernel copy_from_user passed"); + + /* Destination half of buffer should have been zeroed. */ + KUNIT_EXPECT_MEMEQ_MSG(test, kmem + PAGE_SIZE, kmem, PAGE_SIZE, + "zeroing failure for illegal all-kernel copy_from_user"); + +#if 0 + /* + * When running with SMAP/PAN/etc, this will Oops the kernel + * due to the zeroing of userspace memory on failure. This needs + * to be tested in LKDTM instead, since this test module does not + * expect to explode. + */ + KUNIT_EXPECT_NE_MSG(test, copy_from_user(bad_usermem, (char __user *)kmem, + PAGE_SIZE), 0, + "illegal reversed copy_from_user passed"); +#endif + KUNIT_EXPECT_NE_MSG(test, copy_to_user((char __user *)kmem, kmem + PAGE_SIZE, + PAGE_SIZE), 0, + "illegal all-kernel copy_to_user passed"); + + KUNIT_EXPECT_NE_MSG(test, copy_to_user((char __user *)kmem, bad_usermem, + PAGE_SIZE), 0, + "illegal reversed copy_to_user passed"); + +#define test_illegal(size, check) \ + do { \ + size val_##size = (check); \ + /* get_user() */ \ + KUNIT_EXPECT_NE_MSG(test, get_user(val_##size, (size __user *)kmem), 0, \ + "illegal get_user (" #size ") passed"); \ + KUNIT_EXPECT_EQ_MSG(test, val_##size, 0, \ + "zeroing failure for illegal get_user (" #size ")"); \ + /* put_user() */ \ + *kmem_u64 = 0xF09FA4AFF09FA4AF; \ + KUNIT_EXPECT_NE_MSG(test, put_user(val_##size, (size __user *)kmem), 0, \ + "illegal put_user (" #size ") passed"); \ + KUNIT_EXPECT_EQ_MSG(test, *kmem_u64, 0xF09FA4AFF09FA4AF, \ + "illegal put_user (" #size ") wrote to kernel memory!"); \ + } while (0) + + test_illegal(u8, 0x5a); + test_illegal(u16, 0x5a5b); + test_illegal(u32, 0x5a5b5c5d); +#ifdef TEST_U64 + test_illegal(u64, 0x5a5b5c5d6a6b6c6d); +#endif +#undef test_illegal +} + +static int usercopy_test_init(struct kunit *test) +{ + struct usercopy_test_priv *priv; + unsigned long user_addr; + + priv = kunit_kzalloc(test, sizeof(*priv), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, priv); + test->priv = priv; + priv->size = PAGE_SIZE * 2; + + priv->kmem = kunit_kmalloc(test, priv->size, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, priv->kmem); + + user_addr = kunit_vm_mmap(test, NULL, 0, priv->size, + PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_ANONYMOUS | MAP_PRIVATE, 0); + KUNIT_ASSERT_NE_MSG(test, user_addr, 0, + "Could not create userspace mm"); + KUNIT_ASSERT_LT_MSG(test, user_addr, (unsigned long)TASK_SIZE, + "Failed to allocate user memory"); + priv->umem = (char __user *)user_addr; + + return 0; +} + +static struct kunit_case usercopy_test_cases[] = { + KUNIT_CASE(usercopy_test_valid), + KUNIT_CASE(usercopy_test_invalid), + KUNIT_CASE(usercopy_test_check_nonzero_user), + KUNIT_CASE(usercopy_test_copy_struct_from_user), + {} +}; + +static struct kunit_suite usercopy_test_suite = { + .name = "usercopy", + .init = usercopy_test_init, + .test_cases = usercopy_test_cases, +}; + +kunit_test_suites(&usercopy_test_suite); +MODULE_AUTHOR("Kees Cook "); +MODULE_LICENSE("GPL"); -- cgit v1.2.3 From c944bf60c16a65ae812a59fd1b66f6c9e18c91c9 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Sat, 1 Jun 2024 16:38:31 -0700 Subject: lib/alloc_tag: do not register sysctl interface when CONFIG_SYSCTL=n Memory allocation profiling is trying to register sysctl interface even when CONFIG_SYSCTL=n, resulting in proc_do_static_key() being undefined. Prevent that by skipping sysctl registration for such configurations. Link: https://lkml.kernel.org/r/20240601233831.617124-1-surenb@google.com Fixes: 22d407b164ff ("lib: add allocation tagging support for memory allocation profiling") Signed-off-by: Suren Baghdasaryan Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202405280616.wcOGWJEj-lkp@intel.com/ Acked-by: Vlastimil Babka Cc: Kent Overstreet Cc: Kees Cook Cc: Pasha Tatashin Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- lib/alloc_tag.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 11ed973ac359..c347b8b72d78 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -227,6 +227,7 @@ struct page_ext_operations page_alloc_tagging_ops = { }; EXPORT_SYMBOL(page_alloc_tagging_ops); +#ifdef CONFIG_SYSCTL static struct ctl_table memory_allocation_profiling_sysctls[] = { { .procname = "mem_profiling", @@ -241,6 +242,17 @@ static struct ctl_table memory_allocation_profiling_sysctls[] = { { } }; +static void __init sysctl_init(void) +{ + if (!mem_profiling_support) + memory_allocation_profiling_sysctls[0].mode = 0444; + + register_sysctl_init("vm", memory_allocation_profiling_sysctls); +} +#else /* CONFIG_SYSCTL */ +static inline void sysctl_init(void) {} +#endif /* CONFIG_SYSCTL */ + static int __init alloc_tag_init(void) { const struct codetag_type_desc desc = { @@ -253,9 +265,7 @@ 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); + sysctl_init(); procfs_init(); return 0; -- cgit v1.2.3 From 5d272dd1b3430bb31fa30042490fa081512424e4 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 18 Jun 2024 09:00:04 -0700 Subject: cpumask: limit FORCE_NR_CPUS to just the UP case Hardcoding the number of CPUs at compile time does improve code generation, but if you get it wrong the result will be confusion. We already limited this earlier to only "experts" (see commit fe5759d5bfda "cpumask: limit visibility of FORCE_NR_CPUS"), but with distro kernel configs often having EXPERT enabled, that turns out to not be much of a limit. To quote the philosophers at Disney: "Everyone can be an expert. And when everyone's an expert, no one will be". There's a runtime warning if you then set nr_cpus to anything but the forced number, but apparently that can be ignored too [1] and by then it's pretty much too late anyway. If we had some real way to limit this to "embedded only", maybe it would be worth it, but let's see if anybody even notices that the option is gone. We need to simplify kernel configuration anyway. Link: https://lore.kernel.org/all/20240618105036.208a8860@rorschach.local.home/ [1] Reported-by: Steven Rostedt Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Paul McKenney Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Yury Norov Signed-off-by: Linus Torvalds --- lib/Kconfig | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'lib') diff --git a/lib/Kconfig b/lib/Kconfig index d33a268bc256..b0a76dff5c18 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -539,13 +539,7 @@ config CPUMASK_OFFSTACK stack overflow. config FORCE_NR_CPUS - bool "Set number of CPUs at compile time" - depends on SMP && EXPERT && !COMPILE_TEST - help - Say Yes if you have NR_CPUS set to an actual number of possible - CPUs in your system, not to a default value. This forces the core - code to rely on compile-time value and optimize kernel routines - better. + def_bool !SMP config CPU_RMAP bool -- cgit v1.2.3 From e334771d83ec14f755a554394162198a955e3faa Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 09:03:11 -0700 Subject: lib: bitmap: add missing MODULE_DESCRIPTION() macros make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/find_bit_benchmark.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/cpumask_kunit.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_bitmap.o Add the missing invocations of the MODULE_DESCRIPTION() macro. Signed-off-by: Jeff Johnson Signed-off-by: Yury Norov --- lib/cpumask_kunit.c | 1 + lib/find_bit_benchmark.c | 1 + lib/test_bitmap.c | 1 + 3 files changed, 3 insertions(+) (limited to 'lib') diff --git a/lib/cpumask_kunit.c b/lib/cpumask_kunit.c index a105e6369efc..6b62a6bdd50e 100644 --- a/lib/cpumask_kunit.c +++ b/lib/cpumask_kunit.c @@ -152,4 +152,5 @@ static struct kunit_suite test_cpumask_suite = { }; kunit_test_suite(test_cpumask_suite); +MODULE_DESCRIPTION("KUnit tests for cpumask"); MODULE_LICENSE("GPL"); diff --git a/lib/find_bit_benchmark.c b/lib/find_bit_benchmark.c index d3fb09e6eff1..402e160e7186 100644 --- a/lib/find_bit_benchmark.c +++ b/lib/find_bit_benchmark.c @@ -194,4 +194,5 @@ static int __init find_bit_test(void) } module_init(find_bit_test); +MODULE_DESCRIPTION("Test for find_*_bit functions"); MODULE_LICENSE("GPL"); diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 6dfb8d46a4ff..65a75d58ed9e 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -1486,4 +1486,5 @@ static void __init selftest(void) KSTM_MODULE_LOADERS(test_bitmap); MODULE_AUTHOR("david decotigny "); +MODULE_DESCRIPTION("Test cases for bitmap API"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 2003e483a81cc235e29f77da3f6b256cb4b348e7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 19 Jun 2024 13:31:05 -0700 Subject: fortify: Do not special-case 0-sized destinations All fake flexible arrays should have been removed now, so remove the special casing that was avoiding checking them. If a destination claims to be 0 sized, believe it. This is especially important for cases where __counted_by is in use and may have a 0 element count. Link: https://lore.kernel.org/r/20240619203105.work.747-kees@kernel.org Signed-off-by: Kees Cook --- include/linux/fortify-string.h | 8 ++------ lib/fortify_kunit.c | 3 +-- 2 files changed, 3 insertions(+), 8 deletions(-) (limited to 'lib') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 7e0f340bf363..0d99bf11d260 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -601,11 +601,7 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, /* * Warn when writing beyond destination field size. * - * We must ignore p_size_field == 0 for existing 0-element - * fake flexible arrays, until they are all converted to - * proper flexible arrays. - * - * The implementation of __builtin_*object_size() behaves + * Note the implementation of __builtin_*object_size() behaves * like sizeof() when not directly referencing a flexible * array member, which means there will be many bounds checks * that will appear at run-time, without a way for them to be @@ -613,7 +609,7 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, * is specifically the flexible array member). * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101832 */ - if (p_size_field != 0 && p_size_field != SIZE_MAX && + if (p_size_field != SIZE_MAX && p_size != p_size_field && p_size_field < size) return true; diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index f9cc467334ce..f0c64b9e9b46 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -910,10 +910,9 @@ static void fortify_test_##memfunc(struct kunit *test) \ 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); \ + KUNIT_EXPECT_EQ(test, fortify_write_overflows, 1); \ } __fortify_test(memcpy) __fortify_test(memmove) -- cgit v1.2.3 From f0da7a231c7d0bafb6bb56da597cb2bfaf2c7028 Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Fri, 14 Jun 2024 11:09:11 +0800 Subject: crypto: lib/mpi - Use swap() in mpi_ec_mul_point() Use existing swap() function rather than duplicating its implementation. ./lib/crypto/mpi/ec.c:1291:20-21: WARNING opportunity for swap(). ./lib/crypto/mpi/ec.c:1292:20-21: WARNING opportunity for swap(). Reported-by: Abaci Robot Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=9328 Signed-off-by: Jiapeng Chong Signed-off-by: Herbert Xu --- lib/crypto/mpi/ec.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/crypto/mpi/ec.c b/lib/crypto/mpi/ec.c index e16dca1e23d5..4781f00982ef 100644 --- a/lib/crypto/mpi/ec.c +++ b/lib/crypto/mpi/ec.c @@ -1285,14 +1285,12 @@ void mpi_ec_mul_point(MPI_POINT result, sum = &p2_; for (j = nbits-1; j >= 0; j--) { - MPI_POINT t; - sw = mpi_test_bit(scalar, j); point_swap_cond(q1, q2, sw, ctx); montgomery_ladder(prd, sum, q1, q2, point->x, ctx); point_swap_cond(prd, sum, sw, ctx); - t = q1; q1 = prd; prd = t; - t = q2; q2 = sum; sum = t; + swap(q1, prd); + swap(q2, sum); } mpi_clear(result->y); -- cgit v1.2.3 From b44327ebc1c926e4b55a7721e3d91313fcf188b1 Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Fri, 14 Jun 2024 11:09:12 +0800 Subject: crypto: lib/mpi - Use swap() in mpi_powm() Use existing swap() function rather than duplicating its implementation. ./lib/crypto/mpi/mpi-pow.c:211:11-12: WARNING opportunity for swap(). ./lib/crypto/mpi/mpi-pow.c:239:12-13: WARNING opportunity for swap(). Reported-by: Abaci Robot Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=9327 Signed-off-by: Jiapeng Chong Signed-off-by: Herbert Xu --- lib/crypto/mpi/mpi-pow.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'lib') diff --git a/lib/crypto/mpi/mpi-pow.c b/lib/crypto/mpi/mpi-pow.c index 2fd7a46d55ec..67fbd4c2503d 100644 --- a/lib/crypto/mpi/mpi-pow.c +++ b/lib/crypto/mpi/mpi-pow.c @@ -176,7 +176,6 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod) for (;;) { while (c) { - mpi_ptr_t tp; mpi_size_t xsize; /*if (mpihelp_mul_n(xp, rp, rp, rsize) < 0) goto enomem */ @@ -207,9 +206,7 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod) xsize = msize; } - tp = rp; - rp = xp; - xp = tp; + swap(rp, xp); rsize = xsize; if ((mpi_limb_signed_t) e < 0) { @@ -235,9 +232,7 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod) xsize = msize; } - tp = rp; - rp = xp; - xp = tp; + swap(rp, xp); rsize = xsize; } e <<= 1; -- cgit v1.2.3 From 3cbe18b0bc9f0653709adbdadad04491a190c71a Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Sat, 15 Jun 2024 23:14:57 -0700 Subject: crypto: lib - add missing MODULE_DESCRIPTION() macros With ARCH=arm, make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/crypto/libsha256.o Add the missing invocation of the MODULE_DESCRIPTION() macro to all files which have a MODULE_LICENSE(). This includes sha1.c and utils.c which, although they did not produce a warning with the arm allmodconfig configuration, may cause this warning with other configurations. Signed-off-by: Jeff Johnson Signed-off-by: Herbert Xu --- lib/crypto/sha1.c | 1 + lib/crypto/sha256.c | 1 + lib/crypto/utils.c | 1 + 3 files changed, 3 insertions(+) (limited to 'lib') diff --git a/lib/crypto/sha1.c b/lib/crypto/sha1.c index 1aebe7be9401..6d2922747cab 100644 --- a/lib/crypto/sha1.c +++ b/lib/crypto/sha1.c @@ -137,4 +137,5 @@ void sha1_init(__u32 *buf) } EXPORT_SYMBOL(sha1_init); +MODULE_DESCRIPTION("SHA-1 Algorithm"); MODULE_LICENSE("GPL"); diff --git a/lib/crypto/sha256.c b/lib/crypto/sha256.c index 3ac1ef8677db..3f42d203c7bc 100644 --- a/lib/crypto/sha256.c +++ b/lib/crypto/sha256.c @@ -165,4 +165,5 @@ void sha256(const u8 *data, unsigned int len, u8 *out) } EXPORT_SYMBOL(sha256); +MODULE_DESCRIPTION("SHA-256 Algorithm"); MODULE_LICENSE("GPL"); diff --git a/lib/crypto/utils.c b/lib/crypto/utils.c index c852c7151b0a..373364141408 100644 --- a/lib/crypto/utils.c +++ b/lib/crypto/utils.c @@ -85,4 +85,5 @@ void __crypto_xor(u8 *dst, const u8 *src1, const u8 *src2, unsigned int len) } EXPORT_SYMBOL_GPL(__crypto_xor); +MODULE_DESCRIPTION("Crypto library utility functions"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 339b84ab6b1d66900c27bd999271cb2ae40ce812 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Thu, 20 Jun 2024 09:45:09 -0400 Subject: closures: Change BUG_ON() to WARN_ON() If a BUG_ON() can be hit in the wild, it shouldn't be a BUG_ON() For reference, this has popped up once in the CI, and we'll need more info to debug it: 03240 ------------[ cut here ]------------ 03240 kernel BUG at lib/closure.c:21! 03240 kernel BUG at lib/closure.c:21! 03240 Internal error: Oops - BUG: 00000000f2000800 [#1] SMP 03240 Modules linked in: 03240 CPU: 15 PID: 40534 Comm: kworker/u80:1 Not tainted 6.10.0-rc4-ktest-ga56da69799bd #25570 03240 Hardware name: linux,dummy-virt (DT) 03240 Workqueue: btree_update btree_interior_update_work 03240 pstate: 00001005 (nzcv daif -PAN -UAO -TCO -DIT +SSBS BTYPE=--) 03240 pc : closure_put+0x224/0x2a0 03240 lr : closure_put+0x24/0x2a0 03240 sp : ffff0000d12071c0 03240 x29: ffff0000d12071c0 x28: dfff800000000000 x27: ffff0000d1207360 03240 x26: 0000000000000040 x25: 0000000000000040 x24: 0000000000000040 03240 x23: ffff0000c1f20180 x22: 0000000000000000 x21: ffff0000c1f20168 03240 x20: 0000000040000000 x19: ffff0000c1f20140 x18: 0000000000000001 03240 x17: 0000000000003aa0 x16: 0000000000003ad0 x15: 1fffe0001c326974 03240 x14: 0000000000000a1e x13: 0000000000000000 x12: 1fffe000183e402d 03240 x11: ffff6000183e402d x10: dfff800000000000 x9 : ffff6000183e402e 03240 x8 : 0000000000000001 x7 : 00009fffe7c1bfd3 x6 : ffff0000c1f2016b 03240 x5 : ffff0000c1f20168 x4 : ffff6000183e402e x3 : ffff800081391954 03240 x2 : 0000000000000001 x1 : 0000000000000000 x0 : 00000000a8000000 03240 Call trace: 03240 closure_put+0x224/0x2a0 03240 bch2_check_for_deadlock+0x910/0x1028 03240 bch2_six_check_for_deadlock+0x1c/0x30 03240 six_lock_slowpath.isra.0+0x29c/0xed0 03240 six_lock_ip_waiter+0xa8/0xf8 03240 __bch2_btree_node_lock_write+0x14c/0x298 03240 bch2_trans_lock_write+0x6d4/0xb10 03240 __bch2_trans_commit+0x135c/0x5520 03240 btree_interior_update_work+0x1248/0x1c10 03240 process_scheduled_works+0x53c/0xd90 03240 worker_thread+0x370/0x8c8 03240 kthread+0x258/0x2e8 03240 ret_from_fork+0x10/0x20 03240 Code: aa1303e0 d63f0020 a94363f7 17ffff8c (d4210000) 03240 ---[ end trace 0000000000000000 ]--- 03240 Kernel panic - not syncing: Oops - BUG: Fatal exception 03240 SMP: stopping secondary CPUs 03241 SMP: failed to stop secondary CPUs 13,15 03241 Kernel Offset: disabled 03241 CPU features: 0x00,00000003,80000008,4240500b 03241 Memory Limit: none 03241 ---[ end Kernel panic - not syncing: Oops - BUG: Fatal exception ]--- 03246 ========= FAILED TIMEOUT copygc_torture_no_checksum in 7200s Signed-off-by: Kent Overstreet --- lib/closure.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/closure.c b/lib/closure.c index 07409e9e35a5..2e1ee9fdec08 100644 --- a/lib/closure.c +++ b/lib/closure.c @@ -17,12 +17,18 @@ static inline void closure_put_after_sub(struct closure *cl, int flags) { int r = flags & CLOSURE_REMAINING_MASK; - BUG_ON(flags & CLOSURE_GUARD_MASK); - BUG_ON(!r && (flags & ~CLOSURE_DESTRUCTOR)); + if (WARN(flags & CLOSURE_GUARD_MASK, + "closure has guard bits set: %x (%u)", + flags & CLOSURE_GUARD_MASK, (unsigned) __fls(r))) + r &= ~CLOSURE_GUARD_MASK; if (!r) { smp_acquire__after_ctrl_dep(); + WARN(flags & ~CLOSURE_DESTRUCTOR, + "closure ref hit 0 with incorrect flags set: %x (%u)", + flags & ~CLOSURE_DESTRUCTOR, (unsigned) __fls(flags)); + cl->closure_get_happened = false; if (cl->fn && !(flags & CLOSURE_DESTRUCTOR)) { -- cgit v1.2.3 From 06efa5f30c28eaf237247ca8c4cb46eb62cb6bd9 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 22 Jun 2024 21:38:58 -0400 Subject: closures: closure_get_not_zero(), closure_return_sync() Provide new primitives for solving a lifetime issue with bcachefs btree_trans objects. closure_sync_return(): like closure_sync(), wait synchronously for any outstanding gets. like closure_return, the closure is considered "finished" and the ref left at 0. closure_get_not_zero(): get a ref on a closure if it's alive, i.e. the ref is not zero. Signed-off-by: Kent Overstreet --- include/linux/closure.h | 23 ++++++++++++++++++++++ lib/closure.c | 52 +++++++++++++++++++++++++++++++++++++++++++------ 2 files changed, 69 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/include/linux/closure.h b/include/linux/closure.h index 99155df162d0..59b8c06b11ff 100644 --- a/include/linux/closure.h +++ b/include/linux/closure.h @@ -284,6 +284,21 @@ static inline void closure_get(struct closure *cl) #endif } +/** + * closure_get_not_zero + */ +static inline bool closure_get_not_zero(struct closure *cl) +{ + unsigned old = atomic_read(&cl->remaining); + do { + if (!(old & CLOSURE_REMAINING_MASK)) + return false; + + } while (!atomic_try_cmpxchg_acquire(&cl->remaining, &old, old + 1)); + + return true; +} + /** * closure_init - Initialize a closure, setting the refcount to 1 * @cl: closure to initialize @@ -310,6 +325,12 @@ static inline void closure_init_stack(struct closure *cl) atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER); } +static inline void closure_init_stack_release(struct closure *cl) +{ + memset(cl, 0, sizeof(struct closure)); + atomic_set_release(&cl->remaining, CLOSURE_REMAINING_INITIALIZER); +} + /** * closure_wake_up - wake up all closures on a wait list, * with memory barrier @@ -355,6 +376,8 @@ do { \ */ #define closure_return(_cl) continue_at((_cl), NULL, NULL) +void closure_return_sync(struct closure *cl); + /** * continue_at_nobarrier - jump to another function without barrier * diff --git a/lib/closure.c b/lib/closure.c index 2e1ee9fdec08..c971216d9d77 100644 --- a/lib/closure.c +++ b/lib/closure.c @@ -13,7 +13,7 @@ #include #include -static inline void closure_put_after_sub(struct closure *cl, int flags) +static inline void closure_put_after_sub_checks(int flags) { int r = flags & CLOSURE_REMAINING_MASK; @@ -22,12 +22,17 @@ static inline void closure_put_after_sub(struct closure *cl, int flags) flags & CLOSURE_GUARD_MASK, (unsigned) __fls(r))) r &= ~CLOSURE_GUARD_MASK; - if (!r) { - smp_acquire__after_ctrl_dep(); + WARN(!r && (flags & ~CLOSURE_DESTRUCTOR), + "closure ref hit 0 with incorrect flags set: %x (%u)", + flags & ~CLOSURE_DESTRUCTOR, (unsigned) __fls(flags)); +} + +static inline void closure_put_after_sub(struct closure *cl, int flags) +{ + closure_put_after_sub_checks(flags); - WARN(flags & ~CLOSURE_DESTRUCTOR, - "closure ref hit 0 with incorrect flags set: %x (%u)", - flags & ~CLOSURE_DESTRUCTOR, (unsigned) __fls(flags)); + if (!(flags & CLOSURE_REMAINING_MASK)) { + smp_acquire__after_ctrl_dep(); cl->closure_get_happened = false; @@ -145,6 +150,41 @@ void __sched __closure_sync(struct closure *cl) } EXPORT_SYMBOL(__closure_sync); +/* + * closure_return_sync - finish running a closure, synchronously (i.e. waiting + * for outstanding get()s to finish) and returning once closure refcount is 0. + * + * Unlike closure_sync() this doesn't reinit the ref to 1; subsequent + * closure_get_not_zero() calls waill fail. + */ +void __sched closure_return_sync(struct closure *cl) +{ + struct closure_syncer s = { .task = current }; + + cl->s = &s; + set_closure_fn(cl, closure_sync_fn, NULL); + + unsigned flags = atomic_sub_return_release(1 + CLOSURE_RUNNING - CLOSURE_DESTRUCTOR, + &cl->remaining); + + closure_put_after_sub_checks(flags); + + if (unlikely(flags & CLOSURE_REMAINING_MASK)) { + while (1) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (s.done) + break; + schedule(); + } + + __set_current_state(TASK_RUNNING); + } + + if (cl->parent) + closure_put(cl->parent); +} +EXPORT_SYMBOL(closure_return_sync); + int __sched __closure_sync_timeout(struct closure *cl, unsigned long timeout) { struct closure_syncer s = { .task = current }; -- cgit v1.2.3 From a03a84bee36ab018d5757a29bb85e0fb804bb253 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 13 Jun 2024 21:18:01 +0200 Subject: lib/fonts: Fix visiblity of SUN12x22 and TER16x32 if DRM_PANIC When CONFIG_FONTS ("Select compiled-in fonts") is not enabled, the user should not be asked about any fonts. However, when CONFIG_DRM_PANIC is enabled, the user is still asked about the Sparc console 12x22 and Terminus 16x32 fonts. Fix this by moving the "|| DRM_PANIC" to where it belongs. Split the dependency in two rules to improve readability. Fixes: b94605a3889b9084 ("lib/fonts: Allow to select fonts for drm_panic") Signed-off-by: Geert Uytterhoeven Reviewed-by: Jocelyn Falempe Signed-off-by: Jocelyn Falempe Link: https://patchwork.freedesktop.org/patch/msgid/ac474c6755800e61e18bd5af407c6acb449c5149.1718305355.git.geert+renesas@glider.be --- lib/fonts/Kconfig | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/fonts/Kconfig b/lib/fonts/Kconfig index befcb463f738..3ac26bdbc3ff 100644 --- a/lib/fonts/Kconfig +++ b/lib/fonts/Kconfig @@ -105,7 +105,8 @@ config FONT_SUN8x16 config FONT_SUN12x22 bool "Sparc console 12x22 font (not supported by all drivers)" - depends on (FRAMEBUFFER_CONSOLE && (!SPARC && FONTS || SPARC)) || DRM_PANIC + depends on FRAMEBUFFER_CONSOLE || DRM_PANIC + depends on !SPARC && FONTS help This is the high resolution console font for Sun machines with very big letters (like the letters used in the SPARC PROM). If the @@ -113,7 +114,8 @@ config FONT_SUN12x22 config FONT_TER16x32 bool "Terminus 16x32 font (not supported by all drivers)" - depends on (FRAMEBUFFER_CONSOLE && (!SPARC && FONTS || SPARC)) || DRM_PANIC + depends on FRAMEBUFFER_CONSOLE || DRM_PANIC + depends on !SPARC && FONTS || SPARC help Terminus Font is a clean, fixed width bitmap font, designed for long (8 and more hours per day) work with computers. -- cgit v1.2.3 From 5b5baba6222255d29626f63c41f101379ec5400b Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Tue, 11 Jun 2024 02:18:12 -0700 Subject: debugobjects: Annotate racy debug variables KCSAN has identified a potential data race in debugobjects, where the global variable debug_objects_maxchain is accessed for both reading and writing simultaneously in separate and parallel data paths. This results in the following splat printed by KCSAN: BUG: KCSAN: data-race in debug_check_no_obj_freed / debug_object_activate write to 0xffffffff847ccfc8 of 4 bytes by task 734 on cpu 41: debug_object_activate (lib/debugobjects.c:199 lib/debugobjects.c:564 lib/debugobjects.c:710) call_rcu (kernel/rcu/rcu.h:227 kernel/rcu/tree.c:2719 kernel/rcu/tree.c:2838) security_inode_free (security/security.c:1626) __destroy_inode (./include/linux/fsnotify.h:222 fs/inode.c:287) ... read to 0xffffffff847ccfc8 of 4 bytes by task 384 on cpu 31: debug_check_no_obj_freed (lib/debugobjects.c:1000 lib/debugobjects.c:1019) kfree (mm/slub.c:2081 mm/slub.c:4280 mm/slub.c:4390) percpu_ref_exit (lib/percpu-refcount.c:147) css_free_rwork_fn (kernel/cgroup/cgroup.c:5357) ... value changed: 0x00000070 -> 0x00000071 The data race is actually harmless as this is just used for debugfs statistics, as all other debug variables. Annotate all debug variables as racy explicitly, since these variables are known to be racy and harmless. Signed-off-by: Breno Leitao Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20240611091813.1189860-1-leitao@debian.org --- lib/debugobjects.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) (limited to 'lib') diff --git a/lib/debugobjects.c b/lib/debugobjects.c index fb12a9bacd2f..7cea91e193a8 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -78,16 +78,17 @@ static bool obj_freeing; /* The number of objs on the global free list */ static int obj_nr_tofree; -static int debug_objects_maxchain __read_mostly; -static int __maybe_unused debug_objects_maxchecked __read_mostly; -static int debug_objects_fixups __read_mostly; -static int debug_objects_warnings __read_mostly; -static int debug_objects_enabled __read_mostly - = CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT; -static int debug_objects_pool_size __read_mostly - = ODEBUG_POOL_SIZE; -static int debug_objects_pool_min_level __read_mostly - = ODEBUG_POOL_MIN_LEVEL; +static int __data_racy debug_objects_maxchain __read_mostly; +static int __data_racy __maybe_unused debug_objects_maxchecked __read_mostly; +static int __data_racy debug_objects_fixups __read_mostly; +static int __data_racy debug_objects_warnings __read_mostly; +static int __data_racy debug_objects_enabled __read_mostly + = CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT; +static int __data_racy debug_objects_pool_size __read_mostly + = ODEBUG_POOL_SIZE; +static int __data_racy debug_objects_pool_min_level __read_mostly + = ODEBUG_POOL_MIN_LEVEL; + static const struct debug_obj_descr *descr_test __read_mostly; static struct kmem_cache *obj_cache __ro_after_init; -- cgit v1.2.3 From 873ce25766019dd017c1a3a10c19ac3fc4bf24aa Mon Sep 17 00:00:00 2001 From: Kuan-Wei Chiu Date: Fri, 24 May 2024 23:29:46 +0800 Subject: lib min_heap: add type safe interface Implement a type-safe interface for min_heap using strong type pointers instead of void * in the data field. This change includes adding small macro wrappers around functions, enabling the use of __minheap_cast and __minheap_obj_size macros for type casting and obtaining element size. This implementation removes the necessity of passing element size in min_heap_callbacks. Additionally, introduce the MIN_HEAP_PREALLOCATED macro for preallocating some elements. Link: https://lkml.kernel.org/ioyfizrzq7w7mjrqcadtzsfgpuntowtjdw5pgn4qhvsdp4mqqg@nrlek5vmisbu Link: https://lkml.kernel.org/r/20240524152958.919343-5-visitorckw@gmail.com Signed-off-by: Kuan-Wei Chiu Reviewed-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Bagas Sanjaya Cc: Brian Foster Cc: Ching-Chun (Jim) Huang Cc: Coly Li Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kent Overstreet Cc: Mark Rutland Cc: Matthew Sakai Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Randy Dunlap Signed-off-by: Andrew Morton --- drivers/md/dm-vdo/repair.c | 9 ++--- drivers/md/dm-vdo/slab-depot.c | 5 ++- include/linux/min_heap.h | 79 +++++++++++++++++++++++++++--------------- kernel/events/core.c | 11 +++--- lib/test_min_heap.c | 13 ++++--- 5 files changed, 70 insertions(+), 47 deletions(-) (limited to 'lib') diff --git a/drivers/md/dm-vdo/repair.c b/drivers/md/dm-vdo/repair.c index defc9359f10e..e8ad611fe7c1 100644 --- a/drivers/md/dm-vdo/repair.c +++ b/drivers/md/dm-vdo/repair.c @@ -51,6 +51,8 @@ struct recovery_point { bool increment_applied; }; +DEFINE_MIN_HEAP(struct numbered_block_mapping, replay_heap); + struct repair_completion { /* The completion header */ struct vdo_completion completion; @@ -97,7 +99,7 @@ struct repair_completion { * order, then original journal order. This permits efficient iteration over the journal * entries in order. */ - struct min_heap replay_heap; + struct replay_heap replay_heap; /* Fields tracking progress through the journal entries. */ struct numbered_block_mapping *current_entry; struct numbered_block_mapping *current_unfetched_entry; @@ -163,14 +165,13 @@ static void swap_mappings(void *item1, void *item2) } static const struct min_heap_callbacks repair_min_heap = { - .elem_size = sizeof(struct numbered_block_mapping), .less = mapping_is_less_than, .swp = swap_mappings, }; static struct numbered_block_mapping *sort_next_heap_element(struct repair_completion *repair) { - struct min_heap *heap = &repair->replay_heap; + struct replay_heap *heap = &repair->replay_heap; struct numbered_block_mapping *last; if (heap->nr == 0) @@ -1117,7 +1118,7 @@ static void recover_block_map(struct vdo_completion *completion) * Organize the journal entries into a binary heap so we can iterate over them in sorted * order incrementally, avoiding an expensive sort call. */ - repair->replay_heap = (struct min_heap) { + repair->replay_heap = (struct replay_heap) { .data = repair->entries, .nr = repair->block_map_entry_count, .size = repair->block_map_entry_count, diff --git a/drivers/md/dm-vdo/slab-depot.c b/drivers/md/dm-vdo/slab-depot.c index 46e4721e5b4f..ef9a6e53109c 100644 --- a/drivers/md/dm-vdo/slab-depot.c +++ b/drivers/md/dm-vdo/slab-depot.c @@ -3309,7 +3309,6 @@ static void swap_slab_statuses(void *item1, void *item2) } static const struct min_heap_callbacks slab_status_min_heap = { - .elem_size = sizeof(struct slab_status), .less = slab_status_is_less_than, .swp = swap_slab_statuses, }; @@ -3509,7 +3508,7 @@ static int get_slab_statuses(struct block_allocator *allocator, static int __must_check vdo_prepare_slabs_for_allocation(struct block_allocator *allocator) { struct slab_status current_slab_status; - struct min_heap heap; + DEFINE_MIN_HEAP(struct slab_status, heap) heap; int result; struct slab_status *slab_statuses; struct slab_depot *depot = allocator->depot; @@ -3521,7 +3520,7 @@ static int __must_check vdo_prepare_slabs_for_allocation(struct block_allocator return result; /* Sort the slabs by cleanliness, then by emptiness hint. */ - heap = (struct min_heap) { + heap = (struct heap) { .data = slab_statuses, .nr = allocator->slab_count, .size = allocator->slab_count, diff --git a/include/linux/min_heap.h b/include/linux/min_heap.h index d52daf45861b..92830f41642a 100644 --- a/include/linux/min_heap.h +++ b/include/linux/min_heap.h @@ -7,45 +7,53 @@ #include /** - * struct min_heap - Data structure to hold a min-heap. - * @data: Start of array holding the heap elements. + * Data structure to hold a min-heap. * @nr: Number of elements currently in the heap. * @size: Maximum number of elements that can be held in current storage. + * @data: Pointer to the start of array holding the heap elements. + * @preallocated: Start of the static preallocated array holding the heap elements. */ -struct min_heap { - void *data; - int nr; - int size; -}; +#define MIN_HEAP_PREALLOCATED(_type, _name, _nr) \ +struct _name { \ + int nr; \ + int size; \ + _type *data; \ + _type preallocated[_nr]; \ +} + +#define DEFINE_MIN_HEAP(_type, _name) MIN_HEAP_PREALLOCATED(_type, _name, 0) + +typedef DEFINE_MIN_HEAP(char, min_heap_char) min_heap_char; + +#define __minheap_cast(_heap) (typeof((_heap)->data[0]) *) +#define __minheap_obj_size(_heap) sizeof((_heap)->data[0]) /** * struct min_heap_callbacks - Data/functions to customise the min_heap. - * @elem_size: The nr of each element in bytes. * @less: Partial order function for this heap. * @swp: Swap elements function. */ struct min_heap_callbacks { - int elem_size; bool (*less)(const void *lhs, const void *rhs); void (*swp)(void *lhs, void *rhs); }; /* Sift the element at pos down the heap. */ static __always_inline -void min_heapify(struct min_heap *heap, int pos, +void __min_heapify(min_heap_char *heap, int pos, size_t elem_size, const struct min_heap_callbacks *func) { void *left, *right; void *data = heap->data; - void *root = data + pos * func->elem_size; + void *root = data + pos * elem_size; int i = pos, j; /* Find the sift-down path all the way to the leaves. */ for (;;) { if (i * 2 + 2 >= heap->nr) break; - left = data + (i * 2 + 1) * func->elem_size; - right = data + (i * 2 + 2) * func->elem_size; + left = data + (i * 2 + 1) * elem_size; + right = data + (i * 2 + 2) * elem_size; i = func->less(left, right) ? i * 2 + 1 : i * 2 + 2; } @@ -54,31 +62,37 @@ void min_heapify(struct min_heap *heap, int pos, i = i * 2 + 1; /* Backtrack to the correct location. */ - while (i != pos && func->less(root, data + i * func->elem_size)) + while (i != pos && func->less(root, data + i * elem_size)) i = (i - 1) / 2; /* Shift the element into its correct place. */ j = i; while (i != pos) { i = (i - 1) / 2; - func->swp(data + i * func->elem_size, data + j * func->elem_size); + func->swp(data + i * elem_size, data + j * elem_size); } } +#define min_heapify(_heap, _pos, _func) \ + __min_heapify((min_heap_char *)_heap, _pos, __minheap_obj_size(_heap), _func) + /* Floyd's approach to heapification that is O(nr). */ static __always_inline -void min_heapify_all(struct min_heap *heap, +void __min_heapify_all(min_heap_char *heap, size_t elem_size, const struct min_heap_callbacks *func) { int i; for (i = heap->nr / 2 - 1; i >= 0; i--) - min_heapify(heap, i, func); + __min_heapify(heap, i, elem_size, func); } +#define min_heapify_all(_heap, _func) \ + __min_heapify_all((min_heap_char *)_heap, __minheap_obj_size(_heap), _func) + /* Remove minimum element from the heap, O(log2(nr)). */ static __always_inline -void min_heap_pop(struct min_heap *heap, +void __min_heap_pop(min_heap_char *heap, size_t elem_size, const struct min_heap_callbacks *func) { void *data = heap->data; @@ -88,27 +102,33 @@ void min_heap_pop(struct min_heap *heap, /* Place last element at the root (position 0) and then sift down. */ heap->nr--; - memcpy(data, data + (heap->nr * func->elem_size), func->elem_size); - min_heapify(heap, 0, func); + memcpy(data, data + (heap->nr * elem_size), elem_size); + __min_heapify(heap, 0, elem_size, func); } +#define min_heap_pop(_heap, _func) \ + __min_heap_pop((min_heap_char *)_heap, __minheap_obj_size(_heap), _func) + /* * Remove the minimum element and then push the given element. The * implementation performs 1 sift (O(log2(nr))) and is therefore more * efficient than a pop followed by a push that does 2. */ static __always_inline -void min_heap_pop_push(struct min_heap *heap, - const void *element, +void __min_heap_pop_push(min_heap_char *heap, + const void *element, size_t elem_size, const struct min_heap_callbacks *func) { - memcpy(heap->data, element, func->elem_size); - min_heapify(heap, 0, func); + memcpy(heap->data, element, elem_size); + __min_heapify(heap, 0, elem_size, func); } +#define min_heap_pop_push(_heap, _element, _func) \ + __min_heap_pop_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), _func) + /* Push an element on to the heap, O(log2(nr)). */ static __always_inline -void min_heap_push(struct min_heap *heap, const void *element, +void __min_heap_push(min_heap_char *heap, const void *element, size_t elem_size, const struct min_heap_callbacks *func) { void *data = heap->data; @@ -120,17 +140,20 @@ void min_heap_push(struct min_heap *heap, const void *element, /* Place at the end of data. */ pos = heap->nr; - memcpy(data + (pos * func->elem_size), element, func->elem_size); + memcpy(data + (pos * elem_size), element, elem_size); heap->nr++; /* Sift child at pos up. */ for (; pos > 0; pos = (pos - 1) / 2) { - child = data + (pos * func->elem_size); - parent = data + ((pos - 1) / 2) * func->elem_size; + child = data + (pos * elem_size); + parent = data + ((pos - 1) / 2) * elem_size; if (func->less(parent, child)) break; func->swp(parent, child); } } +#define min_heap_push(_heap, _element, _func) \ + __min_heap_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), _func) + #endif /* _LINUX_MIN_HEAP_H */ diff --git a/kernel/events/core.c b/kernel/events/core.c index effe9c15ec7d..5ae4e429b3fb 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3701,13 +3701,14 @@ static void swap_ptr(void *l, void *r) swap(*lp, *rp); } +DEFINE_MIN_HEAP(struct perf_event *, perf_event_min_heap); + static const struct min_heap_callbacks perf_min_heap = { - .elem_size = sizeof(struct perf_event *), .less = perf_less_group_idx, .swp = swap_ptr, }; -static void __heap_add(struct min_heap *heap, struct perf_event *event) +static void __heap_add(struct perf_event_min_heap *heap, struct perf_event *event) { struct perf_event **itrs = heap->data; @@ -3741,7 +3742,7 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx = NULL; /* Space for per CPU and/or any CPU event iterators. */ struct perf_event *itrs[2]; - struct min_heap event_heap; + struct perf_event_min_heap event_heap; struct perf_event **evt; int ret; @@ -3750,7 +3751,7 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx, if (!ctx->task) { cpuctx = this_cpu_ptr(&perf_cpu_context); - event_heap = (struct min_heap){ + event_heap = (struct perf_event_min_heap){ .data = cpuctx->heap, .nr = 0, .size = cpuctx->heap_size, @@ -3763,7 +3764,7 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx, css = &cpuctx->cgrp->css; #endif } else { - event_heap = (struct min_heap){ + event_heap = (struct perf_event_min_heap){ .data = itrs, .nr = 0, .size = ARRAY_SIZE(itrs), diff --git a/lib/test_min_heap.c b/lib/test_min_heap.c index 7b01b4387cfb..52efab9fb2f1 100644 --- a/lib/test_min_heap.c +++ b/lib/test_min_heap.c @@ -11,6 +11,8 @@ #include #include +DEFINE_MIN_HEAP(int, min_heap_test); + static __init bool less_than(const void *lhs, const void *rhs) { return *(int *)lhs < *(int *)rhs; @@ -30,7 +32,7 @@ static __init void swap_ints(void *lhs, void *rhs) } static __init int pop_verify_heap(bool min_heap, - struct min_heap *heap, + struct min_heap_test *heap, const struct min_heap_callbacks *funcs) { int *values = heap->data; @@ -63,13 +65,12 @@ static __init int test_heapify_all(bool min_heap) { int values[] = { 3, 1, 2, 4, 0x8000000, 0x7FFFFFF, 0, -3, -1, -2, -4, 0x8000000, 0x7FFFFFF }; - struct min_heap heap = { + struct min_heap_test heap = { .data = values, .nr = ARRAY_SIZE(values), .size = ARRAY_SIZE(values), }; struct min_heap_callbacks funcs = { - .elem_size = sizeof(int), .less = min_heap ? less_than : greater_than, .swp = swap_ints, }; @@ -96,13 +97,12 @@ static __init int test_heap_push(bool min_heap) const int data[] = { 3, 1, 2, 4, 0x80000000, 0x7FFFFFFF, 0, -3, -1, -2, -4, 0x80000000, 0x7FFFFFFF }; int values[ARRAY_SIZE(data)]; - struct min_heap heap = { + struct min_heap_test heap = { .data = values, .nr = 0, .size = ARRAY_SIZE(values), }; struct min_heap_callbacks funcs = { - .elem_size = sizeof(int), .less = min_heap ? less_than : greater_than, .swp = swap_ints, }; @@ -129,13 +129,12 @@ static __init int test_heap_pop_push(bool min_heap) const int data[] = { 3, 1, 2, 4, 0x80000000, 0x7FFFFFFF, 0, -3, -1, -2, -4, 0x80000000, 0x7FFFFFFF }; int values[ARRAY_SIZE(data)]; - struct min_heap heap = { + struct min_heap_test heap = { .data = values, .nr = 0, .size = ARRAY_SIZE(values), }; struct min_heap_callbacks funcs = { - .elem_size = sizeof(int), .less = min_heap ? less_than : greater_than, .swp = swap_ints, }; -- cgit v1.2.3 From 267607e87599509a6a39a5f7dd3959365e58af27 Mon Sep 17 00:00:00 2001 From: Kuan-Wei Chiu Date: Fri, 24 May 2024 23:29:50 +0800 Subject: lib min_heap: add args for min_heap_callbacks Add a third parameter 'args' for the 'less' and 'swp' functions in the 'struct min_heap_callbacks'. This additional parameter allows these comparison and swap functions to handle extra arguments when necessary. Link: https://lkml.kernel.org/r/20240524152958.919343-9-visitorckw@gmail.com Signed-off-by: Kuan-Wei Chiu Reviewed-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Bagas Sanjaya Cc: Brian Foster Cc: Ching-Chun (Jim) Huang Cc: Coly Li Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kent Overstreet Cc: Mark Rutland Cc: Matthew Sakai Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Randy Dunlap Signed-off-by: Andrew Morton --- drivers/md/dm-vdo/repair.c | 10 ++++----- drivers/md/dm-vdo/slab-depot.c | 9 ++++---- include/linux/min_heap.h | 51 +++++++++++++++++++++--------------------- kernel/events/core.c | 10 ++++----- lib/test_min_heap.c | 26 ++++++++++----------- 5 files changed, 54 insertions(+), 52 deletions(-) (limited to 'lib') diff --git a/drivers/md/dm-vdo/repair.c b/drivers/md/dm-vdo/repair.c index e8ad611fe7c1..eae990859db4 100644 --- a/drivers/md/dm-vdo/repair.c +++ b/drivers/md/dm-vdo/repair.c @@ -137,7 +137,7 @@ struct repair_completion { * to sort by slot while still ensuring we replay all entries with the same slot in the exact order * as they appeared in the journal. */ -static bool mapping_is_less_than(const void *item1, const void *item2) +static bool mapping_is_less_than(const void *item1, const void *item2, void __always_unused *args) { const struct numbered_block_mapping *mapping1 = (const struct numbered_block_mapping *) item1; @@ -156,7 +156,7 @@ static bool mapping_is_less_than(const void *item1, const void *item2) return 0; } -static void swap_mappings(void *item1, void *item2) +static void swap_mappings(void *item1, void *item2, void __always_unused *args) { struct numbered_block_mapping *mapping1 = item1; struct numbered_block_mapping *mapping2 = item2; @@ -182,8 +182,8 @@ static struct numbered_block_mapping *sort_next_heap_element(struct repair_compl * restore the heap invariant, and return a pointer to the popped element. */ last = &repair->entries[--heap->nr]; - swap_mappings(heap->data, last); - min_heapify(heap, 0, &repair_min_heap); + swap_mappings(heap->data, last, NULL); + min_heapify(heap, 0, &repair_min_heap, NULL); return last; } @@ -1123,7 +1123,7 @@ static void recover_block_map(struct vdo_completion *completion) .nr = repair->block_map_entry_count, .size = repair->block_map_entry_count, }; - min_heapify_all(&repair->replay_heap, &repair_min_heap); + min_heapify_all(&repair->replay_heap, &repair_min_heap, NULL); vdo_log_info("Replaying %zu recovery entries into block map", repair->block_map_entry_count); diff --git a/drivers/md/dm-vdo/slab-depot.c b/drivers/md/dm-vdo/slab-depot.c index ef9a6e53109c..274f9ccd072f 100644 --- a/drivers/md/dm-vdo/slab-depot.c +++ b/drivers/md/dm-vdo/slab-depot.c @@ -3288,7 +3288,8 @@ int vdo_release_block_reference(struct block_allocator *allocator, * Thus, the ordering is reversed from the usual sense since min_heap returns smaller elements * before larger ones. */ -static bool slab_status_is_less_than(const void *item1, const void *item2) +static bool slab_status_is_less_than(const void *item1, const void *item2, + void __always_unused *args) { const struct slab_status *info1 = item1; const struct slab_status *info2 = item2; @@ -3300,7 +3301,7 @@ static bool slab_status_is_less_than(const void *item1, const void *item2) return info1->slab_number < info2->slab_number; } -static void swap_slab_statuses(void *item1, void *item2) +static void swap_slab_statuses(void *item1, void *item2, void __always_unused *args) { struct slab_status *info1 = item1; struct slab_status *info2 = item2; @@ -3525,7 +3526,7 @@ static int __must_check vdo_prepare_slabs_for_allocation(struct block_allocator .nr = allocator->slab_count, .size = allocator->slab_count, }; - min_heapify_all(&heap, &slab_status_min_heap); + min_heapify_all(&heap, &slab_status_min_heap, NULL); while (heap.nr > 0) { bool high_priority; @@ -3533,7 +3534,7 @@ static int __must_check vdo_prepare_slabs_for_allocation(struct block_allocator struct slab_journal *journal; current_slab_status = slab_statuses[0]; - min_heap_pop(&heap, &slab_status_min_heap); + min_heap_pop(&heap, &slab_status_min_heap, NULL); slab = depot->slabs[current_slab_status.slab_number]; if ((depot->load_type == VDO_SLAB_DEPOT_REBUILD_LOAD) || diff --git a/include/linux/min_heap.h b/include/linux/min_heap.h index f41898c05f5a..4acd0f4b3faf 100644 --- a/include/linux/min_heap.h +++ b/include/linux/min_heap.h @@ -34,8 +34,8 @@ typedef DEFINE_MIN_HEAP(char, min_heap_char) min_heap_char; * @swp: Swap elements function. */ struct min_heap_callbacks { - bool (*less)(const void *lhs, const void *rhs); - void (*swp)(void *lhs, void *rhs); + bool (*less)(const void *lhs, const void *rhs, void *args); + void (*swp)(void *lhs, void *rhs, void *args); }; /* Initialize a min-heap. */ @@ -76,7 +76,7 @@ bool __min_heap_full(min_heap_char *heap) /* Sift the element at pos down the heap. */ static __always_inline void __min_heapify(min_heap_char *heap, int pos, size_t elem_size, - const struct min_heap_callbacks *func) + const struct min_heap_callbacks *func, void *args) { void *left, *right; void *data = heap->data; @@ -89,7 +89,7 @@ void __min_heapify(min_heap_char *heap, int pos, size_t elem_size, break; left = data + (i * 2 + 1) * elem_size; right = data + (i * 2 + 2) * elem_size; - i = func->less(left, right) ? i * 2 + 1 : i * 2 + 2; + i = func->less(left, right, args) ? i * 2 + 1 : i * 2 + 2; } /* Special case for the last leaf with no sibling. */ @@ -97,38 +97,38 @@ void __min_heapify(min_heap_char *heap, int pos, size_t elem_size, i = i * 2 + 1; /* Backtrack to the correct location. */ - while (i != pos && func->less(root, data + i * elem_size)) + while (i != pos && func->less(root, data + i * elem_size, args)) i = (i - 1) / 2; /* Shift the element into its correct place. */ j = i; while (i != pos) { i = (i - 1) / 2; - func->swp(data + i * elem_size, data + j * elem_size); + func->swp(data + i * elem_size, data + j * elem_size, args); } } -#define min_heapify(_heap, _pos, _func) \ - __min_heapify((min_heap_char *)_heap, _pos, __minheap_obj_size(_heap), _func) +#define min_heapify(_heap, _pos, _func, _args) \ + __min_heapify((min_heap_char *)_heap, _pos, __minheap_obj_size(_heap), _func, _args) /* Floyd's approach to heapification that is O(nr). */ static __always_inline void __min_heapify_all(min_heap_char *heap, size_t elem_size, - const struct min_heap_callbacks *func) + const struct min_heap_callbacks *func, void *args) { int i; for (i = heap->nr / 2 - 1; i >= 0; i--) - __min_heapify(heap, i, elem_size, func); + __min_heapify(heap, i, elem_size, func, args); } -#define min_heapify_all(_heap, _func) \ - __min_heapify_all((min_heap_char *)_heap, __minheap_obj_size(_heap), _func) +#define min_heapify_all(_heap, _func, _args) \ + __min_heapify_all((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args) /* Remove minimum element from the heap, O(log2(nr)). */ static __always_inline void __min_heap_pop(min_heap_char *heap, size_t elem_size, - const struct min_heap_callbacks *func) + const struct min_heap_callbacks *func, void *args) { void *data = heap->data; @@ -138,11 +138,11 @@ void __min_heap_pop(min_heap_char *heap, size_t elem_size, /* Place last element at the root (position 0) and then sift down. */ heap->nr--; memcpy(data, data + (heap->nr * elem_size), elem_size); - __min_heapify(heap, 0, elem_size, func); + __min_heapify(heap, 0, elem_size, func, args); } -#define min_heap_pop(_heap, _func) \ - __min_heap_pop((min_heap_char *)_heap, __minheap_obj_size(_heap), _func) +#define min_heap_pop(_heap, _func, _args) \ + __min_heap_pop((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args) /* * Remove the minimum element and then push the given element. The @@ -152,19 +152,20 @@ void __min_heap_pop(min_heap_char *heap, size_t elem_size, static __always_inline void __min_heap_pop_push(min_heap_char *heap, const void *element, size_t elem_size, - const struct min_heap_callbacks *func) + const struct min_heap_callbacks *func, + void *args) { memcpy(heap->data, element, elem_size); - __min_heapify(heap, 0, elem_size, func); + __min_heapify(heap, 0, elem_size, func, args); } -#define min_heap_pop_push(_heap, _element, _func) \ - __min_heap_pop_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), _func) +#define min_heap_pop_push(_heap, _element, _func, _args) \ + __min_heap_pop_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), _func, _args) /* Push an element on to the heap, O(log2(nr)). */ static __always_inline void __min_heap_push(min_heap_char *heap, const void *element, size_t elem_size, - const struct min_heap_callbacks *func) + const struct min_heap_callbacks *func, void *args) { void *data = heap->data; void *child, *parent; @@ -182,13 +183,13 @@ void __min_heap_push(min_heap_char *heap, const void *element, size_t elem_size, for (; pos > 0; pos = (pos - 1) / 2) { child = data + (pos * elem_size); parent = data + ((pos - 1) / 2) * elem_size; - if (func->less(parent, child)) + if (func->less(parent, child, args)) break; - func->swp(parent, child); + func->swp(parent, child, args); } } -#define min_heap_push(_heap, _element, _func) \ - __min_heap_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), _func) +#define min_heap_push(_heap, _element, _func, _args) \ + __min_heap_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), _func, _args) #endif /* _LINUX_MIN_HEAP_H */ diff --git a/kernel/events/core.c b/kernel/events/core.c index 5ae4e429b3fb..27cafe661740 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3686,7 +3686,7 @@ void __perf_event_task_sched_out(struct task_struct *task, perf_cgroup_switch(next); } -static bool perf_less_group_idx(const void *l, const void *r) +static bool perf_less_group_idx(const void *l, const void *r, void __always_unused *args) { const struct perf_event *le = *(const struct perf_event **)l; const struct perf_event *re = *(const struct perf_event **)r; @@ -3694,7 +3694,7 @@ static bool perf_less_group_idx(const void *l, const void *r) return le->group_index < re->group_index; } -static void swap_ptr(void *l, void *r) +static void swap_ptr(void *l, void *r, void __always_unused *args) { void **lp = l, **rp = r; @@ -3786,7 +3786,7 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx, perf_assert_pmu_disabled((*evt)->pmu_ctx->pmu); } - min_heapify_all(&event_heap, &perf_min_heap); + min_heapify_all(&event_heap, &perf_min_heap, NULL); while (event_heap.nr) { ret = func(*evt, data); @@ -3795,9 +3795,9 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx, *evt = perf_event_groups_next(*evt, pmu); if (*evt) - min_heapify(&event_heap, 0, &perf_min_heap); + min_heapify(&event_heap, 0, &perf_min_heap, NULL); else - min_heap_pop(&event_heap, &perf_min_heap); + min_heap_pop(&event_heap, &perf_min_heap, NULL); } return 0; diff --git a/lib/test_min_heap.c b/lib/test_min_heap.c index 52efab9fb2f1..f59638cf5dfa 100644 --- a/lib/test_min_heap.c +++ b/lib/test_min_heap.c @@ -13,17 +13,17 @@ DEFINE_MIN_HEAP(int, min_heap_test); -static __init bool less_than(const void *lhs, const void *rhs) +static __init bool less_than(const void *lhs, const void *rhs, void __always_unused *args) { return *(int *)lhs < *(int *)rhs; } -static __init bool greater_than(const void *lhs, const void *rhs) +static __init bool greater_than(const void *lhs, const void *rhs, void __always_unused *args) { return *(int *)lhs > *(int *)rhs; } -static __init void swap_ints(void *lhs, void *rhs) +static __init void swap_ints(void *lhs, void *rhs, void __always_unused *args) { int temp = *(int *)lhs; @@ -40,7 +40,7 @@ static __init int pop_verify_heap(bool min_heap, int last; last = values[0]; - min_heap_pop(heap, funcs); + min_heap_pop(heap, funcs, NULL); while (heap->nr > 0) { if (min_heap) { if (last > values[0]) { @@ -56,7 +56,7 @@ static __init int pop_verify_heap(bool min_heap, } } last = values[0]; - min_heap_pop(heap, funcs); + min_heap_pop(heap, funcs, NULL); } return err; } @@ -77,7 +77,7 @@ static __init int test_heapify_all(bool min_heap) int i, err; /* Test with known set of values. */ - min_heapify_all(&heap, &funcs); + min_heapify_all(&heap, &funcs, NULL); err = pop_verify_heap(min_heap, &heap, &funcs); @@ -86,7 +86,7 @@ static __init int test_heapify_all(bool min_heap) for (i = 0; i < heap.nr; i++) values[i] = get_random_u32(); - min_heapify_all(&heap, &funcs); + min_heapify_all(&heap, &funcs, NULL); err += pop_verify_heap(min_heap, &heap, &funcs); return err; @@ -110,14 +110,14 @@ static __init int test_heap_push(bool min_heap) /* Test with known set of values copied from data. */ for (i = 0; i < ARRAY_SIZE(data); i++) - min_heap_push(&heap, &data[i], &funcs); + min_heap_push(&heap, &data[i], &funcs, NULL); err = pop_verify_heap(min_heap, &heap, &funcs); /* Test with randomly generated values. */ while (heap.nr < heap.size) { temp = get_random_u32(); - min_heap_push(&heap, &temp, &funcs); + min_heap_push(&heap, &temp, &funcs, NULL); } err += pop_verify_heap(min_heap, &heap, &funcs); @@ -143,22 +143,22 @@ static __init int test_heap_pop_push(bool min_heap) /* Fill values with data to pop and replace. */ temp = min_heap ? 0x80000000 : 0x7FFFFFFF; for (i = 0; i < ARRAY_SIZE(data); i++) - min_heap_push(&heap, &temp, &funcs); + min_heap_push(&heap, &temp, &funcs, NULL); /* Test with known set of values copied from data. */ for (i = 0; i < ARRAY_SIZE(data); i++) - min_heap_pop_push(&heap, &data[i], &funcs); + min_heap_pop_push(&heap, &data[i], &funcs, NULL); err = pop_verify_heap(min_heap, &heap, &funcs); heap.nr = 0; for (i = 0; i < ARRAY_SIZE(data); i++) - min_heap_push(&heap, &temp, &funcs); + min_heap_push(&heap, &temp, &funcs, NULL); /* Test with randomly generated values. */ for (i = 0; i < ARRAY_SIZE(data); i++) { temp = get_random_u32(); - min_heap_pop_push(&heap, &temp, &funcs); + min_heap_pop_push(&heap, &temp, &funcs, NULL); } err += pop_verify_heap(min_heap, &heap, &funcs); -- cgit v1.2.3 From 7099f74dc31058ee9ac01da5590321173c2b771a Mon Sep 17 00:00:00 2001 From: Kuan-Wei Chiu Date: Fri, 24 May 2024 23:29:56 +0800 Subject: lib/test_min_heap: add test for heap_del() Add test cases for the min_heap_del() to ensure its functionality is thoroughly tested. Link: https://lkml.kernel.org/r/20240524152958.919343-15-visitorckw@gmail.com Signed-off-by: Kuan-Wei Chiu Reviewed-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Bagas Sanjaya Cc: Brian Foster Cc: Ching-Chun (Jim) Huang Cc: Coly Li Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kent Overstreet Cc: Mark Rutland Cc: Matthew Sakai Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Randy Dunlap Signed-off-by: Andrew Morton --- lib/test_min_heap.c | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'lib') diff --git a/lib/test_min_heap.c b/lib/test_min_heap.c index f59638cf5dfa..9e1feb9b679c 100644 --- a/lib/test_min_heap.c +++ b/lib/test_min_heap.c @@ -165,6 +165,40 @@ static __init int test_heap_pop_push(bool min_heap) return err; } +static __init int test_heap_del(bool min_heap) +{ + int values[] = { 3, 1, 2, 4, 0x8000000, 0x7FFFFFF, 0, + -3, -1, -2, -4, 0x8000000, 0x7FFFFFF }; + struct min_heap_test heap; + + min_heap_init(&heap, values, ARRAY_SIZE(values)); + heap.nr = ARRAY_SIZE(values); + struct min_heap_callbacks funcs = { + .less = min_heap ? less_than : greater_than, + .swp = swap_ints, + }; + int i, err; + + /* Test with known set of values. */ + min_heapify_all(&heap, &funcs, NULL); + for (i = 0; i < ARRAY_SIZE(values) / 2; i++) + min_heap_del(&heap, get_random_u32() % heap.nr, &funcs, NULL); + err = pop_verify_heap(min_heap, &heap, &funcs); + + + /* Test with randomly generated values. */ + heap.nr = ARRAY_SIZE(values); + for (i = 0; i < heap.nr; i++) + values[i] = get_random_u32(); + min_heapify_all(&heap, &funcs, NULL); + + for (i = 0; i < ARRAY_SIZE(values) / 2; i++) + min_heap_del(&heap, get_random_u32() % heap.nr, &funcs, NULL); + err += pop_verify_heap(min_heap, &heap, &funcs); + + return err; +} + static int __init test_min_heap_init(void) { int err = 0; @@ -175,6 +209,8 @@ static int __init test_min_heap_init(void) err += test_heap_push(false); err += test_heap_pop_push(true); err += test_heap_pop_push(false); + err += test_heap_del(true); + err += test_heap_del(false); if (err) { pr_err("test failed with %d errors\n", err); return -EINVAL; -- cgit v1.2.3 From 85fb11a87921a017e5551835eaaf58f9da173686 Mon Sep 17 00:00:00 2001 From: Kuan-Wei Chiu Date: Tue, 28 May 2024 04:30:08 +0800 Subject: lib/sort: remove unused pr_fmt macro Patch series "lib/sort: Optimizations and cleanups". This patch series optimizes the handling of the last 2 or 3 elements in lib/sort and adds a testcase in lib/test_sort to maintain 100% code coverage reflecting this change. Additionally, it corrects outdated descriptions regarding glibc qsort() and removes the unused pr_fmt macro. This patch (of 4): The pr_fmt macro is defined but not used in lib/sort.c. Since there are no pr_* functions printing any messages, the pr_fmt macro is redundant and can be safely removed. Link: https://lkml.kernel.org/r/20240527203011.1644280-1-visitorckw@gmail.com Link: https://lkml.kernel.org/r/20240527203011.1644280-2-visitorckw@gmail.com Signed-off-by: Kuan-Wei Chiu Cc: Ching-Chun (Jim) Huang Signed-off-by: Andrew Morton --- lib/sort.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'lib') diff --git a/lib/sort.c b/lib/sort.c index a0509088f82a..651b73205f6d 100644 --- a/lib/sort.c +++ b/lib/sort.c @@ -10,8 +10,6 @@ * quicksort's O(n^2) worst case. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - #include #include #include -- cgit v1.2.3 From f49ac9571b8f1de4dfcce941a936a4d19dd7bb8a Mon Sep 17 00:00:00 2001 From: Kuan-Wei Chiu Date: Tue, 28 May 2024 04:30:09 +0800 Subject: lib/sort: fix outdated comment regarding glibc qsort() The existing comment in lib/sort refers to glibc qsort() using quicksort. However, glibc qsort() no longer uses quicksort; it now uses mergesort and falls back to heapsort if memory allocation for mergesort fails. This makes the comment outdated and incorrect. Update the comment to refer to quicksort in general rather than glibc's implementation to provide accurate information about the comparisons and trade-offs without implying an outdated implementation. Link: https://lkml.kernel.org/r/20240527203011.1644280-3-visitorckw@gmail.com Signed-off-by: Kuan-Wei Chiu Cc: Ching-Chun (Jim) Huang Signed-off-by: Andrew Morton --- lib/sort.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/sort.c b/lib/sort.c index 651b73205f6d..b918ae15302d 100644 --- a/lib/sort.c +++ b/lib/sort.c @@ -5,7 +5,7 @@ * This performs n*log2(n) + 0.37*n + o(n) comparisons on average, * and 1.5*n*log2(n) + O(n) in the (very contrived) worst case. * - * Glibc qsort() manages n*log2(n) - 1.26*n for random inputs (1.63*n + * Quicksort manages n*log2(n) - 1.26*n for random inputs (1.63*n * better) at the expense of stack usage and much larger code to avoid * quicksort's O(n^2) worst case. */ -- cgit v1.2.3 From 41ed7804350839608308fed0225894fdab8b71fd Mon Sep 17 00:00:00 2001 From: Kuan-Wei Chiu Date: Tue, 28 May 2024 04:30:10 +0800 Subject: lib/sort: optimize heapsort for handling final 2 or 3 elements After building the heap, the code continuously pops two elements from the heap until only 2 or 3 elements remain, at which point it switches back to a regular heapsort with one element popped at a time. However, to handle the final 2 or 3 elements, an additional else-if statement in the while loop was introduced, potentially increasing branch misses. Moreover, when there are only 2 or 3 elements left, continuing with regular heapify operations is unnecessary as these cases are simple enough to be handled with a single comparison and 1 or 2 swaps outside the while loop. Eliminating the additional else-if statement and directly managing cases involving 2 or 3 elements outside the loop reduces unnecessary conditional branches resulting from the numerous loops and conditionals in heapify. This optimization maintains consistent numbers of comparisons and swaps for arrays with even lengths while reducing swaps and comparisons for arrays with odd lengths from 2.5 swaps and 1 comparison to 1.5 swaps and 1 comparison. Link: https://lkml.kernel.org/r/20240527203011.1644280-4-visitorckw@gmail.com Signed-off-by: Kuan-Wei Chiu Cc: Ching-Chun (Jim) Huang Signed-off-by: Andrew Morton --- lib/sort.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/sort.c b/lib/sort.c index b918ae15302d..048b7a6ef967 100644 --- a/lib/sort.c +++ b/lib/sort.c @@ -250,10 +250,7 @@ void sort_r(void *base, size_t num, size_t size, a = size << shift; n -= size; do_swap(base + a, base + n, size, swap_func, priv); - } else if (n > size) { /* Sorting: Extract root */ - n -= size; - do_swap(base, base + n, size, swap_func, priv); - } else { /* Sort complete */ + } else { /* Sort complete */ break; } @@ -283,6 +280,11 @@ void sort_r(void *base, size_t num, size_t size, do_swap(base + b, base + c, size, swap_func, priv); } } + + n -= size; + do_swap(base, base + n, size, swap_func, priv); + if (n == size * 2 && do_cmp(base, base + size, cmp_func, priv) > 0) + do_swap(base, base + size, size, swap_func, priv); } EXPORT_SYMBOL(sort_r); -- cgit v1.2.3 From 54ce43da25816e6134ffc777b02f9a720d07a8db Mon Sep 17 00:00:00 2001 From: Kuan-Wei Chiu Date: Tue, 28 May 2024 04:30:11 +0800 Subject: lib/test_sort: add a testcase to ensure code coverage The addition of an if statement in lib/sort to handle the final unsorted 2 or 3 elements is not covered by existing test cases, leading to incomplete test coverage. To ensure comprehensive testing and maintain 100% code coverage, add a new testcase for scenarios where the if statement is triggered. Since the if statement is only triggered when the array length is odd and the first element is greater than the second element, a testcase is created using an array length of TEST_LEN - 1 and a suitable random seed to maintain full code coverage. Link: https://lkml.kernel.org/r/20240527203011.1644280-5-visitorckw@gmail.com Signed-off-by: Kuan-Wei Chiu Cc: Ching-Chun (Jim) Huang Signed-off-by: Andrew Morton --- lib/test_sort.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/test_sort.c b/lib/test_sort.c index be02e3a098cf..da4495125097 100644 --- a/lib/test_sort.c +++ b/lib/test_sort.c @@ -29,7 +29,19 @@ static void test_sort(struct kunit *test) sort(a, TEST_LEN, sizeof(*a), cmpint, NULL); - for (i = 0; i < TEST_LEN-1; i++) + for (i = 0; i < TEST_LEN - 1; i++) + KUNIT_ASSERT_LE(test, a[i], a[i + 1]); + + r = 48; + + for (i = 0; i < TEST_LEN - 1; i++) { + r = (r * 725861) % 6599; + a[i] = r; + } + + sort(a, TEST_LEN - 1, sizeof(*a), cmpint, NULL); + + for (i = 0; i < TEST_LEN - 2; i++) KUNIT_ASSERT_LE(test, a[i], a[i + 1]); } -- cgit v1.2.3 From 51d821654be4286b005ad2b7dc8b973d5008a2ec Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Tue, 28 May 2024 22:42:57 +0200 Subject: percpu_counter: add a cmpxchg-based _add_batch variant Interrupt disable/enable trips are quite expensive on x86-64 compared to a mere cmpxchg (note: no lock prefix!) and percpu counters are used quite often. With this change I get a bump of 1% ops/s for negative path lookups, plugged into will-it-scale: void testcase(unsigned long long *iterations, unsigned long nr) { while (1) { int fd = open("/tmp/nonexistent", O_RDONLY); assert(fd == -1); (*iterations)++; } } The win would be higher if it was not for other slowdowns, but one has to start somewhere. Link: https://lkml.kernel.org/r/20240528204257.434817-1-mjguzik@gmail.com Signed-off-by: Mateusz Guzik Acked-by: Vlastimil Babka Acked-by: Dennis Zhou Cc: Hugh Dickins Cc: Tejun Heo Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- lib/percpu_counter.c | 44 +++++++++++++++++++++++++++++++++++++++----- 1 file changed, 39 insertions(+), 5 deletions(-) (limited to 'lib') diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 44dd133594d4..51bc5246986d 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -73,17 +73,50 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) EXPORT_SYMBOL(percpu_counter_set); /* - * local_irq_save() is needed to make the function irq safe: - * - The slow path would be ok as protected by an irq-safe spinlock. - * - this_cpu_add would be ok as it is irq-safe by definition. - * But: - * The decision slow path/fast path and the actual update must be atomic, too. + * Add to a counter while respecting batch size. + * + * There are 2 implementations, both dealing with the following problem: + * + * The decision slow path/fast path and the actual update must be atomic. * Otherwise a call in process context could check the current values and * decide that the fast path can be used. If now an interrupt occurs before * the this_cpu_add(), and the interrupt updates this_cpu(*fbc->counters), * then the this_cpu_add() that is executed after the interrupt has completed * can produce values larger than "batch" or even overflows. */ +#ifdef CONFIG_HAVE_CMPXCHG_LOCAL +/* + * Safety against interrupts is achieved in 2 ways: + * 1. the fast path uses local cmpxchg (note: no lock prefix) + * 2. the slow path operates with interrupts disabled + */ +void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) +{ + s64 count; + unsigned long flags; + + count = this_cpu_read(*fbc->counters); + do { + if (unlikely(abs(count + amount) >= batch)) { + raw_spin_lock_irqsave(&fbc->lock, flags); + /* + * Note: by now we might have migrated to another CPU + * or the value might have changed. + */ + count = __this_cpu_read(*fbc->counters); + fbc->count += count + amount; + __this_cpu_sub(*fbc->counters, count); + raw_spin_unlock_irqrestore(&fbc->lock, flags); + return; + } + } while (!this_cpu_try_cmpxchg(*fbc->counters, &count, count + amount)); +} +#else +/* + * local_irq_save() is used to make the function irq safe: + * - The slow path would be ok as protected by an irq-safe spinlock. + * - this_cpu_add would be ok as it is irq-safe by definition. + */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; @@ -101,6 +134,7 @@ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) } local_irq_restore(flags); } +#endif EXPORT_SYMBOL(percpu_counter_add_batch); /* -- cgit v1.2.3 From 7abcb84f953df037d40fad66f2109db318dd155b Mon Sep 17 00:00:00 2001 From: I Hsin Cheng Date: Sun, 26 May 2024 22:01:39 +0800 Subject: lib/plist.c: enforce memory ordering in plist_check_list There exists an iteration over a plist in plist_check_list(), and memory dependency exists between variables "prev", "next" and "prev->next". As plist is used in the scheduling subsystem, we should guarantee the memory ordering between multiple processors. Using macro "WRITE_ONCE()" can help us to ensure the memory ordering as it was stated in "Documentation/memory-barriers.txt". Link: https://lkml.kernel.org/r/20240526140139.17220-1-richard120310@gmail.com Signed-off-by: I Hsin Cheng Signed-off-by: Andrew Morton --- lib/plist.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/plist.c b/lib/plist.c index 0d86ed7a76ac..2e51829d3db9 100644 --- a/lib/plist.c +++ b/lib/plist.c @@ -47,8 +47,8 @@ static void plist_check_list(struct list_head *top) plist_check_prev_next(top, prev, next); while (next != top) { - prev = next; - next = prev->next; + WRITE_ONCE(prev, next); + WRITE_ONCE(next, prev->next); plist_check_prev_next(top, prev, next); } } -- cgit v1.2.3 From 21516c56ffe280d547af656fa9ba0ae62779ec98 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 08:14:56 -0700 Subject: lib/ts: add missing MODULE_DESCRIPTION() macros make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/ts_kmp.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/ts_bm.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/ts_fsm.o Add the missing invocations of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240531-lib-ts-v1-1-03d7f3546c49@quicinc.com Signed-off-by: Jeff Johnson Signed-off-by: Andrew Morton --- lib/ts_bm.c | 1 + lib/ts_fsm.c | 1 + lib/ts_kmp.c | 1 + 3 files changed, 3 insertions(+) (limited to 'lib') diff --git a/lib/ts_bm.c b/lib/ts_bm.c index e5f30f9177df..eed5967238c5 100644 --- a/lib/ts_bm.c +++ b/lib/ts_bm.c @@ -216,6 +216,7 @@ static void __exit exit_bm(void) textsearch_unregister(&bm_ops); } +MODULE_DESCRIPTION("Boyer-Moore text search implementation"); MODULE_LICENSE("GPL"); module_init(init_bm); diff --git a/lib/ts_fsm.c b/lib/ts_fsm.c index 64fd9015ad80..053615f4fcd7 100644 --- a/lib/ts_fsm.c +++ b/lib/ts_fsm.c @@ -331,6 +331,7 @@ static void __exit exit_fsm(void) textsearch_unregister(&fsm_ops); } +MODULE_DESCRIPTION("naive finite state machine text search"); MODULE_LICENSE("GPL"); module_init(init_fsm); diff --git a/lib/ts_kmp.c b/lib/ts_kmp.c index c77a3d537f24..5520dc28255a 100644 --- a/lib/ts_kmp.c +++ b/lib/ts_kmp.c @@ -147,6 +147,7 @@ static void __exit exit_kmp(void) textsearch_unregister(&kmp_ops); } +MODULE_DESCRIPTION("Knuth-Morris-Pratt text search implementation"); MODULE_LICENSE("GPL"); module_init(init_kmp); -- cgit v1.2.3 From 2f183c68345a26213e5e7f798399bee68d1c4a97 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Fri, 31 May 2024 12:04:57 +0300 Subject: kernel/panic: add verbose logging of kernel taints in backtraces With nearly 20 taint flags and respective characters, it's getting a bit difficult to remember what each taint flag character means. Add verbose logging of the set taints in the format: Tainted: [P]=PROPRIETARY_MODULE, [W]=WARN in dump_stack_print_info() when there are taints. Note that the "negative flag" G is not included. Link: https://lkml.kernel.org/r/7321e306166cb2ca2807ab8639e665baa2462e9c.1717146197.git.jani.nikula@intel.com Signed-off-by: Jani Nikula Reviewed-by: Greg Kroah-Hartman Signed-off-by: Andrew Morton --- include/linux/panic.h | 8 +++++--- kernel/panic.c | 45 ++++++++++++++++++++++++++++++++++----------- lib/dump_stack.c | 3 +++ 3 files changed, 42 insertions(+), 14 deletions(-) (limited to 'lib') diff --git a/include/linux/panic.h b/include/linux/panic.h index 6717b15e798c..3130e0b5116b 100644 --- a/include/linux/panic.h +++ b/include/linux/panic.h @@ -77,9 +77,10 @@ static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout) #define TAINT_FLAGS_MAX ((1UL << TAINT_FLAGS_COUNT) - 1) struct taint_flag { - char c_true; /* character printed when tainted */ - char c_false; /* character printed when not tainted */ - bool module; /* also show as a per-module taint flag */ + char c_true; /* character printed when tainted */ + char c_false; /* character printed when not tainted */ + bool module; /* also show as a per-module taint flag */ + const char *desc; /* verbose description of the set taint flag */ }; extern const struct taint_flag taint_flags[TAINT_FLAGS_COUNT]; @@ -90,6 +91,7 @@ enum lockdep_ok { }; extern const char *print_tainted(void); +extern const char *print_tainted_verbose(void); extern void add_taint(unsigned flag, enum lockdep_ok); extern int test_taint(unsigned flag); extern unsigned long get_taint(void); diff --git a/kernel/panic.c b/kernel/panic.c index 21975497bfa4..f861bedc1925 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -475,6 +475,7 @@ EXPORT_SYMBOL(panic); [ TAINT_##taint ] = { \ .c_true = _c_true, .c_false = _c_false, \ .module = _module, \ + .desc = #taint, \ } /* @@ -505,8 +506,9 @@ const struct taint_flag taint_flags[TAINT_FLAGS_COUNT] = { #undef TAINT_FLAG -static void print_tainted_seq(struct seq_buf *s) +static void print_tainted_seq(struct seq_buf *s, bool verbose) { + const char *sep = ""; int i; if (!tainted_mask) { @@ -520,10 +522,32 @@ static void print_tainted_seq(struct seq_buf *s) bool is_set = test_bit(i, &tainted_mask); char c = is_set ? t->c_true : t->c_false; - seq_buf_putc(s, c); + if (verbose) { + if (is_set) { + seq_buf_printf(s, "%s[%c]=%s", sep, c, t->desc); + sep = ", "; + } + } else { + seq_buf_putc(s, c); + } } } +static const char *_print_tainted(bool verbose) +{ + /* FIXME: what should the size be? */ + static char buf[sizeof(taint_flags)]; + struct seq_buf s; + + BUILD_BUG_ON(ARRAY_SIZE(taint_flags) != TAINT_FLAGS_COUNT); + + seq_buf_init(&s, buf, sizeof(buf)); + + print_tainted_seq(&s, verbose); + + return seq_buf_str(&s); +} + /** * print_tainted - return a string to represent the kernel taint state. * @@ -534,16 +558,15 @@ static void print_tainted_seq(struct seq_buf *s) */ const char *print_tainted(void) { - static char buf[TAINT_FLAGS_COUNT + sizeof("Tainted: ")]; - struct seq_buf s; - - BUILD_BUG_ON(ARRAY_SIZE(taint_flags) != TAINT_FLAGS_COUNT); - - seq_buf_init(&s, buf, sizeof(buf)); - - print_tainted_seq(&s); + return _print_tainted(false); +} - return seq_buf_str(&s); +/** + * print_tainted_verbose - A more verbose version of print_tainted() + */ +const char *print_tainted_verbose(void) +{ + return _print_tainted(true); } int test_taint(unsigned flag) diff --git a/lib/dump_stack.c b/lib/dump_stack.c index 222c6d6c8281..8b6b70eaf949 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -62,6 +62,9 @@ void dump_stack_print_info(const char *log_lvl) (int)strcspn(init_utsname()->version, " "), init_utsname()->version, BUILD_ID_VAL); + if (get_taint()) + printk("%s%s\n", log_lvl, print_tainted_verbose()); + if (dump_stack_arch_desc_str[0] != '\0') printk("%sHardware name: %s\n", log_lvl, dump_stack_arch_desc_str); -- cgit v1.2.3 From e471831be2bea5f253396796c7691209c0065c65 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 15:45:22 -0700 Subject: kunit/fortify: add missing MODULE_DESCRIPTION() macros make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/memcpy_kunit.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/fortify_kunit.o Add the missing invocations of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240531-md-lib-fortify_source-v1-1-2c37f7fbaafc@quicinc.com Signed-off-by: Jeff Johnson Cc: Kees Cook Signed-off-by: Andrew Morton --- lib/fortify_kunit.c | 1 + lib/memcpy_kunit.c | 1 + 2 files changed, 2 insertions(+) (limited to 'lib') diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index e17d520f532c..47b5d247c37e 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -1096,4 +1096,5 @@ static struct kunit_suite fortify_test_suite = { kunit_test_suite(fortify_test_suite); +MODULE_DESCRIPTION("Runtime test cases for CONFIG_FORTIFY_SOURCE"); MODULE_LICENSE("GPL"); diff --git a/lib/memcpy_kunit.c b/lib/memcpy_kunit.c index 20ea9038c3ff..d36933554e46 100644 --- a/lib/memcpy_kunit.c +++ b/lib/memcpy_kunit.c @@ -510,4 +510,5 @@ static struct kunit_suite memcpy_test_suite = { kunit_test_suite(memcpy_test_suite); +MODULE_DESCRIPTION("test cases for memcpy(), memmove(), and memset()"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From f069e33dafe17aab332e6671275cc61d16795064 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Sat, 1 Jun 2024 16:33:23 -0700 Subject: KUnit: add missing MODULE_DESCRIPTION() macros for lib/*_test.ko make allmodconfig && make W=1 C=1 reports for lib/*_test.ko: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/atomic64_test.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/hashtable_test.o Add the missing invocations of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240601-md-lib-test2-v1-1-be764b785f17@quicinc.com Signed-off-by: Jeff Johnson Signed-off-by: Andrew Morton --- lib/atomic64_test.c | 1 + lib/hashtable_test.c | 1 + 2 files changed, 2 insertions(+) (limited to 'lib') diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c index d9d170238165..759ea1783cc5 100644 --- a/lib/atomic64_test.c +++ b/lib/atomic64_test.c @@ -273,4 +273,5 @@ static __exit void test_atomics_exit(void) {} module_init(test_atomics_init); module_exit(test_atomics_exit); +MODULE_DESCRIPTION("Testsuite for atomic64_t functions"); MODULE_LICENSE("GPL"); diff --git a/lib/hashtable_test.c b/lib/hashtable_test.c index 1d1b3288dee2..3521de6bad15 100644 --- a/lib/hashtable_test.c +++ b/lib/hashtable_test.c @@ -314,4 +314,5 @@ static struct kunit_suite hashtable_test_module = { kunit_test_suites(&hashtable_test_module); +MODULE_DESCRIPTION("KUnit test for the Kernel Hashtable structures"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 2e29fcb7743649649418e9aadcbcf032d2ec488f Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Sat, 1 Jun 2024 16:09:47 -0700 Subject: lib/asn1_encoder: add missing MODULE_DESCRIPTION() macro make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/asn1_encoder.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240601-md-lib-asn1_encoder-v1-1-8c634ed2d2e8@quicinc.com Signed-off-by: Jeff Johnson Signed-off-by: Andrew Morton --- lib/asn1_encoder.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/asn1_encoder.c b/lib/asn1_encoder.c index 0fd3c454a468..92f35aae13b1 100644 --- a/lib/asn1_encoder.c +++ b/lib/asn1_encoder.c @@ -449,4 +449,5 @@ asn1_encode_boolean(unsigned char *data, const unsigned char *end_data, } EXPORT_SYMBOL_GPL(asn1_encode_boolean); +MODULE_DESCRIPTION("Simple encoder primitives for ASN.1 BER/DER/CER"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 1c5a13b39daf823b4b0349ef2345bf997cb8c257 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Sat, 1 Jun 2024 10:53:34 -0700 Subject: kunit: add missing MODULE_DESCRIPTION() macros to lib/*.c make allmodconfig && make W=1 C=1 reports for lib/*kunit: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/bitfield_kunit.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/checksum_kunit.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/cmdline_kunit.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/is_signed_type_kunit.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/overflow_kunit.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/stackinit_kunit.o Add the missing invocations of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240601-md-lib-kunit-tests-v1-1-4493fe0032b9@quicinc.com Signed-off-by: Jeff Johnson Signed-off-by: Andrew Morton --- lib/bitfield_kunit.c | 1 + lib/checksum_kunit.c | 1 + lib/cmdline_kunit.c | 1 + lib/is_signed_type_kunit.c | 1 + lib/overflow_kunit.c | 1 + lib/stackinit_kunit.c | 1 + 6 files changed, 6 insertions(+) (limited to 'lib') diff --git a/lib/bitfield_kunit.c b/lib/bitfield_kunit.c index 1473d8b4bf0f..5ccd86f61896 100644 --- a/lib/bitfield_kunit.c +++ b/lib/bitfield_kunit.c @@ -151,4 +151,5 @@ static struct kunit_suite bitfields_test_suite = { kunit_test_suites(&bitfields_test_suite); MODULE_AUTHOR("Johannes Berg "); +MODULE_DESCRIPTION("Test cases for bitfield helpers"); MODULE_LICENSE("GPL"); diff --git a/lib/checksum_kunit.c b/lib/checksum_kunit.c index 404dba36bae3..4e4d081a1d3b 100644 --- a/lib/checksum_kunit.c +++ b/lib/checksum_kunit.c @@ -639,4 +639,5 @@ static struct kunit_suite checksum_test_suite = { kunit_test_suites(&checksum_test_suite); MODULE_AUTHOR("Noah Goldstein "); +MODULE_DESCRIPTION("Test cases csum_* APIs"); MODULE_LICENSE("GPL"); diff --git a/lib/cmdline_kunit.c b/lib/cmdline_kunit.c index 705b82736be0..c1602f797637 100644 --- a/lib/cmdline_kunit.c +++ b/lib/cmdline_kunit.c @@ -153,4 +153,5 @@ static struct kunit_suite cmdline_test_suite = { }; kunit_test_suite(cmdline_test_suite); +MODULE_DESCRIPTION("Test cases for API provided by cmdline.c"); MODULE_LICENSE("GPL"); diff --git a/lib/is_signed_type_kunit.c b/lib/is_signed_type_kunit.c index 0a7f6ae62839..88adbe813f3a 100644 --- a/lib/is_signed_type_kunit.c +++ b/lib/is_signed_type_kunit.c @@ -46,4 +46,5 @@ static struct kunit_suite is_signed_type_test_suite = { kunit_test_suite(is_signed_type_test_suite); +MODULE_DESCRIPTION("is_signed_type() KUnit test suite"); MODULE_LICENSE("Dual MIT/GPL"); diff --git a/lib/overflow_kunit.c b/lib/overflow_kunit.c index d305b0c054bb..f314a0c15a6d 100644 --- a/lib/overflow_kunit.c +++ b/lib/overflow_kunit.c @@ -1237,4 +1237,5 @@ static struct kunit_suite overflow_test_suite = { kunit_test_suite(overflow_test_suite); +MODULE_DESCRIPTION("Test cases for arithmetic overflow checks"); MODULE_LICENSE("Dual MIT/GPL"); diff --git a/lib/stackinit_kunit.c b/lib/stackinit_kunit.c index 3bc14d1ee816..c14c6f8e6308 100644 --- a/lib/stackinit_kunit.c +++ b/lib/stackinit_kunit.c @@ -471,4 +471,5 @@ static struct kunit_suite stackinit_test_suite = { kunit_test_suites(&stackinit_test_suite); +MODULE_DESCRIPTION("Test cases for compiler-based stack variable zeroing"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 683da20738fd3e0687a939b684c4a94a09de096c Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 19:19:09 -0700 Subject: uuid: add missing MODULE_DESCRIPTION() macro make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_uuid.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240531-md-lib-test_uuid-v1-1-67fa498104c0@quicinc.com Signed-off-by: Jeff Johnson Acked-by: Andy Shevchenko Signed-off-by: Andrew Morton --- lib/test_uuid.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/test_uuid.c b/lib/test_uuid.c index cd819c397dc7..0124fad5d72c 100644 --- a/lib/test_uuid.c +++ b/lib/test_uuid.c @@ -130,4 +130,5 @@ static void __exit test_uuid_exit(void) module_exit(test_uuid_exit); MODULE_AUTHOR("Andy Shevchenko "); +MODULE_DESCRIPTION("Test cases for lib/uuid.c module"); MODULE_LICENSE("Dual BSD/GPL"); -- cgit v1.2.3 From d46a555d3cd97132e21014b28a459c928925fa0f Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 18:49:47 -0700 Subject: siphash: add missing MODULE_DESCRIPTION() macro make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/siphash_kunit.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240531-md-lib-siphash_kunit-v1-1-38688065b796@quicinc.com Signed-off-by: Jeff Johnson Cc: Jason A. Donenfeld Signed-off-by: Andrew Morton --- lib/siphash_kunit.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/siphash_kunit.c b/lib/siphash_kunit.c index a3c697e8be35..26bd4e8dc03e 100644 --- a/lib/siphash_kunit.c +++ b/lib/siphash_kunit.c @@ -194,4 +194,5 @@ static struct kunit_suite siphash_test_suite = { kunit_test_suite(siphash_test_suite); MODULE_AUTHOR("Jason A. Donenfeld "); +MODULE_DESCRIPTION("Test cases for siphash.c"); MODULE_LICENSE("Dual BSD/GPL"); -- cgit v1.2.3 From 7ef148daa56dfcad7b554a79c28b8e94726771a5 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 17:23:09 -0700 Subject: lib/test_kmod: add missing MODULE_DESCRIPTION() macro make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_kmod.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240531-md-lib-test_kmod-v1-1-fdf11bc6095e@quicinc.com Signed-off-by: Jeff Johnson Reviewed-by: Lucas De Marchi Cc: Luis Chamberlain Signed-off-by: Andrew Morton --- lib/test_kmod.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/test_kmod.c b/lib/test_kmod.c index 1eec3b7ac67c..064ed0fce75a 100644 --- a/lib/test_kmod.c +++ b/lib/test_kmod.c @@ -1223,4 +1223,5 @@ static void __exit test_kmod_exit(void) module_exit(test_kmod_exit); MODULE_AUTHOR("Luis R. Rodriguez "); +MODULE_DESCRIPTION("kmod stress test driver"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 09aaf15a7826717b75d2b4305daaee099636ca5c Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 16:45:16 -0700 Subject: lib/test_linear_ranges: add missing MODULE_DESCRIPTION() macro make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_linear_ranges.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240531-md-lib-test_linear_ranges-v1-1-053a1aad37c6@quicinc.com Signed-off-by: Jeff Johnson Reviewed-by: Matti Vaittinen Cc: Mark Brown Signed-off-by: Andrew Morton --- lib/test_linear_ranges.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/test_linear_ranges.c b/lib/test_linear_ranges.c index c18f9c0f1f25..f482be00f1bc 100644 --- a/lib/test_linear_ranges.c +++ b/lib/test_linear_ranges.c @@ -216,4 +216,5 @@ static struct kunit_suite range_test_module = { kunit_test_suites(&range_test_module); +MODULE_DESCRIPTION("KUnit test for the linear_ranges helper"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From d0bff054053f7a46a3819aba55ad803aa639ed7e Mon Sep 17 00:00:00 2001 From: Brian Masney Date: Fri, 7 Jun 2024 11:24:43 -0400 Subject: lib/Kconfig.debug: document panic= command line option and procfs entry for PANIC_TIMEOUT PANIC_TIMEOUT can also be controlled with the panic= kernel command line option and the file /proc/sys/kernel/panic. Let's document both of these in the Kconfig help text. Link: https://lkml.kernel.org/r/20240607152443.925168-1-bmasney@redhat.com Signed-off-by: Brian Masney Reviewed-by: Javier Martinez Canillas Signed-off-by: Andrew Morton --- lib/Kconfig.debug | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 59b6765d86b8..86c24d9ed376 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1043,7 +1043,9 @@ config PANIC_TIMEOUT Set the timeout value (in seconds) until a reboot occurs when the kernel panics. If n = 0, then we wait forever. A timeout value n > 0 will wait n seconds before rebooting, while a timeout - value n < 0 will reboot immediately. + value n < 0 will reboot immediately. This setting can be overridden + with the kernel command line option panic=, and from userspace via + /proc/sys/kernel/panic. config LOCKUP_DETECTOR bool -- cgit v1.2.3 From c8dab79f9eef6f1063128f1340f266321cccd17c Mon Sep 17 00:00:00 2001 From: I Hsin Cheng Date: Fri, 14 Jun 2024 23:46:03 +0800 Subject: lib/plist.c: avoid worst case scenario in plist_add Worst case scenario of plist_add() happens when the priority of the inserted plist_node is going to be the largest after the insertion is done. The cost is going to be more significant when the original plist is longer, because the iterator is going to traverse the whole plist to find the correct position to insert the new node. The situation can be avoided by using a reverse iterator at the same time, doing so the maximum possible number of iteration is going to shrink from N to N/2. The proposed change of plist_add pasts the test in lib/plist.c to validate its correctness, also add the worst case scenario test for plist_add() in plist_test(). The worst case test are tested with the size of test_data and test_node growing from 200 to 1000. The result are showned in the following table, in which we can observed that the proposed change of plist_add performs better than the original version, and the difference between these two implementations are more significant with the size of N growing. The random case test [1], and best case test [2] are also provided, with result showing the proposed change performs slightly better in random case test while the original implementation performs slightly better in best case test, while the difference in both test are minor, we can see them as even in those two situations. ----------------------------------------------------------- | Test size | 200 | 400 | 600 | 800 | 1000 | ----------------------------------------------------------- | new_plist_add | 140911| 548681| 1220512| 2048493| 3763755| ----------------------------------------------------------- | old_plist_add | 188198| 774222| 1643547| 3008929| 4947435| ----------------------------------------------------------- Link: https://lkml.kernel.org/r/20240614154603.65203-1-richard120310@gmail.com Signed-off-by: I Hsin Cheng Signed-off-by: Ching-Chun (Jim) Huang Signed-off-by: Andrew Morton --- lib/plist.c | 38 +++++++++++++++++++++++++++++++++++++- 1 file changed, 37 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/plist.c b/lib/plist.c index 2e51829d3db9..c6bce1226874 100644 --- a/lib/plist.c +++ b/lib/plist.c @@ -72,7 +72,7 @@ static void plist_check_head(struct plist_head *head) */ void plist_add(struct plist_node *node, struct plist_head *head) { - struct plist_node *first, *iter, *prev = NULL; + struct plist_node *first, *iter, *prev = NULL, *last, *reverse_iter; struct list_head *node_next = &head->node_list; plist_check_head(head); @@ -83,16 +83,26 @@ void plist_add(struct plist_node *node, struct plist_head *head) goto ins_node; first = iter = plist_first(head); + last = reverse_iter = list_entry(first->prio_list.prev, struct plist_node, prio_list); do { if (node->prio < iter->prio) { node_next = &iter->node_list; break; + } else if (node->prio >= reverse_iter->prio) { + prev = reverse_iter; + iter = list_entry(reverse_iter->prio_list.next, + struct plist_node, prio_list); + if (likely(reverse_iter != last)) + node_next = &iter->node_list; + break; } prev = iter; iter = list_entry(iter->prio_list.next, struct plist_node, prio_list); + reverse_iter = list_entry(reverse_iter->prio_list.prev, + struct plist_node, prio_list); } while (iter != first); if (!prev || prev->prio != node->prio) @@ -255,6 +265,32 @@ static int __init plist_test(void) } printk(KERN_DEBUG "end plist test\n"); + + /* Worst case test for plist_add() */ + unsigned int test_data[241]; + + for (i = 0; i < ARRAY_SIZE(test_data); i++) + test_data[i] = i; + + ktime_t start, end, time_elapsed = 0; + + plist_head_init(&test_head); + + for (i = 0; i < ARRAY_SIZE(test_node); i++) { + plist_node_init(test_node + i, 0); + test_node[i].prio = test_data[i]; + } + + for (i = 0; i < ARRAY_SIZE(test_node); i++) { + if (plist_node_empty(test_node + i)) { + start = ktime_get(); + plist_add(test_node + i, &test_head); + end = ktime_get(); + time_elapsed += (end - start); + } + } + + pr_debug("plist_add worst case test time elapsed %lld\n", time_elapsed); return 0; } -- cgit v1.2.3 From d2917ff19962951399bc33f596648836cc5a0be4 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Fri, 14 Jun 2024 21:13:58 -0700 Subject: lib/dump_stack: report process UID in dump_stack_print_info() To make it easier to identify the crashing process, report effective UID when dumping the stack. Link: https://lkml.kernel.org/r/20240615041358.103791-1-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- lib/dump_stack.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/dump_stack.c b/lib/dump_stack.c index 8b6b70eaf949..1a996fbbf50a 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -54,8 +54,10 @@ void __init dump_stack_set_arch_desc(const char *fmt, ...) */ void dump_stack_print_info(const char *log_lvl) { - printk("%sCPU: %d PID: %d Comm: %.20s %s%s %s %.*s" BUILD_ID_FMT "\n", - log_lvl, raw_smp_processor_id(), current->pid, current->comm, + printk("%sCPU: %d UID: %u PID: %d Comm: %.20s %s%s %s %.*s" BUILD_ID_FMT "\n", + log_lvl, raw_smp_processor_id(), + __kuid_val(current_real_cred()->euid), + current->pid, current->comm, kexec_crash_loaded() ? "Kdump: loaded " : "", print_tainted(), init_utsname()->release, -- cgit v1.2.3 From 303474913271af4eb3ec1c5f955d1e01682f3e1f Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Wed, 19 Jun 2024 13:59:15 -0700 Subject: KUnit: add missing MODULE_DESCRIPTION() macros for lib/test_*.ko make allmodconfig && make W=1 C=1 reports for lib/test_*.ko: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_hexdump.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_dhry.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_firmware.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_sysctl.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_hash.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_ida.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_list_sort.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_min_heap.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_module.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_sort.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_static_keys.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_static_key_base.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_memcat_p.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_blackhole_dev.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_meminit.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_free_pages.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_kprobes.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_ref_tracker.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_bits.o Add the missing invocations of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240619-md-lib-test-v2-1-301e30eeba1e@quicinc.com Signed-off-by: Jeff Johnson Reviewed-by: Kees Cook Reviewed-by: Masami Hiramatsu (Google) Cc: Anil S Keshavamurthy Cc: "David S. Miller" Cc: Masami Hiramatsu (Google) Cc: "Naveen N. Rao" Signed-off-by: Andrew Morton --- lib/dhry_run.c | 1 + lib/test-kstrtox.c | 1 + lib/test_bits.c | 1 + lib/test_blackhole_dev.c | 1 + lib/test_firmware.c | 1 + lib/test_free_pages.c | 1 + lib/test_hash.c | 1 + lib/test_hexdump.c | 1 + lib/test_ida.c | 1 + lib/test_kprobes.c | 3 ++- lib/test_list_sort.c | 1 + lib/test_memcat_p.c | 1 + lib/test_meminit.c | 1 + lib/test_min_heap.c | 1 + lib/test_module.c | 1 + lib/test_ref_tracker.c | 3 ++- lib/test_sort.c | 1 + lib/test_static_key_base.c | 1 + lib/test_static_keys.c | 1 + lib/test_sysctl.c | 1 + 20 files changed, 22 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/dhry_run.c b/lib/dhry_run.c index e6a279dabf84..4a6d05ce4361 100644 --- a/lib/dhry_run.c +++ b/lib/dhry_run.c @@ -83,4 +83,5 @@ static int __init dhry_init(void) module_init(dhry_init); MODULE_AUTHOR("Geert Uytterhoeven "); +MODULE_DESCRIPTION("Dhrystone benchmark test module"); MODULE_LICENSE("GPL"); diff --git a/lib/test-kstrtox.c b/lib/test-kstrtox.c index f355f67169b6..ee87fef66cb5 100644 --- a/lib/test-kstrtox.c +++ b/lib/test-kstrtox.c @@ -732,4 +732,5 @@ static int __init test_kstrtox_init(void) return -EINVAL; } module_init(test_kstrtox_init); +MODULE_DESCRIPTION("Module test for kstrto*() APIs"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/lib/test_bits.c b/lib/test_bits.c index c9368a2314e7..01313980f175 100644 --- a/lib/test_bits.c +++ b/lib/test_bits.c @@ -72,4 +72,5 @@ static struct kunit_suite bits_test_suite = { }; kunit_test_suite(bits_test_suite); +MODULE_DESCRIPTION("Test cases for functions and macros in bits.h"); MODULE_LICENSE("GPL"); diff --git a/lib/test_blackhole_dev.c b/lib/test_blackhole_dev.c index f247089d63c0..ec290ac2a0d9 100644 --- a/lib/test_blackhole_dev.c +++ b/lib/test_blackhole_dev.c @@ -96,4 +96,5 @@ module_init(test_blackholedev_init); module_exit(test_blackholedev_exit); MODULE_AUTHOR("Mahesh Bandewar "); +MODULE_DESCRIPTION("module test of the blackhole_dev"); MODULE_LICENSE("GPL"); diff --git a/lib/test_firmware.c b/lib/test_firmware.c index 9cfdcd6d21db..bcb32cbff188 100644 --- a/lib/test_firmware.c +++ b/lib/test_firmware.c @@ -1567,4 +1567,5 @@ static void __exit test_firmware_exit(void) module_exit(test_firmware_exit); MODULE_AUTHOR("Kees Cook "); +MODULE_DESCRIPTION("interface to trigger and test firmware loading"); MODULE_LICENSE("GPL"); diff --git a/lib/test_free_pages.c b/lib/test_free_pages.c index 9ebf6f5549f3..48952364c540 100644 --- a/lib/test_free_pages.c +++ b/lib/test_free_pages.c @@ -44,4 +44,5 @@ static void m_ex(void) module_init(m_in); module_exit(m_ex); MODULE_AUTHOR("Matthew Wilcox "); +MODULE_DESCRIPTION("Check that free_pages() doesn't leak memory"); MODULE_LICENSE("GPL"); diff --git a/lib/test_hash.c b/lib/test_hash.c index bb25fda34794..a7af39662a0a 100644 --- a/lib/test_hash.c +++ b/lib/test_hash.c @@ -235,4 +235,5 @@ static struct kunit_suite hash_test_suite = { kunit_test_suite(hash_test_suite); +MODULE_DESCRIPTION("Test cases for and "); MODULE_LICENSE("GPL"); diff --git a/lib/test_hexdump.c b/lib/test_hexdump.c index fe2682bb21e6..751645645988 100644 --- a/lib/test_hexdump.c +++ b/lib/test_hexdump.c @@ -253,4 +253,5 @@ static void __exit test_hexdump_exit(void) module_exit(test_hexdump_exit); MODULE_AUTHOR("Andy Shevchenko "); +MODULE_DESCRIPTION("Test cases for lib/hexdump.c module"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/lib/test_ida.c b/lib/test_ida.c index 072a49897e71..c80155a1956d 100644 --- a/lib/test_ida.c +++ b/lib/test_ida.c @@ -214,4 +214,5 @@ static void ida_exit(void) module_init(ida_checks); module_exit(ida_exit); MODULE_AUTHOR("Matthew Wilcox "); +MODULE_DESCRIPTION("Test the IDA API"); MODULE_LICENSE("GPL"); diff --git a/lib/test_kprobes.c b/lib/test_kprobes.c index 0648f7154f5c..b7582010125c 100644 --- a/lib/test_kprobes.c +++ b/lib/test_kprobes.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * test_kprobes.c - simple sanity test for *probes + * test_kprobes.c - simple sanity test for k*probes * * Copyright IBM Corp. 2008 */ @@ -400,4 +400,5 @@ static struct kunit_suite kprobes_test_suite = { kunit_test_suites(&kprobes_test_suite); +MODULE_DESCRIPTION("simple sanity test for k*probes"); MODULE_LICENSE("GPL"); diff --git a/lib/test_list_sort.c b/lib/test_list_sort.c index cc5f335f29b5..30879abc8a42 100644 --- a/lib/test_list_sort.c +++ b/lib/test_list_sort.c @@ -119,4 +119,5 @@ static struct kunit_suite list_sort_suite = { kunit_test_suites(&list_sort_suite); +MODULE_DESCRIPTION("list_sort() KUnit test suite"); MODULE_LICENSE("GPL"); diff --git a/lib/test_memcat_p.c b/lib/test_memcat_p.c index 849c477d49d0..7e0797a6bebf 100644 --- a/lib/test_memcat_p.c +++ b/lib/test_memcat_p.c @@ -112,4 +112,5 @@ static void __exit test_memcat_p_exit(void) module_init(test_memcat_p_init); module_exit(test_memcat_p_exit); +MODULE_DESCRIPTION("Test cases for memcat_p() in lib/memcat_p.c"); MODULE_LICENSE("GPL"); diff --git a/lib/test_meminit.c b/lib/test_meminit.c index 0dc173849a54..6298f66c964b 100644 --- a/lib/test_meminit.c +++ b/lib/test_meminit.c @@ -436,4 +436,5 @@ static int __init test_meminit_init(void) } module_init(test_meminit_init); +MODULE_DESCRIPTION("Test cases for SL[AOU]B/page initialization at alloc/free time"); MODULE_LICENSE("GPL"); diff --git a/lib/test_min_heap.c b/lib/test_min_heap.c index 9e1feb9b679c..64c877e73b64 100644 --- a/lib/test_min_heap.c +++ b/lib/test_min_heap.c @@ -226,4 +226,5 @@ static void __exit test_min_heap_exit(void) } module_exit(test_min_heap_exit); +MODULE_DESCRIPTION("Test cases for the min max heap"); MODULE_LICENSE("GPL"); diff --git a/lib/test_module.c b/lib/test_module.c index debd19e35198..3d1b29b74807 100644 --- a/lib/test_module.c +++ b/lib/test_module.c @@ -31,4 +31,5 @@ static void __exit test_module_exit(void) module_exit(test_module_exit); MODULE_AUTHOR("Kees Cook "); +MODULE_DESCRIPTION("module loading subsystem test module"); MODULE_LICENSE("GPL"); diff --git a/lib/test_ref_tracker.c b/lib/test_ref_tracker.c index 49970a7c96f3..b983ceb12afc 100644 --- a/lib/test_ref_tracker.c +++ b/lib/test_ref_tracker.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Referrence tracker self test. + * Reference tracker self test. * * Copyright (c) 2021 Eric Dumazet */ @@ -112,4 +112,5 @@ static void __exit test_ref_tracker_exit(void) module_init(test_ref_tracker_init); module_exit(test_ref_tracker_exit); +MODULE_DESCRIPTION("Reference tracker self test"); MODULE_LICENSE("GPL v2"); diff --git a/lib/test_sort.c b/lib/test_sort.c index da4495125097..cd4a338d1153 100644 --- a/lib/test_sort.c +++ b/lib/test_sort.c @@ -57,4 +57,5 @@ static struct kunit_suite sort_test_suite = { kunit_test_suites(&sort_test_suite); +MODULE_DESCRIPTION("sort() KUnit test suite"); MODULE_LICENSE("GPL"); diff --git a/lib/test_static_key_base.c b/lib/test_static_key_base.c index 5089a2e2bdd8..9f507672afa5 100644 --- a/lib/test_static_key_base.c +++ b/lib/test_static_key_base.c @@ -57,4 +57,5 @@ module_init(test_static_key_base_init); module_exit(test_static_key_base_exit); MODULE_AUTHOR("Jason Baron "); +MODULE_DESCRIPTION("Kernel module to support testing static keys"); MODULE_LICENSE("GPL"); diff --git a/lib/test_static_keys.c b/lib/test_static_keys.c index 42daa74be029..00c715f30df9 100644 --- a/lib/test_static_keys.c +++ b/lib/test_static_keys.c @@ -236,4 +236,5 @@ module_init(test_static_key_init); module_exit(test_static_key_exit); MODULE_AUTHOR("Jason Baron "); +MODULE_DESCRIPTION("Kernel module for testing static keys"); MODULE_LICENSE("GPL"); diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c index 9321d850931f..b6696fa1d426 100644 --- a/lib/test_sysctl.c +++ b/lib/test_sysctl.c @@ -280,4 +280,5 @@ static void __exit test_sysctl_exit(void) module_exit(test_sysctl_exit); MODULE_AUTHOR("Luis R. Rodriguez "); +MODULE_DESCRIPTION("proc sysctl test driver"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 0e942053e4dc42a760f48c1981f3239825430f15 Mon Sep 17 00:00:00 2001 From: Heng Qi Date: Fri, 21 Jun 2024 18:13:49 +0800 Subject: linux/dim: move useful macros to .h file Useful macros will be used effectively elsewhere. These will be utilized in subsequent patches. Signed-off-by: Heng Qi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240621101353.107425-2-hengqi@linux.alibaba.com Signed-off-by: Jakub Kicinski --- include/linux/dim.h | 7 +++++++ lib/dim/net_dim.c | 6 ------ 2 files changed, 7 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/include/linux/dim.h b/include/linux/dim.h index f343bc9aa2ec..43398f5eade2 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -10,6 +10,13 @@ #include #include +/* Number of DIM profiles and period mode. */ +#define NET_DIM_PARAMS_NUM_PROFILES 5 +#define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256 +#define NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE 128 +#define NET_DIM_DEF_PROFILE_CQE 1 +#define NET_DIM_DEF_PROFILE_EQE 1 + /* * Number of events between DIM iterations. * Causes a moderation of the algorithm run. diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index 4e32f7aaac86..67d5beb34dc3 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -11,12 +11,6 @@ * There are different set of profiles for RX/TX CQs. * Each profile size must be of NET_DIM_PARAMS_NUM_PROFILES */ -#define NET_DIM_PARAMS_NUM_PROFILES 5 -#define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256 -#define NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE 128 -#define NET_DIM_DEF_PROFILE_CQE 1 -#define NET_DIM_DEF_PROFILE_EQE 1 - #define NET_DIM_RX_EQE_PROFILES { \ {.usec = 1, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \ {.usec = 8, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \ -- cgit v1.2.3 From b65e697a7c9e0ae28a6255257d8b9b3271960426 Mon Sep 17 00:00:00 2001 From: Heng Qi Date: Fri, 21 Jun 2024 18:13:50 +0800 Subject: dim: make DIMLIB dependent on NET DIMLIB's capabilities are supplied by the dim, net_dim, and rdma_dim objects, and dim's interfaces solely act as a base for net_dim and rdma_dim and are not explicitly used anywhere else. rdma_dim is utilized by the infiniband driver, while net_dim is for network devices, excluding the soc/fsl driver. In this patch, net_dim relies on some NET's interfaces, thus DIMLIB needs to explicitly depend on the NET Kconfig. The soc/fsl driver uses the functions provided by net_dim, so it also needs to depend on NET. Signed-off-by: Heng Qi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240621101353.107425-3-hengqi@linux.alibaba.com Signed-off-by: Jakub Kicinski --- drivers/soc/fsl/Kconfig | 2 +- lib/Kconfig | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/drivers/soc/fsl/Kconfig b/drivers/soc/fsl/Kconfig index fcec6ed83d5e..a1e0bc8c1757 100644 --- a/drivers/soc/fsl/Kconfig +++ b/drivers/soc/fsl/Kconfig @@ -22,7 +22,7 @@ config FSL_GUTS config FSL_MC_DPIO tristate "QorIQ DPAA2 DPIO driver" - depends on FSL_MC_BUS + depends on FSL_MC_BUS && NET select SOC_BUS select FSL_GUTS select DIMLIB diff --git a/lib/Kconfig b/lib/Kconfig index b0a76dff5c18..b38849af6f13 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -623,6 +623,7 @@ config SIGNATURE config DIMLIB tristate + depends on NET help Dynamic Interrupt Moderation library. Implements an algorithm for dynamically changing CQ moderation values -- cgit v1.2.3 From f750dfe825b904164688adeb147950e0e0c4d262 Mon Sep 17 00:00:00 2001 From: Heng Qi Date: Fri, 21 Jun 2024 18:13:51 +0800 Subject: ethtool: provide customized dim profile management The NetDIM library, currently leveraged by an array of NICs, delivers excellent acceleration benefits. Nevertheless, NICs vary significantly in their dim profile list prerequisites. Specifically, virtio-net backends may present diverse sw or hw device implementation, making a one-size-fits-all parameter list impractical. On Alibaba Cloud, the virtio DPU's performance under the default DIM profile falls short of expectations, partly due to a mismatch in parameter configuration. I also noticed that ice/idpf/ena and other NICs have customized profilelist or placed some restrictions on dim capabilities. Motivated by this, I tried adding new params for "ethtool -C" that provides a per-device control to modify and access a device's interrupt parameters. Usage ======== The target NIC is named ethx. Assume that ethx only declares support for rx profile setting (with DIM_PROFILE_RX flag set in profile_flags) and supports modification of usec and pkt fields. 1. Query the currently customized list of the device $ ethtool -c ethx ... rx-profile: {.usec = 1, .pkts = 256, .comps = n/a,}, {.usec = 8, .pkts = 256, .comps = n/a,}, {.usec = 64, .pkts = 256, .comps = n/a,}, {.usec = 128, .pkts = 256, .comps = n/a,}, {.usec = 256, .pkts = 256, .comps = n/a,} tx-profile: n/a 2. Tune $ ethtool -C ethx rx-profile 1,1,n_2,n,n_3,3,n_4,4,n_n,5,n "n" means do not modify this field. $ ethtool -c ethx ... rx-profile: {.usec = 1, .pkts = 1, .comps = n/a,}, {.usec = 2, .pkts = 256, .comps = n/a,}, {.usec = 3, .pkts = 3, .comps = n/a,}, {.usec = 4, .pkts = 4, .comps = n/a,}, {.usec = 256, .pkts = 5, .comps = n/a,} tx-profile: n/a 3. Hint If the device does not support some type of customized dim profiles, the corresponding "n/a" will display. If the "n/a" field is being modified, -EOPNOTSUPP will be reported. Signed-off-by: Heng Qi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240621101353.107425-4-hengqi@linux.alibaba.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/ethtool.yaml | 31 +++ Documentation/networking/ethtool-netlink.rst | 8 + Documentation/networking/net_dim.rst | 42 +++++ include/linux/dim.h | 58 ++++++ include/linux/ethtool.h | 4 +- include/linux/netdevice.h | 3 + include/uapi/linux/ethtool_netlink.h | 22 +++ lib/dim/net_dim.c | 70 +++++++ net/Kconfig | 1 + net/ethtool/coalesce.c | 273 ++++++++++++++++++++++++++- 10 files changed, 509 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 00dc61358be8..6c2ab3d1c22f 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -414,6 +414,26 @@ attribute-sets: name: combined-count type: u32 + - + name: irq-moderation + attributes: + - + name: usec + type: u32 + - + name: pkts + type: u32 + - + name: comps + type: u32 + - + name: profile + attributes: + - + name: irq-moderation + type: nest + multi-attr: true + nested-attributes: irq-moderation - name: coalesce attributes: @@ -502,6 +522,15 @@ attribute-sets: - name: tx-aggr-time-usecs type: u32 + - + name: rx-profile + type: nest + nested-attributes: profile + - + name: tx-profile + type: nest + nested-attributes: profile + - name: pause-stat attributes: @@ -1325,6 +1354,8 @@ operations: - tx-aggr-max-bytes - tx-aggr-max-frames - tx-aggr-time-usecs + - rx-profile + - tx-profile dump: *coalesce-get-op - name: coalesce-set diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 160bfb0ae8ba..7ec08e903bab 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1033,6 +1033,8 @@ Kernel response contents: ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES`` u32 max aggr size, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES`` u32 max aggr packets, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS`` u32 time (us), aggr, Tx + ``ETHTOOL_A_COALESCE_RX_PROFILE`` nested profile of DIM, Rx + ``ETHTOOL_A_COALESCE_TX_PROFILE`` nested profile of DIM, Tx =========================================== ====== ======================= Attributes are only included in reply if their value is not zero or the @@ -1062,6 +1064,10 @@ block should be sent. This feature is mainly of interest for specific USB devices which does not cope well with frequent small-sized URBs transmissions. +``ETHTOOL_A_COALESCE_RX_PROFILE`` and ``ETHTOOL_A_COALESCE_TX_PROFILE`` refer +to DIM parameters, see `Generic Network Dynamic Interrupt Moderation (Net DIM) +`_. + COALESCE_SET ============ @@ -1098,6 +1104,8 @@ Request contents: ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES`` u32 max aggr size, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES`` u32 max aggr packets, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS`` u32 time (us), aggr, Tx + ``ETHTOOL_A_COALESCE_RX_PROFILE`` nested profile of DIM, Rx + ``ETHTOOL_A_COALESCE_TX_PROFILE`` nested profile of DIM, Tx =========================================== ====== ======================= Request is rejected if it attributes declared as unsupported by driver (i.e. diff --git a/Documentation/networking/net_dim.rst b/Documentation/networking/net_dim.rst index 3bed9fd95336..8908fd7b0a8d 100644 --- a/Documentation/networking/net_dim.rst +++ b/Documentation/networking/net_dim.rst @@ -169,6 +169,48 @@ usage is not complete but it should make the outline of the usage clear. ... } + +Tuning DIM +========== + +Net DIM serves a range of network devices and delivers excellent acceleration +benefits. Yet, it has been observed that some preset configurations of DIM may +not align seamlessly with the varying specifications of network devices, and +this discrepancy has been identified as a factor to the suboptimal performance +outcomes of DIM-enabled network devices, related to a mismatch in profiles. + +To address this issue, Net DIM introduces a per-device control to modify and +access a device's ``rx-profile`` and ``tx-profile`` parameters: +Assume that the target network device is named ethx, and ethx only declares +support for RX profile setting and supports modification of ``usec`` field +and ``pkts`` field (See the data structure: +:c:type:`struct dim_cq_moder `). + +You can use ethtool to modify the current RX DIM profile where all +values are 64:: + + $ ethtool -C ethx rx-profile 1,1,n_2,2,n_3,n,n_n,4,n_n,n,n + +``n`` means do not modify this field, and ``_`` separates structure +elements of the profile array. + +Querying the current profiles using:: + + $ ethtool -c ethx + ... + rx-profile: + {.usec = 1, .pkts = 1, .comps = n/a,}, + {.usec = 2, .pkts = 2, .comps = n/a,}, + {.usec = 3, .pkts = 64, .comps = n/a,}, + {.usec = 64, .pkts = 4, .comps = n/a,}, + {.usec = 64, .pkts = 64, .comps = n/a,} + tx-profile: n/a + +If the network device does not support specific fields of DIM profiles, +the corresponding ``n/a`` will display. If the ``n/a`` field is being +modified, error messages will be reported. + + Dynamic Interrupt Moderation (DIM) library API ============================================== diff --git a/include/linux/dim.h b/include/linux/dim.h index 43398f5eade2..e0f39bd85432 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -10,6 +10,8 @@ #include #include +struct net_device; + /* Number of DIM profiles and period mode. */ #define NET_DIM_PARAMS_NUM_PROFILES 5 #define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256 @@ -45,12 +47,45 @@ * @pkts: CQ packet counter suggestion (by DIM) * @comps: Completion counter * @cq_period_mode: CQ period count mode (from CQE/EQE) + * @rcu: for asynchronous kfree_rcu */ struct dim_cq_moder { u16 usec; u16 pkts; u16 comps; u8 cq_period_mode; + struct rcu_head rcu; +}; + +#define DIM_PROFILE_RX BIT(0) /* support rx profile modification */ +#define DIM_PROFILE_TX BIT(1) /* support tx profile modification */ + +#define DIM_COALESCE_USEC BIT(0) /* support usec field modification */ +#define DIM_COALESCE_PKTS BIT(1) /* support pkts field modification */ +#define DIM_COALESCE_COMPS BIT(2) /* support comps field modification */ + +/** + * struct dim_irq_moder - Structure for irq moderation information. + * Used to collect irq moderation related information. + * + * @profile_flags: DIM_PROFILE_* + * @coal_flags: DIM_COALESCE_* for Rx and Tx + * @dim_rx_mode: Rx DIM period count mode: CQE or EQE + * @dim_tx_mode: Tx DIM period count mode: CQE or EQE + * @rx_profile: DIM profile list for Rx + * @tx_profile: DIM profile list for Tx + * @rx_dim_work: Rx DIM worker scheduled by net_dim() + * @tx_dim_work: Tx DIM worker scheduled by net_dim() + */ +struct dim_irq_moder { + u8 profile_flags; + u8 coal_flags; + u8 dim_rx_mode; + u8 dim_tx_mode; + struct dim_cq_moder __rcu *rx_profile; + struct dim_cq_moder __rcu *tx_profile; + void (*rx_dim_work)(struct work_struct *work); + void (*tx_dim_work)(struct work_struct *work); }; /** @@ -198,6 +233,29 @@ enum dim_step_result { DIM_ON_EDGE, }; +/** + * net_dim_init_irq_moder - collect information to initialize irq moderation + * @dev: target network device + * @profile_flags: Rx or Tx profile modification capability + * @coal_flags: irq moderation params flags + * @rx_mode: CQ period mode for Rx + * @tx_mode: CQ period mode for Tx + * @rx_dim_work: Rx worker called after dim decision + * @tx_dim_work: Tx worker called after dim decision + * + * Return: 0 on success or a negative error code. + */ +int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags, + u8 coal_flags, u8 rx_mode, u8 tx_mode, + void (*rx_dim_work)(struct work_struct *work), + void (*tx_dim_work)(struct work_struct *work)); + +/** + * net_dim_free_irq_moder - free fields for irq moderation + * @dev: target network device + */ +void net_dim_free_irq_moder(struct net_device *dev); + /** * dim_on_top - check if current state is a good place to stop (top location) * @dim: DIM context diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 6fd9107d3cc0..959196af7f5a 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -284,7 +284,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, #define ETHTOOL_COALESCE_TX_AGGR_MAX_BYTES BIT(24) #define ETHTOOL_COALESCE_TX_AGGR_MAX_FRAMES BIT(25) #define ETHTOOL_COALESCE_TX_AGGR_TIME_USECS BIT(26) -#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(26, 0) +#define ETHTOOL_COALESCE_RX_PROFILE BIT(27) +#define ETHTOOL_COALESCE_TX_PROFILE BIT(28) +#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(28, 0) #define ETHTOOL_COALESCE_USECS \ (ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4e81660b4462..cc18acd3c58b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2402,6 +2402,9 @@ struct net_device { /** @page_pools: page pools created for this netdevice */ struct hlist_head page_pools; #endif + + /** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */ + struct dim_irq_moder *irq_moder; }; #define to_net_dev(d) container_of(d, struct net_device, dev) diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index b49b804b9495..d15856c7e001 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -415,12 +415,34 @@ enum { ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES, /* u32 */ ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES, /* u32 */ ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS, /* u32 */ + /* nest - _A_PROFILE_IRQ_MODERATION */ + ETHTOOL_A_COALESCE_RX_PROFILE, + /* nest - _A_PROFILE_IRQ_MODERATION */ + ETHTOOL_A_COALESCE_TX_PROFILE, /* add new constants above here */ __ETHTOOL_A_COALESCE_CNT, ETHTOOL_A_COALESCE_MAX = (__ETHTOOL_A_COALESCE_CNT - 1) }; +enum { + ETHTOOL_A_PROFILE_UNSPEC, + /* nest, _A_IRQ_MODERATION_* */ + ETHTOOL_A_PROFILE_IRQ_MODERATION, + __ETHTOOL_A_PROFILE_CNT, + ETHTOOL_A_PROFILE_MAX = (__ETHTOOL_A_PROFILE_CNT - 1) +}; + +enum { + ETHTOOL_A_IRQ_MODERATION_UNSPEC, + ETHTOOL_A_IRQ_MODERATION_USEC, /* u32 */ + ETHTOOL_A_IRQ_MODERATION_PKTS, /* u32 */ + ETHTOOL_A_IRQ_MODERATION_COMPS, /* u32 */ + + __ETHTOOL_A_IRQ_MODERATION_CNT, + ETHTOOL_A_IRQ_MODERATION_MAX = (__ETHTOOL_A_IRQ_MODERATION_CNT - 1) +}; + /* PAUSE */ enum { diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index 67d5beb34dc3..0cd41277c7a3 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -4,6 +4,7 @@ */ #include +#include /* * Net DIM profiles: @@ -95,6 +96,75 @@ net_dim_get_def_tx_moderation(u8 cq_period_mode) } EXPORT_SYMBOL(net_dim_get_def_tx_moderation); +int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags, + u8 coal_flags, u8 rx_mode, u8 tx_mode, + void (*rx_dim_work)(struct work_struct *work), + void (*tx_dim_work)(struct work_struct *work)) +{ + struct dim_cq_moder *rxp = NULL, *txp; + struct dim_irq_moder *moder; + int len; + + dev->irq_moder = kzalloc(sizeof(*dev->irq_moder), GFP_KERNEL); + if (!dev->irq_moder) + return -ENOMEM; + + moder = dev->irq_moder; + len = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*moder->rx_profile); + + moder->coal_flags = coal_flags; + moder->profile_flags = profile_flags; + + if (profile_flags & DIM_PROFILE_RX) { + moder->rx_dim_work = rx_dim_work; + moder->dim_rx_mode = rx_mode; + rxp = kmemdup(rx_profile[rx_mode], len, GFP_KERNEL); + if (!rxp) + goto free_moder; + + rcu_assign_pointer(moder->rx_profile, rxp); + } + + if (profile_flags & DIM_PROFILE_TX) { + moder->tx_dim_work = tx_dim_work; + moder->dim_tx_mode = tx_mode; + txp = kmemdup(tx_profile[tx_mode], len, GFP_KERNEL); + if (!txp) + goto free_rxp; + + rcu_assign_pointer(moder->tx_profile, txp); + } + + return 0; + +free_rxp: + kfree(rxp); +free_moder: + kfree(moder); + return -ENOMEM; +} +EXPORT_SYMBOL(net_dim_init_irq_moder); + +/* RTNL lock is held. */ +void net_dim_free_irq_moder(struct net_device *dev) +{ + struct dim_cq_moder *rxp, *txp; + + if (!dev->irq_moder) + return; + + rxp = rtnl_dereference(dev->irq_moder->rx_profile); + txp = rtnl_dereference(dev->irq_moder->tx_profile); + + rcu_assign_pointer(dev->irq_moder->rx_profile, NULL); + rcu_assign_pointer(dev->irq_moder->tx_profile, NULL); + + kfree_rcu(rxp, rcu); + kfree_rcu(txp, rcu); + kfree(dev->irq_moder); +} +EXPORT_SYMBOL(net_dim_free_irq_moder); + static int net_dim_step(struct dim *dim) { if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2)) diff --git a/net/Kconfig b/net/Kconfig index 9fe65fa26e48..d27d0deac0bf 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -508,6 +508,7 @@ config FAILOVER config ETHTOOL_NETLINK bool "Netlink interface for ethtool" + select DIMLIB default y help An alternative userspace interface for ethtool based on generic diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c index 83112c1a71ae..759b16e3d134 100644 --- a/net/ethtool/coalesce.c +++ b/net/ethtool/coalesce.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#include #include "netlink.h" #include "common.h" @@ -82,6 +83,14 @@ static int coalesce_prepare_data(const struct ethnl_req_info *req_base, static int coalesce_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { + int modersz = nla_total_size(0) + /* _PROFILE_IRQ_MODERATION, nest */ + nla_total_size(sizeof(u32)) + /* _IRQ_MODERATION_USEC */ + nla_total_size(sizeof(u32)) + /* _IRQ_MODERATION_PKTS */ + nla_total_size(sizeof(u32)); /* _IRQ_MODERATION_COMPS */ + + int total_modersz = nla_total_size(0) + /* _{R,T}X_PROFILE, nest */ + modersz * NET_DIM_PARAMS_NUM_PROFILES; + return nla_total_size(sizeof(u32)) + /* _RX_USECS */ nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES */ nla_total_size(sizeof(u32)) + /* _RX_USECS_IRQ */ @@ -108,7 +117,8 @@ static int coalesce_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u8)) + /* _USE_CQE_MODE_RX */ nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_BYTES */ nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_FRAMES */ - nla_total_size(sizeof(u32)); /* _TX_AGGR_TIME_USECS */ + nla_total_size(sizeof(u32)) + /* _TX_AGGR_TIME_USECS */ + total_modersz * 2; /* _{R,T}X_PROFILE */ } static bool coalesce_put_u32(struct sk_buff *skb, u16 attr_type, u32 val, @@ -127,14 +137,84 @@ static bool coalesce_put_bool(struct sk_buff *skb, u16 attr_type, u32 val, return nla_put_u8(skb, attr_type, !!val); } +/** + * coalesce_put_profile - fill reply with a nla nest with four child nla nests. + * @skb: socket buffer the message is stored in + * @attr_type: nest attr type ETHTOOL_A_COALESCE_*X_PROFILE + * @profile: data passed to userspace + * @coal_flags: modifiable parameters supported by the driver + * + * Put a dim profile nest attribute. Refer to ETHTOOL_A_PROFILE_IRQ_MODERATION. + * + * Return: 0 on success or a negative error code. + */ +static int coalesce_put_profile(struct sk_buff *skb, u16 attr_type, + const struct dim_cq_moder *profile, + u8 coal_flags) +{ + struct nlattr *profile_attr, *moder_attr; + int i, ret; + + if (!profile || !coal_flags) + return 0; + + profile_attr = nla_nest_start(skb, attr_type); + if (!profile_attr) + return -EMSGSIZE; + + for (i = 0; i < NET_DIM_PARAMS_NUM_PROFILES; i++) { + moder_attr = nla_nest_start(skb, + ETHTOOL_A_PROFILE_IRQ_MODERATION); + if (!moder_attr) { + ret = -EMSGSIZE; + goto cancel_profile; + } + + if (coal_flags & DIM_COALESCE_USEC) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_USEC, + profile[i].usec); + if (ret) + goto cancel_moder; + } + + if (coal_flags & DIM_COALESCE_PKTS) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_PKTS, + profile[i].pkts); + if (ret) + goto cancel_moder; + } + + if (coal_flags & DIM_COALESCE_COMPS) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_COMPS, + profile[i].comps); + if (ret) + goto cancel_moder; + } + + nla_nest_end(skb, moder_attr); + } + + nla_nest_end(skb, profile_attr); + + return 0; + +cancel_moder: + nla_nest_cancel(skb, moder_attr); +cancel_profile: + nla_nest_cancel(skb, profile_attr); + return ret; +} + static int coalesce_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base); const struct kernel_ethtool_coalesce *kcoal = &data->kernel_coalesce; + struct dim_irq_moder *moder = req_base->dev->irq_moder; const struct ethtool_coalesce *coal = &data->coalesce; u32 supported = data->supported_params; + int ret = 0; if (coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS, coal->rx_coalesce_usecs, supported) || @@ -192,11 +272,41 @@ static int coalesce_fill_reply(struct sk_buff *skb, kcoal->tx_aggr_time_usecs, supported)) return -EMSGSIZE; - return 0; + if (!moder) + return 0; + + rcu_read_lock(); + if (moder->profile_flags & DIM_PROFILE_RX) { + ret = coalesce_put_profile(skb, ETHTOOL_A_COALESCE_RX_PROFILE, + rcu_dereference(moder->rx_profile), + moder->coal_flags); + if (ret) + goto out; + } + + if (moder->profile_flags & DIM_PROFILE_TX) + ret = coalesce_put_profile(skb, ETHTOOL_A_COALESCE_TX_PROFILE, + rcu_dereference(moder->tx_profile), + moder->coal_flags); + +out: + rcu_read_unlock(); + return ret; } /* COALESCE_SET */ +static const struct nla_policy coalesce_irq_moderation_policy[] = { + [ETHTOOL_A_IRQ_MODERATION_USEC] = { .type = NLA_U32 }, + [ETHTOOL_A_IRQ_MODERATION_PKTS] = { .type = NLA_U32 }, + [ETHTOOL_A_IRQ_MODERATION_COMPS] = { .type = NLA_U32 }, +}; + +static const struct nla_policy coalesce_profile_policy[] = { + [ETHTOOL_A_PROFILE_IRQ_MODERATION] = + NLA_POLICY_NESTED(coalesce_irq_moderation_policy), +}; + const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), @@ -227,6 +337,10 @@ const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_RX_PROFILE] = + NLA_POLICY_NESTED(coalesce_profile_policy), + [ETHTOOL_A_COALESCE_TX_PROFILE] = + NLA_POLICY_NESTED(coalesce_profile_policy), }; static int @@ -234,6 +348,7 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; + struct dim_irq_moder *irq_moder = req_info->dev->irq_moder; struct nlattr **tb = info->attrs; u32 supported_params; u16 a; @@ -243,6 +358,12 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, /* make sure that only supported parameters are present */ supported_params = ops->supported_coalesce_params; + if (irq_moder && irq_moder->profile_flags & DIM_PROFILE_RX) + supported_params |= ETHTOOL_COALESCE_RX_PROFILE; + + if (irq_moder && irq_moder->profile_flags & DIM_PROFILE_TX) + supported_params |= ETHTOOL_COALESCE_TX_PROFILE; + for (a = ETHTOOL_A_COALESCE_RX_USECS; a < __ETHTOOL_A_COALESCE_CNT; a++) if (tb[a] && !(supported_params & attr_to_mask(a))) { NL_SET_ERR_MSG_ATTR(info->extack, tb[a], @@ -253,6 +374,138 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, return 1; } +/** + * ethnl_update_irq_moder - update a specific field in the given profile + * @irq_moder: place that collects dim related information + * @irq_field: field in profile to modify + * @attr_type: attr type ETHTOOL_A_IRQ_MODERATION_* + * @tb: netlink attribute with new values or null + * @coal_bit: DIM_COALESCE_* bit from coal_flags + * @mod: pointer to bool for modification tracking + * @extack: netlink extended ack + * + * Return: 0 on success or a negative error code. + */ +static int ethnl_update_irq_moder(struct dim_irq_moder *irq_moder, + u16 *irq_field, u16 attr_type, + struct nlattr **tb, + u8 coal_bit, bool *mod, + struct netlink_ext_ack *extack) +{ + int ret = 0; + u32 val; + + if (!tb[attr_type]) + return 0; + + if (irq_moder->coal_flags & coal_bit) { + val = nla_get_u32(tb[attr_type]); + if (*irq_field == val) + return 0; + + *irq_field = val; + *mod = true; + } else { + NL_SET_BAD_ATTR(extack, tb[attr_type]); + ret = -EOPNOTSUPP; + } + + return ret; +} + +/** + * ethnl_update_profile - get a profile nest with child nests from userspace. + * @dev: netdevice to update the profile + * @dst: profile get from the driver and modified by ethnl_update_profile. + * @nests: nest attr ETHTOOL_A_COALESCE_*X_PROFILE to set profile. + * @mod: pointer to bool for modification tracking + * @extack: Netlink extended ack + * + * Layout of nests: + * Nested ETHTOOL_A_COALESCE_*X_PROFILE attr + * Nested ETHTOOL_A_PROFILE_IRQ_MODERATION attr + * ETHTOOL_A_IRQ_MODERATION_USEC attr + * ETHTOOL_A_IRQ_MODERATION_PKTS attr + * ETHTOOL_A_IRQ_MODERATION_COMPS attr + * ... + * Nested ETHTOOL_A_PROFILE_IRQ_MODERATION attr + * ETHTOOL_A_IRQ_MODERATION_USEC attr + * ETHTOOL_A_IRQ_MODERATION_PKTS attr + * ETHTOOL_A_IRQ_MODERATION_COMPS attr + * + * Return: 0 on success or a negative error code. + */ +static int ethnl_update_profile(struct net_device *dev, + struct dim_cq_moder __rcu **dst, + const struct nlattr *nests, + bool *mod, + struct netlink_ext_ack *extack) +{ + int len_irq_moder = ARRAY_SIZE(coalesce_irq_moderation_policy); + struct nlattr *tb[ARRAY_SIZE(coalesce_irq_moderation_policy)]; + struct dim_irq_moder *irq_moder = dev->irq_moder; + struct dim_cq_moder *new_profile, *old_profile; + int ret, rem, i = 0, len; + struct nlattr *nest; + + if (!nests) + return 0; + + if (!*dst) + return -EOPNOTSUPP; + + old_profile = rtnl_dereference(*dst); + len = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*old_profile); + new_profile = kmemdup(old_profile, len, GFP_KERNEL); + if (!new_profile) + return -ENOMEM; + + nla_for_each_nested_type(nest, ETHTOOL_A_PROFILE_IRQ_MODERATION, + nests, rem) { + ret = nla_parse_nested(tb, len_irq_moder - 1, nest, + coalesce_irq_moderation_policy, + extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].usec, + ETHTOOL_A_IRQ_MODERATION_USEC, + tb, DIM_COALESCE_USEC, + mod, extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].pkts, + ETHTOOL_A_IRQ_MODERATION_PKTS, + tb, DIM_COALESCE_PKTS, + mod, extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].comps, + ETHTOOL_A_IRQ_MODERATION_COMPS, + tb, DIM_COALESCE_COMPS, + mod, extack); + if (ret) + goto err_out; + + i++; + } + + /* After the profile is modified, dim itself is a dynamic + * mechanism and will quickly fit to the appropriate + * coalescing parameters according to the new profile. + */ + rcu_assign_pointer(*dst, new_profile); + kfree_rcu(old_profile, rcu); + + return 0; + +err_out: + kfree(new_profile); + return ret; +} + static int __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info, bool *dual_change) @@ -317,6 +570,22 @@ __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info, ethnl_update_u32(&kernel_coalesce.tx_aggr_time_usecs, tb[ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS], &mod); + if (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_RX) { + ret = ethnl_update_profile(dev, &dev->irq_moder->rx_profile, + tb[ETHTOOL_A_COALESCE_RX_PROFILE], + &mod, info->extack); + if (ret < 0) + return ret; + } + + if (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_TX) { + ret = ethnl_update_profile(dev, &dev->irq_moder->tx_profile, + tb[ETHTOOL_A_COALESCE_TX_PROFILE], + &mod, info->extack); + if (ret < 0) + return ret; + } + /* Update operation modes */ ethnl_update_bool32(&coalesce.use_adaptive_rx_coalesce, tb[ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX], &mod_mode); -- cgit v1.2.3 From 13ba28c5cd047e272f9dbbeb5c62c403873d8987 Mon Sep 17 00:00:00 2001 From: Heng Qi Date: Fri, 21 Jun 2024 18:13:52 +0800 Subject: dim: add new interfaces for initialization and getting results DIM-related mode and work have been collected in one same place, so new interfaces are added to provide convenience. Signed-off-by: Heng Qi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240621101353.107425-5-hengqi@linux.alibaba.com Signed-off-by: Jakub Kicinski --- include/linux/dim.h | 48 +++++++++++++++++++++++++++++++++++++ lib/dim/net_dim.c | 68 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 116 insertions(+) (limited to 'lib') diff --git a/include/linux/dim.h b/include/linux/dim.h index e0f39bd85432..1b581ff25a15 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -256,6 +256,54 @@ int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags, */ void net_dim_free_irq_moder(struct net_device *dev); +/** + * net_dim_setting - initialize DIM's cq mode and schedule worker + * @dev: target network device + * @dim: DIM context + * @is_tx: true indicates the tx direction, false indicates the rx direction + */ +void net_dim_setting(struct net_device *dev, struct dim *dim, bool is_tx); + +/** + * net_dim_work_cancel - synchronously cancel dim's worker + * @dim: DIM context + */ +void net_dim_work_cancel(struct dim *dim); + +/** + * net_dim_get_rx_irq_moder - get DIM rx results based on profile_ix + * @dev: target network device + * @dim: DIM context + * + * Return: DIM irq moderation + */ +struct dim_cq_moder +net_dim_get_rx_irq_moder(struct net_device *dev, struct dim *dim); + +/** + * net_dim_get_tx_irq_moder - get DIM tx results based on profile_ix + * @dev: target network device + * @dim: DIM context + * + * Return: DIM irq moderation + */ +struct dim_cq_moder +net_dim_get_tx_irq_moder(struct net_device *dev, struct dim *dim); + +/** + * net_dim_set_rx_mode - set DIM rx cq mode + * @dev: target network device + * @rx_mode: target rx cq mode + */ +void net_dim_set_rx_mode(struct net_device *dev, u8 rx_mode); + +/** + * net_dim_set_tx_mode - set DIM tx cq mode + * @dev: target network device + * @tx_mode: target tx cq mode + */ +void net_dim_set_tx_mode(struct net_device *dev, u8 tx_mode); + /** * dim_on_top - check if current state is a good place to stop (top location) * @dim: DIM context diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index 0cd41277c7a3..d7e7028e9b19 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -165,6 +165,74 @@ void net_dim_free_irq_moder(struct net_device *dev) } EXPORT_SYMBOL(net_dim_free_irq_moder); +void net_dim_setting(struct net_device *dev, struct dim *dim, bool is_tx) +{ + struct dim_irq_moder *irq_moder = dev->irq_moder; + + if (!irq_moder) + return; + + if (is_tx) { + INIT_WORK(&dim->work, irq_moder->tx_dim_work); + dim->mode = READ_ONCE(irq_moder->dim_tx_mode); + return; + } + + INIT_WORK(&dim->work, irq_moder->rx_dim_work); + dim->mode = READ_ONCE(irq_moder->dim_rx_mode); +} +EXPORT_SYMBOL(net_dim_setting); + +void net_dim_work_cancel(struct dim *dim) +{ + cancel_work_sync(&dim->work); +} +EXPORT_SYMBOL(net_dim_work_cancel); + +struct dim_cq_moder net_dim_get_rx_irq_moder(struct net_device *dev, + struct dim *dim) +{ + struct dim_cq_moder res, *profile; + + rcu_read_lock(); + profile = rcu_dereference(dev->irq_moder->rx_profile); + res = profile[dim->profile_ix]; + rcu_read_unlock(); + + res.cq_period_mode = dim->mode; + + return res; +} +EXPORT_SYMBOL(net_dim_get_rx_irq_moder); + +struct dim_cq_moder net_dim_get_tx_irq_moder(struct net_device *dev, + struct dim *dim) +{ + struct dim_cq_moder res, *profile; + + rcu_read_lock(); + profile = rcu_dereference(dev->irq_moder->tx_profile); + res = profile[dim->profile_ix]; + rcu_read_unlock(); + + res.cq_period_mode = dim->mode; + + return res; +} +EXPORT_SYMBOL(net_dim_get_tx_irq_moder); + +void net_dim_set_rx_mode(struct net_device *dev, u8 rx_mode) +{ + WRITE_ONCE(dev->irq_moder->dim_rx_mode, rx_mode); +} +EXPORT_SYMBOL(net_dim_set_rx_mode); + +void net_dim_set_tx_mode(struct net_device *dev, u8 tx_mode) +{ + WRITE_ONCE(dev->irq_moder->dim_tx_mode, tx_mode); +} +EXPORT_SYMBOL(net_dim_set_tx_mode); + static int net_dim_step(struct dim *dim) { if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2)) -- cgit v1.2.3 From d65f3767de20782e75d8a665fdc54f822f344802 Mon Sep 17 00:00:00 2001 From: Leon Hwang Date: Tue, 25 Jun 2024 22:53:51 +0800 Subject: bpf: Fix tailcall cases in test_bpf Since f663a03c8e35 ("bpf, x64: Remove tail call detection"), tail_call_reachable won't be detected in x86 JIT. And, tail_call_reachable is provided by verifier. Therefore, in test_bpf, the tail_call_reachable must be provided in test cases before running. Fix and test: [ 174.828662] test_bpf: #0 Tail call leaf jited:1 170 PASS [ 174.829574] test_bpf: #1 Tail call 2 jited:1 244 PASS [ 174.830363] test_bpf: #2 Tail call 3 jited:1 296 PASS [ 174.830924] test_bpf: #3 Tail call 4 jited:1 719 PASS [ 174.831863] test_bpf: #4 Tail call load/store leaf jited:1 197 PASS [ 174.832240] test_bpf: #5 Tail call load/store jited:1 326 PASS [ 174.832240] test_bpf: #6 Tail call error path, max count reached jited:1 2214 PASS [ 174.835713] test_bpf: #7 Tail call count preserved across function calls jited:1 609751 PASS [ 175.446098] test_bpf: #8 Tail call error path, NULL target jited:1 472 PASS [ 175.447597] test_bpf: #9 Tail call error path, index out of range jited:1 206 PASS [ 175.448833] test_bpf: test_tail_calls: Summary: 10 PASSED, 0 FAILED, [10/10 JIT'ed] Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202406251415.c51865bc-oliver.sang@intel.com Fixes: f663a03c8e35 ("bpf, x64: Remove tail call detection") Signed-off-by: Leon Hwang Link: https://lore.kernel.org/r/20240625145351.40072-1-hffilwlqm@gmail.com Signed-off-by: Alexei Starovoitov --- lib/test_bpf.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'lib') diff --git a/lib/test_bpf.c b/lib/test_bpf.c index ce5716c3999a..b7acc29bcc3b 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -15198,6 +15198,7 @@ struct tail_call_test { int flags; int result; int stack_depth; + bool has_tail_call; }; /* Flags that can be passed to tail call test cases */ @@ -15273,6 +15274,7 @@ static struct tail_call_test tail_call_tests[] = { BPF_EXIT_INSN(), }, .result = 3, + .has_tail_call = true, }, { "Tail call 3", @@ -15283,6 +15285,7 @@ static struct tail_call_test tail_call_tests[] = { BPF_EXIT_INSN(), }, .result = 6, + .has_tail_call = true, }, { "Tail call 4", @@ -15293,6 +15296,7 @@ static struct tail_call_test tail_call_tests[] = { BPF_EXIT_INSN(), }, .result = 10, + .has_tail_call = true, }, { "Tail call load/store leaf", @@ -15323,6 +15327,7 @@ static struct tail_call_test tail_call_tests[] = { }, .result = 0, .stack_depth = 16, + .has_tail_call = true, }, { "Tail call error path, max count reached", @@ -15335,6 +15340,7 @@ static struct tail_call_test tail_call_tests[] = { }, .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, .result = (MAX_TAIL_CALL_CNT + 1) * MAX_TESTRUNS, + .has_tail_call = true, }, { "Tail call count preserved across function calls", @@ -15357,6 +15363,7 @@ static struct tail_call_test tail_call_tests[] = { .stack_depth = 8, .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, .result = (MAX_TAIL_CALL_CNT + 1) * MAX_TESTRUNS, + .has_tail_call = true, }, { "Tail call error path, NULL target", @@ -15369,6 +15376,7 @@ static struct tail_call_test tail_call_tests[] = { }, .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, .result = MAX_TESTRUNS, + .has_tail_call = true, }, { "Tail call error path, index out of range", @@ -15381,6 +15389,7 @@ static struct tail_call_test tail_call_tests[] = { }, .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, .result = MAX_TESTRUNS, + .has_tail_call = true, }, }; @@ -15430,6 +15439,7 @@ static __init int prepare_tail_call_tests(struct bpf_array **pprogs) fp->len = len; fp->type = BPF_PROG_TYPE_SOCKET_FILTER; fp->aux->stack_depth = test->stack_depth; + fp->aux->tail_call_reachable = test->has_tail_call; memcpy(fp->insnsi, test->insns, len * sizeof(struct bpf_insn)); /* Relocate runtime tail call offsets and addresses */ -- cgit v1.2.3 From 6a4805b2f51a2e5dc346651e0d0cd8abcc2937c8 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 16:07:26 -0700 Subject: string: kunit: add missing MODULE_DESCRIPTION() macros make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/string_kunit.o WARNING: modpost: missing MODULE_DESCRIPTION() in lib/string_helpers_kunit.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Signed-off-by: Jeff Johnson Link: https://lore.kernel.org/r/20240531-md-lib-string-v1-1-2738cf057d94@quicinc.com Signed-off-by: Kees Cook --- lib/string_helpers_kunit.c | 1 + lib/string_kunit.c | 1 + 2 files changed, 2 insertions(+) (limited to 'lib') diff --git a/lib/string_helpers_kunit.c b/lib/string_helpers_kunit.c index f88e39fd68d6..c853046183d2 100644 --- a/lib/string_helpers_kunit.c +++ b/lib/string_helpers_kunit.c @@ -625,4 +625,5 @@ static struct kunit_suite string_helpers_test_suite = { kunit_test_suites(&string_helpers_test_suite); +MODULE_DESCRIPTION("Test cases for string helpers module"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/lib/string_kunit.c b/lib/string_kunit.c index 2a812decf14b..c919e3293da6 100644 --- a/lib/string_kunit.c +++ b/lib/string_kunit.c @@ -633,4 +633,5 @@ static struct kunit_suite string_test_suite = { kunit_test_suites(&string_test_suite); +MODULE_DESCRIPTION("Test cases for string functions"); MODULE_LICENSE("GPL v2"); -- cgit v1.2.3 From 961a2851324561caed579764ffbee3db82b32829 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 21 Jun 2024 21:39:33 +0300 Subject: build-id: require program headers to be right after ELF header Neither ELF spec not ELF loader require program header to be placed right after ELF header, but build-id code very much assumes such placement: See find_get_page(vma->vm_file->f_mapping, 0); line and checks against PAGE_SIZE. Returns errors for now until someone rewrites build-id parser to be more inline with load_elf_binary(). Link: https://lkml.kernel.org/r/d58bc281-6ca7-467a-9a64-40fa214bd63e@p183 Signed-off-by: Alexey Dobriyan Reviewed-by: Jiri Olsa Signed-off-by: Andrew Morton --- lib/buildid.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'lib') diff --git a/lib/buildid.c b/lib/buildid.c index 7954dd92e36c..e02b5507418b 100644 --- a/lib/buildid.c +++ b/lib/buildid.c @@ -73,6 +73,13 @@ static int get_build_id_32(const void *page_addr, unsigned char *build_id, Elf32_Phdr *phdr; int i; + /* + * FIXME + * Neither ELF spec nor ELF loader require that program headers + * start immediately after ELF header. + */ + if (ehdr->e_phoff != sizeof(Elf32_Ehdr)) + return -EINVAL; /* only supports phdr that fits in one page */ if (ehdr->e_phnum > (PAGE_SIZE - sizeof(Elf32_Ehdr)) / sizeof(Elf32_Phdr)) @@ -98,6 +105,13 @@ static int get_build_id_64(const void *page_addr, unsigned char *build_id, Elf64_Phdr *phdr; int i; + /* + * FIXME + * Neither ELF spec nor ELF loader require that program headers + * start immediately after ELF header. + */ + if (ehdr->e_phoff != sizeof(Elf64_Ehdr)) + return -EINVAL; /* only supports phdr that fits in one page */ if (ehdr->e_phnum > (PAGE_SIZE - sizeof(Elf64_Ehdr)) / sizeof(Elf64_Phdr)) -- cgit v1.2.3 From 2a49c8b6b6d0dba9c5a4e921f07fbd7a8ad7a5f1 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Sat, 22 Jun 2024 07:55:05 -0700 Subject: selftests/fpu: add missing MODULE_DESCRIPTION() macro make allmodconfig && make W=1 C=1 now reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_fpu.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240622-md-i386-lib-test_fpu_glue-v1-1-a4e40b7b1264@quicinc.com Fixes: 9613736d852d ("selftests/fpu: move FP code to a separate translation unit") Signed-off-by: Jeff Johnson Reviewed-by: Samuel Holland Signed-off-by: Andrew Morton --- lib/test_fpu_glue.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/test_fpu_glue.c b/lib/test_fpu_glue.c index eef282a2715f..074f30301f29 100644 --- a/lib/test_fpu_glue.c +++ b/lib/test_fpu_glue.c @@ -59,4 +59,5 @@ static void __exit test_fpu_exit(void) module_init(test_fpu_init); module_exit(test_fpu_exit); +MODULE_DESCRIPTION("Test cases for floating point operations"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 4d6cf248325f686f256f2446f3f9d5fbab6e4356 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 19 Jun 2024 13:25:17 -0700 Subject: kunit/usercopy: Disable testing on !CONFIG_MMU Since arch_pick_mmap_layout() is an inline for non-MMU systems, disable this test there. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202406160505.uBge6TMY-lkp@intel.com/ Signed-off-by: Kees Cook Reviewed-by: Rae Moar Reviewed-by: David Gow Signed-off-by: Shuah Khan --- lib/kunit/user_alloc.c | 4 ++++ lib/usercopy_kunit.c | 5 +++++ mm/util.c | 2 ++ 3 files changed, 11 insertions(+) (limited to 'lib') diff --git a/lib/kunit/user_alloc.c b/lib/kunit/user_alloc.c index 76d3d1345ed7..ae935df09a5e 100644 --- a/lib/kunit/user_alloc.c +++ b/lib/kunit/user_alloc.c @@ -30,6 +30,10 @@ static int kunit_attach_mm(void) if (current->mm) return 0; + /* arch_pick_mmap_layout() is only sane with MMU systems. */ + if (!IS_ENABLED(CONFIG_MMU)) + return -EINVAL; + mm = mm_alloc(); if (!mm) return -ENOMEM; diff --git a/lib/usercopy_kunit.c b/lib/usercopy_kunit.c index 45f1e558c464..e819561a540d 100644 --- a/lib/usercopy_kunit.c +++ b/lib/usercopy_kunit.c @@ -290,6 +290,11 @@ static int usercopy_test_init(struct kunit *test) struct usercopy_test_priv *priv; unsigned long user_addr; + if (!IS_ENABLED(CONFIG_MMU)) { + kunit_skip(test, "Userspace allocation testing not available on non-MMU systems"); + return 0; + } + priv = kunit_kzalloc(test, sizeof(*priv), GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, priv); test->priv = priv; diff --git a/mm/util.c b/mm/util.c index df37c47d9374..e70e8e439258 100644 --- a/mm/util.c +++ b/mm/util.c @@ -484,7 +484,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) clear_bit(MMF_TOPDOWN, &mm->flags); } #endif +#ifdef CONFIG_MMU EXPORT_SYMBOL_IF_KUNIT(arch_pick_mmap_layout); +#endif /** * __account_locked_vm - account locked pages to an mm's locked_vm -- cgit v1.2.3 From 67c9971cd6d309ecbcb87b942e22ffc194d7a376 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Wed, 19 Jun 2024 13:26:59 -0700 Subject: kunit/usercopy: Add missing MODULE_DESCRIPTION() Fix warning seen with: $ make allmodconfig && make W=1 C=1 lib/usercopy_kunit.ko WARNING: modpost: missing MODULE_DESCRIPTION() in lib/usercopy_kunit.o Signed-off-by: Jeff Johnson Signed-off-by: Kees Cook Reviewed-by: Rae Moar Reviewed-by: David Gow Signed-off-by: Shuah Khan --- lib/usercopy_kunit.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/usercopy_kunit.c b/lib/usercopy_kunit.c index e819561a540d..77fa00a13df7 100644 --- a/lib/usercopy_kunit.c +++ b/lib/usercopy_kunit.c @@ -331,4 +331,5 @@ static struct kunit_suite usercopy_test_suite = { kunit_test_suites(&usercopy_test_suite); MODULE_AUTHOR("Kees Cook "); +MODULE_DESCRIPTION("Kernel module for testing copy_to/from_user infrastructure"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From f48955e038eaf43812c3701079c7371abe0315a4 Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Mon, 1 Jul 2024 16:47:54 +0200 Subject: vdso/gettimeofday: Clarify comment about open coded function The two comments state, that the following code open codes something but they lack to specify what exactly is open coded. Expand comments by mentioning the reference to the open coded function. Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Reviewed-by: Vincenzo Frascino Link: https://lore.kernel.org/r/20240701-vdso-cleanup-v1-1-36eb64e7ece2@linutronix.de --- lib/vdso/gettimeofday.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'lib') diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c index 899850bd6f0b..c01eaafd8041 100644 --- a/lib/vdso/gettimeofday.c +++ b/lib/vdso/gettimeofday.c @@ -140,14 +140,14 @@ static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk, do { /* - * Open coded to handle VDSO_CLOCKMODE_TIMENS. Time namespace - * enabled tasks have a special VVAR page installed which - * has vd->seq set to 1 and vd->clock_mode set to - * VDSO_CLOCKMODE_TIMENS. For non time namespace affected tasks - * this does not affect performance because if vd->seq is - * odd, i.e. a concurrent update is in progress the extra - * check for vd->clock_mode is just a few extra - * instructions while spin waiting for vd->seq to become + * Open coded function vdso_read_begin() to handle + * VDSO_CLOCKMODE_TIMENS. Time namespace enabled tasks have a + * special VVAR page installed which has vd->seq set to 1 and + * vd->clock_mode set to VDSO_CLOCKMODE_TIMENS. For non time + * namespace affected tasks this does not affect performance + * because if vd->seq is odd, i.e. a concurrent update is in + * progress the extra check for vd->clock_mode is just a few + * extra instructions while spin waiting for vd->seq to become * even again. */ while (unlikely((seq = READ_ONCE(vd->seq)) & 1)) { @@ -223,8 +223,8 @@ static __always_inline int do_coarse(const struct vdso_data *vd, clockid_t clk, do { /* - * Open coded to handle VDSO_CLOCK_TIMENS. See comment in - * do_hres(). + * Open coded function vdso_read_begin() to handle + * VDSO_CLOCK_TIMENS. See comment in do_hres(). */ while ((seq = READ_ONCE(vd->seq)) & 1) { if (IS_ENABLED(CONFIG_TIME_NS) && -- cgit v1.2.3 From 757234f1ad673e0f86698d75f7fc3bff930b5636 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 20:08:37 -0700 Subject: test_xarray: add missing MODULE_DESCRIPTION() macro make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_xarray.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240531-md-lib-test_xarray-v1-1-42fd6833bdd4@quicinc.com Signed-off-by: Jeff Johnson Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- lib/test_xarray.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/test_xarray.c b/lib/test_xarray.c index ab9cc42a0d74..d5c5cbba33ed 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -2173,4 +2173,5 @@ static void xarray_exit(void) module_init(xarray_checks); module_exit(xarray_exit); MODULE_AUTHOR("Matthew Wilcox "); +MODULE_DESCRIPTION("XArray API test module"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 2ec83987a53e30f3b07090ebd3a03cc7febfc34c Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 19:06:48 -0700 Subject: ubsan: add missing MODULE_DESCRIPTION() macro make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_ubsan.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240531-md-lib-test_ubsan-v1-1-c2a80d258842@quicinc.com Signed-off-by: Jeff Johnson Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Kees Cook Cc: Marco Elver Signed-off-by: Andrew Morton --- lib/test_ubsan.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/test_ubsan.c b/lib/test_ubsan.c index c288df9372ed..5d7b10e98610 100644 --- a/lib/test_ubsan.c +++ b/lib/test_ubsan.c @@ -156,4 +156,5 @@ static void __exit test_ubsan_exit(void) module_exit(test_ubsan_exit); MODULE_AUTHOR("Jinbum Park "); +MODULE_DESCRIPTION("UBSAN unit test"); MODULE_LICENSE("GPL v2"); -- cgit v1.2.3 From a619dd394883ca01e19f81f8a2108cb616907538 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 17:13:16 -0700 Subject: test_maple_tree: add the missing MODULE_DESCRIPTION() macro make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_maple_tree.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240531-md-lib-test_maple_tree-v1-1-7b1b485aeec3@quicinc.com Signed-off-by: Jeff Johnson Reviewed-by: Liam R. Howlett Signed-off-by: Andrew Morton --- lib/test_maple_tree.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c index 399380db449c..31561e0e1a0d 100644 --- a/lib/test_maple_tree.c +++ b/lib/test_maple_tree.c @@ -3946,4 +3946,5 @@ static void __exit maple_tree_harvest(void) module_init(maple_tree_seed); module_exit(maple_tree_harvest); MODULE_AUTHOR("Liam R. Howlett "); +MODULE_DESCRIPTION("maple tree API test module"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 3c666d0a32d83ea5f500ec1ce02c801520044da1 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Fri, 31 May 2024 16:26:03 -0700 Subject: lib: test_hmm: add missing MODULE_DESCRIPTION() macro MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/test_hmm.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240531-lib-md-test_hmm-v1-1-e4aa17daa57b@quicinc.com Signed-off-by: Jeff Johnson Cc: Jérôme Glisse Signed-off-by: Andrew Morton --- lib/test_hmm.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/test_hmm.c b/lib/test_hmm.c index b823ba7cb6a1..ee20e1f9bae9 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -1550,4 +1550,5 @@ static void __exit hmm_dmirror_exit(void) module_init(hmm_dmirror_init); module_exit(hmm_dmirror_exit); +MODULE_DESCRIPTION("HMM (Heterogeneous Memory Management) test module"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 739820a6178b03b1b6b99a467c85e9e7146d51c1 Mon Sep 17 00:00:00 2001 From: JaeJoon Jung Date: Fri, 14 Jun 2024 18:24:28 +0900 Subject: maple_tree: modified return type of mas_wr_store_entry() Since the return value of mas_wr_store_entry() is not used, the return type can be changed to void. Link: https://lkml.kernel.org/r/20240614092428.29491-1-rgbi3307@gmail.com Signed-off-by: JaeJoon Jung Reviewed-by: Liam R. Howlett Cc: Sidhartha Kumar Signed-off-by: Andrew Morton --- lib/maple_tree.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'lib') diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 2d7d27e6ae3c..aa3a5df15b8e 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -4203,31 +4203,28 @@ slow_path: * * Return: The contents that was stored at the index. */ -static inline void *mas_wr_store_entry(struct ma_wr_state *wr_mas) +static inline void mas_wr_store_entry(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; wr_mas->content = mas_start(mas); if (mas_is_none(mas) || mas_is_ptr(mas)) { mas_store_root(mas, wr_mas->entry); - return wr_mas->content; + return; } if (unlikely(!mas_wr_walk(wr_mas))) { mas_wr_spanning_store(wr_mas); - return wr_mas->content; + return; } /* At this point, we are at the leaf node that needs to be altered. */ mas_wr_end_piv(wr_mas); /* New root for a single pointer */ - if (unlikely(!mas->index && mas->last == ULONG_MAX)) { + if (unlikely(!mas->index && mas->last == ULONG_MAX)) mas_new_root(mas, wr_mas->entry); - return wr_mas->content; - } - - mas_wr_modify(wr_mas); - return wr_mas->content; + else + mas_wr_modify(wr_mas); } /** -- cgit v1.2.3 From 89f42df66c32690a2d0087b12948bcf9e336d56e Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Fri, 21 Jun 2024 13:35:04 +0200 Subject: lib/zlib: unpoison DFLTCC output buffers The constraints of the DFLTCC inline assembly are not precise: they do not communicate the size of the output buffers to the compiler, so it cannot automatically instrument it. Add the manual kmsan_unpoison_memory() calls for the output buffers. The logic is the same as in [1]. [1] https://github.com/zlib-ng/zlib-ng/commit/1f5ddcc009ac3511e99fc88736a9e1a6381168c5 Link: https://lkml.kernel.org/r/20240621113706.315500-21-iii@linux.ibm.com Signed-off-by: Ilya Leoshkevich Reported-by: Alexander Gordeev Reviewed-by: Alexander Potapenko Cc: Christian Borntraeger Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Heiko Carstens Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Joonsoo Kim Cc: Cc: Marco Elver Cc: Mark Rutland Cc: Masami Hiramatsu (Google) Cc: Pekka Enberg Cc: Roman Gushchin Cc: Steven Rostedt (Google) Cc: Sven Schnelle Cc: Vasily Gorbik Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- lib/zlib_dfltcc/dfltcc.h | 1 + lib/zlib_dfltcc/dfltcc_util.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 29 insertions(+) (limited to 'lib') diff --git a/lib/zlib_dfltcc/dfltcc.h b/lib/zlib_dfltcc/dfltcc.h index b96232bdd44d..0f2a16d7a48a 100644 --- a/lib/zlib_dfltcc/dfltcc.h +++ b/lib/zlib_dfltcc/dfltcc.h @@ -80,6 +80,7 @@ struct dfltcc_param_v0 { uint8_t csb[1152]; }; +static_assert(offsetof(struct dfltcc_param_v0, csb) == 384); static_assert(sizeof(struct dfltcc_param_v0) == 1536); #define CVT_CRC32 0 diff --git a/lib/zlib_dfltcc/dfltcc_util.h b/lib/zlib_dfltcc/dfltcc_util.h index 4a46b5009f0d..10509270d822 100644 --- a/lib/zlib_dfltcc/dfltcc_util.h +++ b/lib/zlib_dfltcc/dfltcc_util.h @@ -2,6 +2,8 @@ #ifndef DFLTCC_UTIL_H #define DFLTCC_UTIL_H +#include "dfltcc.h" +#include #include /* @@ -20,6 +22,7 @@ typedef enum { #define DFLTCC_CMPR 2 #define DFLTCC_XPND 4 #define HBT_CIRCULAR (1 << 7) +#define DFLTCC_FN_MASK ((1 << 7) - 1) #define HB_BITS 15 #define HB_SIZE (1 << HB_BITS) @@ -34,6 +37,7 @@ static inline dfltcc_cc dfltcc( ) { Byte *t2 = op1 ? *op1 : NULL; + unsigned char *orig_t2 = t2; size_t t3 = len1 ? *len1 : 0; const Byte *t4 = op2 ? *op2 : NULL; size_t t5 = len2 ? *len2 : 0; @@ -59,6 +63,30 @@ static inline dfltcc_cc dfltcc( : "cc", "memory"); t2 = r2; t3 = r3; t4 = r4; t5 = r5; + /* + * Unpoison the parameter block and the output buffer. + * This is a no-op in non-KMSAN builds. + */ + switch (fn & DFLTCC_FN_MASK) { + case DFLTCC_QAF: + kmsan_unpoison_memory(param, sizeof(struct dfltcc_qaf_param)); + break; + case DFLTCC_GDHT: + kmsan_unpoison_memory(param, offsetof(struct dfltcc_param_v0, csb)); + break; + case DFLTCC_CMPR: + kmsan_unpoison_memory(param, sizeof(struct dfltcc_param_v0)); + kmsan_unpoison_memory( + orig_t2, + t2 - orig_t2 + + (((struct dfltcc_param_v0 *)param)->sbb == 0 ? 0 : 1)); + break; + case DFLTCC_XPND: + kmsan_unpoison_memory(param, sizeof(struct dfltcc_param_v0)); + kmsan_unpoison_memory(orig_t2, t2 - orig_t2); + break; + } + if (op1) *op1 = t2; if (len1) -- cgit v1.2.3 From cedb08caac587b55c79d0463400839acab4638c0 Mon Sep 17 00:00:00 2001 From: Hsin Chang Yu Date: Fri, 28 Jun 2024 22:22:29 +0800 Subject: lib/rbtree.c: fix the example typo Replace the "Sr" with "sr", the example is wrong if sl and N don't have child nodes, so sr should be red node. Link: https://lkml.kernel.org/r/20240628142229.69419-1-zxcvb600870024@gmail.com Signed-off-by: Hsin Chang Yu Signed-off-by: Andrew Morton --- lib/rbtree.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/rbtree.c b/lib/rbtree.c index 5114eda6309c..989c2d615f92 100644 --- a/lib/rbtree.c +++ b/lib/rbtree.c @@ -297,9 +297,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root, * / \ / \ * N S --> N sl * / \ \ - * sl Sr S + * sl sr S * \ - * Sr + * sr * * Note: p might be red, and then both * p and sl are red after rotation(which @@ -312,9 +312,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root, * / \ / \ * N sl --> P S * \ / \ - * S N Sr + * S N sr * \ - * Sr + * sr */ tmp1 = tmp2->rb_right; WRITE_ONCE(sibling->rb_left, tmp1); -- cgit v1.2.3 From bee6c683de2f7c086963b20afffb40b03e6c264d Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Thu, 13 Jun 2024 22:01:09 -0700 Subject: lib/zlib: add missing MODULE_DESCRIPTION() macro With ARCH=csky, make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/zlib_deflate/zlib_deflate.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240613-md-csky-lib-zlib_deflate-v1-1-83504d9a27d6@quicinc.com Signed-off-by: Jeff Johnson Cc: Guo Ren Signed-off-by: Andrew Morton --- lib/zlib_deflate/deflate_syms.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/zlib_deflate/deflate_syms.c b/lib/zlib_deflate/deflate_syms.c index 24b740b99678..68941a2350ea 100644 --- a/lib/zlib_deflate/deflate_syms.c +++ b/lib/zlib_deflate/deflate_syms.c @@ -17,4 +17,5 @@ EXPORT_SYMBOL(zlib_deflate); EXPORT_SYMBOL(zlib_deflateInit2); EXPORT_SYMBOL(zlib_deflateEnd); EXPORT_SYMBOL(zlib_deflateReset); +MODULE_DESCRIPTION("Data compression using the deflation algorithm"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 8547d1150f0dbd1d04f397c780182fc83ec2ab16 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Tue, 2 Jul 2024 15:47:59 -0700 Subject: math: rational: add missing MODULE_DESCRIPTION() macro With ARCH=sh, make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/math/rational.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Link: https://lkml.kernel.org/r/20240702-md-sh-lib-math-v1-1-93f4ac4fa8fd@quicinc.com Signed-off-by: Jeff Johnson Signed-off-by: Andrew Morton --- lib/math/rational.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/math/rational.c b/lib/math/rational.c index ec59d426ea63..d2c34e629ee1 100644 --- a/lib/math/rational.c +++ b/lib/math/rational.c @@ -108,4 +108,5 @@ void rational_best_approximation( EXPORT_SYMBOL(rational_best_approximation); +MODULE_DESCRIPTION("Rational fraction support library"); MODULE_LICENSE("GPL v2"); -- cgit v1.2.3 From 2fe29fe945637b9834c5569fbb1c9d4f881d8263 Mon Sep 17 00:00:00 2001 From: Paul Menzel Date: Mon, 1 Jul 2024 17:58:01 +0200 Subject: lib/build_OID_registry: avoid non-destructive substitution for Perl < 5.13.2 compat MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On a system with Perl 5.12.1, commit 5ef6dc08cfde ("lib/build_OID_registry: don't mention the full path of the script in output") causes the build to fail with the error below. Bareword found where operator expected at ./lib/build_OID_registry line 41, near "s#^\Q$abs_srctree/\E##r" syntax error at ./lib/build_OID_registry line 41, near "s#^\Q$abs_srctree/\E##r" Execution of ./lib/build_OID_registry aborted due to compilation errors. make[3]: *** [lib/Makefile:352: lib/oid_registry_data.c] Error 255 Ahmad Fatoum analyzed that non-destructive substitution is only supported since Perl 5.13.2. Instead of dropping `r` and having the side effect of modifying `$0`, introduce a dedicated variable to support older Perl versions. Link: https://lkml.kernel.org/r/20240702223512.8329-2-pmenzel@molgen.mpg.de Link: https://lkml.kernel.org/r/20240701155802.75152-1-pmenzel@molgen.mpg.de Fixes: 5ef6dc08cfde ("lib/build_OID_registry: don't mention the full path of the script in output") Link: https://lore.kernel.org/all/259f7a87-2692-480e-9073-1c1c35b52f67@molgen.mpg.de/ Signed-off-by: Paul Menzel Suggested-by: Ahmad Fatoum Cc: Uwe Kleine-König Cc: Nicolas Schier Cc: Masahiro Yamada Cc: Ahmad Fatoum Signed-off-by: Andrew Morton --- lib/build_OID_registry | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/build_OID_registry b/lib/build_OID_registry index 56d8bafeb848..8267e8d71338 100755 --- a/lib/build_OID_registry +++ b/lib/build_OID_registry @@ -38,7 +38,9 @@ close IN_FILE || die; # open C_FILE, ">$ARGV[1]" or die; print C_FILE "/*\n"; -print C_FILE " * Automatically generated by ", $0 =~ s#^\Q$abs_srctree/\E##r, ". Do not edit\n"; +my $scriptname = $0; +$scriptname =~ s#^\Q$abs_srctree/\E##; +print C_FILE " * Automatically generated by ", $scriptname, ". Do not edit\n"; print C_FILE " */\n"; # -- cgit v1.2.3 From 1f9a8286bc0c3df7d789ea625d9d9db3d7779f2d Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 28 May 2024 14:58:03 +0000 Subject: uaccess: always export _copy_[from|to]_user with CONFIG_RUST Rust code needs to be able to access _copy_from_user and _copy_to_user so that it can skip the check_copy_size check in cases where the length is known at compile-time, mirroring the logic for when C code will skip check_copy_size. To do this, we ensure that exported versions of these methods are available when CONFIG_RUST is enabled. Alice has verified that this patch passes the CONFIG_TEST_USER_COPY test on x86 using the Android cuttlefish emulator. Signed-off-by: Arnd Bergmann Tested-by: Alice Ryhl Reviewed-by: Boqun Feng Reviewed-by: Kees Cook Signed-off-by: Alice Ryhl Acked-by: Andrew Morton Link: https://lore.kernel.org/r/20240528-alice-mm-v7-2-78222c31b8f4@google.com Signed-off-by: Miguel Ojeda --- include/linux/uaccess.h | 46 ++++++++++++++++++++++++++++++++-------------- lib/usercopy.c | 30 ++++-------------------------- 2 files changed, 36 insertions(+), 40 deletions(-) (limited to 'lib') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 3064314f4832..d8e4105a2f21 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include @@ -138,13 +139,26 @@ __copy_to_user(void __user *to, const void *from, unsigned long n) return raw_copy_to_user(to, from, n); } -#ifdef INLINE_COPY_FROM_USER +/* + * Architectures that #define INLINE_COPY_TO_USER use this function + * directly in the normal copy_to/from_user(), the other ones go + * through an extern _copy_to/from_user(), which expands the same code + * here. + * + * Rust code always uses the extern definition. + */ static inline __must_check unsigned long -_copy_from_user(void *to, const void __user *from, unsigned long n) +_inline_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { + /* + * Ensure that bad access_ok() speculation will not + * lead to nasty side effects *after* the copy is + * finished: + */ + barrier_nospec(); instrument_copy_from_user_before(to, from, n); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); @@ -153,14 +167,11 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) memset(to + (n - res), 0, res); return res; } -#else extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); -#endif -#ifdef INLINE_COPY_TO_USER static inline __must_check unsigned long -_copy_to_user(void __user *to, const void *from, unsigned long n) +_inline_copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) @@ -171,25 +182,32 @@ _copy_to_user(void __user *to, const void *from, unsigned long n) } return n; } -#else extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); -#endif static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { - if (check_copy_size(to, n, false)) - n = _copy_from_user(to, from, n); - return n; + if (!check_copy_size(to, n, false)) + return n; +#ifdef INLINE_COPY_FROM_USER + return _inline_copy_from_user(to, from, n); +#else + return _copy_from_user(to, from, n); +#endif } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { - if (check_copy_size(from, n, true)) - n = _copy_to_user(to, from, n); - return n; + if (!check_copy_size(from, n, true)) + return n; + +#ifdef INLINE_COPY_TO_USER + return _inline_copy_to_user(to, from, n); +#else + return _copy_to_user(to, from, n); +#endif } #ifndef copy_mc_to_kernel diff --git a/lib/usercopy.c b/lib/usercopy.c index 499a7a7d54db..7b17b83c8042 100644 --- a/lib/usercopy.c +++ b/lib/usercopy.c @@ -12,40 +12,18 @@ /* out-of-line parts */ -#ifndef INLINE_COPY_FROM_USER +#if !defined(INLINE_COPY_FROM_USER) || defined(CONFIG_RUST) unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { - unsigned long res = n; - might_fault(); - if (!should_fail_usercopy() && likely(access_ok(from, n))) { - /* - * Ensure that bad access_ok() speculation will not - * lead to nasty side effects *after* the copy is - * finished: - */ - barrier_nospec(); - instrument_copy_from_user_before(to, from, n); - res = raw_copy_from_user(to, from, n); - instrument_copy_from_user_after(to, from, n, res); - } - if (unlikely(res)) - memset(to + (n - res), 0, res); - return res; + return _inline_copy_from_user(to, from, n); } EXPORT_SYMBOL(_copy_from_user); #endif -#ifndef INLINE_COPY_TO_USER +#if !defined(INLINE_COPY_TO_USER) || defined(CONFIG_RUST) unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { - might_fault(); - if (should_fail_usercopy()) - return n; - if (likely(access_ok(to, n))) { - instrument_copy_to_user(to, from, n); - n = raw_copy_to_user(to, from, n); - } - return n; + return _inline_copy_to_user(to, from, n); } EXPORT_SYMBOL(_copy_to_user); #endif -- cgit v1.2.3 From 29f1c1ae6d2fff3bf4f89d265f4a1a7c8ab78a8e Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 29 Jun 2024 22:12:09 -0400 Subject: closures: fix closure_sync + closure debugging originally, stack closures were only used synchronously, and with the original implementation of closure_sync() the ref never hit 0; thus, closure_put_after_sub() assumes that if the ref hits 0 it's on the debug list, in debug mode. that's no longer true with the current implementation of closure_sync, so we need a new magic so closure_debug_destroy() doesn't pop an assert. Signed-off-by: Kent Overstreet --- include/linux/closure.h | 7 +++++++ lib/closure.c | 3 +++ 2 files changed, 10 insertions(+) (limited to 'lib') diff --git a/include/linux/closure.h b/include/linux/closure.h index 59b8c06b11ff..2af44427107d 100644 --- a/include/linux/closure.h +++ b/include/linux/closure.h @@ -159,6 +159,7 @@ struct closure { #ifdef CONFIG_DEBUG_CLOSURES #define CLOSURE_MAGIC_DEAD 0xc054dead #define CLOSURE_MAGIC_ALIVE 0xc054a11e +#define CLOSURE_MAGIC_STACK 0xc05451cc unsigned int magic; struct list_head all; @@ -323,12 +324,18 @@ static inline void closure_init_stack(struct closure *cl) { memset(cl, 0, sizeof(struct closure)); atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER); +#ifdef CONFIG_DEBUG_CLOSURES + cl->magic = CLOSURE_MAGIC_STACK; +#endif } static inline void closure_init_stack_release(struct closure *cl) { memset(cl, 0, sizeof(struct closure)); atomic_set_release(&cl->remaining, CLOSURE_REMAINING_INITIALIZER); +#ifdef CONFIG_DEBUG_CLOSURES + cl->magic = CLOSURE_MAGIC_STACK; +#endif } /** diff --git a/lib/closure.c b/lib/closure.c index c971216d9d77..116afae2eed9 100644 --- a/lib/closure.c +++ b/lib/closure.c @@ -244,6 +244,9 @@ void closure_debug_destroy(struct closure *cl) { unsigned long flags; + if (cl->magic == CLOSURE_MAGIC_STACK) + return; + BUG_ON(cl->magic != CLOSURE_MAGIC_ALIVE); cl->magic = CLOSURE_MAGIC_DEAD; -- cgit v1.2.3 From 0d9c0a67b14401344183cc0f8239f8d1851637fd Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Thu, 11 Jul 2024 10:43:16 +0200 Subject: bootconfig: Remove duplicate included header file linux/bootconfig.h The header file linux/bootconfig.h is included whether __KERNEL__ is defined or not. Include it only once before the #ifdef/#else/#endif preprocessor directives and remove the following make includecheck warning: linux/bootconfig.h is included more than once Move the comment to the top and delete the now empty #else block. Link: https://lore.kernel.org/all/20240711084315.1507-1-thorsten.blum@toblux.com/ Signed-off-by: Thorsten Blum Signed-off-by: Masami Hiramatsu (Google) --- lib/bootconfig.c | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) (limited to 'lib') diff --git a/lib/bootconfig.c b/lib/bootconfig.c index 97f8911ea339..81f29c29f47b 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -4,8 +4,16 @@ * Masami Hiramatsu */ -#ifdef __KERNEL__ +/* + * NOTE: This is only for tools/bootconfig, because tools/bootconfig will + * run the parser sanity test. + * This does NOT mean lib/bootconfig.c is available in the user space. + * However, if you change this file, please make sure the tools/bootconfig + * has no issue on building and running. + */ #include + +#ifdef __KERNEL__ #include #include #include @@ -24,16 +32,6 @@ const char * __init xbc_get_embedded_bootconfig(size_t *size) return (*size) ? embedded_bootconfig_data : NULL; } #endif - -#else /* !__KERNEL__ */ -/* - * NOTE: This is only for tools/bootconfig, because tools/bootconfig will - * run the parser sanity test. - * This does NOT mean lib/bootconfig.c is available in the user space. - * However, if you change this file, please make sure the tools/bootconfig - * has no issue on building and running. - */ -#include #endif /* -- cgit v1.2.3 From 7554a7b96dc0dcc445d4af7077c96c6ab0988c79 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 11 Jul 2024 09:54:32 -0700 Subject: kunit: executor: Simplify string allocation handling The alloc/copy code pattern is better consolidated to single kstrdup (and kstrndup) calls instead. This gets rid of deprecated[1] strncpy() uses as well. Replace one other strncpy() use with the more idiomatic strscpy(). Link: https://github.com/KSPP/linux/issues/90 [1] Reviewed-by: David Gow Signed-off-by: Kees Cook Signed-off-by: Shuah Khan --- lib/kunit/executor.c | 12 +++--------- lib/kunit/executor_test.c | 2 +- 2 files changed, 4 insertions(+), 10 deletions(-) (limited to 'lib') diff --git a/lib/kunit/executor.c b/lib/kunit/executor.c index 70b9a43cd257..34b7b6833df3 100644 --- a/lib/kunit/executor.c +++ b/lib/kunit/executor.c @@ -70,32 +70,26 @@ struct kunit_glob_filter { static int kunit_parse_glob_filter(struct kunit_glob_filter *parsed, const char *filter_glob) { - const int len = strlen(filter_glob); const char *period = strchr(filter_glob, '.'); if (!period) { - parsed->suite_glob = kzalloc(len + 1, GFP_KERNEL); + parsed->suite_glob = kstrdup(filter_glob, GFP_KERNEL); if (!parsed->suite_glob) return -ENOMEM; - parsed->test_glob = NULL; - strcpy(parsed->suite_glob, filter_glob); return 0; } - parsed->suite_glob = kzalloc(period - filter_glob + 1, GFP_KERNEL); + parsed->suite_glob = kstrndup(filter_glob, period - filter_glob, GFP_KERNEL); if (!parsed->suite_glob) return -ENOMEM; - parsed->test_glob = kzalloc(len - (period - filter_glob) + 1, GFP_KERNEL); + parsed->test_glob = kstrdup(period + 1, GFP_KERNEL); if (!parsed->test_glob) { kfree(parsed->suite_glob); return -ENOMEM; } - strncpy(parsed->suite_glob, filter_glob, period - filter_glob); - strncpy(parsed->test_glob, period + 1, len - (period - filter_glob)); - return 0; } diff --git a/lib/kunit/executor_test.c b/lib/kunit/executor_test.c index 3f7f967e3688..f0090c2729cd 100644 --- a/lib/kunit/executor_test.c +++ b/lib/kunit/executor_test.c @@ -286,7 +286,7 @@ static struct kunit_suite *alloc_fake_suite(struct kunit *test, /* We normally never expect to allocate suites, hence the non-const cast. */ suite = kunit_kzalloc(test, sizeof(*suite), GFP_KERNEL); - strncpy((char *)suite->name, suite_name, sizeof(suite->name) - 1); + strscpy((char *)suite->name, suite_name, sizeof(suite->name)); suite->test_cases = test_cases; return suite; -- cgit v1.2.3 From 4f5d4a1ba7a1a23173e356186f3f8b7c27d2e948 Mon Sep 17 00:00:00 2001 From: Chen Ni Date: Tue, 9 Jul 2024 11:43:23 +0800 Subject: test_bpf: convert comma to semicolon Replace commas between expression statements with semicolons. Link: https://lkml.kernel.org/r/20240709034323.586185-1-nichen@iscas.ac.cn Signed-off-by: Chen Ni Cc: Alexei Starovoitov Cc: Andrii Nakryiko Cc: Daniel Borkmann Cc: Eduard Zingerman Cc: Hao Luo Cc: Jiri Olsa Cc: John Fastabend Cc: KP Singh Cc: Martin KaFai Lau Cc: Song Liu Cc: Stanislav Fomichev Cc: Yonghong Song Signed-off-by: Andrew Morton --- lib/test_bpf.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 207ff87194db..a6edbe842f65 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -1740,7 +1740,7 @@ static int __bpf_emit_cmpxchg32(struct bpf_test *self, void *arg, /* Result unsuccessful */ insns[i++] = BPF_STX_MEM(BPF_W, R10, R1, -4); insns[i++] = BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, R10, R2, -4); - insns[i++] = BPF_ZEXT_REG(R0), /* Zext always inserted by verifier */ + insns[i++] = BPF_ZEXT_REG(R0); /* Zext always inserted by verifier */ insns[i++] = BPF_LDX_MEM(BPF_W, R3, R10, -4); insns[i++] = BPF_JMP32_REG(BPF_JEQ, R1, R3, 2); @@ -1754,7 +1754,7 @@ static int __bpf_emit_cmpxchg32(struct bpf_test *self, void *arg, /* Result successful */ i += __bpf_ld_imm64(&insns[i], R0, dst); insns[i++] = BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, R10, R2, -4); - insns[i++] = BPF_ZEXT_REG(R0), /* Zext always inserted by verifier */ + insns[i++] = BPF_ZEXT_REG(R0); /* Zext always inserted by verifier */ insns[i++] = BPF_LDX_MEM(BPF_W, R3, R10, -4); insns[i++] = BPF_JMP32_REG(BPF_JEQ, R2, R3, 2); -- cgit v1.2.3 From e1fb7430fcb00431087fc1c088ec9e8737cf6c7d Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Tue, 9 Jul 2024 00:40:24 +0200 Subject: lib/bch.c: use swap() to improve code Use the swap() macro to simplify the functions solve_linear_system() and gf_poly_gcd() and improve their readability. Remove the local variable tmp. Fixes the following three Coccinelle/coccicheck warnings reported by swap.cocci: WARNING opportunity for swap() WARNING opportunity for swap() WARNING opportunity for swap() Link: https://lkml.kernel.org/r/20240708224023.9312-2-thorsten.blum@toblux.com Signed-off-by: Thorsten Blum Signed-off-by: Andrew Morton --- lib/bch.c | 20 +++++--------------- 1 file changed, 5 insertions(+), 15 deletions(-) (limited to 'lib') diff --git a/lib/bch.c b/lib/bch.c index 5f71fd76eca8..1c0cb07cdfeb 100644 --- a/lib/bch.c +++ b/lib/bch.c @@ -479,11 +479,8 @@ static int solve_linear_system(struct bch_control *bch, unsigned int *rows, /* find suitable row for elimination */ for (r = p; r < m; r++) { if (rows[r] & mask) { - if (r != p) { - tmp = rows[r]; - rows[r] = rows[p]; - rows[p] = tmp; - } + if (r != p) + swap(rows[r], rows[p]); rem = r+1; break; } @@ -799,21 +796,14 @@ static void gf_poly_div(struct bch_control *bch, struct gf_poly *a, static struct gf_poly *gf_poly_gcd(struct bch_control *bch, struct gf_poly *a, struct gf_poly *b) { - struct gf_poly *tmp; - dbg("gcd(%s,%s)=", gf_poly_str(a), gf_poly_str(b)); - if (a->deg < b->deg) { - tmp = b; - b = a; - a = tmp; - } + if (a->deg < b->deg) + swap(a, b); while (b->deg > 0) { gf_poly_mod(bch, a, b, NULL); - tmp = b; - b = a; - a = tmp; + swap(a, b); } dbg("%s\n", gf_poly_str(a)); -- cgit v1.2.3 From fe69b772e35e181ff0576ab4a610515ffe7a3325 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 4 Jul 2024 10:25:05 -0500 Subject: crypto: lib/mpi - delete unnecessary condition We checked that "nlimbs" is non-zero in the outside if statement so delete the duplicate check here. Signed-off-by: Dan Carpenter Reviewed-by: Tianjia Zhang Signed-off-by: Herbert Xu --- lib/crypto/mpi/mpi-bit.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/lib/crypto/mpi/mpi-bit.c b/lib/crypto/mpi/mpi-bit.c index 070ba784c9f1..e08fc202ea5c 100644 --- a/lib/crypto/mpi/mpi-bit.c +++ b/lib/crypto/mpi/mpi-bit.c @@ -212,12 +212,10 @@ void mpi_rshift(MPI x, MPI a, unsigned int n) return; } - if (nlimbs) { - for (i = 0; i < x->nlimbs - nlimbs; i++) - x->d[i] = x->d[i+nlimbs]; - x->d[i] = 0; - x->nlimbs -= nlimbs; - } + for (i = 0; i < x->nlimbs - nlimbs; i++) + x->d[i] = x->d[i+nlimbs]; + x->d[i] = 0; + x->nlimbs -= nlimbs; if (x->nlimbs && nbits) mpihelp_rshift(x->d, x->d, x->nlimbs, nbits); -- cgit v1.2.3 From 84679f04ceafd58d9b35f790203520b2930f1a03 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 15 Jul 2024 02:04:32 +0900 Subject: fortify: fix warnings in fortify tests with KASAN When a software KASAN mode is enabled, the fortify tests emit warnings on some architectures. For example, for ARCH=arm, the combination of CONFIG_FORTIFY_SOURCE=y and CONFIG_KASAN=y produces the following warnings: TEST lib/test_fortify/read_overflow-memchr.log warning: unsafe memchr() usage lacked '__read_overflow' warning in lib/test_fortify/read_overflow-memchr.c TEST lib/test_fortify/read_overflow-memchr_inv.log warning: unsafe memchr_inv() usage lacked '__read_overflow' symbol in lib/test_fortify/read_overflow-memchr_inv.c TEST lib/test_fortify/read_overflow-memcmp.log warning: unsafe memcmp() usage lacked '__read_overflow' warning in lib/test_fortify/read_overflow-memcmp.c TEST lib/test_fortify/read_overflow-memscan.log warning: unsafe memscan() usage lacked '__read_overflow' symbol in lib/test_fortify/read_overflow-memscan.c TEST lib/test_fortify/read_overflow2-memcmp.log warning: unsafe memcmp() usage lacked '__read_overflow2' warning in lib/test_fortify/read_overflow2-memcmp.c [ more and more similar warnings... ] Commit 9c2d1328f88a ("kbuild: provide reasonable defaults for tool coverage") removed KASAN flags from non-kernel objects by default. It was an intended behavior because lib/test_fortify/*.c are unit tests that are not linked to the kernel. As it turns out, some architectures require -fsanitize=kernel-(hw)address to define __SANITIZE_ADDRESS__ for the fortify tests. Without __SANITIZE_ADDRESS__ defined, arch/arm/include/asm/string.h defines __NO_FORTIFY, thus excluding . This issue does not occur on x86 thanks to commit 4ec4190be4cf ("kasan, x86: don't rename memintrinsics in uninstrumented files"), but there are still some architectures that define __NO_FORTIFY in such a situation. Set KASAN_SANITIZE=y explicitly to the fortify tests. Fixes: 9c2d1328f88a ("kbuild: provide reasonable defaults for tool coverage") Reported-by: Arnd Bergmann Closes: https://lore.kernel.org/all/0e8dee26-41cc-41ae-9493-10cd1a8e3268@app.fastmail.com/ Signed-off-by: Masahiro Yamada --- lib/Makefile | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'lib') diff --git a/lib/Makefile b/lib/Makefile index 3b1769045651..30337431d10e 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -426,3 +426,7 @@ $(obj)/$(TEST_FORTIFY_LOG): $(addprefix $(obj)/, $(TEST_FORTIFY_LOGS)) FORCE ifeq ($(CONFIG_FORTIFY_SOURCE),y) $(obj)/string.o: $(obj)/$(TEST_FORTIFY_LOG) endif + +# Some architectures define __NO_FORTIFY if __SANITIZE_ADDRESS__ is undefined. +# Pass CFLAGS_KASAN to avoid warnings. +$(foreach x, $(patsubst %.log,%.o,$(TEST_FORTIFY_LOGS)), $(eval KASAN_SANITIZE_$(x) := y)) -- cgit v1.2.3 From 72d04bdcf3f7d7e07d82f9757946f68802a7270a Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Tue, 16 Jul 2024 16:26:27 +0800 Subject: sbitmap: fix io hung due to race on sbitmap_word::cleared Configuration for sbq: depth=64, wake_batch=6, shift=6, map_nr=1 1. There are 64 requests in progress: map->word = 0xFFFFFFFFFFFFFFFF 2. After all the 64 requests complete, and no more requests come: map->word = 0xFFFFFFFFFFFFFFFF, map->cleared = 0xFFFFFFFFFFFFFFFF 3. Now two tasks try to allocate requests: T1: T2: __blk_mq_get_tag . __sbitmap_queue_get . sbitmap_get . sbitmap_find_bit . sbitmap_find_bit_in_word . __sbitmap_get_word -> nr=-1 __blk_mq_get_tag sbitmap_deferred_clear __sbitmap_queue_get /* map->cleared=0xFFFFFFFFFFFFFFFF */ sbitmap_find_bit if (!READ_ONCE(map->cleared)) sbitmap_find_bit_in_word return false; __sbitmap_get_word -> nr=-1 mask = xchg(&map->cleared, 0) sbitmap_deferred_clear atomic_long_andnot() /* map->cleared=0 */ if (!(map->cleared)) return false; /* * map->cleared is cleared by T1 * T2 fail to acquire the tag */ 4. T2 is the sole tag waiter. When T1 puts the tag, T2 cannot be woken up due to the wake_batch being set at 6. If no more requests come, T1 will wait here indefinitely. This patch achieves two purposes: 1. Check on ->cleared and update on both ->cleared and ->word need to be done atomically, and using spinlock could be the simplest solution. 2. Add extra check in sbitmap_deferred_clear(), to identify whether ->word has free bits. Fixes: ea86ea2cdced ("sbitmap: ammortize cost of clearing bits") Signed-off-by: Yang Yang Reviewed-by: Ming Lei Reviewed-by: Bart Van Assche Link: https://lore.kernel.org/r/20240716082644.659566-1-yang.yang@vivo.com Signed-off-by: Jens Axboe --- include/linux/sbitmap.h | 5 +++++ lib/sbitmap.c | 36 +++++++++++++++++++++++++++++------- 2 files changed, 34 insertions(+), 7 deletions(-) (limited to 'lib') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index d662cf136021..c09cdcc99471 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -36,6 +36,11 @@ struct sbitmap_word { * @cleared: word holding cleared bits */ unsigned long cleared ____cacheline_aligned_in_smp; + + /** + * @swap_lock: serializes simultaneous updates of ->word and ->cleared + */ + spinlock_t swap_lock; } ____cacheline_aligned_in_smp; /** diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 1e453f825c05..5e2e93307f0d 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -60,12 +60,30 @@ static inline void update_alloc_hint_after_get(struct sbitmap *sb, /* * See if we have deferred clears that we can batch move */ -static inline bool sbitmap_deferred_clear(struct sbitmap_word *map) +static inline bool sbitmap_deferred_clear(struct sbitmap_word *map, + unsigned int depth, unsigned int alloc_hint, bool wrap) { - unsigned long mask; + unsigned long mask, word_mask; - if (!READ_ONCE(map->cleared)) - return false; + guard(spinlock_irqsave)(&map->swap_lock); + + if (!map->cleared) { + if (depth == 0) + return false; + + word_mask = (~0UL) >> (BITS_PER_LONG - depth); + /* + * The current behavior is to always retry after moving + * ->cleared to word, and we change it to retry in case + * of any free bits. To avoid an infinite loop, we need + * to take wrap & alloc_hint into account, otherwise a + * soft lockup may occur. + */ + if (!wrap && alloc_hint) + word_mask &= ~((1UL << alloc_hint) - 1); + + return (READ_ONCE(map->word) & word_mask) != word_mask; + } /* * First get a stable cleared mask, setting the old mask to 0. @@ -85,6 +103,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, bool alloc_hint) { unsigned int bits_per_word; + int i; if (shift < 0) shift = sbitmap_calculate_shift(depth); @@ -116,6 +135,9 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, return -ENOMEM; } + for (i = 0; i < sb->map_nr; i++) + spin_lock_init(&sb->map[i].swap_lock); + return 0; } EXPORT_SYMBOL_GPL(sbitmap_init_node); @@ -126,7 +148,7 @@ void sbitmap_resize(struct sbitmap *sb, unsigned int depth) unsigned int i; for (i = 0; i < sb->map_nr; i++) - sbitmap_deferred_clear(&sb->map[i]); + sbitmap_deferred_clear(&sb->map[i], 0, 0, 0); sb->depth = depth; sb->map_nr = DIV_ROUND_UP(sb->depth, bits_per_word); @@ -179,7 +201,7 @@ static int sbitmap_find_bit_in_word(struct sbitmap_word *map, alloc_hint, wrap); if (nr != -1) break; - if (!sbitmap_deferred_clear(map)) + if (!sbitmap_deferred_clear(map, depth, alloc_hint, wrap)) break; } while (1); @@ -496,7 +518,7 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags, unsigned int map_depth = __map_depth(sb, index); unsigned long val; - sbitmap_deferred_clear(map); + sbitmap_deferred_clear(map, 0, 0, 0); val = READ_ONCE(map->word); if (val == (1UL << (map_depth - 1)) - 1) goto next; -- cgit v1.2.3 From 4ad10a5f5f78a5b3e525a63bd075a4eb1139dde1 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Fri, 18 Nov 2022 17:23:34 +0100 Subject: random: introduce generic vDSO getrandom() implementation Provide a generic C vDSO getrandom() implementation, which operates on an opaque state returned by vgetrandom_alloc() and produces random bytes the same way as getrandom(). This has the following API signature: ssize_t vgetrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len); The return value and the first three arguments are the same as ordinary getrandom(), while the last two arguments are a pointer to the opaque allocated state and its size. Were all five arguments passed to the getrandom() syscall, nothing different would happen, and the functions would have the exact same behavior. The actual vDSO RNG algorithm implemented is the same one implemented by drivers/char/random.c, using the same fast-erasure techniques as that. Should the in-kernel implementation change, so too will the vDSO one. It requires an implementation of ChaCha20 that does not use any stack, in order to maintain forward secrecy if a multi-threaded program forks (though this does not account for a similar issue with SA_SIGINFO copying registers to the stack), so this is left as an architecture-specific fill-in. Stack-less ChaCha20 is an easy algorithm to implement on a variety of architectures, so this shouldn't be too onerous. Initially, the state is keyless, and so the first call makes a getrandom() syscall to generate that key, and then uses it for subsequent calls. By keeping track of a generation counter, it knows when its key is invalidated and it should fetch a new one using the syscall. Later, more than just a generation counter might be used. Since MADV_WIPEONFORK is set on the opaque state, the key and related state is wiped during a fork(), so secrets don't roll over into new processes, and the same state doesn't accidentally generate the same random stream. The generation counter, as well, is always >0, so that the 0 counter is a useful indication of a fork() or otherwise uninitialized state. If the kernel RNG is not yet initialized, then the vDSO always calls the syscall, because that behavior cannot be emulated in userspace, but fortunately that state is short lived and only during early boot. If it has been initialized, then there is no need to inspect the `flags` argument, because the behavior does not change post-initialization regardless of the `flags` value. Since the opaque state passed to it is mutated, vDSO getrandom() is not reentrant, when used with the same opaque state, which libc should be mindful of. The function works over an opaque per-thread state of a particular size, which must be marked VM_WIPEONFORK, VM_DONTDUMP, VM_NORESERVE, and VM_DROPPABLE for proper operation. Over time, the nuances of these allocations may change or grow or even differ based on architectural features. The opaque state passed to vDSO getrandom() must be allocated using the mmap_flags and mmap_prot parameters provided by the vgetrandom_opaque_params struct, which also contains the size of each state. That struct can be obtained with a call to vgetrandom(NULL, 0, 0, ¶ms, ~0UL). Then, libc can call mmap(2) and slice up the returned array into a state per each thread, while ensuring that no single state straddles a page boundary. Libc is expected to allocate a chunk of these on first use, and then dole them out to threads as they're created, allocating more when needed. vDSO getrandom() provides the ability for userspace to generate random bytes quickly and safely, and is intended to be integrated into libc's thread management. As an illustrative example, the introduced code in the vdso_test_getrandom self test later in this series might be used to do the same outside of libc. In a libc the various pthread-isms are expected to be elided into libc internals. Reviewed-by: Thomas Gleixner Signed-off-by: Jason A. Donenfeld --- MAINTAINERS | 2 + drivers/char/random.c | 18 +++- include/uapi/linux/random.h | 15 +++ include/vdso/datapage.h | 11 ++ include/vdso/getrandom.h | 46 ++++++++ lib/vdso/Kconfig | 5 + lib/vdso/getrandom.c | 251 ++++++++++++++++++++++++++++++++++++++++++++ 7 files changed, 347 insertions(+), 1 deletion(-) create mode 100644 include/vdso/getrandom.h create mode 100644 lib/vdso/getrandom.c (limited to 'lib') diff --git a/MAINTAINERS b/MAINTAINERS index 2a4d4b3a9b40..7edb30b4abf0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18745,6 +18745,8 @@ T: git https://git.kernel.org/pub/scm/linux/kernel/git/crng/random.git F: Documentation/devicetree/bindings/rng/microsoft,vmgenid.yaml F: drivers/char/random.c F: drivers/virt/vmgenid.c +F: include/vdso/getrandom.h +F: lib/vdso/getrandom.c RAPIDIO SUBSYSTEM M: Matt Porter diff --git a/drivers/char/random.c b/drivers/char/random.c index 2597cb43f438..b02a12436750 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* - * Copyright (C) 2017-2022 Jason A. Donenfeld . All Rights Reserved. + * Copyright (C) 2017-2024 Jason A. Donenfeld . All Rights Reserved. * Copyright Matt Mackall , 2003, 2004, 2005 * Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All rights reserved. * @@ -56,6 +56,10 @@ #include #include #include +#ifdef CONFIG_VDSO_GETRANDOM +#include +#include +#endif #include #include #include @@ -271,6 +275,15 @@ static void crng_reseed(struct work_struct *work) if (next_gen == ULONG_MAX) ++next_gen; WRITE_ONCE(base_crng.generation, next_gen); +#ifdef CONFIG_VDSO_GETRANDOM + /* base_crng.generation's invalid value is ULONG_MAX, while + * _vdso_rng_data.generation's invalid value is 0, so add one to the + * former to arrive at the latter. Use smp_store_release so that this + * is ordered with the write above to base_crng.generation. Pairs with + * the smp_rmb() before the syscall in the vDSO code. + */ + smp_store_release(&_vdso_rng_data.generation, next_gen + 1); +#endif if (!static_branch_likely(&crng_is_ready)) crng_init = CRNG_READY; spin_unlock_irqrestore(&base_crng.lock, flags); @@ -721,6 +734,9 @@ static void __cold _credit_init_bits(size_t bits) if (static_key_initialized && system_unbound_wq) queue_work(system_unbound_wq, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); +#ifdef CONFIG_VDSO_GETRANDOM + WRITE_ONCE(_vdso_rng_data.is_ready, true); +#endif wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); pr_notice("crng init done\n"); diff --git a/include/uapi/linux/random.h b/include/uapi/linux/random.h index e744c23582eb..2a3fe4c2cdc9 100644 --- a/include/uapi/linux/random.h +++ b/include/uapi/linux/random.h @@ -55,4 +55,19 @@ struct rand_pool_info { #define GRND_RANDOM 0x0002 #define GRND_INSECURE 0x0004 +/** + * struct vgetrandom_opaque_params - arguments for allocating memory for vgetrandom + * + * @size_per_opaque_state: Size of each state that is to be passed to vgetrandom(). + * @mmap_prot: Value of the prot argument in mmap(2). + * @mmap_flags: Value of the flags argument in mmap(2). + * @reserved: Reserved for future use. + */ +struct vgetrandom_opaque_params { + __u32 size_of_opaque_state; + __u32 mmap_prot; + __u32 mmap_flags; + __u32 reserved[13]; +}; + #endif /* _UAPI_LINUX_RANDOM_H */ diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h index d04d394db064..05e5787beb73 100644 --- a/include/vdso/datapage.h +++ b/include/vdso/datapage.h @@ -113,6 +113,16 @@ struct vdso_data { struct arch_vdso_data arch_data; }; +/** + * struct vdso_rng_data - vdso RNG state information + * @generation: counter representing the number of RNG reseeds + * @is_ready: boolean signaling whether the RNG is initialized + */ +struct vdso_rng_data { + u64 generation; + u8 is_ready; +}; + /* * We use the hidden visibility to prevent the compiler from generating a GOT * relocation. Not only is going through a GOT useless (the entry couldn't and @@ -124,6 +134,7 @@ struct vdso_data { */ extern struct vdso_data _vdso_data[CS_BASES] __attribute__((visibility("hidden"))); extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("hidden"))); +extern struct vdso_rng_data _vdso_rng_data __attribute__((visibility("hidden"))); /** * union vdso_data_store - Generic vDSO data page diff --git a/include/vdso/getrandom.h b/include/vdso/getrandom.h new file mode 100644 index 000000000000..a8b7c14b0ae0 --- /dev/null +++ b/include/vdso/getrandom.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022-2024 Jason A. Donenfeld . All Rights Reserved. + */ + +#ifndef _VDSO_GETRANDOM_H +#define _VDSO_GETRANDOM_H + +#include + +#define CHACHA_KEY_SIZE 32 +#define CHACHA_BLOCK_SIZE 64 + +/** + * struct vgetrandom_state - State used by vDSO getrandom(). + * + * @batch: One and a half ChaCha20 blocks of buffered RNG output. + * + * @key: Key to be used for generating next batch. + * + * @batch_key: Union of the prior two members, which is exactly two full + * ChaCha20 blocks in size, so that @batch and @key can be filled + * together. + * + * @generation: Snapshot of @rng_info->generation in the vDSO data page at + * the time @key was generated. + * + * @pos: Offset into @batch of the next available random byte. + * + * @in_use: Reentrancy guard for reusing a state within the same thread + * due to signal handlers. + */ +struct vgetrandom_state { + union { + struct { + u8 batch[CHACHA_BLOCK_SIZE * 3 / 2]; + u32 key[CHACHA_KEY_SIZE / sizeof(u32)]; + }; + u8 batch_key[CHACHA_BLOCK_SIZE * 2]; + }; + u64 generation; + u8 pos; + bool in_use; +}; + +#endif /* _VDSO_GETRANDOM_H */ diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig index c46c2300517c..82fe827af542 100644 --- a/lib/vdso/Kconfig +++ b/lib/vdso/Kconfig @@ -38,3 +38,8 @@ config GENERIC_VDSO_OVERFLOW_PROTECT in the hotpath. endif + +config VDSO_GETRANDOM + bool + help + Selected by architectures that support vDSO getrandom(). diff --git a/lib/vdso/getrandom.c b/lib/vdso/getrandom.c new file mode 100644 index 000000000000..b230f0b10832 --- /dev/null +++ b/lib/vdso/getrandom.c @@ -0,0 +1,251 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024 Jason A. Donenfeld . All Rights Reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define MEMCPY_AND_ZERO_SRC(type, dst, src, len) do { \ + while (len >= sizeof(type)) { \ + __put_unaligned_t(type, __get_unaligned_t(type, src), dst); \ + __put_unaligned_t(type, 0, src); \ + dst += sizeof(type); \ + src += sizeof(type); \ + len -= sizeof(type); \ + } \ +} while (0) + +static void memcpy_and_zero_src(void *dst, void *src, size_t len) +{ + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) { + if (IS_ENABLED(CONFIG_64BIT)) + MEMCPY_AND_ZERO_SRC(u64, dst, src, len); + MEMCPY_AND_ZERO_SRC(u32, dst, src, len); + MEMCPY_AND_ZERO_SRC(u16, dst, src, len); + } + MEMCPY_AND_ZERO_SRC(u8, dst, src, len); +} + +/** + * __cvdso_getrandom_data - Generic vDSO implementation of getrandom() syscall. + * @rng_info: Describes state of kernel RNG, memory shared with kernel. + * @buffer: Destination buffer to fill with random bytes. + * @len: Size of @buffer in bytes. + * @flags: Zero or more GRND_* flags. + * @opaque_state: Pointer to an opaque state area. + * @opaque_len: Length of opaque state area. + * + * This implements a "fast key erasure" RNG using ChaCha20, in the same way that the kernel's + * getrandom() syscall does. It periodically reseeds its key from the kernel's RNG, at the same + * schedule that the kernel's RNG is reseeded. If the kernel's RNG is not ready, then this always + * calls into the syscall. + * + * If @buffer, @len, and @flags are 0, and @opaque_len is ~0UL, then @opaque_state is populated + * with a struct vgetrandom_opaque_params and the function returns 0; if it does not return 0, + * this function should not be used. + * + * @opaque_state *must* be allocated by calling mmap(2) using the mmap_prot and mmap_flags fields + * from the struct vgetrandom_opaque_params, and states must not straddle pages. Unless external + * locking is used, one state must be allocated per thread, as it is not safe to call this function + * concurrently with the same @opaque_state. However, it is safe to call this using the same + * @opaque_state that is shared between main code and signal handling code, within the same thread. + * + * Returns: The number of random bytes written to @buffer, or a negative value indicating an error. + */ +static __always_inline ssize_t +__cvdso_getrandom_data(const struct vdso_rng_data *rng_info, void *buffer, size_t len, + unsigned int flags, void *opaque_state, size_t opaque_len) +{ + ssize_t ret = min_t(size_t, INT_MAX & PAGE_MASK /* = MAX_RW_COUNT */, len); + struct vgetrandom_state *state = opaque_state; + size_t batch_len, nblocks, orig_len = len; + bool in_use, have_retried = false; + unsigned long current_generation; + void *orig_buffer = buffer; + u32 counter[2] = { 0 }; + + if (unlikely(opaque_len == ~0UL && !buffer && !len && !flags)) { + *(struct vgetrandom_opaque_params *)opaque_state = (struct vgetrandom_opaque_params) { + .size_of_opaque_state = sizeof(*state), + .mmap_prot = PROT_READ | PROT_WRITE, + .mmap_flags = MAP_DROPPABLE | MAP_ANONYMOUS + }; + return 0; + } + + /* The state must not straddle a page, since pages can be zeroed at any time. */ + if (unlikely(((unsigned long)opaque_state & ~PAGE_MASK) + sizeof(*state) > PAGE_SIZE)) + return -EFAULT; + + /* If the caller passes the wrong size, which might happen due to CRIU, fallback. */ + if (unlikely(opaque_len != sizeof(*state))) + goto fallback_syscall; + + /* + * If the kernel's RNG is not yet ready, then it's not possible to provide random bytes from + * userspace, because A) the various @flags require this to block, or not, depending on + * various factors unavailable to userspace, and B) the kernel's behavior before the RNG is + * ready is to reseed from the entropy pool at every invocation. + */ + if (unlikely(!READ_ONCE(rng_info->is_ready))) + goto fallback_syscall; + + /* + * This condition is checked after @rng_info->is_ready, because before the kernel's RNG is + * initialized, the @flags parameter may require this to block or return an error, even when + * len is zero. + */ + if (unlikely(!len)) + return 0; + + /* + * @state->in_use is basic reentrancy protection against this running in a signal handler + * with the same @opaque_state, but obviously not atomic wrt multiple CPUs or more than one + * level of reentrancy. If a signal interrupts this after reading @state->in_use, but before + * writing @state->in_use, there is still no race, because the signal handler will run to + * its completion before returning execution. + */ + in_use = READ_ONCE(state->in_use); + if (unlikely(in_use)) + /* The syscall simply fills the buffer and does not touch @state, so fallback. */ + goto fallback_syscall; + WRITE_ONCE(state->in_use, true); + +retry_generation: + /* + * @rng_info->generation must always be read here, as it serializes @state->key with the + * kernel's RNG reseeding schedule. + */ + current_generation = READ_ONCE(rng_info->generation); + + /* + * If @state->generation doesn't match the kernel RNG's generation, then it means the + * kernel's RNG has reseeded, and so @state->key is reseeded as well. + */ + if (unlikely(state->generation != current_generation)) { + /* + * Write the generation before filling the key, in case of fork. If there is a fork + * just after this line, the parent and child will get different random bytes from + * the syscall, which is good. However, were this line to occur after the getrandom + * syscall, then both child and parent could have the same bytes and the same + * generation counter, so the fork would not be detected. Therefore, write + * @state->generation before the call to the getrandom syscall. + */ + WRITE_ONCE(state->generation, current_generation); + + /* + * Prevent the syscall from being reordered wrt current_generation. Pairs with the + * smp_store_release(&_vdso_rng_data.generation) in random.c. + */ + smp_rmb(); + + /* Reseed @state->key using fresh bytes from the kernel. */ + if (getrandom_syscall(state->key, sizeof(state->key), 0) != sizeof(state->key)) { + /* + * If the syscall failed to refresh the key, then @state->key is now + * invalid, so invalidate the generation so that it is not used again, and + * fallback to using the syscall entirely. + */ + WRITE_ONCE(state->generation, 0); + + /* + * Set @state->in_use to false only after the last write to @state in the + * line above. + */ + WRITE_ONCE(state->in_use, false); + + goto fallback_syscall; + } + + /* + * Set @state->pos to beyond the end of the batch, so that the batch is refilled + * using the new key. + */ + state->pos = sizeof(state->batch); + } + + /* Set len to the total amount of bytes that this function is allowed to read, ret. */ + len = ret; +more_batch: + /* + * First use bytes out of @state->batch, which may have been filled by the last call to this + * function. + */ + batch_len = min_t(size_t, sizeof(state->batch) - state->pos, len); + if (batch_len) { + /* Zeroing at the same time as memcpying helps preserve forward secrecy. */ + memcpy_and_zero_src(buffer, state->batch + state->pos, batch_len); + state->pos += batch_len; + buffer += batch_len; + len -= batch_len; + } + + if (!len) { + /* Prevent the loop from being reordered wrt ->generation. */ + barrier(); + + /* + * Since @rng_info->generation will never be 0, re-read @state->generation, rather + * than using the local current_generation variable, to learn whether a fork + * occurred or if @state was zeroed due to memory pressure. Primarily, though, this + * indicates whether the kernel's RNG has reseeded, in which case generate a new key + * and start over. + */ + if (unlikely(READ_ONCE(state->generation) != READ_ONCE(rng_info->generation))) { + /* + * Prevent this from looping forever in case of low memory or racing with a + * user force-reseeding the kernel's RNG using the ioctl. + */ + if (have_retried) { + WRITE_ONCE(state->in_use, false); + goto fallback_syscall; + } + + have_retried = true; + buffer = orig_buffer; + goto retry_generation; + } + + /* + * Set @state->in_use to false only when there will be no more reads or writes of + * @state. + */ + WRITE_ONCE(state->in_use, false); + return ret; + } + + /* Generate blocks of RNG output directly into @buffer while there's enough room left. */ + nblocks = len / CHACHA_BLOCK_SIZE; + if (nblocks) { + __arch_chacha20_blocks_nostack(buffer, state->key, counter, nblocks); + buffer += nblocks * CHACHA_BLOCK_SIZE; + len -= nblocks * CHACHA_BLOCK_SIZE; + } + + BUILD_BUG_ON(sizeof(state->batch_key) % CHACHA_BLOCK_SIZE != 0); + + /* Refill the batch and overwrite the key, in order to preserve forward secrecy. */ + __arch_chacha20_blocks_nostack(state->batch_key, state->key, counter, + sizeof(state->batch_key) / CHACHA_BLOCK_SIZE); + + /* Since the batch was just refilled, set the position back to 0 to indicate a full batch. */ + state->pos = 0; + goto more_batch; + +fallback_syscall: + return getrandom_syscall(orig_buffer, orig_len, flags); +} + +static __always_inline ssize_t +__cvdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len) +{ + return __cvdso_getrandom_data(__arch_get_vdso_rng_data(), buffer, len, flags, opaque_state, opaque_len); +} -- cgit v1.2.3 From bf6acd5d16057d7accbbb1bf7dc6d8c56eeb4ecc Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Wed, 17 Jul 2024 17:20:16 +0100 Subject: decompress_bunzip2: fix rare decompression failure The decompression code parses a huffman tree and counts the number of symbols for a given bit length. In rare cases, there may be >= 256 symbols with a given bit length, causing the unsigned char to overflow. This causes a decompression failure later when the code tries and fails to find the bit length for a given symbol. Since the maximum number of symbols is 258, use unsigned short instead. Link: https://lkml.kernel.org/r/20240717162016.1514077-1-ross.lagerwall@citrix.com Fixes: bc22c17e12c1 ("bzip2/lzma: library support for gzip, bzip2 and lzma decompression") Signed-off-by: Ross Lagerwall Cc: Alain Knaff Cc: "H. Peter Anvin" Cc: Signed-off-by: Andrew Morton --- lib/decompress_bunzip2.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c index 3518e7394eca..ca736166f100 100644 --- a/lib/decompress_bunzip2.c +++ b/lib/decompress_bunzip2.c @@ -232,7 +232,8 @@ static int INIT get_next_block(struct bunzip_data *bd) RUNB) */ symCount = symTotal+2; for (j = 0; j < groupCount; j++) { - unsigned char length[MAX_SYMBOLS], temp[MAX_HUFCODE_BITS+1]; + unsigned char length[MAX_SYMBOLS]; + unsigned short temp[MAX_HUFCODE_BITS+1]; int minLen, maxLen, pp; /* Read Huffman code lengths for each symbol. They're stored in a way similar to mtf; record a starting -- cgit v1.2.3