diff options
Diffstat (limited to 'lib')
-rw-r--r-- | lib/Kconfig.debug | 13 | ||||
-rw-r--r-- | lib/Kconfig.kcsan | 42 | ||||
-rw-r--r-- | lib/bootconfig.c | 8 | ||||
-rw-r--r-- | lib/debug_info.c | 3 | ||||
-rw-r--r-- | lib/dump_stack.c | 3 | ||||
-rw-r--r-- | lib/iov_iter.c | 8 | ||||
-rw-r--r-- | lib/kasprintf.c | 2 | ||||
-rw-r--r-- | lib/kunit/string-stream.h | 2 | ||||
-rw-r--r-- | lib/kunit/test.c | 109 | ||||
-rw-r--r-- | lib/logic_iomem.c | 16 | ||||
-rw-r--r-- | lib/math/Kconfig | 2 | ||||
-rw-r--r-- | lib/math/rational.c | 3 | ||||
-rw-r--r-- | lib/scatterlist.c | 160 | ||||
-rw-r--r-- | lib/sg_pool.c | 3 | ||||
-rw-r--r-- | lib/test_kasan.c | 80 | ||||
-rw-r--r-- | lib/test_kasan_module.c | 20 | ||||
-rw-r--r-- | lib/test_printf.c | 66 | ||||
-rw-r--r-- | lib/test_scanf.c | 79 | ||||
-rw-r--r-- | lib/test_sort.c | 40 | ||||
-rw-r--r-- | lib/test_stackinit.c | 253 | ||||
-rw-r--r-- | lib/test_vmalloc.c | 5 | ||||
-rw-r--r-- | lib/ubsan.c | 3 | ||||
-rw-r--r-- | lib/vsprintf.c | 12 |
23 files changed, 657 insertions, 275 deletions
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 12b805dabbc9..ed4a31e34098 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -346,7 +346,7 @@ config FRAME_WARN int "Warn for stack frames larger than" range 0 8192 default 2048 if GCC_PLUGIN_LATENT_ENTROPY - default 1280 if (!64BIT && PARISC) + default 1536 if (!64BIT && PARISC) default 1024 if (!64BIT && !PARISC) default 2048 if 64BIT help @@ -365,6 +365,7 @@ config STRIP_ASM_SYMS config READABLE_ASM bool "Generate readable assembler code" depends on DEBUG_KERNEL + depends on CC_IS_GCC help Disable some compiler optimizations that tend to generate human unreadable assembler output. This may make the kernel slightly slower, but it helps @@ -383,6 +384,7 @@ config HEADERS_INSTALL config DEBUG_SECTION_MISMATCH bool "Enable full Section mismatch analysis" + depends on CC_IS_GCC help The section mismatch analysis checks if there are illegal references from one section to another section. @@ -1062,7 +1064,6 @@ config HARDLOCKUP_DETECTOR depends on HAVE_HARDLOCKUP_DETECTOR_PERF || HAVE_HARDLOCKUP_DETECTOR_ARCH select LOCKUP_DETECTOR select HARDLOCKUP_DETECTOR_PERF if HAVE_HARDLOCKUP_DETECTOR_PERF - select HARDLOCKUP_DETECTOR_ARCH if HAVE_HARDLOCKUP_DETECTOR_ARCH help Say Y here to enable the kernel to act as a watchdog to detect hard lockups. @@ -2059,8 +2060,9 @@ config TEST_MIN_HEAP If unsure, say N. config TEST_SORT - tristate "Array-based sort test" - depends on DEBUG_KERNEL || m + tristate "Array-based sort test" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS help This option enables the self-test function of 'sort()' at boot, or at module load time. @@ -2441,8 +2443,7 @@ config SLUB_KUNIT_TEST config RATIONAL_KUNIT_TEST tristate "KUnit test for rational.c" if !KUNIT_ALL_TESTS - depends on KUNIT - select RATIONAL + depends on KUNIT && RATIONAL default KUNIT_ALL_TESTS help This builds the rational math unit test. diff --git a/lib/Kconfig.kcsan b/lib/Kconfig.kcsan index 0440f373248e..e0a93ffdef30 100644 --- a/lib/Kconfig.kcsan +++ b/lib/Kconfig.kcsan @@ -40,10 +40,14 @@ menuconfig KCSAN if KCSAN -# Compiler capabilities that should not fail the test if they are unavailable. config CC_HAS_TSAN_COMPOUND_READ_BEFORE_WRITE def_bool (CC_IS_CLANG && $(cc-option,-fsanitize=thread -mllvm -tsan-compound-read-before-write=1)) || \ (CC_IS_GCC && $(cc-option,-fsanitize=thread --param tsan-compound-read-before-write=1)) + help + The compiler instruments plain compound read-write operations + differently (++, --, +=, -=, |=, &=, etc.), which allows KCSAN to + distinguish them from other plain accesses. This is currently + supported by Clang 12 or later. config KCSAN_VERBOSE bool "Show verbose reports with more information about system state" @@ -58,9 +62,6 @@ config KCSAN_VERBOSE generated from any one of them, system stability may suffer due to deadlocks or recursion. If in doubt, say N. -config KCSAN_DEBUG - bool "Debugging of KCSAN internals" - config KCSAN_SELFTEST bool "Perform short selftests on boot" default y @@ -149,7 +150,8 @@ config KCSAN_SKIP_WATCH_RANDOMIZE KCSAN_WATCH_SKIP. config KCSAN_INTERRUPT_WATCHER - bool "Interruptible watchers" + bool "Interruptible watchers" if !KCSAN_STRICT + default KCSAN_STRICT help If enabled, a task that set up a watchpoint may be interrupted while delayed. This option will allow KCSAN to detect races between @@ -169,13 +171,9 @@ config KCSAN_REPORT_ONCE_IN_MS reporting to avoid flooding the console with reports. Setting this to 0 disables rate limiting. -# The main purpose of the below options is to control reported data races (e.g. -# in fuzzer configs), and are not expected to be switched frequently by other -# users. We could turn some of them into boot parameters, but given they should -# not be switched normally, let's keep them here to simplify configuration. -# -# The defaults below are chosen to be very conservative, and may miss certain -# bugs. +# The main purpose of the below options is to control reported data races, and +# are not expected to be switched frequently by non-testers or at runtime. +# The defaults are chosen to be conservative, and can miss certain bugs. config KCSAN_REPORT_RACE_UNKNOWN_ORIGIN bool "Report races of unknown origin" @@ -186,9 +184,17 @@ config KCSAN_REPORT_RACE_UNKNOWN_ORIGIN reported if it was only possible to infer a race due to a data value change while an access is being delayed on a watchpoint. +config KCSAN_STRICT + bool "Strict data-race checking" + help + KCSAN will report data races with the strictest possible rules, which + closely aligns with the rules defined by the Linux-kernel memory + consistency model (LKMM). + config KCSAN_REPORT_VALUE_CHANGE_ONLY bool "Only report races where watcher observed a data value change" default y + depends on !KCSAN_STRICT help If enabled and a conflicting write is observed via a watchpoint, but the data value of the memory location was observed to remain @@ -197,6 +203,7 @@ config KCSAN_REPORT_VALUE_CHANGE_ONLY config KCSAN_ASSUME_PLAIN_WRITES_ATOMIC bool "Assume that plain aligned writes up to word size are atomic" default y + depends on !KCSAN_STRICT help Assume that plain aligned writes up to word size are atomic by default, and also not subject to other unsafe compiler optimizations @@ -209,6 +216,7 @@ config KCSAN_ASSUME_PLAIN_WRITES_ATOMIC config KCSAN_IGNORE_ATOMICS bool "Do not instrument marked atomic accesses" + depends on !KCSAN_STRICT help Never instrument marked atomic accesses. This option can be used for additional filtering. Conflicting marked atomic reads and plain @@ -224,4 +232,14 @@ config KCSAN_IGNORE_ATOMICS due to two conflicting plain writes will be reported (aligned and unaligned, if CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC=n). +config KCSAN_PERMISSIVE + bool "Enable all additional permissive rules" + depends on KCSAN_REPORT_VALUE_CHANGE_ONLY + help + Enable additional permissive rules to ignore certain classes of data + races (also see kernel/kcsan/permissive.h). None of the permissive + rules imply that such data races are generally safe, but can be used + to further reduce reported data races due to data-racy patterns + common across the kernel. + endif # KCSAN diff --git a/lib/bootconfig.c b/lib/bootconfig.c index 927017431fb6..f8419cff1147 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -142,16 +142,16 @@ xbc_node_match_prefix(struct xbc_node *node, const char **prefix) } /** - * xbc_node_find_child() - Find a child node which matches given key + * xbc_node_find_subkey() - Find a subkey node which matches given key * @parent: An XBC node. * @key: A key string. * - * Search a node under @parent which matches @key. The @key can contain + * Search a key node under @parent which matches @key. The @key can contain * several words jointed with '.'. If @parent is NULL, this searches the * node from whole tree. Return NULL if no node is matched. */ struct xbc_node * __init -xbc_node_find_child(struct xbc_node *parent, const char *key) +xbc_node_find_subkey(struct xbc_node *parent, const char *key) { struct xbc_node *node; @@ -191,7 +191,7 @@ const char * __init xbc_node_find_value(struct xbc_node *parent, const char *key, struct xbc_node **vnode) { - struct xbc_node *node = xbc_node_find_child(parent, key); + struct xbc_node *node = xbc_node_find_subkey(parent, key); if (!node || !xbc_node_is_key(node)) return NULL; diff --git a/lib/debug_info.c b/lib/debug_info.c index 36daf753293c..cc4723c74af5 100644 --- a/lib/debug_info.c +++ b/lib/debug_info.c @@ -5,8 +5,6 @@ * CONFIG_DEBUG_INFO_REDUCED. Please do not add actual code. However, * adding appropriate #includes is fine. */ -#include <stdarg.h> - #include <linux/cred.h> #include <linux/crypto.h> #include <linux/dcache.h> @@ -22,6 +20,7 @@ #include <linux/net.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/stdarg.h> #include <linux/types.h> #include <net/addrconf.h> #include <net/sock.h> diff --git a/lib/dump_stack.c b/lib/dump_stack.c index cd3387bb34e5..6b7f1bf6715d 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -89,7 +89,8 @@ static void __dump_stack(const char *log_lvl) } /** - * dump_stack - dump the current task information and its stack trace + * dump_stack_lvl - dump the current task information and its stack trace + * @log_lvl: log level * * Architectures can override this implementation by implementing its own. */ diff --git a/lib/iov_iter.c b/lib/iov_iter.c index e23123ae3a13..f2d50d69a6c3 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -672,7 +672,7 @@ static size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes, * _copy_mc_to_iter - copy to iter with source memory error exception handling * @addr: source kernel address * @bytes: total transfer length - * @iter: destination iterator + * @i: destination iterator * * The pmem driver deploys this for the dax operation * (dax_copy_to_iter()) for dax reads (bypass page-cache and the @@ -690,6 +690,8 @@ static size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes, * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies. * Compare to copy_to_iter() where only ITER_IOVEC attempts might return * a short copy. + * + * Return: number of bytes copied (may be %0) */ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { @@ -744,7 +746,7 @@ EXPORT_SYMBOL(_copy_from_iter_nocache); * _copy_from_iter_flushcache - write destination through cpu cache * @addr: destination kernel address * @bytes: total transfer length - * @iter: source iterator + * @i: source iterator * * The pmem driver arranges for filesystem-dax to use this facility via * dax_copy_from_iter() for ensuring that writes to persistent memory @@ -753,6 +755,8 @@ EXPORT_SYMBOL(_copy_from_iter_nocache); * all iterator types. The _copy_from_iter_nocache() only attempts to * bypass the cache for the ITER_IOVEC case, and on some archs may use * instructions that strand dirty-data in the cache. + * + * Return: number of bytes copied (may be %0) */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { diff --git a/lib/kasprintf.c b/lib/kasprintf.c index bacf7b83ccf0..cd2f5974ed98 100644 --- a/lib/kasprintf.c +++ b/lib/kasprintf.c @@ -5,7 +5,7 @@ * Copyright (C) 1991, 1992 Linus Torvalds */ -#include <stdarg.h> +#include <linux/stdarg.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/types.h> diff --git a/lib/kunit/string-stream.h b/lib/kunit/string-stream.h index 5e94b623454f..43f9508a55b4 100644 --- a/lib/kunit/string-stream.h +++ b/lib/kunit/string-stream.h @@ -11,7 +11,7 @@ #include <linux/spinlock.h> #include <linux/types.h> -#include <stdarg.h> +#include <linux/stdarg.h> struct string_stream_fragment { struct kunit *test; diff --git a/lib/kunit/test.c b/lib/kunit/test.c index d79ecb86ea57..f246b847024e 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -10,6 +10,7 @@ #include <kunit/test-bug.h> #include <linux/kernel.h> #include <linux/kref.h> +#include <linux/moduleparam.h> #include <linux/sched/debug.h> #include <linux/sched.h> @@ -52,6 +53,51 @@ EXPORT_SYMBOL_GPL(__kunit_fail_current_test); #endif /* + * KUnit statistic mode: + * 0 - disabled + * 1 - only when there is more than one subtest + * 2 - enabled + */ +static int kunit_stats_enabled = 1; +module_param_named(stats_enabled, kunit_stats_enabled, int, 0644); +MODULE_PARM_DESC(stats_enabled, + "Print test stats: never (0), only for multiple subtests (1), or always (2)"); + +struct kunit_result_stats { + unsigned long passed; + unsigned long skipped; + unsigned long failed; + unsigned long total; +}; + +static bool kunit_should_print_stats(struct kunit_result_stats stats) +{ + if (kunit_stats_enabled == 0) + return false; + + if (kunit_stats_enabled == 2) + return true; + + return (stats.total > 1); +} + +static void kunit_print_test_stats(struct kunit *test, + struct kunit_result_stats stats) +{ + if (!kunit_should_print_stats(stats)) + return; + + kunit_log(KERN_INFO, test, + KUNIT_SUBTEST_INDENT + "# %s: pass:%lu fail:%lu skip:%lu total:%lu", + test->name, + stats.passed, + stats.failed, + stats.skipped, + stats.total); +} + +/* * Append formatted message to log, size of which is limited to * KUNIT_LOG_SIZE bytes (including null terminating byte). */ @@ -393,15 +439,69 @@ static void kunit_run_case_catch_errors(struct kunit_suite *suite, test_case->status = KUNIT_SUCCESS; } +static void kunit_print_suite_stats(struct kunit_suite *suite, + struct kunit_result_stats suite_stats, + struct kunit_result_stats param_stats) +{ + if (kunit_should_print_stats(suite_stats)) { + kunit_log(KERN_INFO, suite, + "# %s: pass:%lu fail:%lu skip:%lu total:%lu", + suite->name, + suite_stats.passed, + suite_stats.failed, + suite_stats.skipped, + suite_stats.total); + } + + if (kunit_should_print_stats(param_stats)) { + kunit_log(KERN_INFO, suite, + "# Totals: pass:%lu fail:%lu skip:%lu total:%lu", + param_stats.passed, + param_stats.failed, + param_stats.skipped, + param_stats.total); + } +} + +static void kunit_update_stats(struct kunit_result_stats *stats, + enum kunit_status status) +{ + switch (status) { + case KUNIT_SUCCESS: + stats->passed++; + break; + case KUNIT_SKIPPED: + stats->skipped++; + break; + case KUNIT_FAILURE: + stats->failed++; + break; + } + + stats->total++; +} + +static void kunit_accumulate_stats(struct kunit_result_stats *total, + struct kunit_result_stats add) +{ + total->passed += add.passed; + total->skipped += add.skipped; + total->failed += add.failed; + total->total += add.total; +} + int kunit_run_tests(struct kunit_suite *suite) { char param_desc[KUNIT_PARAM_DESC_SIZE]; struct kunit_case *test_case; + struct kunit_result_stats suite_stats = { 0 }; + struct kunit_result_stats total_stats = { 0 }; kunit_print_subtest_start(suite); kunit_suite_for_each_test_case(suite, test_case) { struct kunit test = { .param_value = NULL, .param_index = 0 }; + struct kunit_result_stats param_stats = { 0 }; test_case->status = KUNIT_SKIPPED; if (test_case->generate_params) { @@ -431,14 +531,23 @@ int kunit_run_tests(struct kunit_suite *suite) test.param_value = test_case->generate_params(test.param_value, param_desc); test.param_index++; } + + kunit_update_stats(¶m_stats, test.status); + } while (test.param_value); + kunit_print_test_stats(&test, param_stats); + kunit_print_ok_not_ok(&test, true, test_case->status, kunit_test_case_num(suite, test_case), test_case->name, test.status_comment); + + kunit_update_stats(&suite_stats, test_case->status); + kunit_accumulate_stats(&total_stats, param_stats); } + kunit_print_suite_stats(suite, suite_stats, total_stats); kunit_print_subtest_end(suite); return 0; diff --git a/lib/logic_iomem.c b/lib/logic_iomem.c index b76b92dd0f1f..9bdfde0c0f86 100644 --- a/lib/logic_iomem.c +++ b/lib/logic_iomem.c @@ -6,6 +6,7 @@ #include <linux/types.h> #include <linux/slab.h> #include <linux/logic_iomem.h> +#include <asm/io.h> struct logic_iomem_region { const struct resource *res; @@ -78,7 +79,7 @@ static void __iomem *real_ioremap(phys_addr_t offset, size_t size) static void real_iounmap(void __iomem *addr) { WARN(1, "invalid iounmap for addr 0x%llx\n", - (unsigned long long)addr); + (unsigned long long __force)addr); } #endif /* CONFIG_LOGIC_IOMEM_FALLBACK */ @@ -172,14 +173,15 @@ EXPORT_SYMBOL(iounmap); static u##sz real_raw_read ## op(const volatile void __iomem *addr) \ { \ WARN(1, "Invalid read" #op " at address %llx\n", \ - (unsigned long long)addr); \ + (unsigned long long __force)addr); \ return (u ## sz)~0ULL; \ } \ \ -void real_raw_write ## op(u ## sz val, volatile void __iomem *addr) \ +static void real_raw_write ## op(u ## sz val, \ + volatile void __iomem *addr) \ { \ WARN(1, "Invalid writeq" #op " of 0x%llx at address %llx\n", \ - (unsigned long long)val, (unsigned long long)addr); \ + (unsigned long long)val, (unsigned long long __force)addr);\ } \ MAKE_FALLBACK(b, 8); @@ -192,14 +194,14 @@ MAKE_FALLBACK(q, 64); static void real_memset_io(volatile void __iomem *addr, int value, size_t size) { WARN(1, "Invalid memset_io at address 0x%llx\n", - (unsigned long long)addr); + (unsigned long long __force)addr); } static void real_memcpy_fromio(void *buffer, const volatile void __iomem *addr, size_t size) { WARN(1, "Invalid memcpy_fromio at address 0x%llx\n", - (unsigned long long)addr); + (unsigned long long __force)addr); memset(buffer, 0xff, size); } @@ -208,7 +210,7 @@ static void real_memcpy_toio(volatile void __iomem *addr, const void *buffer, size_t size) { WARN(1, "Invalid memcpy_toio at address 0x%llx\n", - (unsigned long long)addr); + (unsigned long long __force)addr); } #endif /* CONFIG_LOGIC_IOMEM_FALLBACK */ diff --git a/lib/math/Kconfig b/lib/math/Kconfig index f19bc9734fa7..0634b428d0cb 100644 --- a/lib/math/Kconfig +++ b/lib/math/Kconfig @@ -14,4 +14,4 @@ config PRIME_NUMBERS If unsure, say N. config RATIONAL - bool + tristate diff --git a/lib/math/rational.c b/lib/math/rational.c index c0ab51d8fbb9..ec59d426ea63 100644 --- a/lib/math/rational.c +++ b/lib/math/rational.c @@ -13,6 +13,7 @@ #include <linux/export.h> #include <linux/minmax.h> #include <linux/limits.h> +#include <linux/module.h> /* * calculate best rational approximation for a given fraction @@ -106,3 +107,5 @@ void rational_best_approximation( } EXPORT_SYMBOL(rational_best_approximation); + +MODULE_LICENSE("GPL v2"); diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 27efa6178153..abb3432ed744 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -182,6 +182,7 @@ static void sg_kfree(struct scatterlist *sg, unsigned int nents) * @nents_first_chunk: Number of entries int the (preallocated) first * scatterlist chunk, 0 means no such preallocated first chunk * @free_fn: Free function + * @num_ents: Number of entries in the table * * Description: * Free an sg table previously allocated and setup with @@ -190,7 +191,8 @@ static void sg_kfree(struct scatterlist *sg, unsigned int nents) * **/ void __sg_free_table(struct sg_table *table, unsigned int max_ents, - unsigned int nents_first_chunk, sg_free_fn *free_fn) + unsigned int nents_first_chunk, sg_free_fn *free_fn, + unsigned int num_ents) { struct scatterlist *sgl, *next; unsigned curr_max_ents = nents_first_chunk ?: max_ents; @@ -199,8 +201,8 @@ void __sg_free_table(struct sg_table *table, unsigned int max_ents, return; sgl = table->sgl; - while (table->orig_nents) { - unsigned int alloc_size = table->orig_nents; + while (num_ents) { + unsigned int alloc_size = num_ents; unsigned int sg_size; /* @@ -218,7 +220,7 @@ void __sg_free_table(struct sg_table *table, unsigned int max_ents, next = NULL; } - table->orig_nents -= sg_size; + num_ents -= sg_size; if (nents_first_chunk) nents_first_chunk = 0; else @@ -232,13 +234,27 @@ void __sg_free_table(struct sg_table *table, unsigned int max_ents, EXPORT_SYMBOL(__sg_free_table); /** + * sg_free_append_table - Free a previously allocated append sg table. + * @table: The mapped sg append table header + * + **/ +void sg_free_append_table(struct sg_append_table *table) +{ + __sg_free_table(&table->sgt, SG_MAX_SINGLE_ALLOC, false, sg_kfree, + table->total_nents); +} +EXPORT_SYMBOL(sg_free_append_table); + + +/** * sg_free_table - Free a previously allocated sg table * @table: The mapped sg table header * **/ void sg_free_table(struct sg_table *table) { - __sg_free_table(table, SG_MAX_SINGLE_ALLOC, false, sg_kfree); + __sg_free_table(table, SG_MAX_SINGLE_ALLOC, false, sg_kfree, + table->orig_nents); } EXPORT_SYMBOL(sg_free_table); @@ -359,13 +375,12 @@ int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask) ret = __sg_alloc_table(table, nents, SG_MAX_SINGLE_ALLOC, NULL, 0, gfp_mask, sg_kmalloc); if (unlikely(ret)) - __sg_free_table(table, SG_MAX_SINGLE_ALLOC, 0, sg_kfree); - + sg_free_table(table); return ret; } EXPORT_SYMBOL(sg_alloc_table); -static struct scatterlist *get_next_sg(struct sg_table *table, +static struct scatterlist *get_next_sg(struct sg_append_table *table, struct scatterlist *cur, unsigned long needed_sges, gfp_t gfp_mask) @@ -386,54 +401,52 @@ static struct scatterlist *get_next_sg(struct sg_table *table, return ERR_PTR(-ENOMEM); sg_init_table(new_sg, alloc_size); if (cur) { + table->total_nents += alloc_size - 1; __sg_chain(next_sg, new_sg); - table->orig_nents += alloc_size - 1; } else { - table->sgl = new_sg; - table->orig_nents = alloc_size; - table->nents = 0; + table->sgt.sgl = new_sg; + table->total_nents = alloc_size; } return new_sg; } /** - * __sg_alloc_table_from_pages - Allocate and initialize an sg table from - * an array of pages - * @sgt: The sg table header to use - * @pages: Pointer to an array of page pointers - * @n_pages: Number of pages in the pages array + * sg_alloc_append_table_from_pages - Allocate and initialize an append sg + * table from an array of pages + * @sgt_append: The sg append table to use + * @pages: Pointer to an array of page pointers + * @n_pages: Number of pages in the pages array * @offset: Offset from start of the first page to the start of a buffer * @size: Number of valid bytes in the buffer (after offset) * @max_segment: Maximum size of a scatterlist element in bytes - * @prv: Last populated sge in sgt * @left_pages: Left pages caller have to set after this call * @gfp_mask: GFP allocation mask * * Description: - * If @prv is NULL, allocate and initialize an sg table from a list of pages, - * else reuse the scatterlist passed in at @prv. - * Contiguous ranges of the pages are squashed into a single scatterlist - * entry up to the maximum size specified in @max_segment. A user may - * provide an offset at a start and a size of valid data in a buffer - * specified by the page array. + * In the first call it allocate and initialize an sg table from a list of + * pages, else reuse the scatterlist from sgt_append. Contiguous ranges of + * the pages are squashed into a single scatterlist entry up to the maximum + * size specified in @max_segment. A user may provide an offset at a start + * and a size of valid data in a buffer specified by the page array. The + * returned sg table is released by sg_free_append_table * * Returns: - * Last SGE in sgt on success, PTR_ERR on otherwise. - * The allocation in @sgt must be released by sg_free_table. + * 0 on success, negative error on failure * * Notes: * If this function returns non-0 (eg failure), the caller must call - * sg_free_table() to cleanup any leftover allocations. + * sg_free_append_table() to cleanup any leftover allocations. + * + * In the fist call, sgt_append must by initialized. */ -struct scatterlist *__sg_alloc_table_from_pages(struct sg_table *sgt, +int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, unsigned int max_segment, - struct scatterlist *prv, unsigned int left_pages, - gfp_t gfp_mask) + unsigned int left_pages, gfp_t gfp_mask) { unsigned int chunks, cur_page, seg_len, i, prv_len = 0; unsigned int added_nents = 0; - struct scatterlist *s = prv; + struct scatterlist *s = sgt_append->prv; /* * The algorithm below requires max_segment to be aligned to PAGE_SIZE @@ -441,25 +454,26 @@ struct scatterlist *__sg_alloc_table_from_pages(struct sg_table *sgt, */ max_segment = ALIGN_DOWN(max_segment, PAGE_SIZE); if (WARN_ON(max_segment < PAGE_SIZE)) - return ERR_PTR(-EINVAL); + return -EINVAL; - if (IS_ENABLED(CONFIG_ARCH_NO_SG_CHAIN) && prv) - return ERR_PTR(-EOPNOTSUPP); + if (IS_ENABLED(CONFIG_ARCH_NO_SG_CHAIN) && sgt_append->prv) + return -EOPNOTSUPP; - if (prv) { - unsigned long paddr = (page_to_pfn(sg_page(prv)) * PAGE_SIZE + - prv->offset + prv->length) / - PAGE_SIZE; + if (sgt_append->prv) { + unsigned long paddr = + (page_to_pfn(sg_page(sgt_append->prv)) * PAGE_SIZE + + sgt_append->prv->offset + sgt_append->prv->length) / + PAGE_SIZE; if (WARN_ON(offset)) - return ERR_PTR(-EINVAL); + return -EINVAL; /* Merge contiguous pages into the last SG */ - prv_len = prv->length; + prv_len = sgt_append->prv->length; while (n_pages && page_to_pfn(pages[0]) == paddr) { - if (prv->length + PAGE_SIZE > max_segment) + if (sgt_append->prv->length + PAGE_SIZE > max_segment) break; - prv->length += PAGE_SIZE; + sgt_append->prv->length += PAGE_SIZE; paddr++; pages++; n_pages--; @@ -496,15 +510,16 @@ struct scatterlist *__sg_alloc_table_from_pages(struct sg_table *sgt, } /* Pass how many chunks might be left */ - s = get_next_sg(sgt, s, chunks - i + left_pages, gfp_mask); + s = get_next_sg(sgt_append, s, chunks - i + left_pages, + gfp_mask); if (IS_ERR(s)) { /* * Adjust entry length to be as before function was * called. */ - if (prv) - prv->length = prv_len; - return s; + if (sgt_append->prv) + sgt_append->prv->length = prv_len; + return PTR_ERR(s); } chunk_size = ((j - cur_page) << PAGE_SHIFT) - offset; sg_set_page(s, pages[cur_page], @@ -514,42 +529,58 @@ struct scatterlist *__sg_alloc_table_from_pages(struct sg_table *sgt, offset = 0; cur_page = j; } - sgt->nents += added_nents; + sgt_append->sgt.nents += added_nents; + sgt_append->sgt.orig_nents = sgt_append->sgt.nents; + sgt_append->prv = s; out: if (!left_pages) sg_mark_end(s); - return s; + return 0; } -EXPORT_SYMBOL(__sg_alloc_table_from_pages); +EXPORT_SYMBOL(sg_alloc_append_table_from_pages); /** - * sg_alloc_table_from_pages - Allocate and initialize an sg table from - * an array of pages + * sg_alloc_table_from_pages_segment - Allocate and initialize an sg table from + * an array of pages and given maximum + * segment. * @sgt: The sg table header to use * @pages: Pointer to an array of page pointers * @n_pages: Number of pages in the pages array * @offset: Offset from start of the first page to the start of a buffer * @size: Number of valid bytes in the buffer (after offset) + * @max_segment: Maximum size of a scatterlist element in bytes * @gfp_mask: GFP allocation mask * * Description: * Allocate and initialize an sg table from a list of pages. Contiguous - * ranges of the pages are squashed into a single scatterlist node. A user - * may provide an offset at a start and a size of valid data in a buffer - * specified by the page array. The returned sg table is released by - * sg_free_table. + * ranges of the pages are squashed into a single scatterlist node up to the + * maximum size specified in @max_segment. A user may provide an offset at a + * start and a size of valid data in a buffer specified by the page array. * - * Returns: + * The returned sg table is released by sg_free_table. + * + * Returns: * 0 on success, negative error on failure */ -int sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages, - unsigned int n_pages, unsigned int offset, - unsigned long size, gfp_t gfp_mask) +int sg_alloc_table_from_pages_segment(struct sg_table *sgt, struct page **pages, + unsigned int n_pages, unsigned int offset, + unsigned long size, unsigned int max_segment, + gfp_t gfp_mask) { - return PTR_ERR_OR_ZERO(__sg_alloc_table_from_pages(sgt, pages, n_pages, - offset, size, UINT_MAX, NULL, 0, gfp_mask)); + struct sg_append_table append = {}; + int err; + + err = sg_alloc_append_table |