diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-12-13 14:05:39 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-12-13 14:05:39 -0800 |
commit | 3ba2c3ff98ea8bfb219288dbacf2a23a902c751b (patch) | |
tree | 90165b304a5b0cf50bc88883ca7a61f1cec65b8c | |
parent | 0015edd6f66172f93aa720192020138ca13ba0a6 (diff) | |
parent | 4f1354d5c6a3264c91238962d1597eef40c40419 (diff) |
Merge tag 'modules-6.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux
Pull modules updates from Luis Chamberlain:
"Tux gets for xmas an improvement to the average lookup performance of
kallsyms_lookup_name() by 715x thanks to the work by Zhen Lei, which
upgraded our old implementation from being O(n) to O(log(n)), while
also retaining the old implementation support on /proc/kallsyms.
The only penalty was increasing the memory footprint by 3 *
kallsyms_num_syms. Folks who want to improve this further now also
have a dedicated selftest facility through KALLSYMS_SELFTEST.
Stephen Boyd added zstd in-kernel decompression support, but the only
users of this would be folks using the load-pin LSM because otherwise
we do module decompression in userspace.
The only other thing with mentioning is a minor boot time optimization
by Rasmus Villemoes which deferes param_sysfs_init() to late init. The
rest is cleanups and minor fixes"
* tag 'modules-6.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux:
livepatch: Call klp_match_callback() in klp_find_callback() to avoid code duplication
module/decompress: Support zstd in-kernel decompression
kallsyms: Remove unneeded semicolon
kallsyms: Add self-test facility
livepatch: Use kallsyms_on_each_match_symbol() to improve performance
kallsyms: Add helper kallsyms_on_each_match_symbol()
kallsyms: Reduce the memory occupied by kallsyms_seqs_of_names[]
kallsyms: Correctly sequence symbols when CONFIG_LTO_CLANG=y
kallsyms: Improve the performance of kallsyms_lookup_name()
scripts/kallsyms: rename build_initial_tok_table()
module: Fix NULL vs IS_ERR checking for module_get_next_page
kernel/params.c: defer most of param_sysfs_init() to late_initcall time
module: Remove unused macros module_addr_min/max
module: remove redundant module_sysfs_initialized variable
-rw-r--r-- | include/linux/kallsyms.h | 9 | ||||
-rw-r--r-- | include/linux/module.h | 1 | ||||
-rw-r--r-- | init/Kconfig | 13 | ||||
-rw-r--r-- | kernel/Makefile | 1 | ||||
-rw-r--r-- | kernel/kallsyms.c | 116 | ||||
-rw-r--r-- | kernel/kallsyms_internal.h | 1 | ||||
-rw-r--r-- | kernel/kallsyms_selftest.c | 485 | ||||
-rw-r--r-- | kernel/kallsyms_selftest.h | 13 | ||||
-rw-r--r-- | kernel/livepatch/core.c | 31 | ||||
-rw-r--r-- | kernel/module/Kconfig | 3 | ||||
-rw-r--r-- | kernel/module/decompress.c | 100 | ||||
-rw-r--r-- | kernel/module/main.c | 3 | ||||
-rw-r--r-- | kernel/module/sysfs.c | 2 | ||||
-rw-r--r-- | kernel/params.c | 23 | ||||
-rw-r--r-- | scripts/kallsyms.c | 78 | ||||
-rwxr-xr-x | scripts/link-vmlinux.sh | 4 |
16 files changed, 840 insertions, 43 deletions
diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 649faac31ddb..0065209cc004 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -66,9 +66,12 @@ static inline void *dereference_symbol_descriptor(void *ptr) } #ifdef CONFIG_KALLSYMS +unsigned long kallsyms_sym_address(int idx); int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data); +int kallsyms_on_each_match_symbol(int (*fn)(void *, unsigned long), + const char *name, void *data); /* Lookup the address for a symbol. Returns 0 if not found. */ unsigned long kallsyms_lookup_name(const char *name); @@ -168,6 +171,12 @@ static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct { return -EOPNOTSUPP; } + +static inline int kallsyms_on_each_match_symbol(int (*fn)(void *, unsigned long), + const char *name, void *data) +{ + return -EOPNOTSUPP; +} #endif /*CONFIG_KALLSYMS*/ static inline void print_ip_sym(const char *loglvl, unsigned long ip) diff --git a/include/linux/module.h b/include/linux/module.h index ec61fb53979a..676614d56c25 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -827,7 +827,6 @@ void *dereference_module_function_descriptor(struct module *mod, void *ptr) #ifdef CONFIG_SYSFS extern struct kset *module_kset; extern struct kobj_type module_ktype; -extern int module_sysfs_initialized; #endif /* CONFIG_SYSFS */ #define symbol_request(x) try_then_request_module(symbol_get(x), "symbol:" #x) diff --git a/init/Kconfig b/init/Kconfig index 94125d3b6893..e1938e3a753e 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1723,6 +1723,19 @@ config KALLSYMS symbolic stack backtraces. This increases the size of the kernel somewhat, as all symbols have to be loaded into the kernel image. +config KALLSYMS_SELFTEST + bool "Test the basic functions and performance of kallsyms" + depends on KALLSYMS + default n + help + Test the basic functions and performance of some interfaces, such as + kallsyms_lookup_name. It also calculates the compression rate of the + kallsyms compression algorithm for the current symbol set. + + Start self-test automatically after system startup. Suggest executing + "dmesg | grep kallsyms_selftest" to collect test results. "finish" is + displayed in the last line, indicating that the test is complete. + config KALLSYMS_ALL bool "Include all symbols in kallsyms" depends on DEBUG_KERNEL && KALLSYMS diff --git a/kernel/Makefile b/kernel/Makefile index d754e0be1176..e7fc37a68069 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -69,6 +69,7 @@ endif obj-$(CONFIG_UID16) += uid16.o obj-$(CONFIG_MODULE_SIG_FORMAT) += module_signature.o obj-$(CONFIG_KALLSYMS) += kallsyms.o +obj-$(CONFIG_KALLSYMS_SELFTEST) += kallsyms_selftest.o obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o obj-$(CONFIG_CRASH_CORE) += crash_core.o obj-$(CONFIG_KEXEC_CORE) += kexec_core.o diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 60c20f301a6b..83f499182c9a 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -146,7 +146,7 @@ static unsigned int get_symbol_offset(unsigned long pos) return name - kallsyms_names; } -static unsigned long kallsyms_sym_address(int idx) +unsigned long kallsyms_sym_address(int idx) { if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE)) return kallsyms_addresses[idx]; @@ -187,26 +187,100 @@ static bool cleanup_symbol_name(char *s) return false; } +static int compare_symbol_name(const char *name, char *namebuf) +{ + int ret; + + ret = strcmp(name, namebuf); + if (!ret) + return ret; + + if (cleanup_symbol_name(namebuf) && !strcmp(name, namebuf)) + return 0; + + return ret; +} + +static unsigned int get_symbol_seq(int index) +{ + unsigned int i, seq = 0; + + for (i = 0; i < 3; i++) + seq = (seq << 8) | kallsyms_seqs_of_names[3 * index + i]; + + return seq; +} + +static int kallsyms_lookup_names(const char *name, + unsigned int *start, + unsigned int *end) +{ + int ret; + int low, mid, high; + unsigned int seq, off; + char namebuf[KSYM_NAME_LEN]; + + low = 0; + high = kallsyms_num_syms - 1; + + while (low <= high) { + mid = low + (high - low) / 2; + seq = get_symbol_seq(mid); + off = get_symbol_offset(seq); + kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); + ret = compare_symbol_name(name, namebuf); + if (ret > 0) + low = mid + 1; + else if (ret < 0) + high = mid - 1; + else + break; + } + + if (low > high) + return -ESRCH; + + low = mid; + while (low) { + seq = get_symbol_seq(low - 1); + off = get_symbol_offset(seq); + kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); + if (compare_symbol_name(name, namebuf)) + break; + low--; + } + *start = low; + + if (end) { + high = mid; + while (high < kallsyms_num_syms - 1) { + seq = get_symbol_seq(high + 1); + off = get_symbol_offset(seq); + kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); + if (compare_symbol_name(name, namebuf)) + break; + high++; + } + *end = high; + } + + return 0; +} + /* Lookup the address for this symbol. Returns 0 if not found. */ unsigned long kallsyms_lookup_name(const char *name) { - char namebuf[KSYM_NAME_LEN]; - unsigned long i; - unsigned int off; + int ret; + unsigned int i; /* Skip the search for empty string. */ if (!*name) return 0; - for (i = 0, off = 0; i < kallsyms_num_syms; i++) { - off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); - - if (strcmp(namebuf, name) == 0) - return kallsyms_sym_address(i); + ret = kallsyms_lookup_names(name, &i, NULL); + if (!ret) + return kallsyms_sym_address(get_symbol_seq(i)); - if (cleanup_symbol_name(namebuf) && strcmp(namebuf, name) == 0) - return kallsyms_sym_address(i); - } return module_kallsyms_lookup_name(name); } @@ -233,6 +307,24 @@ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, return 0; } +int kallsyms_on_each_match_symbol(int (*fn)(void *, unsigned long), + const char *name, void *data) +{ + int ret; + unsigned int i, start, end; + + ret = kallsyms_lookup_names(name, &start, &end); + if (ret) + return 0; + + for (i = start; !ret && i <= end; i++) { + ret = fn(data, kallsyms_sym_address(get_symbol_seq(i))); + cond_resched(); + } + + return ret; +} + static unsigned long get_symbol_pos(unsigned long addr, unsigned long *symbolsize, unsigned long *offset) diff --git a/kernel/kallsyms_internal.h b/kernel/kallsyms_internal.h index 2d0c6f2f0243..27fabdcc40f5 100644 --- a/kernel/kallsyms_internal.h +++ b/kernel/kallsyms_internal.h @@ -26,5 +26,6 @@ extern const char kallsyms_token_table[] __weak; extern const u16 kallsyms_token_index[] __weak; extern const unsigned int kallsyms_markers[] __weak; +extern const u8 kallsyms_seqs_of_names[] __weak; #endif // LINUX_KALLSYMS_INTERNAL_H_ diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c new file mode 100644 index 000000000000..f35d9cc1aab1 --- /dev/null +++ b/kernel/kallsyms_selftest.c @@ -0,0 +1,485 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Test the function and performance of kallsyms + * + * Copyright (C) Huawei Technologies Co., Ltd., 2022 + * + * Authors: Zhen Lei <thunder.leizhen@huawei.com> Huawei + */ + +#define pr_fmt(fmt) "kallsyms_selftest: " fmt + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/kallsyms.h> +#include <linux/random.h> +#include <linux/sched/clock.h> +#include <linux/kthread.h> +#include <linux/vmalloc.h> + +#include "kallsyms_internal.h" +#include "kallsyms_selftest.h" + + +#define MAX_NUM_OF_RECORDS 64 + +struct test_stat { + int min; + int max; + int save_cnt; + int real_cnt; + int perf; + u64 sum; + char *name; + unsigned long addr; + unsigned long addrs[MAX_NUM_OF_RECORDS]; +}; + +struct test_item { + char *name; + unsigned long addr; +}; + +#define ITEM_FUNC(s) \ + { \ + .name = #s, \ + .addr = (unsigned long)s, \ + } + +#define ITEM_DATA(s) \ + { \ + .name = #s, \ + .addr = (unsigned long)&s, \ + } + + +static int kallsyms_test_var_bss_static; +static int kallsyms_test_var_data_static = 1; +int kallsyms_test_var_bss; +int kallsyms_test_var_data = 1; + +static int kallsyms_test_func_static(void) +{ + kallsyms_test_var_bss_static++; + kallsyms_test_var_data_static++; + + return 0; +} + +int kallsyms_test_func(void) +{ + return kallsyms_test_func_static(); +} + +__weak int kallsyms_test_func_weak(void) +{ + kallsyms_test_var_bss++; + kallsyms_test_var_data++; + return 0; +} + +static struct test_item test_items[] = { + ITEM_FUNC(kallsyms_test_func_static), + ITEM_FUNC(kallsyms_test_func), + ITEM_FUNC(kallsyms_test_func_weak), + ITEM_FUNC(vmalloc), + ITEM_FUNC(vfree), +#ifdef CONFIG_KALLSYMS_ALL + ITEM_DATA(kallsyms_test_var_bss_static), + ITEM_DATA(kallsyms_test_var_data_static), + ITEM_DATA(kallsyms_test_var_bss), + ITEM_DATA(kallsyms_test_var_data), + ITEM_DATA(vmap_area_list), +#endif +}; + +static char stub_name[KSYM_NAME_LEN]; + +static int stat_symbol_len(void *data, const char *name, struct module *mod, unsigned long addr) +{ + *(u32 *)data += strlen(name); + + return 0; +} + +static void test_kallsyms_compression_ratio(void) +{ + u32 pos, off, len, num; + u32 ratio, total_size, total_len = 0; + + kallsyms_on_each_symbol(stat_symbol_len, &total_len); + + /* + * A symbol name cannot start with a number. This stub name helps us + * traverse the entire symbol table without finding a match. It's used + * for subsequent performance tests, and its length is the average + * length of all symbol names. + */ + memset(stub_name, '4', sizeof(stub_name)); + pos = total_len / kallsyms_num_syms; + stub_name[pos] = 0; + + pos = 0; + num = 0; + off = 0; + while (pos < kallsyms_num_syms) { + len = kallsyms_names[off]; + num++; + off++; + pos++; + if ((len & 0x80) != 0) { + len = (len & 0x7f) | (kallsyms_names[off] << 7); + num++; + off++; + } + off += len; + } + + /* + * 1. The length fields is not counted + * 2. The memory occupied by array kallsyms_token_table[] and + * kallsyms_token_index[] needs to be counted. + */ + total_size = off - num; + pos = kallsyms_token_index[0xff]; + total_size += pos + strlen(&kallsyms_token_table[pos]) + 1; + total_size += 0x100 * sizeof(u16); + + pr_info(" ---------------------------------------------------------\n"); + pr_info("| nr_symbols | compressed size | original size | ratio(%%) |\n"); + pr_info("|---------------------------------------------------------|\n"); + ratio = (u32)div_u64(10000ULL * total_size, total_len); + pr_info("| %10d | %10d | %10d | %2d.%-2d |\n", + kallsyms_num_syms, total_size, total_len, ratio / 100, ratio % 100); + pr_info(" ---------------------------------------------------------\n"); +} + +static int lookup_name(void *data, const char *name, struct module *mod, unsigned long addr) +{ + u64 t0, t1, t; + unsigned long flags; + struct test_stat *stat = (struct test_stat *)data; + + local_irq_save(flags); + t0 = sched_clock(); + (void)kallsyms_lookup_name(name); + t1 = sched_clock(); + local_irq_restore(flags); + + t = t1 - t0; + if (t < stat->min) + stat->min = t; + + if (t > stat->max) + stat->max = t; + + stat->real_cnt++; + stat->sum += t; + + return 0; +} + +static void test_perf_kallsyms_lookup_name(void) +{ + struct test_stat stat; + + memset(&stat, 0, sizeof(stat)); + stat.min = INT_MAX; + kallsyms_on_each_symbol(lookup_name, &stat); + pr_info("kallsyms_lookup_name() looked up %d symbols\n", stat.real_cnt); + pr_info("The time spent on each symbol is (ns): min=%d, max=%d, avg=%lld\n", + stat.min, stat.max, div_u64(stat.sum, stat.real_cnt)); +} + +static bool match_cleanup_name(const char *s, const char *name) +{ + char *p; + int len; + + if (!IS_ENABLED(CONFIG_LTO_CLANG)) + return false; + + p = strchr(s, '.'); + if (!p) + return false; + + len = strlen(name); + if (p - s != len) + return false; + + return !strncmp(s, name, len); +} + +static int find_symbol(void *data, const char *name, struct module *mod, unsigned long addr) +{ + struct test_stat *stat = (struct test_stat *)data; + + if (strcmp(name, stat->name) == 0 || + (!stat->perf && match_cleanup_name(name, stat->name))) { + stat->real_cnt++; + stat->addr = addr; + + if (stat->save_cnt < MAX_NUM_OF_RECORDS) { + stat->addrs[stat->save_cnt] = addr; + stat->save_cnt++; + } + + if (stat->real_cnt == stat->max) + return 1; + } + + return 0; +} + +static void test_perf_kallsyms_on_each_symbol(void) +{ + u64 t0, t1; + unsigned long flags; + struct test_stat stat; + + memset(&stat, 0, sizeof(stat)); + stat.max = INT_MAX; + stat.name = stub_name; + stat.perf = 1; + local_irq_save(flags); + t0 = sched_clock(); + kallsyms_on_each_symbol(find_symbol, &stat); + t1 = sched_clock(); + local_irq_restore(flags); + pr_info("kallsyms_on_each_symbol() traverse all: %lld ns\n", t1 - t0); +} + +static int match_symbol(void *data, unsigned long addr) +{ + struct test_stat *stat = (struct test_stat *)data; + + stat->real_cnt++; + stat->addr = addr; + + if (stat->save_cnt < MAX_NUM_OF_RECORDS) { + stat->addrs[stat->save_cnt] = addr; + stat->save_cnt++; + } + + if (stat->real_cnt == stat->max) + return 1; + + return 0; +} + +static void test_perf_kallsyms_on_each_match_symbol(void) +{ + u64 t0, t1; + unsigned long flags; + struct test_stat stat; + + memset(&stat, 0, sizeof(stat)); + stat.max = INT_MAX; + stat.name = stub_name; + local_irq_save(flags); + t0 = sched_clock(); + kallsyms_on_each_match_symbol(match_symbol, stat.name, &stat); + t1 = sched_clock(); + local_irq_restore(flags); + pr_info("kallsyms_on_each_match_symbol() traverse all: %lld ns\n", t1 - t0); +} + +static int test_kallsyms_basic_function(void) +{ + int i, j, ret; + int next = 0, nr_failed = 0; + char *prefix; + unsigned short rand; + unsigned long addr, lookup_addr; + char namebuf[KSYM_NAME_LEN]; + struct test_stat *stat, *stat2; + + stat = kmalloc(sizeof(*stat) * 2, GFP_KERNEL); + if (!stat) + return -ENOMEM; + stat2 = stat + 1; + + prefix = "kallsyms_lookup_name() for"; + for (i = 0; i < ARRAY_SIZE(test_items); i++) { + addr = kallsyms_lookup_name(test_items[i].name); + if (addr != test_items[i].addr) { + nr_failed++; + pr_info("%s %s failed: addr=%lx, expect %lx\n", + prefix, test_items[i].name, addr, test_items[i].addr); + } + } + + prefix = "kallsyms_on_each_symbol() for"; + for (i = 0; i < ARRAY_SIZE(test_items); i++) { + memset(stat, 0, sizeof(*stat)); + stat->max = INT_MAX; + stat->name = test_items[i].name; + kallsyms_on_each_symbol(find_symbol, stat); + if (stat->addr != test_items[i].addr || stat->real_cnt != 1) { + nr_failed++; + pr_info("%s %s failed: count=%d, addr=%lx, expect %lx\n", + prefix, test_items[i].name, + stat->real_cnt, stat->addr, test_items[i].addr); + } + } + + prefix = "kallsyms_on_each_match_symbol() for"; + for (i = 0; i < ARRAY_SIZE(test_items); i++) { + memset(stat, 0, sizeof(*stat)); + stat->max = INT_MAX; + stat->name = test_items[i].name; + kallsyms_on_each_match_symbol(match_symbol, test_items[i].name, stat); + if (stat->addr != test_items[i].addr || stat->real_cnt != 1) { + nr_failed++; + pr_info("%s %s failed: count=%d, addr=%lx, expect %lx\n", + prefix, test_items[i].name, + stat->real_cnt, stat->addr, test_items[i].addr); + } + } + + if (nr_failed) { + kfree(stat); + return -ESRCH; + } + + for (i = 0; i < kallsyms_num_syms; i++) { + addr = kallsyms_sym_address(i); + if (!is_ksym_addr(addr)) + continue; + + ret = lookup_symbol_name(addr, namebuf); + if (unlikely(ret)) { + namebuf[0] = 0; + goto failed; + } + + /* + * The first '.' may be the initial letter, in which case the + * entire symbol name will be truncated to an empty string in + * cleanup_symbol_name(). Do not test these symbols. + * + * For example: + * cat /proc/kallsyms | awk '{print $3}' | grep -E "^\." | head + * .E_read_words + * .E_leading_bytes + * .E_trailing_bytes + * .E_write_words + * .E_copy + * .str.292.llvm.12122243386960820698 + * .str.24.llvm.12122243386960820698 + * .str.29.llvm.12122243386960820698 + * .str.75.llvm.12122243386960820698 + * .str.99.llvm.12122243386960820698 + */ + if (IS_ENABLED(CONFIG_LTO_CLANG) && !namebuf[0]) + continue; + + lookup_addr = kallsyms_lookup_name(namebuf); + + memset(stat, 0, sizeof(*stat)); + stat->max = INT_MAX; + kallsyms_on_each_match_symbol(match_symbol, namebuf, stat); + + /* + * kallsyms_on_each_symbol() is too slow, randomly select some + * symbols for test. + */ + if (i >= next) { + memset(stat2, 0, sizeof(*stat2)); + stat2->max = INT_MAX; + stat2->name = namebuf; + kallsyms_on_each_symbol(find_symbol, stat2); + + /* + * kallsyms_on_each_symbol() and kallsyms_on_each_match_symbol() + * need to get the same traversal result. + */ + if (stat->addr != stat2->addr || + stat->real_cnt != stat2->real_cnt || + memcmp(stat->addrs, stat2->addrs, + stat->save_cnt * sizeof(stat->addrs[0]))) + goto failed; + + /* + * The average of random increments is 128, that is, one of + * them is tested every 128 symbols. + */ + get_random_bytes(&rand, sizeof(rand)); + next = i + (rand & 0xff) + 1; + } + + /* Need to be found at least once */ + if (!stat->real_cnt) + goto failed; + + /* + * kallsyms_lookup_name() returns the address of the first + * symbol found and cannot be NULL. + */ + if (!lookup_addr || lookup_addr != stat->addrs[0]) + goto failed; + + /* + * If the addresses of all matching symbols are recorded, the + * target address needs to be exist. + */ + if (stat->real_cnt <= MAX_NUM_OF_RECORDS) { + for (j = 0; j < stat->save_cnt; j++) { + if (stat->addrs[j] == addr) + break; + } + + if (j == stat->save_cnt) + goto failed; + } + } + + kfree(stat); + + return 0; + +failed: + pr_info("Test for %dth symbol failed: (%s) addr=%lx", i, namebuf, addr); + kfree(stat); + return -ESRCH; +} + +static int test_entry(void *p) +{ + int ret; + + do { + schedule_timeout(5 * HZ); + } while (system_state != SYSTEM_RUNNING); + + pr_info("start\n"); + ret = test_kallsyms_basic_function(); + if (ret) { + pr_info("abort\n"); + return 0; + } + + test_kallsyms_compression_ratio(); + test_perf_kallsyms_lookup_name(); + test_perf_kallsyms_on_each_symbol(); + test_perf_kallsyms_on_each_match_symbol(); + pr_info("finish\n"); + + return 0; +} + +static int __init kallsyms_test_init(void) +{ + struct task_struct *t; + + t = kthread_create(test_entry, NULL, "kallsyms_test"); + if (IS_ERR(t)) { + pr_info("Create kallsyms selftest task failed\n"); + return PTR_ERR(t); + } + kthread_bind(t, 0); + wake_up_process(t); + + return 0; +} +late_initcall(kallsyms_test_init); diff --git a/kernel/kallsyms_selftest.h b/kernel/kallsyms_selftest.h new file mode 100644 index 000000000000..c0ca548e2a22 --- /dev/null +++ b/kernel/kallsyms_selftest.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef LINUX_KALLSYMS_SELFTEST_H_ +#define LINUX_KALLSYMS_SELFTEST_H_ + +#include <linux/types.h> + +extern int kallsyms_test_var_bss; +extern int kallsyms_test_var_data; + +extern int kallsyms_test_func(void); +extern int kallsyms_test_func_weak(void); + +#endif // LINUX_KALLSYMS_SELFTEST_H_ diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 9ada0bc5247b..201f0c0482fb 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -125,20 +125,10 @@ struct klp_find_arg { unsigned long pos; }; -static int klp_find_callback(void *data, const char *name, - struct module *mod, unsigned long addr) +static int klp_match_callback(void *data, unsigned long addr) { struct klp_find_arg *args = data; - if ((mod && !args->objname) || (!mod && args->objname)) - return 0; - - if (strcmp(args->name, name)) - return 0; - - if (args->objname && strcmp(args->objname, mod->name)) - return 0; - args->addr = addr; args->count++; @@ -153,6 +143,23 @@ static int klp_find_callback(void *data, const char *name, return 0; } +static int klp_find_callback(void *data, const char *name, + struct module *mod, unsigned long addr) +{ + struct klp_find_arg *args = data; + + if ((mod && !args->objname) || (!mod && args->objname)) + return 0; + + if (strcmp(args->name, name)) + return 0; + + if (args->objname && strcmp(args->objname, mod->name)) + return 0; + + return klp_match_callback(data, addr); +} + static int klp_find_object_symbol(const char *objname, const char *name, unsigned long sympos, unsigned long *addr) { @@ -167,7 +174,7 @@ static int klp_find_object_symbol(const char *objname, const char *name, if (objname) module_kallsyms_on_each_symbol(klp_find_callback, &args); else - kallsyms_on_each_symbol(klp_find_callback, &args); + kallsyms_on_each_match_symbol(klp_match_callback, name, &args); /* * Ensure an address was found. If sympos is 0, ensure symbol is unique; diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index 26ea5d04f56c..424b3bc58f3f 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -221,9 +221,10 @@ endchoice config MODULE_DECOMPRESS bool "Support in-kernel module decompression" - depends on MODULE_COMPRESS_GZIP || MODULE_COMPRESS_XZ + depends on MODULE_COMPRESS_GZIP || MODULE_COMPRESS_XZ || MODULE_COMPRESS_ZSTD select ZLIB_INFLATE if MODULE_COMPRESS_GZIP select XZ_DEC if MODULE_COMPRESS_XZ + select ZSTD_DECOMPRESS if MODULE_COMPRESS_ZSTD help Support for decompressing kernel modules by the kernel itself diff --git a/kernel/module/decompress.c b/kernel/module/decompress.c index c033572d83f0..bb79ac1a6d8f 100644 --- a/kernel/module/decompress.c +++ b/kernel/module/decompress.c @@ -50,7 +50,7 @@ static struct page *module_get_next_page(struct load_info *info) return page; } -#ifdef CONFIG_MODULE_COMPRESS_GZIP +#if defined(CONFIG_MODULE_COMPRESS_GZIP) #include <linux/zlib.h> #define MODULE_COMPRESSION gzip #define MODULE_DECOMPRESS_FN module_gzip_decompress @@ -114,8 +114,8 @@ static ssize_t module_gzip_decompress(struct load_info *info, do { struct page *page = module_get_next_page(info); - if (!page) { - retval = -ENOMEM; + if (IS_ERR(page)) { + retval = PTR_ERR(page); goto out_inflate_end; } @@ -141,7 +141,7 @@ out: kfree(s.workspace); return retval; } -#elif CONFIG_MODULE_COMPRESS_XZ +#elif defined(CONFIG_MODULE_COMPRESS_XZ) #include <linux/xz.h> #define MODULE_COMPRESSION xz #define MODULE_DECOMPRESS_FN module_xz_decompress @@ -173,8 +173,8 @@ static ssize_t module_xz_decompress(struct load_info *info, do { struct page *page = module_get_next_page(info); - if (!page) { - retval = -ENOMEM; + if (IS_ERR(page)) { + retval = PTR_ERR(page); goto out; } @@ -199,6 +199,94 @@ static ssize_t module_xz_decompress(struct load_info *info, xz_dec_end(xz_dec); return retval; } +#elif defined(CONFIG_MODULE_COMPRESS_ZSTD) +#include <linux/zstd.h> +#define MODULE_COMPRESSION zstd +#define MODULE_DECOMPRESS_FN module_zstd_decompress + +static ssize_t module_zstd_decompress(struct load_info *info, + const void *buf, size_t size) +{ + static const u8 signature[] = { 0x28, 0xb5, 0x2f, 0xfd }; + ZSTD_outBuffer zstd_dec; + ZSTD_inBuffer zstd_buf; + zstd_frame_header header; + size_t wksp_size; + void *wksp = NULL; + ZSTD_DStream *dstream; + size_t ret; + size_t new_size = 0; + int retval; + + if (size < sizeof(signature) || + memcmp(buf, signature, sizeof(signature))) { + pr_err("not a zstd compressed module\n"); + return -EINVAL; + } + + zstd_buf.src = buf; + zstd_buf.pos = 0; + zstd_buf.size = size; + + ret = zstd_get_frame_header(&header, zstd_buf.src, zstd_buf.size); + if (ret != 0) { + pr_err("ZSTD-compressed data has an incomplete frame header\n"); + retval = -EINVAL; + goto out; + } + if (header.windowSize > (1 << ZSTD_WINDOWLOG_MAX)) { + pr_err("ZSTD-compressed data has too large a window size\n"); + retval = -EINVAL; + goto out; + } + + wksp_size = zstd_dstream_workspace_bound(header.windowSize); + wksp = kmalloc(wksp_size, GFP_KERNEL); + if (!wksp) { + retval = -ENOMEM; + goto out; + } + + dstream = zstd_init_dstream(header.windowSize, wksp, wksp_size); + if (!dstream) { + pr_err("Can't initialize ZSTD stream\n"); + retval = -ENOMEM; + goto out; + } + + do { + struct page *page = module_get_next_page(info); + + if (!IS_ERR(page)) { + retval = PTR_ERR(page); + goto out; + } + + zstd_dec.dst = kmap_local_page(page); + zstd_dec.pos = 0; + zstd_dec.size = PAGE_SIZE; + + ret = zstd_decompress_stream(dstream, &zstd_dec, &zstd_buf); + kunmap(page); + retval = zstd_get_error_code(ret); + if (retval) + break; + + new_size += zstd_dec.pos; + } while (zstd_dec.pos == PAGE_SIZE && ret != 0); + + if (retval) { + pr_err("ZSTD-decompression failed with status %d\n", retval); + retval = -EINVAL; + goto out; + } + + retval = new_size; + + out: + kfree(wksp); + return retval; +} #else #error "Unexpected configuration for CONFIG_MODULE_DECOMPRESS" #endif diff --git a/kernel/module/main.c b/kernel/module/main.c index d02d39c7174e..ff2dfd1f548d 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -85,9 +85,6 @@ struct mod_tree_root mod_data_tree __cacheline_aligned = { }; #endif -#define module_addr_min mod_tree.addr_min -#define module_addr_max mod_tree.addr_max - struct symsearch { const struct kernel_symbol *start, *stop; const s32 *crcs; diff --git a/kernel/module/sysfs.c b/kernel/module/sysfs.c index ce68f821dcd1..c921bf044050 100644 --- a/kernel/module/sysfs.c +++ b/kernel/module/sysfs.c @@ -340,7 +340,7 @@ static int mod_sysfs_init(struct module *mod) int err; struct kobject *kobj; - if (!module_sysfs_initialized) { + if (!module_kset) { pr_err("%s: module sysfs not initialized\n", mod->name); err = -EINVAL; goto out; diff --git a/kernel/params.c b/kernel/params.c index 5b92310425c5..a06f80c56f19 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -940,7 +940,6 @@ static const struct kset_uevent_ops module_uevent_ops = { }; struct kset *module_kset; -int module_sysfs_initialized; static void module_kobj_release(struct kobject *kobj) { @@ -954,7 +953,11 @@ struct kobj_type module_ktype = { }; /* - * param_sysfs_init - wrapper for built-in params support + * param_sysfs_init - create "module" kset + * + * This must be done before the initramfs is unpacked and + * request_module() thus becomes possible, because otherwise the + * module load would fail in mod_sysfs_init. */ static int __init param_sysfs_init(void) { @@ -964,13 +967,25 @@ static int __init param_sysfs_init(void) __FILE__, __LINE__); return -ENOMEM; } - module_sysfs_initialized = 1; + + return 0; +} +subsys_initcall(param_sysfs_init); + +/* + * param_sysfs_builtin_init - add sysfs version and parameter + * attributes for built-in modules + */ +static int __init param_sysfs_builtin_init(void) +{ + if (!module_kset) + return -ENOMEM; version_sysfs_builtin(); param_sysfs_builtin(); return 0; } -subsys_initcall(param_sysfs_init); +late_initcall(param_sysfs_builtin_init); #endif /* CONFIG_SYSFS */ diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 03fa07ad45d9..04e04fbd9625 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -49,6 +49,7 @@ _Static_assert( struct sym_entry { unsigned long long addr; unsigned int len; + unsigned int seq; unsigned int start_pos; unsigned int percpu_absolute; unsigned char sym[]; @@ -77,6 +78,7 @@ static unsigned int table_size, table_cnt; static int all_symbols; static int absolute_percpu; static int base_relative; +static int lto_clang; static int token_profit[0x10000]; @@ -88,7 +90,7 @@ static unsigned char best_table_len[256]; static void usage(void) { fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] " - "[--base-relative] in.map > out.S\n"); + "[--base-relative] [--lto-clang] in.map > out.S\n"); exit(1); } @@ -410,6 +412,65 @@ static int symbol_absolute(const struct sym_entry *s) return s->percpu_absolute; } +static char * s_name(char *buf) +{ + /* Skip the symbol type */ + return buf + 1; +} + +static void cleanup_symbol_name(char *s) +{ + char *p; + + if (!lto_clang) + return; + + /* + * ASCII[.] = 2e + * ASCII[0-9] = 30,39 + * ASCII[A-Z] = 41,5a + * ASCII[_] = 5f + * ASCII[a-z] = 61,7a + * + * As above, replacing '.' with '\0' does not affect the main sorting, + * but it helps us with subsorting. + */ + p = strchr(s, '.'); + if (p) + *p = '\0'; +} + +static int compare_names(const void *a, const void *b) +{ + int ret; + char sa_namebuf[KSYM_NAME_LEN]; + char sb_namebuf[KSYM_NAME_LEN]; + const struct sym_entry *sa = *(const struct sym_entry **)a; + const struct sym_entry *sb = *(const struct sym_entry **)b; + + expand_symbol(sa->sym, sa->len, sa_namebuf); + expand_symbol(sb->sym, sb->len, sb_namebuf); + cleanup_symbol_name(s_name(sa_namebuf)); + cleanup_symbol_name(s_name(sb_namebuf)); + ret = strcmp(s_name(sa_namebuf), s_name(sb_namebuf)); + if (!ret) { + if (sa->addr > sb->addr) + return 1; + else if (sa->addr < sb->addr) + return -1; + + /* keep old order */ + return (int)(sa->seq - sb->seq); + } + + return ret; +} + +static void sort_symbols_by_name(void) +{ + qsort(table, table_cnt, sizeof(table[0]), compare_names); +} + static void write_src(void) { unsigned int i, k, off; @@ -495,6 +556,7 @@ static void write_src(void) for (i = 0; i < table_cnt; i++) { if ((i & 0xFF) == 0) markers[i >> 8] = off; + table[i]->seq = i; /* There cannot be any symbol of length zero. */ if (table[i]->len == 0) { @@ -535,6 +597,15 @@ static void write_src(void) free(markers); + sort_symbols_by_name(); + output_label("kallsyms_seqs_of_names"); + for (i = 0; i < table_cnt; i++) + printf("\t.byte 0x%02x, 0x%02x, 0x%02x\n", + (unsigned char)(table[i]->seq >> 16), + (unsigned char)(table[i]->seq >> 8), + (unsigned char)(table[i]->seq >> 0)); + printf("\n"); + output_label("kallsyms_token_table"); off = 0; for (i = 0; i < 256; i++) { @@ -573,7 +644,7 @@ static void forget_symbol(const unsigned char *symbol, int len) } /* do the initial token count */ -static void build_initial_tok_table(void) +static void build_initial_token_table(void) { unsigned int i; @@ -698,7 +769,7 @@ static void insert_real_symbols_in_table(void) static void optimize_token_table(void) { - build_initial_tok_table(); + build_initial_token_table(); insert_real_symbols_in_table(); @@ -818,6 +889,7 @@ int main(int argc, char **argv) {"all-symbols", no_argument, &all_symbols, 1}, {"absolute-percpu", no_argument, &absolute_percpu, 1}, {"base-relative", no_argument, &base_relative, 1}, + {"lto-clang", no_argument, <o_clang, 1}, {}, }; diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 918470d768e9..32e573943cf0 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -156,6 +156,10 @@ kallsyms() kallsymopt="${kallsymopt} --base-relative" fi + if is_enabled CONFIG_LTO_CLANG; then + kallsymopt="${kallsymopt} --lto-clang" + fi + info KSYMS ${2} scripts/kallsyms ${kallsymopt} ${1} > ${2} } |