diff options
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/Kconfig.debug | 20 | ||||
| -rw-r--r-- | lib/Makefile | 3 | ||||
| -rw-r--r-- | lib/kunit/test.c | 8 | ||||
| -rw-r--r-- | lib/math/div64.c | 13 | ||||
| -rw-r--r-- | lib/math/gcd.c | 27 | ||||
| -rw-r--r-- | lib/raid6/algos.c | 3 | ||||
| -rw-r--r-- | lib/raid6/recov.c | 6 | ||||
| -rw-r--r-- | lib/raid6/recov_avx2.c | 6 | ||||
| -rw-r--r-- | lib/raid6/recov_avx512.c | 6 | ||||
| -rw-r--r-- | lib/raid6/recov_loongarch_simd.c | 12 | ||||
| -rw-r--r-- | lib/raid6/recov_neon.c | 6 | ||||
| -rw-r--r-- | lib/raid6/recov_rvv.c | 6 | ||||
| -rw-r--r-- | lib/raid6/recov_s390xc.c | 6 | ||||
| -rw-r--r-- | lib/raid6/recov_ssse3.c | 6 | ||||
| -rw-r--r-- | lib/stackdepot.c | 67 | ||||
| -rw-r--r-- | lib/sys_info.c | 122 | ||||
| -rw-r--r-- | lib/test_kho.c | 305 | ||||
| -rw-r--r-- | lib/xxhash.c | 107 |
18 files changed, 556 insertions, 173 deletions
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 53332a1d8af4..dc0e0c6ed075 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -3214,6 +3214,26 @@ config TEST_OBJPOOL If unsure, say N. +config TEST_KEXEC_HANDOVER + bool "Test for Kexec HandOver" + default n + depends on KEXEC_HANDOVER + help + This option enables test for Kexec HandOver (KHO). + The test consists of two parts: saving kernel data before kexec and + restoring the data after kexec and verifying that it was properly + handed over. This test module creates and saves data on the boot of + the first kernel and restores and verifies the data on the boot of + kexec'ed kernel. + + For detailed documentation about KHO, see Documentation/core-api/kho. + + To run the test run: + + tools/testing/selftests/kho/vmtest.sh -h + + If unsure, say N. + config RATELIMIT_KUNIT_TEST tristate "KUnit Test for correctness and stress of ratelimit" if !KUNIT_ALL_TESTS depends on KUNIT diff --git a/lib/Makefile b/lib/Makefile index 06b954473222..392ff808c9b9 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -40,7 +40,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ earlycpio.o seq_buf.o siphash.o dec_and_lock.o \ nmi_backtrace.o win_minmax.o memcat_p.o \ - buildid.o objpool.o iomem_copy.o + buildid.o objpool.o iomem_copy.o sys_info.o lib-$(CONFIG_UNION_FIND) += union_find.o lib-$(CONFIG_PRINTK) += dump_stack.o @@ -102,6 +102,7 @@ obj-$(CONFIG_TEST_HMM) += test_hmm.o obj-$(CONFIG_TEST_FREE_PAGES) += test_free_pages.o obj-$(CONFIG_TEST_REF_TRACKER) += test_ref_tracker.o obj-$(CONFIG_TEST_OBJPOOL) += test_objpool.o +obj-$(CONFIG_TEST_KEXEC_HANDOVER) += test_kho.o obj-$(CONFIG_TEST_FPU) += test_fpu.o test_fpu-y := test_fpu_glue.o test_fpu_impl.o diff --git a/lib/kunit/test.c b/lib/kunit/test.c index f3c6b11f12b8..d2bfa331a2b1 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -802,7 +802,6 @@ void __kunit_test_suites_exit(struct kunit_suite **suites, int num_suites) } EXPORT_SYMBOL_GPL(__kunit_test_suites_exit); -#ifdef CONFIG_MODULES static void kunit_module_init(struct module *mod) { struct kunit_suite_set suite_set, filtered_set; @@ -890,7 +889,6 @@ static struct notifier_block kunit_mod_nb = { .notifier_call = kunit_module_notify, .priority = 0, }; -#endif KUNIT_DEFINE_ACTION_WRAPPER(kfree_action_wrapper, kfree, const void *) @@ -981,20 +979,14 @@ static int __init kunit_init(void) kunit_debugfs_init(); kunit_bus_init(); -#ifdef CONFIG_MODULES return register_module_notifier(&kunit_mod_nb); -#else - return 0; -#endif } late_initcall(kunit_init); static void __exit kunit_exit(void) { memset(&kunit_hooks, 0, sizeof(kunit_hooks)); -#ifdef CONFIG_MODULES unregister_module_notifier(&kunit_mod_nb); -#endif kunit_bus_shutdown(); diff --git a/lib/math/div64.c b/lib/math/div64.c index 5faa29208bdb..bf77b9843175 100644 --- a/lib/math/div64.c +++ b/lib/math/div64.c @@ -212,12 +212,13 @@ u64 mul_u64_u64_div_u64(u64 a, u64 b, u64 c) #endif - /* make sure c is not zero, trigger exception otherwise */ -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wdiv-by-zero" - if (unlikely(c == 0)) - return 1/0; -#pragma GCC diagnostic pop + /* make sure c is not zero, trigger runtime exception otherwise */ + if (unlikely(c == 0)) { + unsigned long zero = 0; + + OPTIMIZER_HIDE_VAR(zero); + return ~0UL/zero; + } int shift = __builtin_ctzll(c); diff --git a/lib/math/gcd.c b/lib/math/gcd.c index e3b042214d1b..62efca6787ae 100644 --- a/lib/math/gcd.c +++ b/lib/math/gcd.c @@ -11,22 +11,16 @@ * has decent hardware division. */ +DEFINE_STATIC_KEY_TRUE(efficient_ffs_key); + #if !defined(CONFIG_CPU_NO_EFFICIENT_FFS) /* If __ffs is available, the even/odd algorithm benchmarks slower. */ -/** - * gcd - calculate and return the greatest common divisor of 2 unsigned longs - * @a: first value - * @b: second value - */ -unsigned long gcd(unsigned long a, unsigned long b) +static unsigned long binary_gcd(unsigned long a, unsigned long b) { unsigned long r = a | b; - if (!a || !b) - return r; - b >>= __ffs(b); if (b == 1) return r & -r; @@ -44,9 +38,15 @@ unsigned long gcd(unsigned long a, unsigned long b) } } -#else +#endif /* If normalization is done by loops, the even/odd algorithm is a win. */ + +/** + * gcd - calculate and return the greatest common divisor of 2 unsigned longs + * @a: first value + * @b: second value + */ unsigned long gcd(unsigned long a, unsigned long b) { unsigned long r = a | b; @@ -54,6 +54,11 @@ unsigned long gcd(unsigned long a, unsigned long b) if (!a || !b) return r; +#if !defined(CONFIG_CPU_NO_EFFICIENT_FFS) + if (static_branch_likely(&efficient_ffs_key)) + return binary_gcd(a, b); +#endif + /* Isolate lsbit of r */ r &= -r; @@ -80,6 +85,4 @@ unsigned long gcd(unsigned long a, unsigned long b) } } -#endif - EXPORT_SYMBOL_GPL(gcd); diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c index 75ce3e134b7c..799e0e5eac26 100644 --- a/lib/raid6/algos.c +++ b/lib/raid6/algos.c @@ -18,9 +18,6 @@ #else #include <linux/module.h> #include <linux/gfp.h> -/* In .bss so it's zeroed */ -const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256))); -EXPORT_SYMBOL(raid6_empty_zero_page); #endif struct raid6_calls raid6_call; diff --git a/lib/raid6/recov.c b/lib/raid6/recov.c index a7c1b2bbe40d..b5e47c008b41 100644 --- a/lib/raid6/recov.c +++ b/lib/raid6/recov.c @@ -31,10 +31,10 @@ static void raid6_2data_recov_intx1(int disks, size_t bytes, int faila, Use the dead data pages as temporary storage for delta p and delta q */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -72,7 +72,7 @@ static void raid6_datap_recov_intx1(int disks, size_t bytes, int faila, /* Compute syndrome with zero for the missing data page Use the dead data page as temporary storage for delta q */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); diff --git a/lib/raid6/recov_avx2.c b/lib/raid6/recov_avx2.c index 4e8095403ee2..97d598d2535c 100644 --- a/lib/raid6/recov_avx2.c +++ b/lib/raid6/recov_avx2.c @@ -28,10 +28,10 @@ static void raid6_2data_recov_avx2(int disks, size_t bytes, int faila, Use the dead data pages as temporary storage for delta p and delta q */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -196,7 +196,7 @@ static void raid6_datap_recov_avx2(int disks, size_t bytes, int faila, /* Compute syndrome with zero for the missing data page Use the dead data page as temporary storage for delta q */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); diff --git a/lib/raid6/recov_avx512.c b/lib/raid6/recov_avx512.c index 310c715db313..7986120ca444 100644 --- a/lib/raid6/recov_avx512.c +++ b/lib/raid6/recov_avx512.c @@ -37,10 +37,10 @@ static void raid6_2data_recov_avx512(int disks, size_t bytes, int faila, */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -238,7 +238,7 @@ static void raid6_datap_recov_avx512(int disks, size_t bytes, int faila, */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); diff --git a/lib/raid6/recov_loongarch_simd.c b/lib/raid6/recov_loongarch_simd.c index 94aeac85e6f7..93dc515997a1 100644 --- a/lib/raid6/recov_loongarch_simd.c +++ b/lib/raid6/recov_loongarch_simd.c @@ -42,10 +42,10 @@ static void raid6_2data_recov_lsx(int disks, size_t bytes, int faila, * delta p and delta q */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks - 2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks - 1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -197,7 +197,7 @@ static void raid6_datap_recov_lsx(int disks, size_t bytes, int faila, * Use the dead data page as temporary storage for delta q */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks - 1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -316,10 +316,10 @@ static void raid6_2data_recov_lasx(int disks, size_t bytes, int faila, * delta p and delta q */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks - 2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks - 1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -436,7 +436,7 @@ static void raid6_datap_recov_lasx(int disks, size_t bytes, int faila, * Use the dead data page as temporary storage for delta q */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks - 1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); diff --git a/lib/raid6/recov_neon.c b/lib/raid6/recov_neon.c index 1bfc14174d4d..70e1404c1512 100644 --- a/lib/raid6/recov_neon.c +++ b/lib/raid6/recov_neon.c @@ -36,10 +36,10 @@ static void raid6_2data_recov_neon(int disks, size_t bytes, int faila, * delta p and delta q */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks - 2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks - 1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -74,7 +74,7 @@ static void raid6_datap_recov_neon(int disks, size_t bytes, int faila, * Use the dead data page as temporary storage for delta q */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks - 1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); diff --git a/lib/raid6/recov_rvv.c b/lib/raid6/recov_rvv.c index f29303795ccf..5d54c4b437df 100644 --- a/lib/raid6/recov_rvv.c +++ b/lib/raid6/recov_rvv.c @@ -165,10 +165,10 @@ static void raid6_2data_recov_rvv(int disks, size_t bytes, int faila, * delta p and delta q */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks - 2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks - 1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -203,7 +203,7 @@ static void raid6_datap_recov_rvv(int disks, size_t bytes, int faila, * Use the dead data page as temporary storage for delta q */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks - 1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); diff --git a/lib/raid6/recov_s390xc.c b/lib/raid6/recov_s390xc.c index 4a7aa466f0ef..487018f81192 100644 --- a/lib/raid6/recov_s390xc.c +++ b/lib/raid6/recov_s390xc.c @@ -34,10 +34,10 @@ static void raid6_2data_recov_s390xc(int disks, size_t bytes, int faila, Use the dead data pages as temporary storage for delta p and delta q */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -81,7 +81,7 @@ static void raid6_datap_recov_s390xc(int disks, size_t bytes, int faila, /* Compute syndrome with zero for the missing data page Use the dead data page as temporary storage for delta q */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); diff --git a/lib/raid6/recov_ssse3.c b/lib/raid6/recov_ssse3.c index 4bfa3c6b60de..2e849185c32b 100644 --- a/lib/raid6/recov_ssse3.c +++ b/lib/raid6/recov_ssse3.c @@ -30,10 +30,10 @@ static void raid6_2data_recov_ssse3(int disks, size_t bytes, int faila, Use the dead data pages as temporary storage for delta p and delta q */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -203,7 +203,7 @@ static void raid6_datap_recov_ssse3(int disks, size_t bytes, int faila, /* Compute syndrome with zero for the missing data page Use the dead data page as temporary storage for delta q */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 73d7b50924ef..de0b0025af2b 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -36,11 +36,11 @@ #include <linux/memblock.h> #include <linux/kasan-enabled.h> -#define DEPOT_POOLS_CAP 8192 -/* The pool_index is offset by 1 so the first record does not have a 0 handle. */ -#define DEPOT_MAX_POOLS \ - (((1LL << (DEPOT_POOL_INDEX_BITS)) - 1 < DEPOT_POOLS_CAP) ? \ - (1LL << (DEPOT_POOL_INDEX_BITS)) - 1 : DEPOT_POOLS_CAP) +/* + * The pool_index is offset by 1 so the first record does not have a 0 handle. + */ +static unsigned int stack_max_pools __read_mostly = + MIN((1LL << DEPOT_POOL_INDEX_BITS) - 1, 8192); static bool stack_depot_disabled; static bool __stack_depot_early_init_requested __initdata = IS_ENABLED(CONFIG_STACKDEPOT_ALWAYS_INIT); @@ -62,7 +62,7 @@ static unsigned int stack_bucket_number_order; static unsigned int stack_hash_mask; /* Array of memory regions that store stack records. */ -static void *stack_pools[DEPOT_MAX_POOLS]; +static void **stack_pools; /* Newly allocated pool that is not yet added to stack_pools. */ static void *new_pool; /* Number of pools in stack_pools. */ @@ -101,6 +101,34 @@ static int __init disable_stack_depot(char *str) } early_param("stack_depot_disable", disable_stack_depot); +static int __init parse_max_pools(char *str) +{ + const long long limit = (1LL << (DEPOT_POOL_INDEX_BITS)) - 1; + unsigned int max_pools; + int rv; + + rv = kstrtouint(str, 0, &max_pools); + if (rv) + return rv; + + if (max_pools < 1024) { + pr_err("stack_depot_max_pools below 1024, using default of %u\n", + stack_max_pools); + goto out; + } + + if (max_pools > limit) { + pr_err("stack_depot_max_pools exceeds %lld, using default of %u\n", + limit, stack_max_pools); + goto out; + } + + stack_max_pools = max_pools; +out: + return 0; +} +early_param("stack_depot_max_pools", parse_max_pools); + void __init stack_depot_request_early_init(void) { /* Too late to request early init now. */ @@ -182,6 +210,17 @@ int __init stack_depot_early_init(void) } init_stack_table(entries); + pr_info("allocating space for %u stack pools via memblock\n", + stack_max_pools); + stack_pools = + memblock_alloc(stack_max_pools * sizeof(void *), PAGE_SIZE); + if (!stack_pools) { + pr_err("stack pools allocation failed, disabling\n"); + memblock_free(stack_table, entries * sizeof(struct list_head)); + stack_depot_disabled = true; + return -ENOMEM; + } + return 0; } @@ -231,6 +270,16 @@ int stack_depot_init(void) stack_hash_mask = entries - 1; init_stack_table(entries); + pr_info("allocating space for %u stack pools via kvcalloc\n", + stack_max_pools); + stack_pools = kvcalloc(stack_max_pools, sizeof(void *), GFP_KERNEL); + if (!stack_pools) { + pr_err("stack pools allocation failed, disabling\n"); + kvfree(stack_table); + stack_depot_disabled = true; + ret = -ENOMEM; + } + out_unlock: mutex_unlock(&stack_depot_init_mutex); @@ -245,9 +294,9 @@ static bool depot_init_pool(void **prealloc) { lockdep_assert_held(&pool_lock); - if (unlikely(pools_num >= DEPOT_MAX_POOLS)) { + if (unlikely(pools_num >= stack_max_pools)) { /* Bail out if we reached the pool limit. */ - WARN_ON_ONCE(pools_num > DEPOT_MAX_POOLS); /* should never happen */ + WARN_ON_ONCE(pools_num > stack_max_pools); /* should never happen */ WARN_ON_ONCE(!new_pool); /* to avoid unnecessary pre-allocation */ WARN_ONCE(1, "Stack depot reached limit capacity"); return false; @@ -273,7 +322,7 @@ static bool depot_init_pool(void **prealloc) * NULL; do not reset to NULL if we have reached the maximum number of * pools. */ - if (pools_num < DEPOT_MAX_POOLS) + if (pools_num < stack_max_pools) WRITE_ONCE(new_pool, NULL); else WRITE_ONCE(new_pool, STACK_DEPOT_POISON); diff --git a/lib/sys_info.c b/lib/sys_info.c new file mode 100644 index 000000000000..5bf503fd7ec1 --- /dev/null +++ b/lib/sys_info.c @@ -0,0 +1,122 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/sched/debug.h> +#include <linux/console.h> +#include <linux/kernel.h> +#include <linux/ftrace.h> +#include <linux/sysctl.h> +#include <linux/nmi.h> + +#include <linux/sys_info.h> + +struct sys_info_name { + unsigned long bit; + const char *name; +}; + +/* + * When 'si_names' gets updated, please make sure the 'sys_info_avail' + * below is updated accordingly. + */ +static const struct sys_info_name si_names[] = { + { SYS_INFO_TASKS, "tasks" }, + { SYS_INFO_MEM, "mem" }, + { SYS_INFO_TIMERS, "timers" }, + { SYS_INFO_LOCKS, "locks" }, + { SYS_INFO_FTRACE, "ftrace" }, + { SYS_INFO_ALL_CPU_BT, "all_bt" }, + { SYS_INFO_BLOCKED_TASKS, "blocked_tasks" }, +}; + +/* Expecting string like "xxx_sys_info=tasks,mem,timers,locks,ftrace,..." */ +unsigned long sys_info_parse_param(char *str) +{ + unsigned long si_bits = 0; + char *s, *name; + int i; + + s = str; + while ((name = strsep(&s, ",")) && *name) { + for (i = 0; i < ARRAY_SIZE(si_names); i++) { + if (!strcmp(name, si_names[i].name)) { + si_bits |= si_names[i].bit; + break; + } + } + } + + return si_bits; +} + +#ifdef CONFIG_SYSCTL + +static const char sys_info_avail[] __maybe_unused = "tasks,mem,timers,locks,ftrace,all_bt,blocked_tasks"; + +int sysctl_sys_info_handler(const struct ctl_table *ro_table, int write, + void *buffer, size_t *lenp, + loff_t *ppos) +{ + char names[sizeof(sys_info_avail) + 1]; + struct ctl_table table; + unsigned long *si_bits_global; + + si_bits_global = ro_table->data; + + if (write) { + unsigned long si_bits; + int ret; + + table = *ro_table; + table.data = names; + table.maxlen = sizeof(names); + ret = proc_dostring(&table, write, buffer, lenp, ppos); + if (ret) + return ret; + + si_bits = sys_info_parse_param(names); + /* The access to the global value is not synchronized. */ + WRITE_ONCE(*si_bits_global, si_bits); + return 0; + } else { + /* for 'read' operation */ + char *delim = ""; + int i, len = 0; + + for (i = 0; i < ARRAY_SIZE(si_names); i++) { + if (*si_bits_global & si_names[i].bit) { + len += scnprintf(names + len, sizeof(names) - len, + "%s%s", delim, si_names[i].name); + delim = ","; + } + } + + table = *ro_table; + table.data = names; + table.maxlen = sizeof(names); + return proc_dostring(&table, write, buffer, lenp, ppos); + } +} +#endif + +void sys_info(unsigned long si_mask) +{ + if (si_mask & SYS_INFO_TASKS) + show_state(); + + if (si_mask & SYS_INFO_MEM) + show_mem(); + + if (si_mask & SYS_INFO_TIMERS) + sysrq_timer_list_show(); + + if (si_mask & SYS_INFO_LOCKS) + debug_show_all_locks(); + + if (si_mask & SYS_INFO_FTRACE) + ftrace_dump(DUMP_ALL); + + if (si_mask & SYS_INFO_ALL_CPU_BT) + trigger_all_cpu_backtrace(); + + if (si_mask & SYS_INFO_BLOCKED_TASKS) + show_state_filter(TASK_UNINTERRUPTIBLE); +} diff --git a/lib/test_kho.c b/lib/test_kho.c new file mode 100644 index 000000000000..c2eb899c3b45 --- /dev/null +++ b/lib/test_kho.c @@ -0,0 +1,305 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Test module for KHO + * Copyright (c) 2025 Microsoft Corporation. + * + * Authors: + * Saurabh Sengar <ssengar@microsoft.com> + * Mike Rapoport <rppt@kernel.org> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/mm.h> +#include <linux/gfp.h> +#include <linux/slab.h> +#include <linux/kexec.h> +#include <linux/libfdt.h> +#include <linux/module.h> +#include <linux/printk.h> +#include <linux/vmalloc.h> +#include <linux/kexec_handover.h> + +#include <net/checksum.h> + +#define KHO_TEST_MAGIC 0x4b484f21 /* KHO! */ +#define KHO_TEST_FDT "kho_test" +#define KHO_TEST_COMPAT "kho-test-v1" + +static long max_mem = (PAGE_SIZE << MAX_PAGE_ORDER) * 2; +module_param(max_mem, long, 0644); + +struct kho_test_state { + unsigned int nr_folios; + struct folio **folios; + struct folio *fdt; + __wsum csum; +}; + +static struct kho_test_state kho_test_state; + +static int kho_test_notifier(struct notifier_block *self, unsigned long cmd, + void *v) +{ + struct kho_test_state *state = &kho_test_state; + struct kho_serialization *ser = v; + int err = 0; + + switch (cmd) { + case KEXEC_KHO_ABORT: + return NOTIFY_DONE; + case KEXEC_KHO_FINALIZE: + /* Handled below */ + break; + default: + return NOTIFY_BAD; + } + + err |= kho_preserve_folio(state->fdt); + err |= kho_add_subtree(ser, KHO_TEST_FDT, folio_address(state->fdt)); + + return err ? NOTIFY_BAD : NOTIFY_DONE; +} + +static struct notifier_block kho_test_nb = { + .notifier_call = kho_test_notifier, +}; + +static int kho_test_save_data(struct kho_test_state *state, void *fdt) +{ + phys_addr_t *folios_info __free(kvfree) = NULL; + int err = 0; + + folios_info = kvmalloc_array(state->nr_folios, sizeof(*folios_info), + GFP_KERNEL); + if (!folios_info) + return -ENOMEM; + + for (int i = 0; i < state->nr_folios; i++) { + struct folio *folio = state->folios[i]; + unsigned int order = folio_order(folio); + + folios_info[i] = virt_to_phys(folio_address(folio)) | order; + + err = kho_preserve_folio(folio); + if (err) + return err; + } + + err |= fdt_begin_node(fdt, "data"); + err |= fdt_property(fdt, "nr_folios", &state->nr_folios, + sizeof(state->nr_folios)); + err |= fdt_property(fdt, "folios_info", folios_info, + state->nr_folios * sizeof(*folios_info)); + err |= fdt_property(fdt, "csum", &state->csum, sizeof(state->csum)); + err |= fdt_end_node(fdt); + + return err; +} + +static int kho_test_prepare_fdt(struct kho_test_state *state) +{ + const char compatible[] = KHO_TEST_COMPAT; + unsigned int magic = KHO_TEST_MAGIC; + ssize_t fdt_size; + int err = 0; + void *fdt; + + fdt_size = state->nr_folios * sizeof(phys_addr_t) + PAGE_SIZE; + state->fdt = folio_alloc(GFP_KERNEL, get_order(fdt_size)); + if (!state->fdt) + return -ENOMEM; + + fdt = folio_address(state->fdt); + + err |= fdt_create(fdt, fdt_size); + err |= fdt_finish_reservemap(fdt); + + err |= fdt_begin_node(fdt, ""); + err |= fdt_property(fdt, "compatible", compatible, sizeof(compatible)); + err |= fdt_property(fdt, "magic", &magic, sizeof(magic)); + err |= kho_test_save_data(state, fdt); + err |= fdt_end_node(fdt); + + err |= fdt_finish(fdt); + + if (err) + folio_put(state->fdt); + + return err; +} + +static int kho_test_generate_data(struct kho_test_state *state) +{ + size_t alloc_size = 0; + __wsum csum = 0; + + while (alloc_size < max_mem) { + int order = get_random_u32() % NR_PAGE_ORDERS; + struct folio *folio; + unsigned int size; + void *addr; + + /* cap allocation so that we won't exceed max_mem */ + if (alloc_size + (PAGE_SIZE << order) > max_mem) { + order = get_order(max_mem - alloc_size); + if (order) + order--; + } + size = PAGE_SIZE << order; + + folio = folio_alloc(GFP_KERNEL | __GFP_NORETRY, order); + if (!folio) + goto err_free_folios; + + state->folios[state->nr_folios++] = folio; + addr = folio_address(folio); + get_random_bytes(addr, size); + csum = csum_partial(addr, size, csum); + alloc_size += size; + } + + state->csum = csum; + return 0; + +err_free_folios: + for (int i = 0; i < state->nr_folios; i++) + folio_put(state->folios[i]); + return -ENOMEM; +} + +static int kho_test_save(void) +{ + struct kho_test_state *state = &kho_test_state; + struct folio **folios __free(kvfree) = NULL; + unsigned long max_nr; + int err; + + max_mem = PAGE_ALIGN(max_mem); + max_nr = max_mem >> PAGE_SHIFT; + + folios = kvmalloc_array(max_nr, sizeof(*state->folios), GFP_KERNEL); + if (!folios) + return -ENOMEM; + state->folios = folios; + + err = kho_test_generate_data(state); + if (err) + return err; + + err = kho_test_prepare_fdt(state); + if (err) + return err; + + return register_kho_notifier(&kho_test_nb); +} + +static int kho_test_restore_data(const void *fdt, int node) +{ + const unsigned int *nr_folios; + const phys_addr_t *folios_info; + const __wsum *old_csum; + __wsum csum = 0; + int len; + + node = fdt_path_offset(fdt, "/data"); + + nr_folios = fdt_getprop(fdt, node, "nr_folios", &len); + if (!nr_folios || len != sizeof(*nr_folios)) + return -EINVAL; + + old_csum = fdt_getprop(fdt, node, "csum", &len); + if (!old_csum || len != sizeof(*old_csum)) + return -EINVAL; + + folios_info = fdt_getprop(fdt, node, "folios_info", &len); + if (!folios_info || len != sizeof(*folios_info) * *nr_folios) + return -EINVAL; + + for (int i = 0; i < *nr_folios; i++) { + unsigned int order = folios_info[i] & ~PAGE_MASK; + phys_addr_t phys = folios_info[i] & PAGE_MASK; + unsigned int size = PAGE_SIZE << order; + struct folio *folio; + + folio = kho_restore_folio(phys); + if (!folio) + break; + + if (folio_order(folio) != order) + break; + + csum = csum_partial(folio_address(folio), size, csum); + folio_put(folio); + } + + if (csum != *old_csum) + return -EINVAL; + + return 0; +} + +static int kho_test_restore(phys_addr_t fdt_phys) +{ + void *fdt = phys_to_virt(fdt_phys); + const unsigned int *magic; + int node, len, err; + + node = fdt_path_offset(fdt, "/"); + if (node < 0) + return -EINVAL; + + if (fdt_node_check_compatible(fdt, node, KHO_TEST_COMPAT)) + return -EINVAL; + + magic = fdt_getprop(fdt, node, "magic", &len); + if (!magic || len != sizeof(*magic)) + return -EINVAL; + + if (*magic != KHO_TEST_MAGIC) + return -EINVAL; + + err = kho_test_restore_data(fdt, node); + if (err) + return err; + + pr_info("KHO restore succeeded\n"); + return 0; +} + +static int __init kho_test_init(void) +{ + phys_addr_t fdt_phys; + int err; + + err = kho_retrieve_subtree(KHO_TEST_FDT, &fdt_phys); + if (!err) + return kho_test_restore(fdt_phys); + + if (err != -ENOENT) { + pr_warn("failed to retrieve %s FDT: %d\n", KHO_TEST_FDT, err); + return err; + } + + return kho_test_save(); +} +module_init(kho_test_init); + +static void kho_test_cleanup(void) +{ + for (int i = 0; i < kho_test_state.nr_folios; i++) + folio_put(kho_test_state.folios[i]); + + kvfree(kho_test_state.folios); +} + +static void __exit kho_test_exit(void) +{ + unregister_kho_notifier(&kho_test_nb); + kho_test_cleanup(); +} +module_exit(kho_test_exit); + +MODULE_AUTHOR("Mike Rapoport <rppt@kernel.org>"); +MODULE_DESCRIPTION("KHO test module"); +MODULE_LICENSE("GPL"); diff --git a/lib/xxhash.c b/lib/xxhash.c index b5bd567aa6b3..cf629766f376 100644 --- a/lib/xxhash.c +++ b/lib/xxhash.c @@ -267,113 +267,6 @@ void xxh64_reset(struct xxh64_state *statePtr, const uint64_t seed) } EXPORT_SYMBOL(xxh64_reset); -int xxh32_update(struct xxh32_state *state, const void *input, const size_t len) -{ - const uint8_t *p = (const uint8_t *)input; - const uint8_t *const b_end = p + len; - - if (input == NULL) - return -EINVAL; - - state->total_len_32 += (uint32_t)len; - state->large_len |= (len >= 16) | (state->total_len_32 >= 16); - - if (state->memsize + len < 16) { /* fill in tmp buffer */ - memcpy((uint8_t *)(state->mem32) + state->memsize, input, len); - state->memsize += (uint32_t)len; - return 0; - } - - if (state->memsize) { /* some data left from previous update */ - const uint32_t *p32 = state->mem32; - - memcpy((uint8_t *)(state->mem32) + state->memsize, input, - 16 - state->memsize); - - state->v1 = xxh32_round(state->v1, get_unaligned_le32(p32)); - p32++; - state->v2 = xxh32_round(state->v2, get_unaligned_le32(p32)); - p32++; - state->v3 = xxh32_round(state->v3, get_unaligned_le32(p32)); - p32++; - state->v4 = xxh32_round(state->v4, get_unaligned_le32(p32)); - p32++; - - p += 16-state->memsize; - state->memsize = 0; - } - - if (p <= b_end - 16) { - const uint8_t *const limit = b_end - 16; - uint32_t v1 = state->v1; - uint32_t v2 = state->v2; - uint32_t v3 = state->v3; - uint32_t v4 = state->v4; - - do { - v1 = xxh32_round(v1, get_unaligned_le32(p)); - p += 4; - v2 = xxh32_round(v2, get_unaligned_le32(p)); - p += 4; - v3 = xxh32_round(v3, get_unaligned_le32(p)); - p += 4; - v4 = xxh32_round(v4, get_unaligned_le32(p)); - p += 4; - } while (p <= limit); - - state->v1 = v1; - state->v2 = v2; - state->v3 = v3; - state->v4 = v4; - } - - if (p < b_end) { - memcpy(state->mem32, p, (size_t)(b_end-p)); - state->memsize = (uint32_t)(b_end-p); - } - - return 0; -} -EXPORT_SYMBOL(xxh32_update); - -uint32_t xxh32_digest(const struct xxh32_state *state) -{ - const uint8_t *p = (const uint8_t *)state->mem32; - const uint8_t *const b_end = (const uint8_t *)(state->mem32) + - state->memsize; - uint32_t h32; - - if (state->large_len) { - h32 = xxh_rotl32(state->v1, 1) + xxh_rotl32(state->v2, 7) + - xxh_rotl32(state->v3, 12) + xxh_rotl32(state->v4, 18); - } else { - h32 = state->v3 /* == seed */ + PRIME32_5; - } - - h32 += state->total_len_32; - - while (p + 4 <= b_end) { - h32 += get_unaligned_le32(p) * PRIME32_3; - h32 = xxh_rotl32(h32, 17) * PRIME32_4; - p += 4; - } - - while (p < b_end) { - h32 += (*p) * PRIME32_5; - h32 = xxh_rotl32(h32, 11) * PRIME32_1; - p++; - } - - h32 ^= h32 >> 15; - h32 *= PRIME32_2; - h32 ^= h32 >> 13; - h32 *= PRIME32_3; - h32 ^= h32 >> 16; - - return h32; -} -EXPORT_SYMBOL(xxh32_digest); - int xxh64_update(struct xxh64_state *state, const void *input, const size_t len) { const uint8_t *p = (const uint8_t *)input; |