diff options
Diffstat (limited to 'lib')
41 files changed, 2540 insertions, 251 deletions
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 6f543a4bc704..e718487c97c3 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -222,7 +222,6 @@ config ENABLE_MUST_CHECK config FRAME_WARN int "Warn for stack frames larger than (needs gcc 4.4)" range 0 8192 - default 3072 if KASAN_EXTRA default 2048 if GCC_PLUGIN_LATENT_ENTROPY default 1280 if (!64BIT && PARISC) default 1024 if (!64BIT && !PARISC) @@ -266,23 +265,6 @@ config UNUSED_SYMBOLS you really need it, and what the merge plan to the mainline kernel for your module is. -config PAGE_OWNER - bool "Track page owner" - depends on DEBUG_KERNEL && STACKTRACE_SUPPORT - select DEBUG_FS - select STACKTRACE - select STACKDEPOT - select PAGE_EXTENSION - help - This keeps track of what call chain is the owner of a page, may - help to find bare alloc_page(s) leaks. Even if you include this - feature on your build, it is disabled in default. You should pass - "page_owner=on" to boot parameter in order to enable it. Eats - a fair amount of memory if enabled. See tools/vm/page_owner_sort.c - for user-space helper. - - If unsure, say N. - config DEBUG_FS bool "Debug Filesystem" help @@ -1700,7 +1682,6 @@ if RUNTIME_TESTING_MENU config LKDTM tristate "Linux Kernel Dump Test Tool Module" depends on DEBUG_FS - depends on BLOCK help This module enables testing of the different dumping mechanisms by inducing system failures at predefined crash points. @@ -1876,6 +1857,19 @@ config TEST_LKM If unsure, say N. +config TEST_VMALLOC + tristate "Test module for stress/performance analysis of vmalloc allocator" + default n + depends on MMU + depends on m + help + This builds the "test_vmalloc" module that should be used for + stress and performance analysis. So, any new change for vmalloc + subsystem can be evaluated from performance and stability point + of view. + + If unsure, say N. + config TEST_USER_COPY tristate "Test user/kernel boundary protections" depends on m @@ -1991,6 +1985,28 @@ config TEST_MEMCAT_P If unsure, say N. +config TEST_LIVEPATCH + tristate "Test livepatching" + default n + depends on DYNAMIC_DEBUG + depends on LIVEPATCH + depends on m + help + Test kernel livepatching features for correctness. The tests will + load test modules that will be livepatched in various scenarios. + + To run all the livepatching tests: + + make -C tools/testing/selftests TARGETS=livepatch run_tests + + Alternatively, individual tests may be invoked: + + tools/testing/selftests/livepatch/test-callbacks.sh + tools/testing/selftests/livepatch/test-livepatch.sh + tools/testing/selftests/livepatch/test-shadow-vars.sh + + If unsure, say N. + config TEST_OBJAGG tristate "Perform selftest on object aggreration manager" default n @@ -1999,7 +2015,6 @@ config TEST_OBJAGG Enable this option to test object aggregation manager on boot (or module load). - If unsure, say N. config TEST_STACKINIT tristate "Test level of stack variable initialization" diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index d8c474b6691e..9950b660e62d 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -78,16 +78,6 @@ config KASAN_SW_TAGS endchoice -config KASAN_EXTRA - bool "KASAN: extra checks" - depends on KASAN_GENERIC && DEBUG_KERNEL && !COMPILE_TEST - help - This enables further checks in generic KASAN, for now it only - includes the address-use-after-scope check that can lead to - excessive kernel stack usage, frame size warnings and longer - compile time. - See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 - choice prompt "Instrumentation type" depends on KASAN @@ -113,6 +103,28 @@ config KASAN_INLINE endchoice +config KASAN_STACK_ENABLE + bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST + default !(CLANG_VERSION < 90000) + depends on KASAN + help + The LLVM stack address sanitizer has a know problem that + causes excessive stack usage in a lot of functions, see + https://bugs.llvm.org/show_bug.cgi?id=38809 + Disabling asan-stack makes it safe to run kernels build + with clang-8 with KASAN enabled, though it loses some of + the functionality. + This feature is always disabled when compile-testing with clang-8 + or earlier to avoid cluttering the output in stack overflow + warnings, but clang-8 users can still enable it for builds without + CONFIG_COMPILE_TEST. On gcc and later clang versions it is + assumed to always be safe to use and enabled by default. + +config KASAN_STACK + int + default 1 if KASAN_STACK_ENABLE || CC_IS_GCC + default 0 + config KASAN_S390_4_LEVEL_PAGING bool "KASan: use 4-level paging" depends on KASAN && S390 diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index 98fa559ebd80..a2ae4a8e4fa6 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -27,15 +27,19 @@ config UBSAN_SANITIZE_ALL Enabling this option will get kernel image size increased significantly. -config UBSAN_ALIGNMENT - bool "Enable checking of pointers alignment" +config UBSAN_NO_ALIGNMENT + bool "Disable checking of pointers alignment" depends on UBSAN - default y if !HAVE_EFFICIENT_UNALIGNED_ACCESS + default y if HAVE_EFFICIENT_UNALIGNED_ACCESS help - This option enables detection of unaligned memory accesses. - Enabling this option on architectures that support unaligned + This option disables the check of unaligned memory accesses. + This option should be used when building allmodconfig. + Disabling this option on architectures that support unaligned accesses may produce a lot of false positives. +config UBSAN_ALIGNMENT + def_bool !UBSAN_NO_ALIGNMENT + config TEST_UBSAN tristate "Module for testing for undefined behavior detection" depends on m && UBSAN diff --git a/lib/Makefile b/lib/Makefile index c81a66d4d00d..647517940b29 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -60,6 +60,7 @@ UBSAN_SANITIZE_test_ubsan.o := y obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o obj-$(CONFIG_TEST_LIST_SORT) += test_list_sort.o obj-$(CONFIG_TEST_LKM) += test_module.o +obj-$(CONFIG_TEST_VMALLOC) += test_vmalloc.o obj-$(CONFIG_TEST_OVERFLOW) += test_overflow.o obj-$(CONFIG_TEST_RHASHTABLE) += test_rhashtable.o obj-$(CONFIG_TEST_SORT) += test_sort.o @@ -78,6 +79,8 @@ obj-$(CONFIG_TEST_MEMCAT_P) += test_memcat_p.o obj-$(CONFIG_TEST_OBJAGG) += test_objagg.o obj-$(CONFIG_TEST_STACKINIT) += test_stackinit.o +obj-$(CONFIG_TEST_LIVEPATCH) += livepatch/ + ifeq ($(CONFIG_DEBUG_KOBJECT),y) CFLAGS_kobject.o += -DDEBUG CFLAGS_kobject_uevent.o += -DDEBUG diff --git a/lib/assoc_array.c b/lib/assoc_array.c index c6659cb37033..edc3c14af41d 100644 --- a/lib/assoc_array.c +++ b/lib/assoc_array.c @@ -768,9 +768,11 @@ all_leaves_cluster_together: new_s0->index_key[i] = ops->get_key_chunk(index_key, i * ASSOC_ARRAY_KEY_CHUNK_SIZE); - blank = ULONG_MAX << (level & ASSOC_ARRAY_KEY_CHUNK_MASK); - pr_devel("blank off [%zu] %d: %lx\n", keylen - 1, level, blank); - new_s0->index_key[keylen - 1] &= ~blank; + if (level & ASSOC_ARRAY_KEY_CHUNK_MASK) { + blank = ULONG_MAX << (level & ASSOC_ARRAY_KEY_CHUNK_MASK); + pr_devel("blank off [%zu] %d: %lx\n", keylen - 1, level, blank); + new_s0->index_key[keylen - 1] &= ~blank; + } /* This now reduces to a node splitting exercise for which we'll need * to regenerate the disparity table. @@ -1115,6 +1117,7 @@ struct assoc_array_edit *assoc_array_delete(struct assoc_array *array, index_key)) goto found_leaf; } + /* fall through */ case assoc_array_walk_tree_empty: case assoc_array_walk_found_wrong_shortcut: default: diff --git a/lib/bsearch.c b/lib/bsearch.c index 18b445b010c3..82512fe7b33c 100644 --- a/lib/bsearch.c +++ b/lib/bsearch.c @@ -11,6 +11,7 @@ #include <linux/export.h> #include <linux/bsearch.h> +#include <linux/kprobes.h> /* * bsearch - binary search an array of elements @@ -53,3 +54,4 @@ void *bsearch(const void *key, const void *base, size_t num, size_t size, return NULL; } EXPORT_SYMBOL(bsearch); +NOKPROBE_SYMBOL(bsearch); diff --git a/lib/cpumask.c b/lib/cpumask.c index 8d666ab84b5c..087a3e9a0202 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -5,6 +5,7 @@ #include <linux/cpumask.h> #include <linux/export.h> #include <linux/memblock.h> +#include <linux/numa.h> /** * cpumask_next - get the next cpu in a cpumask @@ -206,7 +207,7 @@ unsigned int cpumask_local_spread(unsigned int i, int node) /* Wrap: we always want a cpu. */ i %= num_online_cpus(); - if (node == -1) { + if (node == NUMA_NO_NODE) { for_each_cpu(cpu, cpu_online_mask) if (i-- == 0) return cpu; diff --git a/lib/crc32.c b/lib/crc32.c index 45b1d67a1767..4a20455d1f61 100644 --- a/lib/crc32.c +++ b/lib/crc32.c @@ -206,8 +206,8 @@ u32 __pure __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len) EXPORT_SYMBOL(crc32_le); EXPORT_SYMBOL(__crc32c_le); -u32 crc32_le_base(u32, unsigned char const *, size_t) __alias(crc32_le); -u32 __crc32c_le_base(u32, unsigned char const *, size_t) __alias(__crc32c_le); +u32 __pure crc32_le_base(u32, unsigned char const *, size_t) __alias(crc32_le); +u32 __pure __crc32c_le_base(u32, unsigned char const *, size_t) __alias(__crc32c_le); /* * This multiplies the polynomials x and y modulo the given modulus. diff --git a/lib/devres.c b/lib/devres.c index faccf1a037d0..69bed2f38306 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -134,7 +134,6 @@ EXPORT_SYMBOL(devm_iounmap); void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res) { resource_size_t size; - const char *name; void __iomem *dest_ptr; BUG_ON(!dev); @@ -145,9 +144,8 @@ void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res) } size = resource_size(res); - name = res->name ?: dev_name(dev); - if (!devm_request_mem_region(dev, res->start, size, name)) { + if (!devm_request_mem_region(dev, res->start, size, dev_name(dev))) { dev_err(dev, "can't request region for resource %pR\n", res); return IOMEM_ERR_PTR(-EBUSY); } diff --git a/lib/div64.c b/lib/div64.c index 01c8602bb6ff..ee146bb4c558 100644 --- a/lib/div64.c +++ b/lib/div64.c @@ -109,7 +109,7 @@ u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder) quot = div_u64_rem(dividend, divisor, &rem32); *remainder = rem32; } else { - int n = 1 + fls(high); + int n = fls(high); quot = div_u64(dividend >> n, divisor >> n); if (quot != 0) @@ -147,7 +147,7 @@ u64 div64_u64(u64 dividend, u64 divisor) if (high == 0) { quot = div_u64(dividend, divisor); } else { - int n = 1 + fls(high); + int n = fls(high); quot = div_u64(dividend >> n, divisor >> n); if (quot != 0) diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index dbf2b457e47e..7bdf98c37e91 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -847,17 +847,19 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n, const char *name) { struct ddebug_table *dt; - const char *new_name; dt = kzalloc(sizeof(*dt), GFP_KERNEL); - if (dt == NULL) - return -ENOMEM; - new_name = kstrdup_const(name, GFP_KERNEL); - if (new_name == NULL) { - kfree(dt); + if (dt == NULL) { + pr_err("error adding module: %s\n", name); return -ENOMEM; } - dt->mod_name = new_name; + /* + * For built-in modules, name lives in .rodata and is + * immortal. For loaded modules, name points at the name[] + * member of struct module, which lives at least as long as + * this struct ddebug_table. + */ + dt->mod_name = name; dt->num_ddebugs = n; dt->ddebugs = tab; @@ -868,7 +870,6 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n, vpr_info("%u debug prints in module %s\n", n, dt->mod_name); return 0; } -EXPORT_SYMBOL_GPL(ddebug_add_module); /* helper for ddebug_dyndbg_(boot|module)_param_cb */ static int ddebug_dyndbg_param_cb(char *param, char *val, @@ -913,7 +914,6 @@ int ddebug_dyndbg_module_param_cb(char *param, char *val, const char *module) static void ddebug_table_free(struct ddebug_table *dt) { list_del_init(&dt->link); - kfree_const(dt->mod_name); kfree(dt); } @@ -930,15 +930,15 @@ int ddebug_remove_module(const char *mod_name) mutex_lock(&ddebug_lock); list_for_each_entry_safe(dt, nextdt, &ddebug_tables, link) { - if (!strcmp(dt->mod_name, mod_name)) { + if (dt->mod_name == mod_name) { ddebug_table_free(dt); ret = 0; + break; } } mutex_unlock(&ddebug_lock); return ret; } -EXPORT_SYMBOL_GPL(ddebug_remove_module); static void ddebug_remove_all_tables(void) { diff --git a/lib/iomap.c b/lib/iomap.c index 541d926da95e..e909ab71e995 100644 --- a/lib/iomap.c +++ b/lib/iomap.c @@ -65,8 +65,9 @@ static void bad_io_access(unsigned long port, const char *access) #endif #ifndef mmio_read16be -#define mmio_read16be(addr) be16_to_cpu(__raw_readw(addr)) -#define mmio_read32be(addr) be32_to_cpu(__raw_readl(addr)) +#define mmio_read16be(addr) swab16(readw(addr)) +#define mmio_read32be(addr) swab32(readl(addr)) +#define mmio_read64be(addr) swab64(readq(addr)) #endif unsigned int ioread8(void __iomem *addr) @@ -100,14 +101,89 @@ EXPORT_SYMBOL(ioread16be); EXPORT_SYMBOL(ioread32); EXPORT_SYMBOL(ioread32be); +#ifdef readq +static u64 pio_read64_lo_hi(unsigned long port) +{ + u64 lo, hi; + + lo = inl(port); + hi = inl(port + sizeof(u32)); + + return lo | (hi << 32); +} + +static u64 pio_read64_hi_lo(unsigned long port) +{ + u64 lo, hi; + + hi = inl(port + sizeof(u32)); + lo = inl(port); + + return lo | (hi << 32); +} + +static u64 pio_read64be_lo_hi(unsigned long port) +{ + u64 lo, hi; + + lo = pio_read32be(port + sizeof(u32)); + hi = pio_read32be(port); + + return lo | (hi << 32); +} + +static u64 pio_read64be_hi_lo(unsigned long port) +{ + u64 lo, hi; + + hi = pio_read32be(port); + lo = pio_read32be(port + sizeof(u32)); + + return lo | (hi << 32); +} + +u64 ioread64_lo_hi(void __iomem *addr) +{ + IO_COND(addr, return pio_read64_lo_hi(port), return readq(addr)); + return 0xffffffffffffffffULL; +} + +u64 ioread64_hi_lo(void __iomem *addr) +{ + IO_COND(addr, return pio_read64_hi_lo(port), return readq(addr)); + return 0xffffffffffffffffULL; +} + +u64 ioread64be_lo_hi(void __iomem *addr) +{ + IO_COND(addr, return pio_read64be_lo_hi(port), + return mmio_read64be(addr)); + return 0xffffffffffffffffULL; +} + +u64 ioread64be_hi_lo(void __iomem *addr) +{ + IO_COND(addr, return pio_read64be_hi_lo(port), + return mmio_read64be(addr)); + return 0xffffffffffffffffULL; +} + +EXPORT_SYMBOL(ioread64_lo_hi); +EXPORT_SYMBOL(ioread64_hi_lo); +EXPORT_SYMBOL(ioread64be_lo_hi); +EXPORT_SYMBOL(ioread64be_hi_lo); + +#endif /* readq */ + #ifndef pio_write16be #define pio_write16be(val,port) outw(swab16(val),port) #define pio_write32be(val,port) outl(swab32(val),port) #endif #ifndef mmio_write16be -#define mmio_write16be(val,port) __raw_writew(be16_to_cpu(val),port) -#define mmio_write32be(val,port) __raw_writel(be32_to_cpu(val),port) +#define mmio_write16be(val,port) writew(swab16(val),port) +#define mmio_write32be(val,port) writel(swab32(val),port) +#define mmio_write64be(val,port) writeq(swab64(val),port) #endif void iowrite8(u8 val, void __iomem *addr) @@ -136,6 +212,62 @@ EXPORT_SYMBOL(iowrite16be); EXPORT_SYMBOL(iowrite32); EXPORT_SYMBOL(iowrite32be); +#ifdef writeq +static void pio_write64_lo_hi(u64 val, unsigned long port) +{ + outl(val, port); + outl(val >> 32, port + sizeof(u32)); +} + +static void pio_write64_hi_lo(u64 val, unsigned long port) +{ + outl(val >> 32, port + sizeof(u32)); + outl(val, port); +} + +static void pio_write64be_lo_hi(u64 val, unsigned long port) +{ + pio_write32be(val, port + sizeof(u32)); + pio_write32be(val >> 32, port); +} + +static void pio_write64be_hi_lo(u64 val, unsigned long port) +{ + pio_write32be(val >> 32, port); + pio_write32be(val, port + sizeof(u32)); +} + +void iowrite64_lo_hi(u64 val, void __iomem *addr) +{ + IO_COND(addr, pio_write64_lo_hi(val, port), + writeq(val, addr)); +} + +void iowrite64_hi_lo(u64 val, void __iomem *addr) +{ + IO_COND(addr, pio_write64_hi_lo(val, port), + writeq(val, addr)); +} + +void iowrite64be_lo_hi(u64 val, void __iomem *addr) +{ + IO_COND(addr, pio_write64be_lo_hi(val, port), + mmio_write64be(val, addr)); +} + +void iowrite64be_hi_lo(u64 val, void __iomem *addr) +{ + IO_COND(addr, pio_write64be_hi_lo(val, port), + mmio_write64be(val, addr)); +} + +EXPORT_SYMBOL(iowrite64_lo_hi); +EXPORT_SYMBOL(iowrite64_hi_lo); +EXPORT_SYMBOL(iowrite64be_lo_hi); +EXPORT_SYMBOL(iowrite64be_hi_lo); + +#endif /* readq */ + /* * These are the "repeat MMIO read/write" functions. * Note the "__raw" accesses, since we don't want to diff --git a/lib/kobject.c b/lib/kobject.c index b72e00fd7d09..aa89edcd2b63 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -887,7 +887,7 @@ static void kset_release(struct kobject *kobj) kfree(kset); } -void kset_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) +static void kset_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) { if (kobj->parent) kobject_get_ownership(kobj->parent, uid, gid); diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 27c6118afd1c..f05802687ba4 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -200,7 +200,7 @@ int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count) r = kobject_action_type(buf, count, &action, &action_args); if (r) { - msg = "unknown uevent action string\n"; + msg = "unknown uevent action string"; goto out; } @@ -212,7 +212,7 @@ int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count) r = kobject_action_args(action_args, count - (action_args - buf), &env); if (r == -EINVAL) { - msg = "incorrect uevent action arguments\n"; + msg = "incorrect uevent action arguments"; goto out; } @@ -224,7 +224,7 @@ int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count) out: if (r) { devpath = kobject_get_path(kobj, GFP_KERNEL); - printk(KERN_WARNING "synth uevent: %s: %s", + pr_warn("synth uevent: %s: %s\n", devpath ?: "unknown device", msg ?: "failed to send uevent"); kfree(devpath); @@ -765,8 +765,7 @@ static int uevent_net_init(struct net *net) ue_sk->sk = netlink_kernel_create(net, NETLINK_KOBJECT_UEVENT, &cfg); if (!ue_sk->sk) { - printk(KERN_ERR - "kobject_uevent: unable to create netlink socket!\n"); + pr_err("kobject_uevent: unable to create netlink socket!\n"); kfree(ue_sk); return -ENODEV; } diff --git a/lib/livepatch/Makefile b/lib/livepatch/Makefile new file mode 100644 index 000000000000..26900ddaef82 --- /dev/null +++ b/lib/livepatch/Makefile @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for livepatch test code. + +obj-$(CONFIG_TEST_LIVEPATCH) += test_klp_atomic_replace.o \ + test_klp_callbacks_demo.o \ + test_klp_callbacks_demo2.o \ + test_klp_callbacks_busy.o \ + test_klp_callbacks_mod.o \ + test_klp_livepatch.o \ + test_klp_shadow_vars.o + +# Target modules to be livepatched require CC_FLAGS_FTRACE +CFLAGS_test_klp_callbacks_busy.o += $(CC_FLAGS_FTRACE) +CFLAGS_test_klp_callbacks_mod.o += $(CC_FLAGS_FTRACE) diff --git a/lib/livepatch/test_klp_atomic_replace.c b/lib/livepatch/test_klp_atomic_replace.c new file mode 100644 index 000000000000..5af7093ca00c --- /dev/null +++ b/lib/livepatch/test_klp_atomic_replace.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018 Joe Lawrence <joe.lawrence@redhat.com> + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/livepatch.h> + +static int replace; +module_param(replace, int, 0644); +MODULE_PARM_DESC(replace, "replace (default=0)"); + +#include <linux/seq_file.h> +static int livepatch_meminfo_proc_show(struct seq_file *m, void *v) +{ + seq_printf(m, "%s: %s\n", THIS_MODULE->name, + "this has been live patched"); + return 0; +} + +static struct klp_func funcs[] = { + { + .old_name = "meminfo_proc_show", + .new_func = livepatch_meminfo_proc_show, + }, {} +}; + +static struct klp_object objs[] = { + { + /* name being NULL means vmlinux */ + .funcs = funcs, + }, {} +}; + +static struct klp_patch patch = { + .mod = THIS_MODULE, + .objs = objs, + /* set .replace in the init function below for demo purposes */ +}; + +static int test_klp_atomic_replace_init(void) +{ + patch.replace = replace; + return klp_enable_patch(&patch); +} + +static void test_klp_atomic_replace_exit(void) +{ +} + +module_init(test_klp_atomic_replace_init); +module_exit(test_klp_atomic_replace_exit); +MODULE_LICENSE("GPL"); +MODULE_INFO(livepatch, "Y"); +MODULE_AUTHOR("Joe Lawrence <joe.lawrence@redhat.com>"); +MODULE_DESCRIPTION("Livepatch test: atomic replace"); diff --git a/lib/livepatch/test_klp_callbacks_busy.c b/lib/livepatch/test_klp_callbacks_busy.c new file mode 100644 index 000000000000..40beddf8a0e2 --- /dev/null +++ b/lib/livepatch/test_klp_callbacks_busy.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018 Joe Lawrence <joe.lawrence@redhat.com> + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/workqueue.h> +#include <linux/delay.h> + +static int sleep_secs; +module_param(sleep_secs, int, 0644); +MODULE_PARM_DESC(sleep_secs, "sleep_secs (default=0)"); + +static void busymod_work_func(struct work_struct *work); +static DECLARE_DELAYED_WORK(work, busymod_work_func); + +static void busymod_work_func(struct work_struct *work) +{ + pr_info("%s, sleeping %d seconds ...\n", __func__, sleep_secs); + msleep(sleep_secs * 1000); + pr_info("%s exit\n", __func__); +} + +static int test_klp_callbacks_busy_init(void) +{ + pr_info("%s\n", __func__); + schedule_delayed_work(&work, + msecs_to_jiffies(1000 * 0)); + return 0; +} + +static void test_klp_callbacks_busy_exit(void) +{ + cancel_delayed_work_sync(&work); + pr_info("%s\n", __func__); +} + +module_init(test_klp_callbacks_busy_init); +module_exit(test_klp_callbacks_busy_exit); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Joe Lawrence <joe.lawrence@redhat.com>"); +MODULE_DESCRIPTION("Livepatch test: busy target module"); diff --git a/lib/livepatch/test_klp_callbacks_demo.c b/lib/livepatch/test_klp_callbacks_demo.c new file mode 100644 index 000000000000..3fd8fe1cd1cc --- /dev/null +++ b/lib/livepatch/test_klp_callbacks_demo.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018 Joe Lawrence <joe.lawrence@redhat.com> + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/livepatch.h> + +static int pre_patch_ret; +module_param(pre_patch_ret, int, 0644); +MODULE_PARM_DESC(pre_patch_ret, "pre_patch_ret (default=0)"); + +static const char *const module_state[] = { + [MODULE_STATE_LIVE] = "[MODULE_STATE_LIVE] Normal state", + [MODULE_STATE_COMING] = "[MODULE_STATE_COMING] Full formed, running module_init", + [MODULE_STATE_GOING] = "[MODULE_STATE_GOING] Going away", + [MODULE_STATE_UNFORMED] = "[MODULE_STATE_UNFORMED] Still setting it up", +}; + +static void callback_info(const char *callback, struct klp_object *obj) +{ + if (obj->mod) + pr_info("%s: %s -> %s\n", callback, obj->mod->name, + module_state[obj->mod->state]); + else + pr_info("%s: vmlinux\n", callback); +} + +/* Executed on object patching (ie, patch enablement) */ +static int pre_patch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); + return pre_patch_ret; +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void post_patch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void pre_unpatch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void post_unpatch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); +} + +static void patched_work_func(struct work_struct *work) +{ + pr_info("%s\n", __func__); +} + +static struct klp_func no_funcs[] = { + {} +}; + +static struct klp_func busymod_funcs[] = { + { + .old_name = "busymod_work_func", + .new_func = patched_work_func, + }, {} +}; + +static struct klp_object objs[] = { + { + .name = NULL, /* vmlinux */ + .funcs = no_funcs, + .callbacks = { + .pre_patch = pre_patch_callback, + .post_patch = post_patch_callback, + .pre_unpatch = pre_unpatch_callback, + .post_unpatch = post_unpatch_callback, + }, + }, { + .name = "test_klp_callbacks_mod", + .funcs = no_funcs, + .callbacks = { + .pre_patch = pre_patch_callback, + .post_patch = post_patch_callback, + .pre_unpatch = pre_unpatch_callback, + .post_unpatch = post_unpatch_callback, + }, + }, { + .name = "test_klp_callbacks_busy", + .funcs = busymod_funcs, + .callbacks = { + .pre_patch = pre_patch_callback, + .post_patch = post_patch_callback, + .pre_unpatch = pre_unpatch_callback, + .post_unpatch = post_unpatch_callback, + }, + }, { } +}; + +static struct klp_patch patch = { + .mod = THIS_MODULE, + .objs = objs, +}; + +static int test_klp_callbacks_demo_init(void) +{ + return klp_enable_patch(&patch); +} + +static void test_klp_callbacks_demo_exit(void) +{ +} + +module_init(test_klp_callbacks_demo_init); +module_exit(test_klp_callbacks_demo_exit); +MODULE_LICENSE("GPL"); +MODULE_INFO(livepatch, "Y"); +MODULE_AUTHOR("Joe Lawrence <joe.lawrence@redhat.com>"); +MODULE_DESCRIPTION("Livepatch test: livepatch demo"); diff --git a/lib/livepatch/test_klp_callbacks_demo2.c b/lib/livepatch/test_klp_callbacks_demo2.c new file mode 100644 index 000000000000..5417573e80af --- /dev/null +++ b/lib/livepatch/test_klp_callbacks_demo2.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018 Joe Lawrence <joe.lawrence@redhat.com> + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/livepatch.h> + +static int replace; +module_param(replace, int, 0644); +MODULE_PARM_DESC(replace, "replace (default=0)"); + +static const char *const module_state[] = { + [MODULE_STATE_LIVE] = "[MODULE_STATE_LIVE] Normal state", + [MODULE_STATE_COMING] = "[MODULE_STATE_COMING] Full formed, running module_init", + [MODULE_STATE_GOING] = "[MODULE_STATE_GOING] Going away", + [MODULE_STATE_UNFORMED] = "[MODULE_STATE_UNFORMED] Still setting it up", +}; + +static void callback_info(const char *callback, struct klp_object *obj) +{ + if (obj->mod) + pr_info("%s: %s -> %s\n", callback, obj->mod->name, + module_state[obj->mod->state]); + else + pr_info("%s: vmlinux\n", callback); +} + +/* Executed on object patching (ie, patch enablement) */ +static int pre_patch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); + return 0; +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void post_patch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void pre_unpatch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void post_unpatch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); +} + +static struct klp_func no_funcs[] = { + { } +}; + +static struct klp_object objs[] = { + { + .name = NULL, /* vmlinux */ + .funcs = no_funcs, + .callbacks = { + .pre_patch = pre_patch_callback, + .post_patch = post_patch_callback, + .pre_unpatch = pre_unpatch_callback, + .post_unpatch = post_unpatch_callback, + }, + }, { } +}; + +static struct klp_patch patch = { + .mod = THIS_MODULE, + .objs = objs, + /* set .replace in the init function below for demo purposes */ +}; + +static int test_klp_callbacks_demo2_init(void) +{ + patch.replace = replace; + return klp_enable_patch(&patch); +} + +static void test_klp_callbacks_demo2_exit(void) +{ +} + +module_init(test_klp_callbacks_demo2_init); +module_exit(test_klp_callbacks_demo2_exit); +MODULE_LICENSE("GPL"); +MODULE_INFO(livepatch, "Y"); +MODULE_AUTHOR("Joe Lawrence <joe.lawrence@redhat.com>"); +MODULE_DESCRIPTION("Livepatch test: livepatch demo2"); diff --git a/lib/livepatch/test_klp_callbacks_mod.c b/lib/livepatch/test_klp_callbacks_mod.c new file mode 100644 index 000000000000..8fbe645b1c2c --- /dev/null +++ b/lib/livepatch/test_klp_callbacks_mod.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018 Joe Lawrence <joe.lawrence@redhat.com> + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/kernel.h> + +static int test_klp_callbacks_mod_init(void) +{ + pr_info("%s\n", __func__); + return 0; +} + +static void test_klp_callbacks_mod_exit(void) +{ + pr_info("%s\n", __func__); +} + +module_init(test_klp_callbacks_mod_init); +module_exit(test_klp_callbacks_mod_exit); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Joe Lawrence <joe.lawrence@redhat.com>"); +MODULE_DESCRIPTION("Livepatch test: target module"); diff --git a/lib/livepatch/test_klp_livepatch.c b/lib/livepatch/test_klp_livepatch.c new file mode 100644 index 000000000000..aff08199de71 --- /dev/null +++ b/lib/livepatch/test_klp_livepatch.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2014 Seth Jennings <sjenning@redhat.com> + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/livepatch.h> + +#include <linux/seq_file.h> +static int livepatch_cmdline_proc_show(struct seq_file *m, void *v) +{ + seq_printf(m, "%s: %s\n", THIS_MODULE->name, + "this has been live patched"); + return 0; +} + +static struct klp_func funcs[] = { + { + .old_name = "cmdline_proc_show", + .new_func = livepatch_cmdline_proc_show, + }, { } +}; + +static struct klp_object objs[] = { + { + /* name being NULL means vmlinux */ + .funcs = funcs, + }, { } +}; + +static struct klp_patch patch = { + .mod = THIS_MODULE, + .objs = objs, +}; + +static int test_klp_livepatch_init(void) +{ + return klp_enable_patch(&patch); +} + +static void test_klp_livepatch_exit(void) +{ +} + +module_init(test_klp_livepatch_init); +module_exit(test_klp_livepatch_exit); +MODULE_LICENSE("GPL"); +MODULE_INFO(livepatch, "Y"); +MODULE_AUTHOR("Seth Jennings <sjenning@redhat.com>"); +MODULE_DESCRIPTION("Livepatch test: livepatch module"); diff --git a/lib/livepatch/test_klp_shadow_vars.c b/lib/livepatch/test_klp_shadow_vars.c new file mode 100644 index 000000000000..fe5c413efe96 --- /dev/null +++ b/lib/livepatch/test_klp_shadow_vars.c @@ -0,0 +1,258 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018 Joe Lawrence <joe.lawrence@redhat.com> + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/livepatch.h> +#include <linux/slab.h> + +/* + * Keep a small list of pointers so that we can print address-agnostic + * pointer values. Use a rolling integer count to differentiate the values. + * Ironically we could have used the shadow variable API to do this, but + * let's not lean too heavily on the very code we're testing. + */ +static LIST_HEAD(ptr_list); +struct shadow_ptr { + void *ptr; + int id; + struct list_head list; +}; + +static void free_ptr_list(void) +{ + struct shadow_ptr *sp, *tmp_sp; + + list_for_each_entry_safe(sp, tmp_sp, &ptr_list, list) { + list_del(&sp->list); + kfree(sp); + } +} + +static int ptr_id(void *ptr) +{ + struct shadow_ptr *sp; + static int count; + + list_for_each_entry(sp, &ptr_list, list) { + if (sp->ptr == ptr) + return sp->id; + } + + sp = kmalloc(sizeof(*sp), GFP_ATOMIC); + if (!sp) + return -ENOMEM; + sp->ptr = ptr; + sp->id = count++; + + list_add(&sp->list, &ptr_list); + + return sp->id; +} + +/* + * Shadow variable wrapper functions that echo the function and arguments + * to the kernel log for testing verification. Don't display raw pointers, + * but use the ptr_id() value instead. + */ +static void *shadow_get(void *obj, unsigned long id) +{ + void *ret = klp_shadow_get(obj, id); + + pr_info("klp_%s(obj=PTR%d, id=0x%lx) = PTR%d\n", + __func__, ptr_id(obj), id, ptr_id(ret)); + + return ret; +} + +static void *shadow_alloc(void *obj, unsigned long id, size_t size, + gfp_t gfp_flags, klp_shadow_ctor_t ctor, + void *ctor_data) +{ + void *ret = klp_shadow_alloc(obj, id, size, gfp_flags, ctor, + ctor_data); + pr_info("klp_%s(obj=PTR%d, id=0x%lx, size=%zx, gfp_flags=%pGg), ctor=PTR%d, ctor_data=PTR%d = PTR%d\n", + __func__, ptr_id(obj), id, size, &gfp_flags, ptr_id(ctor), + ptr_id(ctor_data), ptr_id(ret)); + return ret; +} + +static void *shadow_get_or_alloc(void *obj, unsigned long id, size_t size, + gfp_t gfp_flags, klp_shadow_ctor_t ctor, + void *ctor_data) +{ + void *ret = klp_shadow_get_or_alloc(obj, id, size, gfp_flags, ctor, + ctor_data); + pr_info("klp_%s(obj=PTR%d, id=0x%lx, size=%zx, gfp_flags=%pGg), ctor=PTR%d, ctor_data=PTR%d = PTR%d\n", + __func__, ptr_id(obj), id, size, &gfp_flags, ptr_id(ctor), + ptr_id(ctor_data), ptr_id(ret)); + return ret; +} + +static void shadow_free(void *obj, unsigned long id, klp_shadow_dtor_t dtor) +{ + klp_shadow_free(obj, id, dtor); + pr_info("klp_%s(obj=PTR%d, id=0x%lx, dtor=PTR%d)\n", + __func__, ptr_id(obj), id, ptr_id(dtor)); +} + +static void shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor) +{ + klp_shadow_free_all(id, dtor); + pr_info("klp_%s(id=0x%lx, dtor=PTR%d)\n", + __func__, id, ptr_id(dtor)); +} + + +/* Shadow variable constructor - remember simple pointer data */ +static int shadow_ctor(void *obj, void *shadow_data, void *ctor_data) +{ + int **shadow_int = shadow_data; + *shadow_int = ctor_data; + pr_info("%s: PTR%d -> PTR%d\n", + __func__, ptr_id(shadow_int), ptr_id(ctor_data)); + + return 0; +} + +static void shadow_dtor(void *obj, void *shadow_data) +{ + pr_info("%s(obj=PTR%d, shadow_data=PTR%d)\n", + __func__, ptr_id(obj), ptr_id(shadow_data)); +} + +static int test_klp_shadow_vars_init(void) +{ + void *obj = THIS_MODULE; + int id = 0x1234; + size_t size = sizeof(int *); + gfp_t gfp_flags = GFP_KERNEL; + + int var1, var2, var3, var4; + int **sv1, **sv2, **sv3, **sv4; + + void *ret; + + ptr_id(NULL); + ptr_id(&var1); + ptr_id(&var2); + ptr_id(&var3); + ptr_id(&var4); + + /* + * With an empty shadow variable hash table, expect not to find + * any matches. + */ + ret = shadow_get(obj, id); + if (!ret) + pr_info(" got expected NULL result\n"); + + /* + * Allocate a few shadow variables with different <obj> and <id>. + */ + sv1 = shadow_alloc(obj, id, size, gfp_flags, shadow_ctor, &var1); + if (!sv1) + return -ENOMEM; + + sv2 = shadow_alloc(obj + 1, id, size, gfp_flags, shadow_ctor, &var2); + if (!sv2) + return -ENOMEM; + + sv3 = shadow_alloc(obj, id + 1, size, gfp_flags, shadow_ctor, &var3); + if (!sv3) + return -ENOMEM; + + /* + * Verify we can find our new shadow variables and that they point + * to expected data. + */ + ret = shadow_get(obj, id); + if (!ret) + return -EINVAL; + if (ret == sv1 && *sv1 == &var1) + pr_info(" got expected PTR%d -> PTR%d result\n", + ptr_id(sv1), ptr_id(*sv1)); + + ret = shadow_get(obj + 1, id); + if (!ret) + return -EINVAL; + if (ret == sv2 && *sv2 == &var2) + pr_info(" got expected PTR%d -> PTR%d result\n", + ptr_id(sv2), ptr_id(*sv2)); + ret = shadow_get(obj, id + 1); + if (!ret) + return -EINVAL; + if (ret == sv3 && *sv3 == &var3) + pr_info(" got expected PTR%d -> PTR%d result\n", + ptr_id(sv3), ptr_id(*sv3)); + + /* + * Allocate or get a few more, this time with the same <obj>, <id>. + * The second invocation should return the same shadow var. + */ + sv4 = shadow_get_or_alloc(obj + 2, id, size, gfp_flags, shadow_ctor, &var4); + if (!sv4) + return -ENOMEM; + + ret = shadow_get_or_alloc(obj + 2, id, size, gfp_flags, shadow_ctor, &var4); + if (!ret) + return -EINVAL; + if (ret == sv4 && *sv4 == &var4) + pr_info(" got expected PTR%d -> PTR%d result\n", + ptr_id(sv4), ptr_id(*sv4)); + + /* + * Free the <obj=*, id> shadow variables and check that we can no + * longer find them. + */ + shadow_free(obj, id, shadow_dtor); /* sv1 */ + ret = shadow_get(obj, id); + if (!ret) + pr_info(" got expected NULL result\n"); + + shadow_free(obj + 1, id, shadow_dtor); /* sv2 */ + ret = shadow_get(obj + 1, id); + if (!ret) + pr_info(" got expected NULL result\n"); + + shadow_free(obj + 2, id, shadow_dtor); /* sv4 */ + ret = shadow_get(obj + 2, id); + if (!ret) + pr_info(" got expected NULL result\n"); + + /* + * We should still find an <id+1> variable. + */ + ret = shadow_get(obj, id + 1); + if (!ret) + return -EINVAL; + if (ret == sv3 && *sv3 == &var3) + pr_info(" got expected PTR%d -> PTR%d result\n", + ptr_id(sv3), ptr_id(*sv3)); + + /* + * Free all the <id+1> variables, too. + */ + shadow_free_all(id + 1, shadow_dtor); /* sv3 */ + ret = shadow_get(obj, id); + if (!ret) + pr_info(" shadow_get() got expected NULL result\n"); + + + free_ptr_list(); + + return 0; +} + +static void test_klp_shadow_vars_exit(void) +{ +} + +module_init(test_klp_shadow_vars_init); +module_exit(test_klp_shadow_vars_exit); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Joe Lawrence <joe.lawrence@redhat.com>"); +MODULE_DESCRIPTION("Livepatch test: shadow variables"); diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index 1e1bbf171eca..a1705545e6ac 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -1989,6 +1989,7 @@ void locking_selftest(void) init_shared_classes(); debug_locks_silent = !debug_locks_verbose; + lockdep_set_selftest_task(current); DO_TESTCASE_6R("A-A deadlock", AA); DO_TESTCASE_6R("A-B-B-A deadlock", ABBA); @@ -2097,5 +2098,6 @@ void locking_selftest(void) printk("---------------------------------\n"); debug_locks = 1; } + lockdep_set_selftest_task(NULL); debug_locks_silent = 0; } diff --git a/lib/lzo/lzo1x_compress.c b/lib/lzo/lzo1x_compress.c index 236eb21167b5..4525fb094844 100644 --- a/lib/lzo/lzo1x_compress.c +++ b/lib/lzo/lzo1x_compress.c @@ -20,7 +20,8 @@ static noinline size_t lzo1x_1_do_compress(const unsigned char *in, size_t in_len, unsigned char *out, size_t *out_len, - size_t ti, void *wrkmem) + size_t ti, void *wrkmem, signed char *state_offset, + const unsigned char bitstream_version) { const unsigned char *ip; unsigned char *op; @@ -35,27 +36,85 @@ lzo1x_1_do_compress(const unsigned char *in, size_t in_len, ip += ti < 4 ? 4 - ti : 0; for (;;) { - const unsigned char *m_pos; + const unsigned char *m_pos = NULL; size_t t, m_len, m_off; u32 dv; + u32 run_length = 0; literal: ip += 1 + ((ip - ii) >> 5); next: if (unlikely(ip >= ip_end)) break; dv = get_unaligned_le32(ip); - t = ((dv * 0x1824429d) >> (32 - D_BITS)) & D_MASK; - m_pos = in + dict[t]; - dict[t] = (lzo_dict_t) (ip - in); - if (unlikely(dv != get_unaligned_le32(m_pos))) - goto literal; + + if (dv == 0 && bitstream_version) { + const unsigned char *ir = ip + 4; + const unsigned char *limit = ip_end + < (ip + MAX_ZERO_RUN_LENGTH + 1) + ? ip_end : ip + MAX_ZERO_RUN_LENGTH + 1; +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && \ + defined(LZO_FAST_64BIT_MEMORY_ACCESS) + u64 dv64; + + for (; (ir + 32) <= limit; ir += 32) { + dv64 = get_unaligned((u64 *)ir); + dv64 |= get_unaligned((u64 *)ir + 1); + dv64 |= get_unaligned((u64 *)ir + 2); + dv64 |= get_unaligned((u64 *)ir + 3); + if (dv64) + break; + } + for (; (ir + 8) <= limit; ir += 8) { + dv64 = get_unaligned((u64 *)ir); + if (dv64) { +# if defined(__LITTLE_ENDIAN) + ir += __builtin_ctzll(dv64) >> 3; +# elif defined(__BIG_ENDIAN) + ir += __builtin_clzll(dv64) >> 3; +# else +# error "missing endian definition" +# endif + break; + } + } +#else + while ((ir < (const unsigned char *) + ALIGN((uintptr_t)ir, 4)) && + (ir < limit) && (*ir == 0)) + ir++; + for (; (ir + 4) <= limit; ir += 4) { + dv = *((u32 *)ir); + if (dv) { +# if defined(__LITTLE_ENDIAN) + ir += __builtin_ctz(dv) >> 3; +# elif defined(__BIG_ENDIAN) + ir += __builtin_clz(dv) >> 3; +# else +# error "missing endian definition" +# endif + break; + } + } +#endif + while (likely(ir < limit) && unlikely(*ir == 0)) + ir++; + run_length = ir - ip; + if (run_length > MAX_ZERO_RUN_LENGTH) + run_length = MAX_ZERO_RUN_LENGTH; + } else { + t = ((dv * 0x1824429d) >> (32 - D_BITS)) & D_MASK; + m_pos = in + dict[t]; + dict[t] = (lzo_dict_t) (ip - in); + if (unlikely(dv != get_unaligned_le32(m_pos))) + goto literal; + } ii -= ti; ti = 0; t = ip - ii; if (t != 0) { if (t <= 3) { - op[-2] |= t; + op[*state_offset] |= t; COPY4(op, ii); op += t; } else if (t <= 16) { @@ -88,6 +147,17 @@ next: } } + if (unlikely(run_length)) { + ip += run_length; + run_length -= MIN_ZERO_RUN_LENGTH; + put_unaligned_le32((run_length << 21) | 0xfffc18 + | (run_length & 0x7), op); + op += 4; + run_length = 0; + *state_offset = -3; + goto finished_writing_instruction; + } + m_len = 4; { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(LZO_USE_CTZ64) @@ -170,7 +240,6 @@ m_len_done: m_off = ip - m_pos; ip += m_len; - ii = ip; if (m_len <= M2_MAX_LEN && m_off <= M2_MAX_OFFSET) { m_off -= 1; *op++ = (((m_len - 1) << 5) | ((m_off & 7) << 2)); @@ -207,29 +276,45 @@ m_len_done: *op++ = (m_off << 2); *op++ = (m_off >> 6); } + *state_offset = -2; +finished_writing_instruction: + ii = ip; goto next; } *out_len = op - out; return in_end - (ii - ti); } -int lzo1x_1_compress(const unsigned char *in, size_t in_len, +int lzogeneric1x_1_compress(const unsigned char *in, size_t in_len, unsigned char *out, size_t *out_len, - void *wrkmem) + void *wrkmem, const unsigned char bitstream_version) { const unsigned char *ip = in; unsigned char *op = out; size_t l = in_len; size_t t = 0; + signed char state_offset = -2; + unsigned int m4_max_offset; + + // LZO v0 will never write 17 as first byte, + // so this is used to version the bitstream + if (bitstream_version > 0) { + *op++ = 17; + *op++ = bitstream_version; + m4_max_offset = M4_MAX_OFFSET_V1; + } else { + m4_max_offset = M4_MAX_OFFSET_V0; + } while (l > 20) { - size_t ll = l <= (M4_MAX_OFFSET + 1) ? l : (M4_MAX_OFFSET + 1); + size_t ll = l <= (m4_max_offset + 1) ? l : (m4_max_offset + 1); uintptr_t ll_end = (uintptr_t) ip + ll; if ((ll_end + ((t + ll) >> 5)) <= ll_end) break; BUILD_BUG_ON(D_SIZE * sizeof(lzo_dict_t) > LZO1X_1_MEM_COMPRESS); memset(wrkmem, 0, D_SIZE * sizeof(lzo_dict_t)); - t = lzo1x_1_do_compress(ip, ll, op, out_len, t, wrkmem); + t = lzo1x_1_do_compress(ip, ll, op, out_len, t, wrkmem, + &state_offset, bitstream_version); ip += ll; op += *out_len; l -= ll; @@ -242,7 +327,7 @@ int lzo1x_1_compress(const unsigned char *in, size_t in_len, if (op == out && t <= 238) { *op++ = (17 + t); } else if (t <= 3) { - op[-2] |= t; + op[state_offset] |= t; } else if (t <= 18) { *op++ = (t - 3); } else { @@ -273,7 +358,24 @@ int lzo1x_1_compress(const unsigned char *in, size_t in_len, *out_len = op - out; return LZO_E_OK; } + +int lzo1x_1_compress(const unsigned char *in, size_t in_len, + unsigned char *out, size_t *out_len, + void *wrkmem) +{ + return lzogeneric1x_1_compress(in, in_len, out, out_len, wrkmem, 0); +} + +int lzorle1x_1_compress(const unsigned char *in, size_t in_len, + unsigned char *out, size_t *out_len, + void *wrkmem) +{ + return lzogeneric1x_1_compress(in, in_len, out, out_len, + wrkmem, LZO_VERSION); +} + EXPORT_SYMBOL_GPL(lzo1x_1_compress); +EXPORT_SYMBOL_GPL(lzorle1x_1_compress); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("LZO1X-1 Compressor"); diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c index a1c387f6afba..6d2600ea3b55 100644 --- a/lib/lzo/lzo1x_decompress_safe.c +++ b/lib/lzo/lzo1x_decompress_safe.c @@ -46,11 +46,23 @@ int lzo1x_decompress_safe(const unsigned char *in, size_t in_len, const unsigned char * const ip_end = in + in_len; unsigned char * const op_end = out + *out_len; + unsigned char bitstream_version; + op = out; ip = in; if (unlikely(in_len < 3)) goto input_overrun; + + if (likely(*ip == 17)) { + bitstream_version = ip[1]; + ip += 2; + if (unlikely(in_len < 5)) + goto input_overrun; + } else { + bitstream_version = 0; + } + if (*ip > 17) { t = *ip++ - 17; if (t < 4) { @@ -154,32 +166,49 @@ copy_literal_run: m_pos -= next >> 2; next &= 3; } else { - m_pos = op; - m_pos -= (t & 8) << 11; - t = (t & 7) + (3 - 1); - if (unlikely(t == 2)) { - size_t offset; - const unsigned char *ip_last = ip; + NEED_IP(2); + next = get_unaligned_le16(ip); + if (((next & 0xfffc) == 0xfffc) && + ((t & 0xf8) == 0x18) && + likely(bitstream_version)) { + NEED_IP(3); + t &= 7; + t |= ip[2] << 3; + t += MIN_ZERO_RUN_LENGTH; + NEED_OP(t); + memset(op, 0, t); + op += t; + next &= 3; + ip += 3; + goto match_next; + } else { + m_pos = op; + m_pos -= (t & 8) << 11; + t = (t & 7) + (3 - 1); + if (unlikely(t == 2)) { + size_t offset; + const unsigned char *ip_last = ip; - while (unlikely(*ip == 0)) { - ip++; - NEED_IP(1); - } - offset = ip - ip_last; - if (unlikely(offset > MAX_255_COUNT)) - return LZO_E_ERROR; + while (unlikely(*ip == 0)) { + ip++; + NEED_IP(1); + } + offset = ip - ip_last; + if (unlikely(offset > MAX_255_COUNT)) + return LZO_E_ERROR; - offset = (offset << 8) - offset; - t += offset + 7 + *ip++; - NEED_IP(2); + offset = (offset << 8) - offset; + t += offset + 7 + *ip++; + NEED_IP(2); + next = get_unaligned_le16(ip); + } + ip += 2; + m_pos -= next >> 2; + next &= 3; + if (m_pos == op) + goto eof_found; + m_pos -= 0x4000; } - next = get_unaligned_le16(ip); - ip += 2; - m_pos -= next >> 2; - next &= 3; - if (m_pos == op) - goto eof_found; - m_pos -= 0x4000; } TEST_LB(m_pos); #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) diff --git a/lib/lzo/lzodefs.h b/lib/lzo/lzodefs.h index 4edefd2f540c..b60851fcf6ce 100644 --- a/lib/lzo/lzodefs.h +++ b/lib/lzo/lzodefs.h @@ -13,9 +13,15 @@ */ +/* Version + * 0: original lzo version + * 1: lzo with support for RLE + */ +#define LZO_VERSION 1 + #define COPY4(dst, src) \ put_unaligned(get_unaligned((const u32 *)(src)), (u32 *)(dst)) -#if defined(__x86_64__) +#if defined(CONFIG_X86_64) || defined(CONFIG_ARM64) #define COPY8(dst, src) \ put_unaligned(get_unaligned((const u64 *)(src)), (u64 *)(dst)) #else @@ -25,19 +31,21 @@ #if defined(__BIG_ENDIAN) && defined(__LITTLE_ENDIAN) #error "conflicting endian definitions" -#elif defined(__x86_64__) +#elif defined(CONFIG_X86_64) || defined(CONFIG_ARM64) #define LZO_USE_CTZ64 1 #define LZO_USE_CTZ32 1 -#elif defined(__i386__) || defined(__powerpc__) +#define LZO_FAST_64BIT_MEMORY_ACCESS +#elif defined(CONFIG_X86) || defined(CONFIG_PPC) #define LZO_USE_CTZ32 1 -#elif defined(__arm__) && (__LINUX_ARM_ARCH__ >= 5) +#elif defined(CONFIG_ARM) && (__LINUX_ARM_ARCH__ >= 5) #define LZO_USE_CTZ32 1 #endif #define M1_MAX_OFFSET 0x0400 #define M2_MAX_OFFSET 0x0800 #define M3_MAX_OFFSET 0x4000 -#define M4_MAX_OFFSET 0xbfff +#define M4_MAX_OFFSET_V0 0xbfff +#define M4_MAX_OFFSET_V1 0xbffe #define M1_MIN_LEN 2 #define M1_MAX_LEN 2 @@ -53,6 +61,9 @@ #define M3_MARKER 32 #define M4_MARKER 16 +#define MIN_ZERO_RUN_LENGTH 4 +#define MAX_ZERO_RUN_LENGTH (2047 + MIN_ZERO_RUN_LENGTH) + #define lzo_dict_t unsigned short #define D_BITS 13 #define D_SIZE (1u << D_BITS) diff --git a/lib/objagg.c b/lib/objagg.c index c9b457a91153..576be22e86de 100644 --- a/lib/objagg.c +++ b/lib/objagg.c @@ -4,6 +4,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/rhashtable.h> +#include <linux/idr.h> #include <linux/list.h> #include <linux/sort.h> #include <linux/objagg.h> @@ -11,6 +12,34 @@ #define CREATE_TRACE_POINTS #include <trace/events/objagg.h> +struct objagg_hints { + struct rhashtable node_ht; + struct rhashtable_params ht_params; + struct list_head node_list; + unsigned int node_count; + unsigned int root_count; + unsigned int refcount; + const struct objagg_ops *ops; +}; + +struct objagg_hints_node { + struct rhash_head ht_node; /* member of objagg_hints->node_ht */ + struct list_head list; /* member of objagg_hints->node_list */ + struct objagg_hints_node *parent; + unsigned int root_id; + struct objagg_obj_stats_info stats_info; + unsigned long obj[0]; +}; + +static struct objagg_hints_node * +objagg_hints_lookup(struct objagg_hints *objagg_hints, void *obj) +{ + if (!objagg_hints) + return NULL; + return rhashtable_lookup_fast(&objagg_hints->node_ht, obj, + objagg_hints->ht_params); +} + struct objagg { const struct objagg_ops *ops; void *priv; @@ -18,6 +47,8 @@ struct objagg { struct rhashtable_params ht_params; struct list_head obj_list; unsigned int obj_count; + struct ida root_ida; + struct objagg_hints *hints; }; struct objagg_obj { @@ -30,6 +61,7 @@ struct objagg_obj { void *delta_priv; /* user delta private */ void *root_priv; /* user root private */ }; + unsigned int root_id; unsigned int refcount; /* counts number of users of this object * including nested objects */ @@ -130,7 +162,8 @@ static struct objagg_obj *objagg_obj_lookup(struct objagg *objagg, void *obj) static int objagg_obj_parent_assign(struct objagg *objagg, struct objagg_obj *objagg_obj, - struct objagg_obj *parent) + struct objagg_obj *parent, + bool take_parent_ref) { void *delta_priv; @@ -144,7 +177,8 @@ static int objagg_obj_parent_assign(struct objagg *objagg, */ objagg_obj->parent = parent; objagg_obj->delta_priv = delta_priv; - objagg_obj_ref_inc(objagg_obj->parent); + if (take_parent_ref) + objagg_obj_ref_inc(objagg_obj->parent); trace_objagg_obj_parent_assign(objagg, objagg_obj, parent, parent->refcount); @@ -164,7 +198,7 @@ static int objagg_obj_parent_lookup_assign(struct objagg *objagg, if (!objagg_obj_is_root(objagg_obj_cur)) continue; err = objagg_obj_parent_assign(objagg, objagg_obj, - objagg_obj_cur); + objagg_obj_cur, true); if (!err) return 0; } @@ -184,16 +218,68 @@ static void objagg_obj_parent_unassign(struct objagg *objagg, __objagg_obj_put(objagg, objagg_obj->parent); } +static int objagg_obj_root_id_alloc(struct objagg *objagg, + struct objagg_obj *objagg_obj, + struct objagg_hints_node *hnode) +{ + unsigned int min, max; + int root_id; + + /* In case there are no hints available, the root id is invalid. */ + if (!objagg->hints) { + objagg_obj->root_id = OBJAGG_OBJ_ROOT_ID_INVALID; + return 0; + } + + if (hnode) { + min = hnode->root_id; + max = hnode->root_id; + } else { + /* For objects with no hint, start after the last + * hinted root_id. + */ + min = objagg->hints->root_count; + max = ~0; + } + + root_id = ida_alloc_range(&objagg->root_ida, min, max, GFP_KERNEL); + + if (root_id < 0) + return root_id; + objagg_obj->root_id = root_id; + return 0; +} + +static void objagg_obj_root_id_free(struct objagg *objagg, + struct objagg_obj *objagg_obj) +{ + if (!objagg->hints) + return; + ida_free(&objagg->root_ida, objagg_obj->root_id); +} + static int objagg_obj_root_create(struct objagg *objagg, - struct objagg_obj *objagg_obj) + struct objagg_obj *objagg_obj, + struct objagg_hints_node *hnode) { - objagg_obj->root_priv = objagg->ops->root_create(objagg->priv, - objagg_obj->obj); - if (IS_ERR(objagg_obj->root_priv)) - return PTR_ERR(objagg_obj->root_priv); + int err; + err = objagg_obj_root_id_alloc(objagg, objagg_obj, hnode); + if (err) + return err; + objagg_obj->root_priv = objagg->ops->root_create(objagg->priv, + objagg_obj->obj, + objagg_obj->root_id); + if (IS_ERR(objagg_obj->root_priv)) { + err = PTR_ERR(objagg_obj->root_priv); + goto err_root_create; + } trace_objagg_obj_root_create(objagg, objagg_obj); return 0; + +err_root_create: + objagg_obj_root_id_free(objagg, objagg_obj); + return err; } static void objagg_obj_root_destroy(struct objagg *objagg, @@ -201,19 +287,69 @@ static void objagg_obj_root_destroy(struct objagg *objagg, { trace_objagg_obj_root_destroy(objagg, objagg_obj); objagg->ops->root_destroy(objagg->priv, objagg_obj->root_priv); + objagg_obj_root_id_free(objagg, objagg_obj); +} + +static struct objagg_obj *__objagg_obj_get(struct objagg *objagg, void *obj); + +static int objagg_obj_init_with_hints(struct objagg *objagg, + struct objagg_obj *objagg_obj, + bool *hint_found) +{ + struct objagg_hints_node *hnode; + struct objagg_obj *parent; + int err; + + hnode = objagg_hints_lookup(objagg->hints, objagg_obj->obj); + if (!hnode) { + *hint_found = false; + return 0; + } + *hint_found = true; + + if (!hnode->parent) + return objagg_obj_root_create(objagg, objagg_obj, hnode); + + parent = __objagg_obj_get(objagg, hnode->parent->obj); + if (IS_ERR(parent)) + return PTR_ERR(parent); + + err = objagg_obj_parent_assign(objagg, objagg_obj, parent, false); + if (err) { + *hint_found = false; + err = 0; + goto err_parent_assign; + } + + return 0; + +err_parent_assign: + objagg_obj_put(objagg, parent); + return err; } static int objagg_obj_init(struct objagg *objagg, struct objagg_obj *objagg_obj) { + bool hint_found; int err; + /* First, try to use hints if they are available and + * if they provide result. + */ + err = objagg_obj_init_with_hints(objagg, objagg_obj, &hint_found); + if (err) + return err; + + if (hint_found) + return 0; + /* Try to find if the object can be aggregated under an existing one. */ err = objagg_obj_parent_lookup_assign(objagg, objagg_obj); if (!err) return 0; /* If aggregation is not possible, make the object a root. */ - return objagg_obj_root_create(objagg, objagg_obj); + return objagg_obj_root_create(objagg, objagg_obj, NULL); } static void objagg_obj_fini(struct objagg *objagg, @@ -349,8 +485,9 @@ EXPORT_SYMBOL(objagg_obj_put); /** * objagg_create - creates a new objagg instance - * @ops: user-specific callbacks - * @priv: pointer to a private data passed to the ops + * @ops: user-specific callbacks + * @objagg_hints: hints, can be NULL + * @priv: pointer to a private data passed to the ops * * Note: all locking must be provided by the caller. * @@ -374,18 +511,25 @@ EXPORT_SYMBOL(objagg_obj_put); * Returns a pointer to newly created objagg instance in case of success, * otherwise it returns pointer error using ERR_PTR macro. */ -struct objagg *objagg_create(const struct objagg_ops *ops, void *priv) +struct objagg *objagg_create(const struct objagg_ops *ops, + struct objagg_hints *objagg_hints, void *priv) { struct objagg *objagg; int err; if (WARN_ON(!ops || !ops->root_create || !ops->root_destroy || - !ops->delta_create || !ops->delta_destroy)) + !ops->delta_check || !ops->delta_create || + !ops->delta_destroy)) return ERR_PTR(-EINVAL); + objagg = kzalloc(sizeof(*objagg), GFP_KERNEL); if (!objagg) return ERR_PTR(-ENOMEM); objagg->ops = ops; + if (objagg_hints) { + objagg->hints = objagg_hints; + objagg_hints->refcount++; + } objagg->priv = priv; INIT_LIST_HEAD(&objagg->obj_list); @@ -397,6 +541,8 @@ struct objagg *objagg_create(const struct objagg_ops *ops, void *priv) if (err) goto err_rhashtable_init; + ida_init(&objagg->root_ida); + trace_objagg_create(objagg); return objagg; @@ -415,8 +561,11 @@ EXPORT_SYMBOL(objagg_create); void objagg_destroy(struct objagg *objagg) { trace_objagg_destroy(objagg); + ida_destroy(&objagg->root_ida); WARN_ON(!list_empty(&objagg->obj_list)); rhashtable_destroy(&objagg->obj_ht); + if (objagg->hints) + objagg_hints_put(objagg->hints); kfree(objagg); } EXPORT_SYMBOL(objagg_destroy); @@ -472,6 +621,8 @@ const struct objagg_stats *objagg_stats_get(struct objagg *objagg) objagg_stats->stats_info[i].objagg_obj = objagg_obj; objagg_stats->stats_info[i].is_root = objagg_obj_is_root(objagg_obj); + if (objagg_stats->stats_info[i].is_root) + objagg_stats->root_count++; i++; } objagg_stats->stats_info_count = i; @@ -485,7 +636,7 @@ const struct objagg_stats *objagg_stats_get(struct objagg *objagg) EXPORT_SYMBOL(objagg_stats_get); /** - * objagg_stats_puts - puts stats of the objagg instance + * objagg_stats_put - puts stats of the objagg instance * @objagg_stats: objagg instance stats * * Note: all locking must be provided by the caller. @@ -496,6 +647,410 @@ void objagg_stats_put(const struct objagg_stats *objagg_stats) } EXPORT_SYMBOL(objagg_stats_put); +static struct objagg_hints_node * +objagg_hints_node_create(struct objagg_hints *objagg_hints, + struct objagg_obj *objagg_obj, size_t obj_size, + struct objagg_hints_node *parent_hnode) +{ + unsigned int user_count = objagg_obj->stats.user_count; + struct objagg_hints_node *hnode; + int err; + + hnode = kzalloc(sizeof(*hnode) + obj_size, GFP_KERNEL); + if (!hnode) + return ERR_PTR(-ENOMEM); + memcpy(hnode->obj, &objagg_obj->obj, obj_size); + hnode->stats_info.stats.user_count = user_count; + hnode->stats_info.stats.delta_user_count = user_count; + if (parent_hnode) { + parent_hnode->stats_info.stats.delta_user_count += user_count; + } else { + hnode->root_id = objagg_hints->root_count++; + hnode->stats_info.is_root = true; + } + hnode->stats_info.objagg_obj = objagg_obj; + + err = rhashtable_insert_fast(&objagg_hints->node_ht, &hnode->ht_node, + objagg_hints->ht_params); + if (err) + goto err_ht_insert; + + list_add(&hnode->list, &objagg_hints->node_list); + hnode->parent = parent_hnode; + objagg_hints->node_count++; + + return hnode; + +err_ht_insert: + kfree(hnode); + return ERR_PTR(err); +} + +static void objagg_hints_flush(struct objagg_hints *objagg_hints) +{ + struct objagg_hints_node *hnode, *tmp; + + list_for_each_entry_safe(hnode, tmp, &objagg_hints->node_list, list) { + list_del(&hnode->list); + rhashtable_remove_fast(&objagg_hints->node_ht, &hnode->ht_node, + objagg_hints->ht_params); + kfree(hnode); + } +} + +struct objagg_tmp_node { + struct objagg_obj *objagg_obj; + bool crossed_out; +}; + +struct objagg_tmp_graph { + struct objagg_tmp_node *nodes; + unsigned long nodes_count; + unsigned long *edges; +}; + +static int objagg_tmp_graph_edge_index(struct objagg_tmp_graph *graph, + int parent_index, int index) +{ + return index * graph->nodes_count + parent_index; +} + +static void objagg_tmp_graph_edge_set(struct objagg_tmp_graph *graph, + int parent_index, int index) +{ + int edge_index = objagg_tmp_graph_edge_index(graph, index, + parent_index); + + __set_bit(edge_index, graph->edges); +} + +static bool objagg_tmp_graph_is_edge(struct objagg_tmp_graph *graph, + int parent_index, int index) +{ + int edge_index = objagg_tmp_graph_edge_index(graph, index, + parent_index); + + return test_bit(edge_index, graph->edges); +} + +static unsigned int objagg_tmp_graph_node_weight(struct objagg_tmp_graph *graph, + unsigned int index) +{ + struct objagg_tmp_node *node = &graph->nodes[index]; + unsigned int weight = node->objagg_obj->stats.user_count; + int j; + + /* Node weight is sum of node users and all other nodes users + * that this node can represent with delta. + */ + + for (j = 0; j < graph->nodes_count; j++) { + if (!objagg_tmp_graph_is_edge(graph, index, j)) + continue; + node = &graph->nodes[j]; + if (node->crossed_out) + continue; + weight += node->objagg_obj->stats.user_count; + } + return weight; +} + +static int objagg_tmp_graph_node_max_weight(struct objagg_tmp_graph *graph) +{ + struct objagg_tmp_node *node; + unsigned int max_weight = 0; + unsigned int weight; + int max_index = -1; + int i; + + for (i = 0; i < graph->nodes_count; i++) { + node = &graph->nodes[i]; + if (node->crossed_out) + continue; + weight = objagg_tmp_graph_node_weight(graph, i); + if (weight >= max_weight) { + max_weight = weight; + max_index = i; + } + } + return max_index; +} + +static struct objagg_tmp_graph *objagg_tmp_graph_create(struct objagg *objagg) +{ + unsigned int nodes_count = objagg->obj_count; + struct objagg_tmp_graph *graph; + struct objagg_tmp_node *node; + struct objagg_tmp_node *pnode; + struct objagg_obj *objagg_obj; + size_t alloc_size; + int i, j; + + graph = kzalloc(sizeof(*graph), GFP_KERNEL); + if (!graph) + return NULL; + + graph->nodes = kcalloc(nodes_count, sizeof(*graph->nodes), GFP_KERNEL); + if (!graph->nodes) + goto err_nodes_alloc; + graph->nodes_count = nodes_count; + + alloc_size = BITS_TO_LONGS(nodes_count * nodes_count) * + sizeof(unsigned long); + graph->edges = kzalloc(alloc_size, GFP_KERNEL); + if (!graph->edges) + goto err_edges_alloc; + + i = 0; + list_for_each_entry(objagg_obj, &objagg->obj_list, list) { + node = &graph->nodes[i++]; + node->objagg_obj = objagg_obj; + } + + /* Assemble a temporary graph. Insert edge X->Y in case Y can be + * in delta of X. + */ + for (i = 0; i < nodes_count; i++) { + for (j = 0; j < nodes_count; j++) { + if (i == j) + continue; + pnode = &graph->nodes[i]; + node = &graph->nodes[j]; + if (objagg->ops->delta_check(objagg->priv, + pnode->objagg_obj->obj, + node->objagg_obj->obj)) { + objagg_tmp_graph_edge_set(graph, i, j); + + } + } + } + return graph; + +err_edges_alloc: + kfree(graph->nodes); +err_nodes_alloc: + kfree(graph); + return NULL; +} + +static void objagg_tmp_graph_destroy(struct objagg_tmp_graph *graph) +{ + kfree(graph->edges); + kfree(graph->nodes); + kfree(graph); +} + +static int +objagg_opt_simple_greedy_fillup_hints(struct objagg_hints *objagg_hints, + struct objagg *objagg) +{ + struct objagg_hints_node *hnode, *parent_hnode; + struct objagg_tmp_graph *graph; + struct objagg_tmp_node *node; + int index; + int j; + int err; + + graph = objagg_tmp_graph_create(objagg); + if (!graph) + return -ENOMEM; + + /* Find the nodes from the ones that can accommodate most users + * and cross them out of the graph. Save them to the hint list. + */ + while ((index = objagg_tmp_graph_node_max_weight(graph)) != -1) { + node = &graph->nodes[index]; + node->crossed_out = true; + hnode = objagg_hints_node_create(objagg_hints, + node->objagg_obj, + objagg->ops->obj_size, + NULL); + if (IS_ERR(hnode)) { + err = PTR_ERR(hnode); + goto out; + } + parent_hnode = hnode; + for (j = 0; j < graph->nodes_count; j++) { + if (!objagg_tmp_graph_is_edge(graph, index, j)) + continue; + node = &graph->nodes[j]; + if (node->crossed_out) + continue; + node->crossed_out = true; + hnode = objagg_hints_node_create(objagg_hints, + node->objagg_obj, + objagg->ops->obj_size, + parent_hnode); + if (IS_ERR(hnode)) { + err = PTR_ERR(hnode); + goto out; + } + } + } + + err = 0; +out: + objagg_tmp_graph_destroy(graph); + return err; +} + +struct objagg_opt_algo { + int (*fillup_hints)(struct objagg_hints *objagg_hints, + struct objagg *objagg); +}; + +static const struct objagg_opt_algo objagg_opt_simple_greedy = { + .fillup_hints = objagg_opt_simple_greedy_fillup_hints, +}; + + +static const struct objagg_opt_algo *objagg_opt_algos[] = { + [OBJAGG_OPT_ALGO_SIMPLE_GREEDY] = &objagg_opt_simple_greedy, +}; + +static int objagg_hints_obj_cmp(struct rhashtable_compare_arg *arg, + const void *obj) +{ + struct rhashtable *ht = arg->ht; + struct objagg_hints *objagg_hints = + container_of(ht, struct objagg_hints, node_ht); + const struct objagg_ops *ops = objagg_hints->ops; + const char *ptr = obj; + + ptr += ht->p.key_offset; + return ops->hints_obj_cmp ? ops->hints_obj_cmp(ptr, arg->key) : + memcmp(ptr, arg->key, ht->p.key_len); +} + +/** + * objagg_hints_get - obtains hints instance + * @objagg: objagg instance + * @opt_algo_type: type of hints finding algorithm + * + * Note: all locking must be provided by the caller. + * + * According to the algo type, the existing objects of objagg instance + * are going to be went-through to assemble an optimal tree. We call this + * tree hints. These hints can be later on used for creation of + * a new objagg instance. There, the future object creations are going + * to be consulted with these hints in order to find out, where exactly + * the new object should be put as a root or delta. + * + * Returns a pointer to hints instance in case of success, + * otherwise it returns pointer error using ERR_PTR macro. + */ +struct objagg_hints *objagg_hints_get(struct objagg *objagg, + enum objagg_opt_algo_type opt_algo_type) +{ + const struct objagg_opt_algo *algo = objagg_opt_algos[opt_algo_type]; + struct objagg_hints *objagg_hints; + int err; + + objagg_hints = kzalloc(sizeof(*objagg_hints), GFP_KERNEL); + if (!objagg_hints) + return ERR_PTR(-ENOMEM); + + objagg_hints->ops = objagg->ops; + objagg_hints->refcount = 1; + + INIT_LIST_HEAD(&objagg_hints->node_list); + + objagg_hints->ht_params.key_len = objagg->ops->obj_size; + objagg_hints->ht_params.key_offset = + offsetof(struct objagg_hints_node, obj); + objagg_hints->ht_params.head_offset = + offsetof(struct objagg_hints_node, ht_node); + objagg_hints->ht_params.obj_cmpfn = objagg_hints_obj_cmp; + + err = rhashtable_init(&objagg_hints->node_ht, &objagg_hints->ht_params); + if (err) + goto err_rhashtable_init; + + err = algo->fillup_hints(objagg_hints, objagg); + if (err) + goto err_fillup_hints; + + if (WARN_ON(objagg_hints->node_count != objagg->obj_count)) { + err = -EINVAL; + goto err_node_count_check; + } + + return objagg_hints; + +err_node_count_check: +err_fillup_hints: + objagg_hints_flush(objagg_hints); + rhashtable_destroy(&objagg_hints->node_ht); +err_rhashtable_init: + kfree(objagg_hints); + return ERR_PTR(err); +} +EXPORT_SYMBOL(objagg_hints_get); + +/** + * objagg_hints_put - puts hints instance + * @objagg_hints: objagg hints instance + * + * Note: all locking must be provided by the caller. + */ +void objagg_hints_put(struct objagg_hints *objagg_hints) +{ + if (--objagg_hints->refcount) + return; + objagg_hints_flush(objagg_hints); + rhashtable_destroy(&objagg_hints->node_ht); + kfree(objagg_hints); +} +EXPORT_SYMBOL(objagg_hints_put); + +/** + * objagg_hints_stats_get - obtains stats of the hints instance + * @objagg_hints: hints instance + * + * Note: all locking must be provided by the caller. + * + * The returned structure contains statistics of all objects + * currently in use, ordered by following rules: + * 1) Root objects are always on lower indexes than the rest. + * 2) Objects with higher delta user count are always on lower + * indexes. + * 3) In case multiple objects have the same delta user count, + * the objects are ordered by user count. + * + * Returns a pointer to stats instance in case of success, + * otherwise it returns pointer error using ERR_PTR macro. + */ +const struct objagg_stats * +objagg_hints_stats_get(struct objagg_hints *objagg_hints) +{ + struct objagg_stats *objagg_stats; + struct objagg_hints_node *hnode; + int i; + + objagg_stats = kzalloc(struct_size(objagg_stats, stats_info, + objagg_hints->node_count), + GFP_KERNEL); + if (!objagg_stats) + return ERR_PTR(-ENOMEM); + + i = 0; + list_for_each_entry(hnode, &objagg_hints->node_list, list) { + memcpy(&objagg_stats->stats_info[i], &hnode->stats_info, + sizeof(objagg_stats->stats_info[0])); + if (objagg_stats->stats_info[i].is_root) + objagg_stats->root_count++; + i++; + } + objagg_stats->stats_info_count = i; + + sort(objagg_stats->stats_info, objagg_stats->stats_info_count, + sizeof(struct objagg_obj_stats_info), + objagg_stats_info_sort_cmp_func, NULL); + + return objagg_stats; +} +EXPORT_SYMBOL(objagg_hints_stats_get); + MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>"); MODULE_DESCRIPTION("Object aggregation manager"); diff --git a/lib/refcount.c b/lib/refcount.c index ebcf8cd49e05..6e904af0fb3e 100644 --- a/lib/refcount.c +++ b/lib/refcount.c @@ -33,6 +33,9 @@ * Note that the allocator is responsible for ordering things between free() * and alloc(). * + * The decrements dec_and_test() and sub_and_test() also provide acquire + * ordering on success. + * */ #include <linux/mutex.h> @@ -164,8 +167,8 @@ EXPORT_SYMBOL(refcount_inc_checked); * at UINT_MAX. * * Provides release memory ordering, such that prior loads and stores are done - * before, and provides a control dependency such that free() must come after. - * See the comment on top. + * before, and provides an acquire ordering on success such that free() + * must come after. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these @@ -190,7 +193,12 @@ bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r) } while (!atomic_try_cmpxchg_release(&r->refs, &val, new)); - return !new; + if (!new) { + smp_acquire__after_ctrl_dep(); + return true; + } + return false; + } EXPORT_SYMBOL(refcount_sub_and_test_checked); @@ -202,8 +210,8 @@ EXPORT_SYMBOL(refcount_sub_and_test_checked); * decrement when saturated at UINT_MAX. * * Provides release memory ordering, such that prior loads and stores are done - * before, and provides a control dependency such that free() must come after. - * See the comment on top. + * before, and provides an acquire ordering on success such that free() + * must come after. * * Return: true if the resulting refcount is 0, false otherwise */ diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 852ffa5160f1..0a105d4af166 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -682,7 +682,7 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_enter); * rhashtable_walk_exit - Free an iterator * @iter: Hash table Iterator * - * This function frees resources allocated by rhashtable_walk_init. + * This function frees resources allocated by rhashtable_walk_enter. */ void rhashtable_walk_exit(struct rhashtable_iter *iter) { diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c index 85925aaa4fff..157d9e31f6c2 100644 --- a/lib/smp_processor_id.c +++ b/lib/smp_processor_id.c @@ -5,10 +5,11 @@ * DEBUG_PREEMPT variant of smp_processor_id(). */ #include <linux/export.h> +#include <linux/kprobes.h> #include <linux/sched.h> -notrace static unsigned int check_preemption_disabled(const char *what1, - const char *what2) +notrace static nokprobe_inline +unsigned int check_preemption_disabled(const char *what1, const char *what2) { int this_cpu = raw_smp_processor_id(); @@ -56,9 +57,11 @@ notrace unsigned int debug_smp_processor_id(void) return check_preemption_disabled("smp_processor_id", ""); } EXPORT_SYMBOL(debug_smp_processor_id); +NOKPROBE_SYMBOL(debug_smp_processor_id); notrace void __this_cpu_preempt_check(const char *op) { check_preemption_disabled("__this_cpu_", op); } EXPORT_SYMBOL(__this_cpu_preempt_check); +NOKPROBE_SYMBOL(__this_cpu_preempt_check); diff --git a/lib/test_bpf.c b/lib/test_bpf.c index f3e570722a7e..0845f635f404 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -6668,12 +6668,14 @@ static int __run_one(const struct bpf_prog *fp, const void *data, u64 start, finish; int ret = 0, i; + preempt_disable(); start = ktime_get_ns(); for (i = 0; i < runs; i++) ret = BPF_PROG_RUN(fp, data); finish = ktime_get_ns(); + preempt_enable(); *duration = finish - start; do_div(*duration, runs); diff --git a/lib/test_firmware.c b/lib/test_firmware.c index 7cab9a9869ac..7222093ee00b 100644 --- a/lib/test_firmware.c +++ b/lib/test_firmware.c @@ -631,11 +631,6 @@ static ssize_t trigger_batched_requests_store(struct device *dev, for (i = 0; i < test_fw_config->num_requests; i++) { req = &test_fw_config->reqs[i]; - if (!req) { - WARN_ON(1); - rc = -ENOMEM; - goto out_bail; - } req->fw = NULL; req->idx = i; req->name = test_fw_config->name; @@ -737,10 +732,6 @@ ssize_t trigger_batched_requests_async_store(struct device *dev, for (i = 0; i < test_fw_config->num_requests; i++) { req = &test_fw_config->reqs[i]; - if (!req) { - WARN_ON(1); - goto out_bail; - } req->name = test_fw_config->name; req->fw = NULL; req->idx = i; diff --git a/lib/test_kasan.c b/lib/test_kasan.c index 51b78405bf24..7de2702621dc 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -480,29 +480,6 @@ static noinline void __init copy_user_test(void) kfree(kmem); } -static noinline void __init use_after_scope_test(void) -{ - volatile char *volatile p; - - pr_info("use-after-scope on int\n"); - { - int local = 0; - - p = (char *)&local; - } - p[0] = 1; - p[3] = 1; - - pr_info("use-after-scope on array\n"); - { - char local[1024] = {0}; - - p = local; - } - p[0] = 1; - p[1023] = 1; -} - static noinline void __init kasan_alloca_oob_left(void) { volatile int i = 10; @@ -682,7 +659,6 @@ static int __init kmalloc_tests_init(void) kasan_alloca_oob_right(); ksize_unpoisons_memory(); copy_user_test(); - use_after_scope_test(); kmem_cache_double_free(); kmem_cache_invalid_free(); kasan_memchr(); diff --git a/lib/test_kmod.c b/lib/test_kmod.c index d82d022111e0..9cf77628fc91 100644 --- a/lib/test_kmod.c +++ b/lib/test_kmod.c @@ -632,7 +632,7 @@ static void __kmod_config_free(struct test_config *config) config->test_driver = NULL; kfree_const(config->test_fs); - config->test_driver = NULL; + config->test_fs = NULL; } static void kmod_config_free(struct kmod_test_device *test_dev) diff --git a/lib/test_objagg.c b/lib/test_objagg.c index ab57144bb0cd..72c1abfa154d 100644 --- a/lib/test_objagg.c +++ b/lib/test_objagg.c @@ -87,6 +87,15 @@ static void world_obj_put(struct world *world, struct objagg *objagg, #define MAX_KEY_ID_DIFF 5 +static bool delta_check(void *priv, const void *parent_obj, const void *obj) +{ + const struct tokey *parent_key = parent_obj; + const struct tokey *key = obj; + int diff = key->id - parent_key->id; + + return diff >= 0 && diff <= MAX_KEY_ID_DIFF; +} + static void *delta_create(void *priv, void *parent_obj, void *obj) { struct tokey *parent_key = parent_obj; @@ -95,7 +104,7 @@ static void *delta_create(void *priv, void *parent_obj, void *obj) int diff = key->id - parent_key->id; struct delta *delta; - if (diff < 0 || diff > MAX_KEY_ID_DIFF) + if (!delta_check(priv, parent_obj, obj)) return ERR_PTR(-EINVAL); delta = kzalloc(sizeof(*delta), GFP_KERNEL); @@ -115,7 +124,7 @@ static void delta_destroy(void *priv, void *delta_priv) kfree(delta); } -static void *root_create(void *priv, void *obj) +static void *root_create(void *priv, void *obj, unsigned int id) { struct world *world = priv; struct tokey *key = obj; @@ -268,6 +277,12 @@ stats_put: return err; } +static bool delta_check_dummy(void *priv, const void *parent_obj, + const void *obj) +{ + return false; +} + static void *delta_create_dummy(void *priv, void *parent_obj, void *obj) { return ERR_PTR(-EOPNOTSUPP); @@ -279,6 +294,7 @@ static void delta_destroy_dummy(void *priv, void *delta_priv) static const struct objagg_ops nodelta_ops = { .obj_size = sizeof(struct tokey), + .delta_check = delta_check_dummy, .delta_create = delta_create_dummy, .delta_destroy = delta_destroy_dummy, .root_create = root_create, @@ -292,7 +308,7 @@ static int test_nodelta(void) int i; int err; - objagg = objagg_create(&nodelta_ops, &world); + objagg = objagg_create(&nodelta_ops, NULL, &world); if (IS_ERR(objagg)) return PTR_ERR(objagg); @@ -357,6 +373,7 @@ err_stats_second_zero: static const struct objagg_ops delta_ops = { .obj_size = sizeof(struct tokey), + .delta_check = delta_check, .delta_create = delta_create, .delta_destroy = delta_destroy, .root_create = root_create, @@ -728,8 +745,10 @@ static int check_expect_stats(struct objagg *objagg, int err; stats = objagg_stats_get(objagg); - if (IS_ERR(stats)) + if (IS_ERR(stats)) { + *errmsg = "objagg_stats_get() failed."; return PTR_ERR(stats); + } err = __check_expect_stats(stats, expect_stats, errmsg); objagg_stats_put(stats); return err; @@ -769,7 +788,6 @@ static int test_delta_action_item(struct world *world, if (err) goto errout; - errmsg = NULL; err = check_expect_stats(objagg, &action_item->expect_stats, &errmsg); if (err) { pr_err("Key %u: Stats: %s\n", action_item->key_id, errmsg); @@ -793,7 +811,7 @@ static int test_delta(void) int i; int err; - objagg = objagg_create(&delta_ops, &world); + objagg = objagg_create(&delta_ops, NULL, &world); if (IS_ERR(objagg)) return PTR_ERR(objagg); @@ -815,6 +833,170 @@ err_do_action_item: return err; } +struct hints_case { + const unsigned int *key_ids; + size_t key_ids_count; + struct expect_stats expect_stats; + struct expect_stats expect_stats_hints; +}; + +static const unsigned int hints_case_key_ids[] = { + 1, 7, 3, 5, 3, 1, 30, 8, 8, 5, 6, 8, +}; + +static const struct hints_case hints_case = { + .key_ids = hints_case_key_ids, + .key_ids_count = ARRAY_SIZE(hints_case_key_ids), + .expect_stats = + EXPECT_STATS(7, ROOT(1, 2, 7), ROOT(7, 1, 4), ROOT(30, 1, 1), + DELTA(8, 3), DELTA(3, 2), + DELTA(5, 2), DELTA(6, 1)), + .expect_stats_hints = + EXPECT_STATS(7, ROOT(3, 2, 9), ROOT(1, 2, 2), ROOT(30, 1, 1), + DELTA(8, 3), DELTA(5, 2), + DELTA(6, 1), DELTA(7, 1)), +}; + +static void __pr_debug_stats(const struct objagg_stats *stats) +{ + int i; + + for (i = 0; i < stats->stats_info_count; i++) + pr_debug("Stat index %d key %u: u %d, d %d, %s\n", i, + obj_to_key_id(stats->stats_info[i].objagg_obj), + stats->stats_info[i].stats.user_count, + stats->stats_info[i].stats.delta_user_count, + stats->stats_info[i].is_root ? "root" : "noroot"); +} + +static void pr_debug_stats(struct objagg *objagg) +{ + const struct objagg_stats *stats; + + stats = objagg_stats_get(objagg); + if (IS_ERR(stats)) + return; + __pr_debug_stats(stats); + objagg_stats_put(stats); +} + +static void pr_debug_hints_stats(struct objagg_hints *objagg_hints) +{ + const struct objagg_stats *stats; + + stats = objagg_hints_stats_get(objagg_hints); + if (IS_ERR(stats)) + return; + __pr_debug_stats(stats); + objagg_stats_put(stats); +} + +static int check_expect_hints_stats(struct objagg_hints *objagg_hints, + const struct expect_stats *expect_stats, + const char **errmsg) +{ + const struct objagg_stats *stats; + int err; + + stats = objagg_hints_stats_get(objagg_hints); + if (IS_ERR(stats)) + return PTR_ERR(stats); + err = __check_expect_stats(stats, expect_stats, errmsg); + objagg_stats_put(stats); + return err; +} + +static int test_hints_case(const struct hints_case *hints_case) +{ + struct objagg_obj *objagg_obj; + struct objagg_hints *hints; + struct world world2 = {}; + struct world world = {}; + struct objagg *objagg2; + struct objagg *objagg; + const char *errmsg; + int i; + int err; + + objagg = objagg_create(&delta_ops, NULL, &world); + if (IS_ERR(objagg)) + return PTR_ERR(objagg); + + for (i = 0; i < hints_case->key_ids_count; i++) { + objagg_obj = world_obj_get(&world, objagg, + hints_case->key_ids[i]); + if (IS_ERR(objagg_obj)) { + err = PTR_ERR(objagg_obj); + goto err_world_obj_get; + } + } + + pr_debug_stats(objagg); + err = check_expect_stats(objagg, &hints_case->expect_stats, &errmsg); + if (err) { + pr_err("Stats: %s\n", errmsg); + goto err_check_expect_stats; + } + + hints = objagg_hints_get(objagg, OBJAGG_OPT_ALGO_SIMPLE_GREEDY); + if (IS_ERR(hints)) { + err = PTR_ERR(hints); + goto err_hints_get; + } + + pr_debug_hints_stats(hints); + err = check_expect_hints_stats(hints, &hints_case->expect_stats_hints, + &errmsg); + if (err) { + pr_err("Hints stats: %s\n", errmsg); + goto err_check_expect_hints_stats; + } + + objagg2 = objagg_create(&delta_ops, hints, &world2); + if (IS_ERR(objagg2)) + return PTR_ERR(objagg2); + + for (i = 0; i < hints_case->key_ids_count; i++) { + objagg_obj = world_obj_get(&world2, objagg2, + hints_case->key_ids[i]); + if (IS_ERR(objagg_obj)) { + err = PTR_ERR(objagg_obj); + goto err_world2_obj_get; + } + } + + pr_debug_stats(objagg2); + err = check_expect_stats(objagg2, &hints_case->expect_stats_hints, + &errmsg); + if (err) { + pr_err("Stats2: %s\n", errmsg); + goto err_check_expect_stats2; + } + + err = 0; + +err_check_expect_stats2: +err_world2_obj_get: + for (i--; i >= 0; i--) + world_obj_put(&world2, objagg, hints_case->key_ids[i]); + objagg_hints_put(hints); + objagg_destroy(objagg2); + i = hints_case->key_ids_count; +err_check_expect_hints_stats: +err_hints_get: +err_check_expect_stats: +err_world_obj_get: + for (i--; i >= 0; i--) + world_obj_put(&world, objagg, hints_case->key_ids[i]); + + objagg_destroy(objagg); + return err; +} +static int test_hints(void) +{ + return test_hints_case(&hints_case); +} + static int __init test_objagg_init(void) { int err; @@ -822,7 +1004,10 @@ static int __init test_objagg_init(void) err = test_nodelta(); if (err) return err; - return test_delta(); + err = test_delta(); + if (err) + return err; + return test_hints(); } static void __exit test_objagg_exit(void) diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index 6a8ac7626797..3bd2e91bfc29 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -177,16 +177,11 @@ static int __init test_rht_lookup(struct rhashtable *ht, struct test_obj *array, static void test_bucket_stats(struct rhashtable *ht, unsigned int entries) { - unsigned int err, total = 0, chain_len = 0; + unsigned int total = 0, chain_len = 0; struct rhashtable_iter hti; struct rhash_head *pos; - err = rhashtable_walk_init(ht, &hti, GFP_KERNEL); - if (err) { - pr_warn("Test failed: allocation error"); - return; - } - + rhashtable_walk_enter(ht, &hti); rhashtable_walk_start(&hti); while ((pos = rhashtable_walk_next(&hti))) { @@ -395,7 +390,7 @@ static int __init test_rhltable(unsigned int entries) if (WARN(err, "cannot remove element at slot %d", i)) continue; } else { - if (WARN(err != -ENOENT, "removed non-existant element %d, error %d not %d", + if (WARN(err != -ENOENT, "removed non-existent element %d, error %d not %d", i, err, -ENOENT)) continue; } @@ -440,7 +435,7 @@ static int __init test_rhltable(unsigned int entries) if (WARN(err, "cannot remove element at slot %d", i)) continue; } else { - if (WARN(err != -ENOENT, "removed non-existant element, error %d not %d", + if (WARN(err != -ENOENT, "removed non-existent element, error %d not %d", err, -ENOENT)) continue; } @@ -541,38 +536,45 @@ static unsigned int __init print_ht(struct rhltable *rhlt) static int __init test_insert_dup(struct test_obj_rhl *rhl_test_objects, int cnt, bool slow) { - struct rhltable rhlt; + struct rhltable *rhlt; unsigned int i, ret; const char *key; int err = 0; - err = rhltable_init(&rhlt, &test_rht_params_dup); - if (WARN_ON(err)) + rhlt = kmalloc(sizeof(*rhlt), GFP_KERNEL); + if (WARN_ON(!rhlt)) + return -EINVAL; + + err = rhltable_init(rhlt, &test_rht_params_dup); + if (WARN_ON(err)) { + kfree(rhlt); return err; + } for (i = 0; i < cnt; i++) { rhl_test_objects[i].value.tid = i; - key = rht_obj(&rhlt.ht, &rhl_test_objects[i].list_node.rhead); + key = rht_obj(&rhlt->ht, &rhl_test_objects[i].list_node.rhead); key += test_rht_params_dup.key_offset; if (slow) { - err = PTR_ERR(rhashtable_insert_slow(&rhlt.ht, key, + err = PTR_ERR(rhashtable_insert_slow(&rhlt->ht, key, &rhl_test_objects[i].list_node.rhead)); if (err == -EAGAIN) err = 0; } else - err = rhltable_insert(&rhlt, + err = rhltable_insert(rhlt, &rhl_test_objects[i].list_node, test_rht_params_dup); if (WARN(err, "error %d on element %d/%d (%s)\n", err, i, cnt, slow? "slow" : "fast")) goto skip_print; } - ret = print_ht(&rhlt); + ret = print_ht(rhlt); WARN(ret != cnt, "missing rhltable elements (%d != %d, %s)\n", ret, cnt, slow? "slow" : "fast"); skip_print: - rhltable_destroy(&rhlt); + rhltable_destroy(rhlt); + kfree(rhlt); return 0; } diff --git a/lib/test_ubsan.c b/lib/test_ubsan.c index 280f4979d00e..9ea10adf7a66 100644 --- a/lib/test_ubsan.c +++ b/lib/test_ubsan.c @@ -42,14 +42,6 @@ static void test_ubsan_divrem_overflow(void) val /= val2; } -static void test_ubsan_vla_bound_not_positive(void) -{ - volatile int size = -1; - char buf[size]; - - (void)buf; -} - static void test_ubsan_shift_out_of_bounds(void) { volatile int val = -1; @@ -61,7 +53,7 @@ static void test_ubsan_shift_out_of_bounds(void) static void test_ubsan_out_of_bounds(void) { volatile int i = 4, j = 5; - volatile int arr[i]; + volatile int arr[4]; arr[j] = i; } @@ -113,7 +105,6 @@ static const test_ubsan_fp test_ubsan_array[] = { test_ubsan_mul_overflow, test_ubsan_negate_overflow, test_ubsan_divrem_overflow, - test_ubsan_vla_bound_not_positive, test_ubsan_shift_out_of_bounds, test_ubsan_out_of_bounds, test_ubsan_load_invalid_value, diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c new file mode 100644 index 000000000000..83cdcaa82bf6 --- /dev/null +++ b/lib/test_vmalloc.c @@ -0,0 +1,551 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Test module for stress and analyze performance of vmalloc allocator. + * (C) 2018 Uladzislau Rezki (Sony) <urezki@gmail.com> + */ +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/vmalloc.h> +#include <linux/random.h> +#include <linux/kthread.h> +#include <linux/moduleparam.h> +#include <linux/completion.h> +#include <linux/delay.h> +#include <linux/rwsem.h> +#include <linux/mm.h> + +#define __param(type, name, init, msg) \ + static type name = init; \ + module_param(name, type, 0444); \ + MODULE_PARM_DESC(name, msg) \ + +__param(bool, single_cpu_test, false, + "Use single first online CPU to run tests"); + +__param(bool, sequential_test_order, false, + "Use sequential stress tests order"); + +__param(int, test_repeat_count, 1, + "Set test repeat counter"); + +__param(int, test_loop_count, 1000000, + "Set test loop counter"); + +__param(int, run_test_mask, INT_MAX, + "Set tests specified in the mask.\n\n" + "\t\tid: 1, name: fix_size_alloc_test\n" + "\t\tid: 2, name: full_fit_alloc_test\n" + "\t\tid: 4, name: long_busy_list_alloc_test\n" + "\t\tid: 8, name: random_size_alloc_test\n" + "\t\tid: 16, name: fix_align_alloc_test\n" + "\t\tid: 32, name: random_size_align_alloc_test\n" + "\t\tid: 64, name: align_shift_alloc_test\n" + "\t\tid: 128, name: pcpu_alloc_test\n" + /* Add a new test case description here. */ +); + +/* + * Depends on single_cpu_test parameter. If it is true, then + * use first online CPU to trigger a test on, otherwise go with + * all online CPUs. + */ +static cpumask_t cpus_run_test_mask = CPU_MASK_NONE; + +/* + * Read write semaphore for synchronization of setup + * phase that is done in main thread and workers. + */ +static DECLARE_RWSEM(prepare_for_test_rwsem); + +/* + * Completion tracking for worker threads. + */ +static DECLARE_COMPLETION(test_all_done_comp); +static atomic_t test_n_undone = ATOMIC_INIT(0); + +static inline void +test_report_one_done(void) +{ + if (atomic_dec_and_test(&test_n_undone)) + complete(&test_all_done_comp); +} + +static int random_size_align_alloc_test(void) +{ + unsigned long size, align, rnd; + void *ptr; + int i; + + for (i = 0; i < test_loop_count; i++) { + get_random_bytes(&rnd, sizeof(rnd)); + + /* + * Maximum 1024 pages, if PAGE_SIZE is 4096. + */ + align = 1 << (rnd % 23); + + /* + * Maximum 10 pages. + */ + size = ((rnd % 10) + 1) * PAGE_SIZE; + + ptr = __vmalloc_node_range(size, align, + VMALLOC_START, VMALLOC_END, + GFP_KERNEL | __GFP_ZERO, + PAGE_KERNEL, + 0, 0, __builtin_return_address(0)); + + if (!ptr) + return -1; + + vfree(ptr); + } + + return 0; +} + +/* + * This test case is supposed to be failed. + */ +static int align_shift_alloc_test(void) +{ + unsigned long align; + void *ptr; + int i; + + for (i = 0; i < BITS_PER_LONG; i++) { + align = ((unsigned long) 1) << i; + + ptr = __vmalloc_node_range(PAGE_SIZE, align, + VMALLOC_START, VMALLOC_END, + GFP_KERNEL | __GFP_ZERO, + PAGE_KERNEL, + 0, 0, __builtin_return_address(0)); + + if (!ptr) + return -1; + + vfree(ptr); + } + + return 0; +} + +static int fix_align_alloc_test(void) +{ + void *ptr; + int i; + + for (i = 0; i < test_loop_count; i++) { + ptr = __vmalloc_node_range(5 * PAGE_SIZE, + THREAD_ALIGN << 1, + VMALLOC_START, VMALLOC_END, + GFP_KERNEL | __GFP_ZERO, + PAGE_KERNEL, + 0, 0, __builtin_return_address(0)); + + if (!ptr) + return -1; + + vfree(ptr); + } + + return 0; +} + +static int random_size_alloc_test(void) +{ + unsigned int n; + void *p; + int i; + + for (i = 0; i < test_loop_count; i++) { + get_random_bytes(&n, sizeof(i)); + n = (n % 100) + 1; + + p = vmalloc(n * PAGE_SIZE); + + if (!p) + return -1; + + *((__u8 *)p) = 1; + vfree(p); + } + + return 0; +} + +static int long_busy_list_alloc_test(void) +{ + void *ptr_1, *ptr_2; + void **ptr; + int rv = -1; + int i; + + ptr = vmalloc(sizeof(void *) * 15000); + if (!ptr) + return rv; + + for (i = 0; i < 15000; i++) + ptr[i] = vmalloc(1 * PAGE_SIZE); + + for (i = 0; i < test_loop_count; i++) { + ptr_1 = vmalloc(100 * PAGE_SIZE); + if (!ptr_1) + goto leave; + + ptr_2 = vmalloc(1 * PAGE_SIZE); + if (!ptr_2) { + vfree(ptr_1); + goto leave; + } + + *((__u8 *)ptr_1) = 0; + *((__u8 *)ptr_2) = 1; + + vfree(ptr_1); + vfree(ptr_2); + } + + /* Success */ + rv = 0; + +leave: + for (i = 0; i < 15000; i++) + vfree(ptr[i]); + + vfree(ptr); + return rv; +} + +static int full_fit_alloc_test(void) +{ + void **ptr, **junk_ptr, *tmp; + int junk_length; + int rv = -1; + int i; + + junk_length = fls(num_online_cpus()); + junk_length *= (32 * 1024 * 1024 / PAGE_SIZE); + + ptr = vmalloc(sizeof(void *) * junk_length); + if (!ptr) + return rv; + + junk_ptr = vmalloc(sizeof(void *) * junk_length); + if (!junk_ptr) { + vfree(ptr); + return rv; + } + + for (i = 0; i < junk_length; i++) { + ptr[i] = vmalloc(1 * PAGE_SIZE); + junk_ptr[i] = vmalloc(1 * PAGE_SIZE); + } + + for (i = 0; i < junk_length; i++) + vfree(junk_ptr[i]); + + for (i = 0; i < test_loop_count; i++) { + tmp = vmalloc(1 * PAGE_SIZE); + + if (!tmp) + goto error; + + *((__u8 *)tmp) = 1; + vfree(tmp); + } + + /* Success */ + rv = 0; + +error: + for (i = 0; i < junk_length; i++) + vfree(ptr[i]); + + vfree(ptr); + vfree(junk_ptr); + + return rv; +} + +static int fix_size_alloc_test(void) +{ + void *ptr; + int i; + + for (i = 0; i < test_loop_count; i++) { + ptr = vmalloc(3 * PAGE_SIZE); + + if (!ptr) + return -1; + + *((__u8 *)ptr) = 0; + + vfree(ptr); + } + + return 0; +} + +static int +pcpu_alloc_test(void) +{ + int rv = 0; +#ifndef CONFIG_NEED_PER_CPU_KM + void __percpu **pcpu; + size_t size, align; + int i; + + pcpu = vmalloc(sizeof(void __percpu *) * 35000); + if (!pcpu) + return -1; + + for (i = 0; i < 35000; i++) { + unsigned int r; + + get_random_bytes(&r, sizeof(i)); + size = (r % (PAGE_SIZE / 4)) + 1; + + /* + * Maximum PAGE_SIZE + */ + get_random_bytes(&r, sizeof(i)); + align = 1 << ((i % 11) + 1); + + pcpu[i] = __alloc_percpu(size, align); + if (!pcpu[i]) + rv = -1; + } + + for (i = 0; i < 35000; i++) + free_percpu(pcpu[i]); + + vfree(pcpu); +#endif + return rv; +} + +struct test_case_desc { + const char *test_name; + int (*test_func)(void); +}; + +static struct test_case_desc test_case_array[] = { + { "fix_size_alloc_test", fix_size_alloc_test }, + { "full_fit_alloc_test", full_fit_alloc_test }, + { "long_busy_list_alloc_test", long_busy_list_alloc_test }, + { "random_size_alloc_test", random_size_alloc_test }, + { "fix_align_alloc_test", fix_align_alloc_test }, + { "random_size_align_alloc_test", random_size_align_alloc_test }, + { "align_shift_alloc_test", align_shift_alloc_test }, + { "pcpu_alloc_test", pcpu_alloc_test }, + /* Add a new test case here. */ +}; + +struct test_case_data { + int test_failed; + int test_passed; + u64 time; +}; + +/* Split it to get rid of: WARNING: line over 80 characters */ +static struct test_case_data + per_cpu_test_data[NR_CPUS][ARRAY_SIZE(test_case_array)]; + +static struct test_driver { + struct task_struct *task; + unsigned long start; + unsigned long stop; + int cpu; +} per_cpu_test_driver[NR_CPUS]; + +static void shuffle_array(int *arr, int n) +{ + unsigned int rnd; + int i, j, x; + + for (i = n - 1; i > 0; i--) { + get_random_bytes(&rnd, sizeof(rnd)); + + /* Cut the range. */ + j = rnd % i; + + /* Swap indexes. */ + x = arr[i]; + arr[i] = arr[j]; + arr[j] = x; + } +} + +static int test_func(void *private) +{ + struct test_driver *t = private; + cpumask_t newmask = CPU_MASK_NONE; + int random_array[ARRAY_SIZE(test_case_array)]; + int index, i, j, ret; + ktime_t kt; + u64 delta; + + cpumask_set_cpu(t->cpu, &newmask); + set_cpus_allowed_ptr(current, &newmask); + + for (i = 0; i < ARRAY_SIZE(test_case_array); i++) + random_array[i] = i; + + if (!sequential_test_order) + shuffle_array(random_array, ARRAY_SIZE(test_case_array)); + + /* + * Block until initialization is done. + */ + down_read(&prepare_for_test_rwsem); + + t->start = get_cycles(); + for (i = 0; i < ARRAY_SIZE(test_case_array); i++) { + index = random_array[i]; + + /* + * Skip tests if run_test_mask has been specified. + */ + if (!((run_test_mask & (1 << index)) >> index)) + continue; + + kt = ktime_get(); + for (j = 0; j < test_repeat_count; j++) { + ret = test_case_array[index].test_func(); + if (!ret) + per_cpu_test_data[t->cpu][index].test_passed++; + else + per_cpu_test_data[t->cpu][index].test_failed++; + } + + /* + * Take an average time that test took. + */ + delta = (u64) ktime_us_delta(ktime_get(), kt); + do_div(delta, (u32) test_repeat_count); + + per_cpu_test_data[t->cpu][index].time = delta; + } + t->stop = get_cycles(); + + up_read(&prepare_for_test_rwsem); + test_report_one_done(); + + /* + * Wait for the kthread_stop() call. + */ + while (!kthread_should_stop()) + msleep(10); + + return 0; +} + +static void +init_test_configurtion(void) +{ + /* + * Reset all data of all CPUs. + */ + memset(per_cpu_test_data, 0, sizeof(per_cpu_test_data)); + + if (single_cpu_test) + cpumask_set_cpu(cpumask_first(cpu_online_mask), + &cpus_run_test_mask); + else + cpumask_and(&cpus_run_test_mask, cpu_online_mask, + cpu_online_mask); + + if (test_repeat_count <= 0) + test_repeat_count = 1; + + if (test_loop_count <= 0) + test_loop_count = 1; +} + +static void do_concurrent_test(void) +{ + int cpu, ret; + + /* + * Set some basic configurations plus sanity check. + */ + init_test_configurtion(); + + /* + * Put on hold all workers. + */ + down_write(&prepare_for_test_rwsem); + + for_each_cpu(cpu, &cpus_run_test_mask) { + struct test_driver *t = &per_cpu_test_driver[cpu]; + + t->cpu = cpu; + t->task = kthread_run(test_func, t, "vmalloc_test/%d", cpu); + + if (!IS_ERR(t->task)) + /* Success. */ + atomic_inc(&test_n_undone); + else + pr_err("Failed to start kthread for %d CPU\n", cpu); + } + + /* + * Now let the workers do their job. + */ + up_write(&prepare_for_test_rwsem); + + /* + * Sleep quiet until all workers are done with 1 second + * interval. Since the test can take a lot of time we + * can run into a stack trace of the hung task. That is + * why we go with completion_timeout and HZ value. + */ + do { + ret = wait_for_completion_timeout(&test_all_done_comp, HZ); + } while (!ret); + + for_each_cpu(cpu, &cpus_run_test_mask) { + struct test_driver *t = &per_cpu_test_driver[cpu]; + int i; + + if (!IS_ERR(t->task)) + kthread_stop(t->task); + + for (i = 0; i < ARRAY_SIZE(test_case_array); i++) { + if (!((run_test_mask & (1 << i)) >> i)) + continue; + + pr_info( + "Summary: %s passed: %d failed: %d repeat: %d loops: %d avg: %llu usec\n", + test_case_array[i].test_name, + per_cpu_test_data[cpu][i].test_passed, + per_cpu_test_data[cpu][i].test_failed, + test_repeat_count, test_loop_count, + per_cpu_test_data[cpu][i].time); + } + + pr_info("All test took CPU%d=%lu cycles\n", + cpu, t->stop - t->start); + } +} + +static int vmalloc_test_init(void) +{ + do_concurrent_test(); + return -EAGAIN; /* Fail will directly unload the module */ +} + +static void vmalloc_test_exit(void) +{ +} + +module_init(vmalloc_test_init) +module_exit(vmalloc_test_exit) + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Uladzislau Rezki"); +MODULE_DESCRIPTION("vmalloc test module"); diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 4676c0a1eeca..c596a957f764 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -199,7 +199,7 @@ static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index) XA_BUG_ON(xa, xa_store_index(xa, index + 1, GFP_KERNEL)); xa_set_mark(xa, index + 1, XA_MARK_0); XA_BUG_ON(xa, xa_store_index(xa, index + 2, GFP_KERNEL)); - xa_set_mark(xa, index + 2, XA_MARK_1); + xa_set_mark(xa, index + 2, XA_MARK_2); XA_BUG_ON(xa, xa_store_index(xa, next, GFP_KERNEL)); xa_store_order(xa, index, order, xa_mk_index(index), GFP_KERNEL); @@ -209,8 +209,8 @@ static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index) void *entry; XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_0)); - XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_1)); - XA_BUG_ON(xa, xa_get_mark(xa, i, XA_MARK_2)); + XA_BUG_ON(xa, xa_get_mark(xa, i, XA_MARK_1)); + XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_2)); /* We should see two elements in the array */ rcu_read_lock(); @@ -357,7 +357,7 @@ static noinline void check_cmpxchg(struct xarray *xa) static noinline void check_reserve(struct xarray *xa) { void *entry; - unsigned long index = 0; + unsigned long index; /* An array with a reserved entry is not empty */ XA_BUG_ON(xa, !xa_empty(xa)); @@ -382,10 +382,12 @@ static noinline void check_reserve(struct xarray *xa) xa_erase_index(xa, 12345678); XA_BUG_ON(xa, !xa_empty(xa)); - /* And so does xa_insert */ + /* But xa_insert does not */ xa_reserve(xa, 12345678, GFP_KERNEL); - XA_BUG_ON(xa, xa_insert(xa, 12345678, xa_mk_value(12345678), 0) != 0); - xa_erase_index(xa, 12345678); + XA_BUG_ON(xa, xa_insert(xa, 12345678, xa_mk_value(12345678), 0) != + -EEXIST); + XA_BUG_ON(xa, xa_empty(xa)); + XA_BUG_ON(xa, xa_erase(xa, 12345678) != NULL); XA_BUG_ON(xa, !xa_empty(xa)); /* Can iterate through a reserved entry */ @@ -393,7 +395,7 @@ static noinline void check_reserve(struct xarray *xa) xa_reserve(xa, 6, GFP_KERNEL); xa_store_index(xa, 7, GFP_KERNEL); - xa_for_each(xa, entry, index, ULONG_MAX, XA_PRESENT) { + xa_for_each(xa, index, entry) { XA_BUG_ON(xa, index != 5 && index != 7); } xa_destroy(xa); @@ -812,17 +814,16 @@ static noinline void check_find_1(struct xarray *xa) static noinline void check_find_2(struct xarray *xa) { void *entry; - unsigned long i, j, index = 0; + unsigned long i, j, index; - xa_for_each(xa, entry, index, ULONG_MAX, XA_PRESENT) { + xa_for_each(xa, index, entry) { XA_BUG_ON(xa, true); } for (i = 0; i < 1024; i++) { xa_store_index(xa, index, GFP_KERNEL); j = 0; - index = 0; - xa_for_each(xa, entry, index, ULONG_MAX, XA_PRESENT) { + xa_for_each(xa, index, entry) { XA_BUG_ON(xa, xa_mk_index(index) != entry); XA_BUG_ON(xa, index != j++); } @@ -839,6 +840,7 @@ static noinline void check_find_3(struct xarray *xa) for (i = 0; i < 100; i++) { for (j = 0; j < 100; j++) { + rcu_read_lock(); for (k = 0; k < 100; k++) { xas_set(&xas, j); xas_for_each_marked(&xas, entry, k, XA_MARK_0) @@ -847,6 +849,7 @@ static noinline void check_find_3(struct xarray *xa) XA_BUG_ON(xa, xas.xa_node != XAS_RESTART); } + rcu_read_unlock(); } xa_store_index(xa, i, GFP_KERNEL); xa_set_mark(xa, i, XA_MARK_0); @@ -1183,6 +1186,35 @@ static noinline void check_store_range(struct xarray *xa) } } +static void check_align_1(struct xarray *xa, char *name) +{ + int i; + unsigned int id; + unsigned long index; + void *entry; + + for (i = 0; i < 8; i++) { + id = 0; + XA_BUG_ON(xa, xa_alloc(xa, &id, UINT_MAX, name + i, GFP_KERNEL) + != 0); + XA_BUG_ON(xa, id != i); + } + xa_for_each(xa, index, entry) + XA_BUG_ON(xa, xa_is_err(entry)); + xa_destroy(xa); +} + +static noinline void check_align(struct xarray *xa) +{ + char name[] = "Motorola 68000"; + + check_align_1(xa, name); + check_align_1(xa, name + 1); + check_align_1(xa, name + 2); + check_align_1(xa, name + 3); +// check_align_2(xa, name); +} + static LIST_HEAD(shadow_nodes); static void test_update_node(struct xa_node *node) @@ -1332,6 +1364,7 @@ static int xarray_checks(void) check_create_range(&array); check_store_range(&array); check_store_iter(&array); + check_align(&xa0); check_workingset(&array, 0); check_workingset(&array, 64); diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 3add92329bae..30b00de4f321 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -17,6 +17,7 @@ */ #include <stdarg.h> +#include <linux/build_bug.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/module.h> /* for KSYM_SYMBOL_LEN */ @@ -405,6 +406,8 @@ struct printf_spec { unsigned int base:8; /* number base, 8, 10 or 16 only */ signed int precision:16; /* # of digits/chars */ } __packed; +static_assert(sizeof(struct printf_spec) == 8); + #define FIELD_WIDTH_MAX ((1 << 23) - 1) #define PRECISION_MAX ((1 << 15) - 1) @@ -422,8 +425,6 @@ char *number(char *buf, char *end, unsigned long long num, int field_width = spec.field_width; int precision = spec.precision; - BUILD_BUG_ON(sizeof(struct printf_spec) != 8); - /* locase = 0 or 0x20. ORing digits or letters with 'locase' * produces same digits or (maybe lowercased) letters */ locase = (spec.flags & SMALL); diff --git a/lib/xarray.c b/lib/xarray.c index 5f3f9311de89..81c3171ddde9 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -232,6 +232,8 @@ void *xas_load(struct xa_state *xas) if (xas->xa_shift > node->shift) break; entry = xas_descend(xas, node); + if (node->shift == 0) + break; } return entry; } @@ -506,7 +508,7 @@ static void xas_free_nodes(struct xa_state *xas, struct xa_node *top) for (;;) { void *entry = xa_entry_locked(xas->xa, node, offset); - if (xa_is_node(entry)) { + if (node->shift && xa_is_node(entry)) { node = xa_to_node(entry); offset = 0; continue; @@ -604,6 +606,7 @@ static int xas_expand(struct xa_state *xas, void *head) /* * xas_create() - Create a slot to store an entry in. * @xas: XArray operation state. + * @allow_root: %true if we can store the entry in the root directly * * Most users will not need to call this function directly, as it is called * by xas_store(). It is useful for doing conditional store operations @@ -613,7 +616,7 @@ static int xas_expand(struct xa_state *xas, void *head) * If the slot was newly created, returns %NULL. If it failed to create the * slot, returns %NULL and indicates the error in @xas. */ -static void *xas_create(struct xa_state *xas) +static void *xas_create(struct xa_state *xas, bool allow_root) { struct xarray *xa = xas->xa; void *entry; @@ -628,6 +631,8 @@ static void *xas_create(struct xa_state *xas) shift = xas_expand(xas, entry); if (shift < 0) return NULL; + if (!shift && !allow_root) + shift = XA_CHUNK_SHIFT; entry = xa_head_locked(xa); slot = &xa->xa_head; } else if (xas_error(xas)) { @@ -687,7 +692,7 @@ void xas_create_range(struct xa_state *xas) xas->xa_sibs = 0; for (;;) { - xas_create(xas); + xas_create(xas, true); if (xas_error(xas)) goto restore; if (xas->xa_index <= (index | XA_CHUNK_MASK)) @@ -754,7 +759,7 @@ void *xas_store(struct xa_state *xas, void *entry) bool value = xa_is_value(entry); if (entry) - first = xas_create(xas); + first = xas_create(xas, !xa_is_node(entry)); else first = xas_load(xas); @@ -1251,35 +1256,6 @@ void *xas_find_conflict(struct xa_state *xas) EXPORT_SYMBOL_GPL(xas_find_conflict); /** - * xa_init_flags() - Initialise an empty XArray with flags. - * @xa: XArray. - * @flags: XA_FLAG values. - * - * If you need to initialise an XArray with special flags (eg you need - * to take the lock from interrupt context), use this function instead - * of xa_init(). - * - * Context: Any context. - */ -void xa_init_flags(struct xarray *xa, gfp_t flags) -{ - unsigned int lock_type; - static struct lock_class_key xa_lock_irq; - static struct lock_class_key xa_lock_bh; - - spin_lock_init(&xa->xa_lock); - xa->xa_flags = flags; - xa->xa_head = NULL; - - lock_type = xa_lock_type(xa); - if (lock_type == XA_LOCK_IRQ) - lockdep_set_class(&xa->xa_lock, &xa_lock_irq); - else if (lock_type == XA_LOCK_BH) - lockdep_set_class(&xa->xa_lock, &xa_lock_bh); -} -EXPORT_SYMBOL(xa_init_flags); - -/** * xa_load() - Load an entry from an XArray. * @xa: XArray. * @index: index into array. @@ -1308,7 +1284,6 @@ static void *xas_result(struct xa_state *xas, void *curr) { if (xa_is_zero(curr)) return NULL; - XA_NODE_BUG_ON(xas->xa_node, xa_is_internal(curr)); if (xas_error(xas)) curr = xas->xa_node; return curr; @@ -1378,7 +1353,7 @@ void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) XA_STATE(xas, xa, index); void *curr; - if (WARN_ON_ONCE(xa_is_internal(entry))) + if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); if (xa_track_free(xa) && !entry) entry = XA_ZERO_ENTRY; @@ -1444,7 +1419,7 @@ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, XA_STATE(xas, xa, index); void *curr; - if (WARN_ON_ONCE(xa_is_internal(entry))) + if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); if (xa_track_free(xa) && !entry) entry = XA_ZERO_ENTRY; @@ -1465,6 +1440,47 @@ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, EXPORT_SYMBOL(__xa_cmpxchg); /** + * __xa_insert() - Store this entry in the XArray if no entry is present. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Inserting a NULL entry will store a reserved entry (like xa_reserve()) + * if no entry is present. Inserting will fail if a reserved entry is + * present, even though loading from this index will return NULL. + * + * Context: Any context. Expects xa_lock to be held on entry. May + * release and reacquire xa_lock if @gfp flags permit. + * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * -ENOMEM if memory could not be allocated. + */ +int __xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) +{ + XA_STATE(xas, xa, index); + void *curr; + + if (WARN_ON_ONCE(xa_is_advanced(entry))) + return -EINVAL; + if (!entry) + entry = XA_ZERO_ENTRY; + + do { + curr = xas_load(&xas); + if (!curr) { + xas_store(&xas, entry); + if (xa_track_free(xa)) + xas_clear_mark(&xas, XA_FREE_MARK); + } else { + xas_set_err(&xas, -EEXIST); + } + } while (__xas_nomem(&xas, gfp)); + + return xas_error(&xas); +} +EXPORT_SYMBOL(__xa_insert); + +/** * __xa_reserve() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. @@ -1567,7 +1583,7 @@ void *xa_store_range(struct xarray *xa, unsigned long first, if (last + 1) order = __ffs(last + 1); xas_set_order(&xas, last, order); - xas_create(&xas); + xas_create(&xas, true); if (xas_error(&xas)) goto unlock; } @@ -1609,7 +1625,7 @@ int __xa_alloc(struct xarray *xa, u32 *id, u32 max, void *entry, gfp_t gfp) XA_STATE(xas, xa, 0); int err; - if (WARN_ON_ONCE(xa_is_internal(entry))) + if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (WARN_ON_ONCE(!xa_track_free(xa))) return -EINVAL; |