From 97a6ec4ac021f7fbec05c15a3aa0c4aaf0461af5 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 4 Dec 2017 10:31:41 -0800 Subject: rhashtable: Change rhashtable_walk_start to return void Most callers of rhashtable_walk_start don't care about a resize event which is indicated by a return value of -EAGAIN. So calls to rhashtable_walk_start are wrapped wih code to ignore -EAGAIN. Something like this is common: ret = rhashtable_walk_start(rhiter); if (ret && ret != -EAGAIN) goto out; Since zero and -EAGAIN are the only possible return values from the function this check is pointless. The condition never evaluates to true. This patch changes rhashtable_walk_start to return void. This simplifies code for the callers that ignore -EAGAIN. For the few cases where the caller cares about the resize event, particularly where the table can be walked in mulitple parts for netlink or seq file dump, the function rhashtable_walk_start_check has been added that returns -EAGAIN on a resize event. Signed-off-by: Tom Herbert Acked-by: Herbert Xu Signed-off-by: David S. Miller --- fs/gfs2/glock.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 11066d8647d2..90af87ff29ba 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1549,16 +1549,13 @@ static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp) rhashtable_walk_enter(&gl_hash_table, &iter); do { - gl = ERR_PTR(rhashtable_walk_start(&iter)); - if (IS_ERR(gl)) - goto walk_stop; + rhashtable_walk_start(&iter); while ((gl = rhashtable_walk_next(&iter)) && !IS_ERR(gl)) if (gl->gl_name.ln_sbd == sdp && lockref_get_not_dead(&gl->gl_lockref)) examiner(gl); -walk_stop: rhashtable_walk_stop(&iter); } while (cond_resched(), gl == ERR_PTR(-EAGAIN)); @@ -1947,7 +1944,7 @@ static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos) loff_t n = *pos; rhashtable_walk_enter(&gl_hash_table, &gi->hti); - if (rhashtable_walk_start(&gi->hti) != 0) + if (rhashtable_walk_start_check(&gi->hti) != 0) return NULL; do { -- cgit v1.2.3 From 8556e50994c8a8f5282fea008ae084d6d080648a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 11 Dec 2017 11:36:47 -0500 Subject: btrfs: make open_ctree error injectable This allows us to do error injection with BPF for open_ctree. Signed-off-by: Josef Bacik Acked-by: Ingo Molnar Signed-off-by: Alexei Starovoitov --- fs/btrfs/disk-io.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 10a2a579cc7f..02b5f5667754 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include "ctree.h" #include "disk-io.h" @@ -3123,6 +3124,7 @@ recovery_tree_root: goto fail_block_groups; goto retry_root_backup; } +BPF_ALLOW_ERROR_INJECTION(open_ctree); static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate) { -- cgit v1.2.3 From 023f46c5b807ae5fff83b57d918727a5b9dbee55 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 11 Dec 2017 11:36:50 -0500 Subject: btrfs: allow us to inject errors at io_ctl_init This was instrumental in reproducing a space cache bug. Signed-off-by: Josef Bacik Acked-by: Ingo Molnar Signed-off-by: Alexei Starovoitov --- fs/btrfs/free-space-cache.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 4426d1c73e50..fb1382893bfc 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "ctree.h" #include "free-space-cache.h" #include "transaction.h" @@ -332,6 +333,7 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode, return 0; } +BPF_ALLOW_ERROR_INJECTION(io_ctl_init); static void io_ctl_free(struct btrfs_io_ctl *io_ctl) { -- cgit v1.2.3 From cdab6ba8668d68f031bfd5d237b4586ec4f8cd88 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 27 Dec 2017 18:39:08 -0800 Subject: nsfs: generalize ns_get_path() for path resolution with a task ns_get_path() takes struct task_struct and proc_ns_ops as its parameters. For path resolution directly from a namespace, e.g. based on a networking device's net name space, we need more flexibility. Add a ns_get_path_cb() helper which will allow callers to use any method of obtaining the name space reference. Convert ns_get_path() to use ns_get_path_cb(). Following patches will bring a networking user. CC: Eric W. Biederman Suggested-by: Daniel Borkmann Signed-off-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- fs/nsfs.c | 29 ++++++++++++++++++++++++++--- include/linux/proc_ns.h | 3 +++ 2 files changed, 29 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/nsfs.c b/fs/nsfs.c index 7c6f76d29f56..36b0772701a0 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -103,14 +103,14 @@ slow: goto got_it; } -void *ns_get_path(struct path *path, struct task_struct *task, - const struct proc_ns_operations *ns_ops) +void *ns_get_path_cb(struct path *path, ns_get_path_helper_t *ns_get_cb, + void *private_data) { struct ns_common *ns; void *ret; again: - ns = ns_ops->get(task); + ns = ns_get_cb(private_data); if (!ns) return ERR_PTR(-ENOENT); @@ -120,6 +120,29 @@ again: return ret; } +struct ns_get_path_task_args { + const struct proc_ns_operations *ns_ops; + struct task_struct *task; +}; + +static struct ns_common *ns_get_path_task(void *private_data) +{ + struct ns_get_path_task_args *args = private_data; + + return args->ns_ops->get(args->task); +} + +void *ns_get_path(struct path *path, struct task_struct *task, + const struct proc_ns_operations *ns_ops) +{ + struct ns_get_path_task_args args = { + .ns_ops = ns_ops, + .task = task, + }; + + return ns_get_path_cb(path, ns_get_path_task, &args); +} + int open_related_ns(struct ns_common *ns, struct ns_common *(*get_ns)(struct ns_common *ns)) { diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 2ff18c9840a7..d31cb6215905 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -78,6 +78,9 @@ extern struct file *proc_ns_fget(int fd); #define get_proc_ns(inode) ((struct ns_common *)(inode)->i_private) extern void *ns_get_path(struct path *path, struct task_struct *task, const struct proc_ns_operations *ns_ops); +typedef struct ns_common *ns_get_path_helper_t(void *); +extern void *ns_get_path_cb(struct path *path, ns_get_path_helper_t ns_get_cb, + void *private_data); extern int ns_get_name(char *buf, size_t size, struct task_struct *task, const struct proc_ns_operations *ns_ops); -- cgit v1.2.3 From 540adea3809f61115d2a1ea4ed6e627613452ba1 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sat, 13 Jan 2018 02:55:03 +0900 Subject: error-injection: Separate error-injection from kprobe Since error-injection framework is not limited to be used by kprobes, nor bpf. Other kernel subsystems can use it freely for checking safeness of error-injection, e.g. livepatch, ftrace etc. So this separate error-injection framework from kprobes. Some differences has been made: - "kprobe" word is removed from any APIs/structures. - BPF_ALLOW_ERROR_INJECTION() is renamed to ALLOW_ERROR_INJECTION() since it is not limited for BPF too. - CONFIG_FUNCTION_ERROR_INJECTION is the config item of this feature. It is automatically enabled if the arch supports error injection feature for kprobe or ftrace etc. Signed-off-by: Masami Hiramatsu Reviewed-by: Josef Bacik Signed-off-by: Alexei Starovoitov --- arch/Kconfig | 2 +- arch/x86/Kconfig | 2 +- arch/x86/include/asm/error-injection.h | 13 ++ arch/x86/kernel/kprobes/core.c | 14 --- arch/x86/lib/Makefile | 1 + arch/x86/lib/error-inject.c | 19 +++ fs/btrfs/disk-io.c | 4 +- fs/btrfs/free-space-cache.c | 4 +- include/asm-generic/error-injection.h | 20 ++++ include/asm-generic/vmlinux.lds.h | 14 +-- include/linux/bpf.h | 11 -- include/linux/error-injection.h | 21 ++++ include/linux/kprobes.h | 1 - include/linux/module.h | 6 +- kernel/kprobes.c | 163 ------------------------- kernel/module.c | 8 +- kernel/trace/Kconfig | 2 +- kernel/trace/bpf_trace.c | 4 +- kernel/trace/trace_kprobe.c | 3 +- lib/Kconfig.debug | 4 + lib/Makefile | 1 + lib/error-inject.c | 213 +++++++++++++++++++++++++++++++++ 22 files changed, 317 insertions(+), 213 deletions(-) create mode 100644 arch/x86/include/asm/error-injection.h create mode 100644 arch/x86/lib/error-inject.c create mode 100644 include/asm-generic/error-injection.h create mode 100644 include/linux/error-injection.h create mode 100644 lib/error-inject.c (limited to 'fs') diff --git a/arch/Kconfig b/arch/Kconfig index d3f4aaf9cb7a..97376accfb14 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -196,7 +196,7 @@ config HAVE_OPTPROBES config HAVE_KPROBES_ON_FTRACE bool -config HAVE_KPROBE_OVERRIDE +config HAVE_FUNCTION_ERROR_INJECTION bool config HAVE_NMI diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 45dc6233f2b9..366b19cb79b7 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -154,7 +154,7 @@ config X86 select HAVE_KERNEL_XZ select HAVE_KPROBES select HAVE_KPROBES_ON_FTRACE - select HAVE_KPROBE_OVERRIDE + select HAVE_FUNCTION_ERROR_INJECTION select HAVE_KRETPROBES select HAVE_KVM select HAVE_LIVEPATCH if X86_64 diff --git a/arch/x86/include/asm/error-injection.h b/arch/x86/include/asm/error-injection.h new file mode 100644 index 000000000000..47b7a1296245 --- /dev/null +++ b/arch/x86/include/asm/error-injection.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_ERROR_INJECTION_H +#define _ASM_ERROR_INJECTION_H + +#include +#include +#include +#include + +asmlinkage void just_return_func(void); +void override_function_with_return(struct pt_regs *regs); + +#endif /* _ASM_ERROR_INJECTION_H */ diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index b02a377d5905..bd36f3c33cd0 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1183,17 +1183,3 @@ int arch_trampoline_kprobe(struct kprobe *p) { return 0; } - -asmlinkage void override_func(void); -asm( - ".type override_func, @function\n" - "override_func:\n" - " ret\n" - ".size override_func, .-override_func\n" -); - -void arch_kprobe_override_function(struct pt_regs *regs) -{ - regs->ip = (unsigned long)&override_func; -} -NOKPROBE_SYMBOL(arch_kprobe_override_function); diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 7b181b61170e..171377b83be1 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -26,6 +26,7 @@ lib-y += memcpy_$(BITS).o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o +lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o diff --git a/arch/x86/lib/error-inject.c b/arch/x86/lib/error-inject.c new file mode 100644 index 000000000000..7b881d03d0dd --- /dev/null +++ b/arch/x86/lib/error-inject.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +asmlinkage void just_return_func(void); + +asm( + ".type just_return_func, @function\n" + "just_return_func:\n" + " ret\n" + ".size just_return_func, .-just_return_func\n" +); + +void override_function_with_return(struct pt_regs *regs) +{ + regs->ip = (unsigned long)&just_return_func; +} +NOKPROBE_SYMBOL(override_function_with_return); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 5da18ebc9222..9798e21ebe9d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -30,7 +30,7 @@ #include #include #include -#include +#include #include #include "ctree.h" #include "disk-io.h" @@ -3124,7 +3124,7 @@ recovery_tree_root: goto fail_block_groups; goto retry_root_backup; } -BPF_ALLOW_ERROR_INJECTION(open_ctree); +ALLOW_ERROR_INJECTION(open_ctree); static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate) { diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index fb1382893bfc..ef847699031a 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #include "ctree.h" #include "free-space-cache.h" #include "transaction.h" @@ -333,7 +333,7 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode, return 0; } -BPF_ALLOW_ERROR_INJECTION(io_ctl_init); +ALLOW_ERROR_INJECTION(io_ctl_init); static void io_ctl_free(struct btrfs_io_ctl *io_ctl) { diff --git a/include/asm-generic/error-injection.h b/include/asm-generic/error-injection.h new file mode 100644 index 000000000000..08352c9d9f97 --- /dev/null +++ b/include/asm-generic/error-injection.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_GENERIC_ERROR_INJECTION_H +#define _ASM_GENERIC_ERROR_INJECTION_H + +#if defined(__KERNEL__) && !defined(__ASSEMBLY__) +#ifdef CONFIG_FUNCTION_ERROR_INJECTION +/* + * Whitelist ganerating macro. Specify functions which can be + * error-injectable using this macro. + */ +#define ALLOW_ERROR_INJECTION(fname) \ +static unsigned long __used \ + __attribute__((__section__("_error_injection_whitelist"))) \ + _eil_addr_##fname = (unsigned long)fname; +#else +#define ALLOW_ERROR_INJECTION(fname) +#endif +#endif + +#endif /* _ASM_GENERIC_ERROR_INJECTION_H */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index a2e8582d094a..f2068cca5206 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -136,13 +136,13 @@ #define KPROBE_BLACKLIST() #endif -#ifdef CONFIG_BPF_KPROBE_OVERRIDE -#define ERROR_INJECT_LIST() . = ALIGN(8); \ - VMLINUX_SYMBOL(__start_kprobe_error_inject_list) = .; \ - KEEP(*(_kprobe_error_inject_list)) \ - VMLINUX_SYMBOL(__stop_kprobe_error_inject_list) = .; +#ifdef CONFIG_FUNCTION_ERROR_INJECTION +#define ERROR_INJECT_WHITELIST() . = ALIGN(8); \ + VMLINUX_SYMBOL(__start_error_injection_whitelist) = .;\ + KEEP(*(_error_injection_whitelist)) \ + VMLINUX_SYMBOL(__stop_error_injection_whitelist) = .; #else -#define ERROR_INJECT_LIST() +#define ERROR_INJECT_WHITELIST() #endif #ifdef CONFIG_EVENT_TRACING @@ -573,7 +573,7 @@ FTRACE_EVENTS() \ TRACE_SYSCALLS() \ KPROBE_BLACKLIST() \ - ERROR_INJECT_LIST() \ + ERROR_INJECT_WHITELIST() \ MEM_DISCARD(init.rodata) \ CLK_OF_TABLES() \ RESERVEDMEM_OF_TABLES() \ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 44f26f6df8fc..3496977203a3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -613,15 +613,4 @@ extern const struct bpf_func_proto bpf_sock_map_update_proto; void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); -#if defined(__KERNEL__) && !defined(__ASSEMBLY__) -#ifdef CONFIG_BPF_KPROBE_OVERRIDE -#define BPF_ALLOW_ERROR_INJECTION(fname) \ -static unsigned long __used \ - __attribute__((__section__("_kprobe_error_inject_list"))) \ - _eil_addr_##fname = (unsigned long)fname; -#else -#define BPF_ALLOW_ERROR_INJECTION(fname) -#endif -#endif - #endif /* _LINUX_BPF_H */ diff --git a/include/linux/error-injection.h b/include/linux/error-injection.h new file mode 100644 index 000000000000..130a67c50dac --- /dev/null +++ b/include/linux/error-injection.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_ERROR_INJECTION_H +#define _LINUX_ERROR_INJECTION_H + +#ifdef CONFIG_FUNCTION_ERROR_INJECTION + +#include + +extern bool within_error_injection_list(unsigned long addr); + +#else /* !CONFIG_FUNCTION_ERROR_INJECTION */ + +#include +static inline bool within_error_injection_list(unsigned long addr) +{ + return false; +} + +#endif + +#endif /* _LINUX_ERROR_INJECTION_H */ diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 963fd364f3d6..9440a2fc8893 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -271,7 +271,6 @@ extern bool arch_kprobe_on_func_entry(unsigned long offset); extern bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset); extern bool within_kprobe_blacklist(unsigned long addr); -extern bool within_kprobe_error_injection_list(unsigned long addr); struct kprobe_insn_cache { struct mutex mutex; diff --git a/include/linux/module.h b/include/linux/module.h index 548fa09fa806..792e51d83bda 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -476,9 +476,9 @@ struct module { unsigned int num_ctors; #endif -#ifdef CONFIG_BPF_KPROBE_OVERRIDE - unsigned int num_kprobe_ei_funcs; - unsigned long *kprobe_ei_funcs; +#ifdef CONFIG_FUNCTION_ERROR_INJECTION + unsigned int num_ei_funcs; + unsigned long *ei_funcs; #endif } ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT diff --git a/kernel/kprobes.c b/kernel/kprobes.c index b4aab48ad258..da2ccf142358 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -83,16 +83,6 @@ static raw_spinlock_t *kretprobe_table_lock_ptr(unsigned long hash) return &(kretprobe_table_locks[hash].lock); } -/* List of symbols that can be overriden for error injection. */ -static LIST_HEAD(kprobe_error_injection_list); -static DEFINE_MUTEX(kprobe_ei_mutex); -struct kprobe_ei_entry { - struct list_head list; - unsigned long start_addr; - unsigned long end_addr; - void *priv; -}; - /* Blacklist -- list of struct kprobe_blacklist_entry */ static LIST_HEAD(kprobe_blacklist); @@ -1404,17 +1394,6 @@ bool within_kprobe_blacklist(unsigned long addr) return false; } -bool within_kprobe_error_injection_list(unsigned long addr) -{ - struct kprobe_ei_entry *ent; - - list_for_each_entry(ent, &kprobe_error_injection_list, list) { - if (addr >= ent->start_addr && addr < ent->end_addr) - return true; - } - return false; -} - /* * If we have a symbol_name argument, look it up and add the offset field * to it. This way, we can specify a relative address to a symbol. @@ -2189,86 +2168,6 @@ static int __init populate_kprobe_blacklist(unsigned long *start, return 0; } -#ifdef CONFIG_BPF_KPROBE_OVERRIDE -/* Markers of the _kprobe_error_inject_list section */ -extern unsigned long __start_kprobe_error_inject_list[]; -extern unsigned long __stop_kprobe_error_inject_list[]; - -/* - * Lookup and populate the kprobe_error_injection_list. - * - * For safety reasons we only allow certain functions to be overriden with - * bpf_error_injection, so we need to populate the list of the symbols that have - * been marked as safe for overriding. - */ -static void populate_kprobe_error_injection_list(unsigned long *start, - unsigned long *end, - void *priv) -{ - unsigned long *iter; - struct kprobe_ei_entry *ent; - unsigned long entry, offset = 0, size = 0; - - mutex_lock(&kprobe_ei_mutex); - for (iter = start; iter < end; iter++) { - entry = arch_deref_entry_point((void *)*iter); - - if (!kernel_text_address(entry) || - !kallsyms_lookup_size_offset(entry, &size, &offset)) { - pr_err("Failed to find error inject entry at %p\n", - (void *)entry); - continue; - } - - ent = kmalloc(sizeof(*ent), GFP_KERNEL); - if (!ent) - break; - ent->start_addr = entry; - ent->end_addr = entry + size; - ent->priv = priv; - INIT_LIST_HEAD(&ent->list); - list_add_tail(&ent->list, &kprobe_error_injection_list); - } - mutex_unlock(&kprobe_ei_mutex); -} - -static void __init populate_kernel_kprobe_ei_list(void) -{ - populate_kprobe_error_injection_list(__start_kprobe_error_inject_list, - __stop_kprobe_error_inject_list, - NULL); -} - -static void module_load_kprobe_ei_list(struct module *mod) -{ - if (!mod->num_kprobe_ei_funcs) - return; - populate_kprobe_error_injection_list(mod->kprobe_ei_funcs, - mod->kprobe_ei_funcs + - mod->num_kprobe_ei_funcs, mod); -} - -static void module_unload_kprobe_ei_list(struct module *mod) -{ - struct kprobe_ei_entry *ent, *n; - if (!mod->num_kprobe_ei_funcs) - return; - - mutex_lock(&kprobe_ei_mutex); - list_for_each_entry_safe(ent, n, &kprobe_error_injection_list, list) { - if (ent->priv == mod) { - list_del_init(&ent->list); - kfree(ent); - } - } - mutex_unlock(&kprobe_ei_mutex); -} -#else -static inline void __init populate_kernel_kprobe_ei_list(void) {} -static inline void module_load_kprobe_ei_list(struct module *m) {} -static inline void module_unload_kprobe_ei_list(struct module *m) {} -#endif - /* Module notifier call back, checking kprobes on the module */ static int kprobes_module_callback(struct notifier_block *nb, unsigned long val, void *data) @@ -2279,11 +2178,6 @@ static int kprobes_module_callback(struct notifier_block *nb, unsigned int i; int checkcore = (val == MODULE_STATE_GOING); - if (val == MODULE_STATE_COMING) - module_load_kprobe_ei_list(mod); - else if (val == MODULE_STATE_GOING) - module_unload_kprobe_ei_list(mod); - if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE) return NOTIFY_DONE; @@ -2346,8 +2240,6 @@ static int __init init_kprobes(void) pr_err("Please take care of using kprobes.\n"); } - populate_kernel_kprobe_ei_list(); - if (kretprobe_blacklist_size) { /* lookup the function address from its name */ for (i = 0; kretprobe_blacklist[i].name != NULL; i++) { @@ -2515,56 +2407,6 @@ static const struct file_operations debugfs_kprobe_blacklist_ops = { .release = seq_release, }; -/* - * kprobes/error_injection_list -- shows which functions can be overriden for - * error injection. - * */ -static void *kprobe_ei_seq_start(struct seq_file *m, loff_t *pos) -{ - mutex_lock(&kprobe_ei_mutex); - return seq_list_start(&kprobe_error_injection_list, *pos); -} - -static void kprobe_ei_seq_stop(struct seq_file *m, void *v) -{ - mutex_unlock(&kprobe_ei_mutex); -} - -static void *kprobe_ei_seq_next(struct seq_file *m, void *v, loff_t *pos) -{ - return seq_list_next(v, &kprobe_error_injection_list, pos); -} - -static int kprobe_ei_seq_show(struct seq_file *m, void *v) -{ - char buffer[KSYM_SYMBOL_LEN]; - struct kprobe_ei_entry *ent = - list_entry(v, struct kprobe_ei_entry, list); - - sprint_symbol(buffer, ent->start_addr); - seq_printf(m, "%s\n", buffer); - return 0; -} - -static const struct seq_operations kprobe_ei_seq_ops = { - .start = kprobe_ei_seq_start, - .next = kprobe_ei_seq_next, - .stop = kprobe_ei_seq_stop, - .show = kprobe_ei_seq_show, -}; - -static int kprobe_ei_open(struct inode *inode, struct file *filp) -{ - return seq_open(filp, &kprobe_ei_seq_ops); -} - -static const struct file_operations debugfs_kprobe_ei_ops = { - .open = kprobe_ei_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - static void arm_all_kprobes(void) { struct hlist_head *head; @@ -2706,11 +2548,6 @@ static int __init debugfs_kprobe_init(void) if (!file) goto error; - file = debugfs_create_file("error_injection_list", 0444, dir, NULL, - &debugfs_kprobe_ei_ops); - if (!file) - goto error; - return 0; error: diff --git a/kernel/module.c b/kernel/module.c index bd695bfdc5c4..601494d4b7ea 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3118,10 +3118,10 @@ static int find_module_sections(struct module *mod, struct load_info *info) sizeof(*mod->ftrace_callsites), &mod->num_ftrace_callsites); #endif -#ifdef CONFIG_BPF_KPROBE_OVERRIDE - mod->kprobe_ei_funcs = section_objs(info, "_kprobe_error_inject_list", - sizeof(*mod->kprobe_ei_funcs), - &mod->num_kprobe_ei_funcs); +#ifdef CONFIG_FUNCTION_ERROR_INJECTION + mod->ei_funcs = section_objs(info, "_error_injection_whitelist", + sizeof(*mod->ei_funcs), + &mod->num_ei_funcs); #endif mod->extable = section_objs(info, "__ex_table", sizeof(*mod->extable), &mod->num_exentries); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 6400e1bf97c5..7114c885a78a 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -533,7 +533,7 @@ config FUNCTION_PROFILER config BPF_KPROBE_OVERRIDE bool "Enable BPF programs to override a kprobed function" depends on BPF_EVENTS - depends on HAVE_KPROBE_OVERRIDE + depends on FUNCTION_ERROR_INJECTION default n help Allows BPF to override the execution of a probed function and diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 24ed6363e00f..f274468cbc45 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include "trace_probe.h" #include "trace.h" @@ -84,7 +84,7 @@ EXPORT_SYMBOL_GPL(trace_call_bpf); BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc) { regs_set_return_value(regs, rc); - arch_kprobe_override_function(regs); + override_function_with_return(regs); return 0; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index b8c90441bc87..1fad24acd444 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -21,6 +21,7 @@ #include #include #include +#include #include "trace_probe.h" @@ -107,7 +108,7 @@ bool trace_kprobe_error_injectable(struct trace_event_call *call) } else { addr = (unsigned long)tk->rp.kp.addr; } - return within_kprobe_error_injection_list(addr); + return within_error_injection_list(addr); } static int register_kprobe_event(struct trace_kprobe *tk); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 9d5b78aad4c5..2a33efdd1fea 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1500,6 +1500,10 @@ config FAULT_INJECTION Provide fault-injection framework. For more details, see Documentation/fault-injection/. +config FUNCTION_ERROR_INJECTION + def_bool y + depends on HAVE_FUNCTION_ERROR_INJECTION && KPROBES + config FAILSLAB bool "Fault-injection capability for kmalloc" depends on FAULT_INJECTION diff --git a/lib/Makefile b/lib/Makefile index a6c8529dd9b2..75ec13778cd8 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -149,6 +149,7 @@ obj-$(CONFIG_NETDEV_NOTIFIER_ERROR_INJECT) += netdev-notifier-error-inject.o obj-$(CONFIG_MEMORY_NOTIFIER_ERROR_INJECT) += memory-notifier-error-inject.o obj-$(CONFIG_OF_RECONFIG_NOTIFIER_ERROR_INJECT) += \ of-reconfig-notifier-error-inject.o +obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o lib-$(CONFIG_GENERIC_BUG) += bug.o diff --git a/lib/error-inject.c b/lib/error-inject.c new file mode 100644 index 000000000000..bccadcf3c981 --- /dev/null +++ b/lib/error-inject.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0 +// error-inject.c: Function-level error injection table +#include +#include +#include +#include +#include +#include +#include +#include + +/* Whitelist of symbols that can be overridden for error injection. */ +static LIST_HEAD(error_injection_list); +static DEFINE_MUTEX(ei_mutex); +struct ei_entry { + struct list_head list; + unsigned long start_addr; + unsigned long end_addr; + void *priv; +}; + +bool within_error_injection_list(unsigned long addr) +{ + struct ei_entry *ent; + bool ret = false; + + mutex_lock(&ei_mutex); + list_for_each_entry(ent, &error_injection_list, list) { + if (addr >= ent->start_addr && addr < ent->end_addr) { + ret = true; + break; + } + } + mutex_unlock(&ei_mutex); + return ret; +} + +/* + * Lookup and populate the error_injection_list. + * + * For safety reasons we only allow certain functions to be overridden with + * bpf_error_injection, so we need to populate the list of the symbols that have + * been marked as safe for overriding. + */ +static void populate_error_injection_list(unsigned long *start, + unsigned long *end, void *priv) +{ + unsigned long *iter; + struct ei_entry *ent; + unsigned long entry, offset = 0, size = 0; + + mutex_lock(&ei_mutex); + for (iter = start; iter < end; iter++) { + entry = arch_deref_entry_point((void *)*iter); + + if (!kernel_text_address(entry) || + !kallsyms_lookup_size_offset(entry, &size, &offset)) { + pr_err("Failed to find error inject entry at %p\n", + (void *)entry); + continue; + } + + ent = kmalloc(sizeof(*ent), GFP_KERNEL); + if (!ent) + break; + ent->start_addr = entry; + ent->end_addr = entry + size; + ent->priv = priv; + INIT_LIST_HEAD(&ent->list); + list_add_tail(&ent->list, &error_injection_list); + } + mutex_unlock(&ei_mutex); +} + +/* Markers of the _error_inject_whitelist section */ +extern unsigned long __start_error_injection_whitelist[]; +extern unsigned long __stop_error_injection_whitelist[]; + +static void __init populate_kernel_ei_list(void) +{ + populate_error_injection_list(__start_error_injection_whitelist, + __stop_error_injection_whitelist, + NULL); +} + +#ifdef CONFIG_MODULES +static void module_load_ei_list(struct module *mod) +{ + if (!mod->num_ei_funcs) + return; + + populate_error_injection_list(mod->ei_funcs, + mod->ei_funcs + mod->num_ei_funcs, mod); +} + +static void module_unload_ei_list(struct module *mod) +{ + struct ei_entry *ent, *n; + + if (!mod->num_ei_funcs) + return; + + mutex_lock(&ei_mutex); + list_for_each_entry_safe(ent, n, &error_injection_list, list) { + if (ent->priv == mod) { + list_del_init(&ent->list); + kfree(ent); + } + } + mutex_unlock(&ei_mutex); +} + +/* Module notifier call back, checking error injection table on the module */ +static int ei_module_callback(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct module *mod = data; + + if (val == MODULE_STATE_COMING) + module_load_ei_list(mod); + else if (val == MODULE_STATE_GOING) + module_unload_ei_list(mod); + + return NOTIFY_DONE; +} + +static struct notifier_block ei_module_nb = { + .notifier_call = ei_module_callback, + .priority = 0 +}; + +static __init int module_ei_init(void) +{ + return register_module_notifier(&ei_module_nb); +} +#else /* !CONFIG_MODULES */ +#define module_ei_init() (0) +#endif + +/* + * error_injection/whitelist -- shows which functions can be overridden for + * error injection. + */ +static void *ei_seq_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&ei_mutex); + return seq_list_start(&error_injection_list, *pos); +} + +static void ei_seq_stop(struct seq_file *m, void *v) +{ + mutex_unlock(&ei_mutex); +} + +static void *ei_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + return seq_list_next(v, &error_injection_list, pos); +} + +static int ei_seq_show(struct seq_file *m, void *v) +{ + struct ei_entry *ent = list_entry(v, struct ei_entry, list); + + seq_printf(m, "%pf\n", (void *)ent->start_addr); + return 0; +} + +static const struct seq_operations ei_seq_ops = { + .start = ei_seq_start, + .next = ei_seq_next, + .stop = ei_seq_stop, + .show = ei_seq_show, +}; + +static int ei_open(struct inode *inode, struct file *filp) +{ + return seq_open(filp, &ei_seq_ops); +} + +static const struct file_operations debugfs_ei_ops = { + .open = ei_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init ei_debugfs_init(void) +{ + struct dentry *dir, *file; + + dir = debugfs_create_dir("error_injection", NULL); + if (!dir) + return -ENOMEM; + + file = debugfs_create_file("list", 0444, dir, NULL, &debugfs_ei_ops); + if (!file) { + debugfs_remove(dir); + return -ENOMEM; + } + + return 0; +} + +static int __init init_error_injection(void) +{ + populate_kernel_ei_list(); + + if (!module_ei_init()) + ei_debugfs_init(); + + return 0; +} +late_initcall(init_error_injection); -- cgit v1.2.3 From 663faf9f7beeaca4ad0176bb96c776eed9dad0c5 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sat, 13 Jan 2018 02:55:33 +0900 Subject: error-injection: Add injectable error types Add injectable error types for each error-injectable function. One motivation of error injection test is to find software flaws, mistakes or mis-handlings of expectable errors. If we find such flaws by the test, that is a program bug, so we need to fix it. But if the tester miss input the error (e.g. just return success code without processing anything), it causes unexpected behavior even if the caller is correctly programmed to handle any errors. That is not what we want to test by error injection. To clarify what type of errors the caller must expect for each injectable function, this introduces injectable error types: - EI_ETYPE_NULL : means the function will return NULL if it fails. No ERR_PTR, just a NULL. - EI_ETYPE_ERRNO : means the function will return -ERRNO if it fails. - EI_ETYPE_ERRNO_NULL : means the function will return -ERRNO (ERR_PTR) or NULL. ALLOW_ERROR_INJECTION() macro is expanded to get one of NULL, ERRNO, ERRNO_NULL to record the error type for each function. e.g. ALLOW_ERROR_INJECTION(open_ctree, ERRNO) This error types are shown in debugfs as below. ==== / # cat /sys/kernel/debug/error_injection/list open_ctree [btrfs] ERRNO io_ctl_init [btrfs] ERRNO ==== Signed-off-by: Masami Hiramatsu Reviewed-by: Josef Bacik Signed-off-by: Alexei Starovoitov --- fs/btrfs/disk-io.c | 2 +- fs/btrfs/free-space-cache.c | 2 +- include/asm-generic/error-injection.h | 23 +++++++++++++++---- include/asm-generic/vmlinux.lds.h | 2 +- include/linux/error-injection.h | 6 +++++ include/linux/module.h | 3 ++- lib/error-inject.c | 43 +++++++++++++++++++++++++++++------ 7 files changed, 66 insertions(+), 15 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 9798e21ebe9d..83e2349e1362 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3124,7 +3124,7 @@ recovery_tree_root: goto fail_block_groups; goto retry_root_backup; } -ALLOW_ERROR_INJECTION(open_ctree); +ALLOW_ERROR_INJECTION(open_ctree, ERRNO); static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate) { diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index ef847699031a..586bb06472bb 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -333,7 +333,7 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode, return 0; } -ALLOW_ERROR_INJECTION(io_ctl_init); +ALLOW_ERROR_INJECTION(io_ctl_init, ERRNO); static void io_ctl_free(struct btrfs_io_ctl *io_ctl) { diff --git a/include/asm-generic/error-injection.h b/include/asm-generic/error-injection.h index 08352c9d9f97..296c65442f00 100644 --- a/include/asm-generic/error-injection.h +++ b/include/asm-generic/error-injection.h @@ -3,17 +3,32 @@ #define _ASM_GENERIC_ERROR_INJECTION_H #if defined(__KERNEL__) && !defined(__ASSEMBLY__) +enum { + EI_ETYPE_NONE, /* Dummy value for undefined case */ + EI_ETYPE_NULL, /* Return NULL if failure */ + EI_ETYPE_ERRNO, /* Return -ERRNO if failure */ + EI_ETYPE_ERRNO_NULL, /* Return -ERRNO or NULL if failure */ +}; + +struct error_injection_entry { + unsigned long addr; + int etype; +}; + #ifdef CONFIG_FUNCTION_ERROR_INJECTION /* * Whitelist ganerating macro. Specify functions which can be * error-injectable using this macro. */ -#define ALLOW_ERROR_INJECTION(fname) \ -static unsigned long __used \ +#define ALLOW_ERROR_INJECTION(fname, _etype) \ +static struct error_injection_entry __used \ __attribute__((__section__("_error_injection_whitelist"))) \ - _eil_addr_##fname = (unsigned long)fname; + _eil_addr_##fname = { \ + .addr = (unsigned long)fname, \ + .etype = EI_ETYPE_##_etype, \ + }; #else -#define ALLOW_ERROR_INJECTION(fname) +#define ALLOW_ERROR_INJECTION(fname, _etype) #endif #endif diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index f2068cca5206..ebe544e048cd 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -137,7 +137,7 @@ #endif #ifdef CONFIG_FUNCTION_ERROR_INJECTION -#define ERROR_INJECT_WHITELIST() . = ALIGN(8); \ +#define ERROR_INJECT_WHITELIST() STRUCT_ALIGN(); \ VMLINUX_SYMBOL(__start_error_injection_whitelist) = .;\ KEEP(*(_error_injection_whitelist)) \ VMLINUX_SYMBOL(__stop_error_injection_whitelist) = .; diff --git a/include/linux/error-injection.h b/include/linux/error-injection.h index 130a67c50dac..280c61ecbf20 100644 --- a/include/linux/error-injection.h +++ b/include/linux/error-injection.h @@ -7,6 +7,7 @@ #include extern bool within_error_injection_list(unsigned long addr); +extern int get_injectable_error_type(unsigned long addr); #else /* !CONFIG_FUNCTION_ERROR_INJECTION */ @@ -16,6 +17,11 @@ static inline bool within_error_injection_list(unsigned long addr) return false; } +static inline int get_injectable_error_type(unsigned long addr) +{ + return EI_ETYPE_NONE; +} + #endif #endif /* _LINUX_ERROR_INJECTION_H */ diff --git a/include/linux/module.h b/include/linux/module.h index 792e51d83bda..9642d3116718 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -477,8 +478,8 @@ struct module { #endif #ifdef CONFIG_FUNCTION_ERROR_INJECTION + struct error_injection_entry *ei_funcs; unsigned int num_ei_funcs; - unsigned long *ei_funcs; #endif } ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT diff --git a/lib/error-inject.c b/lib/error-inject.c index bccadcf3c981..c0d4600f4896 100644 --- a/lib/error-inject.c +++ b/lib/error-inject.c @@ -16,6 +16,7 @@ struct ei_entry { struct list_head list; unsigned long start_addr; unsigned long end_addr; + int etype; void *priv; }; @@ -35,6 +36,17 @@ bool within_error_injection_list(unsigned long addr) return ret; } +int get_injectable_error_type(unsigned long addr) +{ + struct ei_entry *ent; + + list_for_each_entry(ent, &error_injection_list, list) { + if (addr >= ent->start_addr && addr < ent->end_addr) + return ent->etype; + } + return EI_ETYPE_NONE; +} + /* * Lookup and populate the error_injection_list. * @@ -42,16 +54,17 @@ bool within_error_injection_list(unsigned long addr) * bpf_error_injection, so we need to populate the list of the symbols that have * been marked as safe for overriding. */ -static void populate_error_injection_list(unsigned long *start, - unsigned long *end, void *priv) +static void populate_error_injection_list(struct error_injection_entry *start, + struct error_injection_entry *end, + void *priv) { - unsigned long *iter; + struct error_injection_entry *iter; struct ei_entry *ent; unsigned long entry, offset = 0, size = 0; mutex_lock(&ei_mutex); for (iter = start; iter < end; iter++) { - entry = arch_deref_entry_point((void *)*iter); + entry = arch_deref_entry_point((void *)iter->addr); if (!kernel_text_address(entry) || !kallsyms_lookup_size_offset(entry, &size, &offset)) { @@ -65,6 +78,7 @@ static void populate_error_injection_list(unsigned long *start, break; ent->start_addr = entry; ent->end_addr = entry + size; + ent->etype = iter->etype; ent->priv = priv; INIT_LIST_HEAD(&ent->list); list_add_tail(&ent->list, &error_injection_list); @@ -73,8 +87,8 @@ static void populate_error_injection_list(unsigned long *start, } /* Markers of the _error_inject_whitelist section */ -extern unsigned long __start_error_injection_whitelist[]; -extern unsigned long __stop_error_injection_whitelist[]; +extern struct error_injection_entry __start_error_injection_whitelist[]; +extern struct error_injection_entry __stop_error_injection_whitelist[]; static void __init populate_kernel_ei_list(void) { @@ -157,11 +171,26 @@ static void *ei_seq_next(struct seq_file *m, void *v, loff_t *pos) return seq_list_next(v, &error_injection_list, pos); } +static const char *error_type_string(int etype) +{ + switch (etype) { + case EI_ETYPE_NULL: + return "NULL"; + case EI_ETYPE_ERRNO: + return "ERRNO"; + case EI_ETYPE_ERRNO_NULL: + return "ERRNO_NULL"; + default: + return "(unknown)"; + } +} + static int ei_seq_show(struct seq_file *m, void *v) { struct ei_entry *ent = list_entry(v, struct ei_entry, list); - seq_printf(m, "%pf\n", (void *)ent->start_addr); + seq_printf(m, "%pf\t%s\n", (void *)ent->start_addr, + error_type_string(ent->etype)); return 0; } -- cgit v1.2.3