From becf33f694dc50656766e0fde8883437d5c8d4b4 Mon Sep 17 00:00:00 2001 From: Eiichi Tsukata Date: Mon, 10 Jun 2019 13:00:16 +0900 Subject: tracing: Fix out-of-range read in trace_stack_print() Puts range check before dereferencing the pointer. Reproducer: # echo stacktrace > trace_options # echo 1 > events/enable # cat trace > /dev/null KASAN report: ================================================================== BUG: KASAN: use-after-free in trace_stack_print+0x26b/0x2c0 Read of size 8 at addr ffff888069d20000 by task cat/1953 CPU: 0 PID: 1953 Comm: cat Not tainted 5.2.0-rc3+ #5 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 Call Trace: dump_stack+0x8a/0xce print_address_description+0x60/0x224 ? trace_stack_print+0x26b/0x2c0 ? trace_stack_print+0x26b/0x2c0 __kasan_report.cold+0x1a/0x3e ? trace_stack_print+0x26b/0x2c0 kasan_report+0xe/0x20 trace_stack_print+0x26b/0x2c0 print_trace_line+0x6ea/0x14d0 ? tracing_buffers_read+0x700/0x700 ? trace_find_next_entry_inc+0x158/0x1d0 s_show+0xea/0x310 seq_read+0xaa7/0x10e0 ? seq_escape+0x230/0x230 __vfs_read+0x7c/0x100 vfs_read+0x16c/0x3a0 ksys_read+0x121/0x240 ? kernel_write+0x110/0x110 ? perf_trace_sys_enter+0x8a0/0x8a0 ? syscall_slow_exit_work+0xa9/0x410 do_syscall_64+0xb7/0x390 ? prepare_exit_to_usermode+0x165/0x200 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f867681f910 Code: b6 fe ff ff 48 8d 3d 0f be 08 00 48 83 ec 08 e8 06 db 01 00 66 0f 1f 44 00 00 83 3d f9 2d 2c 00 00 75 10 b8 00 00 00 00 04 RSP: 002b:00007ffdabf23488 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 RAX: ffffffffffffffda RBX: 0000000000020000 RCX: 00007f867681f910 RDX: 0000000000020000 RSI: 00007f8676cde000 RDI: 0000000000000003 RBP: 00007f8676cde000 R08: ffffffffffffffff R09: 0000000000000000 R10: 0000000000000871 R11: 0000000000000246 R12: 00007f8676cde000 R13: 0000000000000003 R14: 0000000000020000 R15: 0000000000000ec0 Allocated by task 1214: save_stack+0x1b/0x80 __kasan_kmalloc.constprop.0+0xc2/0xd0 kmem_cache_alloc+0xaf/0x1a0 getname_flags+0xd2/0x5b0 do_sys_open+0x277/0x5a0 do_syscall_64+0xb7/0x390 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Freed by task 1214: save_stack+0x1b/0x80 __kasan_slab_free+0x12c/0x170 kmem_cache_free+0x8a/0x1c0 putname+0xe1/0x120 do_sys_open+0x2c5/0x5a0 do_syscall_64+0xb7/0x390 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The buggy address belongs to the object at ffff888069d20000 which belongs to the cache names_cache of size 4096 The buggy address is located 0 bytes inside of 4096-byte region [ffff888069d20000, ffff888069d21000) The buggy address belongs to the page: page:ffffea0001a74800 refcount:1 mapcount:0 mapping:ffff88806ccd1380 index:0x0 compound_mapcount: 0 flags: 0x100000000010200(slab|head) raw: 0100000000010200 dead000000000100 dead000000000200 ffff88806ccd1380 raw: 0000000000000000 0000000000070007 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888069d1ff00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff888069d1ff80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff888069d20000: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888069d20080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888069d20100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Link: http://lkml.kernel.org/r/20190610040016.5598-1-devel@etsukata.com Fixes: 4285f2fcef80 ("tracing: Remove the ULONG_MAX stack trace hackery") Signed-off-by: Eiichi Tsukata Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 54373d93e251..ba751f993c3b 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1057,7 +1057,7 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter, trace_seq_puts(s, "\n"); - for (p = field->caller; p && *p != ULONG_MAX && p < end; p++) { + for (p = field->caller; p && p < end && *p != ULONG_MAX; p++) { if (trace_seq_has_overflowed(s)) break; -- cgit v1.2.3-55-g7522 From cbdaeaf050b730ea02e9ab4ff844ce54d85dbe1d Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 5 Jun 2019 13:11:58 +0200 Subject: tracing: avoid build warning with HAVE_NOP_MCOUNT Selecting HAVE_NOP_MCOUNT enables -mnop-mcount (if gcc supports it) and sets CC_USING_NOP_MCOUNT. Reuse __is_defined (which is suitable for testing CC_USING_* defines) to avoid conditional compilation and fix the following gcc 9 warning on s390: kernel/trace/ftrace.c:2514:1: warning: ‘ftrace_code_disable’ defined but not used [-Wunused-function] Link: http://lkml.kernel.org/r/patch.git-1a82d13f33ac.your-ad-here.call-01559732716-ext-6629@work.hours Fixes: 2f4df0017baed ("tracing: Add -mcount-nop option support") Signed-off-by: Vasily Gorbik Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index a12aff849c04..e77a6c92620f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2935,14 +2935,13 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) p = &pg->records[i]; p->flags = rec_flags; -#ifndef CC_USING_NOP_MCOUNT /* * Do the initial record conversion from mcount jump * to the NOP instructions. */ - if (!ftrace_code_disable(mod, p)) + if (!__is_defined(CC_USING_NOP_MCOUNT) && + !ftrace_code_disable(mod, p)) break; -#endif update_cnt++; } -- cgit v1.2.3-55-g7522 From ff585c5b9a27e64084c84e2ddf24fd00bf8dcfc1 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Fri, 14 Jun 2019 23:32:10 +0800 Subject: tracing: Make two symbols static Fix sparse warnings: kernel/trace/trace.c:6927:24: warning: symbol 'get_tracing_log_err' was not declared. Should it be static? kernel/trace/trace.c:8196:15: warning: symbol 'trace_instance_dir' was not declared. Should it be static? Link: http://lkml.kernel.org/r/20190614153210.24424-1-yuehaibing@huawei.com Acked-by: Tom Zanussi Reported-by: Hulk Robot Signed-off-by: YueHaibing Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1c80521fd436..83e08b78dbee 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6923,7 +6923,7 @@ struct tracing_log_err { static DEFINE_MUTEX(tracing_err_log_lock); -struct tracing_log_err *get_tracing_log_err(struct trace_array *tr) +static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr) { struct tracing_log_err *err; @@ -8192,7 +8192,7 @@ static const struct file_operations buffer_percent_fops = { .llseek = default_llseek, }; -struct dentry *trace_instance_dir; +static struct dentry *trace_instance_dir; static void init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer); -- cgit v1.2.3-55-g7522 From f01098c74b5219f3969d4750eeed1a36bfc038e3 Mon Sep 17 00:00:00 2001 From: Eiichi Tsukata Date: Fri, 14 Jun 2019 16:40:25 +0900 Subject: tracing/uprobe: Fix NULL pointer dereference in trace_uprobe_create() Just like the case of commit 8b05a3a7503c ("tracing/kprobes: Fix NULL pointer dereference in trace_kprobe_create()"), writing an incorrectly formatted string to uprobe_events can trigger NULL pointer dereference. Reporeducer: # echo r > /sys/kernel/debug/tracing/uprobe_events dmesg: BUG: kernel NULL pointer dereference, address: 0000000000000000 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 8000000079d12067 P4D 8000000079d12067 PUD 7b7ab067 PMD 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 1903 Comm: bash Not tainted 5.2.0-rc3+ #15 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 RIP: 0010:strchr+0x0/0x30 Code: c0 eb 0d 84 c9 74 18 48 83 c0 01 48 39 d0 74 0f 0f b6 0c 07 3a 0c 06 74 ea 19 c0 83 c8 01 c3 31 c0 c3 0f 1f 84 00 00 00 00 00 <0f> b6 07 89 f2 40 38 f0 75 0e eb 13 0f b6 47 01 48 83 c RSP: 0018:ffffb55fc0403d10 EFLAGS: 00010293 RAX: ffff993ffb793400 RBX: 0000000000000000 RCX: ffffffffa4852625 RDX: 0000000000000000 RSI: 000000000000002f RDI: 0000000000000000 RBP: ffffb55fc0403dd0 R08: ffff993ffb793400 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: ffff993ff9cc1668 R14: 0000000000000001 R15: 0000000000000000 FS: 00007f30c5147700(0000) GS:ffff993ffda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007b628000 CR4: 00000000000006f0 Call Trace: trace_uprobe_create+0xe6/0xb10 ? __kmalloc_track_caller+0xe6/0x1c0 ? __kmalloc+0xf0/0x1d0 ? trace_uprobe_create+0xb10/0xb10 create_or_delete_trace_uprobe+0x35/0x90 ? trace_uprobe_create+0xb10/0xb10 trace_run_command+0x9c/0xb0 trace_parse_run_command+0xf9/0x1eb ? probes_open+0x80/0x80 __vfs_write+0x43/0x90 vfs_write+0x14a/0x2a0 ksys_write+0xa2/0x170 do_syscall_64+0x7f/0x200 entry_SYSCALL_64_after_hwframe+0x49/0xbe Link: http://lkml.kernel.org/r/20190614074026.8045-1-devel@etsukata.com Cc: stable@vger.kernel.org Fixes: 0597c49c69d5 ("tracing/uprobes: Use dyn_event framework for uprobe events") Reviewed-by: Srikar Dronamraju Signed-off-by: Eiichi Tsukata Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_uprobe.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index eb7e06b54741..a88c692e3b8a 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -443,10 +443,17 @@ static int trace_uprobe_create(int argc, const char **argv) ret = 0; ref_ctr_offset = 0; - /* argc must be >= 1 */ - if (argv[0][0] == 'r') + switch (argv[0][0]) { + case 'r': is_return = true; - else if (argv[0][0] != 'p' || argc < 2) + break; + case 'p': + break; + default: + return -ECANCELED; + } + + if (argc < 2) return -ECANCELED; if (argv[0][1] == ':') -- cgit v1.2.3-55-g7522 From a4158345ec5acb44cc0a9ef4381e0784c1bc7722 Mon Sep 17 00:00:00 2001 From: Eiichi Tsukata Date: Fri, 14 Jun 2019 16:40:26 +0900 Subject: tracing/uprobe: Fix obsolete comment on trace_uprobe_create() Commit 0597c49c69d5 ("tracing/uprobes: Use dyn_event framework for uprobe events") cleaned up the usage of trace_uprobe_create(), and the function has been no longer used for removing uprobe/uretprobe. Link: http://lkml.kernel.org/r/20190614074026.8045-2-devel@etsukata.com Reviewed-by: Srikar Dronamraju Signed-off-by: Eiichi Tsukata Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_uprobe.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index a88c692e3b8a..b55906c77ce0 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -426,8 +426,6 @@ end: /* * Argument syntax: * - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS] - * - * - Remove uprobe: -:[GRP/]EVENT */ static int trace_uprobe_create(int argc, const char **argv) { -- cgit v1.2.3-55-g7522 From 9f255b632bf12c4dd7fc31caee89aa991ef75176 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 13 Jun 2019 20:07:22 -0500 Subject: module: Fix livepatch/ftrace module text permissions race It's possible for livepatch and ftrace to be toggling a module's text permissions at the same time, resulting in the following panic: BUG: unable to handle page fault for address: ffffffffc005b1d9 #PF: supervisor write access in kernel mode #PF: error_code(0x0003) - permissions violation PGD 3ea0c067 P4D 3ea0c067 PUD 3ea0e067 PMD 3cc13067 PTE 3b8a1061 Oops: 0003 [#1] PREEMPT SMP PTI CPU: 1 PID: 453 Comm: insmod Tainted: G O K 5.2.0-rc1-a188339ca5 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-20181126_142135-anatol 04/01/2014 RIP: 0010:apply_relocate_add+0xbe/0x14c Code: fa 0b 74 21 48 83 fa 18 74 38 48 83 fa 0a 75 40 eb 08 48 83 38 00 74 33 eb 53 83 38 00 75 4e 89 08 89 c8 eb 0a 83 38 00 75 43 <89> 08 48 63 c1 48 39 c8 74 2e eb 48 83 38 00 75 32 48 29 c1 89 08 RSP: 0018:ffffb223c00dbb10 EFLAGS: 00010246 RAX: ffffffffc005b1d9 RBX: 0000000000000000 RCX: ffffffff8b200060 RDX: 000000000000000b RSI: 0000004b0000000b RDI: ffff96bdfcd33000 RBP: ffffb223c00dbb38 R08: ffffffffc005d040 R09: ffffffffc005c1f0 R10: ffff96bdfcd33c40 R11: ffff96bdfcd33b80 R12: 0000000000000018 R13: ffffffffc005c1f0 R14: ffffffffc005e708 R15: ffffffff8b2fbc74 FS: 00007f5f447beba8(0000) GS:ffff96bdff900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffc005b1d9 CR3: 000000003cedc002 CR4: 0000000000360ea0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: klp_init_object_loaded+0x10f/0x219 ? preempt_latency_start+0x21/0x57 klp_enable_patch+0x662/0x809 ? virt_to_head_page+0x3a/0x3c ? kfree+0x8c/0x126 patch_init+0x2ed/0x1000 [livepatch_test02] ? 0xffffffffc0060000 do_one_initcall+0x9f/0x1c5 ? kmem_cache_alloc_trace+0xc4/0xd4 ? do_init_module+0x27/0x210 do_init_module+0x5f/0x210 load_module+0x1c41/0x2290 ? fsnotify_path+0x3b/0x42 ? strstarts+0x2b/0x2b ? kernel_read+0x58/0x65 __do_sys_finit_module+0x9f/0xc3 ? __do_sys_finit_module+0x9f/0xc3 __x64_sys_finit_module+0x1a/0x1c do_syscall_64+0x52/0x61 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The above panic occurs when loading two modules at the same time with ftrace enabled, where at least one of the modules is a livepatch module: CPU0 CPU1 klp_enable_patch() klp_init_object_loaded() module_disable_ro() ftrace_module_enable() ftrace_arch_code_modify_post_process() set_all_modules_text_ro() klp_write_object_relocations() apply_relocate_add() *patches read-only code* - BOOM A similar race exists when toggling ftrace while loading a livepatch module. Fix it by ensuring that the livepatch and ftrace code patching operations -- and their respective permissions changes -- are protected by the text_mutex. Link: http://lkml.kernel.org/r/ab43d56ab909469ac5d2520c5d944ad6d4abd476.1560474114.git.jpoimboe@redhat.com Reported-by: Johannes Erdfelt Fixes: 444d13ff10fb ("modules: add ro_after_init support") Acked-by: Jessica Yu Reviewed-by: Petr Mladek Reviewed-by: Miroslav Benes Signed-off-by: Josh Poimboeuf Signed-off-by: Steven Rostedt (VMware) --- kernel/livepatch/core.c | 6 ++++++ kernel/trace/ftrace.c | 10 +++++++++- 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 91cd519756d3..2d17e6e364b5 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include "core.h" #include "patch.h" @@ -730,16 +731,21 @@ static int klp_init_object_loaded(struct klp_patch *patch, struct klp_func *func; int ret; + mutex_lock(&text_mutex); + module_disable_ro(patch->mod); ret = klp_write_object_relocations(patch->mod, obj); if (ret) { module_enable_ro(patch->mod, true); + mutex_unlock(&text_mutex); return ret; } arch_klp_init_object_loaded(patch, obj); module_enable_ro(patch->mod, true); + mutex_unlock(&text_mutex); + klp_for_each_func(obj, func) { ret = klp_find_object_symbol(obj->name, func->old_name, func->old_sympos, diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index e77a6c92620f..a89700590485 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -34,6 +34,7 @@ #include #include #include +#include #include @@ -2610,10 +2611,12 @@ static void ftrace_run_update_code(int command) { int ret; + mutex_lock(&text_mutex); + ret = ftrace_arch_code_modify_prepare(); FTRACE_WARN_ON(ret); if (ret) - return; + goto out_unlock; /* * By default we use stop_machine() to modify the code. @@ -2625,6 +2628,9 @@ static void ftrace_run_update_code(int command) ret = ftrace_arch_code_modify_post_process(); FTRACE_WARN_ON(ret); + +out_unlock: + mutex_unlock(&text_mutex); } static void ftrace_run_modify_code(struct ftrace_ops *ops, int command, @@ -5775,6 +5781,7 @@ void ftrace_module_enable(struct module *mod) struct ftrace_page *pg; mutex_lock(&ftrace_lock); + mutex_lock(&text_mutex); if (ftrace_disabled) goto out_unlock; @@ -5836,6 +5843,7 @@ void ftrace_module_enable(struct module *mod) ftrace_arch_code_modify_post_process(); out_unlock: + mutex_unlock(&text_mutex); mutex_unlock(&ftrace_lock); process_cached_mods(mod->name); -- cgit v1.2.3-55-g7522 From 04e03d9a616c19a47178eaca835358610e63a1dd Mon Sep 17 00:00:00 2001 From: Wei Li Date: Thu, 6 Jun 2019 11:17:54 +0800 Subject: ftrace: Fix NULL pointer dereference in free_ftrace_func_mapper() The mapper may be NULL when called from register_ftrace_function_probe() with probe->data == NULL. This issue can be reproduced as follow (it may be covered by compiler optimization sometime): / # cat /sys/kernel/debug/tracing/set_ftrace_filter #### all functions enabled #### / # echo foo_bar:dump > /sys/kernel/debug/tracing/set_ftrace_filter [ 206.949100] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 206.952402] Mem abort info: [ 206.952819] ESR = 0x96000006 [ 206.955326] Exception class = DABT (current EL), IL = 32 bits [ 206.955844] SET = 0, FnV = 0 [ 206.956272] EA = 0, S1PTW = 0 [ 206.956652] Data abort info: [ 206.957320] ISV = 0, ISS = 0x00000006 [ 206.959271] CM = 0, WnR = 0 [ 206.959938] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000419f3a000 [ 206.960483] [0000000000000000] pgd=0000000411a87003, pud=0000000411a83003, pmd=0000000000000000 [ 206.964953] Internal error: Oops: 96000006 [#1] SMP [ 206.971122] Dumping ftrace buffer: [ 206.973677] (ftrace buffer empty) [ 206.975258] Modules linked in: [ 206.976631] Process sh (pid: 281, stack limit = 0x(____ptrval____)) [ 206.978449] CPU: 10 PID: 281 Comm: sh Not tainted 5.2.0-rc1+ #17 [ 206.978955] Hardware name: linux,dummy-virt (DT) [ 206.979883] pstate: 60000005 (nZCv daif -PAN -UAO) [ 206.980499] pc : free_ftrace_func_mapper+0x2c/0x118 [ 206.980874] lr : ftrace_count_free+0x68/0x80 [ 206.982539] sp : ffff0000182f3ab0 [ 206.983102] x29: ffff0000182f3ab0 x28: ffff8003d0ec1700 [ 206.983632] x27: ffff000013054b40 x26: 0000000000000001 [ 206.984000] x25: ffff00001385f000 x24: 0000000000000000 [ 206.984394] x23: ffff000013453000 x22: ffff000013054000 [ 206.984775] x21: 0000000000000000 x20: ffff00001385fe28 [ 206.986575] x19: ffff000013872c30 x18: 0000000000000000 [ 206.987111] x17: 0000000000000000 x16: 0000000000000000 [ 206.987491] x15: ffffffffffffffb0 x14: 0000000000000000 [ 206.987850] x13: 000000000017430e x12: 0000000000000580 [ 206.988251] x11: 0000000000000000 x10: cccccccccccccccc [ 206.988740] x9 : 0000000000000000 x8 : ffff000013917550 [ 206.990198] x7 : ffff000012fac2e8 x6 : ffff000012fac000 [ 206.991008] x5 : ffff0000103da588 x4 : 0000000000000001 [ 206.991395] x3 : 0000000000000001 x2 : ffff000013872a28 [ 206.991771] x1 : 0000000000000000 x0 : 0000000000000000 [ 206.992557] Call trace: [ 206.993101] free_ftrace_func_mapper+0x2c/0x118 [ 206.994827] ftrace_count_free+0x68/0x80 [ 206.995238] release_probe+0xfc/0x1d0 [ 206.995555] register_ftrace_function_probe+0x4a8/0x868 [ 206.995923] ftrace_trace_probe_callback.isra.4+0xb8/0x180 [ 206.996330] ftrace_dump_callback+0x50/0x70 [ 206.996663] ftrace_regex_write.isra.29+0x290/0x3a8 [ 206.997157] ftrace_filter_write+0x44/0x60 [ 206.998971] __vfs_write+0x64/0xf0 [ 206.999285] vfs_write+0x14c/0x2f0 [ 206.999591] ksys_write+0xbc/0x1b0 [ 206.999888] __arm64_sys_write+0x3c/0x58 [ 207.000246] el0_svc_common.constprop.0+0x408/0x5f0 [ 207.000607] el0_svc_handler+0x144/0x1c8 [ 207.000916] el0_svc+0x8/0xc [ 207.003699] Code: aa0003f8 a9025bf5 aa0103f5 f946ea80 (f9400303) [ 207.008388] ---[ end trace 7b6d11b5f542bdf1 ]--- [ 207.010126] Kernel panic - not syncing: Fatal exception [ 207.011322] SMP: stopping secondary CPUs [ 207.013956] Dumping ftrace buffer: [ 207.014595] (ftrace buffer empty) [ 207.015632] Kernel Offset: disabled [ 207.017187] CPU features: 0x002,20006008 [ 207.017985] Memory Limit: none [ 207.019825] ---[ end Kernel panic - not syncing: Fatal exception ]--- Link: http://lkml.kernel.org/r/20190606031754.10798-1-liwei391@huawei.com Signed-off-by: Wei Li Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index a89700590485..38277af44f5c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4226,10 +4226,13 @@ void free_ftrace_func_mapper(struct ftrace_func_mapper *mapper, struct ftrace_func_entry *entry; struct ftrace_func_map *map; struct hlist_head *hhd; - int size = 1 << mapper->hash.size_bits; - int i; + int size, i; + + if (!mapper) + return; if (free_func && mapper->hash.count) { + size = 1 << mapper->hash.size_bits; for (i = 0; i < size; i++) { hhd = &mapper->hash.buckets[i]; hlist_for_each_entry(entry, hhd, hlist) { -- cgit v1.2.3-55-g7522 From 9594dc3c7e71b9f52bee1d7852eb3d4e3aea9e99 Mon Sep 17 00:00:00 2001 From: Matt Mullins Date: Tue, 11 Jun 2019 14:53:04 -0700 Subject: bpf: fix nested bpf tracepoints with per-cpu data BPF_PROG_TYPE_RAW_TRACEPOINTs can be executed nested on the same CPU, as they do not increment bpf_prog_active while executing. This enables three levels of nesting, to support - a kprobe or raw tp or perf event, - another one of the above that irq context happens to call, and - another one in nmi context (at most one of which may be a kprobe or perf event). Fixes: 20b9d7ac4852 ("bpf: avoid excessive stack usage for perf_sample_data") Signed-off-by: Matt Mullins Acked-by: Andrii Nakryiko Acked-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- kernel/trace/bpf_trace.c | 100 +++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 84 insertions(+), 16 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index f92d6ad5e080..1c9a4745e596 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -410,8 +410,6 @@ static const struct bpf_func_proto bpf_perf_event_read_value_proto = { .arg4_type = ARG_CONST_SIZE, }; -static DEFINE_PER_CPU(struct perf_sample_data, bpf_trace_sd); - static __always_inline u64 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, u64 flags, struct perf_sample_data *sd) @@ -442,24 +440,50 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, return perf_event_output(event, sd, regs); } +/* + * Support executing tracepoints in normal, irq, and nmi context that each call + * bpf_perf_event_output + */ +struct bpf_trace_sample_data { + struct perf_sample_data sds[3]; +}; + +static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_trace_sds); +static DEFINE_PER_CPU(int, bpf_trace_nest_level); BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, u64, flags, void *, data, u64, size) { - struct perf_sample_data *sd = this_cpu_ptr(&bpf_trace_sd); + struct bpf_trace_sample_data *sds = this_cpu_ptr(&bpf_trace_sds); + int nest_level = this_cpu_inc_return(bpf_trace_nest_level); struct perf_raw_record raw = { .frag = { .size = size, .data = data, }, }; + struct perf_sample_data *sd; + int err; - if (unlikely(flags & ~(BPF_F_INDEX_MASK))) - return -EINVAL; + if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) { + err = -EBUSY; + goto out; + } + + sd = &sds->sds[nest_level - 1]; + + if (unlikely(flags & ~(BPF_F_INDEX_MASK))) { + err = -EINVAL; + goto out; + } perf_sample_data_init(sd, 0, 0); sd->raw = &raw; - return __bpf_perf_event_output(regs, map, flags, sd); + err = __bpf_perf_event_output(regs, map, flags, sd); + +out: + this_cpu_dec(bpf_trace_nest_level); + return err; } static const struct bpf_func_proto bpf_perf_event_output_proto = { @@ -822,16 +846,48 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) /* * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp * to avoid potential recursive reuse issue when/if tracepoints are added - * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack + * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack. + * + * Since raw tracepoints run despite bpf_prog_active, support concurrent usage + * in normal, irq, and nmi context. */ -static DEFINE_PER_CPU(struct pt_regs, bpf_raw_tp_regs); +struct bpf_raw_tp_regs { + struct pt_regs regs[3]; +}; +static DEFINE_PER_CPU(struct bpf_raw_tp_regs, bpf_raw_tp_regs); +static DEFINE_PER_CPU(int, bpf_raw_tp_nest_level); +static struct pt_regs *get_bpf_raw_tp_regs(void) +{ + struct bpf_raw_tp_regs *tp_regs = this_cpu_ptr(&bpf_raw_tp_regs); + int nest_level = this_cpu_inc_return(bpf_raw_tp_nest_level); + + if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(tp_regs->regs))) { + this_cpu_dec(bpf_raw_tp_nest_level); + return ERR_PTR(-EBUSY); + } + + return &tp_regs->regs[nest_level - 1]; +} + +static void put_bpf_raw_tp_regs(void) +{ + this_cpu_dec(bpf_raw_tp_nest_level); +} + BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags, void *, data, u64, size) { - struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs); + struct pt_regs *regs = get_bpf_raw_tp_regs(); + int ret; + + if (IS_ERR(regs)) + return PTR_ERR(regs); perf_fetch_caller_regs(regs); - return ____bpf_perf_event_output(regs, map, flags, data, size); + ret = ____bpf_perf_event_output(regs, map, flags, data, size); + + put_bpf_raw_tp_regs(); + return ret; } static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { @@ -848,12 +904,18 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags) { - struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs); + struct pt_regs *regs = get_bpf_raw_tp_regs(); + int ret; + + if (IS_ERR(regs)) + return PTR_ERR(regs); perf_fetch_caller_regs(regs); /* similar to bpf_perf_event_output_tp, but pt_regs fetched differently */ - return bpf_get_stackid((unsigned long) regs, (unsigned long) map, - flags, 0, 0); + ret = bpf_get_stackid((unsigned long) regs, (unsigned long) map, + flags, 0, 0); + put_bpf_raw_tp_regs(); + return ret; } static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = { @@ -868,11 +930,17 @@ static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = { BPF_CALL_4(bpf_get_stack_raw_tp, struct bpf_raw_tracepoint_args *, args, void *, buf, u32, size, u64, flags) { - struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs); + struct pt_regs *regs = get_bpf_raw_tp_regs(); + int ret; + + if (IS_ERR(regs)) + return PTR_ERR(regs); perf_fetch_caller_regs(regs); - return bpf_get_stack((unsigned long) regs, (unsigned long) buf, - (unsigned long) size, flags, 0); + ret = bpf_get_stack((unsigned long) regs, (unsigned long) buf, + (unsigned long) size, flags, 0); + put_bpf_raw_tp_regs(); + return ret; } static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = { -- cgit v1.2.3-55-g7522