From e0213434fe3e4a0d118923dc98d31e7ff1cd9e45 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 1 Mar 2023 20:00:52 -0500 Subject: [PATCH 1/5] tracing: Do not let histogram values have some modifiers Histogram values can not be strings, stacktraces, graphs, symbols, syscalls, or grouped in buckets or log. Give an error if a value is set to do so. Note, the histogram code was not prepared to handle these modifiers for histograms and caused a bug. Mark Rutland reported: # echo 'p:copy_to_user __arch_copy_to_user n=$arg2' >> /sys/kernel/tracing/kprobe_events # echo 'hist:keys=n:vals=hitcount.buckets=8:sort=hitcount' > /sys/kernel/tracing/events/kprobes/copy_to_user/trigger # cat /sys/kernel/tracing/events/kprobes/copy_to_user/hist [ 143.694628] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 143.695190] Mem abort info: [ 143.695362] ESR = 0x0000000096000004 [ 143.695604] EC = 0x25: DABT (current EL), IL = 32 bits [ 143.695889] SET = 0, FnV = 0 [ 143.696077] EA = 0, S1PTW = 0 [ 143.696302] FSC = 0x04: level 0 translation fault [ 143.702381] Data abort info: [ 143.702614] ISV = 0, ISS = 0x00000004 [ 143.702832] CM = 0, WnR = 0 [ 143.703087] user pgtable: 4k pages, 48-bit VAs, pgdp=00000000448f9000 [ 143.703407] [0000000000000000] pgd=0000000000000000, p4d=0000000000000000 [ 143.704137] Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP [ 143.704714] Modules linked in: [ 143.705273] CPU: 0 PID: 133 Comm: cat Not tainted 6.2.0-00003-g6fc512c10a7c #3 [ 143.706138] Hardware name: linux,dummy-virt (DT) [ 143.706723] pstate: 80000005 (Nzcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 143.707120] pc : hist_field_name.part.0+0x14/0x140 [ 143.707504] lr : hist_field_name.part.0+0x104/0x140 [ 143.707774] sp : ffff800008333a30 [ 143.707952] x29: ffff800008333a30 x28: 0000000000000001 x27: 0000000000400cc0 [ 143.708429] x26: ffffd7a653b20260 x25: 0000000000000000 x24: ffff10d303ee5800 [ 143.708776] x23: ffffd7a6539b27b0 x22: ffff10d303fb8c00 x21: 0000000000000001 [ 143.709127] x20: ffff10d303ec2000 x19: 0000000000000000 x18: 0000000000000000 [ 143.709478] x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 [ 143.709824] x14: 0000000000000000 x13: 203a6f666e692072 x12: 6567676972742023 [ 143.710179] x11: 0a230a6d6172676f x10: 000000000000002c x9 : ffffd7a6521e018c [ 143.710584] x8 : 000000000000002c x7 : 7f7f7f7f7f7f7f7f x6 : 000000000000002c [ 143.710915] x5 : ffff10d303b0103e x4 : ffffd7a653b20261 x3 : 000000000000003d [ 143.711239] x2 : 0000000000020001 x1 : 0000000000000001 x0 : 0000000000000000 [ 143.711746] Call trace: [ 143.712115] hist_field_name.part.0+0x14/0x140 [ 143.712642] hist_field_name.part.0+0x104/0x140 [ 143.712925] hist_field_print+0x28/0x140 [ 143.713125] event_hist_trigger_print+0x174/0x4d0 [ 143.713348] hist_show+0xf8/0x980 [ 143.713521] seq_read_iter+0x1bc/0x4b0 [ 143.713711] seq_read+0x8c/0xc4 [ 143.713876] vfs_read+0xc8/0x2a4 [ 143.714043] ksys_read+0x70/0xfc [ 143.714218] __arm64_sys_read+0x24/0x30 [ 143.714400] invoke_syscall+0x50/0x120 [ 143.714587] el0_svc_common.constprop.0+0x4c/0x100 [ 143.714807] do_el0_svc+0x44/0xd0 [ 143.714970] el0_svc+0x2c/0x84 [ 143.715134] el0t_64_sync_handler+0xbc/0x140 [ 143.715334] el0t_64_sync+0x190/0x194 [ 143.715742] Code: a9bd7bfd 910003fd a90153f3 aa0003f3 (f9400000) [ 143.716510] ---[ end trace 0000000000000000 ]--- Segmentation fault Link: https://lkml.kernel.org/r/20230302020810.559462599@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Andrew Morton Fixes: c6afad49d127f ("tracing: Add hist trigger 'sym' and 'sym-offset' modifiers") Reported-by: Mark Rutland Tested-by: Mark Rutland Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_hist.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 89877a18f933..6e8ab726a7b5 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -4235,6 +4235,15 @@ static int __create_val_field(struct hist_trigger_data *hist_data, goto out; } + /* Some types cannot be a value */ + if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT | + HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 | + HIST_FIELD_FL_SYM | HIST_FIELD_FL_SYM_OFFSET | + HIST_FIELD_FL_SYSCALL | HIST_FIELD_FL_STACKTRACE)) { + hist_err(file->tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str)); + ret = -EINVAL; + } + hist_data->fields[val_idx] = hist_field; ++hist_data->n_vals; From 9f116f76fa8c04c81aef33ad870dbf9a158e5b70 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 1 Mar 2023 20:00:53 -0500 Subject: [PATCH 2/5] tracing: Check field value in hist_field_name() The function hist_field_name() cannot handle being passed a NULL field parameter. It should never be NULL, but due to a previous bug, NULL was passed to the function and the kernel crashed due to a NULL dereference. Mark Rutland reported this to me on IRC. The bug was fixed, but to prevent future bugs from crashing the kernel, check the field and add a WARN_ON() if it is NULL. Link: https://lkml.kernel.org/r/20230302020810.762384440@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Andrew Morton Reported-by: Mark Rutland Fixes: c6afad49d127f ("tracing: Add hist trigger 'sym' and 'sym-offset' modifiers") Tested-by: Mark Rutland Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_hist.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 6e8ab726a7b5..486cca3c2b75 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1331,6 +1331,9 @@ static const char *hist_field_name(struct hist_field *field, { const char *field_name = ""; + if (WARN_ON_ONCE(!field)) + return field_name; + if (level > 1) return field_name; From ee92fa443358f4fc0017c1d0d325c27b37802504 Mon Sep 17 00:00:00 2001 From: Chen Zhongjin Date: Thu, 9 Mar 2023 16:02:30 +0800 Subject: [PATCH 3/5] ftrace: Fix invalid address access in lookup_rec() when index is 0 KASAN reported follow problem: BUG: KASAN: use-after-free in lookup_rec Read of size 8 at addr ffff000199270ff0 by task modprobe CPU: 2 Comm: modprobe Call trace: kasan_report __asan_load8 lookup_rec ftrace_location arch_check_ftrace_location check_kprobe_address_safe register_kprobe When checking pg->records[pg->index - 1].ip in lookup_rec(), it can get a pg which is newly added to ftrace_pages_start in ftrace_process_locs(). Before the first pg->index++, index is 0 and accessing pg->records[-1].ip will cause this problem. Don't check the ip when pg->index is 0. Link: https://lore.kernel.org/linux-trace-kernel/20230309080230.36064-1-chenzhongjin@huawei.com Cc: stable@vger.kernel.org Fixes: 9644302e3315 ("ftrace: Speed up search by skipping pages by address") Suggested-by: Steven Rostedt (Google) Signed-off-by: Chen Zhongjin Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 750aa3f08b25..a47f7d93e32d 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1537,7 +1537,8 @@ static struct dyn_ftrace *lookup_rec(unsigned long start, unsigned long end) key.flags = end; /* overload flags, as it is unsigned long */ for (pg = ftrace_pages_start; pg; pg = pg->next) { - if (end < pg->records[0].ip || + if (pg->index == 0 || + end < pg->records[0].ip || start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE)) continue; rec = bsearch(&key, pg->records, pg->index, From aa69f814920d85a2d4cfd5c294757c3d59d2fba6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 31 Jan 2023 10:36:30 +0100 Subject: [PATCH 4/5] ftrace,kcfi: Define ftrace_stub_graph conditionally When CONFIG_FUNCTION_GRAPH_TRACER is disabled, __kcfi_typeid_ftrace_stub_graph is missing, causing a link failure: ld.lld: error: undefined symbol: __kcfi_typeid_ftrace_stub_graph referenced by arch/x86/kernel/ftrace_64.o:(__cfi_ftrace_stub_graph) in archive vmlinux.a Mark the reference to it as conditional on the same symbol, as is done on arm64. Link: https://lore.kernel.org/linux-trace-kernel/20230131093643.3850272-1-arnd@kernel.org Cc: Peter Zijlstra Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Josh Poimboeuf Fixes: 883bbbffa5a4 ("ftrace,kcfi: Separate ftrace_stub() and ftrace_stub_graph()") See-also: 2598ac6ec493 ("arm64: ftrace: Define ftrace_stub_graph only with FUNCTION_GRAPH_TRACER") Signed-off-by: Arnd Bergmann Signed-off-by: Steven Rostedt (Google) --- arch/x86/kernel/ftrace_64.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 1265ad519249..fb4f1e01b64a 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -136,10 +136,12 @@ SYM_TYPED_FUNC_START(ftrace_stub) RET SYM_FUNC_END(ftrace_stub) +#ifdef CONFIG_FUNCTION_GRAPH_TRACER SYM_TYPED_FUNC_START(ftrace_stub_graph) CALL_DEPTH_ACCOUNT RET SYM_FUNC_END(ftrace_stub_graph) +#endif #ifdef CONFIG_DYNAMIC_FTRACE From c2679254b9c9980d9045f0f722cf093a2b1f7590 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Fri, 10 Mar 2023 17:28:56 -0500 Subject: [PATCH 5/5] tracing: Make tracepoint lockdep check actually test something A while ago where the trace events had the following: rcu_read_lock_sched_notrace(); rcu_dereference_sched(...); rcu_read_unlock_sched_notrace(); If the tracepoint is enabled, it could trigger RCU issues if called in the wrong place. And this warning was only triggered if lockdep was enabled. If the tracepoint was never enabled with lockdep, the bug would not be caught. To handle this, the above sequence was done when lockdep was enabled regardless if the tracepoint was enabled or not (although the always enabled code really didn't do anything, it would still trigger a warning). But a lot has changed since that lockdep code was added. One is, that sequence no longer triggers any warning. Another is, the tracepoint when enabled doesn't even do that sequence anymore. The main check we care about today is whether RCU is "watching" or not. So if lockdep is enabled, always check if rcu_is_watching() which will trigger a warning if it is not (tracepoints require RCU to be watching). Note, that old sequence did add a bit of overhead when lockdep was enabled, and with the latest kernel updates, would cause the system to slow down enough to trigger kernel "stalled" warnings. Link: http://lore.kernel.org/lkml/20140806181801.GA4605@redhat.com Link: http://lore.kernel.org/lkml/20140807175204.C257CAC5@viggo.jf.intel.com Link: https://lore.kernel.org/lkml/20230307184645.521db5c9@gandalf.local.home/ Link: https://lore.kernel.org/linux-trace-kernel/20230310172856.77406446@gandalf.local.home Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Dave Hansen Cc: "Paul E. McKenney" Cc: Mathieu Desnoyers Cc: Joel Fernandes Acked-by: Peter Zijlstra (Intel) Acked-by: Paul E. McKenney Fixes: e6753f23d961 ("tracepoint: Make rcuidle tracepoint callers use SRCU") Signed-off-by: Steven Rostedt (Google) --- include/linux/tracepoint.h | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index fa1004fcf810..2083f2d2f05b 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -231,12 +231,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * not add unwanted padding between the beginning of the section and the * structure. Force alignment to the same alignment as the section start. * - * When lockdep is enabled, we make sure to always do the RCU portions of - * the tracepoint code, regardless of whether tracing is on. However, - * don't check if the condition is false, due to interaction with idle - * instrumentation. This lets us find RCU issues triggered with tracepoints - * even when this tracepoint is off. This code has no purpose other than - * poking RCU a bit. + * When lockdep is enabled, we make sure to always test if RCU is + * "watching" regardless if the tracepoint is enabled or not. Tracepoints + * require RCU to be active, and it should always warn at the tracepoint + * site if it is not watching, as it will need to be active when the + * tracepoint is enabled. */ #define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ extern int __traceiter_##name(data_proto); \ @@ -249,9 +248,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) TP_ARGS(args), \ TP_CONDITION(cond), 0); \ if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \ - rcu_read_lock_sched_notrace(); \ - rcu_dereference_sched(__tracepoint_##name.funcs);\ - rcu_read_unlock_sched_notrace(); \ + WARN_ON_ONCE(!rcu_is_watching()); \ } \ } \ __DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args), \