Include additional patch (Andrii Nakryiko) since its a dependency
Andrii Nakryiko (1): uprobes: encapsulate preparation of uprobe args buffer
Qiao Ma (1): uprobe: avoid out-of-bounds memory access of fetching args
kernel/trace/trace_uprobe.c | 86 ++++++++++++++++++++----------------- 1 file changed, 46 insertions(+), 40 deletions(-)
From: Andrii Nakryiko andrii@kernel.org
[ Upstream commit 3eaea21b4d27cff0017c20549aeb53034c58fc23 ]
Move the logic of fetching temporary per-CPU uprobe buffer and storing uprobes args into it to a new helper function. Store data size as part of this buffer, simplifying interfaces a bit, as now we only pass single uprobe_cpu_buffer reference around, instead of pointer + dsize.
This logic was duplicated across uprobe_dispatcher and uretprobe_dispatcher, and now will be centralized. All this is also in preparation to make this uprobe_cpu_buffer handling logic optional in the next patch.
Link: https://lore.kernel.org/all/20240318181728.2795838-2-andrii@kernel.org/ [Masami: update for v6.9-rc3 kernel]
Signed-off-by: Andrii Nakryiko andrii@kernel.org Reviewed-by: Jiri Olsa jolsa@kernel.org Acked-by: Masami Hiramatsu (Google) mhiramat@kernel.org Signed-off-by: Masami Hiramatsu (Google) mhiramat@kernel.org Stable-dep-of: 373b9338c972 ("uprobe: avoid out-of-bounds memory access of fetching args") Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Vamsi Krishna Brahmajosyula vamsi-krishna.brahmajosyula@broadcom.com --- kernel/trace/trace_uprobe.c | 79 +++++++++++++++++++------------------ 1 file changed, 41 insertions(+), 38 deletions(-)
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 127c78aec17d..e09eef65d32f 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -858,6 +858,7 @@ static const struct file_operations uprobe_profile_ops = { struct uprobe_cpu_buffer { struct mutex mutex; void *buf; + int dsize; }; static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer; static int uprobe_buffer_refcnt; @@ -947,9 +948,26 @@ static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb) mutex_unlock(&ucb->mutex); }
+static struct uprobe_cpu_buffer *prepare_uprobe_buffer(struct trace_uprobe *tu, + struct pt_regs *regs) +{ + struct uprobe_cpu_buffer *ucb; + int dsize, esize; + + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + dsize = __get_data_size(&tu->tp, regs); + + ucb = uprobe_buffer_get(); + ucb->dsize = tu->tp.size + dsize; + + store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize); + + return ucb; +} + static void __uprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize, + struct uprobe_cpu_buffer *ucb, struct trace_event_file *trace_file) { struct uprobe_trace_entry_head *entry; @@ -960,14 +978,14 @@ static void __uprobe_trace_func(struct trace_uprobe *tu,
WARN_ON(call != trace_file->event_call);
- if (WARN_ON_ONCE(tu->tp.size + dsize > PAGE_SIZE)) + if (WARN_ON_ONCE(ucb->dsize > PAGE_SIZE)) return;
if (trace_trigger_soft_disabled(trace_file)) return;
esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); - size = esize + tu->tp.size + dsize; + size = esize + ucb->dsize; entry = trace_event_buffer_reserve(&fbuffer, trace_file, size); if (!entry) return; @@ -981,14 +999,14 @@ static void __uprobe_trace_func(struct trace_uprobe *tu, data = DATAOF_TRACE_ENTRY(entry, false); }
- memcpy(data, ucb->buf, tu->tp.size + dsize); + memcpy(data, ucb->buf, ucb->dsize);
trace_event_buffer_commit(&fbuffer); }
/* uprobe handler */ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize) + struct uprobe_cpu_buffer *ucb) { struct event_file_link *link;
@@ -997,7 +1015,7 @@ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs,
rcu_read_lock(); trace_probe_for_each_link_rcu(link, &tu->tp) - __uprobe_trace_func(tu, 0, regs, ucb, dsize, link->file); + __uprobe_trace_func(tu, 0, regs, ucb, link->file); rcu_read_unlock();
return 0; @@ -1005,13 +1023,13 @@ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs,
static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize) + struct uprobe_cpu_buffer *ucb) { struct event_file_link *link;
rcu_read_lock(); trace_probe_for_each_link_rcu(link, &tu->tp) - __uprobe_trace_func(tu, func, regs, ucb, dsize, link->file); + __uprobe_trace_func(tu, func, regs, ucb, link->file); rcu_read_unlock(); }
@@ -1339,7 +1357,7 @@ static bool uprobe_perf_filter(struct uprobe_consumer *uc,
static void __uprobe_perf_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize) + struct uprobe_cpu_buffer *ucb) { struct trace_event_call *call = trace_probe_event_call(&tu->tp); struct uprobe_trace_entry_head *entry; @@ -1360,7 +1378,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
- size = esize + tu->tp.size + dsize; + size = esize + ucb->dsize; size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) return; @@ -1383,13 +1401,10 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, data = DATAOF_TRACE_ENTRY(entry, false); }
- memcpy(data, ucb->buf, tu->tp.size + dsize); - - if (size - esize > tu->tp.size + dsize) { - int len = tu->tp.size + dsize; + memcpy(data, ucb->buf, ucb->dsize);
- memset(data + len, 0, size - esize - len); - } + if (size - esize > ucb->dsize) + memset(data + ucb->dsize, 0, size - esize - ucb->dsize);
perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); @@ -1399,21 +1414,21 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
/* uprobe profile handler */ static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize) + struct uprobe_cpu_buffer *ucb) { if (!uprobe_perf_filter(&tu->consumer, 0, current->mm)) return UPROBE_HANDLER_REMOVE;
if (!is_ret_probe(tu)) - __uprobe_perf_func(tu, 0, regs, ucb, dsize); + __uprobe_perf_func(tu, 0, regs, ucb); return 0; }
static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize) + struct uprobe_cpu_buffer *ucb) { - __uprobe_perf_func(tu, func, regs, ucb, dsize); + __uprobe_perf_func(tu, func, regs, ucb); }
int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, @@ -1479,10 +1494,8 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) struct trace_uprobe *tu; struct uprobe_dispatch_data udd; struct uprobe_cpu_buffer *ucb; - int dsize, esize; int ret = 0;
- tu = container_of(con, struct trace_uprobe, consumer); tu->nhit++;
@@ -1494,18 +1507,14 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) if (WARN_ON_ONCE(!uprobe_cpu_buffer)) return 0;
- dsize = __get_data_size(&tu->tp, regs); - esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); - - ucb = uprobe_buffer_get(); - store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize); + ucb = prepare_uprobe_buffer(tu, regs);
if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) - ret |= uprobe_trace_func(tu, regs, ucb, dsize); + ret |= uprobe_trace_func(tu, regs, ucb);
#ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE)) - ret |= uprobe_perf_func(tu, regs, ucb, dsize); + ret |= uprobe_perf_func(tu, regs, ucb); #endif uprobe_buffer_put(ucb); return ret; @@ -1517,7 +1526,6 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con, struct trace_uprobe *tu; struct uprobe_dispatch_data udd; struct uprobe_cpu_buffer *ucb; - int dsize, esize;
tu = container_of(con, struct trace_uprobe, consumer);
@@ -1529,18 +1537,13 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con, if (WARN_ON_ONCE(!uprobe_cpu_buffer)) return 0;
- dsize = __get_data_size(&tu->tp, regs); - esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); - - ucb = uprobe_buffer_get(); - store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize); - + ucb = prepare_uprobe_buffer(tu, regs); if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) - uretprobe_trace_func(tu, func, regs, ucb, dsize); + uretprobe_trace_func(tu, func, regs, ucb);
#ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE)) - uretprobe_perf_func(tu, func, regs, ucb, dsize); + uretprobe_perf_func(tu, func, regs, ucb); #endif uprobe_buffer_put(ucb); return 0;
From: Qiao Ma mqaio@linux.alibaba.com
[ Upstream commit 373b9338c9722a368925d83bc622c596896b328e ]
Uprobe needs to fetch args into a percpu buffer, and then copy to ring buffer to avoid non-atomic context problem.
Sometimes user-space strings, arrays can be very large, but the size of percpu buffer is only page size. And store_trace_args() won't check whether these data exceeds a single page or not, caused out-of-bounds memory access.
It could be reproduced by following steps: 1. build kernel with CONFIG_KASAN enabled 2. save follow program as test.c
``` #include <stdio.h> #include <stdlib.h> #include <string.h>
// If string length large than MAX_STRING_SIZE, the fetch_store_strlen() // will return 0, cause __get_data_size() return shorter size, and // store_trace_args() will not trigger out-of-bounds access. // So make string length less than 4096. #define STRLEN 4093
void generate_string(char *str, int n) { int i; for (i = 0; i < n; ++i) { char c = i % 26 + 'a'; str[i] = c; } str[n-1] = '\0'; }
void print_string(char *str) { printf("%s\n", str); }
int main() { char tmp[STRLEN];
generate_string(tmp, STRLEN); print_string(tmp);
return 0; } ``` 3. compile program `gcc -o test test.c`
4. get the offset of `print_string()` ``` objdump -t test | grep -w print_string 0000000000401199 g F .text 000000000000001b print_string ```
5. configure uprobe with offset 0x1199 ``` off=0x1199
cd /sys/kernel/debug/tracing/ echo "p /root/test:${off} arg1=+0(%di):ustring arg2=$comm arg3=+0(%di):ustring"
uprobe_events
echo 1 > events/uprobes/enable echo 1 > tracing_on ```
6. run `test`, and kasan will report error. ================================================================== BUG: KASAN: use-after-free in strncpy_from_user+0x1d6/0x1f0 Write of size 8 at addr ffff88812311c004 by task test/499CPU: 0 UID: 0 PID: 499 Comm: test Not tainted 6.12.0-rc3+ #18 Hardware name: Red Hat KVM, BIOS 1.16.0-4.al8 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x55/0x70 print_address_description.constprop.0+0x27/0x310 kasan_report+0x10f/0x120 ? strncpy_from_user+0x1d6/0x1f0 strncpy_from_user+0x1d6/0x1f0 ? rmqueue.constprop.0+0x70d/0x2ad0 process_fetch_insn+0xb26/0x1470 ? __pfx_process_fetch_insn+0x10/0x10 ? _raw_spin_lock+0x85/0xe0 ? __pfx__raw_spin_lock+0x10/0x10 ? __pte_offset_map+0x1f/0x2d0 ? unwind_next_frame+0xc5f/0x1f80 ? arch_stack_walk+0x68/0xf0 ? is_bpf_text_address+0x23/0x30 ? kernel_text_address.part.0+0xbb/0xd0 ? __kernel_text_address+0x66/0xb0 ? unwind_get_return_address+0x5e/0xa0 ? __pfx_stack_trace_consume_entry+0x10/0x10 ? arch_stack_walk+0xa2/0xf0 ? _raw_spin_lock_irqsave+0x8b/0xf0 ? __pfx__raw_spin_lock_irqsave+0x10/0x10 ? depot_alloc_stack+0x4c/0x1f0 ? _raw_spin_unlock_irqrestore+0xe/0x30 ? stack_depot_save_flags+0x35d/0x4f0 ? kasan_save_stack+0x34/0x50 ? kasan_save_stack+0x24/0x50 ? mutex_lock+0x91/0xe0 ? __pfx_mutex_lock+0x10/0x10 prepare_uprobe_buffer.part.0+0x2cd/0x500 uprobe_dispatcher+0x2c3/0x6a0 ? __pfx_uprobe_dispatcher+0x10/0x10 ? __kasan_slab_alloc+0x4d/0x90 handler_chain+0xdd/0x3e0 handle_swbp+0x26e/0x3d0 ? __pfx_handle_swbp+0x10/0x10 ? uprobe_pre_sstep_notifier+0x151/0x1b0 irqentry_exit_to_user_mode+0xe2/0x1b0 asm_exc_int3+0x39/0x40 RIP: 0033:0x401199 Code: 01 c2 0f b6 45 fb 88 02 83 45 fc 01 8b 45 fc 3b 45 e4 7c b7 8b 45 e4 48 98 48 8d 50 ff 48 8b 45 e8 48 01 d0 ce RSP: 002b:00007ffdf00576a8 EFLAGS: 00000206 RAX: 00007ffdf00576b0 RBX: 0000000000000000 RCX: 0000000000000ff2 RDX: 0000000000000ffc RSI: 0000000000000ffd RDI: 00007ffdf00576b0 RBP: 00007ffdf00586b0 R08: 00007feb2f9c0d20 R09: 00007feb2f9c0d20 R10: 0000000000000001 R11: 0000000000000202 R12: 0000000000401040 R13: 00007ffdf0058780 R14: 0000000000000000 R15: 0000000000000000 </TASK>
This commit enforces the buffer's maxlen less than a page-size to avoid store_trace_args() out-of-memory access.
Link: https://lore.kernel.org/all/20241015060148.1108331-1-mqaio@linux.alibaba.com...
Fixes: dcad1a204f72 ("tracing/uprobes: Fetch args before reserving a ring buffer") Signed-off-by: Qiao Ma mqaio@linux.alibaba.com Signed-off-by: Masami Hiramatsu (Google) mhiramat@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Vamsi Krishna Brahmajosyula vamsi-krishna.brahmajosyula@broadcom.com --- kernel/trace/trace_uprobe.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index e09eef65d32f..a6a3ff2a441e 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -862,6 +862,7 @@ struct uprobe_cpu_buffer { }; static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer; static int uprobe_buffer_refcnt; +#define MAX_UCB_BUFFER_SIZE PAGE_SIZE
static int uprobe_buffer_init(void) { @@ -960,6 +961,11 @@ static struct uprobe_cpu_buffer *prepare_uprobe_buffer(struct trace_uprobe *tu, ucb = uprobe_buffer_get(); ucb->dsize = tu->tp.size + dsize;
+ if (WARN_ON_ONCE(ucb->dsize > MAX_UCB_BUFFER_SIZE)) { + ucb->dsize = MAX_UCB_BUFFER_SIZE; + dsize = MAX_UCB_BUFFER_SIZE - tu->tp.size; + } + store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize);
return ucb; @@ -978,9 +984,6 @@ static void __uprobe_trace_func(struct trace_uprobe *tu,
WARN_ON(call != trace_file->event_call);
- if (WARN_ON_ONCE(ucb->dsize > PAGE_SIZE)) - return; - if (trace_trigger_soft_disabled(trace_file)) return;
linux-stable-mirror@lists.linaro.org