x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 174 insertions, 0 deletions

diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
new file mode 100644
index 000000000..2386d08bf
--- /dev/null
+++ b/drivers/md/bcache/io.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Some low level IO code, and hacks for various block layer limitations
+ *
+ * Copyright 2010, 2011 Kent Overstreet <kent.overstreet@gmail.com>
+ * Copyright 2012 Google, Inc.
+ */
+
+#include "bcache.h"
+#include "bset.h"
+#include "debug.h"
+
+#include <linux/blkdev.h>
+
+/* Bios with headers */
+
+void bch_bbio_free(struct bio *bio, struct cache_set *c)
+{
+	struct bbio *b = container_of(bio, struct bbio, bio);
+
+	mempool_free(b, &c->bio_meta);
+}
+
+struct bio *bch_bbio_alloc(struct cache_set *c)
+{
+	struct bbio *b = mempool_alloc(&c->bio_meta, GFP_NOIO);
+	struct bio *bio = &b->bio;
+
+	bio_init_inline(bio, NULL, meta_bucket_pages(&c->cache->sb), 0);
+
+	return bio;
+}
+
+void __bch_submit_bbio(struct bio *bio, struct cache_set *c)
+{
+	struct bbio *b = container_of(bio, struct bbio, bio);
+
+	bio->bi_iter.bi_sector	= PTR_OFFSET(&b->key, 0);
+	bio_set_dev(bio, c->cache->bdev);
+
+	b->submit_time_us = local_clock_us();
+	closure_bio_submit(c, bio, bio->bi_private);
+}
+
+void bch_submit_bbio(struct bio *bio, struct cache_set *c,
+		     struct bkey *k, unsigned int ptr)
+{
+	struct bbio *b = container_of(bio, struct bbio, bio);
+
+	bch_bkey_copy_single_ptr(&b->key, k, ptr);
+	__bch_submit_bbio(bio, c);
+}
+
+/* IO errors */
+void bch_count_backing_io_errors(struct cached_dev *dc, struct bio *bio)
+{
+	unsigned int errors;
+
+	WARN_ONCE(!dc, "NULL pointer of struct cached_dev");
+
+	/*
+	 * Read-ahead requests on a degrading and recovering md raid
+	 * (e.g. raid6) device might be failured immediately by md
+	 * raid code, which is not a real hardware media failure. So
+	 * we shouldn't count failed REQ_RAHEAD bio to dc->io_errors.
+	 */
+	if (bio->bi_opf & REQ_RAHEAD) {
+		pr_warn_ratelimited("%pg: Read-ahead I/O failed on backing device, ignore\n",
+				    dc->bdev);
+		return;
+	}
+
+	errors = atomic_add_return(1, &dc->io_errors);
+	if (errors < dc->error_limit)
+		pr_err("%pg: IO error on backing device, unrecoverable\n",
+			dc->bdev);
+	else
+		bch_cached_dev_error(dc);
+}
+
+void bch_count_io_errors(struct cache *ca,
+			 blk_status_t error,
+			 int is_read,
+			 const char *m)
+{
+	/*
+	 * The halflife of an error is:
+	 * log2(1/2)/log2(127/128) * refresh ~= 88 * refresh
+	 */
+
+	if (ca->set->error_decay) {
+		unsigned int count = atomic_inc_return(&ca->io_count);
+
+		while (count > ca->set->error_decay) {
+			unsigned int errors;
+			unsigned int old = count;
+			unsigned int new = count - ca->set->error_decay;
+
+			/*
+			 * First we subtract refresh from count; each time we
+			 * successfully do so, we rescale the errors once:
+			 */
+
+			count = atomic_cmpxchg(&ca->io_count, old, new);
+
+			if (count == old) {
+				count = new;
+
+				errors = atomic_read(&ca->io_errors);
+				do {
+					old = errors;
+					new = ((uint64_t) errors * 127) / 128;
+					errors = atomic_cmpxchg(&ca->io_errors,
+								old, new);
+				} while (old != errors);
+			}
+		}
+	}
+
+	if (error) {
+		unsigned int errors = atomic_add_return(1 << IO_ERROR_SHIFT,
+						    &ca->io_errors);
+		errors >>= IO_ERROR_SHIFT;
+
+		if (errors < ca->set->error_limit)
+			pr_err("%pg: IO error on %s%s\n",
+			       ca->bdev, m,
+			       is_read ? ", recovering." : ".");
+		else
+			bch_cache_set_error(ca->set,
+					    "%pg: too many IO errors %s\n",
+					    ca->bdev, m);
+	}
+}
+
+void bch_bbio_count_io_errors(struct cache_set *c, struct bio *bio,
+			      blk_status_t error, const char *m)
+{
+	struct bbio *b = container_of(bio, struct bbio, bio);
+	struct cache *ca = c->cache;
+	int is_read = (bio_data_dir(bio) == READ ? 1 : 0);
+
+	unsigned int threshold = op_is_write(bio_op(bio))
+		? c->congested_write_threshold_us
+		: c->congested_read_threshold_us;
+
+	if (threshold) {
+		unsigned int t = local_clock_us();
+		int us = t - b->submit_time_us;
+		int congested = atomic_read(&c->congested);
+
+		if (us > (int) threshold) {
+			int ms = us / 1024;
+
+			c->congested_last_us = t;
+
+			ms = min(ms, CONGESTED_MAX + congested);
+			atomic_sub(ms, &c->congested);
+		} else if (congested < 0)
+			atomic_inc(&c->congested);
+	}
+
+	bch_count_io_errors(ca, error, is_read, m);
+}
+
+void bch_bbio_endio(struct cache_set *c, struct bio *bio,
+		    blk_status_t error, const char *m)
+{
+	struct closure *cl = bio->bi_private;
+
+	bch_bbio_count_io_errors(c, bio, error, m);
+	bio_put(bio);
+	closure_put(cl);
+}