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, 252 insertions, 0 deletions

diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
new file mode 100644
index 000000000..73918e55b
--- /dev/null
+++ b/drivers/md/bcache/movinggc.c
@@ -0,0 +1,252 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Moving/copying garbage collector
+ *
+ * Copyright 2012 Google, Inc.
+ */
+
+#include "bcache.h"
+#include "btree.h"
+#include "debug.h"
+#include "request.h"
+
+#include <trace/events/bcache.h>
+
+struct moving_io {
+	struct closure		cl;
+	struct keybuf_key	*w;
+	struct data_insert_op	op;
+	struct bbio		bio;
+};
+
+static bool moving_pred(struct keybuf *buf, struct bkey *k)
+{
+	struct cache_set *c = container_of(buf, struct cache_set,
+					   moving_gc_keys);
+	unsigned int i;
+
+	for (i = 0; i < KEY_PTRS(k); i++)
+		if (ptr_available(c, k, i) &&
+		    GC_MOVE(PTR_BUCKET(c, k, i)))
+			return true;
+
+	return false;
+}
+
+/* Moving GC - IO loop */
+
+static CLOSURE_CALLBACK(moving_io_destructor)
+{
+	closure_type(io, struct moving_io, cl);
+
+	kfree(io);
+}
+
+static CLOSURE_CALLBACK(write_moving_finish)
+{
+	closure_type(io, struct moving_io, cl);
+	struct bio *bio = &io->bio.bio;
+
+	bio_free_pages(bio);
+
+	if (io->op.replace_collision)
+		trace_bcache_gc_copy_collision(&io->w->key);
+
+	bch_keybuf_del(&io->op.c->moving_gc_keys, io->w);
+
+	up(&io->op.c->moving_in_flight);
+
+	closure_return_with_destructor(cl, moving_io_destructor);
+}
+
+static void read_moving_endio(struct bio *bio)
+{
+	struct bbio *b = container_of(bio, struct bbio, bio);
+	struct moving_io *io = container_of(bio->bi_private,
+					    struct moving_io, cl);
+
+	if (bio->bi_status)
+		io->op.status = bio->bi_status;
+	else if (!KEY_DIRTY(&b->key) &&
+		 ptr_stale(io->op.c, &b->key, 0)) {
+		io->op.status = BLK_STS_IOERR;
+	}
+
+	bch_bbio_endio(io->op.c, bio, bio->bi_status, "reading data to move");
+}
+
+static void moving_init(struct moving_io *io)
+{
+	struct bio *bio = &io->bio.bio;
+
+	bio_init_inline(bio, NULL,
+		 DIV_ROUND_UP(KEY_SIZE(&io->w->key), PAGE_SECTORS), 0);
+	bio_get(bio);
+	bio->bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0);
+
+	bio->bi_iter.bi_size	= KEY_SIZE(&io->w->key) << 9;
+	bio->bi_private		= &io->cl;
+	bch_bio_map(bio, NULL);
+}
+
+static CLOSURE_CALLBACK(write_moving)
+{
+	closure_type(io, struct moving_io, cl);
+	struct data_insert_op *op = &io->op;
+
+	if (!op->status) {
+		moving_init(io);
+
+		io->bio.bio.bi_iter.bi_sector = KEY_START(&io->w->key);
+		op->write_prio		= 1;
+		op->bio			= &io->bio.bio;
+
+		op->writeback		= KEY_DIRTY(&io->w->key);
+		op->csum		= KEY_CSUM(&io->w->key);
+
+		bkey_copy(&op->replace_key, &io->w->key);
+		op->replace		= true;
+
+		closure_call(&op->cl, bch_data_insert, NULL, cl);
+	}
+
+	continue_at(cl, write_moving_finish, op->wq);
+}
+
+static CLOSURE_CALLBACK(read_moving_submit)
+{
+	closure_type(io, struct moving_io, cl);
+	struct bio *bio = &io->bio.bio;
+
+	bch_submit_bbio(bio, io->op.c, &io->w->key, 0);
+
+	continue_at(cl, write_moving, io->op.wq);
+}
+
+static void read_moving(struct cache_set *c)
+{
+	struct keybuf_key *w;
+	struct moving_io *io;
+	struct bio *bio;
+	struct closure cl;
+
+	closure_init_stack(&cl);
+
+	/* XXX: if we error, background writeback could stall indefinitely */
+
+	while (!test_bit(CACHE_SET_STOPPING, &c->flags)) {
+		w = bch_keybuf_next_rescan(c, &c->moving_gc_keys,
+					   &MAX_KEY, moving_pred);
+		if (!w)
+			break;
+
+		if (ptr_stale(c, &w->key, 0)) {
+			bch_keybuf_del(&c->moving_gc_keys, w);
+			continue;
+		}
+
+		io = kzalloc(sizeof(*io) + sizeof(struct bio_vec) *
+				DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS),
+				GFP_KERNEL);
+		if (!io)
+			goto err;
+
+		w->private	= io;
+		io->w		= w;
+		io->op.inode	= KEY_INODE(&w->key);
+		io->op.c	= c;
+		io->op.wq	= c->moving_gc_wq;
+
+		moving_init(io);
+		bio = &io->bio.bio;
+
+		bio->bi_opf = REQ_OP_READ;
+		bio->bi_end_io	= read_moving_endio;
+
+		if (bch_bio_alloc_pages(bio, GFP_KERNEL))
+			goto err;
+
+		trace_bcache_gc_copy(&w->key);
+
+		down(&c->moving_in_flight);
+		closure_call(&io->cl, read_moving_submit, NULL, &cl);
+	}
+
+	if (0) {
+err:		if (!IS_ERR_OR_NULL(w->private))
+			kfree(w->private);
+
+		bch_keybuf_del(&c->moving_gc_keys, w);
+	}
+
+	closure_sync(&cl);
+}
+
+static bool bucket_cmp(struct bucket *l, struct bucket *r)
+{
+	return GC_SECTORS_USED(l) < GC_SECTORS_USED(r);
+}
+
+static unsigned int bucket_heap_top(struct cache *ca)
+{
+	struct bucket *b;
+
+	return (b = heap_peek(&ca->heap)) ? GC_SECTORS_USED(b) : 0;
+}
+
+void bch_moving_gc(struct cache_set *c)
+{
+	struct cache *ca = c->cache;
+	struct bucket *b;
+	unsigned long sectors_to_move, reserve_sectors;
+
+	if (!c->copy_gc_enabled)
+		return;
+
+	mutex_lock(&c->bucket_lock);
+
+	sectors_to_move = 0;
+	reserve_sectors = ca->sb.bucket_size *
+			     fifo_used(&ca->free[RESERVE_MOVINGGC]);
+
+	ca->heap.used = 0;
+
+	for_each_bucket(b, ca) {
+		if (GC_MARK(b) == GC_MARK_METADATA ||
+		    !GC_SECTORS_USED(b) ||
+		    GC_SECTORS_USED(b) == ca->sb.bucket_size ||
+		    atomic_read(&b->pin))
+			continue;
+
+		if (!heap_full(&ca->heap)) {
+			sectors_to_move += GC_SECTORS_USED(b);
+			heap_add(&ca->heap, b, bucket_cmp);
+		} else if (bucket_cmp(b, heap_peek(&ca->heap))) {
+			sectors_to_move -= bucket_heap_top(ca);
+			sectors_to_move += GC_SECTORS_USED(b);
+
+			ca->heap.data[0] = b;
+			heap_sift(&ca->heap, 0, bucket_cmp);
+		}
+	}
+
+	while (sectors_to_move > reserve_sectors) {
+		heap_pop(&ca->heap, b, bucket_cmp);
+		sectors_to_move -= GC_SECTORS_USED(b);
+	}
+
+	while (heap_pop(&ca->heap, b, bucket_cmp))
+		SET_GC_MOVE(b, 1);
+
+	mutex_unlock(&c->bucket_lock);
+
+	c->moving_gc_keys.last_scanned = ZERO_KEY;
+
+	read_moving(c);
+}
+
+void bch_moving_init_cache_set(struct cache_set *c)
+{
+	bch_keybuf_init(&c->moving_gc_keys);
+	sema_init(&c->moving_in_flight, 64);
+}