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, 249 insertions, 0 deletions

diff --git a/fs/netfs/rolling_buffer.c b/fs/netfs/rolling_buffer.c
new file mode 100644
index 000000000..424e77a9a
--- /dev/null
+++ b/fs/netfs/rolling_buffer.c
@@ -0,0 +1,249 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Rolling buffer helpers
+ *
+ * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/bitops.h>
+#include <linux/mempool.h>
+#include <linux/pagemap.h>
+#include <linux/rolling_buffer.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+static atomic_t debug_ids;
+
+/**
+ * netfs_folioq_alloc - Allocate a folio_queue struct
+ * @rreq_id: Associated debugging ID for tracing purposes
+ * @gfp: Allocation constraints
+ * @trace: Trace tag to indicate the purpose of the allocation
+ *
+ * Allocate, initialise and account the folio_queue struct and log a trace line
+ * to mark the allocation.
+ */
+struct folio_queue *netfs_folioq_alloc(unsigned int rreq_id, gfp_t gfp,
+				       unsigned int /*enum netfs_folioq_trace*/ trace)
+{
+	struct folio_queue *fq;
+
+	if (gfp == GFP_KERNEL)
+		fq = netfs_folioq_pool.alloc(gfp, netfs_folioq_pool.pool_data);
+	else
+		fq = mempool_alloc(&netfs_folioq_pool, gfp);
+	if (fq) {
+		netfs_stat(&netfs_n_folioq);
+		folioq_init(fq, rreq_id);
+		fq->debug_id = atomic_inc_return(&debug_ids);
+		trace_netfs_folioq(fq, trace);
+	}
+	return fq;
+}
+EXPORT_SYMBOL(netfs_folioq_alloc);
+
+/**
+ * netfs_folioq_free - Free a folio_queue struct
+ * @folioq: The object to free
+ * @trace: Trace tag to indicate which free
+ *
+ * Free and unaccount the folio_queue struct.
+ */
+void netfs_folioq_free(struct folio_queue *folioq,
+		       unsigned int /*enum netfs_trace_folioq*/ trace)
+{
+	trace_netfs_folioq(folioq, trace);
+	netfs_stat_d(&netfs_n_folioq);
+	mempool_free(folioq, &netfs_folioq_pool);
+}
+EXPORT_SYMBOL(netfs_folioq_free);
+
+/*
+ * Initialise a rolling buffer.  We allocate an empty folio queue struct to so
+ * that the pointers can be independently driven by the producer and the
+ * consumer.
+ */
+int rolling_buffer_init(struct rolling_buffer *roll, unsigned int rreq_id,
+			unsigned int direction, gfp_t gfp)
+{
+	struct folio_queue *fq;
+
+	fq = netfs_folioq_alloc(rreq_id, gfp, netfs_trace_folioq_rollbuf_init);
+	if (!fq)
+		return -ENOMEM;
+
+	roll->head = fq;
+	roll->tail = fq;
+	iov_iter_folio_queue(&roll->iter, direction, fq, 0, 0, 0);
+	return 0;
+}
+
+/*
+ * Add another folio_queue to a rolling buffer if there's no space left.
+ */
+int rolling_buffer_make_space(struct rolling_buffer *roll, gfp_t gfp)
+{
+	struct folio_queue *fq, *head = roll->head;
+
+	if (!folioq_full(head))
+		return 0;
+
+	fq = netfs_folioq_alloc(head->rreq_id, gfp, netfs_trace_folioq_make_space);
+	if (!fq)
+		return -ENOMEM;
+	fq->prev = head;
+
+	roll->head = fq;
+	if (folioq_full(head)) {
+		/* Make sure we don't leave the master iterator pointing to a
+		 * block that might get immediately consumed.
+		 */
+		if (roll->iter.folioq == head &&
+		    roll->iter.folioq_slot == folioq_nr_slots(head)) {
+			roll->iter.folioq = fq;
+			roll->iter.folioq_slot = 0;
+		}
+	}
+
+	/* Make sure the initialisation is stored before the next pointer.
+	 *
+	 * [!] NOTE: After we set head->next, the consumer is at liberty to
+	 * immediately delete the old head.
+	 */
+	smp_store_release(&head->next, fq);
+	return 0;
+}
+
+/*
+ * Decant the entire list of folios to read into a rolling buffer.
+ */
+ssize_t rolling_buffer_bulk_load_from_ra(struct rolling_buffer *roll,
+					 struct readahead_control *ractl,
+					 unsigned int rreq_id, gfp_t gfp)
+{
+	struct folio_queue *fq;
+	ssize_t loaded = 0;
+
+	while (ractl->_nr_pages - ractl->_batch_count > 0) {
+		unsigned int nr;
+
+		/* Allocate a folioq to put some folios into and attach it to
+		 * the rolling buffer.
+		 */
+		fq = netfs_folioq_alloc(rreq_id, gfp,
+					netfs_trace_folioq_make_space);
+		if (!fq)
+			goto nomem_unlock;
+		fq->prev = roll->head;
+		if (!roll->tail)
+			roll->tail = fq;
+		else
+			roll->head->next = fq;
+		roll->head = fq;
+
+		/* Get a batch of folios and note their orders. */
+		nr = __readahead_batch(ractl, (struct page **)fq->vec.folios,
+				       folioq_nr_slots(fq));
+		if (WARN_ON_ONCE(!nr))
+			break;
+		fq->vec.nr = nr;
+
+		for (int slot = 0; slot < nr; slot++) {
+			struct folio *folio = folioq_folio(fq, slot);
+			unsigned int order;
+
+			order = folio_order(folio);
+			fq->orders[slot] = order;
+			loaded += PAGE_SIZE << order;
+			trace_netfs_folio(folio, netfs_folio_trace_read);
+		}
+	}
+
+	WRITE_ONCE(roll->iter.count, loaded);
+	iov_iter_folio_queue(&roll->iter, ITER_DEST, roll->tail, 0, 0, loaded);
+	return loaded;
+
+nomem_unlock:
+	for (fq = roll->tail; fq; fq = fq->next) {
+		for (int slot = 0; slot < folioq_count(fq); slot++) {
+			folio_unlock(fq->vec.folios[slot]);
+			folioq_mark(fq, slot);
+		}
+	}
+	rolling_buffer_clear(roll);
+	roll->head = NULL;
+	roll->tail = NULL;
+	return -ENOMEM;
+}
+
+/*
+ * Append a folio to the rolling buffer.
+ */
+ssize_t rolling_buffer_append(struct rolling_buffer *roll, struct folio *folio,
+			      unsigned int flags, gfp_t gfp)
+{
+	ssize_t size = folio_size(folio);
+	int slot;
+
+	if (rolling_buffer_make_space(roll, gfp) < 0)
+		return -ENOMEM;
+
+	slot = folioq_append(roll->head, folio);
+	if (flags & ROLLBUF_MARK_1)
+		folioq_mark(roll->head, slot);
+	if (flags & ROLLBUF_MARK_2)
+		folioq_mark2(roll->head, slot);
+
+	WRITE_ONCE(roll->iter.count, roll->iter.count + size);
+
+	/* Store the counter after setting the slot. */
+	smp_store_release(&roll->next_head_slot, slot);
+	return size;
+}
+
+/*
+ * Delete a spent buffer from a rolling queue and return the next in line.  We
+ * don't return the last buffer to keep the pointers independent, but return
+ * NULL instead.
+ */
+struct folio_queue *rolling_buffer_delete_spent(struct rolling_buffer *roll)
+{
+	struct folio_queue *spent = roll->tail, *next = READ_ONCE(spent->next);
+
+	if (!next)
+		return NULL;
+	next->prev = NULL;
+	netfs_folioq_free(spent, netfs_trace_folioq_delete);
+	roll->tail = next;
+	return next;
+}
+
+/*
+ * Clear out a rolling queue.  Folios that have mark 1 set are put.
+ */
+void rolling_buffer_clear(struct rolling_buffer *roll)
+{
+	struct folio_batch fbatch;
+	struct folio_queue *p;
+
+	folio_batch_init(&fbatch);
+
+	while ((p = roll->tail)) {
+		roll->tail = p->next;
+		for (int slot = 0; slot < folioq_count(p); slot++) {
+			struct folio *folio = folioq_folio(p, slot);
+
+			if (!folio)
+				continue;
+			if (folioq_is_marked(p, slot)) {
+				trace_netfs_folio(folio, netfs_folio_trace_put);
+				if (!folio_batch_add(&fbatch, folio))
+					folio_batch_release(&fbatch);
+			}
+		}
+
+		netfs_folioq_free(p, netfs_trace_folioq_clear);
+	}
+
+	folio_batch_release(&fbatch);
+}