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, 230 insertions, 0 deletions

diff --git a/lib/generic-radix-tree.c b/lib/generic-radix-tree.c
new file mode 100644
index 000000000..79e067b51
--- /dev/null
+++ b/lib/generic-radix-tree.c
@@ -0,0 +1,230 @@
+
+#include <linux/atomic.h>
+#include <linux/export.h>
+#include <linux/generic-radix-tree.h>
+#include <linux/gfp.h>
+#include <linux/kmemleak.h>
+
+/*
+ * Returns pointer to the specified byte @offset within @radix, or NULL if not
+ * allocated
+ */
+void *__genradix_ptr(struct __genradix *radix, size_t offset)
+{
+	return __genradix_ptr_inlined(radix, offset);
+}
+EXPORT_SYMBOL(__genradix_ptr);
+
+/*
+ * Returns pointer to the specified byte @offset within @radix, allocating it if
+ * necessary - newly allocated slots are always zeroed out:
+ */
+void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset,
+			   struct genradix_node **preallocated,
+			   gfp_t gfp_mask)
+{
+	struct genradix_root *v = READ_ONCE(radix->root);
+	struct genradix_node *n, *new_node = NULL;
+	unsigned level;
+
+	if (preallocated)
+		swap(new_node, *preallocated);
+
+	/* Increase tree depth if necessary: */
+	while (1) {
+		struct genradix_root *r = v, *new_root;
+
+		n	= genradix_root_to_node(r);
+		level	= genradix_root_to_depth(r);
+
+		if (n && ilog2(offset) < genradix_depth_shift(level))
+			break;
+
+		if (!new_node) {
+			new_node = genradix_alloc_node(gfp_mask);
+			if (!new_node)
+				return NULL;
+		}
+
+		new_node->children[0] = n;
+		new_root = ((struct genradix_root *)
+			    ((unsigned long) new_node | (n ? level + 1 : 0)));
+
+		if ((v = cmpxchg_release(&radix->root, r, new_root)) == r) {
+			v = new_root;
+			new_node = NULL;
+		} else {
+			new_node->children[0] = NULL;
+		}
+	}
+
+	while (level--) {
+		struct genradix_node **p =
+			&n->children[offset >> genradix_depth_shift(level)];
+		offset &= genradix_depth_size(level) - 1;
+
+		n = READ_ONCE(*p);
+		if (!n) {
+			if (!new_node) {
+				new_node = genradix_alloc_node(gfp_mask);
+				if (!new_node)
+					return NULL;
+			}
+
+			if (!(n = cmpxchg_release(p, NULL, new_node)))
+				swap(n, new_node);
+		}
+	}
+
+	if (new_node)
+		genradix_free_node(new_node);
+
+	return &n->data[offset];
+}
+EXPORT_SYMBOL(__genradix_ptr_alloc);
+
+void *__genradix_iter_peek(struct genradix_iter *iter,
+			   struct __genradix *radix,
+			   size_t objs_per_page)
+{
+	struct genradix_root *r;
+	struct genradix_node *n;
+	unsigned level, i;
+
+	if (iter->offset == SIZE_MAX)
+		return NULL;
+
+restart:
+	r = READ_ONCE(radix->root);
+	if (!r)
+		return NULL;
+
+	n	= genradix_root_to_node(r);
+	level	= genradix_root_to_depth(r);
+
+	if (ilog2(iter->offset) >= genradix_depth_shift(level))
+		return NULL;
+
+	while (level) {
+		level--;
+
+		i = (iter->offset >> genradix_depth_shift(level)) &
+			(GENRADIX_ARY - 1);
+
+		while (!n->children[i]) {
+			size_t objs_per_ptr = genradix_depth_size(level);
+
+			if (iter->offset + objs_per_ptr < iter->offset) {
+				iter->offset	= SIZE_MAX;
+				iter->pos	= SIZE_MAX;
+				return NULL;
+			}
+
+			i++;
+			iter->offset = round_down(iter->offset + objs_per_ptr,
+						  objs_per_ptr);
+			iter->pos = (iter->offset >> GENRADIX_NODE_SHIFT) *
+				objs_per_page;
+			if (i == GENRADIX_ARY)
+				goto restart;
+		}
+
+		n = n->children[i];
+	}
+
+	return &n->data[iter->offset & (GENRADIX_NODE_SIZE - 1)];
+}
+EXPORT_SYMBOL(__genradix_iter_peek);
+
+void *__genradix_iter_peek_prev(struct genradix_iter *iter,
+				struct __genradix *radix,
+				size_t objs_per_page,
+				size_t obj_size_plus_page_remainder)
+{
+	struct genradix_root *r;
+	struct genradix_node *n;
+	unsigned level, i;
+
+	if (iter->offset == SIZE_MAX)
+		return NULL;
+
+restart:
+	r = READ_ONCE(radix->root);
+	if (!r)
+		return NULL;
+
+	n	= genradix_root_to_node(r);
+	level	= genradix_root_to_depth(r);
+
+	if (ilog2(iter->offset) >= genradix_depth_shift(level)) {
+		iter->offset = genradix_depth_size(level);
+		iter->pos = (iter->offset >> GENRADIX_NODE_SHIFT) * objs_per_page;
+
+		iter->offset -= obj_size_plus_page_remainder;
+		iter->pos--;
+	}
+
+	while (level) {
+		level--;
+
+		i = (iter->offset >> genradix_depth_shift(level)) &
+			(GENRADIX_ARY - 1);
+
+		while (!n->children[i]) {
+			size_t objs_per_ptr = genradix_depth_size(level);
+
+			iter->offset = round_down(iter->offset, objs_per_ptr);
+			iter->pos = (iter->offset >> GENRADIX_NODE_SHIFT) * objs_per_page;
+
+			if (!iter->offset)
+				return NULL;
+
+			iter->offset -= obj_size_plus_page_remainder;
+			iter->pos--;
+
+			if (!i)
+				goto restart;
+			--i;
+		}
+
+		n = n->children[i];
+	}
+
+	return &n->data[iter->offset & (GENRADIX_NODE_SIZE - 1)];
+}
+EXPORT_SYMBOL(__genradix_iter_peek_prev);
+
+static void genradix_free_recurse(struct genradix_node *n, unsigned level)
+{
+	if (level) {
+		unsigned i;
+
+		for (i = 0; i < GENRADIX_ARY; i++)
+			if (n->children[i])
+				genradix_free_recurse(n->children[i], level - 1);
+	}
+
+	genradix_free_node(n);
+}
+
+int __genradix_prealloc(struct __genradix *radix, size_t size,
+			gfp_t gfp_mask)
+{
+	size_t offset;
+
+	for (offset = 0; offset < size; offset += GENRADIX_NODE_SIZE)
+		if (!__genradix_ptr_alloc(radix, offset, NULL, gfp_mask))
+			return -ENOMEM;
+
+	return 0;
+}
+EXPORT_SYMBOL(__genradix_prealloc);
+
+void __genradix_free(struct __genradix *radix)
+{
+	struct genradix_root *r = xchg(&radix->root, NULL);
+
+	genradix_free_recurse(genradix_root_to_node(r),
+			      genradix_root_to_depth(r));
+}
+EXPORT_SYMBOL(__genradix_free);