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, 158 insertions, 0 deletions

diff --git a/io_uring/filetable.c b/io_uring/filetable.c
new file mode 100644
index 000000000..cb1838c9f
--- /dev/null
+++ b/io_uring/filetable.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/nospec.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "rsrc.h"
+#include "filetable.h"
+
+static int io_file_bitmap_get(struct io_ring_ctx *ctx)
+{
+	struct io_file_table *table = &ctx->file_table;
+	unsigned long nr = ctx->file_alloc_end;
+	int ret;
+
+	if (!table->bitmap)
+		return -ENFILE;
+
+	if (table->alloc_hint < ctx->file_alloc_start ||
+	    table->alloc_hint >= ctx->file_alloc_end)
+		table->alloc_hint = ctx->file_alloc_start;
+
+	do {
+		ret = find_next_zero_bit(table->bitmap, nr, table->alloc_hint);
+		if (ret != nr)
+			return ret;
+
+		if (table->alloc_hint == ctx->file_alloc_start)
+			break;
+		nr = table->alloc_hint;
+		table->alloc_hint = ctx->file_alloc_start;
+	} while (1);
+
+	return -ENFILE;
+}
+
+bool io_alloc_file_tables(struct io_ring_ctx *ctx, struct io_file_table *table,
+			  unsigned nr_files)
+{
+	if (io_rsrc_data_alloc(&table->data, nr_files))
+		return false;
+	table->bitmap = bitmap_zalloc(nr_files, GFP_KERNEL_ACCOUNT);
+	if (table->bitmap)
+		return true;
+	io_rsrc_data_free(ctx, &table->data);
+	return false;
+}
+
+void io_free_file_tables(struct io_ring_ctx *ctx, struct io_file_table *table)
+{
+	io_rsrc_data_free(ctx, &table->data);
+	bitmap_free(table->bitmap);
+	table->bitmap = NULL;
+}
+
+static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file,
+				 u32 slot_index)
+	__must_hold(&ctx->uring_lock)
+{
+	struct io_rsrc_node *node;
+
+	if (io_is_uring_fops(file))
+		return -EBADF;
+	if (!ctx->file_table.data.nr)
+		return -ENXIO;
+	if (slot_index >= ctx->file_table.data.nr)
+		return -EINVAL;
+
+	node = io_rsrc_node_alloc(ctx, IORING_RSRC_FILE);
+	if (!node)
+		return -ENOMEM;
+
+	if (!io_reset_rsrc_node(ctx, &ctx->file_table.data, slot_index))
+		io_file_bitmap_set(&ctx->file_table, slot_index);
+
+	ctx->file_table.data.nodes[slot_index] = node;
+	io_fixed_file_set(node, file);
+	return 0;
+}
+
+int __io_fixed_fd_install(struct io_ring_ctx *ctx, struct file *file,
+			  unsigned int file_slot)
+{
+	bool alloc_slot = file_slot == IORING_FILE_INDEX_ALLOC;
+	int ret;
+
+	if (alloc_slot) {
+		ret = io_file_bitmap_get(ctx);
+		if (unlikely(ret < 0))
+			return ret;
+		file_slot = ret;
+	} else {
+		file_slot--;
+	}
+
+	ret = io_install_fixed_file(ctx, file, file_slot);
+	if (!ret && alloc_slot)
+		ret = file_slot;
+	return ret;
+}
+/*
+ * Note when io_fixed_fd_install() returns error value, it will ensure
+ * fput() is called correspondingly.
+ */
+int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags,
+			struct file *file, unsigned int file_slot)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	int ret;
+
+	io_ring_submit_lock(ctx, issue_flags);
+	ret = __io_fixed_fd_install(ctx, file, file_slot);
+	io_ring_submit_unlock(ctx, issue_flags);
+
+	if (unlikely(ret < 0))
+		fput(file);
+	return ret;
+}
+
+int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset)
+{
+	struct io_rsrc_node *node;
+
+	if (unlikely(!ctx->file_table.data.nr))
+		return -ENXIO;
+	if (offset >= ctx->file_table.data.nr)
+		return -EINVAL;
+
+	node = io_rsrc_node_lookup(&ctx->file_table.data, offset);
+	if (!node)
+		return -EBADF;
+	io_reset_rsrc_node(ctx, &ctx->file_table.data, offset);
+	io_file_bitmap_clear(&ctx->file_table, offset);
+	return 0;
+}
+
+int io_register_file_alloc_range(struct io_ring_ctx *ctx,
+				 struct io_uring_file_index_range __user *arg)
+{
+	struct io_uring_file_index_range range;
+	u32 end;
+
+	if (copy_from_user(&range, arg, sizeof(range)))
+		return -EFAULT;
+	if (check_add_overflow(range.off, range.len, &end))
+		return -EOVERFLOW;
+	if (range.resv || end > ctx->file_table.data.nr)
+		return -EINVAL;
+
+	io_file_table_set_alloc_range(ctx, range.off, range.len);
+	return 0;
+}