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, 176 insertions, 0 deletions

diff --git a/lib/crypto/x86/chacha.h b/lib/crypto/x86/chacha.h
new file mode 100644
index 000000000..10cf8f1c5
--- /dev/null
+++ b/lib/crypto/x86/chacha.h
@@ -0,0 +1,176 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * ChaCha and HChaCha functions (x86_64 optimized)
+ *
+ * Copyright (C) 2015 Martin Willi
+ */
+
+#include <asm/simd.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/sizes.h>
+
+asmlinkage void chacha_block_xor_ssse3(const struct chacha_state *state,
+				       u8 *dst, const u8 *src,
+				       unsigned int len, int nrounds);
+asmlinkage void chacha_4block_xor_ssse3(const struct chacha_state *state,
+					u8 *dst, const u8 *src,
+					unsigned int len, int nrounds);
+asmlinkage void hchacha_block_ssse3(const struct chacha_state *state,
+				    u32 out[HCHACHA_OUT_WORDS], int nrounds);
+
+asmlinkage void chacha_2block_xor_avx2(const struct chacha_state *state,
+				       u8 *dst, const u8 *src,
+				       unsigned int len, int nrounds);
+asmlinkage void chacha_4block_xor_avx2(const struct chacha_state *state,
+				       u8 *dst, const u8 *src,
+				       unsigned int len, int nrounds);
+asmlinkage void chacha_8block_xor_avx2(const struct chacha_state *state,
+				       u8 *dst, const u8 *src,
+				       unsigned int len, int nrounds);
+
+asmlinkage void chacha_2block_xor_avx512vl(const struct chacha_state *state,
+					   u8 *dst, const u8 *src,
+					   unsigned int len, int nrounds);
+asmlinkage void chacha_4block_xor_avx512vl(const struct chacha_state *state,
+					   u8 *dst, const u8 *src,
+					   unsigned int len, int nrounds);
+asmlinkage void chacha_8block_xor_avx512vl(const struct chacha_state *state,
+					   u8 *dst, const u8 *src,
+					   unsigned int len, int nrounds);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_simd);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx2);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx512vl);
+
+static unsigned int chacha_advance(unsigned int len, unsigned int maxblocks)
+{
+	len = min(len, maxblocks * CHACHA_BLOCK_SIZE);
+	return round_up(len, CHACHA_BLOCK_SIZE) / CHACHA_BLOCK_SIZE;
+}
+
+static void chacha_dosimd(struct chacha_state *state, u8 *dst, const u8 *src,
+			  unsigned int bytes, int nrounds)
+{
+	if (static_branch_likely(&chacha_use_avx512vl)) {
+		while (bytes >= CHACHA_BLOCK_SIZE * 8) {
+			chacha_8block_xor_avx512vl(state, dst, src, bytes,
+						   nrounds);
+			bytes -= CHACHA_BLOCK_SIZE * 8;
+			src += CHACHA_BLOCK_SIZE * 8;
+			dst += CHACHA_BLOCK_SIZE * 8;
+			state->x[12] += 8;
+		}
+		if (bytes > CHACHA_BLOCK_SIZE * 4) {
+			chacha_8block_xor_avx512vl(state, dst, src, bytes,
+						   nrounds);
+			state->x[12] += chacha_advance(bytes, 8);
+			return;
+		}
+		if (bytes > CHACHA_BLOCK_SIZE * 2) {
+			chacha_4block_xor_avx512vl(state, dst, src, bytes,
+						   nrounds);
+			state->x[12] += chacha_advance(bytes, 4);
+			return;
+		}
+		if (bytes) {
+			chacha_2block_xor_avx512vl(state, dst, src, bytes,
+						   nrounds);
+			state->x[12] += chacha_advance(bytes, 2);
+			return;
+		}
+	}
+
+	if (static_branch_likely(&chacha_use_avx2)) {
+		while (bytes >= CHACHA_BLOCK_SIZE * 8) {
+			chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
+			bytes -= CHACHA_BLOCK_SIZE * 8;
+			src += CHACHA_BLOCK_SIZE * 8;
+			dst += CHACHA_BLOCK_SIZE * 8;
+			state->x[12] += 8;
+		}
+		if (bytes > CHACHA_BLOCK_SIZE * 4) {
+			chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
+			state->x[12] += chacha_advance(bytes, 8);
+			return;
+		}
+		if (bytes > CHACHA_BLOCK_SIZE * 2) {
+			chacha_4block_xor_avx2(state, dst, src, bytes, nrounds);
+			state->x[12] += chacha_advance(bytes, 4);
+			return;
+		}
+		if (bytes > CHACHA_BLOCK_SIZE) {
+			chacha_2block_xor_avx2(state, dst, src, bytes, nrounds);
+			state->x[12] += chacha_advance(bytes, 2);
+			return;
+		}
+	}
+
+	while (bytes >= CHACHA_BLOCK_SIZE * 4) {
+		chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
+		bytes -= CHACHA_BLOCK_SIZE * 4;
+		src += CHACHA_BLOCK_SIZE * 4;
+		dst += CHACHA_BLOCK_SIZE * 4;
+		state->x[12] += 4;
+	}
+	if (bytes > CHACHA_BLOCK_SIZE) {
+		chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
+		state->x[12] += chacha_advance(bytes, 4);
+		return;
+	}
+	if (bytes) {
+		chacha_block_xor_ssse3(state, dst, src, bytes, nrounds);
+		state->x[12]++;
+	}
+}
+
+static void hchacha_block_arch(const struct chacha_state *state,
+			       u32 out[HCHACHA_OUT_WORDS], int nrounds)
+{
+	if (!static_branch_likely(&chacha_use_simd)) {
+		hchacha_block_generic(state, out, nrounds);
+	} else {
+		kernel_fpu_begin();
+		hchacha_block_ssse3(state, out, nrounds);
+		kernel_fpu_end();
+	}
+}
+
+static void chacha_crypt_arch(struct chacha_state *state, u8 *dst,
+			      const u8 *src, unsigned int bytes, int nrounds)
+{
+	if (!static_branch_likely(&chacha_use_simd) ||
+	    bytes <= CHACHA_BLOCK_SIZE)
+		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
+
+	do {
+		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+
+		kernel_fpu_begin();
+		chacha_dosimd(state, dst, src, todo, nrounds);
+		kernel_fpu_end();
+
+		bytes -= todo;
+		src += todo;
+		dst += todo;
+	} while (bytes);
+}
+
+#define chacha_mod_init_arch chacha_mod_init_arch
+static void chacha_mod_init_arch(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_SSSE3))
+		return;
+
+	static_branch_enable(&chacha_use_simd);
+
+	if (boot_cpu_has(X86_FEATURE_AVX) &&
+	    boot_cpu_has(X86_FEATURE_AVX2) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
+		static_branch_enable(&chacha_use_avx2);
+
+		if (boot_cpu_has(X86_FEATURE_AVX512VL) &&
+		    boot_cpu_has(X86_FEATURE_AVX512BW)) /* kmovq */
+			static_branch_enable(&chacha_use_avx512vl);
+	}
+}