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

5 files changed, 841 insertions, 0 deletions

diff --git a/lib/lzo/Makefile b/lib/lzo/Makefile
new file mode 100644
index 000000000..fc7b2b7ef
--- /dev/null
+++ b/lib/lzo/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+lzo_compress-objs := lzo1x_compress.o lzo1x_compress_safe.o
+lzo_decompress-objs := lzo1x_decompress_safe.o
+
+obj-$(CONFIG_LZO_COMPRESS) += lzo_compress.o
+obj-$(CONFIG_LZO_DECOMPRESS) += lzo_decompress.o
diff --git a/lib/lzo/lzo1x_compress.c b/lib/lzo/lzo1x_compress.c
new file mode 100644
index 000000000..01586af23
--- /dev/null
+++ b/lib/lzo/lzo1x_compress.c
@@ -0,0 +1,450 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  LZO1X Compressor from LZO
+ *
+ *  Copyright (C) 1996-2012 Markus F.X.J. Oberhumer <markus@oberhumer.com>
+ *
+ *  The full LZO package can be found at:
+ *  http://www.oberhumer.com/opensource/lzo/
+ *
+ *  Changed for Linux kernel use by:
+ *  Nitin Gupta <nitingupta910@gmail.com>
+ *  Richard Purdie <rpurdie@openedhand.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/unaligned.h>
+#include <linux/lzo.h>
+#include "lzodefs.h"
+
+#undef LZO_UNSAFE
+
+#ifndef LZO_SAFE
+#define LZO_UNSAFE 1
+#define LZO_SAFE(name) name
+#define HAVE_OP(x) 1
+#endif
+
+#define NEED_OP(x) if (unlikely(!HAVE_OP(x))) goto output_overrun
+
+static noinline int
+LZO_SAFE(lzo1x_1_do_compress)(const unsigned char *in, size_t in_len,
+			      unsigned char **out, unsigned char *op_end,
+			      size_t *tp, void *wrkmem,
+			      signed char *state_offset,
+			      const unsigned char bitstream_version)
+{
+	const unsigned char *ip;
+	unsigned char *op;
+	const unsigned char * const in_end = in + in_len;
+	const unsigned char * const ip_end = in + in_len - 20;
+	const unsigned char *ii;
+	lzo_dict_t * const dict = (lzo_dict_t *) wrkmem;
+	size_t ti = *tp;
+
+	op = *out;
+	ip = in;
+	ii = ip;
+	ip += ti < 4 ? 4 - ti : 0;
+
+	for (;;) {
+		const unsigned char *m_pos = NULL;
+		size_t t, m_len, m_off;
+		u32 dv;
+		u32 run_length = 0;
+literal:
+		ip += 1 + ((ip - ii) >> 5);
+next:
+		if (unlikely(ip >= ip_end))
+			break;
+		dv = get_unaligned_le32(ip);
+
+		if (dv == 0 && bitstream_version) {
+			const unsigned char *ir = ip + 4;
+			const unsigned char *limit = min(ip_end, ip + MAX_ZERO_RUN_LENGTH + 1);
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && \
+	defined(LZO_FAST_64BIT_MEMORY_ACCESS)
+			u64 dv64;
+
+			for (; (ir + 32) <= limit; ir += 32) {
+				dv64 = get_unaligned((u64 *)ir);
+				dv64 |= get_unaligned((u64 *)ir + 1);
+				dv64 |= get_unaligned((u64 *)ir + 2);
+				dv64 |= get_unaligned((u64 *)ir + 3);
+				if (dv64)
+					break;
+			}
+			for (; (ir + 8) <= limit; ir += 8) {
+				dv64 = get_unaligned((u64 *)ir);
+				if (dv64) {
+#  if defined(__LITTLE_ENDIAN)
+					ir += __builtin_ctzll(dv64) >> 3;
+#  elif defined(__BIG_ENDIAN)
+					ir += __builtin_clzll(dv64) >> 3;
+#  else
+#    error "missing endian definition"
+#  endif
+					break;
+				}
+			}
+#else
+			while ((ir < (const unsigned char *)
+					ALIGN((uintptr_t)ir, 4)) &&
+					(ir < limit) && (*ir == 0))
+				ir++;
+			if (IS_ALIGNED((uintptr_t)ir, 4)) {
+				for (; (ir + 4) <= limit; ir += 4) {
+					dv = *((u32 *)ir);
+					if (dv) {
+#  if defined(__LITTLE_ENDIAN)
+						ir += __builtin_ctz(dv) >> 3;
+#  elif defined(__BIG_ENDIAN)
+						ir += __builtin_clz(dv) >> 3;
+#  else
+#    error "missing endian definition"
+#  endif
+						break;
+					}
+				}
+			}
+#endif
+			while (likely(ir < limit) && unlikely(*ir == 0))
+				ir++;
+			run_length = ir - ip;
+			if (run_length > MAX_ZERO_RUN_LENGTH)
+				run_length = MAX_ZERO_RUN_LENGTH;
+		} else {
+			t = ((dv * 0x1824429d) >> (32 - D_BITS)) & D_MASK;
+			m_pos = in + dict[t];
+			dict[t] = (lzo_dict_t) (ip - in);
+			if (unlikely(dv != get_unaligned_le32(m_pos)))
+				goto literal;
+		}
+
+		ii -= ti;
+		ti = 0;
+		t = ip - ii;
+		if (t != 0) {
+			if (t <= 3) {
+				op[*state_offset] |= t;
+				NEED_OP(4);
+				COPY4(op, ii);
+				op += t;
+			} else if (t <= 16) {
+				NEED_OP(17);
+				*op++ = (t - 3);
+				COPY8(op, ii);
+				COPY8(op + 8, ii + 8);
+				op += t;
+			} else {
+				if (t <= 18) {
+					NEED_OP(1);
+					*op++ = (t - 3);
+				} else {
+					size_t tt = t - 18;
+					NEED_OP(1);
+					*op++ = 0;
+					while (unlikely(tt > 255)) {
+						tt -= 255;
+						NEED_OP(1);
+						*op++ = 0;
+					}
+					NEED_OP(1);
+					*op++ = tt;
+				}
+				NEED_OP(t);
+				do {
+					COPY8(op, ii);
+					COPY8(op + 8, ii + 8);
+					op += 16;
+					ii += 16;
+					t -= 16;
+				} while (t >= 16);
+				if (t > 0) do {
+					*op++ = *ii++;
+				} while (--t > 0);
+			}
+		}
+
+		if (unlikely(run_length)) {
+			ip += run_length;
+			run_length -= MIN_ZERO_RUN_LENGTH;
+			NEED_OP(4);
+			put_unaligned_le32((run_length << 21) | 0xfffc18
+					   | (run_length & 0x7), op);
+			op += 4;
+			run_length = 0;
+			*state_offset = -3;
+			goto finished_writing_instruction;
+		}
+
+		m_len = 4;
+		{
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(LZO_USE_CTZ64)
+		u64 v;
+		v = get_unaligned((const u64 *) (ip + m_len)) ^
+		    get_unaligned((const u64 *) (m_pos + m_len));
+		if (unlikely(v == 0)) {
+			do {
+				m_len += 8;
+				v = get_unaligned((const u64 *) (ip + m_len)) ^
+				    get_unaligned((const u64 *) (m_pos + m_len));
+				if (unlikely(ip + m_len >= ip_end))
+					goto m_len_done;
+			} while (v == 0);
+		}
+#  if defined(__LITTLE_ENDIAN)
+		m_len += (unsigned) __builtin_ctzll(v) / 8;
+#  elif defined(__BIG_ENDIAN)
+		m_len += (unsigned) __builtin_clzll(v) / 8;
+#  else
+#    error "missing endian definition"
+#  endif
+#elif defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(LZO_USE_CTZ32)
+		u32 v;
+		v = get_unaligned((const u32 *) (ip + m_len)) ^
+		    get_unaligned((const u32 *) (m_pos + m_len));
+		if (unlikely(v == 0)) {
+			do {
+				m_len += 4;
+				v = get_unaligned((const u32 *) (ip + m_len)) ^
+				    get_unaligned((const u32 *) (m_pos + m_len));
+				if (v != 0)
+					break;
+				m_len += 4;
+				v = get_unaligned((const u32 *) (ip + m_len)) ^
+				    get_unaligned((const u32 *) (m_pos + m_len));
+				if (unlikely(ip + m_len >= ip_end))
+					goto m_len_done;
+			} while (v == 0);
+		}
+#  if defined(__LITTLE_ENDIAN)
+		m_len += (unsigned) __builtin_ctz(v) / 8;
+#  elif defined(__BIG_ENDIAN)
+		m_len += (unsigned) __builtin_clz(v) / 8;
+#  else
+#    error "missing endian definition"
+#  endif
+#else
+		if (unlikely(ip[m_len] == m_pos[m_len])) {
+			do {
+				m_len += 1;
+				if (ip[m_len] != m_pos[m_len])
+					break;
+				m_len += 1;
+				if (ip[m_len] != m_pos[m_len])
+					break;
+				m_len += 1;
+				if (ip[m_len] != m_pos[m_len])
+					break;
+				m_len += 1;
+				if (ip[m_len] != m_pos[m_len])
+					break;
+				m_len += 1;
+				if (ip[m_len] != m_pos[m_len])
+					break;
+				m_len += 1;
+				if (ip[m_len] != m_pos[m_len])
+					break;
+				m_len += 1;
+				if (ip[m_len] != m_pos[m_len])
+					break;
+				m_len += 1;
+				if (unlikely(ip + m_len >= ip_end))
+					goto m_len_done;
+			} while (ip[m_len] == m_pos[m_len]);
+		}
+#endif
+		}
+m_len_done:
+
+		m_off = ip - m_pos;
+		ip += m_len;
+		if (m_len <= M2_MAX_LEN && m_off <= M2_MAX_OFFSET) {
+			m_off -= 1;
+			NEED_OP(2);
+			*op++ = (((m_len - 1) << 5) | ((m_off & 7) << 2));
+			*op++ = (m_off >> 3);
+		} else if (m_off <= M3_MAX_OFFSET) {
+			m_off -= 1;
+			NEED_OP(1);
+			if (m_len <= M3_MAX_LEN)
+				*op++ = (M3_MARKER | (m_len - 2));
+			else {
+				m_len -= M3_MAX_LEN;
+				*op++ = M3_MARKER | 0;
+				while (unlikely(m_len > 255)) {
+					m_len -= 255;
+					NEED_OP(1);
+					*op++ = 0;
+				}
+				NEED_OP(1);
+				*op++ = (m_len);
+			}
+			NEED_OP(2);
+			*op++ = (m_off << 2);
+			*op++ = (m_off >> 6);
+		} else {
+			m_off -= 0x4000;
+			NEED_OP(1);
+			if (m_len <= M4_MAX_LEN)
+				*op++ = (M4_MARKER | ((m_off >> 11) & 8)
+						| (m_len - 2));
+			else {
+				if (unlikely(((m_off & 0x403f) == 0x403f)
+						&& (m_len >= 261)
+						&& (m_len <= 264))
+						&& likely(bitstream_version)) {
+					// Under lzo-rle, block copies
+					// for 261 <= length <= 264 and
+					// (distance & 0x80f3) == 0x80f3
+					// can result in ambiguous
+					// output. Adjust length
+					// to 260 to prevent ambiguity.
+					ip -= m_len - 260;
+					m_len = 260;
+				}
+				m_len -= M4_MAX_LEN;
+				*op++ = (M4_MARKER | ((m_off >> 11) & 8));
+				while (unlikely(m_len > 255)) {
+					NEED_OP(1);
+					m_len -= 255;
+					*op++ = 0;
+				}
+				NEED_OP(1);
+				*op++ = (m_len);
+			}
+			NEED_OP(2);
+			*op++ = (m_off << 2);
+			*op++ = (m_off >> 6);
+		}
+		*state_offset = -2;
+finished_writing_instruction:
+		ii = ip;
+		goto next;
+	}
+	*out = op;
+	*tp = in_end - (ii - ti);
+	return LZO_E_OK;
+
+output_overrun:
+	return LZO_E_OUTPUT_OVERRUN;
+}
+
+static int LZO_SAFE(lzogeneric1x_1_compress)(
+	const unsigned char *in, size_t in_len,
+	unsigned char *out, size_t *out_len,
+	void *wrkmem, const unsigned char bitstream_version)
+{
+	unsigned char * const op_end = out + *out_len;
+	const unsigned char *ip = in;
+	unsigned char *op = out;
+	unsigned char *data_start;
+	size_t l = in_len;
+	size_t t = 0;
+	signed char state_offset = -2;
+	unsigned int m4_max_offset;
+
+	// LZO v0 will never write 17 as first byte (except for zero-length
+	// input), so this is used to version the bitstream
+	if (bitstream_version > 0) {
+		*op++ = 17;
+		*op++ = bitstream_version;
+		m4_max_offset = M4_MAX_OFFSET_V1;
+	} else {
+		m4_max_offset = M4_MAX_OFFSET_V0;
+	}
+
+	data_start = op;
+
+	while (l > 20) {
+		size_t ll = min_t(size_t, l, m4_max_offset + 1);
+		uintptr_t ll_end = (uintptr_t) ip + ll;
+		int err;
+
+		if ((ll_end + ((t + ll) >> 5)) <= ll_end)
+			break;
+		BUILD_BUG_ON(D_SIZE * sizeof(lzo_dict_t) > LZO1X_1_MEM_COMPRESS);
+		memset(wrkmem, 0, D_SIZE * sizeof(lzo_dict_t));
+		err = LZO_SAFE(lzo1x_1_do_compress)(
+			ip, ll, &op, op_end, &t, wrkmem,
+			&state_offset, bitstream_version);
+		if (err != LZO_E_OK)
+			return err;
+		ip += ll;
+		l  -= ll;
+	}
+	t += l;
+
+	if (t > 0) {
+		const unsigned char *ii = in + in_len - t;
+
+		if (op == data_start && t <= 238) {
+			NEED_OP(1);
+			*op++ = (17 + t);
+		} else if (t <= 3) {
+			op[state_offset] |= t;
+		} else if (t <= 18) {
+			NEED_OP(1);
+			*op++ = (t - 3);
+		} else {
+			size_t tt = t - 18;
+			NEED_OP(1);
+			*op++ = 0;
+			while (tt > 255) {
+				tt -= 255;
+				NEED_OP(1);
+				*op++ = 0;
+			}
+			NEED_OP(1);
+			*op++ = tt;
+		}
+		NEED_OP(t);
+		if (t >= 16) do {
+			COPY8(op, ii);
+			COPY8(op + 8, ii + 8);
+			op += 16;
+			ii += 16;
+			t -= 16;
+		} while (t >= 16);
+		if (t > 0) do {
+			*op++ = *ii++;
+		} while (--t > 0);
+	}
+
+	NEED_OP(3);
+	*op++ = M4_MARKER | 1;
+	*op++ = 0;
+	*op++ = 0;
+
+	*out_len = op - out;
+	return LZO_E_OK;
+
+output_overrun:
+	return LZO_E_OUTPUT_OVERRUN;
+}
+
+int LZO_SAFE(lzo1x_1_compress)(const unsigned char *in, size_t in_len,
+			       unsigned char *out, size_t *out_len,
+			       void *wrkmem)
+{
+	return LZO_SAFE(lzogeneric1x_1_compress)(
+		in, in_len, out, out_len, wrkmem, 0);
+}
+
+int LZO_SAFE(lzorle1x_1_compress)(const unsigned char *in, size_t in_len,
+				  unsigned char *out, size_t *out_len,
+				  void *wrkmem)
+{
+	return LZO_SAFE(lzogeneric1x_1_compress)(
+		in, in_len, out, out_len, wrkmem, LZO_VERSION);
+}
+
+EXPORT_SYMBOL_GPL(LZO_SAFE(lzo1x_1_compress));
+EXPORT_SYMBOL_GPL(LZO_SAFE(lzorle1x_1_compress));
+
+#ifndef LZO_UNSAFE
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZO1X-1 Compressor");
+#endif
diff --git a/lib/lzo/lzo1x_compress_safe.c b/lib/lzo/lzo1x_compress_safe.c
new file mode 100644
index 000000000..371c9f849
--- /dev/null
+++ b/lib/lzo/lzo1x_compress_safe.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  LZO1X Compressor from LZO
+ *
+ *  Copyright (C) 1996-2012 Markus F.X.J. Oberhumer <markus@oberhumer.com>
+ *
+ *  The full LZO package can be found at:
+ *  http://www.oberhumer.com/opensource/lzo/
+ *
+ *  Changed for Linux kernel use by:
+ *  Nitin Gupta <nitingupta910@gmail.com>
+ *  Richard Purdie <rpurdie@openedhand.com>
+ */
+
+#define LZO_SAFE(name) name##_safe
+#define HAVE_OP(x) ((size_t)(op_end - op) >= (size_t)(x))
+
+#include "lzo1x_compress.c"
diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c
new file mode 100644
index 000000000..318abb82c
--- /dev/null
+++ b/lib/lzo/lzo1x_decompress_safe.c
@@ -0,0 +1,296 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  LZO1X Decompressor from LZO
+ *
+ *  Copyright (C) 1996-2012 Markus F.X.J. Oberhumer <markus@oberhumer.com>
+ *
+ *  The full LZO package can be found at:
+ *  http://www.oberhumer.com/opensource/lzo/
+ *
+ *  Changed for Linux kernel use by:
+ *  Nitin Gupta <nitingupta910@gmail.com>
+ *  Richard Purdie <rpurdie@openedhand.com>
+ */
+
+#ifndef STATIC
+#include <linux/module.h>
+#include <linux/kernel.h>
+#endif
+#include <linux/unaligned.h>
+#include <linux/lzo.h>
+#include "lzodefs.h"
+
+#define HAVE_IP(x)      ((size_t)(ip_end - ip) >= (size_t)(x))
+#define HAVE_OP(x)      ((size_t)(op_end - op) >= (size_t)(x))
+#define NEED_IP(x)      if (unlikely(!HAVE_IP(x))) goto input_overrun
+#define NEED_OP(x)      if (unlikely(!HAVE_OP(x))) goto output_overrun
+#define TEST_LB(m_pos)  if (unlikely((m_pos) < out)) goto lookbehind_overrun
+
+/* This MAX_255_COUNT is the maximum number of times we can add 255 to a base
+ * count without overflowing an integer. The multiply will overflow when
+ * multiplying 255 by more than MAXINT/255. The sum will overflow earlier
+ * depending on the base count. Since the base count is taken from a u8
+ * and a few bits, it is safe to assume that it will always be lower than
+ * or equal to 2*255, thus we can always prevent any overflow by accepting
+ * two less 255 steps. See Documentation/staging/lzo.rst for more information.
+ */
+#define MAX_255_COUNT      ((((size_t)~0) / 255) - 2)
+
+int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
+			  unsigned char *out, size_t *out_len)
+{
+	unsigned char *op;
+	const unsigned char *ip;
+	size_t t, next;
+	size_t state = 0;
+	const unsigned char *m_pos;
+	const unsigned char * const ip_end = in + in_len;
+	unsigned char * const op_end = out + *out_len;
+
+	unsigned char bitstream_version;
+
+	op = out;
+	ip = in;
+
+	if (unlikely(in_len < 3))
+		goto input_overrun;
+
+	if (likely(in_len >= 5) && likely(*ip == 17)) {
+		bitstream_version = ip[1];
+		ip += 2;
+	} else {
+		bitstream_version = 0;
+	}
+
+	if (*ip > 17) {
+		t = *ip++ - 17;
+		if (t < 4) {
+			next = t;
+			goto match_next;
+		}
+		goto copy_literal_run;
+	}
+
+	for (;;) {
+		t = *ip++;
+		if (t < 16) {
+			if (likely(state == 0)) {
+				if (unlikely(t == 0)) {
+					size_t offset;
+					const unsigned char *ip_last = ip;
+
+					while (unlikely(*ip == 0)) {
+						ip++;
+						NEED_IP(1);
+					}
+					offset = ip - ip_last;
+					if (unlikely(offset > MAX_255_COUNT))
+						return LZO_E_ERROR;
+
+					offset = (offset << 8) - offset;
+					t += offset + 15 + *ip++;
+				}
+				t += 3;
+copy_literal_run:
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+				if (likely(HAVE_IP(t + 15) && HAVE_OP(t + 15))) {
+					const unsigned char *ie = ip + t;
+					unsigned char *oe = op + t;
+					do {
+						COPY8(op, ip);
+						op += 8;
+						ip += 8;
+						COPY8(op, ip);
+						op += 8;
+						ip += 8;
+					} while (ip < ie);
+					ip = ie;
+					op = oe;
+				} else
+#endif
+				{
+					NEED_OP(t);
+					NEED_IP(t + 3);
+					do {
+						*op++ = *ip++;
+					} while (--t > 0);
+				}
+				state = 4;
+				continue;
+			} else if (state != 4) {
+				next = t & 3;
+				m_pos = op - 1;
+				m_pos -= t >> 2;
+				m_pos -= *ip++ << 2;
+				TEST_LB(m_pos);
+				NEED_OP(2);
+				op[0] = m_pos[0];
+				op[1] = m_pos[1];
+				op += 2;
+				goto match_next;
+			} else {
+				next = t & 3;
+				m_pos = op - (1 + M2_MAX_OFFSET);
+				m_pos -= t >> 2;
+				m_pos -= *ip++ << 2;
+				t = 3;
+			}
+		} else if (t >= 64) {
+			next = t & 3;
+			m_pos = op - 1;
+			m_pos -= (t >> 2) & 7;
+			m_pos -= *ip++ << 3;
+			t = (t >> 5) - 1 + (3 - 1);
+		} else if (t >= 32) {
+			t = (t & 31) + (3 - 1);
+			if (unlikely(t == 2)) {
+				size_t offset;
+				const unsigned char *ip_last = ip;
+
+				while (unlikely(*ip == 0)) {
+					ip++;
+					NEED_IP(1);
+				}
+				offset = ip - ip_last;
+				if (unlikely(offset > MAX_255_COUNT))
+					return LZO_E_ERROR;
+
+				offset = (offset << 8) - offset;
+				t += offset + 31 + *ip++;
+				NEED_IP(2);
+			}
+			m_pos = op - 1;
+			next = get_unaligned_le16(ip);
+			ip += 2;
+			m_pos -= next >> 2;
+			next &= 3;
+		} else {
+			NEED_IP(2);
+			next = get_unaligned_le16(ip);
+			if (((next & 0xfffc) == 0xfffc) &&
+			    ((t & 0xf8) == 0x18) &&
+			    likely(bitstream_version)) {
+				NEED_IP(3);
+				t &= 7;
+				t |= ip[2] << 3;
+				t += MIN_ZERO_RUN_LENGTH;
+				NEED_OP(t);
+				memset(op, 0, t);
+				op += t;
+				next &= 3;
+				ip += 3;
+				goto match_next;
+			} else {
+				m_pos = op;
+				m_pos -= (t & 8) << 11;
+				t = (t & 7) + (3 - 1);
+				if (unlikely(t == 2)) {
+					size_t offset;
+					const unsigned char *ip_last = ip;
+
+					while (unlikely(*ip == 0)) {
+						ip++;
+						NEED_IP(1);
+					}
+					offset = ip - ip_last;
+					if (unlikely(offset > MAX_255_COUNT))
+						return LZO_E_ERROR;
+
+					offset = (offset << 8) - offset;
+					t += offset + 7 + *ip++;
+					NEED_IP(2);
+					next = get_unaligned_le16(ip);
+				}
+				ip += 2;
+				m_pos -= next >> 2;
+				next &= 3;
+				if (m_pos == op)
+					goto eof_found;
+				m_pos -= 0x4000;
+			}
+		}
+		TEST_LB(m_pos);
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+		if (op - m_pos >= 8) {
+			unsigned char *oe = op + t;
+			if (likely(HAVE_OP(t + 15))) {
+				do {
+					COPY8(op, m_pos);
+					op += 8;
+					m_pos += 8;
+					COPY8(op, m_pos);
+					op += 8;
+					m_pos += 8;
+				} while (op < oe);
+				op = oe;
+				if (HAVE_IP(6)) {
+					state = next;
+					COPY4(op, ip);
+					op += next;
+					ip += next;
+					continue;
+				}
+			} else {
+				NEED_OP(t);
+				do {
+					*op++ = *m_pos++;
+				} while (op < oe);
+			}
+		} else
+#endif
+		{
+			unsigned char *oe = op + t;
+			NEED_OP(t);
+			op[0] = m_pos[0];
+			op[1] = m_pos[1];
+			op += 2;
+			m_pos += 2;
+			do {
+				*op++ = *m_pos++;
+			} while (op < oe);
+		}
+match_next:
+		state = next;
+		t = next;
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+		if (likely(HAVE_IP(6) && HAVE_OP(4))) {
+			COPY4(op, ip);
+			op += t;
+			ip += t;
+		} else
+#endif
+		{
+			NEED_IP(t + 3);
+			NEED_OP(t);
+			while (t > 0) {
+				*op++ = *ip++;
+				t--;
+			}
+		}
+	}
+
+eof_found:
+	*out_len = op - out;
+	return (t != 3       ? LZO_E_ERROR :
+		ip == ip_end ? LZO_E_OK :
+		ip <  ip_end ? LZO_E_INPUT_NOT_CONSUMED : LZO_E_INPUT_OVERRUN);
+
+input_overrun:
+	*out_len = op - out;
+	return LZO_E_INPUT_OVERRUN;
+
+output_overrun:
+	*out_len = op - out;
+	return LZO_E_OUTPUT_OVERRUN;
+
+lookbehind_overrun:
+	*out_len = op - out;
+	return LZO_E_LOOKBEHIND_OVERRUN;
+}
+#ifndef STATIC
+EXPORT_SYMBOL_GPL(lzo1x_decompress_safe);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZO1X Decompressor");
+
+#endif
diff --git a/lib/lzo/lzodefs.h b/lib/lzo/lzodefs.h
new file mode 100644
index 000000000..b60851fcf
--- /dev/null
+++ b/lib/lzo/lzodefs.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  lzodefs.h -- architecture, OS and compiler specific defines
+ *
+ *  Copyright (C) 1996-2012 Markus F.X.J. Oberhumer <markus@oberhumer.com>
+ *
+ *  The full LZO package can be found at:
+ *  http://www.oberhumer.com/opensource/lzo/
+ *
+ *  Changed for Linux kernel use by:
+ *  Nitin Gupta <nitingupta910@gmail.com>
+ *  Richard Purdie <rpurdie@openedhand.com>
+ */
+
+
+/* Version
+ * 0: original lzo version
+ * 1: lzo with support for RLE
+ */
+#define LZO_VERSION 1
+
+#define COPY4(dst, src)	\
+		put_unaligned(get_unaligned((const u32 *)(src)), (u32 *)(dst))
+#if defined(CONFIG_X86_64) || defined(CONFIG_ARM64)
+#define COPY8(dst, src)	\
+		put_unaligned(get_unaligned((const u64 *)(src)), (u64 *)(dst))
+#else
+#define COPY8(dst, src)	\
+		COPY4(dst, src); COPY4((dst) + 4, (src) + 4)
+#endif
+
+#if defined(__BIG_ENDIAN) && defined(__LITTLE_ENDIAN)
+#error "conflicting endian definitions"
+#elif defined(CONFIG_X86_64) || defined(CONFIG_ARM64)
+#define LZO_USE_CTZ64	1
+#define LZO_USE_CTZ32	1
+#define LZO_FAST_64BIT_MEMORY_ACCESS
+#elif defined(CONFIG_X86) || defined(CONFIG_PPC)
+#define LZO_USE_CTZ32	1
+#elif defined(CONFIG_ARM) && (__LINUX_ARM_ARCH__ >= 5)
+#define LZO_USE_CTZ32	1
+#endif
+
+#define M1_MAX_OFFSET	0x0400
+#define M2_MAX_OFFSET	0x0800
+#define M3_MAX_OFFSET	0x4000
+#define M4_MAX_OFFSET_V0	0xbfff
+#define M4_MAX_OFFSET_V1	0xbffe
+
+#define M1_MIN_LEN	2
+#define M1_MAX_LEN	2
+#define M2_MIN_LEN	3
+#define M2_MAX_LEN	8
+#define M3_MIN_LEN	3
+#define M3_MAX_LEN	33
+#define M4_MIN_LEN	3
+#define M4_MAX_LEN	9
+
+#define M1_MARKER	0
+#define M2_MARKER	64
+#define M3_MARKER	32
+#define M4_MARKER	16
+
+#define MIN_ZERO_RUN_LENGTH	4
+#define MAX_ZERO_RUN_LENGTH	(2047 + MIN_ZERO_RUN_LENGTH)
+
+#define lzo_dict_t      unsigned short
+#define D_BITS		13
+#define D_SIZE		(1u << D_BITS)
+#define D_MASK		(D_SIZE - 1)
+#define D_HIGH		((D_MASK >> 1) + 1)