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

17 files changed, 1069 insertions, 0 deletions

diff --git a/arch/csky/abiv1/Makefile b/arch/csky/abiv1/Makefile
new file mode 100644
index 000000000..a4b2ade0f
--- /dev/null
+++ b/arch/csky/abiv1/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_CPU_NEED_SOFTALIGN)	+= alignment.o
+obj-y					+= bswapdi.o
+obj-y					+= bswapsi.o
+obj-y					+= cacheflush.o
+obj-y					+= mmap.o
diff --git a/arch/csky/abiv1/alignment.c b/arch/csky/abiv1/alignment.c
new file mode 100644
index 000000000..aee904833
--- /dev/null
+++ b/arch/csky/abiv1/alignment.c
@@ -0,0 +1,340 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/kernel.h>
+#include <linux/uaccess.h>
+#include <linux/ptrace.h>
+
+static int align_kern_enable = 1;
+static int align_usr_enable = 1;
+static int align_kern_count = 0;
+static int align_usr_count = 0;
+
+static inline uint32_t get_ptreg(struct pt_regs *regs, uint32_t rx)
+{
+	return rx == 15 ? regs->lr : *((uint32_t *)&(regs->a0) - 2 + rx);
+}
+
+static inline void put_ptreg(struct pt_regs *regs, uint32_t rx, uint32_t val)
+{
+	if (rx == 15)
+		regs->lr = val;
+	else
+		*((uint32_t *)&(regs->a0) - 2 + rx) = val;
+}
+
+/*
+ * Get byte-value from addr and set it to *valp.
+ *
+ * Success: return 0
+ * Failure: return 1
+ */
+static int ldb_asm(uint32_t addr, uint32_t *valp)
+{
+	uint32_t val;
+	int err;
+
+	asm volatile (
+		"movi	%0, 0\n"
+		"1:\n"
+		"ldb	%1, (%2)\n"
+		"br	3f\n"
+		"2:\n"
+		"movi	%0, 1\n"
+		"br	3f\n"
+		".section __ex_table,\"a\"\n"
+		".align 2\n"
+		".long	1b, 2b\n"
+		".previous\n"
+		"3:\n"
+		: "=&r"(err), "=r"(val)
+		: "r" (addr)
+	);
+
+	*valp = val;
+
+	return err;
+}
+
+/*
+ * Put byte-value to addr.
+ *
+ * Success: return 0
+ * Failure: return 1
+ */
+static int stb_asm(uint32_t addr, uint32_t val)
+{
+	int err;
+
+	asm volatile (
+		"movi	%0, 0\n"
+		"1:\n"
+		"stb	%1, (%2)\n"
+		"br	3f\n"
+		"2:\n"
+		"movi	%0, 1\n"
+		"br	3f\n"
+		".section __ex_table,\"a\"\n"
+		".align 2\n"
+		".long	1b, 2b\n"
+		".previous\n"
+		"3:\n"
+		: "=&r"(err)
+		: "r"(val), "r" (addr)
+	);
+
+	return err;
+}
+
+/*
+ * Get half-word from [rx + imm]
+ *
+ * Success: return 0
+ * Failure: return 1
+ */
+static int ldh_c(struct pt_regs *regs, uint32_t rz, uint32_t addr)
+{
+	uint32_t byte0, byte1;
+
+	if (ldb_asm(addr, &byte0))
+		return 1;
+	addr += 1;
+	if (ldb_asm(addr, &byte1))
+		return 1;
+
+	byte0 |= byte1 << 8;
+	put_ptreg(regs, rz, byte0);
+
+	return 0;
+}
+
+/*
+ * Store half-word to [rx + imm]
+ *
+ * Success: return 0
+ * Failure: return 1
+ */
+static int sth_c(struct pt_regs *regs, uint32_t rz, uint32_t addr)
+{
+	uint32_t byte0, byte1;
+
+	byte0 = byte1 = get_ptreg(regs, rz);
+
+	byte0 &= 0xff;
+
+	if (stb_asm(addr, byte0))
+		return 1;
+
+	addr += 1;
+	byte1 = (byte1 >> 8) & 0xff;
+	if (stb_asm(addr, byte1))
+		return 1;
+
+	return 0;
+}
+
+/*
+ * Get word from [rx + imm]
+ *
+ * Success: return 0
+ * Failure: return 1
+ */
+static int ldw_c(struct pt_regs *regs, uint32_t rz, uint32_t addr)
+{
+	uint32_t byte0, byte1, byte2, byte3;
+
+	if (ldb_asm(addr, &byte0))
+		return 1;
+
+	addr += 1;
+	if (ldb_asm(addr, &byte1))
+		return 1;
+
+	addr += 1;
+	if (ldb_asm(addr, &byte2))
+		return 1;
+
+	addr += 1;
+	if (ldb_asm(addr, &byte3))
+		return 1;
+
+	byte0 |= byte1 << 8;
+	byte0 |= byte2 << 16;
+	byte0 |= byte3 << 24;
+
+	put_ptreg(regs, rz, byte0);
+
+	return 0;
+}
+
+/*
+ * Store word to [rx + imm]
+ *
+ * Success: return 0
+ * Failure: return 1
+ */
+static int stw_c(struct pt_regs *regs, uint32_t rz, uint32_t addr)
+{
+	uint32_t byte0, byte1, byte2, byte3;
+
+	byte0 = byte1 = byte2 = byte3 = get_ptreg(regs, rz);
+
+	byte0 &= 0xff;
+
+	if (stb_asm(addr, byte0))
+		return 1;
+
+	addr += 1;
+	byte1 = (byte1 >> 8) & 0xff;
+	if (stb_asm(addr, byte1))
+		return 1;
+
+	addr += 1;
+	byte2 = (byte2 >> 16) & 0xff;
+	if (stb_asm(addr, byte2))
+		return 1;
+
+	addr += 1;
+	byte3 = (byte3 >> 24) & 0xff;
+	if (stb_asm(addr, byte3))
+		return 1;
+
+	return 0;
+}
+
+extern int fixup_exception(struct pt_regs *regs);
+
+#define OP_LDH 0xc000
+#define OP_STH 0xd000
+#define OP_LDW 0x8000
+#define OP_STW 0x9000
+
+void csky_alignment(struct pt_regs *regs)
+{
+	int ret;
+	uint16_t tmp;
+	uint32_t opcode = 0;
+	uint32_t rx     = 0;
+	uint32_t rz     = 0;
+	uint32_t imm    = 0;
+	uint32_t addr   = 0;
+
+	if (!user_mode(regs))
+		goto kernel_area;
+
+	if (!align_usr_enable) {
+		pr_err("%s user disabled.\n", __func__);
+		goto bad_area;
+	}
+
+	align_usr_count++;
+
+	ret = get_user(tmp, (uint16_t *)instruction_pointer(regs));
+	if (ret) {
+		pr_err("%s get_user failed.\n", __func__);
+		goto bad_area;
+	}
+
+	goto good_area;
+
+kernel_area:
+	if (!align_kern_enable) {
+		pr_err("%s kernel disabled.\n", __func__);
+		goto bad_area;
+	}
+
+	align_kern_count++;
+
+	tmp = *(uint16_t *)instruction_pointer(regs);
+
+good_area:
+	opcode = (uint32_t)tmp;
+
+	rx  = opcode & 0xf;
+	imm = (opcode >> 4) & 0xf;
+	rz  = (opcode >> 8) & 0xf;
+	opcode &= 0xf000;
+
+	if (rx == 0 || rx == 1 || rz == 0 || rz == 1)
+		goto bad_area;
+
+	switch (opcode) {
+	case OP_LDH:
+		addr = get_ptreg(regs, rx) + (imm << 1);
+		ret = ldh_c(regs, rz, addr);
+		break;
+	case OP_LDW:
+		addr = get_ptreg(regs, rx) + (imm << 2);
+		ret = ldw_c(regs, rz, addr);
+		break;
+	case OP_STH:
+		addr = get_ptreg(regs, rx) + (imm << 1);
+		ret = sth_c(regs, rz, addr);
+		break;
+	case OP_STW:
+		addr = get_ptreg(regs, rx) + (imm << 2);
+		ret = stw_c(regs, rz, addr);
+		break;
+	}
+
+	if (ret)
+		goto bad_area;
+
+	regs->pc += 2;
+
+	return;
+
+bad_area:
+	if (!user_mode(regs)) {
+		if (fixup_exception(regs))
+			return;
+
+		bust_spinlocks(1);
+		pr_alert("%s opcode: %x, rz: %d, rx: %d, imm: %d, addr: %x.\n",
+				__func__, opcode, rz, rx, imm, addr);
+		show_regs(regs);
+		bust_spinlocks(0);
+		make_task_dead(SIGKILL);
+	}
+
+	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)addr);
+}
+
+static const struct ctl_table alignment_tbl[] = {
+	{
+		.procname = "kernel_enable",
+		.data = &align_kern_enable,
+		.maxlen = sizeof(align_kern_enable),
+		.mode = 0666,
+		.proc_handler = &proc_dointvec
+	},
+	{
+		.procname = "user_enable",
+		.data = &align_usr_enable,
+		.maxlen = sizeof(align_usr_enable),
+		.mode = 0666,
+		.proc_handler = &proc_dointvec
+	},
+	{
+		.procname = "kernel_count",
+		.data = &align_kern_count,
+		.maxlen = sizeof(align_kern_count),
+		.mode = 0666,
+		.proc_handler = &proc_dointvec
+	},
+	{
+		.procname = "user_count",
+		.data = &align_usr_count,
+		.maxlen = sizeof(align_usr_count),
+		.mode = 0666,
+		.proc_handler = &proc_dointvec
+	},
+};
+
+static int __init csky_alignment_init(void)
+{
+	register_sysctl_init("csky/csky_alignment", alignment_tbl);
+	return 0;
+}
+
+arch_initcall(csky_alignment_init);
diff --git a/arch/csky/abiv1/bswapdi.c b/arch/csky/abiv1/bswapdi.c
new file mode 100644
index 000000000..f50a1d6e3
--- /dev/null
+++ b/arch/csky/abiv1/bswapdi.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/export.h>
+#include <linux/compiler.h>
+#include <uapi/linux/swab.h>
+
+unsigned long long notrace __bswapdi2(unsigned long long u)
+{
+	return ___constant_swab64(u);
+}
+EXPORT_SYMBOL(__bswapdi2);
diff --git a/arch/csky/abiv1/bswapsi.c b/arch/csky/abiv1/bswapsi.c
new file mode 100644
index 000000000..0f79182e8
--- /dev/null
+++ b/arch/csky/abiv1/bswapsi.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/export.h>
+#include <linux/compiler.h>
+#include <uapi/linux/swab.h>
+
+unsigned int notrace __bswapsi2(unsigned int u)
+{
+	return ___constant_swab32(u);
+}
+EXPORT_SYMBOL(__bswapsi2);
diff --git a/arch/csky/abiv1/cacheflush.c b/arch/csky/abiv1/cacheflush.c
new file mode 100644
index 000000000..4bc0aad3c
--- /dev/null
+++ b/arch/csky/abiv1/cacheflush.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/syscalls.h>
+#include <linux/spinlock.h>
+#include <asm/page.h>
+#include <asm/cache.h>
+#include <asm/cacheflush.h>
+#include <asm/cachectl.h>
+#include <asm/tlbflush.h>
+
+#define PG_dcache_clean		PG_arch_1
+
+void flush_dcache_folio(struct folio *folio)
+{
+	struct address_space *mapping;
+
+	if (is_zero_pfn(folio_pfn(folio)))
+		return;
+
+	mapping = folio_flush_mapping(folio);
+
+	if (mapping && !folio_mapped(folio))
+		clear_bit(PG_dcache_clean, &folio->flags.f);
+	else {
+		dcache_wbinv_all();
+		if (mapping)
+			icache_inv_all();
+		set_bit(PG_dcache_clean, &folio->flags.f);
+	}
+}
+EXPORT_SYMBOL(flush_dcache_folio);
+
+void flush_dcache_page(struct page *page)
+{
+	flush_dcache_folio(page_folio(page));
+}
+EXPORT_SYMBOL(flush_dcache_page);
+
+void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
+		unsigned long addr, pte_t *ptep, unsigned int nr)
+{
+	unsigned long pfn = pte_pfn(*ptep);
+	struct folio *folio;
+
+	flush_tlb_page(vma, addr);
+
+	if (!pfn_valid(pfn))
+		return;
+
+	if (is_zero_pfn(pfn))
+		return;
+
+	folio = page_folio(pfn_to_page(pfn));
+	if (!test_and_set_bit(PG_dcache_clean, &folio->flags.f))
+		dcache_wbinv_all();
+
+	if (folio_flush_mapping(folio)) {
+		if (vma->vm_flags & VM_EXEC)
+			icache_inv_all();
+	}
+}
+
+void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
+	unsigned long end)
+{
+	dcache_wbinv_all();
+
+	if (vma->vm_flags & VM_EXEC)
+		icache_inv_all();
+}
diff --git a/arch/csky/abiv1/inc/abi/cacheflush.h b/arch/csky/abiv1/inc/abi/cacheflush.h
new file mode 100644
index 000000000..21cc7965c
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/cacheflush.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_CSKY_CACHEFLUSH_H
+#define __ABI_CSKY_CACHEFLUSH_H
+
+#include <linux/mm.h>
+#include <asm/string.h>
+#include <asm/cache.h>
+
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
+extern void flush_dcache_page(struct page *);
+void flush_dcache_folio(struct folio *);
+#define flush_dcache_folio flush_dcache_folio
+
+#define flush_cache_mm(mm)			dcache_wbinv_all()
+#define flush_cache_page(vma, page, pfn)	cache_wbinv_all()
+#define flush_cache_dup_mm(mm)			cache_wbinv_all()
+
+#define flush_dcache_mmap_lock(mapping)		xa_lock_irq(&mapping->i_pages)
+#define flush_dcache_mmap_unlock(mapping)	xa_unlock_irq(&mapping->i_pages)
+
+#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1
+static inline void flush_kernel_vmap_range(void *addr, int size)
+{
+	dcache_wbinv_all();
+}
+static inline void invalidate_kernel_vmap_range(void *addr, int size)
+{
+	dcache_wbinv_all();
+}
+
+#define ARCH_HAS_FLUSH_ANON_PAGE
+static inline void flush_anon_page(struct vm_area_struct *vma,
+			 struct page *page, unsigned long vmaddr)
+{
+	if (PageAnon(page))
+		cache_wbinv_all();
+}
+
+/*
+ * if (current_mm != vma->mm) cache_wbinv_range(start, end) will be broken.
+ * Use cache_wbinv_all() here and need to be improved in future.
+ */
+extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
+
+static inline void flush_cache_vmap(unsigned long start, unsigned long end)
+{
+	cache_wbinv_all();
+}
+
+#define flush_cache_vmap_early(start, end)	do { } while (0)
+#define flush_cache_vunmap(start, end)		cache_wbinv_all()
+
+#define flush_icache_range(start, end)		cache_wbinv_range(start, end)
+#define flush_icache_mm_range(mm, start, end)	cache_wbinv_range(start, end)
+#define flush_icache_deferred(mm)		do {} while (0);
+
+#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
+do { \
+	memcpy(dst, src, len); \
+} while (0)
+
+#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
+do { \
+	memcpy(dst, src, len); \
+	cache_wbinv_all(); \
+} while (0)
+
+#endif /* __ABI_CSKY_CACHEFLUSH_H */
diff --git a/arch/csky/abiv1/inc/abi/ckmmu.h b/arch/csky/abiv1/inc/abi/ckmmu.h
new file mode 100644
index 000000000..416b30c57
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/ckmmu.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_CKMMUV1_H
+#define __ASM_CSKY_CKMMUV1_H
+#include <abi/reg_ops.h>
+
+static inline int read_mmu_index(void)
+{
+	return cprcr("cpcr0");
+}
+
+static inline void write_mmu_index(int value)
+{
+	cpwcr("cpcr0", value);
+}
+
+static inline int read_mmu_entrylo0(void)
+{
+	return cprcr("cpcr2") << 6;
+}
+
+static inline int read_mmu_entrylo1(void)
+{
+	return cprcr("cpcr3") << 6;
+}
+
+static inline void write_mmu_pagemask(int value)
+{
+	cpwcr("cpcr6", value);
+}
+
+static inline int read_mmu_entryhi(void)
+{
+	return cprcr("cpcr4");
+}
+
+static inline void write_mmu_entryhi(int value)
+{
+	cpwcr("cpcr4", value);
+}
+
+static inline unsigned long read_mmu_msa0(void)
+{
+	return cprcr("cpcr30");
+}
+
+static inline void write_mmu_msa0(unsigned long value)
+{
+	cpwcr("cpcr30", value);
+}
+
+static inline unsigned long read_mmu_msa1(void)
+{
+	return cprcr("cpcr31");
+}
+
+static inline void write_mmu_msa1(unsigned long value)
+{
+	cpwcr("cpcr31", value);
+}
+
+/*
+ * TLB operations.
+ */
+static inline void tlb_probe(void)
+{
+	cpwcr("cpcr8", 0x80000000);
+}
+
+static inline void tlb_read(void)
+{
+	cpwcr("cpcr8", 0x40000000);
+}
+
+static inline void tlb_invalid_all(void)
+{
+	cpwcr("cpcr8", 0x04000000);
+}
+
+
+static inline void local_tlb_invalid_all(void)
+{
+	tlb_invalid_all();
+}
+
+static inline void tlb_invalid_indexed(void)
+{
+	cpwcr("cpcr8", 0x02000000);
+}
+
+static inline void setup_pgd(pgd_t *pgd, int asid)
+{
+	cpwcr("cpcr29", __pa(pgd) | BIT(0));
+	write_mmu_entryhi(asid);
+}
+
+static inline pgd_t *get_pgd(void)
+{
+	return __va(cprcr("cpcr29") & ~BIT(0));
+}
+#endif /* __ASM_CSKY_CKMMUV1_H */
diff --git a/arch/csky/abiv1/inc/abi/elf.h b/arch/csky/abiv1/inc/abi/elf.h
new file mode 100644
index 000000000..3058cc06b
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/elf.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_CSKY_ELF_H
+#define __ABI_CSKY_ELF_H
+
+#define ELF_CORE_COPY_REGS(pr_reg, regs) do {	\
+	pr_reg[0] = regs->pc;			\
+	pr_reg[1] = regs->regs[9];		\
+	pr_reg[2] = regs->usp;			\
+	pr_reg[3] = regs->sr;			\
+	pr_reg[4] = regs->a0;			\
+	pr_reg[5] = regs->a1;			\
+	pr_reg[6] = regs->a2;			\
+	pr_reg[7] = regs->a3;			\
+	pr_reg[8] = regs->regs[0];		\
+	pr_reg[9] = regs->regs[1];		\
+	pr_reg[10] = regs->regs[2];		\
+	pr_reg[11] = regs->regs[3];		\
+	pr_reg[12] = regs->regs[4];		\
+	pr_reg[13] = regs->regs[5];		\
+	pr_reg[14] = regs->regs[6];		\
+	pr_reg[15] = regs->regs[7];		\
+	pr_reg[16] = regs->regs[8];		\
+	pr_reg[17] = regs->lr;			\
+} while (0);
+#endif /* __ABI_CSKY_ELF_H */
diff --git a/arch/csky/abiv1/inc/abi/entry.h b/arch/csky/abiv1/inc/abi/entry.h
new file mode 100644
index 000000000..b6a2109b8
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/entry.h
@@ -0,0 +1,176 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_ENTRY_H
+#define __ASM_CSKY_ENTRY_H
+
+#include <asm/setup.h>
+#include <abi/regdef.h>
+
+#define LSAVE_PC	8
+#define LSAVE_PSR	12
+#define LSAVE_A0	24
+#define LSAVE_A1	28
+#define LSAVE_A2	32
+#define LSAVE_A3	36
+#define LSAVE_A4	40
+#define LSAVE_A5	44
+
+#define usp ss1
+
+.macro USPTOKSP
+	mtcr	sp, usp
+	mfcr	sp, ss0
+.endm
+
+.macro KSPTOUSP
+	mtcr	sp, ss0
+	mfcr	sp, usp
+.endm
+
+.macro	SAVE_ALL epc_inc
+	mtcr    r13, ss2
+	mfcr    r13, epsr
+	btsti   r13, 31
+	bt      1f
+	USPTOKSP
+1:
+	subi    sp, 32
+	subi    sp, 32
+	subi    sp, 16
+	stw     r13, (sp, 12)
+
+	stw     lr, (sp, 4)
+
+	mfcr	lr, epc
+	movi	r13, \epc_inc
+	add	lr, r13
+	stw     lr, (sp, 8)
+
+	mov	lr, sp
+	addi	lr, 32
+	addi	lr, 32
+	addi	lr, 16
+	bt	2f
+	mfcr	lr, ss1
+2:
+	stw     lr, (sp, 16)
+
+	stw     a0, (sp, 20)
+	stw     a0, (sp, 24)
+	stw     a1, (sp, 28)
+	stw     a2, (sp, 32)
+	stw     a3, (sp, 36)
+
+	addi	sp, 32
+	addi	sp, 8
+	mfcr    r13, ss2
+	stw	r6, (sp)
+	stw	r7, (sp, 4)
+	stw	r8, (sp, 8)
+	stw	r9, (sp, 12)
+	stw	r10, (sp, 16)
+	stw	r11, (sp, 20)
+	stw	r12, (sp, 24)
+	stw	r13, (sp, 28)
+	stw	r14, (sp, 32)
+	stw	r1, (sp, 36)
+	subi	sp, 32
+	subi	sp, 8
+.endm
+
+.macro	RESTORE_ALL
+	ldw	lr, (sp, 4)
+	ldw     a0, (sp, 8)
+	mtcr    a0, epc
+	ldw     a0, (sp, 12)
+	mtcr    a0, epsr
+	btsti   a0, 31
+	bt      1f
+	ldw     a0, (sp, 16)
+	mtcr	a0, ss1
+1:
+	ldw     a0, (sp, 24)
+	ldw     a1, (sp, 28)
+	ldw     a2, (sp, 32)
+	ldw     a3, (sp, 36)
+
+	addi	sp, 32
+	addi	sp, 8
+	ldw	r6, (sp)
+	ldw	r7, (sp, 4)
+	ldw	r8, (sp, 8)
+	ldw	r9, (sp, 12)
+	ldw	r10, (sp, 16)
+	ldw	r11, (sp, 20)
+	ldw	r12, (sp, 24)
+	ldw	r13, (sp, 28)
+	ldw	r14, (sp, 32)
+	ldw	r1, (sp, 36)
+	addi	sp, 32
+	addi	sp, 8
+
+	bt      2f
+	KSPTOUSP
+2:
+	rte
+.endm
+
+.macro SAVE_SWITCH_STACK
+	subi    sp, 32
+	stm     r8-r15, (sp)
+.endm
+
+.macro RESTORE_SWITCH_STACK
+	ldm     r8-r15, (sp)
+	addi    sp, 32
+.endm
+
+/* MMU registers operators. */
+.macro RD_MIR	rx
+	cprcr   \rx, cpcr0
+.endm
+
+.macro RD_MEH	rx
+	cprcr   \rx, cpcr4
+.endm
+
+.macro RD_MCIR	rx
+	cprcr   \rx, cpcr8
+.endm
+
+.macro RD_PGDR  rx
+	cprcr   \rx, cpcr29
+.endm
+
+.macro WR_MEH	rx
+	cpwcr   \rx, cpcr4
+.endm
+
+.macro WR_MCIR	rx
+	cpwcr   \rx, cpcr8
+.endm
+
+.macro SETUP_MMU
+	/* Init psr and enable ee */
+	lrw	r6, DEFAULT_PSR_VALUE
+	mtcr    r6, psr
+	psrset  ee
+
+	/* Select MMU as co-processor */
+	cpseti	cp15
+
+	/*
+	 * cpcr30 format:
+	 * 31 - 29 | 28 - 4 | 3 | 2 | 1 | 0
+	 *   BA     Reserved  C   D   V
+	 */
+	cprcr	r6, cpcr30
+	lsri	r6, 29
+	lsli	r6, 29
+	addi	r6, 0xe
+	cpwcr	r6, cpcr30
+
+	movi	r6, 0
+	cpwcr	r6, cpcr31
+.endm
+#endif /* __ASM_CSKY_ENTRY_H */
diff --git a/arch/csky/abiv1/inc/abi/page.h b/arch/csky/abiv1/inc/abi/page.h
new file mode 100644
index 000000000..58307254e
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/page.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <asm/shmparam.h>
+
+extern void flush_dcache_page(struct page *page);
+
+static inline unsigned long pages_do_alias(unsigned long addr1,
+					   unsigned long addr2)
+{
+	return (addr1 ^ addr2) & (SHMLBA-1);
+}
+
+#define clear_user_page clear_user_page
+static inline void clear_user_page(void *addr, unsigned long vaddr,
+				   struct page *page)
+{
+	clear_page(addr);
+	if (pages_do_alias((unsigned long) addr, vaddr & PAGE_MASK))
+		flush_dcache_page(page);
+}
+
+static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
+				  struct page *page)
+{
+	copy_page(to, from);
+	if (pages_do_alias((unsigned long) to, vaddr & PAGE_MASK))
+		flush_dcache_page(page);
+}
diff --git a/arch/csky/abiv1/inc/abi/pgtable-bits.h b/arch/csky/abiv1/inc/abi/pgtable-bits.h
new file mode 100644
index 000000000..ae7a2f76d
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/pgtable-bits.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_PGTABLE_BITS_H
+#define __ASM_CSKY_PGTABLE_BITS_H
+
+/* implemented in software */
+#define _PAGE_PRESENT		(1<<0)
+#define _PAGE_READ		(1<<1)
+#define _PAGE_WRITE		(1<<2)
+#define _PAGE_ACCESSED		(1<<3)
+#define _PAGE_MODIFIED		(1<<4)
+
+/* We borrow bit 9 to store the exclusive marker in swap PTEs. */
+#define _PAGE_SWP_EXCLUSIVE	(1<<9)
+
+/* implemented in hardware */
+#define _PAGE_GLOBAL		(1<<6)
+#define _PAGE_VALID		(1<<7)
+#define _PAGE_DIRTY		(1<<8)
+
+#define _PAGE_CACHE		(3<<9)
+#define _PAGE_UNCACHE		(2<<9)
+#define _PAGE_SO		_PAGE_UNCACHE
+#define _CACHE_MASK		(7<<9)
+
+#define _CACHE_CACHED		_PAGE_CACHE
+#define _CACHE_UNCACHED		_PAGE_UNCACHE
+
+#define _PAGE_PROT_NONE		_PAGE_READ
+
+/*
+ * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that
+ * are !pte_none() && !pte_present().
+ *
+ * Format of swap PTE:
+ *     bit          0:    _PAGE_PRESENT (zero)
+ *     bit          1:    _PAGE_READ (zero)
+ *     bit      2 - 5:    swap type[0 - 3]
+ *     bit          6:    _PAGE_GLOBAL (zero)
+ *     bit          7:    _PAGE_VALID (zero)
+ *     bit          8:    swap type[4]
+ *     bit          9:    exclusive marker
+ *     bit    10 - 31:    swap offset
+ */
+#define __swp_type(x)			((((x).val >> 2) & 0xf) | \
+					(((x).val >> 4) & 0x10))
+#define __swp_offset(x)			((x).val >> 10)
+#define __swp_entry(type, offset)	((swp_entry_t) { \
+					((type & 0xf) << 2) | \
+					((type & 0x10) << 4) | \
+					((offset) << 10)})
+
+#define HAVE_ARCH_UNMAPPED_AREA
+
+#endif /* __ASM_CSKY_PGTABLE_BITS_H */
diff --git a/arch/csky/abiv1/inc/abi/reg_ops.h b/arch/csky/abiv1/inc/abi/reg_ops.h
new file mode 100644
index 000000000..abd01a243
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/reg_ops.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_REG_OPS_H
+#define __ABI_REG_OPS_H
+#include <asm/reg_ops.h>
+
+#define cprcr(reg)					\
+({							\
+	unsigned int tmp;				\
+	asm volatile("cprcr %0, "reg"\n":"=b"(tmp));	\
+	tmp;						\
+})
+
+#define cpwcr(reg, val)					\
+({							\
+	asm volatile("cpwcr %0, "reg"\n"::"b"(val));	\
+})
+
+static inline unsigned int mfcr_hint(void)
+{
+	return mfcr("cr30");
+}
+
+static inline unsigned int mfcr_ccr2(void) { return 0; }
+
+#endif /* __ABI_REG_OPS_H */
diff --git a/arch/csky/abiv1/inc/abi/regdef.h b/arch/csky/abiv1/inc/abi/regdef.h
new file mode 100644
index 000000000..c75ecf2ca
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/regdef.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_REGDEF_H
+#define __ASM_CSKY_REGDEF_H
+
+#ifdef __ASSEMBLER__
+#define syscallid	r1
+#else
+#define syscallid	"r1"
+#endif
+
+#define regs_syscallid(regs) regs->regs[9]
+#define regs_fp(regs) regs->regs[2]
+
+/*
+ * PSR format:
+ * | 31 | 30-24 | 23-16 | 15 14 | 13-0 |
+ *   S     CPID     VEC     TM
+ *
+ *    S: Super Mode
+ * CPID: Coprocessor id, only 15 for MMU
+ *  VEC: Exception Number
+ *   TM: Trace Mode
+ */
+#define DEFAULT_PSR_VALUE	0x8f000000
+
+#define SYSTRACE_SAVENUM	2
+
+#define TRAP0_SIZE		2
+
+#endif /* __ASM_CSKY_REGDEF_H */
diff --git a/arch/csky/abiv1/inc/abi/string.h b/arch/csky/abiv1/inc/abi/string.h
new file mode 100644
index 000000000..de50117b9
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/string.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_CSKY_STRING_H
+#define __ABI_CSKY_STRING_H
+
+#define __HAVE_ARCH_MEMCPY
+extern void *memcpy(void *, const void *, __kernel_size_t);
+
+#define __HAVE_ARCH_MEMMOVE
+extern void *memmove(void *, const void *, __kernel_size_t);
+
+#define __HAVE_ARCH_MEMSET
+extern void *memset(void *, int,  __kernel_size_t);
+
+#endif /* __ABI_CSKY_STRING_H */
diff --git a/arch/csky/abiv1/inc/abi/switch_context.h b/arch/csky/abiv1/inc/abi/switch_context.h
new file mode 100644
index 000000000..ec73fd7c9
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/switch_context.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_CSKY_PTRACE_H
+#define __ABI_CSKY_PTRACE_H
+
+struct switch_stack {
+	unsigned long r8;
+	unsigned long r9;
+	unsigned long r10;
+	unsigned long r11;
+	unsigned long r12;
+	unsigned long r13;
+	unsigned long r14;
+	unsigned long r15;
+};
+#endif /* __ABI_CSKY_PTRACE_H */
diff --git a/arch/csky/abiv1/inc/abi/vdso.h b/arch/csky/abiv1/inc/abi/vdso.h
new file mode 100644
index 000000000..9e6d0a2fd
--- /dev/null
+++ b/arch/csky/abiv1/inc/abi/vdso.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ABI_CSKY_VDSO_H
+#define __ABI_CSKY_VDSO_H
+
+/* movi r1, 127; addi r1, (139 - 127) */
+#define SET_SYSCALL_ID	.long 0x20b167f1
+
+#endif /* __ABI_CSKY_VDSO_H */
diff --git a/arch/csky/abiv1/mmap.c b/arch/csky/abiv1/mmap.c
new file mode 100644
index 000000000..1047865e8
--- /dev/null
+++ b/arch/csky/abiv1/mmap.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/shm.h>
+#include <linux/sched.h>
+#include <linux/random.h>
+#include <linux/io.h>
+
+#define COLOUR_ALIGN(addr,pgoff)		\
+	((((addr)+SHMLBA-1)&~(SHMLBA-1)) +	\
+	 (((pgoff)<<PAGE_SHIFT) & (SHMLBA-1)))
+
+/*
+ * We need to ensure that shared mappings are correctly aligned to
+ * avoid aliasing issues with VIPT caches.  We need to ensure that
+ * a specific page of an object is always mapped at a multiple of
+ * SHMLBA bytes.
+ *
+ * We unconditionally provide this function for all cases.
+ */
+unsigned long
+arch_get_unmapped_area(struct file *filp, unsigned long addr,
+		unsigned long len, unsigned long pgoff,
+		unsigned long flags, vm_flags_t vm_flags)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	int do_align = 0;
+	struct vm_unmapped_area_info info = {
+		.length = len,
+		.low_limit = mm->mmap_base,
+		.high_limit = TASK_SIZE,
+		.align_offset = pgoff << PAGE_SHIFT
+	};
+
+	/*
+	 * We only need to do colour alignment if either the I or D
+	 * caches alias.
+	 */
+	do_align = filp || (flags & MAP_SHARED);
+
+	/*
+	 * We enforce the MAP_FIXED case.
+	 */
+	if (flags & MAP_FIXED) {
+		if (flags & MAP_SHARED &&
+		    (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
+			return -EINVAL;
+		return addr;
+	}
+
+	if (len > TASK_SIZE)
+		return -ENOMEM;
+
+	if (addr) {
+		if (do_align)
+			addr = COLOUR_ALIGN(addr, pgoff);
+		else
+			addr = PAGE_ALIGN(addr);
+
+		vma = find_vma(mm, addr);
+		if (TASK_SIZE - len >= addr &&
+		    (!vma || addr + len <= vm_start_gap(vma)))
+			return addr;
+	}
+
+	info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0;
+	return vm_unmapped_area(&info);
+}