Merge tag 'loongarch-6.9' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson

Pull LoongArch updates from Huacai Chen:

 - Add objtool support for LoongArch

 - Add ORC stack unwinder support for LoongArch

 - Add kernel livepatching support for LoongArch

 - Select ARCH_HAS_CURRENT_STACK_POINTER in Kconfig

 - Select HAVE_ARCH_USERFAULTFD_MINOR in Kconfig

 - Some bug fixes and other small changes

* tag 'loongarch-6.9' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson:
  LoongArch/crypto: Clean up useless assignment operations
  LoongArch: Define the __io_aw() hook as mmiowb()
  LoongArch: Remove superfluous flush_dcache_page() definition
  LoongArch: Move {dmw,tlb}_virt_to_page() definition to page.h
  LoongArch: Change __my_cpu_offset definition to avoid mis-optimization
  LoongArch: Select HAVE_ARCH_USERFAULTFD_MINOR in Kconfig
  LoongArch: Select ARCH_HAS_CURRENT_STACK_POINTER in Kconfig
  LoongArch: Add kernel livepatching support
  LoongArch: Add ORC stack unwinder support
  objtool: Check local label in read_unwind_hints()
  objtool: Check local label in add_dead_ends()
  objtool/LoongArch: Enable orc to be built
  objtool/x86: Separate arch-specific and generic parts
  objtool/LoongArch: Implement instruction decoder
  objtool/LoongArch: Enable objtool to be built

17 files changed, 182 insertions, 27 deletions

diff --git a/arch/loongarch/include/asm/Kbuild b/arch/loongarch/include/asm/Kbuild
index 93783fa24f6e..2dbec7853ae8 100644
--- a/arch/loongarch/include/asm/Kbuild
+++ b/arch/loongarch/include/asm/Kbuild
@@ -1,9 +1,12 @@
 # SPDX-License-Identifier: GPL-2.0
+generated-y += orc_hash.h
+
 generic-y += dma-contiguous.h
 generic-y += mcs_spinlock.h
 generic-y += parport.h
 generic-y += early_ioremap.h
 generic-y += qrwlock.h
+generic-y += qspinlock.h
 generic-y += rwsem.h
 generic-y += segment.h
 generic-y += user.h
diff --git a/arch/loongarch/include/asm/bug.h b/arch/loongarch/include/asm/bug.h
index d4ca3ba25418..08388876ade4 100644
--- a/arch/loongarch/include/asm/bug.h
+++ b/arch/loongarch/include/asm/bug.h
@@ -44,6 +44,7 @@
 do {								\
 	instrumentation_begin();				\
 	__BUG_FLAGS(BUGFLAG_WARNING|(flags));			\
+	annotate_reachable();					\
 	instrumentation_end();					\
 } while (0)
 
diff --git a/arch/loongarch/include/asm/cacheflush.h b/arch/loongarch/include/asm/cacheflush.h
index 80bd74106985..f8754d08a31a 100644
--- a/arch/loongarch/include/asm/cacheflush.h
+++ b/arch/loongarch/include/asm/cacheflush.h
@@ -37,8 +37,6 @@ void local_flush_icache_range(unsigned long start, unsigned long end);
 #define flush_icache_range	local_flush_icache_range
 #define flush_icache_user_range	local_flush_icache_range
 
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-
 #define flush_cache_all()				do { } while (0)
 #define flush_cache_mm(mm)				do { } while (0)
 #define flush_cache_dup_mm(mm)				do { } while (0)
@@ -47,7 +45,6 @@ void local_flush_icache_range(unsigned long start, unsigned long end);
 #define flush_cache_vmap(start, end)			do { } while (0)
 #define flush_cache_vunmap(start, end)			do { } while (0)
 #define flush_icache_user_page(vma, page, addr, len)	do { } while (0)
-#define flush_dcache_page(page)				do { } while (0)
 #define flush_dcache_mmap_lock(mapping)			do { } while (0)
 #define flush_dcache_mmap_unlock(mapping)		do { } while (0)
 
diff --git a/arch/loongarch/include/asm/exception.h b/arch/loongarch/include/asm/exception.h
index af74a3fdcad1..c6d20736fd92 100644
--- a/arch/loongarch/include/asm/exception.h
+++ b/arch/loongarch/include/asm/exception.h
@@ -6,6 +6,8 @@
 #include <asm/ptrace.h>
 #include <linux/kprobes.h>
 
+extern void *exception_table[];
+
 void show_registers(struct pt_regs *regs);
 
 asmlinkage void cache_parity_error(void);
diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h
index c486c2341b66..4a8adcca329b 100644
--- a/arch/loongarch/include/asm/io.h
+++ b/arch/loongarch/include/asm/io.h
@@ -71,6 +71,8 @@ extern void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t
 #define memcpy_fromio(a, c, l) __memcpy_fromio((a), (c), (l))
 #define memcpy_toio(c, a, l)   __memcpy_toio((c), (a), (l))
 
+#define __io_aw() mmiowb()
+
 #include <asm-generic/io.h>
 
 #define ARCH_HAS_VALID_PHYS_ADDR_RANGE
diff --git a/arch/loongarch/include/asm/module.h b/arch/loongarch/include/asm/module.h
index 2ecd82bb64e1..f33f3fd32ecc 100644
--- a/arch/loongarch/include/asm/module.h
+++ b/arch/loongarch/include/asm/module.h
@@ -6,6 +6,7 @@
 #define _ASM_MODULE_H
 
 #include <asm/inst.h>
+#include <asm/orc_types.h>
 #include <asm-generic/module.h>
 
 #define RELA_STACK_DEPTH 16
@@ -21,6 +22,12 @@ struct mod_arch_specific {
 	struct mod_section plt;
 	struct mod_section plt_idx;
 
+#ifdef CONFIG_UNWINDER_ORC
+	unsigned int num_orcs;
+	int *orc_unwind_ip;
+	struct orc_entry *orc_unwind;
+#endif
+
 	/* For CONFIG_DYNAMIC_FTRACE */
 	struct plt_entry *ftrace_trampolines;
 };
diff --git a/arch/loongarch/include/asm/orc_header.h b/arch/loongarch/include/asm/orc_header.h
new file mode 100644
index 000000000000..f9d509c3fd70
--- /dev/null
+++ b/arch/loongarch/include/asm/orc_header.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _ORC_HEADER_H
+#define _ORC_HEADER_H
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <asm/orc_hash.h>
+
+/*
+ * The header is currently a 20-byte hash of the ORC entry definition; see
+ * scripts/orc_hash.sh.
+ */
+#define ORC_HEADER					\
+	__used __section(".orc_header") __aligned(4)	\
+	static const u8 orc_header[] = { ORC_HASH }
+
+#endif /* _ORC_HEADER_H */
diff --git a/arch/loongarch/include/asm/orc_lookup.h b/arch/loongarch/include/asm/orc_lookup.h
new file mode 100644
index 000000000000..b02e6357def4
--- /dev/null
+++ b/arch/loongarch/include/asm/orc_lookup.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ORC_LOOKUP_H
+#define _ORC_LOOKUP_H
+
+/*
+ * This is a lookup table for speeding up access to the .orc_unwind table.
+ * Given an input address offset, the corresponding lookup table entry
+ * specifies a subset of the .orc_unwind table to search.
+ *
+ * Each block represents the end of the previous range and the start of the
+ * next range.  An extra block is added to give the last range an end.
+ *
+ * The block size should be a power of 2 to avoid a costly 'div' instruction.
+ *
+ * A block size of 256 was chosen because it roughly doubles unwinder
+ * performance while only adding ~5% to the ORC data footprint.
+ */
+#define LOOKUP_BLOCK_ORDER	8
+#define LOOKUP_BLOCK_SIZE	(1 << LOOKUP_BLOCK_ORDER)
+
+#ifndef LINKER_SCRIPT
+
+extern unsigned int orc_lookup[];
+extern unsigned int orc_lookup_end[];
+
+#define LOOKUP_START_IP		(unsigned long)_stext
+#define LOOKUP_STOP_IP		(unsigned long)_etext
+
+#endif /* LINKER_SCRIPT */
+
+#endif /* _ORC_LOOKUP_H */
diff --git a/arch/loongarch/include/asm/orc_types.h b/arch/loongarch/include/asm/orc_types.h
new file mode 100644
index 000000000000..caf1f71a1057
--- /dev/null
+++ b/arch/loongarch/include/asm/orc_types.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ORC_TYPES_H
+#define _ORC_TYPES_H
+
+#include <linux/types.h>
+
+/*
+ * The ORC_REG_* registers are base registers which are used to find other
+ * registers on the stack.
+ *
+ * ORC_REG_PREV_SP, also known as DWARF Call Frame Address (CFA), is the
+ * address of the previous frame: the caller's SP before it called the current
+ * function.
+ *
+ * ORC_REG_UNDEFINED means the corresponding register's value didn't change in
+ * the current frame.
+ *
+ * The most commonly used base registers are SP and FP -- which the previous SP
+ * is usually based on -- and PREV_SP and UNDEFINED -- which the previous FP is
+ * usually based on.
+ *
+ * The rest of the base registers are needed for special cases like entry code
+ * and GCC realigned stacks.
+ */
+#define ORC_REG_UNDEFINED		0
+#define ORC_REG_PREV_SP			1
+#define ORC_REG_SP			2
+#define ORC_REG_FP			3
+#define ORC_REG_MAX			4
+
+#define ORC_TYPE_UNDEFINED		0
+#define ORC_TYPE_END_OF_STACK		1
+#define ORC_TYPE_CALL			2
+#define ORC_TYPE_REGS			3
+#define ORC_TYPE_REGS_PARTIAL		4
+
+#ifndef __ASSEMBLY__
+/*
+ * This struct is more or less a vastly simplified version of the DWARF Call
+ * Frame Information standard.  It contains only the necessary parts of DWARF
+ * CFI, simplified for ease of access by the in-kernel unwinder.  It tells the
+ * unwinder how to find the previous SP and FP (and sometimes entry regs) on
+ * the stack for a given code address.  Each instance of the struct corresponds
+ * to one or more code locations.
+ */
+struct orc_entry {
+	s16		sp_offset;
+	s16		fp_offset;
+	s16		ra_offset;
+	unsigned int	sp_reg:4;
+	unsigned int	fp_reg:4;
+	unsigned int	ra_reg:4;
+	unsigned int	type:3;
+	unsigned int	signal:1;
+};
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ORC_TYPES_H */
diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h
index afb6fa16b826..44027060c54a 100644
--- a/arch/loongarch/include/asm/page.h
+++ b/arch/loongarch/include/asm/page.h
@@ -75,6 +75,9 @@ typedef struct { unsigned long pgprot; } pgprot_t;
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
 #define sym_to_pfn(x)		__phys_to_pfn(__pa_symbol(x))
 
+struct page *dmw_virt_to_page(unsigned long kaddr);
+struct page *tlb_virt_to_page(unsigned long kaddr);
+
 #define virt_to_pfn(kaddr)	PFN_DOWN(PHYSADDR(kaddr))
 
 #define virt_to_page(kaddr)								\
diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h
index 9b36ac003f89..8f290e5546cf 100644
--- a/arch/loongarch/include/asm/percpu.h
+++ b/arch/loongarch/include/asm/percpu.h
@@ -29,7 +29,12 @@ static inline void set_my_cpu_offset(unsigned long off)
 	__my_cpu_offset = off;
 	csr_write64(off, PERCPU_BASE_KS);
 }
-#define __my_cpu_offset __my_cpu_offset
+
+#define __my_cpu_offset					\
+({							\
+	__asm__ __volatile__("":"+r"(__my_cpu_offset));	\
+	__my_cpu_offset;				\
+})
 
 #define PERCPU_OP(op, asm_op, c_op)					\
 static __always_inline unsigned long __percpu_##op(void *ptr,		\
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index 8b5df1bbf9e9..af3acdf3481a 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -363,9 +363,6 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt
 extern pgd_t swapper_pg_dir[];
 extern pgd_t invalid_pg_dir[];
 
-struct page *dmw_virt_to_page(unsigned long kaddr);
-struct page *tlb_virt_to_page(unsigned long kaddr);
-
 /*
  * The following only work if pte_present() is true.
  * Undefined behaviour if not..
diff --git a/arch/loongarch/include/asm/qspinlock.h b/arch/loongarch/include/asm/qspinlock.h
deleted file mode 100644
index 34f43f8ad591..000000000000
--- a/arch/loongarch/include/asm/qspinlock.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_QSPINLOCK_H
-#define _ASM_QSPINLOCK_H
-
-#include <asm-generic/qspinlock_types.h>
-
-#define queued_spin_unlock queued_spin_unlock
-
-static inline void queued_spin_unlock(struct qspinlock *lock)
-{
-	compiletime_assert_atomic_type(lock->locked);
-	c_sync();
-	WRITE_ONCE(lock->locked, 0);
-}
-
-#include <asm-generic/qspinlock.h>
-
-#endif /* _ASM_QSPINLOCK_H */
diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h
index 4fb1e6408b98..45b507a7b06f 100644
--- a/arch/loongarch/include/asm/stackframe.h
+++ b/arch/loongarch/include/asm/stackframe.h
@@ -13,6 +13,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/loongarch.h>
 #include <asm/thread_info.h>
+#include <asm/unwind_hints.h>
 
 /* Make the addition of cfi info a little easier. */
 	.macro cfi_rel_offset reg offset=0 docfi=0
@@ -162,6 +163,7 @@
 	li.w	t0, CSR_CRMD_WE
 	csrxchg	t0, t0, LOONGARCH_CSR_CRMD
 #endif
+	UNWIND_HINT_REGS
 	.endm
 
 	.macro	SAVE_ALL docfi=0
@@ -219,6 +221,7 @@
 
 	.macro	RESTORE_SP_AND_RET docfi=0
 	cfi_ld	sp, PT_R3, \docfi
+	UNWIND_HINT_FUNC
 	ertn
 	.endm
 
diff --git a/arch/loongarch/include/asm/thread_info.h b/arch/loongarch/include/asm/thread_info.h
index 8cb653d49a54..8bf0e6f51546 100644
--- a/arch/loongarch/include/asm/thread_info.h
+++ b/arch/loongarch/include/asm/thread_info.h
@@ -86,6 +86,7 @@ register unsigned long current_stack_pointer __asm__("$sp");
 #define TIF_LASX_CTX_LIVE	18	/* LASX context must be preserved */
 #define TIF_USEDLBT		19	/* LBT was used by this task this quantum (SMP) */
 #define TIF_LBT_CTX_LIVE	20	/* LBT context must be preserved */
+#define TIF_PATCH_PENDING	21	/* pending live patching update */
 
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
@@ -105,6 +106,7 @@ register unsigned long current_stack_pointer __asm__("$sp");
 #define _TIF_LASX_CTX_LIVE	(1<<TIF_LASX_CTX_LIVE)
 #define _TIF_USEDLBT		(1<<TIF_USEDLBT)
 #define _TIF_LBT_CTX_LIVE	(1<<TIF_LBT_CTX_LIVE)
+#define _TIF_PATCH_PENDING	(1<<TIF_PATCH_PENDING)
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/loongarch/include/asm/unwind.h b/arch/loongarch/include/asm/unwind.h
index b9dce87afd2e..40a6763c5aec 100644
--- a/arch/loongarch/include/asm/unwind.h
+++ b/arch/loongarch/include/asm/unwind.h
@@ -16,6 +16,7 @@
 enum unwinder_type {
 	UNWINDER_GUESS,
 	UNWINDER_PROLOGUE,
+	UNWINDER_ORC,
 };
 
 struct unwind_state {
@@ -24,7 +25,7 @@ struct unwind_state {
 	struct task_struct *task;
 	bool first, error, reset;
 	int graph_idx;
-	unsigned long sp, pc, ra;
+	unsigned long sp, fp, pc, ra;
 };
 
 bool default_next_frame(struct unwind_state *state);
@@ -61,14 +62,17 @@ static __always_inline void __unwind_start(struct unwind_state *state,
 		state->sp = regs->regs[3];
 		state->pc = regs->csr_era;
 		state->ra = regs->regs[1];
+		state->fp = regs->regs[22];
 	} else if (task && task != current) {
 		state->sp = thread_saved_fp(task);
 		state->pc = thread_saved_ra(task);
 		state->ra = 0;
+		state->fp = 0;
 	} else {
 		state->sp = (unsigned long)__builtin_frame_address(0);
 		state->pc = (unsigned long)__builtin_return_address(0);
 		state->ra = 0;
+		state->fp = 0;
 	}
 	state->task = task;
 	get_stack_info(state->sp, state->task, &state->stack_info);
@@ -77,6 +81,18 @@ static __always_inline void __unwind_start(struct unwind_state *state,
 
 static __always_inline unsigned long __unwind_get_return_address(struct unwind_state *state)
 {
-	return unwind_done(state) ? 0 : state->pc;
+	if (unwind_done(state))
+		return 0;
+
+	return __kernel_text_address(state->pc) ? state->pc : 0;
 }
+
+#ifdef CONFIG_UNWINDER_ORC
+void unwind_init(void);
+void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size);
+#else
+static inline void unwind_init(void) {}
+static inline void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size) {}
+#endif
+
 #endif /* _ASM_UNWIND_H */
diff --git a/arch/loongarch/include/asm/unwind_hints.h b/arch/loongarch/include/asm/unwind_hints.h
new file mode 100644
index 000000000000..a01086ad9dde
--- /dev/null
+++ b/arch/loongarch/include/asm/unwind_hints.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_LOONGARCH_UNWIND_HINTS_H
+#define _ASM_LOONGARCH_UNWIND_HINTS_H
+
+#include <linux/objtool.h>
+#include <asm/orc_types.h>
+
+#ifdef __ASSEMBLY__
+
+.macro UNWIND_HINT_UNDEFINED
+	UNWIND_HINT type=UNWIND_HINT_TYPE_UNDEFINED
+.endm
+
+.macro UNWIND_HINT_END_OF_STACK
+	UNWIND_HINT type=UNWIND_HINT_TYPE_END_OF_STACK
+.endm
+
+.macro UNWIND_HINT_REGS
+	UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_REGS
+.endm
+
+.macro UNWIND_HINT_FUNC
+	UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_CALL
+.endm
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_LOONGARCH_UNWIND_HINTS_H */